Journal articles on the topic 'Virtual knowledge graphs (VKGs)'
To see the other types of publications on this topic, follow the link: Virtual knowledge graphs (VKGs).
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 38 journal articles for your research on the topic 'Virtual knowledge graphs (VKGs).'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Xiao, Guohui, Linfang Ding, Benjamin Cogrel, and Diego Calvanese. "Virtual Knowledge Graphs: An Overview of Systems and Use Cases." Data Intelligence 1, no. 3 (June 2019): 201–23. http://dx.doi.org/10.1162/dint_a_00011.
Full textAbstract:
In this paper, we present the virtual knowledge graph (VKG) paradigm for data integration and access, also known in the literature as Ontology-based Data Access. Instead of structuring the integration layer as a collection of relational tables, the VKG paradigm replaces the rigid structure of tables with the flexibility of graphs that are kept virtual and embed domain knowledge. We explain the main notions of this paradigm, its tooling ecosystem and significant use cases in a wide range of applications. Finally, we discuss future research directions.
2
Baclawski, Ken, Michael Bennett, Gary Berg-Cross, Todd Schneider, Ravi Sharma, Janet Singer, and Ram D. Sriram. "Ontology summit 2020 communiqué: Knowledge graphs." Applied Ontology 16, no. 2 (April 27, 2021): 229–47. http://dx.doi.org/10.3233/ao-210249.
Full textAbstract:
An increasing amount of data is now available from public and private sources. Furthermore, the types, formats, and number of sources of data are also increasing. Techniques for extracting, storing, processing, and analyzing such data have been developed in the last few years for managing this bewildering variety based on a structure called a knowledge graph. Industry has devoted a great deal of effort to the development of knowledge graphs, and knowledge graphs are now critical to the functions of intelligent virtual assistants such as Siri, Alexa, and Google Assistant. The goal of the Ontology Summit 2020 was to understand not only what knowledge graphs are but also where they originated, why they are so popular, the current issues, and their future prospects. The summit sessions examined many examples of knowledge graphs and surveyed the relevant standards that exist and are in development for knowledge graphs. The purpose of this Communiqué is to summarize our understanding from the Summit in order to foster research and development of knowledge graphs.
3
Ding, Linfang, Guohui Xiao, Albulen Pano, Claus Stadler, and Diego Calvanese. "Towards the next generation of the LinkedGeoData project using virtual knowledge graphs." Journal of Web Semantics 71 (November 2021): 100662. http://dx.doi.org/10.1016/j.websem.2021.100662.
Full text
4
Kurniawan, Kabul, Andreas Ekelhart, Elmar Kiesling, Dietmar Winkler, Gerald Quirchmayr, and A. Min Tjoa. "VloGraph: A Virtual Knowledge Graph Framework for Distributed Security Log Analysis." Machine Learning and Knowledge Extraction 4, no. 2 (April 11, 2022): 371–96. http://dx.doi.org/10.3390/make4020016.
Full textAbstract:
The integration of heterogeneous and weakly linked log data poses a major challenge in many log-analytic applications. Knowledge graphs (KGs) can facilitate such integration by providing a versatile representation that can interlink objects of interest and enrich log events with background knowledge. Furthermore, graph-pattern based query languages, such as SPARQL, can support rich log analyses by leveraging semantic relationships between objects in heterogeneous log streams. Constructing, materializing, and maintaining centralized log knowledge graphs, however, poses significant challenges. To tackle this issue, we propose VloGraph—a distributed and virtualized alternative to centralized log knowledge graph construction. The proposed approach does not involve any a priori parsing, aggregation, and processing of log data, but dynamically constructs a virtual log KG from heterogeneous raw log sources across multiple hosts. To explore the feasibility of this approach, we developed a prototype and demonstrate its applicability to three scenarios. Furthermore, we evaluate the approach in various experimental settings with multiple heterogeneous log sources and machines; the encouraging results from this evaluation suggest that the approach can enable efficient graph-based ad-hoc log analyses in federated settings.
5
Zhang, Yunhao, Jun Zhu, Qing Zhu, Yakun Xie, Weilian Li, Lin Fu, Junxiao Zhang, and Jianmei Tan. "The construction of personalized virtual landslide disaster environments based on knowledge graphs and deep neural networks." International Journal of Digital Earth 13, no. 12 (June 4, 2020): 1637–55. http://dx.doi.org/10.1080/17538947.2020.1773950.
Full text
6
Debruyne, Christophe, Gary Munnelly, Lynn Kilgallon, Declan O’Sullivan, and Peter Crooks. "Creating a Knowledge Graph for Ireland’s Lost History: Knowledge Engineering and Curation in the Beyond 2022 Project." Journal on Computing and Cultural Heritage 15, no. 2 (June 30, 2022): 1–25. http://dx.doi.org/10.1145/3474829.
Full textAbstract:
The Beyond 2022 project aims to create a virtual archive by digitally reconstructing and digitizing historical records lost in a catastrophic fire which consumed items in the Public Record Office of Ireland in 1922. The project is developing a knowledge graph (KG) to facilitate information retrieval and discovery over the reconstructed items. The project decided to adopt Semantic Web technologies to support its distributed KG and reasoning. In this article, we present our approach to KG generation and management. We elaborate on how we help historians contribute to the KG (via a suite of spreadsheets) and its ontology. We furthermore demonstrate how we use named graphs to store different versions of factoids and their provenance information and how these are serviced in two different endpoints. Modeling data in this manner allows us to acknowledge that history is, to some extent, subjective and different perspectives can exist in parallel. The construction of the KG is driven by competency questions elicited from subject matter experts within the consortium. We avail of CIDOC-CRM as our KG’s foundation, though we needed to extend this ontology with various qualifiers (types) and relations to support the competency questions. We illustrate how one can explore the KG to gain insights and answer questions. We conclude that CIDOC-CRM provides an adequate, albeit complex, foundation for the KG and that named graphs and Linked Data principles are a suitable mechanism to manage sets of factoids and their provenance.
7
Beden, Sadeer, Qiushi Cao, and Arnold Beckmann. "SCRO: A Domain Ontology for Describing Steel Cold Rolling Processes towards Industry 4.0." Information 12, no. 8 (July 29, 2021): 304. http://dx.doi.org/10.3390/info12080304.
Full textAbstract:
This paper introduces the Steel Cold Rolling Ontology (SCRO) to model and capture domain knowledge of cold rolling processes and activities within a steel plant. A case study is set up that uses real-world cold rolling data sets to validate the performance and functionality of SCRO. This includes using the Ontop framework to deploy virtual knowledge graphs for data access, data integration, data querying, and condition-based maintenance purposes. SCRO is evaluated using OOPS!, the ontology pitfall detection system, and feedback from domain experts from Tata Steel.
