Siga este link para ver outros tipos de publicações sobre o tema: Module learning with errors.
Artigos de revistas sobre o tema "Module learning with errors"
Crie uma referência precisa em APA, MLA, Chicago, Harvard, e outros estilos
Veja os 50 melhores artigos de revistas para estudos sobre o assunto "Module learning with errors".
Ao lado de cada fonte na lista de referências, há um botão "Adicionar à bibliografia". Clique e geraremos automaticamente a citação bibliográfica do trabalho escolhido no estilo de citação de que você precisa: APA, MLA, Harvard, Chicago, Vancouver, etc.
Você também pode baixar o texto completo da publicação científica em formato .pdf e ler o resumo do trabalho online se estiver presente nos metadados.
Veja os artigos de revistas das mais diversas áreas científicas e compile uma bibliografia correta.
1
Carle, Myriam S., Rebecca Visser e Alison B. Flynn. "Evaluating students’ learning gains, strategies, and errors using OrgChem101's module: organic mechanisms—mastering the arrows". Chemistry Education Research and Practice 21, n.º 2 (2020): 582–96. http://dx.doi.org/10.1039/c9rp00274j.
Texto completo da fonteResumo:
We developed an online learning module called “Organic Mechanisms: Mastering the Arrows” to help students learn part of organic chemistry's language—the electron-pushing formalism. The module guides students to learn and practice the electron-pushing formalism using a combination of interactive videos, questions with instant feedback, and metacognitive skill-building opportunities. This module is part of OrgChem101.com, an open educational resource (OER) that houses a series of learning modules. To evaluate the mechanism module's effects on students’ learning and experiences, we offered a workshop during which undergraduate students used the module. We investigated their learning gains via a pre-test and post-test format and their experiences using a survey. Analysis of responses revealed significant learning gains between the pre- and post-test, especially with questions that asked students to draw the products of a reaction. After using the learning tool, students used more analysis strategies, such as mapping, attempted more questions, and made fewer errors. The students reported positive experiences and a belief that the module would help them in their organic chemistry courses. Previous work also identified greater metacognitive skills after using the module, related to the module's intended learning outcomes. Herein, we describe the module, evaluation study, findings, and implications for research and practice.
2
Harahap, Safinatul Hasanah, Airi Rizki Syahputri, Dania Priskilla Hura e Rahel Novita Simanihuruk. "Analysis of Errors in Using Punctuation and Writing in Indonesian in Physics Learning Modules in Middle Schools: Case Study in Semarang City". QISTINA: Jurnal Multidisiplin Indonesia 3, n.º 1 (1 de junho de 2024): 866–71. http://dx.doi.org/10.57235/qistina.v3i1.2450.
Texto completo da fonteResumo:
This research aims to investigate common errors in the use of punctuation and writing in Indonesian in physics learning modules at secondary school level in Semarang City. These errors can interfere with students' understanding of the material presented in the module. Therefore, it is necessary to improve and perfect the use of Indonesian punctuation and writing in physics learning modules in order to improve the quality and effectiveness of learning. By analyzing these errors, this study hopes to provide better insight into linguistic aspects in physics learning, and provide recommendations for improvements to improve the quality of learning materials. Analysis methods include collecting learning modules, identifying errors, classifying types of errors, analyzing the causes of errors, and recommending improvements. It is hoped that the results of this study can make a significant contribution to the development of the education curriculum in Indonesia.
3
Pak, JuGeon, JooHwa Lee e MyungSuk Lee. "Developing a Learning Data Collection Platform for Learning Analytics in Online Education". Applied Sciences 12, n.º 11 (26 de maio de 2022): 5412. http://dx.doi.org/10.3390/app12115412.
Texto completo da fonteResumo:
During the COVID-19 pandemic, most education has been conducted through online classes. While feedback and interaction between students and instructors are significant in programming education or engineering practice, online education today cannot satisfy these aspects of learning. Therefore, this study proposes a learning support system for programming education and presents the results of designing and implementing this system. The proposed system consists of an online development environment module, a learning monitoring module, and a learning support module. It also provides a web-based programming environment, real-time chat and code mirroring, error guide messages and related lectures, e-learning quizzes, and learning activity analysis features. The system standardizes the development environment between the instructor and students, helps students take the initiative in solving errors, and enables code-oriented interactions between the instructor and students. It also collects data from all learning situations in the database. Conducting a big data analysis with the collected data will enable individual guidance for students by finding errors that frequently occur in programming and recommending learning materials to solve them.
4
Hongli, Chen. "Design and Application of English Grammar Error Correction System Based on Deep Learning". Security and Communication Networks 2021 (23 de novembro de 2021): 1–9. http://dx.doi.org/10.1155/2021/4920461.
Texto completo da fonteResumo:
In order to solve the problems of low correction accuracy and long correction time in the traditional English grammar error correction system, an English grammar error correction system based on deep learning is designed in this paper. This method analyzes the business requirements and functions of the English grammar error correction system and then designs the overall architecture of the system according to the analysis results, including English grammar error correction module, service access module, and feedback filtering module. The multilayer feedforward neural network is used to construct the language model to judge whether the language sequence is a normal sentence, so as to complete the correction of English grammatical errors. The experimental results show that the designed system has high accuracy and fast speed in correcting English grammatical errors.
5
Jiao, Fengming, Jiao Song, Xin Zhao, Ping Zhao e Ru Wang. "A Spoken English Teaching System Based on Speech Recognition and Machine Learning". International Journal of Emerging Technologies in Learning (iJET) 16, n.º 14 (28 de julho de 2021): 68. http://dx.doi.org/10.3991/ijet.v16i14.24049.
Texto completo da fonteResumo:
The learning model and environment are two major constraints on spoken English learning by Chinese learners. The maturity of computer-aided language learning brings a new opportunity to spoken English learners. Based on speech recognition and machine learning, this paper designs a spoken English teaching system, and determines the overall architecture and functional modules of the system according to the system’s functional demand. Specifically, MATLAB was adopted to realize speech recognition, and generate a speech recognition module. Combined with machine learning algorithm, a deep belief network (DBN)-support vector machine (SVM) model was proposed to classify and detect the errors in pronunciation; the module also scores the quality and corrects the errors in pronunciation. This model was extended to a speech evaluation module was created. Next, several experiments were carried out to test multiple attributes of the system, including the accuracy of pronunciation classification and error detection, recognition rates of different environments and vocabularies, and the real-timeliness of recognition. The results show that our system achieved good performance, realized the preset design goals, and satisfied the user demand. This research provides an important theoretical and practical reference to transforming English teaching method, and improving the spoken English of learners.
6
Mohammad Shahid, Sunil Gupta e MS. Sofia Pillai. "Machine Learning-Based False Positive Software Vulnerability Analysis". Global Journal of Innovation and Emerging Technology 1, n.º 1 (15 de junho de 2022): 29–35. http://dx.doi.org/10.58260/j.iet.2202.0105.
Texto completo da fonteResumo:
Measurements and fault data from an older software version were used to build the fault prediction model for the new release. When past fault data isn't available, it's a problem. The software industry's assessment of programme module failure rates without fault labels is a difficult task. Unsupervised learning can be used to build a software fault prediction model when module defect labels are not available. These techniques can help identify programme modules that are more prone to errors. One method is to make use of clustering algorithms. Software module failures can be predicted using unsupervised techniques such as clustering when fault labels are not available. Machine learning clustering-based software failure prediction is our approach to solving this complex problem.
7
Wang, Binquan, Muhammad Asim, Guoqi Ma e Ming Zhu. "Central Feature Learning for Unsupervised Person Re-identification". International Journal of Pattern Recognition and Artificial Intelligence 35, n.º 08 (5 de março de 2021): 2151007. http://dx.doi.org/10.1142/s0218001421510071.
