Щоб переглянути інші типи публікацій з цієї теми, перейдіть за посиланням: User-Centric AI.
Статті в журналах з теми "User-Centric AI"
Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями
Ознайомтеся з топ-50 статей у журналах для дослідження на тему "User-Centric AI".
Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.
Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.
Переглядайте статті в журналах для різних дисциплін та оформлюйте правильно вашу бібліографію.
1
Pazzani, Michael, Severine Soltani, Robert Kaufman, Samson Qian, and Albert Hsiao. "Expert-Informed, User-Centric Explanations for Machine Learning." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 11 (June 28, 2022): 12280–86. http://dx.doi.org/10.1609/aaai.v36i11.21491.
Повний текст джерелаАнотація:
We argue that the dominant approach to explainable AI for explaining image classification, annotating images with heatmaps, provides little value for users unfamiliar with deep learning. We argue that explainable AI for images should produce output like experts produce when communicating with one another, with apprentices, and with novices. We provide an expanded set of goals of explainable AI systems and propose a Turing Test for explainable AI.
2
Saber Ismail, Dr Walaa. "Human-Centric AI : Enhancing User Experience through Natural Language Interfaces." Journal of Wireless Mobile Networks, Ubiquitous Computing, and Dependable Applications 15, no. 1 (March 29, 2024): 172–83. http://dx.doi.org/10.58346/jowua.2024.i1.012.
Повний текст джерелаАнотація:
AI has significantly altered the way humans interact with technology. It is important to observe the impact of Natural Language Interfaces (NLIs) on user experiences in Human-Centric AI across various industries. Therefore, we specifically focus on the influence of Human-Centric AI and user interactions within AI chatbots in the United Arab Emirates (UAE). The aim of this study is to assess the factors that influence the acceptance of AI, examine its practical implications across different industries, and offer valuable insights for the responsible development of AI. A quantitative survey methodology was employed, involving 230 participants in the UAE. The research design, data collection, and analysis followed the Unified Theory of Acceptance and Use of Technology (UTAUT) model, which emphasizes performance expectancy, effort expectancy, social influence, and facilitating conditions. The survey encompassed a variety of participants from various organizations, with a majority expressing positive attitudes towards AI chatbots. The survey found that 80% of users agreed that AI systems improve task efficiency, 84% believe they help achieve goals, and 84% view them as practical. According to 75% of participants, the social impact is strongly influenced by AI chatbot system adoption. However, 80% understood the relevance of organizational infrastructure and favorable conditions. In particular, 72% of users stated that Natural Language Interfaces transform, indicating satisfactory user experiences. These features demonstrate the influence of Human-Centric AI adoption and its use in different organizations. Natural language interfaces play a critical role in improving human-centered AI user experiences, investigating theoretical issues and real-world applications, and providing guidance for the ethical use of AI.
3
Ugochukwu Okwudili Matthew, Kafayat Motomori Bakare, Godwin Nse Ebong, Charles Chukwuebuka Ndukwu, and Andrew Chinonso Nwanakwaugwu. "Generative Artificial Intelligence (AI) Educational Pedagogy Development: Conversational AI with User-Centric ChatGPT4." December 2023 5, no. 4 (December 2023): 401–18. http://dx.doi.org/10.36548/jtcsst.2023.4.003.
Повний текст джерелаАнотація:
In terms of language models, generative artificial intelligence (GenAI), and more specifically ChatGPT, offer a significant technological achievement as a revolutionary tool for natural language processing (NLP) and a transformative educational business tool. ChatGPT users' suggestions have the ability to optimize teaching and learning, thereby having a substantial impact on the educational environment of the twenty-first century. Educational robots are getting easier to access for a number of reasons. The human-robot cooperation that has advanced scientifically in industry 5.0 extreme digital automation, will also probably become a regular aspect of life in the days to come. This study examines the prospective uses of GenAI for NLP synthesis as well as its potential role as a conversational agent in the classroom business. GenAI's capacity to understand and produce language that is human-like by employing NLP to generate semantics was essential to its ability to replicate the most advanced human technology through comprehensive assumptions of patterns and structures it learns from its training data. With the rise of artificial intelligence (AI) driven conversational agents, prompt engineering has become an important aspect of digital learning. It is essential to get ready for an AI-dominated future when general and educational technologies combine. The study demonstrated how society may impact and contribute to the development of AI pedagogic learning using an instructional robotics application driven by AI, emphasizing the responsibility of humans as producers to reduce any potential misfortunes. The study highlights that since generative AI technologies have the potential to drastically change teaching and learning approaches and necessitate new ways of thinking, more research on organizational robotics, with a focus on human collaboration and education, will emerge from the technological concerns raised in this study.
4
Zhang, Pengyi, Kathleen Gregory, Ayoung Yoon, and Carole Palmer. "Conceptualizing Data Behavior: Bridging Data‐centric and User‐centric Approaches." Proceedings of the Association for Information Science and Technology 60, no. 1 (October 2023): 856–60. http://dx.doi.org/10.1002/pra2.878.
Повний текст джерелаАнотація:
ABSTRACTWith the development of technologies in big data and AI, data has become more and more central to users for various tasks in different contexts. Yet the concept of data behavior, an emerging concept that captures the actions and interactions of individuals with data in various contexts and situations is not explicitly defined and framed. Data behavior focuses on the observable actions and reactions of users when they encounter, discover, seek, use, or create data for individual or collaborative tasks, while data practice encompasses the entire spectrum of how people work with data, from creating and managing to sharing and reusing data, as well as the intentional and strategic decisions and actions involved in these processes. This panel proposes a conversation and discussion about the concepts of data practice and data behavior by drawing on literature in data practice, data curation, and information behavior. This panel aims to discuss, compare, and bridge data‐centric and user‐centric approaches to conceptualizing data behavior. It will also present some examples of data behavior research in different domains and scenarios. The panel will highlight the challenges and opportunities of data behavior research for information science and practice.
5
Hassan, Ali, Riza Sulaiman, Mansoor Abdullateef Abdulgabber, and Hasan Kahtan. "TOWARDS USER-CENTRIC EXPLANATIONS FOR EXPLAINABLE MODELS: A REVIEW." Journal of Information System and Technology Management 6, no. 22 (September 1, 2021): 36–50. http://dx.doi.org/10.35631/jistm.622004.
Повний текст джерелаАнотація:
Recent advances in artificial intelligence, particularly in the field of machine learning (ML), have shown that these models can be incredibly successful, producing encouraging results and leading to diverse applications. Despite the promise of artificial intelligence, without transparency of machine learning models, it is difficult for stakeholders to trust the results of such models, which can hinder successful adoption. This concern has sparked scientific interest and led to the development of transparency-supporting algorithms. Although studies have raised awareness of the need for explainable AI, the question of how to meet real users' needs for understanding AI remains unresolved. This study provides a review of the literature on human-centric Machine Learning and new approaches to user-centric explanations for deep learning models. We highlight the challenges and opportunities facing this area of research. The goal is for this review to serve as a resource for both researchers and practitioners. The study found that one of the most difficult aspects of implementing machine learning models is gaining the trust of end-users.
6
Bernardo, Ezekiel, and Rosemary Seva. "Affective Design Analysis of Explainable Artificial Intelligence (XAI): A User-Centric Perspective." Informatics 10, no. 1 (March 16, 2023): 32. http://dx.doi.org/10.3390/informatics10010032.
Повний текст джерелаАнотація:
Explainable Artificial Intelligence (XAI) has successfully solved the black box paradox of Artificial Intelligence (AI). By providing human-level insights on AI, it allowed users to understand its inner workings even with limited knowledge of the machine learning algorithms it uses. As a result, the field grew, and development flourished. However, concerns have been expressed that the techniques are limited in terms of to whom they are applicable and how their effect can be leveraged. Currently, most XAI techniques have been designed by developers. Though needed and valuable, XAI is more critical for an end-user, considering transparency cleaves on trust and adoption. This study aims to understand and conceptualize an end-user-centric XAI to fill in the lack of end-user understanding. Considering recent findings of related studies, this study focuses on design conceptualization and affective analysis. Data from 202 participants were collected from an online survey to identify the vital XAI design components and testbed experimentation to explore the affective and trust change per design configuration. The results show that affective is a viable trust calibration route for XAI. In terms of design, explanation form, communication style, and presence of supplementary information are the components users look for in an effective XAI. Lastly, anxiety about AI, incidental emotion, perceived AI reliability, and experience using the system are significant moderators of the trust calibration process for an end-user.
7
Mardania, Agnes Dini. "The Rise of AI in Business: Uncharted Avenues for Digital Transformation." Equator Journal of Management and Entrepreneurship (EJME) 12, no. 1 (January 29, 2024): 25. http://dx.doi.org/10.26418/ejme.v12i1.75794.
Повний текст джерелаАнотація:
This study investigates the transformative impact of Artificial Intelligence (AI) on PT. Perhutani Anugerah Kimia, with a focus on user experience, AI investments, digital transformation, and their collective influence on increased business efficiency. Through path analysis, the study reveals statistically significant direct effects, highlighting the pivotal role of user experience and strategic AI investments in propelling digital transformation and, consequently, improving business efficiency. The indirect effects analysis underscores the mediating role of digital transformation, elucidating how enhancements in user experience and AI investments positively cascade to boost business efficiency. These findings advocate for a strategic emphasis on user-centric approaches and substantial AI investments, positioning organizations to navigate the evolving business landscape by fostering digital transformation and realizing tangible operational efficiency gains. This research contributes valuable insights to organizations seeking to harness the full potential of AI for holistic and impactful digital evolution.
8
Wang, Yu. "Impact of Social Emotional Intelligence on Students' Interpersonal Relationships and Academic Development." Journal of Education and Educational Research 5, no. 2 (September 1, 2023): 122–26. http://dx.doi.org/10.54097/jeer.v5i2.12552.