8
Palha, Sônia. "Students learning with interactive virtual math: an exploratory study in the classroom." Ensino e Tecnologia em Revista 1, no. 1 (September 6, 2017): 80. http://dx.doi.org/10.3895/etr.v1n1.5990.
Full textAbstract:
Interactive Virtual Math (IVM) is a visualization tool to support secondary school students’ learning of graphs by dynamic events. In the prototype version students construct a graph and try to improve it themselves and with the feedback of the tool. In a small-scale experiment, which involved four classes at secondary and tertiary education and their mathematics teachers we investigated how the students used the tool in the classroom. In this study we focus on the students learning experience and the results are expected to provide knowledge and directions for further development of the tool. The corpus data consists of self-reported questionnaires and lessons observations. One main finding is that students, at different school levels, find the tool useful to construct or improve graphical representations and it can help to get a better understanding of the subject. The tool features that helped students most were the self-construction of the graphs and to get feedback about their own graph at the end. Other findings are that the students can work independently with the tool and we know more about the tool features that are attractive or need to be improved.
9
Varanka, Dalia E. "A Prototype Geospatial Knowledge Graph for National Topographic Mapping." Abstracts of the ICA 2 (October 9, 2020): 1. http://dx.doi.org/10.5194/ica-abs-2-40-2020.
Full textAbstract:
Abstract. Knowledge graphs (KG) are a virtual layer connecting disparate databases into an interoperable framework. Though the application of KGs for enterprises are increasing, geospatial KG design is not common. This presentation describes U.S. Geological Survey (USGS) research to build KGs for integrating geospatial and non-spatial attribute semantics of topographic data. Those geographic information system databases are composed of various feature types and metadata attributes organized various themes and stored in different data formats, such as geodatabases, flat-file spreadsheets, and raster images. The system being created tests two research objectives: 1) the feasibility of semantic technology approaches for geospatial data within the context of national topographic data and 2) the contribution to building a body of knowledge about system architecture for geospatial ontologies and linked open data. This presentation discusses the context of topographic data semantics, the problem and aims of building the system, and the integrated KG framework. The basic workflow and operations of the system architecture consisting of open-source software are described. The architecture modifies existing software with unique solutions such as performing GeoSPAQL queries with Postgres, a relational table datastore, and a map interface with extensions to support linked data queries as browseable graphs. As public spatial data infrastructure, the system is made available as a Docker Container on GitHub.
10
Ronzhin, Folmer, Maria, Brattinga, Beek, Lemmens, and van’t Veer. "Kadaster Knowledge Graph: Beyond the Fifth Star of Open Data." Information 10, no. 10 (October 9, 2019): 310. http://dx.doi.org/10.3390/info10100310.
Full textAbstract:
After more than a decade, the supply-driven approach to publishing public (open) data has resulted in an ever-growing number of data silos. Hundreds of thousands of datasets have been catalogued and can be accessed at data portals at different administrative levels. However, usually, users do not think in terms of datasets when they search for information. Instead, they are interested in information that is most likely scattered across several datasets. In the world of proprietary in-company data, organizations invest heavily in connecting data in knowledge graphs and/or store data in data lakes with the intention of having an integrated view of the data for analysis. With the rise of machine learning, it is a common belief that governments can improve their services, for example, by allowing citizens to get answers related to government information from virtual assistants like Alexa or Siri. To provide high-quality answers, these systems need to be fed with knowledge graphs. In this paper, we share our experience of constructing and using the first open government knowledge graph in the Netherlands. Based on the developed demonstrators, we elaborate on the value of having such a graph and demonstrate its use in the context of improved data browsing, multicriteria analysis for urban planning, and the development of location-aware chat bots.
11
Francia, Ponti, Frizziero, and Liverani. "Virtual Mechanical Product Disassembly Sequences Based on Disassembly Order Graphs and Time Measurement Units." Applied Sciences 9, no. 17 (September 3, 2019): 3638. http://dx.doi.org/10.3390/app9173638.
Full textAbstract:
Recently, the approach that defines the total life cycle assessment (LCA) and the end of life (EoL) in the early design phases is becoming even more promising. Literature evidences many advantages in terms of the saving of costs and time and in the fluent organization of the whole design process. Design for disassembly (DfD) offers the possibility of reducing the time and cost of disassembling a product and accounts for the reusing of parts and of the dismantling of parts, joints, and materials. The sequence of disassembly is the ordered way to extract parts from an assembly and is a focal item in DfD because it can deeply influence times and operations. In this paper, some disassembly sequences are evaluated, and among them, two methods for defining an optimal sequence are provided and tested on a case study of a mechanical assembly. A further sequence of disassembly is provided by the authors based on experience and personal knowledge. All three are analyzed by the disassembly order graph (DOG) approach and compared. The operations evaluated have been converted in time using time measurement units (TMUs). As result, the best sequence has been highlighted in order to define a structured and efficient disassembly.
12
Agosti, Maristella, Maurizio Atzori, Paolo Ciaccia, and Letizia Tanca. "Report on SEBD 2020." ACM SIGIR Forum 54, no. 2 (December 2020): 1–5. http://dx.doi.org/10.1145/3483382.3483392.
Full textAbstract:
This paper reports on the 28th Italian Symposium on Advanced Database Systems (SEBD 2020), held online as a virtual conference from the 21st to the 24th of June 2020. The topics that were addressed in this edition of the conference were organized in the sessions: ontologies and data integration, anomaly detection and dependencies, text analysis and search, deep learning, noSQL data, trajectories and diffusion, health and medicine, context and ranking, social and knowledge graphs, multimedia content analysis, security issues, and data mining.
13
Nazarenko, Artem A., Joao Sarraipa, Luis M. Camarinha-Matos, Oscar Garcia, and Ricardo Jardim-Goncalves. "Semantic Data Management for a Virtual Factory Collaborative Environment." Applied Sciences 9, no. 22 (November 16, 2019): 4936. http://dx.doi.org/10.3390/app9224936.
Full textAbstract:
Recent developments in the area of cyber-physical systems (CPSs) and Internet of Things (IoT) are among the drivers for the emergence of the Industry 4.0 concept, setting new requirements for the architecture, technology, and design approaches of modern industrial systems. Industry 4.0 assumes a higher level of intelligence, and thus autonomy of the systems and subsystems, and a larger focus on the analysis of gathered data for further utilization. The Virtual Factory Open Operating System (vf-OS) project is intended to respond to some of these key challenges, in particular for the smart factory application domain. Complementarily, data and knowledge storage and processing are also in the scope of vf-OS. This article introduces the semantic management component of vf-OS, which aims to analyze the interrelations among stored entities, as well as to define the closeness among them to generate meaningful suggestions, which can be later used by other subsystems or operators in a user-friendly way. The semantic managing system makes use of non relational approaches, namely a graph database, which enables data to be represented as graphs for further semantic querying. The developed prototype and an illustrative application case are also presented.