Texto completo da fonteResumo:
The Exemplar Memory (EM) design has shown its effectiveness in facilitating the unsupervised person re-identification (RE-ID). However, there are obvious defects in the update strategies with most existing results, such as the inability to eliminate static errors and ensure convergence stability of learning. To address these issues, in this paper, we propose a novel center feature learning scheme to improve the update strategies of the traditional EM design for unsupervised RE-ID problems. First, the EM module is regarded as a center feature of a cluster of images, then the goal is transformed into pulling the similar images close to while pushing the dissimilar images away from the center feature space. Second, in order to provide effective guidelines on reducing static errors, we propose an error-memory module to improve the central feature learning performances. In addition, an error-prediction module is designed as well to ensure the stability of convergence. Besides, a camera-invariance learning strategy is also introduced to further improve the proposed algorithm. Finally, extensive comparative experiments are conducted on Market-1501 and DukeMTMC-reID datasets to demonstrate the effectiveness and improvements of the proposed method over existing results. The code of this work is available at https://github.com/binquanwang/CFL_master.
8
Chen, Chi-Feng, Jian-Rong Chen e Ting-Yu Chen. "Identification of the Angle Errors of the LED Parallel-Light Module in PCB Exposure Device by Using Neural Network Learning Algorithms". Coatings 12, n.º 11 (26 de outubro de 2022): 1619. http://dx.doi.org/10.3390/coatings12111619.
Texto completo da fonteResumo:
For the smart manufacturing development of printed-circuit-board (PCB) exposure devices, the LED parallel-light (LPL) module is investigated and the angle errors of those LPL units are identified by neural network learning algorithms. At present, in PCB manufacturing, most circuit boards use photoresist covering etching. After exposure and development, unwanted copper foil is etched and removed to make circuit boards. The exposure process is its key process, and the equipment used in this process is an exposure machine. The LPL unit is designed and the LPL exposure module is searched under the principle of higher irradiance uniformity. The learning data of supervised learning for the convolutional neural network (CNN) include a 2D irradiance distribution image constructed by the ray tracing simulation tool. In these supervised learning data, all units of LPL-EM are randomly added with a self-specific angle error. By using Fast Region-based CNN, the identification of the multi-LPL module with the specific errors of inclination and azimuth angle is verified. Those results preliminarily illustrate that supervised learning techniques should be able to help identify the errors of inclination and azimuth angle for the single LPL unit and multi-light module of PCB exposure devices. In other words, this technology should serve as a reference for the development of the PCB exposure process towards smart manufacturing.
9
Geha, Rabih, Robert L. Trowbridge, Gurpreet Dhaliwal e Andrew P. J. Olson. "Teaching about diagnostic errors through virtual patient cases: a pilot exploration". Diagnosis 5, n.º 4 (27 de novembro de 2018): 223–27. http://dx.doi.org/10.1515/dx-2018-0023.
Texto completo da fonteResumo:
Abstract Background: Diagnostic error is a major problem in health care, yet there are few medical school curricula focused on improving the diagnostic process and decreasing diagnostic errors. Effective strategies to teach medical students about diagnostic error and diagnostic safety have not been established. Methods: We designed, implemented and evaluated a virtual patient module featuring two linked cases involving diagnostic errors. Learning objectives developed by a consensus process among medical educators in the Society to Improve Diagnosis in Medicine (SIDM) were utilized. The module was piloted with internal medicine clerkship students at three institutions and with clerkship faculty members recruited from listservs. Participants completed surveys on their experience using the case and a qualitative analysis was performed. Results: Thirty-five medical students and 25 faculty members completed the survey. Most students found the module to be relevant and instructive. Faculty also found the module valuable for students but identified insufficient curricular time as a barrier to implementation. Conclusions: Medical students and faculty found a prototype virtual patient module about the diagnostic process and diagnostic error to be educational.
10
Jia, Wenjuan, Jiang Zhang e Baocang Wang. "Hardness of Module-LWE with Semiuniform Seeds from Module-NTRU". IET Information Security 2023 (23 de outubro de 2023): 1–16. http://dx.doi.org/10.1049/2023/2969432.
Texto completo da fonteResumo:
The module learning with errors (MLWE) problem has attracted significant attention and has been widely used in building a multitude of lattice-based cryptographic primitives. The hardness of the MLWE problem has been established for several variants, but most of the known results require the seed distribution (i.e., the distribution of matrix A ) to be the uniform distribution. In this paper, we show that under the Module-N-th degree Truncated polynomial Ring Units (NTRU) (MNTRU) assumption, the search MLWE problem can still be hard for some distributions that are not (even computationally indistinguishable from) the uniform distribution. Specifically, we show that if the seed distribution is a semiuniform distribution (namely, the seed distribution can be publicly derived from and has a “small difference” to the uniform distribution), then for appropriate settings of parameters, the search MLWE problem is hard under the MNTRU assumption. Moreover, we also show that under the appropriate settings of parameters, the search learning with errors over rings problem with semiuniform seeds can still be hard under the NTRU assumption due to our results for the search MLWE problem with semiuniform seeds being rank-preserving.
11
Ramadhan, Muhammad Sabir, e Harmayani Harmayani. "Development of The Project-Based Learning Model In Making Teaching Modules for Courses Multimedia Technology and Animation". Journal of Computer Networks, Architecture and High Performance Computing 6, n.º 1 (12 de fevereiro de 2024): 449–60. http://dx.doi.org/10.47709/cnahpc.v6i1.3519.
Texto completo da fonteResumo:
The discovery of errors in the delivery of Multimedia Technology and Animation course material is indirectly caused by the implementation of lectures for the course, which should be given for 2 semesters compressed into 1 semester only. The limited learning time prevents some course material from being delivered to students. This limitation was also triggered by the absence of teaching modules that support condensed learning due to the implementation of lectures for 1 semester. Seeing these problems makes the development of a teaching module in the Multimedia and Animation Technology course with Project-Based Learning to support the implementation of lectures a solution that can be done to overcome existing problems. The feasibility test results show that the teaching module is valid. In contrast, the results of the feasibility test by media experts show that 95.14% of the module is very valid, and seen from the results of the feasibility test by material experts show that 97.14% of the module is very valid for use in learning for 1 semester. In the trial involving students, it shows that through the results of individual trials, it can be seen that 94.17% of the teaching modules developed are very feasible to use in the learning process. In addition, through the results of the small group trial, it can be seen that the teaching module is 85.18% very feasible to use, as well as the results of the usage trial show that the teaching module is 87.45% very feasible to use in learning. Based on the data obtained, it can be concluded that the Multimedia and Animation Technology module with Project-Based Learning is very feasible to be used as a reference and in the learning process of Multimedia and Animation Technology courses.
12
Purnamasari, Heny, Asrori Asrori e Warneri Warneri. "The Development of Learning Module in Social Knowledge on Economic Activity Based on Living Value Education of Responsibility Value". JETL (Journal Of Education, Teaching and Learning) 4, n.º 2 (30 de setembro de 2019): 389. http://dx.doi.org/10.26737/jetl.v4i2.1922.
Texto completo da fonteResumo:
This research intends to develop a learning media in the form of modules based on living values education, a module that develops key personal and social values, especially the value of responsibility, aimed at teaching students about the principle of responsibility, bringing students to be able to take responsibility for their behaviour and life. The research steps for developing the social studies learning module based on the living values education use the steps of the development of Borg and Gall, and the design of the learning model using the design of the Dick and Carey learning model. The steps of research and development start from: (1) studying various research findings related to devices that will be developed products, (2) developing the initial form of the device based on the research findings of living values education, (3) expert validation, (4) revising based on expert comments, (5) conducting a series of field tests (three experiments) on the place where the living values education module is used, and (4) revising the module to correct various weaknesses or errors found from the results of each field test. carried out by observation, interviews, and questionnaires, using research instruments in the form of observation guides, interview guides, and questionnaires. Data analysis used qualitative and quantitative analysis. The results showed that the design of the development of economic activity modules based on living values education consisted of (1) the stages of curriculum analysis and learning resources, (2) Analysis of student characteristics, (3) Analysis of tasks, (4) Analysis of material and concepts, (5) Formulate learning objectives, and (6) Planning phase. The development phase of the economic activity module based on living values education consists of: (1) Writing and compiling economic activity modules, (2) Expert assessment, (3) Module revisions based on expert comments, (4) Empirical trials, and (5) Module revisions based on trial comments. The implementation of learning using economic activity modules based on living values education begins with preparation, introduction, core activities, evaluating student work results, evaluation and closing. Obtaining student learning outcomes after using the module shows an increase, both from (1) aspects of knowledge, (2) aspects of attitude, and. (3) skill aspects, this means that economic activity modules based on living values education have effectiveness on the learning outcomes of VII grade MTs students. Al-Jihad in Pontianak City.