Повний текст джерелаАнотація:
The paper explores the intersection of Artificial Intelligence (AI) and mobile homestay design, elucidating AI’s multifaceted role in optimizing space, fostering sustainability, and enhancing user experience within this specific context. Through a comprehensive literature review, theoretical framework development, and detailed case studies, the paper unveils the significant potential and challenges of implementing AI in mobile homestay design. The case studies spotlight AI’s ability to dynamically optimize small spaces, promote sustainable practices, and tailor user experiences, providing invaluable insights for designers and researchers alike. However, alongside its potential, the ethical considerations, including privacy, security, and bias, are scrutinized, emphasizing the necessity for responsible and ethical AI deployment. Furthermore, the review of various AI tools and techniques provides practical insights for practitioners in the field. The paper concludes by highlighting areas for future research, particularly in developing ethical frameworks and exploring diverse AI applications in various mobile homestay contexts, to further understand and leverage the potent synergy between AI and design in crafting innovative, sustainable, and user-centric spaces.
9
Pawar, Dr Suvarna. "Advancing Interview Preparation: An AI-driven Approach." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, no. 02 (February 16, 2024): 1–13. http://dx.doi.org/10.55041/ijsrem28705.
Повний текст джерелаАнотація:
This research paper presents a transformative approach to interview preparation through the integration of cutting-edge artificial intelligence and personalized learning techniques. In today's competitive job market, traditional methods of interview readiness often lack the immediacy and tailored support needed for success. Addressing this gap, our platform utilizes advanced AI algorithms to analyze user responses, offer real-time feedback, and dynamically adjust question difficulty based on performance. By prioritizing user-centric design and ethical considerations, our research explores the development, implementation, and evaluation of this innovative solution. Insights from user feedback and performance metrics underscore the platform's effectiveness in enhancing interview skills and fostering confidence among job seekers. This paper contributes to the broader discourse on AI-driven learning technologies and their potential to empower individuals in navigating the complexities of professional advancement. Key Words: Interview Preparation, Artificial Intelligence, Natural Language Processing, Personalized Learning, Skill Development.
10
Tan, Seng-Keong, Siew-Chin Chong, Kuok-Kwee Wee, and Lee-Ying Chong. "Personalized Healthcare: A Comprehensive Approach for Symptom Diagnosis and Hospital Recommendations Using AI and Location Services." Journal of Informatics and Web Engineering 3, no. 1 (February 14, 2024): 117–35. http://dx.doi.org/10.33093/jiwe.2024.3.1.8.
Повний текст джерелаАнотація:
Utilizing digital advancements, an integrated Flask-based platform has been engineered to centralize personal health records and facilitate informed healthcare decisions. The platform utilizes a Random Forest model-based symptom checker and an OpenAI API-powered chatbot for preliminary disease diagnosis and integrates Google Maps API to recommend proximal hospitals based on user location. Additionally, it contains a comprehensive user profile encompassing general information, medical history, and allergies. The system includes a medicine reminder feature for medication adherence. This innovative amalgamation of technology and healthcare fosters a user-centric approach to personal health management.
11
Ran, Chenzimo. "Exploring the Opportunities and Challenges of Developing Large AI Models and their Commercialization." Advances in Engineering Technology Research 6, no. 1 (August 1, 2023): 611. http://dx.doi.org/10.56028/aetr.6.1.611.2023.
Повний текст джерелаАнотація:
This article explores the evolution and impact of large models in artificial intelligence (AI), with a focus on their role in advancing fields like natural language processing and image recognition. It categorizes this evolution into three stages: deep learning revival, big data and distributed computing, and self-supervised learning. The capabilities of large-scale models, especially in generating AI content, are discussed, along with the role of small models in personalized enterprise requirements and resource-limited environments. Discusses the development of large AI models and the opportunities they bring, as well as the importance of considering user needs when transitioning from a model to a product. The commercialization of AI products is also explored, with attention paid to the details of this process. The future of AI is predicted to be a dynamic balance between large and small models, depending on task requirements and resource limitations. The article concludes with a discussion on the commercialization of AI products, emphasizing the importance of data, algorithms, user-centric design, and viable business models.
12
Rjsé, Vássil, Titta Jylkäs, and Satu Miettinen. "AI Enabled Airline Cabin Services: AI Augmented Services for Emotional Values. Service Design for High‐Touch Solutions and Service Quality." Design Management Journal 18, no. 1 (October 2023): 100–115. http://dx.doi.org/10.1111/dmj.12090.
Повний текст джерелаАнотація:
AbstractThis paper highlights the significance of emotional values within digital services during the airline cabin experience. Currently, emotional engagement with front‐line AI interactions, such as AI assistants, lacks trust. Thus, the role of AI must be reimagined to better integrate the human factor into the service experience through things like high‐touch in order to create trust and improve the perception of cabin service quality. Service design is a human‐centric approach to service creation in which the user is typically made the main subject of the service research; the service process (service interaction) then co‐creates values alongside the service provider. The major concept discussed here is AI Augmented Services (AIAS), which turn high‐tech capabilities into high‐touch “human centric” services that can offer access, control, and well‐being to the user, all of which are key components in the establishment of trust. Airline future services can then implement this study for the purpose of detecting human emotions, co‐creating emotional values, and promoting emotional intelligence through the AIAS interactive communication channels, thereby transforming high‐tech capabilities into high‐touch opportunities. The methodological approach began by determining a benchmark for the state‐of‐the‐art AI technology in transport and conducting a set of expert interviews. Notably, the possible materialisation and challenges of AIAS high‐touch cabin services are also discussed here. This article can be considered to be a first step toward a service design in which opportunities are discussed with the goal of “discovering” possible AI solutions. Consecutive stages will be presented in future articles in which the concepts introduced here will be further defined and developed.
13
Olabanji, Samuel Oladiipo, Oluwaseun Oladeji Olaniyi, Chinasa Susan Adigwe, Olalekan Jamiu Okunleye, and Tunbosun Oyewale Oladoyinbo. "AI for Identity and Access Management (IAM) in the Cloud: Exploring the Potential of Artificial Intelligence to Improve User Authentication, Authorization, and Access Control within Cloud-Based Systems." Asian Journal of Research in Computer Science 17, no. 3 (January 25, 2024): 38–56. http://dx.doi.org/10.9734/ajrcos/2024/v17i3423.
Повний текст джерелаАнотація:
This comprehensive study explores the integration and effectiveness of Artificial Intelligence (AI) in Identity and Access Management (IAM) within cloud environments. It primarily focuses on how AI can enhance user authentication, authorization, and access control, addressing the challenges and possibilities in cloud computing. The study adopts a mixed-methods approach, employing both quantitative and qualitative analyses. A survey involving 582 cybersecurity experts provides insights into the current state and potential of AI in IAM, while multiple regression analysis examines the impact of various factors on system effectiveness. Four hypotheses are explored: the impact of hardware and software configurations on system accuracy (H1), the influence of computational environments on reliability (H2), the role of demographic factors in user acceptance (H3), and the effect of technological enhancements on system performance and acceptance (H4). Findings indicate significant correlations between these factors and the effectiveness of AI in IAM. Notably, hardware configurations and security concerns influence system accuracy; computational environment variations affect system reliability; demographic factors impact user acceptance; and enhancements such as user feedback, advancements in AI technology, continuous learning algorithms, and system transparency improve performance and acceptance. These insights underscore the need for advanced hardware, standardized software, user-centric design, and continuous improvement in AI technologies for effective IAM in cloud environments. The study provides actionable recommendations for cloud service providers and developers, emphasizing the importance of involving users in development processes, ensuring transparency, and adopting adaptive algorithms. Future research directions include longitudinal studies on the impact of technological advancements and exploring demographic-specific responses to AI-integrated IAM solutions.
14
How, Meng-Leong, Sin-Mei Cheah, Yong-Jiet Chan, Aik Cheow Khor, and Eunice Mei Ping Say. "Artificial Intelligence-Enhanced Decision Support for Informing Global Sustainable Development: A Human-Centric AI-Thinking Approach." Information 11, no. 1 (January 11, 2020): 39. http://dx.doi.org/10.3390/info11010039.
Повний текст джерелаАнотація:
Sustainable development is crucial to humanity. Utilization of primary socio-environmental data for analysis is essential for informing decision making by policy makers about sustainability in development. Artificial intelligence (AI)-based approaches are useful for analyzing data. However, it was not easy for people who are not trained in computer science to use AI. The significance and novelty of this paper is that it shows how the use of AI can be democratized via a user-friendly human-centric probabilistic reasoning approach. Using this approach, analysts who are not computer scientists can also use AI to analyze sustainability-related EPI data. Further, this human-centric probabilistic reasoning approach can also be used as cognitive scaffolding to educe AI-Thinking in the analysts to ask more questions and provide decision making support to inform policy making in sustainable development. This paper uses the 2018 Environmental Performance Index (EPI) data from 180 countries which includes performance indicators covering environmental health and ecosystem vitality. AI-based predictive modeling techniques are applied on 2018 EPI data to reveal the hidden tensions between the two fundamental dimensions of sustainable development: (1) environmental health; which improves with economic growth and increasing affluence; and (2) ecosystem vitality, which worsens due to industrialization and urbanization.
15
Kour, Ravdeep, Miguel Castaño, Ramin Karim, Amit Patwardhan, Manish Kumar, and Rikard Granström. "A Human-Centric Model for Sustainable Asset Management in Railway: A Case Study." Sustainability 14, no. 2 (January 14, 2022): 936. http://dx.doi.org/10.3390/su14020936.