14
Abdulgalimov, G. L., E. G. Kholmogorova, and M. S. Turpalova. "TRAINING TECHNIQUE FOR SUBJECT-ORIENTED PROGRAMMING IN THE LABVIEW SYSTEM." Informatics and education, no. 7 (October 4, 2019): 63–68. http://dx.doi.org/10.32517/0234-0453-2019-34-7-63-68.
Full textAbstract:
The article proposes a methodological approach to the training of future teachers of physics and informatics in subject-oriented programming using the LabVIEW system. The methodological support for the introductory lesson for learning how to get started in the LabVIEW system is considered, and an example of laboratory work on the development of a virtual device for determining the additional resistance to the LED is given. Laboratory work consists of several parts: theme, goals, theory on physics for solving tasks in the current work, stages of work in the LabVIEW system, tasks to control knowledge and skills. The methodology for the training in subject-oriented programming includes, in addition to the laboratory workshop, tasks to design more complex virtual devices as part of undergraduate works. In these works, in addition to the development of one or more virtual devices, it is proposed to solve various research problems using these devices. These research tasks are intended to confirm known physical laws, derive various constants and reference data, build graphs of physical dependencies, etc.
15
Cheatham, Deane B., and Sharolyn Converse Lane. "Differential Access Hypothesis: The Effects of Task and Informatior Type on the Validity of Knowledge Acquisition Methods." Proceedings of the Human Factors and Ergonomics Society Annual Meeting 46, no. 3 (September 2002): 487–91. http://dx.doi.org/10.1177/154193120204600357.
Full textAbstract:
The types of knowledge captured using three knowledge acquisition (KA) methods, conceptual graphs, backward thinking, and sorting tasks, were examined. One hundred and forty-four participants were assigned to one of four conditions: (a) procedural-spatial, (b) procedural-verbal, (c) declarative-spatial, and (d) declarative-verbal. Participants in procedural conditions learned a virtual environment's layout before performing one of three KA tasks. Participants in declarative conditions received a tutorial about McCune-Albright Syndrome before completing a KA task. The procedural and declarative information was presented either spatially or verbally, depending on the condition. The predictive validity of each KA method for each information type (procedural vs. declarative), task type (i.e., spatial vs. verbal), and combinations of information and task types was evaluated by comparing the accuracy of the knowledge depicted by KA methods to various performance measures. Findings indicated that both task type and information type affect the validity of KA methods for capturing knowledge structures.
16
Salcedo-Lagos, Pedro, Sergio Morales-Candia, Karina Fuentes-Riffo, Susan Rivera-Robles, and Cristian Sanhueza-Campos. "Teachers’ Perceptions Analysis on Students’ Emotions in Virtual Classes during COVID19 Pandemic: A Lexical Availability Approach." Sustainability 13, no. 11 (June 4, 2021): 6413. http://dx.doi.org/10.3390/su13116413.
Full textAbstract:
Virtual education has grown exponentially in the past year due to the global COVID19 pandemic. In this context, the exploration of teachers’ perceptions of their students’ emotions when using ICTs has become more relevant. The aim of this study was two-fold, on the one hand, to analyze how teachers perceived their students’ emotions and, on the other hand, to analyze the emotions teachers wanted to modulate in their students when using ICTs. To this end, an interpretative and comparative study was implemented using the Lexical Availability technique. The sample was formed by 178 Chilean teachers who took a lexical availability test. The analysis included general vocabulary through network graphs and a comparison across gender, academic background, school type and knowledge area. The results made it possible to identify the latent mental lexicon of teachers, revealing significant differences in the perception of emotions, according to gender and ICTs use and according to gender and knowledge area. The study further projects the potential of lexical availability to determine the emotions required by Affective Informatics in the adaptability of educational systems and to make adjustments to the instructional design.
17
Zhang, Xiao, Ying Zhi, Jiaqi Xu, and Lixia Han. "Digital Protection and Utilization of Architectural Heritage Using Knowledge Visualization." Buildings 12, no. 10 (October 4, 2022): 1604. http://dx.doi.org/10.3390/buildings12101604.
Full textAbstract:
Architectural heritage is a lively carrier of historical development, as well as providing a valuable resource for human society. Recently, however, the longevity of architectural heritage has been influenced and even threatened by natural and human factors. Furthermore, the future remains uncertain. Therefore, this study aimed to develop a comprehensive method, namely, digital protection and utilization based on knowledge visualization (DPUKV), to protect and utilize architectural heritage. The most important problem to solve involves transforming digital protection data into a digital inheritance culture. We constructed a technical framework of knowledge acquisition, knowledge reconstruction, knowledge innovation, and knowledge management using qualitative and vertical methods to form hierarchical digital resources of architectural heritage. In particular, the knowledge reconstruction converted tacit knowledge of architectural heritage into explicit knowledge via visualization technology, providing research materials for more scholars. In knowledge innovation, architectural heritage culture was excavated and inherited through knowledge graphs, digital displays, and cultural creation with virtual reality, augmented reality, etc. Furthermore, this method was validated over four years via architectural heritage in China as case studies. In this paper, the buildings of Qinglian Temple in Shanxi, China, are discussed in detail as a case study. The results indicated that this method was effective for preserving architectural heritage and is suitable for other cultural heritage. It is also helpful to improve the public’s protection of and interest in cultural heritage, especially architectural heritage.
18
Bhat, Vaibhav, Anita Yadav, Sonal Yadav, Dhivya Chandrasekaran, and Vijay Mago. "AdCOFE: Advanced Contextual Feature Extraction in conversations for emotion classification." PeerJ Computer Science 7 (December 9, 2021): e786. http://dx.doi.org/10.7717/peerj-cs.786.
Full textAbstract:
Emotion recognition in conversations is an important step in various virtual chatbots which require opinion-based feedback, like in social media threads, online support, and many more applications. Current emotion recognition in conversations models face issues like: (a) loss of contextual information in between two dialogues of a conversation, (b) failure to give appropriate importance to significant tokens in each utterance, (c) inability to pass on the emotional information from previous utterances. The proposed model of Advanced Contextual Feature Extraction (AdCOFE) addresses these issues by performing unique feature extraction using knowledge graphs, sentiment lexicons and phrases of natural language at all levels (word and position embedding) of the utterances. Experiments on emotion recognition in conversations datasets show that AdCOFE is beneficial in capturing emotions in conversations.
19
Zotov, Vladimir, Iman Ibrahim, Irina Petunina, and Yuliya Lazareva. "Engagement of Students in Data Visualization for the Purpose of E-Learning Improvement." International Journal of Emerging Technologies in Learning (iJET) 16, no. 02 (January 26, 2021): 46. http://dx.doi.org/10.3991/ijet.v16i02.18745.