13
Krouska, Akrivi, Christos Troussas e Cleo Sgouropoulou. "A Cognitive Diagnostic Module Based on the Repair Theory for a Personalized User Experience in E-Learning Software". Computers 10, n.º 11 (29 de outubro de 2021): 140. http://dx.doi.org/10.3390/computers10110140.
Texto completo da fonteResumo:
This paper presents a novel cognitive diagnostic module which is incorporated in e-learning software for the tutoring of the markup language HTML. The system is responsible for detecting the learners’ cognitive bugs and delivering personalized guidance. The novelty of this approach is that it is based on the Repair theory that incorporates additional features, such as student negligence and test completion times, in its diagnostic mechanism; also, it employs a recommender module that suggests students optimal learning paths based on their misconceptions using descriptive test feedback and adaptability of learning content. Considering the Repair theory, the diagnostic mechanism uses a library of error correction rules to explain the cause of errors observed by the student during the assessment. This library covers common errors, creating a hypothesis space in that way. Therefore, the test items are expanded, so that they belong to the hypothesis space. Both the system and the cognitive diagnostic tool were evaluated with promising results, showing that they offer a personalized experience to learners.
14
McCoy, Lise, Joy H. Lewis, Harvey Simon, Denise Sackett, Tala Dajani, Christine Morgan e Aaron Hunt. "Learning to Speak Up for Patient Safety: Interprofessional Scenarios for Training Future Healthcare Professionals". Journal of Medical Education and Curricular Development 7 (janeiro de 2020): 238212052093546. http://dx.doi.org/10.1177/2382120520935469.
Texto completo da fonteResumo:
Background: Preventable medical errors represent a leading cause of death in the United States. Effective undergraduate medical education (UME) strategies are needed to train medical students in error prevention, early identification of potential errors, and proactive communication. To address this need, a team of faculty from A.T. Still University’s School of Osteopathic Medicine in Arizona developed four digital patient safety case scenarios for second-year medical students. These scenarios were designed to integrate interprofessional collaboration and patient safety principles, increase student ability to identify potential errors, and promote proactive communication skills. Methods: Faculty used Qualtrics to create four digital case scenarios on patient safety covering the following domains: communicating about potential drug-to-drug interactions; effective handoffs; human factors errors, such as fatigue, illness, and stress; and conflicts with supervising resident. In fall 2018, 97 second-year medical students completed the entire safety module in dyad or triad teams. As they worked through each case study, student teams completed 11 assessment questions with instant feedback, and participated in short case debrief discussions. Next, each individual student took a 12-question post-test to assess learning. Descriptive statistics were reviewed for the assessment questions, and case critical thinking discussion answers were reviewed to evaluate student comprehension. Results: The mean score for the module was 95.5% (SD= 6.36%, range = 75%-100%). Seventy-eight students completed the post-test, which had a mean score of 96.5% (SD = 6.51%, range = 66.7%-100%). Student written responses to the four case critical thinking discussion prompts indicated a high level of comprehension. Conclusion: Our results demonstrated that digital case studies can provide an innovative mechanism to introduce key patient safety concepts and experiential practice of interprofessional communication in early UME. Our design and implementation of these engaging interprofessional patient safety training modules provided an opportunity for students to learn key communication and safety concepts in small teams. This training method was cost-effective and could be replicated in other online learning or blended learning environments for a wide range of health professions.
15
Yousif, Jabar H., Hussein A. Kazem, Haitham Al-Balushi, Khaled Abuhmaidan e Reem Al-Badi. "Artificial Neural Network Modelling and Experimental Evaluation of Dust and Thermal Energy Impact on Monocrystalline and Polycrystalline Photovoltaic Modules". Energies 15, n.º 11 (4 de junho de 2022): 4138. http://dx.doi.org/10.3390/en15114138.
Texto completo da fonteResumo:
Many environmental parameters affect the performance of solar photovoltaics (PV), such as dust and temperature. In this paper, three PV technologies have been investigated and experimentally analyzed (mono, poly, and flexible monocrystalline) in terms of the impact of dust and thermal energy on PV behavior. Furthermore, a modular neural network is designed to test the effects of dust and temperature on the PV power production of six PV modules installed at Sohar city, Oman. These experiments employed three pairs of PV modules (one cleaned daily and one kept dusty for 30 days). The performance of the PV power production was evaluated and examined for the three PV modules (monocrystalline, polycrystalline, and flexible), which achieved 30.24%, 28.94%, and 36.21%, respectively. Moreover, the dust reduces the solar irradiance approaching the PV module and reduces the temperature, on the other hand. The neural network and practical models’ performance were compared using different indicators, including MSE, NMSE, MAE, Min Abs Error, and r. The Mean Absolute Error (MAE) is used for evaluating the accuracy of the ANN machine learning model. The results show that the accuracy of the predicting power of the six PV modules was considerable, at 97.5%, 97.4%, 97.6%, 96.7%, 96.5%, and 95.5%, respectively. The dust negatively reduces the PV modules’ power production performance by about 1% in PV modules four and six. Furthermore, the results were evident that the negative effect of the dust on the PV module production based on the values of RMSE, which measures the square root of the average of the square’s errors. The average errors in predicting the power production of the six PV modules are 0.36406, 0.38912, 0.34964, 0.49769, 0.46486, and 0.68238.
16
Gu, Peng, Ping Zhang, Mingfei Jiang, Xiaofeng Qiu, Xinyan Wang, Chun Du e Tianyou Peng. "Research on Carbon Foam Image Segmentation Based on Deep Learning". Wireless Communications and Mobile Computing 2022 (14 de julho de 2022): 1–10. http://dx.doi.org/10.1155/2022/5965302.
Texto completo da fonteResumo:
As a substitute for metal, carbon foam is vital in the electromagnetic shielding industry. Nevertheless, the diameter and density of carbon foam cells are still mostly assessed manually. This research offers a Deep-Res-MixAttention segmentation method to effectively minimize manual labor and increase measurement efficiency. Moreover, the method consists of two modules: the MixAttention module is intended to improve feature extraction skills, and we use the multiscale deep residual module to collect edge information. In addition to enhancing the segmentation capability of incomplete carbon foam, the loss function is adjusted to address the dataset imbalance issue. Additionally, we propose the bidirectional selection rotation calipers algorithm to intelligently determine the density and diameter. The results reveal that the optimized network’s IoU and acc carbon reach 91.05% and 88.31%. Finally, the calculation errors of the average diameter and density are under control at 1.79% and 7.09%, respectively. The approach has a high application value for assessing the electromagnetic shielding effectiveness of carbon foam.
17
Guan, Sheng, Hanchao Ma, Sutanay Choudhury e Yinghui Wu. "GEDet". Proceedings of the VLDB Endowment 14, n.º 12 (julho de 2021): 2875–78. http://dx.doi.org/10.14778/3476311.3476367.
Texto completo da fonteResumo:
Detecting nodes with erroneous values in real-world graphs remains challenging due to the lack of examples and various error scenarios. We demonstrate GEDet, an error detection engine that can detect erroneous nodes in graphs with a few examples. The GEDet framework tackles error detection as a few-shot node classification problem. We invite the attendees to experience the following unique features. (1) Few-shot detection . Users only need to provide a few examples of erroneous nodes to perform error detection with GEDet. GEDet achieves desirable accuracy with (a) a graph augmentation module, which automatically generates synthetic examples to learn the classifier, and (b) an adversarial detection module, which improves classifiers to better distinguish erroneous nodes from both cleaned nodes and synthetic examples. We show that GEDet significantly improves the state-of-the-art error detection methods. (2) Diverse error scenarios . GEDet profiles data errors with a built-in library of transformation functions from correct values to errors. Users can also easily "plug in" new error types or examples. (3) User-centric detection . GEDet supports (a) an active learning mode to engage users to verify detected results, and adapts the error detection process accordingly; and (b) visual interfaces to interpret and track detected errors.
18
Nashaat, Mona, Aindrila Ghosh, James Miller e Shaikh Quader. "TabReformer: Unsupervised Representation Learning for Erroneous Data Detection". ACM/IMS Transactions on Data Science 2, n.º 3 (17 de maio de 2021): 1–29. http://dx.doi.org/10.1145/3447541.