Повний текст джерелаАнотація:
The ongoing digital transformation is changing asset management in the railway industry. Emerging digital technologies and Artificial Intelligence is expected to facilitate decision-making in management, operation, and maintenance of railway by providing an integrated data-driven and model-driven solution. An important aspect when developing decision-support solutions based on AI and digital technology is the users’ experience. User experience design process aims to create relevance, context-awareness, and meaningfulness for the end-user. In railway contexts, it is believed that applying a human-centric design model in the development of AI-based artefacts, will enhance the usability of the solution, which will have a positive impact on the decision-making processes. In this research, the applicability of such advanced technologies i.e., Virtual Reality, Mixed Reality, and AI have been reviewed for the railway asset management. To carry out this research work, literature review has been conducted related to available Virtual Reality/Augmented Reality/Mixed Reality technologies and their applications within railway industry. It has been found that these technologies are available, but not applied in railway asset management. Thus, the aim of this paper is to propose a human-centric design model for the enhancement of railway asset management using Artificial Intelligence, Virtual Reality, and Mixed Reality technologies. The practical implication of the findings from this work will benefit in increased efficiency and effectiveness of the operation and maintenance processes in railway.
16
Song, Feifei. "Incorporating Morris' Design Thoughts for AI and Big Data-Enabled Coverage Optimization in China's Wireless Communication Network." Journal of Information Systems Engineering and Management 9, no. 1 (January 25, 2024): 23622. http://dx.doi.org/10.55267/iadt.07.14076.
Повний текст джерелаАнотація:
Morris changes this study's China cellular network AI and Big Data Analytics. Scalability, regulatory compliance, and resource allocation efficiency are checked. Numerous methods seamlessly combine qualitative interview, document, and case study findings with quantitative network performance statistics. Qualitative study highlights industrial resource allocation, efficiency, and user-centric design issues. Innovative problem-solving emphasizes tech and regs. Researchers think Morris' designs improve China's wireless network. Explain and apply Morris' design concepts to problems. This comprehensive theoretical and practice study optimizes networks using Morris' design theories. Interdisciplinary research improves Morris' digital ideas. This research ingeniously integrates theory and practice to create network theory. Research employing mixed methods. Interviews, document analysis, and case studies increase efficiency, resource allocation, and user-centric design. Data quality and processing speed are investigated in quantitative network performance studies. Quantifying complex relationships with correlation and regression analysis strengthens the study's powerful method. Innovative regulatory compliance and scalability solutions demonstrate the study's cutting-edge approach. The paper then examines key findings and implications. Network optimization requires high-quality data, feature engineering, and user-centered design, according to research. Executives get proper network optimizing guidance. The essay emphasizes industry regulatory and technical improvements. Morris optimized networks theoretically. This integrated strategy boosts theory and digital relevance. Wireless network enhancements in China. Effectiveness, user experience, and data-driven accuracy help researchers optimize networks. This study addresses specific challenges and extends network theory to create future-ready networks utilizing Morris' design methods. Chinese wireless communication network optimization demonstrates this research's practical and theoretical benefits.
17
Lin, Zhiyu, Rohan Agarwal, and Mark Riedl. "Creative Wand: A System to Study Effects of Communications in Co-creative Settings." Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment 18, no. 1 (October 11, 2022): 45–52. http://dx.doi.org/10.1609/aiide.v18i1.21946.
Повний текст джерелаАнотація:
Recent neural generation systems have demonstrated the potential for procedurally generating game content, images, stories, and more. However, most neural generation algorithms are “uncontrolled” in the sense that the user has little say in creative decisions beyond the initial prompt specification. Co-creative, mixed-initiative systems require user-centric means of influencing the algorithm, especially when users are unlikely to have machine learning expertise. The key to co-creative systems is the ability to communicate ideas and intent from the user to the agent, as well as from the agent to the user. Key questions in co-creative AI include: How can users express their creative intentions? How can creative AI systems communicate their beliefs, explain their moves, or instruct users to act on their behalf? When should creative AI systems take initiative? The answer to such questions and more will enable us to develop better co-creative systems that make humans more capable of expressing their creative intents. We introduce CREATIVE-WAND, a customizable framework for investigating co-creative mixed-initiative generation. CREATIVE-WAND enables plug-and-play injection of generative models and human-agent communication channels into a chat-based interface. It provides a number of dimensions along which an AI generator and humans can communicate during the co-creative process. We illustrate the CREATIVE-WAND framework by using it to study one dimension of co-creative communication—global versus local creative intent specification by the user—in the context of storytelling.
18
Brunetti, Davide, Cristina Gena, and Fabiana Vernero. "Smart Interactive Technologies in the Human-Centric Factory 5.0: A Survey." Applied Sciences 12, no. 16 (August 9, 2022): 7965. http://dx.doi.org/10.3390/app12167965.
Повний текст джерелаАнотація:
In this survey paper, we focus on smart interactive technologies and providing a picture of the current state of the art, exploring the way new discoveries and recent technologies changed workers’ operations and activities on the factory floor. We focus in particular on the Industry 4.0 and 5.0 visions, wherein smart interactive technologies can bring benefits to the intelligent behavior machines can expose in a human-centric AI perspective. We consider smart technologies wherein the intelligence may be in and/or behind the user interfaces, and for both groups we try to highlight the importance of designing them with a human-centric approach, framed in the smart factory context. We review relevant work in the field with the aim of highlighting the pros and cons of each technology and its adoption in the industry. Furthermore, we try to collect guidelines for the human-centric integration of smart interactive technologies in the smart factory. In this wa y, we hope to provide the future designers and adopters of such technologies with concrete help in choosing among different options and implementing them in a user-centric manner. To this aim, surveyed works have been also classified based on the supported task(s) and production process phases/activities: access to knowledge, logistics, maintenance, planning, production, security, workers’ wellbeing, and warehousing.
19
Journal, ISJEM. "A Literature Survey on Personalized AI-Based Voice Assistant for Authentication." International Scientific Journal of Engineering and Management 02, no. 12 (December 1, 2023): 1–12. http://dx.doi.org/10.55041/isjem01329.
Повний текст джерелаАнотація:
This literature review critically examines the evolving landscape of personalized AI-based voice assistants in the realm of authentication services, The review begins with an exploration of the development and nuanced functionalities of voice recognition technologies, emphasizing their integration in multi-factor authentication systems. It delves into the synergistic relationship between voice and facial recognition technologies, highlighting advancements and challenges in biometric authentication, including accuracy, user experience, and security vulnerabilities.A significant focus is placed on the role of AI in personalizing user interactions with authentication services, where adaptive learning and contextual awareness are pivotal.The review also addresses the enduring relevance of traditional security measures, such as secure PIN’s, and their interplay with biometric methods to fortify authentication processes.The economic and commercial implications of these technologies are explored, considering their impact on business models and market trends.This comprehensive review identifies gaps in the current research landscape and suggests potential directions for future inquiry, particularly in enhancing security measures and improving user-centric designs. It aims to provide a holistic understanding of the current state and future potential of personalized AI-based voice assistants in authentication services, offering valuable insights for researchers and practitioners in the field. Key Words: Voice Recognition Technologies, Facial Recognition, Multimodal Authentication, Secure PINs, Biometric Authentication.
20
Elkhodr, Mahmoud, Samiya Khan, and Ergun Gide. "A Novel Semantic IoT Middleware for Secure Data Management: Blockchain and AI-Driven Context Awareness." Future Internet 16, no. 1 (January 7, 2024): 22. http://dx.doi.org/10.3390/fi16010022.
Повний текст джерелаАнотація:
In the modern digital landscape of the Internet of Things (IoT), data interoperability and heterogeneity present critical challenges, particularly with the increasing complexity of IoT systems and networks. Addressing these challenges, while ensuring data security and user trust, is pivotal. This paper proposes a novel Semantic IoT Middleware (SIM) for healthcare. The architecture of this middleware comprises the following main processes: data generation, semantic annotation, security encryption, and semantic operations. The data generation module facilitates seamless data and event sourcing, while the Semantic Annotation Component assigns structured vocabulary for uniformity. SIM adopts blockchain technology to provide enhanced data security, and its layered approach ensures robust interoperability and intuitive user-centric operations for IoT systems. The security encryption module offers data protection, and the semantic operations module underpins data processing and integration. A distinctive feature of this middleware is its proficiency in service integration, leveraging semantic descriptions augmented by user feedback. Additionally, SIM integrates artificial intelligence (AI) feedback mechanisms to continuously refine and optimise the middleware’s operational efficiency.
21
Damaševičius, Robertas, and Ligita Zailskaitė-Jakštė. "Usability and Security Testing of Online Links: A Framework for Click-Through Rate Prediction Using Deep Learning." Electronics 11, no. 3 (January 28, 2022): 400. http://dx.doi.org/10.3390/electronics11030400.
Повний текст джерелаАнотація:
The user, usage, and usability (3U’s) are three principal constituents for cyber security. The effective analysis of the 3U data using artificial intelligence (AI) techniques allows to deduce valuable observations, which allow domain experts to design practical strategies to alleviate cyberattacks and ensure decision support. Many internet applications, such as internet advertising and recommendation systems, rely on click-through rate (CTR) prediction to anticipate the possibility that a user would click on an ad or product, which is key for understanding human online behaviour. However, online systems are prone to click on fraud attacks. We propose a Human-Centric Cyber Security (HCCS) model that additionally includes AI techniques targeted at the key elements of user, usage, and usability. As a case study, we analyse a CTR prediction task, using deep learning methods (factorization machines) to predict online fraud through clickbait. The results of experiments on a real-world benchmark Avazu dataset show that the proposed approach outpaces (AUC is 0.8062) other CTR forecasting approaches, demonstrating the viability of the proposed framework.
22
Raimondo Cossu, Roberto Girau, and Luigi Atzori. "Lysis chatbot: A virtual assistant for IoT platforms." ITU Journal on Future and Evolving Technologies 2, no. 5 (August 2, 2021): 81–91. http://dx.doi.org/10.52953/mcyx4245.