Full textAbstract:
The study describes an approach to e-learning based on the Moodle platform that is used to visualize participation in the learning community and is proposed to be used to inform students and teachers about their involvement in the social learn-ing environment. The experiment involved 5 teachers and 3 experts who deter-mined the most significant visualization indicators for the virtual learning envi-ronment dashboards. There were 42 students aged 21 to 23. The virtual learning environment is based on the Moodle and Blackboard platforms that are common-ly used in universities. SocialWall allowed participants to perform actions in the social environment that are visualized in graphs under the specified criteria. A Wiki repository plugin was also added in order to accumulate student knowledge in shared structured documents stored in a shared repository. The relational data-base management system MySQL allows creation of additional relations, data-base design and administration. The visualization activities described in the study are based on modified state transition networks to analyze and visualize the stu-dent learning path. Student trajectory networks show the interaction of individual learners or groups with the course structure and material.
20
Yan, Surong, Kwei-Jay Lin, Xiaolin Zheng, and Haosen Wang. "LkeRec: Toward Lightweight End-to-End Joint Representation Learning for Building Accurate and Effective Recommendation." ACM Transactions on Information Systems 40, no. 3 (July 31, 2022): 1–28. http://dx.doi.org/10.1145/3486673.
Full textAbstract:
Explicit and implicit knowledge about users and items have been used to describe complex and heterogeneous side information for recommender systems (RSs). Many existing methods use knowledge graph embedding (KGE) to learn the representation of a user-item knowledge graph (KG) in low-dimensional space. In this article, we propose a lightweight end-to-end joint learning framework for fusing the tasks of KGE and RSs at the model level. Our method proposes a lightweight KG embedding method by using bidirectional bijection relation-type modeling to enable scalability for large graphs while using self-adaptive negative sampling to optimize negative sample generating. Our method further generates the integrated views for users and items based on relation-types to explicitly model users’ preferences and items’ features, respectively. Finally, we add virtual “recommendation” relations between the integrated views of users and items to model the preferences of users on items, seamlessly integrating RS with user-item KG over a unified graph. Experimental results on multiple datasets and benchmarks show that our method can achieve a better accuracy of recommendation compared with existing state-of-the-art methods. Complexity and runtime analysis suggests that our method can gain a lower time and space complexity than most of existing methods and improve scalability.
21
Imonje, Rosemary Khitieyi. "Undergraduate Student Perceptions on Virtual Online Versus On-campus Teaching – Learning Modes of Delivery and Assessment in Public Universities." Journal of Education and Development 6, no. 5 (December 5, 2022): 25. http://dx.doi.org/10.20849/jed.v6i5.1308.
Full textAbstract:
On the onset of COVID 19 Pandemic, educational institutions took up either virtual online or blended modes of delivery and learning; as an intervention of solving programmed learning retention, transition and completion concerns among students in institutions of higher learning. In spite of the fact that online learning faces access learning challenges; there seems to be myriad issues with online assessment procedures. Despite this, there is still much debate on whether online assessments, particularly examinations, offer the same academic integrity as the traditional on- campus face to face paper assessment (Paulli and Ferrelli 2020). The purpose of this study was to assess the perceptions of undergraduate students on virtual online versus on-campus teaching- learning mode of delivery and assessment. The study anchored on descriptive survey design. A sample of 200 students across different years of study at the Faculty of Education, Kikuyu Campus, University of Nairobi, were targeted. The study used online google form to collect data. Descriptive statistics were applied in data analysis. Data was presented through tables, percentages and graphs. 140 students participated in the study. 86.1% of the respondents were in learning session and 13.9% were not in session. The most preferred mode of delivery is face to face on campus with 69.7 % responses, Virtual online – 21.8% and both, was 8.5%. The major reason for preference was that there are subjects such as mathematics, Kiswahili and English which require physical classroom student – lecturer real interactions and immediate instructional feedback for quality acquisition of skills, knowledge and values; which is completely lacking in online virtual learning; and that online virtual pedagogy flow is usually interrupted with network issues causing in-consistency in coverage of course content. Blended learning was recommended for courses that require intense practical sessions, while the other courses can take up online mode of pedagogy. Conclusively, there is need for further review of online pedagogical approaches, and curriculum policies in order to have aligned online assessments that consider equity in access to online pedagogy, in line with student socio-economic backgrounds and conducive learning environments. More research is needed for effective online pedagogical alignments.
22
Lampropoulos, Georgios, Euclid Keramopoulos, and Konstantinos Diamantaras. "Semantically Enriched Augmented Reality Applications: A Proposed System Architecture and a Case Study." International Journal of Recent Contributions from Engineering, Science & IT (iJES) 10, no. 01 (March 16, 2022): 29–46. http://dx.doi.org/10.3991/ijes.v10i01.27463.
Full textAbstract:
With a view to creating a mixed reality that combines coexisting real and virtual objects and to providing users with real-time access to information in an interactive manner, augmented reality enriches users’ physical environment by incorporating digital and real objects and rendering them in the physical environment in the proper time and spatial framework. Due to its nature, augmented reality can be combined with and exploit other innovative technologies in order to improve its efficiency and potentials. Some such technologies are semantic web, knowledge graphs and deep learning. The study main purpose and contribution is to showcase the benefits of developing semantically enriched augmented reality applications and to present a system architecture for developing such applications as well as to showcase and assess an augmented reality application developed following the proposed architecture. The specific application aims at facilitating end-users’ day-to-day activities, enhancing the learning and informing process and increasing user experience (UX). The results of this study showcase that such applications have the potential to be applied and positively affect various sectors and that they can be a useful, flexible, interactive and informative tool for end-users.
23
Aguilera-Alvarez, Juan, José Padilla-Medina, Coral Martínez-Nolasco, Víctor Samano-Ortega, Micael Bravo-Sanchez, and Juan Martínez-Nolasco. "Development of a Didactic Educational Tool for Learning Fuzzy Control Systems." Mathematical Problems in Engineering 2021 (July 30, 2021): 1–17. http://dx.doi.org/10.1155/2021/3158342.
Full textAbstract:
This paper presents the development of a virtual didactic tool for students of mechatronic engineering taking an intelligent system course. The objective of the tool is for students to learn the structures for fuzzy control systems. This tool makes it easier for students to understand the behavior of the membership functions of input and output variables, the evaluation of the set of fuzzy rules, and the method of defuzzification, giving the students the possibility of applying a fuzzy controller in industrial processes using a data acquisition board. The proposed tool was developed with the virtual instrumentation software LabVIEW. It has the advantage that students can manipulate the internal structure of the fuzzy logic control system in a unique window where students can analyze the behavior of internal signals by looking at the response graphs. The fuzzy controller can be easily translated to a real application by using LabVIEW compatible hardware. To have feedback from students on the use of the tool and to understand if this tool allows an improvement in their academic performance, a 2-hour workshop on the proposed application was given to a group of 93 students. At the end of the workshop, a knowledge assessment and a perception survey were applied to the participants. The academic performance achieved by students who were given the workshop using the proposed teaching tool was compared with the academic performance of students who witnessed the workshop using Matlab tools. The statistical analysis of the results obtained for the knowledge assessment shows that the students that had taken the workshop using the proposed teaching tool had better compression of the topic compared to the students that had taken the workshop using the Fuzzy Logic Toolbox provided by Matlab MathWorks. The students that had taken the workshop using the proposed teaching tool obtained a mean grade of 89.63/100, while students that had taken the workshop using Matlab’s tools obtained a mean grade of 69.85/100. Also, the students’ perception of the proposed tool was that it allowed the design of fuzzy control systems in a simple and intuitive way.