Texto completo da fonteResumo:
Error detection is a crucial preliminary phase in any data analytics pipeline. Existing error detection techniques typically target specific types of errors. Moreover, most of these detection models either require user-defined rules or ample hand-labeled training examples. Therefore, in this article, we present TabReformer, a model that learns bidirectional encoder representations for tabular data. The proposed model consists of two main phases. In the first phase, TabReformer follows encoder architecture with multiple self-attention layers to model the dependencies between cells and capture tuple-level representations. Also, the model utilizes a Gaussian Error Linear Unit activation function with the Masked Data Model objective to achieve deeper probabilistic understanding. In the second phase, the model parameters are fine-tuned for the task of erroneous data detection. The model applies a data augmentation module to generate more erroneous examples to represent the minority class. The experimental evaluation considers a wide range of databases with different types of errors and distributions. The empirical results show that our solution can enhance the recall values by 32.95% on average compared with state-of-the-art techniques while reducing the manual effort by up to 48.86%.
19
Dai, Zhiqi. "The Investigation of Machine Learning in Grammar Correction". Lecture Notes in Education Psychology and Public Media 35, n.º 1 (3 de janeiro de 2024): 311–16. http://dx.doi.org/10.54254/2753-7048/35/20232156.
Texto completo da fonteResumo:
As English continues to be the dominant language acquired by the majority of the global population, the demand for learning it is on the rise. Within English education, grammar plays a vital role and can now benefit from machine learning-based correctional applications. This paper explores various methods employed in prior research for grammar correction. Notably, the feature extraction method proves to be effective in capturing essential information from the text, resulting in more precise revisions of grammatical errors. The feedback filtering module will select valid improvement advice from users to develop more efficient application. Recurrent Neural Network (RNN) which is a widely-used model can also be adopted to grammar correction due to its memorizing ability. In previous studies, these methods are tested to see their validity in English grammar correction. Results of feedback filtering module show that it can sort out users advice into useful and useless so that the modification of the application can be more accurate. In another experiment, the F-0.5 score of RNN is measured with several other models and RNN has apparent advantage over the majority in grammar error detection and correction. Admittedly, however, these methods still have space for further enhancement to provide high precision in correction. Means to eliminate possible errors and inaccuracy are urged to be found, but probably the only way out is the innumerable data fed to computers. This paper offers a comprehensive view of current study progress in the field and encourage new evolution.
20
Ma, Zhenshu, Bo Yang e Yuhang Zhang. "Source File Tracking Localization: A Fault Localization Method for Deep Learning Frameworks". Electronics 12, n.º 22 (9 de novembro de 2023): 4579. http://dx.doi.org/10.3390/electronics12224579.
Texto completo da fonteResumo:
Deep learning has been widely used in computer vision, natural language processing, speech recognition, and other fields. If there are errors in deep learning frameworks, such as missing module errors and GPU/CPU result discrepancy errors, it will cause many application problems. We propose a source-based fault location method, SFTL (Source File Tracking Localization), to improve the fault location efficiency of these two types of errors in deep learning frameworks. We screened 3410 crash reports on GitHub and conducted fault location experiments based on those reports. The experimental results show that the SFTL method has a high accuracy, which can help deep learning framework developers quickly locate faults and improve the stability and reliability of models.
21
Lambert, Sherwood Lane. "Auto Accessories, Inc.: An Educational Case on Online Transaction Processing (OLTP) and Controls as Compared to Batch Processing and Controls". Journal of Emerging Technologies in Accounting 14, n.º 2 (1 de junho de 2017): 59–81. http://dx.doi.org/10.2308/jeta-51844.
Texto completo da fonteResumo:
ABSTRACT The intent of this educational case is to increase students' understanding of online transaction processing (OLTP) and controls as compared to batch processing and controls. Learning concepts about batch processing is important because many entities continue to use batch processing for critical applications such as payroll, credit card processing, and Big Data. Students learn the advantages and disadvantages of batch processing and OLTP. The case provides a Microsoft Access database that includes a working batch program (module) and an online screen (form). Students use the form to update an employee table in a relational database with OLTP and use the module to update an employee master file with batch processing. Students compare the output from batch processing to the output from OLTP after processing the same input transactions and demonstrate that the outputs match when no input or processing errors exist. Students implement similar data validation edits in both the module and the form. Also, students implement run-to-run control total checks in the module and report input data errors in a batch-processed error report. Students learn processing and controls that are unique to batch processing, unique to OLTP, and common to both processing modes.
22
Maggioni, Viviana, Manuela Girotto, Emad Habib e Melissa A. Gallagher. "Building an Online Learning Module for Satellite Remote Sensing Applications in Hydrologic Science". Remote Sensing 12, n.º 18 (16 de setembro de 2020): 3009. http://dx.doi.org/10.3390/rs12183009.
Texto completo da fonteResumo:
This article presents an online teaching tool that introduces students to basic concepts of remote sensing and its applications in hydrology. The learning module is intended for junior/senior undergraduate students or junior graduate students with no (or little) prior experience in remote sensing, but with some basic background of environmental science, hydrology, statistics, and programming. This e-learning environment offers background content on the fundamentals of remote sensing, but also integrates a set of existing online tools for visualization and analysis of satellite observations. Specifically, students are introduced to a variety of satellite products and techniques that can be used to monitor and analyze changes in the hydrological cycle. At completion of the module, students are able to visualize remote sensing data (both in terms of time series and spatial maps), detect temporal trends, interpret satellite images, and assess errors and uncertainties in a remote sensing product. Students are given the opportunity to check their understanding as they progress through the module and also tackle complex real-life problems using remote sensing observations that professionals and scientists commonly use in practice. The learning tool is implemented in HydroLearn, an open-source, online platform for instructors to find and share learning modules and collaborate on developing teaching resources in hydrology and water resources.
23
TOLU, SILVIA, MAURICIO VANEGAS, JESÚS A. GARRIDO, NICETO R. LUQUE e EDUARDO ROS. "ADAPTIVE AND PREDICTIVE CONTROL OF A SIMULATED ROBOT ARM". International Journal of Neural Systems 23, n.º 03 (29 de abril de 2013): 1350010. http://dx.doi.org/10.1142/s012906571350010x.
Texto completo da fonteResumo:
In this work, a basic cerebellar neural layer and a machine learning engine are embedded in a recurrent loop which avoids dealing with the motor error or distal error problem. The presented approach learns the motor control based on available sensor error estimates (position, velocity, and acceleration) without explicitly knowing the motor errors. The paper focuses on how to decompose the input into different components in order to facilitate the learning process using an automatic incremental learning model (locally weighted projection regression (LWPR) algorithm). LWPR incrementally learns the forward model of the robot arm and provides the cerebellar module with optimal pre-processed signals. We present a recurrent adaptive control architecture in which an adaptive feedback (AF) controller guarantees a precise, compliant, and stable control during the manipulation of objects. Therefore, this approach efficiently integrates a bio-inspired module (cerebellar circuitry) with a machine learning component (LWPR). The cerebellar-LWPR synergy makes the robot adaptable to changing conditions. We evaluate how this scheme scales for robot-arms of a high number of degrees of freedom (DOFs) using a simulated model of a robot arm of the new generation of light weight robots (LWRs).
24
Ahmad, Arimuliani. "Developing Cooperative Learning Based E-Module to Teach Basic English Grammar of the First Semester of English Study Program Students at FKIP – UIR". J-SHMIC : Journal of English for Academic 4, n.º 2 (12 de setembro de 2017): 1–11. http://dx.doi.org/10.25299/jshmic.2017.vol4(2).536.