Повний текст джерелаАнотація:
The configuration and management of devices and applications in Internet of Things (IoT) platforms may be very complicated for a user, which may limit the usage of relevant functionalities and which does not allow its full potential to be exploited. To address this issue, in this paper we present a new chatbot which is intended to assist the user in interacting with an IoT platform and allow them to use and exploit its full potential. The requirements for a user-centric design of the chatbot are first analyzed, then a proper solution is designed which exploits a serverless approach and makes extensive use of Artificial Intelligence (AI) tools. The developed chatbot is integrated with Telegram to message between the user and the Lysis IoT platform. The performance of the developed chatbot is analyzed to assess its effectiveness when accessing the platform, set the main devices' parameters and request data of interest.
23
Shukla, Rachit, Adwitiya Sinha, and Ankit Chaudhary. "TweezBot: An AI-Driven Online Media Bot Identification Algorithm for Twitter Social Networks." Electronics 11, no. 5 (February 28, 2022): 743. http://dx.doi.org/10.3390/electronics11050743.
Повний текст джерелаАнотація:
In the ultra-connected age of information, online social media platforms have become an indispensable part of our daily routines. Recently, this online public space is getting largely occupied by suspicious and manipulative social media bots. Such automated deceptive bots often attempt to distort ground realities and manipulate global trends, thus creating astroturfing attacks on the social media online portals. Moreover, these bots often tend to participate in duplicitous activities, including promotion of hidden agendas and indulgence in biased propagation meant for personal gain or scams. Thus, online bots have eventually become one of the biggest menaces for social media platforms. Therefore, we have proposed an AI-driven social media bot identification framework, namely TweezBot, which can identify fraudulent Twitter bots. The proposed bot detection method analyzes Twitter-specific user profiles having essential profile-centric features and several activity-centric characteristics. We have constructed a set of filtering criteria and devised an exhaustive bag of words for performing language-based processing. In order to substantiate our research, we have performed a comparative study of our model with the existing benchmark classifiers, such as Support Vector Machine, Categorical Naïve Bayes, Bernoulli Naïve Bayes, Multilayer Perceptron, Decision Trees, Random Forest and other automation identifiers.
24
Chen, Yung-Yao, Yu-Hsiu Lin, Chia-Ching Kung, Ming-Han Chung, and I.-Hsuan Yen. "Design and Implementation of Cloud Analytics-Assisted Smart Power Meters Considering Advanced Artificial Intelligence as Edge Analytics in Demand-Side Management for Smart Homes." Sensors 19, no. 9 (May 2, 2019): 2047. http://dx.doi.org/10.3390/s19092047.
Повний текст джерелаАнотація:
In a smart home linked to a smart grid (SG), demand-side management (DSM) has the potential to reduce electricity costs and carbon/chlorofluorocarbon emissions, which are associated with electricity used in today’s modern society. To meet continuously increasing electrical energy demands requested from downstream sectors in an SG, energy management systems (EMS), developed with paradigms of artificial intelligence (AI) across Internet of things (IoT) and conducted in fields of interest, monitor, manage, and analyze industrial, commercial, and residential electrical appliances efficiently in response to demand response (DR) signals as DSM. Usually, a DSM service provided by utilities for consumers in an SG is based on cloud-centered data science analytics. However, such cloud-centered data science analytics service involved for DSM is mostly far away from on-site IoT end devices, such as DR switches/power meters/smart meters, which is usually unacceptable for latency-sensitive user-centric IoT applications in DSM. This implies that, for instance, IoT end devices deployed on-site for latency-sensitive user-centric IoT applications in DSM should be aware of immediately analytical, interpretable, and real-time actionable data insights processed on and identified by IoT end devices at IoT sources. Therefore, this work designs and implements a smart edge analytics-empowered power meter prototype considering advanced AI in DSM for smart homes. The prototype in this work works in a cloud analytics-assisted electrical EMS architecture, which is designed and implemented as edge analytics in the architecture described and developed toward a next-generation smart sensing infrastructure for smart homes. Two different types of AI deployed on-site on the prototype are conducted for DSM and compared in this work. The experimentation reported in this work shows the architecture described with the prototype in this work is feasible and workable.
25
Mandaric, Katarina, Ana Keselj Dilberovic, and Gordan Jezic. "A Multi-Agent System for Service Provisioning in an Internet-of-Things Smart Space Based on User Preferences." Sensors 24, no. 6 (March 8, 2024): 1764. http://dx.doi.org/10.3390/s24061764.
Повний текст джерелаАнотація:
The integration of the Internet of Things (IoT) and artificial intelligence (AI) is critical to the advancement of ambient intelligence (AmI), as it enables systems to understand contextual information and react accordingly. While many solutions focus on user-centric services that provide enhanced comfort and support, few expand on scenarios in which multiple users are present simultaneously, leaving a significant gap in service provisioning. To address this problem, this paper presents a multi-agent system in which software agents, aware of context, advocate for their users’ preferences and negotiate service settings to achieve solutions that satisfy everyone, taking into account users’ flexibility. The proposed negotiation algorithm is illustrated through a smart lighting use case, and the results are analyzed in terms of the concrete preferences defined by the user and the selected settings resulting from the negotiation in regard to user flexibility.
26
Israfilzade, Khalil, and Nuraddin Sadili. "Beyond interaction: Generative AI in conversational marketing - foundations, developments, and future directions." JOURNAL OF LIFE ECONOMICS 11, no. 1 (February 9, 2024): 13–29. http://dx.doi.org/10.15637/jlecon.2294.
Повний текст джерелаАнотація:
This paper explores the integration of Generative Artificial Intelligence (AI) in conversational marketing, transitioning from traditional marketing to interactive, customer-centric strategies. It examines the shift from one-way communication to dynamic, AI-driven interactions that personalize customer experiences. Central to this study is how Generative AI facilitates real-time, tailored dialogues between brands and customers, enhancing customer engagement and satisfaction. The paper also addresses the challenges and ethical considerations of using anthropomorphic AI in marketing, balancing human-like AI traits with user expectations. Additionally, it presents a novel framework that conceptualizes the combination of Generative AI and anthropomorphism in conversational marketing into four distinct quadrants, providing a comprehensive analysis of their potential interplay. Conclusively, it offers strategic insights for leveraging AI in marketing while adhering to ethical practices, highlighting the potential of Generative AI to transform customer engagement in the digital age. This research has two important consequences. Practically, it offers valuable insights and strategic recommendations for businesses aiming to integrate Generative AI into their conversational marketing practices effectively. Theoretically, it contributes to the academic discourse by highlighting the transformative role of Generative AI in marketing, suggesting avenues for future research in this rapidly evolving field. This study provides a brief overview of the evolving role of AI in modern marketing strategies, emphasizing the future potential and implications of AI-driven conversational marketing.
27
Partarakis, Nikolaos, and Xenophon Zabulis. "A Review of Immersive Technologies, Knowledge Representation, and AI for Human-Centered Digital Experiences." Electronics 13, no. 2 (January 7, 2024): 269. http://dx.doi.org/10.3390/electronics13020269.
Повний текст джерелаАнотація:
The evolution of digital technologies has resulted in the emergence of diverse interaction technologies. In this paper, we conducted a review of seven domains under a human-centric approach user interface design, human-centered web-based information systems, semantic knowledge representation, X-reality applications, human motion and 3D digitization, serious games, and AI. In this review, we studied these domains concerning their impact on the way we interact with digital interfaces, process information, and engage in immersive experiences. As such, we highlighted the shifts in design paradigms, user-centered principles, and the rise of web-based information systems. The results of such shifts are materialized in modern immersive technologies, semantic knowledge representation, serious games, and the facilitation of artificial intelligence for interactions. Through this exploration, we aimed to assist our understanding of the challenges that lie ahead. The seamless integration of technologies, ethical considerations, accessibility, education for technological literacy, interoperability, user trust, environmental sustainability, and regulatory frameworks are becoming significant. These challenges present opportunities for the future to enrich human experiences while addressing societal needs. This paper lays the groundwork for thoughtful and innovative approaches to the challenges that will define the future of human–computer interaction and information technologies.
28
Park, Soochang. "D-PARK: User-Centric Smart Parking System over BLE-Beacon Based Internet of Things." Electronics 10, no. 5 (February 25, 2021): 541. http://dx.doi.org/10.3390/electronics10050541.
Повний текст джерелаАнотація:
Our daily life services are quickly becoming smarter with intelligence and information through artificial intelligence (AI) and Big Data technologies. Parking services are one of the most frequently used in our daily life-cycle. This parking application could be classified into several features according to demands and properties, such as parking capacity balancing on a city-level view, parking fee maximization for achieving the service provider demand, empty parking spot notification within a parking lot, etc. This paper concentrates on parking space detection and alert to users. Most smart services rely on smart mobile derives of users such as smartphones and smartwatches. The proposed novel mechanism for smart parking is based on a smart device to gather mobile sensing data such as users’ activity and position data. Acquired mobile data are analyzed via machine learning technologies to provide dedicated parking services per user. Based on real testbed setups on campus and the proof-of-concept implementation, the proposed localization can achieve accuracy of a parking spot scale (2m-second guess 95%); moreover, it shows a much lower service operation period of 6.8 times (34s) than the legacy approach (230s).
29
Qian, Chen. "Research on Human-centered Design in College Music Education to Improve Student Experience of Artificial Intelligence-based Information Systems." Journal of Information Systems Engineering and Management 8, no. 3 (October 31, 2023): 23761. http://dx.doi.org/10.55267/iadt.07.13854.