24
Židek, Kamil, Ján Piteľ, Milan Adámek, Peter Lazorík, and Alexander Hošovský. "Digital Twin of Experimental Smart Manufacturing Assembly System for Industry 4.0 Concept." Sustainability 12, no. 9 (May 1, 2020): 3658. http://dx.doi.org/10.3390/su12093658.
Full textAbstract:
This article deals with the creation of a digital twin for an experimental assembly system based on a belt conveyor system and an automatized line for quality production check. The point of interest is a Bowden holder assembly from a 3D printer, which consists of a stepper motor, plastic components, and some fastener parts. The assembly was positioned in a fixture with ultra high frequency (UHF) tags and internet of things (IoT) devices for identification of status and position. The main task was parts identification and inspection, with the synchronization of all data to a digital twin model. The inspection system consisted of an industrial vision system for dimension, part presence, and errors check before and after assembly operation. A digital twin is realized as a 3D model, created in CAD design software (CDS) and imported to a Tecnomatix platform to simulate all processes. Data from the assembly system were collected by a programmable logic controller (PLC) system and were synchronized by an open platform communications (OPC) server to a digital twin model and a cloud platform (CP). Digital twins can visualize the real status of a manufacturing system as 3D simulation with real time actualization. Cloud platforms are used for data mining and knowledge representation in timeline graphs, with some alarms and automatized protocol generation. Virtual digital twins can be used for online optimization of an assembly process without the necessity to stop that is involved in a production line.
25
Yu-Che Huang, Yu-Che Huang, Chin-Feng Lai Yu-Che Huang, 黃國豪 Chin-Feng Lai, and Yueh-Ming Huang Gwo-Haur Hwang. "Explore Behavior Pattern in an Associated AR English Learning System Consider Different Human Factors." 網際網路技術學刊 23, no. 4 (July 2022): 659–67. http://dx.doi.org/10.53106/160792642022072304002.
Full textAbstract:
<p>In this study, an associated AR English learning system (AES) was developed for elementary children. Different from a general AR English learning system, when learners scan the AR target object, AES will provide associated virtual learning materials with the target object, including vocabulary, phrase and example sentences. At the same time, all the operational processes of the learner will be recorded in database within coding scheme by the system. The aim of this research is exploring learners’ behavior differences through analyzed their behavior log considering the human factors with gender and prior knowledge. One thing worth noting is, according to the result of the analysis, we found that learners can get a better performance in class when they are learning with an associated AR English learning system than a general AR English learning system. In addition, through observe the behavior pattern associated graphs, we found that female learners lost the scan directions of AR learning target more often than male learners. However, the female learners learning with an AR target more carefully and detailed than male learners. According to the results of this study, it is shown that when learning English through AR technology, the gender difference is an important impact factor. Therefore, when teachers and AR developers want to use AR to assist English learning in the future, they must pay special attention to this.</p> <p> </p>
26
Jafri, Lena, Muhammad Abbas Abid, Javeria Rehman, Sibtain Ahmed, Ghazanfar Abbas, Howrah Ali, Fatima Kanani, et al. "Development of a virtual classroom for pre-analytical phase of laboratory medicine for undergraduate medical students using the Delphi technique." PLOS ONE 17, no. 4 (April 6, 2022): e0264447. http://dx.doi.org/10.1371/journal.pone.0264447.
Full textAbstract:
Background Amongst the pre-analytical, analytical, and post-analytical phase of laboratory testing, pre-analytical phase is the most error-prone. Knowledge gaps in understanding of pre-analytical factors are identified in the clinical years amongst undergraduate students due to lack of formal teaching modules on the pre-analytical phase. This study was conducted to seek experts’ consensus in Clinical Chemistry on learning objectives and contents using the Delphi technique with an aim to develop an asynchronous virtual classroom for teaching pre-analytical factors of laboratory testing. Methods A mixed method study was conducted at the Aga Khan University. A questionnaire comprising of 16 learning objectives and their associated triggers was developed on Google Docs for developing the case vignettes. A four-point Likert Scale, which included strongly agree, agree, disagree and strongly disagree, was utilized for the learning objectives. An open-ended question was included for experts to suggest new items for inclusion. A cut off of at least 75% agreement was set to establish consensus on each item. A total of 17 Chemical Pathology faculty from 13 institutions across Pakistan were invited to participate in the first round of Delphi. Similar method of response was used in round two to establish consensus on the newly identified items suggested by the faculty in round 1. Later, the agreed-upon objectives and triggers were used to develop interactive scenarios over Moodle to concurrently test and teach medical students in a nonchalant manner. Results A total of 17 responses were received in Round 1 of the Delphi process (response rate = 100%), while 12 responses were received in Round 2 (response rate = 71%). In round 1, all 16 learning objectives reached the required consensus (≥ 75%) with no additional learning objectives suggested by the experts. Out of 75 triggers in round 1, 61 (81.3%) reached the consensus to be included while 39 were additionally suggested. In 2nd round, 17 out of 39 newly suggested triggers met the desired consensus. 14 triggers did not reach the consensus after two rounds, and were therefore eliminated. The virtual classroom developed using the agreed-upon learning objectives and triggers consisted of 20 items with a total score of 31 marks. The questions included multiple choice questions, fill in the blanks, drag and drop sequences and read-and-answer comprehensions. Specific learning points were included after each item and graphs and pictures were included for a vibrant experience. Conclusion We developed an effective and interactive virtual session with expert consensus on the pre-analytical phase of laboratory testing for undergraduate medical students which can be used for medical technologist, graduate students and fellows in Chemical Pathology.
27
R., Priyadarshini, Latha Tamilselvan, and Rajendran N. "Semantic tracking and recommendation using fourfold similarity measure from large scale data using hadoop distributed framework in cloud." International Journal of Intelligent Unmanned Systems 7, no. 4 (October 14, 2019): 189–208. http://dx.doi.org/10.1108/ijius-07-2019-0030.