Texto completo da fonteResumo:
Achieving learning outcome requires a set of the material that can be understood easily by the students. The material should be appropriate in the learning process. It should give the opportunity for the students to learn both in the classroom and out of the classroom. The students can learn independently by using the appropriate material. However, the material of Basic English Grammar is still quite enough to give a chance for the students to practice and learn cooperatively. This research is aimed obtain e-module of Basic English Grammar, so that it can be used as a source of learning for first semester students of English Study Program of FKIP-UIR. The research method used in this study is R & D (Research and development) of Borg and Gall. The participant of this research is 30 students from first semester who learn Basic English Grammar. In this research, the researcher tried to find out students’ need because it is the first step to do in this research design. So, the data was obtained by writing test.The findings suggest that the participants made 386 errors in writing their paragraph. There are 45 errors (11.66%) of the agreement of singular and plural, 106 errors (27.46%) of the using of verb tense, 51 errors (13.21%) of the finite verb, 25 errors (2.48%) of the non-finite verb, 28 errors (7.25%) of the pronoun, 20 errors (5.18%) in using the preposition, 9 errors (2.33%) of the context of usage, 55 errors (14.25%) of the context of meaning, 22 errors (5.70%) of the word choice and 25 errors (6.48%) of word order. To sum up, the most frequent grammatical errors made by the students are errors in writing verb tense. Based on this finding, the researcher will design e-module of Basic English Grammar.
25
Li, Mingxuan, Ou Li, Guangyi Liu e Ce Zhang. "An Automatic Modulation Recognition Method with Low Parameter Estimation Dependence Based on Spatial Transformer Networks". Applied Sciences 9, n.º 5 (11 de março de 2019): 1010. http://dx.doi.org/10.3390/app9051010.
Texto completo da fonteResumo:
Recently, automatic modulation recognition has been an important research topic in wireless communication. Due to the application of deep learning, it is prospective of using convolution neural networks on raw in-phase and quadrature signals in developing automatic modulation recognition methods. However, the errors introduced during signal reception and processing will greatly deteriorate the classification performance, which affects the practical application of such methods. Therefore, we first analyze and quantify the errors introduced by signal detection and isolation in noncooperative communication through a baseline convolution neural network. In response to these errors, we then design a signal spatial transformer module based on the attention model to eliminate errors by a priori learning of signal structure. By cascading a signal spatial transformer module in front of the baseline classification network, we propose a method that can adaptively resample the signal capture to adjust time drift, symbol rate, and clock recovery. Besides, it can also automatically add a perturbation on the signal carrier to correct frequency offset. By applying this improved model to automatic modulation recognition, we obtain a significant improvement in classification performance compared with several existing methods. Our method significantly improves the prospect of the application of automatic modulation recognition based on deep learning under nonideal synchronization.
26
Wang, Zihe, Linzhou Li, Tan Zhang, Tengfei Liu, Ming Li, Zifan Wang e Zixiang Li. "Emulating Artistic Expressions in Robot Painting: A Stroke-Based Approach". Applied Sciences 14, n.º 12 (18 de junho de 2024): 5265. http://dx.doi.org/10.3390/app14125265.
Texto completo da fonteResumo:
Representing art using a robotic system is part of artificial intelligence in our lives, especially in the realm of emotional expression. Developing a painting robot involves addressing how to enable the robot to emulate human artistic processes, which often include imprecise techniques or errors akin to those made by human artists. This paper discusses our development of an innovative painting robot utilizing the sim-to-real approach within learning technology. Specifically, this pipeline operates under a deep reinforcement learning (DRL) framework designed to learn drawing strategies from training data derived from real-world settings, aiming for the robot’s proficiency in emulating human artistic expressions. Accordingly, the framework comprises two modules when given a target drawing image: the first module trains in a simulated environment to break down the target image into individual strokes; the second module then learns how to execute these strokes in a real environment. Our experiments have shown that this system can meet our objectives effectively.
27
He, Haiyin, e Darchia Maia. "Application of Grammar Error Detection Method for English Composition Based on Machine Learning". Security and Communication Networks 2022 (26 de maio de 2022): 1–9. http://dx.doi.org/10.1155/2022/7957365.
Texto completo da fonteResumo:
With the development of grammar-checking technology and algorithms, the grammar-checking system has been widely used in various fields. This paper designs and implements a grammar-checking system for English composition. The grammar-checking system adopts a multimodule design. The grammar-checking system is composed of a multilayer rule error-correcting module and a machine learning error-correcting module. This study aims to build a machine learning algorithm model that can detect English grammar errors by analysing and comparing different algorithm models currently applied in the field of education and then apply the trained model to the English composition grammar detection system. The results show that the system can save a lot of time and labor cost of manual marking, liberate teachers from heavy and repeated evaluation activities, and put more time and energy on teaching. At the same time, it can provide learners with more objective and timely feedback so that learners can intuitively and clearly know that they are prone to make grammatical mistakes in the process of English learning. It plays a certain assisting and guiding role in English learners’ autonomous learning.
28
Chen, Baifan, Hong Chen, Baojun Song e Grace Gong. "TIF-Reg: Point Cloud Registration with Transform-Invariant Features in SE(3)". Sensors 21, n.º 17 (27 de agosto de 2021): 5778. http://dx.doi.org/10.3390/s21175778.
Texto completo da fonteResumo:
Three-dimensional point cloud registration (PCReg) has a wide range of applications in computer vision, 3D reconstruction and medical fields. Although numerous advances have been achieved in the field of point cloud registration in recent years, large-scale rigid transformation is a problem that most algorithms still cannot effectively handle. To solve this problem, we propose a point cloud registration method based on learning and transform-invariant features (TIF-Reg). Our algorithm includes four modules, which are the transform-invariant feature extraction module, deep feature embedding module, corresponding point generation module and decoupled singular value decomposition (SVD) module. In the transform-invariant feature extraction module, we design TIF in SE(3) (which means the 3D rigid transformation space) which contains a triangular feature and local density feature for points. It fully exploits the transformation invariance of point clouds, making the algorithm highly robust to rigid transformation. The deep feature embedding module embeds TIF into a high-dimension space using a deep neural network, further improving the expression ability of features. The corresponding point cloud is generated using an attention mechanism in the corresponding point generation module, and the final transformation for registration is calculated in the decoupled SVD module. In an experiment, we first train and evaluate the TIF-Reg method on the ModelNet40 dataset. The results show that our method keeps the root mean squared error (RMSE) of rotation within 0.5∘ and the RMSE of translation error close to 0 m, even when the rotation is up to [−180∘, 180∘] or the translation is up to [−20 m, 20 m]. We also test the generalization of our method on the TUM3D dataset using the model trained on Modelnet40. The results show that our method’s errors are close to the experimental results on Modelnet40, which verifies the good generalization ability of our method. All experiments prove that the proposed method is superior to state-of-the-art PCReg algorithms in terms of accuracy and complexity.
29
Mukherjee, Anisha, Aikata Aikata, Ahmet Can Mert, Yongwoo Lee, Sunmin Kwon, Maxim Deryabin e Sujoy Sinha Roy. "ModHE: Modular Homomorphic Encryption Using Module Lattices". IACR Transactions on Cryptographic Hardware and Embedded Systems 2024, n.º 1 (4 de dezembro de 2023): 527–62. http://dx.doi.org/10.46586/tches.v2024.i1.527-562.
Texto completo da fonteResumo:
The promising field of homomorphic encryption enables functions to be evaluated on encrypted data and produce results for the same computations done on plaintexts. It, therefore, comes as no surprise that many ventures at constructing homomorphic encryption schemes have come into the limelight in recent years. Most popular are those that rely on the hard lattice problem, called the Ring Learning with Errors problem (RLWE). One major limitation of these homomorphic encryption schemes is that in order to securely increase the maximum multiplicative depth, they need to increase the polynomial-size (degree of the polynomial ring) thereby also ncreasing the complexity of the design. We aim to bridge this gap by proposing a homomorphic encryption (HE) scheme based on the Module Learning with Errors problem (MLWE), ModHE that allows us to break the big computations into smaller ones. Given the popularity of module lattice-based post-quantum schemes, it is an evidently interesting research endeavor to also formulate module lattice-based homomorphic encryption schemes. While our proposed scheme is general, as a case study, we port the well-known RLWE-based CKKS scheme to the MLWE setting. The module version of the scheme completely stops the polynomial-size blowups when aiming for a greater circuit depth. Additionally, it presents greater opportunities for designing flexible, reusable, and parallelizable hardware architecture. A hardware implementation is provided to support our claims. We also acknowledge that as we try to decrease the complexity of computations, the amount of computations (such as relinearizations) increases. We hope that the potential and limitations of using such a hardware-friendly scheme will spark further research.