Повний текст джерелаАнотація:
The integration of Artificial Intelligence (AI) technology with music instruction necessitates a delicate balance between technical advancement and the maintenance of humanistic teaching. This study examined how human-centered design concepts were used to optimize the integration of AI while also investigating the effects of AI technology on college-level music instruction in China. It aimed to identify potential, difficulties and make recommendations for ethical AI deployment in this particular environment. Semi-structured interviews with 20 music students and professors from Chinese higher education institutions were conducted using a qualitative study design. To condense significant themes and subthemes from the data, open coding, axial coding, and selective coding were used. The study revealed complex interactions between AI and Chinese music instruction. Themes included "Enhanced Learning with AI", emphasizing AI's role in motivating and personalizing music education; "User-Centric Design", emphasizing the importance of intuitive interfaces and aesthetic appeal; "Collaboration and Peer Learning", demonstrating AI's facilitation of collaborative projects; "Technical Challenges and Ethical Concerns", addressing technical obstacles and ethical concerns; and "Educator Support and Curriculum Alignment", emphasizing the importance of educator support and curriculum alignment. This study adds knowledge about how AI can be successfully incorporated into Chinese music teaching. It informs best practices for the adoption of AI, ensuring that technology enhances the learning experience for students while preserving cultural nuances. The study improves the conversation about innovative pedagogy and responsible technology integration. Implications include the potential for AI to change music education, cultural preservation, and global viewpoints. However, drawbacks such as sample bias and the dynamic nature of AI technology necessitate more study and development of educational techniques that use AI. Personalization and multimodal methods used in college music instruction in the future, to help increase student involvement. The importance of ethical issues, long-term effect analyses, and user-centered design will call for interdisciplinary cooperation. The future of AI-enhanced music education will also be shaped by assuring accessibility, diversity, and active engagement in policy and regulation discussions.
30
Yvonne Oshevwe Okoro, Oluwatoyin Ayo-Farai, Chinedu Paschal Maduka, Chiamaka Chinaemelum Okongwu, and Olamide Tolulope Sodamade. "THE ROLE OF TECHNOLOGY IN ENHANCING MENTAL HEALTH ADVOCACY: A SYSTEMATIC REVIEW." International Journal of Applied Research in Social Sciences 6, no. 1 (January 2, 2024): 37–50. http://dx.doi.org/10.51594/ijarss.v6i1.690.
Повний текст джерелаАнотація:
This systematic review explores the evolving landscape of mental health advocacy through the lens of technology, investigating its role, impact, and future directions. Tracing historical perspectives, from grassroots movements to digital revolutions, the review analyzes the integration of social media, mobile applications, virtual reality, and artificial intelligence in advocacy efforts. Identified factors influencing effectiveness include accessibility, user engagement, privacy, cultural sensitivity, integration with traditional approaches, and collaborative partnerships. Privacy protection, inclusivity, quality assurance, stigma reduction, and user autonomy are ethical considerations. Future directions emphasize personalized AI interventions, gamification, VR/AR applications, telehealth integration, and community-centric platforms. Balancing innovation with ethical practice is critical for realizing technology's potential in fostering a more connected, informed, and supportive mental health advocacy landscape.
Keywords: Mental Health Advocacy, Technology, Digital Innovation, Ethical Considerations, Inclusivity.
31
Sarode, Prof Vaishali, Bhakti Joshi, Tejaswini Savakare, and Harshada Warule. "A Real Time Chatbot Using Python." International Journal for Research in Applied Science and Engineering Technology 11, no. 5 (May 31, 2023): 7385–89. http://dx.doi.org/10.22214/ijraset.2023.53453.
Повний текст джерелаАнотація:
Abstract: Real-time chatbots developed using Python have emerged as powerful tools for enhancing customer support, improving user experiences, and streamlining business processes. Leveraging Python's extensive libraries and frameworks, such as NLTK, Flask, and telebot, developers can build intelligent and scalable chatbot systems.This paper provides an overview of the key components and techniques involved in developing a real-time chatbot using Python. It explores the process of requirement gathering, use case definition, conversation flow design, and performance optimization. Integration with backend services, error handling, validation, and user experience (UX) design are also discussed. The utilization of natural language understanding (NLU) algorithms and techniques allows chatbots to interpret and comprehend user intents, providing accurate and context-aware responses. Integration with REST APIs, Flask, and telebot facilitates seamless communication and interaction between the chatbot and users. Furthermore, the paper highlights the importance of security, privacy, and ethical considerations in chatbot systems. It emphasizes the significance of continuous testing, feedback iteration, and user-centric design principles to refine the chatbot's performance and enhance the user experience. Looking ahead, future work in real-time chatbot development using Python includes advancements in natural language processing (NLP), personalized user experiences, multi-modal capabilities, and the integration of voice assistants. Ethical considerations and explainable AI techniques will also be critical for building trustworthy and responsible chatbot systems. In conclusion, real-time chatbots developed using Python offer immense potential for transforming customer support, automating processes, and delivering personalized and efficient services. With ongoing advancements in NLP, AI, and user interface design, the future of real-time chatbots holds exciting possibilities for enhanced user interactions and seamless automation.
32
Yilmaz, Erhan, and Ozgu Can. "Unveiling Shadows: Harnessing Artificial Intelligence for Insider Threat Detection." Engineering, Technology & Applied Science Research 14, no. 2 (April 2, 2024): 13341–46. http://dx.doi.org/10.48084/etasr.6911.
Повний текст джерелаАнотація:
Insider threats pose a significant risk to organizations, necessitating robust detection mechanisms to safeguard against potential damage. Traditional methods struggle to detect insider threats operating within authorized access. Therefore, the use of Artificial Intelligence (AI) techniques is essential. This study aimed to provide valuable insights for insider threat research by synthesizing advanced AI methodologies that offer promising avenues to enhance organizational cybersecurity defenses. For this purpose, this paper explores the intersection of AI and insider threat detection by acknowledging organizations' challenges in identifying and preventing malicious activities by insiders. In this context, the limitations of traditional methods are recognized, and AI techniques, including user behavior analytics, Natural Language Processing (NLP), Large Language Models (LLMs), and Graph-based approaches, are investigated as potential solutions to provide more effective detection mechanisms. For this purpose, this paper addresses challenges such as the scarcity of insider threat datasets, privacy concerns, and the evolving nature of employee behavior. This study contributes to the field by investigating the feasibility of AI techniques to detect insider threats and presents feasible approaches to strengthening organizational cybersecurity defenses against them. In addition, the paper outlines future research directions in the field by focusing on the importance of multimodal data analysis, human-centric approaches, privacy-preserving techniques, and explainable AI.
33
ZANNAT, NAHREEN, and MURNI MAHMUD. "MINDFUL UX DESIGN IN INDUSTRY 4.0: MITIGATING ADDICTION AND ENHANCING USER WELL-BEING INSOCIAL MEDIA AND AI ENVIRONMENTS." Journal of Information Systems and Digital Technologies 5, no. 2 (November 29, 2023): 321–44. http://dx.doi.org/10.31436/jisdt.v5i2.428.
Повний текст джерелаАнотація:
The rapid advancements in technology under Industry 4.0 bring forth both opportunities and challenges, particularly in User Experience (UX) design in social media and Artificial Intelligence (AI) environments. This research paper explores these dichotomies, focusing primarily on the role of UX design in mitigating addiction and enhancing user well-being. In this paper, authors begin by exploring the historical evolution of UX design and its increasing importance in the context of technological progression. We then discuss the psychological impacts of UX design on users, drawing a parallel between addictive characteristics of social media platforms and AI-based systems, and the deterioration of user well-being. Recognizing the gravity of the situation, we delve into the concept of 'Responsible UX Design,' a design philosophy that focuses on developing interfaces and systems that foster positive user behaviour while minimizing the risk of digital addiction. Authors present a comprehensive analysis of current strategies, practices, and policies related to responsible UX design in Industry 4.0 and discuss how these could be evolved for future. Drawing on a wide range of case studies, user interviews, and psychological research, the paper provides actionable recommendations for businesses, policymakers, and UX designers. These recommendations promote responsible design practices, discourage addictive design patterns, and encourage user-centric design approaches that improve digital well-being. Additionally, this paper provides a critical review of the challenges and potential ethical considerations in implementing responsible UX design. It introduces the concept of 'Digital Ethics,' which requires organizations and designers to uphold user well-being as a primary consideration during the design process. In conclusion, this research emphasizes the need for a paradigm shift towards responsible UX design, both as a moral obligation and as a competitive advantage in Industries 4.0. It advocates for an approach that balances user engagement with user well-being, and ensures that technological innovations enhance, rather than compromise, human lives. Unprecedented technical developments, including the fusion of social media platforms and artificial intelligence (AI), have been made possible by industry 4.0. User experience (UX) design now faces ethical and societal repercussions as a result of these developments. This paper provides a thorough examination of responsible UX design in Industry 4.0, with a particular emphasis on the growing usage of social media and AI tools. The research emphasizes the significance of ethical issues while examining recent information, trends, and best practices in UX design. Unprecedented technical developments, including the fusion of social media platforms and artificial intelligence (AI), have been made possible by industry 4.0. User experience (UX) design now faces ethical and societal repercussions as a result of these developments. This article provides a thorough examination of responsible UX design in Industry 4.0, with a particular emphasis on the growing usage of social media and AI tools. The research emphasizes the significance of ethical issues while examining recent information, trends, and best practices in UX design.
34
Ness, Stephanie, Nicki James Shepherd, and Teo Rong Xuan. "Synergy Between AI and Robotics: A Comprehensive Integration." Asian Journal of Research in Computer Science 16, no. 4 (September 29, 2023): 80–94. http://dx.doi.org/10.9734/ajrcos/2023/v16i4372.