Full textAbstract:
Purpose The purpose of this paper is to propose a fourfold semantic similarity that results in more accuracy compared to the existing literature. The change detection in the URL and the recommendation of the source documents is facilitated by means of a framework in which the fourfold semantic similarity is implied. The latest trends in technology emerge with the continuous growth of resources on the collaborative web. This interactive and collaborative web pretense big challenges in recent technologies like cloud and big data. Design/methodology/approach The enormous growth of resources should be accessed in a more efficient manner, and this requires clustering and classification techniques. The resources on the web are described in a more meaningful manner. Findings It can be descripted in the form of metadata that is constituted by resource description framework (RDF). Fourfold similarity is proposed compared to three-fold similarity proposed in the existing literature. The fourfold similarity includes the semantic annotation based on the named entity recognition in the user interface, domain-based concept matching and improvised score-based classification of domain-based concept matching based on ontology, sequence-based word sensing algorithm and RDF-based updating of triples. The aggregation of all these similarity measures including the components such as semantic user interface, semantic clustering, and sequence-based classification and semantic recommendation system with RDF updating in change detection. Research limitations/implications The existing work suggests that linking resources semantically increases the retrieving and searching ability. Previous literature shows that keywords can be used to retrieve linked information from the article to determine the similarity between the documents using semantic analysis. Practical implications These traditional systems also lack in scalability and efficiency issues. The proposed study is to design a model that pulls and prioritizes knowledge-based content from the Hadoop distributed framework. This study also proposes the Hadoop-based pruning system and recommendation system. Social implications The pruning system gives an alert about the dynamic changes in the article (virtual document). The changes in the document are automatically updated in the RDF document. This helps in semantic matching and retrieval of the most relevant source with the virtual document. Originality/value The recommendation and detection of changes in the blogs are performed semantically using n-triples and automated data structures. User-focussed and choice-based crawling that is proposed in this system also assists the collaborative filtering. Consecutively collaborative filtering recommends the user focussed source documents. The entire clustering and retrieval system is deployed in multi-node Hadoop in the Amazon AWS environment and graphs are plotted and analyzed.
28
DorMohammdi, Saber, Cody Godines, Frank Abdi, Dade Huang, Massimiliano Repupilli, and Levon Minnetyan. "Damage-tolerant composite design principles for aircraft components under fatigue service loading using multi-scale progressive failure analysis." Journal of Composite Materials 51, no. 15 (March 20, 2017): 2181–202. http://dx.doi.org/10.1177/0021998317691812.
Full textAbstract:
Virtual testing has lately gained widespread acceptance among scientists as a simple, accurate, and reproducible method to determine the mechanical properties of heterogeneous microstructures, early in the production process. As a result of the rapid expansion of the use of composites in aerospace design, virtual testing techniques are, in fact, deemed extremely useful to eliminate unnecessary tests and to reduce cost and time associated with generating allowables for lengthy lifing analyses of structures. Leveraging on a limited set of experimental data, a Progressive Failure Analysis can accurately predict the life and safety of a component/assembly, simply tapping on the physics of its micro-/macro- mechanics material properties, manufacturing processes, and service environments. The robust methodology is showcased using blind predictions of fatigue stiffness degradation and residual strength in tension and compression after fatigue compared with test data from Lockheed Martin Aeronautics and Air Force Research Laboratory). The multi-scale progressive failure analysis methodology in the GENOA software considers uncertainties and defects and evaluated the damage and fracture evolution of three IM7-977-3 laminated composite layups at room temperature. The onset and growth of composite damage was predicted and compared with X-ray CT. After blind predictions, recalibrations were performed with knowledge of the test data using the same set of inputs for all layups and simulations. Damage and fracture mechanism evolution/tracking throughout the cyclic loading is achieved by an integrated multi-scale progressive failure analysis extended FEM solution: (a) damage tracking predicts percentage contributing translaminar and interlaminar failure type, initiation, propagation, crack growth path, and observed shift in failure modes, and (b) fracture mechanics (VCCT, DCZM) predicts crack growth (Crack Tip Energy Release Rate vs. Crack Length), and delamination. The predictive methodology is verified using a building block validation strategy that uses: (a) composite material characterization and qualification (MCQ) software, and (b) the GENOA multi-scale progressive failure analysis fatigue life, stiffness degradation, and post-fatigue strength predictions for open-hole specimens under tension/compression at RTD. The unidirectional tension, compression, and in-plane shear lamina properties supplied by Lockheed Martin Aeronautics and the Air Force Research Laboratory (based on the D3039, D638, D3518 tests) were used by MCQ to reverse engineer effective fiber and matrix static and fatigue properties for the IM7-977-3 material system. The use of constituent properties identified the root cause problem for composite failure and enabled the detection of damage at the micro-scale of the material where damage is incepted. For all three case studies (namely, layups [0/45/90/−45]2s, [+60, 0, −60]3s, and [+30, +60, 90, −60, −30]2s), the blind predictions on the fatigue stiffness degradation and residual strength of the open-hole coupon in tension/compression under cyclic loading (with R = 0.1) at RTD were evaluated using a FE mesh (made of 2k shell elements), in which only one shell element, containing all plies, was employed through the thickness. The results of all analyses correlated very well with the tests, including the damage micro-graphs generated during the cyclic loading.
29
Pellegrino, Maria Angela, Vittorio Scarano, and Carmine Spagnuolo. "Move cultural heritage knowledge graphs in everyone’s pocket." Semantic Web, August 29, 2022, 1–37. http://dx.doi.org/10.3233/sw-223117.
Full textAbstract:
Last years witnessed a shift from the potential utility in digitisation to a crucial need to enjoy activities virtually. In fact, before 2019, data curators recognised the utility of performing data digitisation, while during the lockdown caused by the COVID-19, investing in virtual and remote activities to make culture survive became crucial as no one could enjoy Cultural Heritage in person. The Cultural Heritage community heavily invested in digitisation campaigns, mainly modelling data as Knowledge Graphs by becoming one of the most successful Semantic Web technologies application domains. Despite the vast investment in Cultural Heritage Knowledge Graphs, the syntactic complexity of RDF query languages, e.g., SPARQL, negatively affects and threatens data exploitation, risking leaving this enormous potential untapped. Thus, we aim to support the Cultural Heritage community (and everyone interested in Cultural Heritage) in querying Knowledge Graphs without requiring technical competencies in Semantic Web technologies. We propose an engaging exploitation tool accessible to all without losing sight of developers’ technological challenges. Engagement is achieved by letting the Cultural Heritage community leave the passive position of the visitor and actively create their Virtual Assistant extensions to exploit proprietary or public Knowledge Graphs in question-answering. By accessible to all, we mean that the proposed software framework is freely available on GitHub and Zenodo with an open-source license. We do not lose sight of developers’ technical challenges, which are carefully considered in the design and evaluation phases. This article first analyses the effort invested in publishing Cultural Heritage Knowledge Graphs to quantify data developers can rely on in designing and implementing data exploitation tools in this domain. Moreover, we point out challenges developers may face in exploiting them in automatic approaches. Second, it presents a domain-agnostic Knowledge Graph exploitation approach based on virtual assistants as they naturally enable question-answering features where users formulate questions in natural language directly by their smartphones. Then, we discuss the design and implementation of this approach within an automatic community-shared software framework (a.k.a. generator) of virtual assistant extensions and its evaluation in terms of performance and perceived utility according to end-users. Finally, according to a taxonomy of the Cultural Heritage field, we present a use case for each category to show the applicability of the proposed approach in the Cultural Heritage domain. In overviewing our analysis and the proposed approach, we point out challenges that a developer may face in designing virtual assistant extensions to query Knowledge Graphs, and we show the effect of these challenges in practice.