30
Tan, Yuanjun, Quanling Liu, Tingting Liu, Hai Liu, Shengming Wang e Zengzhao Chen. "RQ-OSPTrans: A Semantic Classification Method Based on Transformer That Combines Overall Semantic Perception and “Repeated Questioning” Learning Mechanism". Applied Sciences 14, n.º 10 (17 de maio de 2024): 4259. http://dx.doi.org/10.3390/app14104259.
Texto completo da fonteResumo:
The pre-trained language model based on Transformers possesses exceptional general text-understanding capabilities, empowering it to adeptly manage a variety of tasks. However, the topic classification ability of the pre-trained language model will be seriously affected in the face of long colloquial texts, expressions with similar semantics but completely different expressions, and text errors caused by partial speech recognition. We propose a long-text topic classification method called RQ-OSPTrans to effectively address these challenges. To this end, two parallel learning modules are proposed to learn long texts, namely, the repeat question module and the overall semantic perception module. The overall semantic perception module will conduct average pooling on the semantic embeddings produced by BERT, in addition to multi-layer perceptron learning. The repeat question module will learn the text-embedding matrix, extracting detailed clues for classification based on words as fundamental elements. Comprehensive experiments demonstrate that RQ-OSPTrans can achieve a generalization performance of 98.5% on the Chinese dataset THUCNews. Moreover, RQ-OSPTrans can achieve state-of-the-art performance on the arXiv-10 dataset (84.4%) and has a comparable performance with other state-of-the-art pre-trained models on the AG’s News dataset. Finally, the results indicate that our method exhibits a superior performance compared with the baseline methods on small-scale domain-specific datasets by validating RQ-OSPTrans on a specific task scenario by using our custom-built dataset CCIPC.
31
Chen, Bingren. "Point Cloud Registration via Heuristic Reward Reinforcement Learning". Stats 6, n.º 1 (6 de fevereiro de 2023): 268–78. http://dx.doi.org/10.3390/stats6010016.
Texto completo da fonteResumo:
This paper proposes a heuristic reward reinforcement learning framework for point cloud registration. As an essential step of many 3D computer vision tasks such as object recognition and 3D reconstruction, point cloud registration has been well studied in the existing literature. This paper contributes to the literature by addressing the limitations of embedding and reward functions in existing methods. An improved state-embedding module and a stochastic reward function are proposed. While the embedding module enriches the captured characteristics of states, the newly designed reward function follows a time-dependent searching strategy, which allows aggressive attempts at the beginning and tends to be conservative in the end. We assess our method based on two public datasets (ModelNet40 and ScanObjectNN) and real-world data. The results confirm the strength of the new method in reducing errors in object rotation and translation, leading to more precise point cloud registration.
32
Yongco, Jayson O., e Jasper M. Del Valle. "Development and Evaluation of Instructional Module for Special Program in Journalism". International Journal of Educational Management and Development Studies 3, n.º 4 (6 de dezembro de 2022): 97–117. http://dx.doi.org/10.53378/352948.
Texto completo da fonteResumo:
The study aimed to develop and evaluate the instructional module for special program in journalism for grade 8 students. It is geared towards probing the errors encountered in learning resource construction and the recommendations in enhancing the instructional material through questionnaires and guidelines for learning resource material (LRM) production. Data were gathered from forty Grade 8 Journalism students enrolled at an Integrated High School in Laguna, Philippines and ten specialists who were purposively selected. The data were collected and treated using Mean. Findings revealed that the student-evaluators strongly agree on the rating criteria of the instructional module in terms of format, content, clarity and usefulness. On the other hand, the specialists rated the instructional module passed on content, format and presentation and organization criteria but failed on accuracy and up-to-datedness of information.
33
Park, Min-Ji, Eul-Bum Lee, Seung-Yeab Lee e Jong-Hyun Kim. "A Digitalized Design Risk Analysis Tool with Machine-Learning Algorithm for EPC Contractor’s Technical Specifications Assessment on Bidding". Energies 14, n.º 18 (17 de setembro de 2021): 5901. http://dx.doi.org/10.3390/en14185901.
Texto completo da fonteResumo:
Engineering, Procurement, and Construction (EPC) projects span the entire cycle of industrial plants, from bidding to engineering, construction, and start-up operation and maintenance. Most EPC contractors do not have systematic decision-making tools when bidding for the project; therefore, they rely on manual analysis and experience in evaluating the bidding contract documents, including technical specifications. Oftentimes, they miss or underestimate the presence of technical risk clauses or risk severity, potentially create with a low bid price and tight construction schedule, and eventually experience severe cost overrun or/and completion delays. Through this study, two digital modules, Technical Risk Extraction and Design Parameter Extraction, were developed to extract and analyze risks in the project’s technical specifications based on machine learning and AI algorithms. In the Technical Risk Extraction module, technical risk keywords in the bidding technical specifications are collected, lexiconized, and then extracted through phrase matcher technology, a machine learning natural language processing technique. The Design Parameter Extraction module compares the collected engineering standards’ so-called standard design parameters and the plant owner’s technical requirements on the bid so that a contractor’s engineers can detect the difference between them and negotiate them. As described above, through the two modules, the risk clauses of the technical specifications of the project are extracted, and the risks are detected and reconsidered in the bidding or execution of the project, thereby minimizing project risk and providing a theoretical foundation and system for contractors. As a result of the pilot test performed to verify the performance and validity of the two modules, the design risk extraction accuracy of the system module has a relative advantage of 50 percent or more, compared to the risk extraction accuracy of manual evaluation by engineers. In addition, the speed of the automatic extraction and analysis of the system modules are 80 times faster than the engineer’s manual analysis time, thereby minimizing project loss due to errors or omissions due to design risk analysis during the project bidding period with a set deadline.
34
Liang, Gen, Xiaoxue Guo, Guoxi Sun e Jingcheng Fang. "A User-Oriented Intelligent Access Selection Algorithm in Heterogeneous Wireless Networks". Computational Intelligence and Neuroscience 2020 (24 de novembro de 2020): 1–20. http://dx.doi.org/10.1155/2020/8828355.
Texto completo da fonteResumo:
A heterogeneous wireless network (HWN) contains many kinds of wireless networks with overlapping areas of signal coverage. One of the research topics on HWNs is how to make users choose the most suitable network. This paper designs a user-oriented intelligent access selection algorithm in HWNs with five modules (input, user preference calculation, candidate network score calculation, output, and learning). Essentially, the input module uses a utility function to calculate the utility value of the judgment parameter; the user preference calculation module calculates the weight of the judgment parameter using the fuzzy analysis hierarchy process (FAHP) approach; the candidate network score calculation module calculates the network score through a fuzzy neural network; the output module calculates the error between the actual output value and the expected output value; and the learning module corrects the parameter of the membership function in the fuzzy neural network structure according to the error. Simulation results show that the algorithm proposed in this paper can enable users to select the most suitable network according to service characteristics and can enable users to obtain higher gains.
35
Li, Yuangang, Tao Guo, Qinghua Li e Xinyue Liu. "Optimized Feature Extraction for Sample Efficient Deep Reinforcement Learning". Electronics 12, n.º 16 (18 de agosto de 2023): 3508. http://dx.doi.org/10.3390/electronics12163508.
Texto completo da fonteResumo:
In deep reinforcement learning, agent exploration still has certain limitations, while low efficiency exploration further leads to the problem of low sample efficiency. In order to solve the exploration dilemma caused by white noise interference and the separation derailment problem in the environment, we present an innovative approach by introducing an intricately honed feature extraction module to harness the predictive errors, generate intrinsic rewards, and use an ancillary agent training paradigm that effectively solves the above problems and significantly enhances the agent’s capacity for comprehensive exploration within environments characterized by sparse reward distribution. The efficacy of the optimized feature extraction module is substantiated through comparative experiments conducted within the arduous exploration problem scenarios often employed in reinforcement learning investigations. Furthermore, a comprehensive performance analysis of our method is executed within the esteemed Atari 2600 experimental setting, yielding noteworthy advancements in performance and showcasing the attainment of superior outcomes in six selected experimental environments.
36
Hufri, Hufri, Sintia Sintia e Sri Indrawati Prihatin Ningsih. "Analisis Praktikalitas Modul Fisika Mengintegrasikan Kemampuan Berpikir Kreatif Pada Materi Hukum Newton". JURNAL EKSAKTA PENDIDIKAN (JEP) 6, n.º 2 (30 de novembro de 2022): 185–94. http://dx.doi.org/10.24036/jep/vol6-iss2/653.