Повний текст джерелаАнотація:
The emergence of artificial intelligence is mostly linked to software-driven robotic systems, including mobile robots, unmanned aerial aircraft, and, to a growing extent, semi-autonomous automobiles. Nevertheless, the significant disparity between the algorithmic realm and the physical realm hinders current systems from achieving the desired outcome of creating intelligent and user-friendly robots that can effectively engage with and manipulate our human-centric environment. The nascent field of machine intelligence (MI), which combines robotics and artificial intelligence, strives to develop reliable and embodiment-aware artificial intelligence systems. These systems possess self-awareness and an understanding of their environment, enabling them to adapt to the interacting body they are operating. The incorporation of artificial intelligence (AI) and robotics into control, perception, and machine-learning systems is necessary for the realization of fully autonomous intelligent systems in our everyday existence. This review provides an overview of the historical development of machine intelligence, tracing its origins to the twelfth century. It then proceeds to examine the present state of robotics and artificial intelligence (AI), discussing significant systems and contemporary research directions. Additionally, the article outlines the remaining challenges in these fields and speculates on the potential future of human-machine interactions that has yet to be realized.
35
Klein, Harry, Tali Mazor, Matthew Galvin, Jason Hansel, Emily Mallaber, Pavel Trukhanov, Joyce Yu, et al. "Abstract 1067: MatchMiner: An open-source AI precision medicine trial matching platform." Cancer Research 83, no. 7_Supplement (April 4, 2023): 1067. http://dx.doi.org/10.1158/1538-7445.am2023-1067.
Повний текст джерелаАнотація:
Abstract As the number of precision medicine (PM) trials and patient genomic data has grown, it has become challenging for clinicians and trial staff to identify PM trial options for patients. Several trial matching software platforms have been developed to match genomic data from patients with PM trials, but these existing platforms are proprietary and are not easily accessible for adoption by institutions. At Dana-Farber Cancer Institute (DFCI), we have addressed this challenge by developing our own open-source institutional trial matching software, MatchMiner. MatchMiner algorithmically matches patient genomic and clinical data with PM trial eligibility data. Trial eligibility data is manually curated into a human-readable markup language, called clinical trial markup language (CTML), for matching with patient genomic data. MatchMiner has 2 main modes of clinical use: (1) patient-centric, where clinicians search for trial matches for individual patients and (2) trial-centric, where trial staff identify patients that match their trial’s genomic eligibility. We recently described MatchMiner’s usage at DFCI and since our report, we have added 90 additional trial consents facilitated by MatchMiner (>250 trial consents, called MatchMiner consents [MMC]). Here, we describe new characteristics of our MMC including which user mode (patient-centric or trial-centric) was used to match the consent, genomic alterations and cancer types that matched to eligibility criteria, and whether the patient went onto trial. MMCs were mostly identified by patient-centric mode (70%), genomic alterations and cancer types among MMC were diverse (n=55 genes and n=20 cancer types), and 87% of MMC went on trial. Among MMCs, the most common altered genes leading to trial eligibility were ERBB2 and KRAS in breast cancer and lung cancer, which is consistent with the number of therapies targeting ERBB2 and KRAS. MMCs also included patients with rare cancer types, like extraskeletal myxoid chondrosarcoma, as well as rare genomic alterations, such as NTRK fusions. Thus, MatchMiner has been successful at facilitating PM trial matching for a broad range of genomic alterations and cancer types at DFCI. MatchMiner matches patients to trials as soon as their genomic report is available, however, many patients are not yet ready to enroll onto a trial because their cancer is responding to the standard of care or they are in a remission period. To address this problem, we are evaluating the use of artificial intelligence (AI) to identify patients that may be ready for a new treatment option. After trial matches have been generated by MatchMiner, radiology scan text from patients’ tumor scans is run through a natural language processing (NLP) model to identify patients who are more likely to be ready to enroll onto a trial. By using NLP to filter trial matches, we hope to improve MatchMiner’s efficiency of finding trial matches and provide more timely trial options for patients. Citation Format: Harry Klein, Tali Mazor, Matthew Galvin, Jason Hansel, Emily Mallaber, Pavel Trukhanov, Joyce Yu, James Lindsay, Kenneth Kehl, Michael Hassett, Ethan Cerami. MatchMiner: An open-source AI precision medicine trial matching platform [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2023; Part 1 (Regular and Invited Abstracts); 2023 Apr 14-19; Orlando, FL. Philadelphia (PA): AACR; Cancer Res 2023;83(7_Suppl):Abstract nr 1067.
36
Alvey, Brendan, Derek Anderson, James Keller, and Andrew Buck. "Linguistic Explanations of Black Box Deep Learning Detectors on Simulated Aerial Drone Imagery." Sensors 23, no. 15 (August 3, 2023): 6879. http://dx.doi.org/10.3390/s23156879.
Повний текст джерелаАнотація:
Deep learning has become increasingly common in aerial imagery analysis. As its use continues to grow, it is crucial that we understand and can explain its behavior. One eXplainable AI (XAI) approach is to generate linguistic summarizations of data and/or models. However, the number of summaries can increase significantly with the number of data attributes, posing a challenge. Herein, we proposed a hierarchical approach for generating and evaluating linguistic statements of black box deep learning models. Our approach scores and ranks statements according to user-specified criteria. A systematic process was outlined for the evaluation of an object detector on a low altitude aerial drone. A deep learning model trained on real imagery was evaluated on a photorealistic simulated dataset with known ground truth across different contexts. The effectiveness and versatility of our approach was demonstrated by showing tailored linguistic summaries for different user types. Ultimately, this process is an efficient human-centric way of identifying successes, shortcomings, and biases in data and deep learning models.
37
Lee, Kyoung Jun, Baek Jeong, Suhyeon Kim, Dam Kim, and Dongju Park. "General Commerce Intelligence: Glocally Federated NLP-Based Engine for Privacy-Preserving and Sustainable Personalized Services of Multi-Merchants." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 21 (March 24, 2024): 22752–60. http://dx.doi.org/10.1609/aaai.v38i21.30309.
Повний текст джерелаАнотація:
One of the most crucial capabilities in the commercial sector is a personalized prediction of a customer's next purchase. We present a novel method of creating a commerce intelligence engine that caters to multiple merchants intended for the UB Platform, managed by e-payment company Harex InfoTech. To cultivate this intelligence, we utilized payment receipt data and created a Natural Language Processing (NLP)-based commerce model using a Transformer to accommodate multinational and merchant trade. Our model, called General Commerce Intelligence (GCI), provides a range of services for merchants, including product recommendations, product brainstorming, product bundling, event promotions, collaborative marketing, target marketing, and demand fore-casting etc. To bolster user privacy and foster sustainable business collaboration, especially among micro-, small-, and medium-sized enterprises (MSMEs), the GCI model was trained through federated learning, especially with glocalization. This study delves into the structure, development, and assessment of GCI, showcasing its transformative capacity to implement User Centric AI and re-shape the global commerce landscape to benefit MSMEs.
38
Bernasconi, Eleonora, Davide Di Pierro, Domenico Redavid, and Stefano Ferilli. "SKATEBOARD: Semantic Knowledge Advanced Tool for Extraction, Browsing, Organisation, Annotation, Retrieval, and Discovery." Applied Sciences 13, no. 21 (October 27, 2023): 11782. http://dx.doi.org/10.3390/app132111782.
Повний текст джерелаАнотація:
This paper introduces Semantic Knowledge Advanced Tool for Extraction Browsing Organisation Annotation Retrieval and Discovery (SKATEBOARD), a tool designed to facilitate knowledge exploration through the application of semantic technologies. The demand for advanced solutions that streamline Knowledge Extraction, management, and visualisation, characterised by abundant information, has grown substantially in the current era. Graph-based representations have emerged as a robust approach for uncovering intricate data relationships, complementing the capabilities offered by AI models. Acknowledging the transparency and user control challenges faced by AI-driven solutions, SKATEBOARD offers a comprehensive framework encompassing Knowledge Extraction, ontology development, management, and interactive exploration. By adhering to Linked Data principles and adopting graph-based exploration, SKATEBOARD provides users with a clear view of data relationships and dependencies. Furthermore, it integrates recommendation systems and reasoning capabilities to augment the knowledge discovery process, thus introducing a serendipity effect generated by the SKATEBOARD interface exploration. This paper elucidates SKATEBOARD’s functionalities while emphasising its user-centric design. After reviewing related research, we provide an overview of the SKATEBOARD pipeline, demonstrating its capacity to bridge RDF and LPG representations. Subsequent sections delve into Knowledge Extraction and exploration, culminating in the evaluation of the tool. SKATEBOARD empowers users to make informed decisions and uncover valuable insights within their data domains, with the added dimension of serendipitous discoveries facilitated by its interface exploration capabilities.
39
Olima Shukhratovna, Ruzyieva, and Ruziyev Shukhrat Narmuradovich. "Enhancing Bank Service Popularity Through Digital Innovation: Strategies for Customer-Centric Technology Integration." INTERNATIONAL JOURNAL OF MANAGEMENT SCIENCE AND BUSINESS ADMINISTRATION 9, no. 6 (September 2023): 7–12. http://dx.doi.org/10.18775/ijmsba.1849-5664-5419.2014.96.1001.
Повний текст джерелаАнотація:
The paper explores the possible strategies to increase the use of digital tools in modern banking. The conceptual study proposes four strategies banks should focus on to be competitive and satisfy diverse customer needs. The primary focus is enhancing the customer experience through digital tools, such as online payments, credit requests, and bill payments while acknowledging the security and technical limitations with which users may have issues—the strategies banks can utilize have a customer-centric approach that includes user-friendly design and personalization. The technology focus would encompass technological advancements with security features like encryption and biometric verification and integration with broader services. Financial product innovation and effective marketing strategies are also essential for increasing the use of digital banking tools. Blockchain and AI, integrated marketing, and customer relationship management should be significant points of emphasis for the banks to serve the business and consumer markets effectively.