30
Ding, Linfang, Guohui Xiao, Albulen Pano, Claus Stadler, and Diego Calvanese. "Towards the Next Generation of the Linkedgeodata Project Using Virtual Knowledge Graphs." SSRN Electronic Journal, 2021. http://dx.doi.org/10.2139/ssrn.3950411.
Full text
31
Kalnoi, S. P. "“PRISM OF KNOWLEDGE” AS A VIRTUAL FORM OF ORGANIZATION OF E-NETWORK KNOWLEDGE BASE IN EDUCATION." Scientific Notes of Junior Academy of Sciences of Ukraine, no. 21-22 (2021). http://dx.doi.org/10.51707/2618-0529-2021-21_22-07.
Full textAbstract:
This is a brief description of the current state of the use of software and information tools ICT in the formation of knowledge bases in education. Examples of the latest information and communication technologies (ICT) used in this area are given. The basic principles of the formation of an electronic network knowledge base in education are given. The goal of building an electronic network knowledge base in education has been determined. The described ontological and e-scenario principles of organizing an electronic network knowledge base in education in the format of an object-oriented “Prism of knowledge”. A general characteristic of the ontological method for constructing an electronic network knowledge base is given, it is based on the theory of graphs, namely, on its tree structure. This operational characteristic of the electronic script of the knowledge base, the specific information structure of its data blocks. An example of an operational tree-like graph-structure of an e-scenario of a knowledge base is given on the example of a physics curriculum for grade 10. The general characteristic of the “Web-software complex, the editor of scripts of the knowledge base” (work.inhost.com.ua) is given and its organizational structure is described. The results of the formation of an electronic network knowledge base in education in the “Knowledge Prism” format based on the use of the “Web-software complex, the knowledge base script editor” are presented. Provided like “Prism of Knowledge – Newton’s Law” and describes its characteristics. Discussion of the prospects of using the proposed method for constructing an electronic network knowledge base in the “Prism of knowledge” format, as a means of increasing the efficiency of information support for education. A conclusion is given on the relevance of the practical application of this method of forming an electronic network knowledge base on the platform of using the “Web-software complex, script editor of the knowledge base”, as a means of supporting distance education and a tool for building personal and corporate e-network knowledge bases in the “Prism of knowledge” format ... For example, such as an e-network knowledge base of lessons or curricula, electronic textbooks, presentations, etc.
32
Rojas-Sánchez, Mario A., Pedro R. Palos-Sánchez, and José A. Folgado-Fernández. "Systematic literature review and bibliometric analysis on virtual reality and education." Education and Information Technologies, June 27, 2022. http://dx.doi.org/10.1007/s10639-022-11167-5.
Full textAbstract:
Abstract The objective of this study is to identify and analyze the scientific literature with a bibliometric analysis to find the main topics, authors, sources, most cited articles, and countries in the literature on virtual reality in education. Another aim is to understand the conceptual, intellectual, and social structure of the literature on the subject and identify the knowledge base of the use of VR in education and whether it is commonly used and integrated into teaching–learning processes. To do this, articles indexed in the Main Collections of the Web of Science, Scopus and Lens were analyzed for the period 2010 to 2021. The research results are presented in two parts: the first is a quantitative analysis that provides an overview of virtual reality (VR) technology used in the educational field, with tables, graphs, and maps, highlighting the main performance indicators for the production of articles and their citation. The results obtained found a total of 718 articles of which the following were analyzed 273 published articles. The second stage consisted of an inductive type of analysis that found six major groups in the cited articles, which are instruction and learning using VR, VR learning environments, use of VR in different fields of knowledge, learning processes using VR applications or games, learning processes employing simulation, and topics published during the Covid-19 pandemic. Another important aspect to mention is that VR is used in many different areas of education, but until the beginning of the pandemic the use of this so-called “disruptive process” came mainly from students, Institutions were reluctant and slow to accept and include VR in the teaching–learning processes.
33
Withnall, M., E. Lindelöf, O. Engkvist, and H. Chen. "Building attention and edge message passing neural networks for bioactivity and physical–chemical property prediction." Journal of Cheminformatics 12, no. 1 (January 8, 2020). http://dx.doi.org/10.1186/s13321-019-0407-y.
Full textAbstract:
AbstractNeural Message Passing for graphs is a promising and relatively recent approach for applying Machine Learning to networked data. As molecules can be described intrinsically as a molecular graph, it makes sense to apply these techniques to improve molecular property prediction in the field of cheminformatics. We introduce Attention and Edge Memory schemes to the existing message passing neural network framework, and benchmark our approaches against eight different physical–chemical and bioactivity datasets from the literature. We remove the need to introduce a priori knowledge of the task and chemical descriptor calculation by using only fundamental graph-derived properties. Our results consistently perform on-par with other state-of-the-art machine learning approaches, and set a new standard on sparse multi-task virtual screening targets. We also investigate model performance as a function of dataset preprocessing, and make some suggestions regarding hyperparameter selection.
34
Jha, Sanjiv Subodhnarayan. "An Overview on the Explainability of Cyber-Physical Systems." International FLAIRS Conference Proceedings 35 (May 4, 2022). http://dx.doi.org/10.32473/flairs.v35i.130646.
Full textAbstract:
The prevalence of automating complex physical processes through learning and interactions among heterogeneous components adds to the increasing complexity of Cyber-Physical Systems (CPS) and their behavior. Popular Explainable Artificial Intelligence (XAI) methodologies usually overlook the impact of physical and virtual context when explaining the outputs of decision-making software models, which are essential factors in explaining CPS' behavior to stakeholders. Hence in this article, we survey the most relevant XAI methods used for explaining CPS' behavior to identify their shortcomings and applicability in explaining the behavior of CPS. Our main findings are (i) several papers point out the importance of context for explaining CPS, but the explanation methods lack context-awareness; (ii) the explanation delivery mechanisms using low-level visualization tools make the explanations unintelligible. Finally (iii), added information about the system's working and context may increase the actionability of the explanations. Therefore, we propose to enrich the explanations further with contextual information using Semantic Technologies, user feedback, and enhanced explanation visualization techniques to improve their understandability. To that end, context-aware explanation and better explanation presentation based on knowledge graphs and counterfactual explanations might be a promising future research direction for explainable CPS.
35
Sellami, Samir, and Nacer Eddine Zarour. "Keyword-based faceted search interface for knowledge graph construction and exploration." International Journal of Web Information Systems, October 25, 2022. http://dx.doi.org/10.1108/ijwis-02-2022-0037.