Texto completo da fonteResumo:
This research is motivated by the low creativity of students' thinking in learning and teaching materials in schools have not fully facilitated students' creative thinking abilities. Creative thinking is very much needed in learning, therefore supporting teaching materials are needed that can facilitate students' creative thinking skills, one of which is a module. For this reason, researchers will develop a Physics module that integrates creative thinking skills in it. This study aims to determine the practicality of the Physics module developed on Newton's law material. This type of research is included in research and development or commonly called R&D research. The research model with the ADDIE step is the model used in this study. The reason for choosing this model is that this model is suitable for module development because each stage carries out an evaluation so as to minimize product errors. for data collection in this study used a practicality test questionnaire that had previously been validated. This practicality test questionnaire was filled out by practitioners consisting of three teachers and 30 students. The data analysis technique uses a practical analysis of the module which is weighted using a Likert scale. The average practicality value of the Physics module by teachers and students who integrate students' creative thinking skills into Newton's law material is 86% and 91% with very practical criteria so that it can be stated that the Physics module has high practicality and can be used in learning.
37
Sun, Jie, Zhaoying Ding, Xiaoshuang Chen, Qi Chen, Yincheng Wang, Kaiqiao Zhan e Ben Wang. "CREAD: A Classification-Restoration Framework with Error Adaptive Discretization for Watch Time Prediction in Video Recommender Systems". Proceedings of the AAAI Conference on Artificial Intelligence 38, n.º 8 (24 de março de 2024): 9027–34. http://dx.doi.org/10.1609/aaai.v38i8.28752.
Texto completo da fonteResumo:
The watch time is a significant indicator of user satisfaction in video recommender systems. However, the prediction of watch time as a target variable is often hindered by its highly imbalanced distribution with a scarcity of observations for larger target values and over-populated samples for small values. State-of-the-art watch time prediction models discretize the continuous watch time into a set of buckets in order to consider the distribution of watch time. However, it is highly uninvestigated how these discrete buckets should be created from the continuous watch time distribution, and existing discretization approaches suffer from either a large learning error or a large restoration error. To address this challenge, we propose a Classification-Restoration framework with Error-Adaptive-Discretization (CREAD) to accurately predict the watch time. The proposed framework contains a discretization module, a classification module, and a restoration module. It predicts the watch time through multiple classification problems. The discretization process is a key contribution of the CREAD framework. We theoretically analyze the impacts of the discretization on the learning error and the restoration error, and then propose the error-adaptive discretization (EAD) technique to better balance the two errors, which achieves better performance over traditional discretization approaches. We conduct detailed offline evaluations on a public dataset and an industrial dataset, both showing performance gains through the proposed approach. Moreover, We have fully launched our framework to an online video platform, which resulted in a significant increase in users' video watch time by 0.29% through A/B testing. These results highlight the effectiveness of the CREAD framework in watch time prediction in video recommender systems.
38
Eroshenko, Stanislav, e Alexandra Khalyasmaa. "Weather data errors analysis in solar power stations generation forecasting". E3S Web of Conferences 51 (2018): 02002. http://dx.doi.org/10.1051/e3scconf/20185102002.
Texto completo da fonteResumo:
The paper presents a short-term forecasting model for solar power stations (SPS) generation developed by the authors. This model is based on weather data and built into the existing software product as a separate short-term forecasting module for the SPS generation. The main problems associated with forecasting the SPS generation on cloudy days were revealed in the framework of authors' research, which is due not to the error of the developed model but to the use of the same learning sample for both solar and cloudy days. This paper contains analysis of the main problems related to the learning sampling, samples pattern, quality and representativeness for forecasting the SPS generation on cloudy days. Besides, the paper includes a calculation example performed for the existing SPS and a detailed analysis of the forecast generation on cloudy days based on the actual weather provider data.
39
Eroshenko, Stanislav, e Alexandra Khalyasmaa. "Weather data errors analysis in solar power stations generation forecasting". E3S Web of Conferences 51 (2018): 02002. http://dx.doi.org/10.1051/e3sconf/20185102002.
Texto completo da fonteResumo:
The paper presents a short-term forecasting model for solar power stations (SPS) generation developed by the authors. This model is based on weather data and built into the existing software product as a separate short-term forecasting module for the SPS generation. The main problems associated with forecasting the SPS generation on cloudy days were revealed in the framework of authors' research, which is due not to the error of the developed model but to the use of the same learning sample for both solar and cloudy days. This paper contains analysis of the main problems related to the learning sampling, samples pattern, quality and representativeness for forecasting the SPS generation on cloudy days. Besides, the paper includes a calculation example performed for the existing SPS and a detailed analysis of the forecast generation on cloudy days based on the actual weather provider data.
40
Pu, Yongming, e Hongming Chen. "Exercise Recommendation Model Based on Cognitive Level and Educational Big Data Mining". Journal of Function Spaces 2022 (27 de julho de 2022): 1–11. http://dx.doi.org/10.1155/2022/3845419.
Texto completo da fonteResumo:
There are differences in the learning ability and cognitive ability of different learners. The unified exercises of traditional teaching ignore the differences of learners and cannot meet the personalized needs of learners. Previous recommendation systems focus on the optimization of recommendation performance, rarely clearly reflect the learning state of learners’ knowledge points, and there are large errors in the recommendation results. This paper combines the comprehensive cognitive analysis module and the classified knowledge point cognitive analysis module to analyze the cognitive degree of learners’ knowledge points. Based on the analysis results, appropriate exercises are selected from the educational resource data to form a list to be recommended. The experimental results show that the exercise recommendation algorithm based on cognitive level and data mining has better recommendation effect and accuracy than the other two recommendation models. The error between the actual difficulty of recommended exercises and the index value is very small. It can recommend an appropriate exercise list according to the actual situation of learners. The teaching comparison results show that the exercise recommendation algorithm can meet the personalized needs of students, recommend targeted exercises, and effectively and greatly improve the learning effect and test scores in a short time. When the motion recommendation algorithm based on cognitive level and data mining has the best recommendation effect, the cognitive module of classifying knowledge points accounts for a large proportion in parameter adjustment. Compared with other recommendation systems, this model has higher accuracy and recommendation effect.
41
Choi, So-Won, Eul-Bum Lee e Jong-Hyun Kim. "The Engineering Machine-Learning Automation Platform (EMAP): A Big-Data-Driven AI Tool for Contractors’ Sustainable Management Solutions for Plant Projects". Sustainability 13, n.º 18 (17 de setembro de 2021): 10384. http://dx.doi.org/10.3390/su131810384.
Texto completo da fonteResumo:
Plant projects, referred to as Engineering Procurement and Construction (EPC), generate massive amounts of data throughout their life cycle, from the planning stages to the operation and maintenance (OM) stages. Many EPC contractors struggle with their projects due to the complexity of the decision-making processes, owing to the vast amount of project data generated during each project stage. In line with the fourth industrial revolution, the demand for engineering project management solutions to apply artificial intelligence (AI) in big data technology is increasing. The purpose of this study was to predict the risk of contractor and support decision-making at each project stage using machine-learning (ML) technology based on data generated in the bidding, engineering, construction, and OM stages of EPC projects. As a result of this study, the Engineering Machine-learning Automation Platform (EMAP), a cloud-based integrated analysis tool applied with big data and AI/ML technology, was developed. EMAP is an intelligent decision support system that consists of five modules: Invitation to Bid (ITB) Analysis, Design Cost Estimation, Design Error Checking, Change Order Forecasting, and Equipment Predictive Maintenance, using advanced AI/ML algorithms. In addition, each module was validated through case studies to assure the performance and accuracy of the module. This study contributes to the strengthening of the risk response for each stage of the EPC project, especially preventing errors by the project managers, and improving their work accuracy. Project risk management using AI/ML breaks away from the existing risk management practices centered on statistical analysis, and further expands the research scalability of related works.
42
Li, Jie, Runran Li, Yuanjie Jia e Zhixin Zhang. "Prediction of I–V Characteristic Curve for Photovoltaic Modules Based on Convolutional Neural Network". Sensors 20, n.º 7 (9 de abril de 2020): 2119. http://dx.doi.org/10.3390/s20072119.