40
Hashiyana, Valerianus, Nalina Suresh, and Abel Natangwe Mwedihanga. "The Development of Climate Agrometeorological Application for Farmers in Namibia." International Journal of Computer Science and Information Technology 15, no. 2 (April 29, 2023): 39–51. http://dx.doi.org/10.5121/ijcsit.2023.15204.
Повний текст джерелаАнотація:
Climate services involve the timely production, translation, and delivery of useful climate data, information and knowledge for societal decision making. In order to create climate services for farmers that are truly integrated with user-centric design into the development process in an African context, the study has finished an important and crucial step by conducting a literature review and designing a prototype for the application. The goal of this study was to create climate services for farmers in an African context that are genuinely integrated with user-centric design. This led to the co-design and development and integration of a mobile application that provide climate and weather information as well as agricultural information for the main crops such millet, maize and sorghum. The research applied using qualitative research using interview with 3 farmers in the field using random sampling with the approach to inform the study. A survey has been administered to find out how people understand climate services, Agro meteorology and help enhance the mobile application’s user experience. A Results shows that farmers are determined and ready to use and excited with the application. These innovations helped farmers to reduce the cost, increase crop capacity and profit. A hypothesis was set that there is a need for integrating AI into a farmer’s application for making farming process more progressive and efficient farming and the integration of Market Place (MP) for farmer’s application to market and sell their product the integration of notification system that allows farmers to receive real-time data and IOT for real-time data. The data collected and the survey results demonstrated that the research objectives were being met. The study aims to develop the application that would be scalable, durable and fault tolerant for farmers to use the application successfully. KEYWORDS
41
Josimovski, Saso, Lidija Pulevska Ivanovska, and Darko Dodevski. "ADVANTAGES OF IMPLEMENTING ARTIFICIAL INTELLIGENCE IN E-BUSINESS FOR CONSUMERS." KNOWLEDGE - International Journal 60, no. 1 (September 30, 2023): 69–75. http://dx.doi.org/10.35120/kij6001069j.
Повний текст джерелаАнотація:
In the contemporary e-business environment, the prioritization of great user experiences and exceptional customer service has emerged as a critical objective. This detailed investigation delves deeply into the tactics that provide the foundation for improving user interactions within digital platforms. This is an exploration of the dynamic landscape of digital commerce, highlighting the importance of design principles that prioritize user needs, advanced search capabilities, effortless navigation, and tailored customer assistance. The central focus of the paper is the crucial significance of user interfaces that include both intuitive qualities and a high level of responsiveness across diverse devices. The interfaces play a crucial role in fostering user engagement and cultivating consumer loyalty within the digital domain, serving as a fundamental basis for facilitating favorable interactions between businesses and their clients. E-businesses foster an inclusive and user-centric environment by providing mobile-friendly content and interfaces that accommodate a wide range of user requirements. This approach promotes user exploration, engagement, and retention. The subsequent analysis focuses on the development of site search mechanisms, emphasizing the transition from rudimentary keyword searches to sophisticated search algorithms, the introduction of faceted search options, the integration of visual search capabilities, the implementation of predictive search functions, and the increasing significance of voice search. These innovations operate in conjunction to transform the accessibility of items and services, improve the process of making purchases, and enhance overall user involvement. Users are able to easily find desired items, explore other options, and obtain pertinent information, all of which enhance the overall satisfaction and effectiveness of the e-commerce experience. The investigation ultimately penetrates into the realm of virtual assistants and chatbots, which are driven by artificial intelligence (AI). These digital entities provide both immediate assistance and a range of functionalities designed to improve the overall purchasing experience. Customers have the opportunity to get support, monitor their orders, stay informed about product availability, and participate in virtual trials for apparel or furniture, thanks to the implementation of augmented reality and virtual reality advancements. Fundamentally, these diverse techniques highlight the utmost significance of placing user-centricity, innovation in search and navigation, customization, and AI-driven support mechanisms at the forefront in order to provide seamless, captivating, and effective e-business experiences. In a continuously evolving digital environment, enterprises that use these components are more strategically positioned to fulfill user demands, foster client allegiance, and sustain their competitive advantage.
42
Huang, Yingjing, Teng Fei, Mei-Po Kwan, Yuhao Kang, Jun Li, Yizhuo Li, Xiang Li, and Meng Bian. "GIS-Based Emotional Computing: A Review of Quantitative Approaches to Measure the Emotion Layer of Human–Environment Relationships." ISPRS International Journal of Geo-Information 9, no. 9 (September 15, 2020): 551. http://dx.doi.org/10.3390/ijgi9090551.
Повний текст джерелаАнотація:
In recent years, with the growing accessibility of abundant contextual emotion information, which is benefited by the numerous georeferenced user-generated content and the maturity of artificial intelligence (AI)-based emotional computing technics, the emotion layer of human–environment relationship is proposed for enriching traditional methods of various related disciplines such as urban planning. This paper proposes the geographic information system (GIS)-based emotional computing concept, which is a novel framework for applying GIS methods to collective human emotion. The methodology presented in this paper consists of three key steps: (1) collecting georeferenced data containing emotion and environment information such as social media and official sites, (2) detecting emotions using AI-based emotional computing technics such as natural language processing (NLP) and computer vision (CV), and (3) visualizing and analyzing the spatiotemporal patterns with GIS tools. This methodology is a great synergy of multidisciplinary cutting-edge techniques, such as GIScience, sociology, and computer science. Moreover, it can effectively and deeply explore the connection between people and their surroundings with the help of GIS methods. Generally, the framework provides a standard workflow to calculate and analyze the new information layer for researchers, in which a measured human-centric perspective onto the environment is possible.
43
Alpika Srivastava Dr. Sony Kulshrestha. "Impact of The Artificial Intelligence in Media: A Need to Address the Problem Relating to Regulation of Ai in Media." Journal of Advanced Zoology 44, S-2 (November 4, 2023): 3157–63. http://dx.doi.org/10.17762/jaz.v44is-2.1547.
Повний текст джерелаАнотація:
Over the past 20 years, technological innovations have caused tremendous disruption to the traditional media sector. A plethora of new opportunities and challenges have arisen as a result of the development and widespread use of AI technology. On the one hand, widespread use of these technologies may open up new avenues for media service expansion, disinformation suppression, and data-centric journalism advancement. Some approaches, such as algorithmic content selection and user customization, have the potential to cause social risks and should thus be implemented with caution. Finding a balance between the benefits and the downsides of these options highlights the need for additional research in the field of responsible media technology. This article's first portion provides a thorough analysis of the most pressing issues brought about by contemporary media technology, with a particular emphasis on how these issues affect society's dynamics and the media industry. We first acknowledge the need for further research, better technical methods, and a technology infrastructure that can sustain moral editorial standards and practices. Then, we go on to outline a number of areas within the media production and distribution spectrum. The argument that is made is that quick action is required to create a thorough framework for media technology research. This strategy is anticipated to integrate interdisciplinary approaches and promote robust cooperation between media companies and educational establishments.
44
Nabi, Aftab UL, Thouraya SNOUSSI, and Zahraa A. Abdalkareem. "A Review of IoT Convergence in Healthcare and Smart Cities: Challenges, Innovations, and Future Perspectives." Babylonian Journal of Internet of Things 2023 (April 17, 2023): 23–30. http://dx.doi.org/10.58496/bjiot/2023/004.
Повний текст джерелаАнотація:
This in depth analysis explores the transformative implications of the convergence of the Internet of Things (IoT) in healthcare and smart cities. By examining the current state, challenges and innovations within these sectors, existing literature highlights how IoT plays a crucial role in reshaping healthcare through remote patient monitoring, personalized treatments and improved healthcare delivery. It also discusses how IoT impacts smart cities by optimizing urban services and resource management. While challenges such as security, interoperability and data governance persist in both sectors, there are promising innovations in secure IoT frameworks and robust governance policies that provide solutions. The analysis identifies similarities in challenges and benefits across different sectors while acknowledging sector specific impacts. To shape the future of healthcare and smart city development effectively, it suggests focusing on fortified security measures, interoperable standards, collaborative efforts among stakeholders, as well as integrating IoT with artificial intelligence (AI) and machine learning (ML) for enhanced decision making. The study emphasizes the importance of user centric design, infrastructure investments and seamless integration of IoT to fully realize its potential in shaping the future of healthcare and smart city development.
45
Bernard Oloo Akello. "Organizational information security threats: Status and challenges." World Journal of Advanced Engineering Technology and Sciences 11, no. 1 (February 28, 2024): 148–62. http://dx.doi.org/10.30574/wjaets.2024.11.1.0152.
Повний текст джерелаАнотація:
Organizational information security is a critical concern in today’s interconnected and data-driven world. With the increasing frequency and sophistication of cyber threats, organizations face significant risks to the confidentiality, integrity, and availability of their sensitive information. This paper provides an overview of the key aspects and challenges related to organizational information security. It highlights the importance of implementing robust security measures, such as firewalls, intrusion detection systems, encryption technologies, and secure coding practices, to protect against external threats. It also demonstrates the need for continuous monitoring, threat intelligence sharing, and incident response capabilities to detect and respond to security incidents effectively. This survey shows importance of user awareness, training, and adherence to security policies and procedures. In addition, the significance of establishing a security-centric culture within organizations to mitigate the risk of insider threats and promote a strong security posture is discussed. The evolving threat landscape, including challenges associated with advanced persistent threats, zero-day vulnerabilities, and the security of emerging technologies such as IoT and AI are highlighted, together with the need for ongoing research and innovation to address these challenges and enhance the effectiveness of preventive measures.
46
Rogushina, J. V., and I. Yu Grishanova. "Problems of scaling semantic information resources with a complex structure." PROBLEMS IN PROGRAMMING, no. 3-4 (December 2022): 171–82. http://dx.doi.org/10.15407/pp2022.03-04.171.