Full textAbstract:
Purpose Massive amounts of data, manifesting in various forms, are being produced on the Web every minute and becoming the new standard. Exploring these information sources distributed in different Web segments in a unified way is becoming a core task for a variety of users’ and companies’ scenarios. However, knowledge creation and exploration from distributed Web data sources is a challenging task. Several data integration conflicts need to be resolved and the knowledge needs to be visualized in an intuitive manner. The purpose of this paper is to extend the authors’ previous integration works to address semantic knowledge exploration of enterprise data combined with heterogeneous social and linked Web data sources. Design/methodology/approach The authors synthesize information in the form of a knowledge graph to resolve interoperability conflicts at integration time. They begin by describing KGMap, a mapping model for leveraging knowledge graphs to bridge heterogeneous relational, social and linked web data sources. The mapping model relies on semantic similarity measures to connect the knowledge graph schema with the sources' metadata elements. Then, based on KGMap, this paper proposes KeyFSI, a keyword-based semantic search engine. KeyFSI provides a responsive faceted navigating Web user interface designed to facilitate the exploration and visualization of embedded data behind the knowledge graph. The authors implemented their approach for a business enterprise data exploration scenario where inputs are retrieved on the fly from a local customer relationship management database combined with the DBpedia endpoint and the Facebook Web application programming interface (API). Findings The authors conducted an empirical study to test the effectiveness of their approach using different similarity measures. The observed results showed better efficiency when using a semantic similarity measure. In addition, a usability evaluation was conducted to compare KeyFSI features with recent knowledge exploration systems. The obtained results demonstrate the added value and usability of the contributed approach. Originality/value Most state-of-the-art interfaces allow users to browse one Web segment at a time. The originality of this paper lies in proposing a cost-effective virtual on-demand knowledge creation approach, a method that enables organizations to explore valuable knowledge across multiple Web segments simultaneously. In addition, the responsive components implemented in KeyFSI allow the interface to adequately handle the uncertainty imposed by the nature of Web information, thereby providing a better user experience.
36
Kerstjens, Alan, and Hans De Winter. "LEADD: Lamarckian evolutionary algorithm for de novo drug design." Journal of Cheminformatics 14, no. 1 (January 15, 2022). http://dx.doi.org/10.1186/s13321-022-00582-y.
Full textAbstract:
AbstractGiven an objective function that predicts key properties of a molecule, goal-directed de novo molecular design is a useful tool to identify molecules that maximize or minimize said objective function. Nonetheless, a common drawback of these methods is that they tend to design synthetically unfeasible molecules. In this paper we describe a Lamarckian evolutionary algorithm for de novo drug design (LEADD). LEADD attempts to strike a balance between optimization power, synthetic accessibility of designed molecules and computational efficiency. To increase the likelihood of designing synthetically accessible molecules, LEADD represents molecules as graphs of molecular fragments, and limits the bonds that can be formed between them through knowledge-based pairwise atom type compatibility rules. A reference library of drug-like molecules is used to extract fragments, fragment preferences and compatibility rules. A novel set of genetic operators that enforce these rules in a computationally efficient manner is presented. To sample chemical space more efficiently we also explore a Lamarckian evolutionary mechanism that adapts the reproductive behavior of molecules. LEADD has been compared to both standard virtual screening and a comparable evolutionary algorithm using a standardized benchmark suite and was shown to be able to identify fitter molecules more efficiently. Moreover, the designed molecules are predicted to be easier to synthesize than those designed by other evolutionary algorithms. Graphical Abstract
37
Koulouris, Alexandros, Georgios Aroutidis, Dimitrios Vardalis, Petros Giannoulis, and Paraskevi Karakosta. "Enhancing food engineering education with interactive web-based simulations." International Journal of Food Studies 4, no. 1 (April 18, 2015). http://dx.doi.org/10.7455/ijfs.v4i1.248.
Full textAbstract:
In the traditional deductive approach in teaching any engineering topic, teachers would first expose students to the derivation of the equations that govern the behavior of a physical system and then demonstrate the use of equations through a limited number of textbook examples. This methodology, however, is rarely adequate to unmask the cause-effect and quantitative relationships between the system variables that the equations embody. Web-based simulation, which is the integration of simulation and internet technologies, has the potential to enhance the learning experience by offering an interactive and easily accessible platform for quick and effortless experimentation with physical phenomena.This paper presents the design and development of a web-based platform for teaching basic food engineering phenomena to food technology students. The platform contains a variety of modules (“virtual experiments”) covering the topics of mass and energy balances, fluid mechanics and heat transfer. In this paper, the design and development of three modules for mass balances and heat transfer is presented. Each webpage representing an educational module has the following features: visualization of the studied phenomenon through graphs, charts or videos, computation through a mathematical model and experimentation. The student is allowed to edit key parameters of the phenomenon and observe the effect of these changes on the outputs. Experimentation can be done in a free or guided fashion with a set of prefabricated examples that students can run and self-test their knowledge by answering multiple-choice questions.
38
Born, Jannis, and Matteo Manica. "Trends in Deep Learning for Property-driven Drug Design." Current Medicinal Chemistry 28 (July 29, 2021). http://dx.doi.org/10.2174/0929867328666210729115728.
Full textAbstract:
: It is more pressing than ever to reduce the time and costs for developing lead compounds in the pharmaceutical industry. The co-occurrence of advances in high-throughput screening and the rise of deep learning (DL) have enabled the development of large-scale multimodal predictive models for virtual drug screening. Recently, deep generative models have emerged as a powerful tool for exploring the chemical space and raising hopes to expedite the drug discovery process. Following this progress in chemocentric approaches for generative chemistry, the next challenge is to build multimodal conditional generative models that leverage disparate knowledge sources when biochemical mapping properties to target structures. Here, we call the community to bridge drug discovery more closely with systems biology when designing deep generative models. Complementing the plethora of reviews on the role of DL in chemoinformatics, we herein specifically focus on the interface of predictive and generative modeling for drug discovery. Through a systematic publication keyword search on PubMed and a selection of preprint servers (arXiv, biorXiv, chemRxiv, and medRxiv), we quantify trends in the field and find that molecular graphs and VAEs have become the most widely adopted molecular representations and architectures in generative models, respectively. We discuss progress on DL for toxicity, drug-target affinity, and drug sensitivity prediction and specifically focus on conditional molecular generative models that encompass multimodal prediction models. Moreover, we outline prospects in the field and identify challenges such as the integration of deep learning systems into experimental workflows in a closed-loop manner or the adoption of federated machine learning techniques to overcome data sharing barriers. Other challenges include, but are not limited to interpretability in generative models, more sophisticated metrics for the evaluation of molecular generative models, and, following up on that, community-accepted benchmarks for both multimodal drug property prediction and property-driven molecular design.