Повний текст джерелаАнотація:
We analyze scaling problems arising in modern intelligent information systems (IISs) and classify main reasons for their occurrence in their practical solutions. IISs integrate various elements of artificial intelligence (AI) for acquisition of knowledge relevant to actual user tasks. Important properties of these IISs are use of data with complex structure and orientation on semantic information resources (IRs). Therefore we analyze main features of the Data-Centric AI and opportunities for acquiring domain knowledge in various representations from Big Data. Knowledge organization systems (KOS) provide models and methods for effective store, retrieval and use of information processed by the Web-oriented IISs, and we consider existing approaches for their software platforms.We analyse the specifics of the scaling for systems focused on the semantic information processing and its differences from traditional data and Big Data scaling. This specifics is caused by complexity of data structure, number of various semantic relations between information objects into IR and complexity of semantic queries executed by KOS. On example of e-VUE – the Wiki-portal of the Great Ukrainian Encyclopedia – we analyze various situations that arise in process of practical development of semantic information resources with large volume and complex structure. Various ways of semantic retrieval into this information resource that use possibilities of the Semantic MediaWiki plugin are considered from the point of view of scaling aspects (such as increase of information objects, their relations and complication of their structure and characteristics). On base of this analysis we generate a set of recommendations aimed at ensuring more efficient development of such resources and their efficient functioning for practical use.
47
Thirunavukarasu, Arun James, Kabilan Elangovan, Laura Gutierrez, Refaat Hassan, Yong Li, Ting Fang Tan, Haoran Cheng, Zhen Ling Teo, Gilbert Lim, and Daniel Shu Wei Ting. "Clinical performance of automated machine learning: A systematic review." Annals of the Academy of Medicine, Singapore 53, no. 3 (March 27, 2024): 187–207. http://dx.doi.org/10.47102/https://doi.org/10.47102/annals-acadmedsg.2023113.
Повний текст джерелаАнотація:
Introduction: Automated machine learning (autoML) removes technical and technological barriers to building artificial intelligence models. We aimed to summarise the clinical applications of autoML, assess the capabilities of utilised platforms, evaluate the quality of the evidence trialling autoML, and gauge the performance of autoML platforms relative to conventionally developed models, as well as each other. Method: This review adhered to a prospectively registered protocol (PROSPERO identifier CRD42022344427). The Cochrane Library, Embase, MEDLINE and Scopus were searched from inception to 11 July 2022. Two researchers screened abstracts and full texts, extracted data and conducted quality assessment. Disagreement was resolved through discussion and as if required, arbitration by a third researcher. Results: There were 26 distinct autoML platforms featured in 82 studies. Brain and lung disease were the most common fields of study of 22 specialties. AutoML exhibited variable performance: area under the receiver operator characteristic curve (AUCROC) 0.35–1.00, F1-score 0.16–0.99, area under the precision-recall curve (AUPRC) 0.51–1.00. AutoML exhibited the highest AUCROC in 75.6% trials; the highest F1-score in 42.3% trials; and the highest AUPRC in 83.3% trials. In autoML platform comparisons, AutoPrognosis and Amazon Rekognition performed strongest with unstructured and structured data, respectively. Quality of reporting was poor, with a median DECIDE-AI score of 14 of 27. Conclusion: A myriad of autoML platforms have been applied in a variety of clinical contexts. The performance of autoML compares well to bespoke computational and clinical benchmarks. Further work is required to improve the quality of validation studies. AutoML may facilitate a transition to data-centric development, and integration with large language models may enable AI to build itself to fulfil user-defined goals.
48
Thirunavukarasu, Arun James, Kabilan Elangovan, Laura Gutierrez, Refaat Hassan, Yong Li, Ting Fang Tan, Haoran Cheng, Zhen Ling Teo, Gilbert Lim, and Daniel Shu Wei Ting. "Clinical performance of automated machine learning: A systematic review." Annals of the Academy of Medicine, Singapore 53, no. 3 - Correct DOI (March 27, 2024): 187–207. http://dx.doi.org/10.47102/annals-acadmedsg.2023113.
Повний текст джерелаАнотація:
Introduction: Automated machine learning (autoML) removes technical and technological barriers to building artificial intelligence models. We aimed to summarise the clinical applications of autoML, assess the capabilities of utilised platforms, evaluate the quality of the evidence trialling autoML, and gauge the performance of autoML platforms relative to conventionally developed models, as well as each other. Method: This review adhered to a prospectively registered protocol (PROSPERO identifier CRD42022344427). The Cochrane Library, Embase, MEDLINE and Scopus were searched from inception to 11 July 2022. Two researchers screened abstracts and full texts, extracted data and conducted quality assessment. Disagreement was resolved through discussion and as if required, arbitration by a third researcher. Results: There were 26 distinct autoML platforms featured in 82 studies. Brain and lung disease were the most common fields of study of 22 specialties. AutoML exhibited variable performance: area under the receiver operator characteristic curve (AUCROC) 0.35–1.00, F1-score 0.16–0.99, area under the precision-recall curve (AUPRC) 0.51–1.00. AutoML exhibited the highest AUCROC in 75.6% trials; the highest F1-score in 42.3% trials; and the highest AUPRC in 83.3% trials. In autoML platform comparisons, AutoPrognosis and Amazon Rekognition performed strongest with unstructured and structured data, respectively. Quality of reporting was poor, with a median DECIDE-AI score of 14 of 27. Conclusion: A myriad of autoML platforms have been applied in a variety of clinical contexts. The performance of autoML compares well to bespoke computational and clinical benchmarks. Further work is required to improve the quality of validation studies. AutoML may facilitate a transition to data-centric development, and integration with large language models may enable AI to build itself to fulfil user-defined goals.
49
Retzlaff, Carl Orge, Srijita Das, Christabel Wayllace, Payam Mousavi, Mohammad Afshari, Tianpei Yang, Anna Saranti, Alessa Angerschmid, Matthew E. Taylor, and Andreas Holzinger. "Human-in-the-Loop Reinforcement Learning: A Survey and Position on Requirements, Challenges, and Opportunities." Journal of Artificial Intelligence Research 79 (January 30, 2024): 359–415. http://dx.doi.org/10.1613/jair.1.15348.
Повний текст джерелаАнотація:
Artificial intelligence (AI) and especially reinforcement learning (RL) have the potential to enable agents to learn and perform tasks autonomously with superhuman performance. However, we consider RL as fundamentally a Human-in-the-Loop (HITL) paradigm, even when an agent eventually performs its task autonomously. In cases where the reward function is challenging or impossible to define, HITL approaches are considered particularly advantageous. The application of Reinforcement Learning from Human Feedback (RLHF) in systems such as ChatGPT demonstrates the effectiveness of optimizing for user experience and integrating their feedback into the training loop. In HITL RL, human input is integrated during the agent’s learning process, allowing iterative updates and fine-tuning based on human feedback, thus enhancing the agent’s performance. Since the human is an essential part of this process, we argue that human-centric approaches are the key to successful RL, a fact that has not been adequately considered in the existing literature. This paper aims to inform readers about current explainability methods in HITL RL. It also shows how the application of explainable AI (xAI) and specific improvements to existing explainability approaches can enable a better human-agent interaction in HITL RL for all types of users, whether for lay people, domain experts, or machine learning specialists. Accounting for the workflow in HITL RL and based on software and machine learning methodologies, this article identifies four phases for human involvement for creating HITL RL systems: (1) Agent Development, (2) Agent Learning, (3) Agent Evaluation, and (4) Agent Deployment. We highlight human involvement, explanation requirements, new challenges, and goals for each phase. We furthermore identify low-risk, high-return opportunities for explainability research in HITL RL and present long-term research goals to advance the field. Finally, we propose a vision of human-robot collaboration that allows both parties to reach their full potential and cooperate effectively.
50
Gao, Hongmin, Zhaofeng Ma, Shoushan Luo, Yanping Xu, and Zheng Wu. "BSSPD: A Blockchain-Based Security Sharing Scheme for Personal Data with Fine-Grained Access Control." Wireless Communications and Mobile Computing 2021 (February 19, 2021): 1–20. http://dx.doi.org/10.1155/2021/6658920.
Повний текст джерелаАнотація:
Privacy protection and open sharing are the core of data governance in the AI-driven era. A common data-sharing management platform is indispensable in the existing data-sharing solutions, and users upload their data to the cloud server for storage and dissemination. However, from the moment users upload the data to the server, they will lose absolute ownership of their data, and security and privacy will become a critical issue. Although data encryption and access control are considered up-and-coming technologies in protecting personal data security on the cloud server, they alleviate this problem to a certain extent. However, it still depends too much on a third-party organization’s credibility, the Cloud Service Provider (CSP). In this paper, we combined blockchain, ciphertext-policy attribute-based encryption (CP-ABE), and InterPlanetary File System (IPFS) to address this problem to propose a blockchain-based security sharing scheme for personal data named BSSPD. In this user-centric scheme, the data owner encrypts the sharing data and stores it on IPFS, which maximizes the scheme’s decentralization. The address and the decryption key of the shared data will be encrypted with CP-ABE according to the specific access policy, and the data owner uses blockchain to publish his data-related information and distribute keys for data users. Only the data user whose attributes meet the access policy can download and decrypt the data. The data owner has fine-grained access control over his data, and BSSPD supports an attribute-level revocation of a specific data user without affecting others. To further protect the data user’s privacy, the ciphertext keyword search is used when retrieving data. We analyzed the security of the BBSPD and simulated our scheme on the EOS blockchain, which proved that our scheme is feasible. Meanwhile, we provided a thorough analysis of the storage and computing overhead, which proved that BSSPD has a good performance.