Texto completo da fonteResumo:
Photovoltaic (PV) modules are exposed to the outside, which is affected by radiation, the temperature of the PV module back-surface, relative humidity, atmospheric pressure and other factors, which makes it difficult to test and analyze the performance of photovoltaic modules. Traditionally, the equivalent circuit method is used to analyze the performance of PV modules, but there are large errors. In this paper—based on machine learning methods and large amounts of photovoltaic test data—convolutional neural network (CNN) and multilayer perceptron (MLP) neural network models are established to predict the I–V curve of photovoltaic modules. Furthermore, the accuracy and the fitting degree of these methods for current–voltage (I–V) curve prediction are compared in detail. The results show that the prediction accuracy of the CNN and MLP neural network model is significantly better than that of the traditional equivalent circuit models. Compared with MLP models, the CNN model has better accuracy and fitting degree. In addition, the error distribution concentration of CNN has better robustness and the pre-test curve is smoother and has better nonlinear segment fitting effects. Thus, the CNN is superior to MLP model and the traditional equivalent circuit model in complex climate conditions. CNN is a high-confidence method to predict the performance of PV modules.
43
Yin, Yunsheng, e Linhai Xu. "MGCNet: Low-cost MEMS gyro correction network". Journal of Physics: Conference Series 2820, n.º 1 (1 de agosto de 2024): 012038. http://dx.doi.org/10.1088/1742-6596/2820/1/012038.
Texto completo da fonteResumo:
Abstract MEMS gyro is widely used in the field of autonomous system navigation, but due to the large measurement error of low-cost MEMS gyro, the orientation estimation of gyro carriers cannot be met by simple calibration only. In this paper, we propose a learning method to correct the measurement error of MEMS gyro in IMU. Our method utilizes dilated convolution to increase the receptive field, designs a lightweight attention module to extract the gyro random error, and uses channel transformation to extract deterministic errors. We also design a multi-timescale loss function, enabling the network to notice the cumulative orientation errors at different timescales. We tested our method on public datasets EUROC and TUM-VI and compared it with the Visual-Inertial Odometry (VIO) methods as well as other gyro correction methods. The experimental results show that the proposed method can have comparable or even higher accuracy of orientation estimation than the visual inertial combination method, and the gyro orientation estimation error using MGCNet correction is reduced by 15-20% compared to other advanced gyro processing methods.
44
Wang, Jinhong, e Wei Yao. "An End-to-End Geometric Characterization-aware Semantic Instance Segmentation Network for ALS Point Clouds". International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences XLVIII-2-2024 (11 de junho de 2024): 435–42. http://dx.doi.org/10.5194/isprs-archives-xlviii-2-2024-435-2024.
Texto completo da fonteResumo:
Abstract. Semantic instance segmentation from scenes, serving as a crucial role for 3D modelling and scene understanding. Conducting semantic segmentation before grouping instances is adopted by the existing state-of-the-art methods. However, without additional refinement, semantic errors will fully propagate into the grouping stage, resulting in low overlap with the ground truth instance. Furthermore, the proposed methods focused on indoor level scenes, which are limited when directly applied to large-scale outdoor Airborne Laser Scanning (ALS) point clouds. Numerous instances, significant object density and scale variations make ALS point clouds distinct from indoor data. In order to address the problems, we proposed a geometric characterization-aware semantic instance segmentation network, which utilized both semantic and objectness score to select potential points for grouping. And in point cloud feature learning stage, hand-craft geometry features are taken as input for geometric characterization awareness. Moreover, to address errors propagated from previous modules after grouping, we have additionally designed a per-instance refinement module. To assess semantic instance segmentation, we conducted experiments on an open-source dataset. Additionally, we performed semantic segmentation experiments to evaluate the performance of our proposed point cloud feature learning method.
45
Meritet, Danielle, M. Elena Gorman, Katy L. Townsend, Patrick Chappell, Laura Kelly e Duncan S. Russell. "Investigating the Effects of Error Management Training versus Error Avoidance Training on the Performance of Veterinary Students Learning Blood Smear Analysis". Journal of Veterinary Medical Education 48, n.º 3 (junho de 2021): 319–29. http://dx.doi.org/10.3138/jvme.2019-0055.
Texto completo da fonteResumo:
Conventional veterinary training emphasizes correct methodologies, potentially failing to exploit learning opportunities that arise as a result of errors. Error management training (EMT) encourages mistakes during low-stakes training, with the intention of modifying perceptions toward errors and using them to improve performance in unfamiliar scenarios (adaptive transfer). Herein, we aimed to determine the efficacy of EMT, supplemented by a metacognitive module, for veterinary students learning blood smear preparation and interpretation. Our hypothesis was that EMT and metacognition are associated with improved adaptive transfer performance, as compared with error avoidance training (EAT). A total of 26 students were prospectively enrolled in this double-blind study. Performance was evaluated according to monolayer area, smear quality, cell identification, calculated white blood cell differential counts, and overall application/interpretation. Students were trained with normal canine blood and static photomicrographs. Participants tested 72 hours after training demonstrated improved performance in a test that directly recapitulated training (Wilcoxon matched-pairs signed-rank test; two-tailed p all ≤ .001). There were no significant differences between EAT and EMT in this test (Mann–Whitney U test and Welch’s t-test; two-tailed p ≥ .26) or in short- and long-term adaptive transfer tests ( p ≥ .22). Survey data indicate that participants found errors to be a valuable element of training, and that many felt capable of accurately reflecting on their own performance. These data suggest that EMT might produce outcomes comparable to EAT as it relates to blood smear analysis.
46
Rosmawati, Rosmawati, Zarwan Zarwan, Yuni Astuti, Dessi Novita Sari, Zulbahri Zulbahri e Erianti Erianti. "E-module design of sport modification and cybergogy-based small games". Linguistics and Culture Review 6 (24 de janeiro de 2022): 264–74. http://dx.doi.org/10.21744/lingcure.v6ns3.2143.
Texto completo da fonteResumo:
The low learning outcomes of students in the subject of modification of sports and small games are considered as the problem in this research that is mostly caused by the lack of learning media facilities for students in the online classes that leads them to difficulty in understanding the provided learning materials. This study aims to develop an e-module on the subject of modification of sports and small games. The ADDIE development model is being used in this Research and Development (R&D). There are several activities needed as the research method, such as exploring the potential and actual problems, collecting all information by developing, validating, revising, conducting trials and errors of the game models for the effectiveness and efficiency of the model used. The results of the study showed from the experts of materials that at the development stage and the level of validity by the score of 3.60 which was in the highly valid by the percentage of 90.5%. From the media experts validation by the score of 3.65 which was high valid category by the percentage of 92, 55%.
47
Zhang, Qi, Wenjin Sun, Huaihai Guo, Changming Dong e Hong Zheng. "A Transfer Learning-Enhanced Generative Adversarial Network for Downscaling Sea Surface Height through Heterogeneous Data Fusion". Remote Sensing 16, n.º 5 (22 de fevereiro de 2024): 763. http://dx.doi.org/10.3390/rs16050763.
Texto completo da fonteResumo:
In recent decades, satellites have played a pivotal role in observing ocean dynamics, providing diverse datasets with varying spatial resolutions. Notably, within these datasets, sea surface height (SSH) data typically exhibit low resolution, while sea surface temperature (SST) data have significantly higher resolution. This study introduces a Transfer Learning-enhanced Generative Adversarial Network (TLGAN) for reconstructing high-resolution SSH fields through the fusion of heterogeneous SST data. In contrast to alternative deep learning approaches that involve directly stacking SSH and SST data as input channels in neural networks, our methodology utilizes bifurcated blocks comprising Residual Dense Module and Residual Feature Distillation Module to extract features from SSH and SST data, respectively. A pixelshuffle module-based upscaling block is then concatenated to map these features into a common latent space. Employing a hybrid strategy involving adversarial training and transfer learning, we overcome the limitation that SST and SSH data should share the same time dimension and achieve significant resolution enhancement in SSH reconstruction. Experimental results demonstrate that, when compared to interpolation method, TLGAN effectively reduces reconstruction errors and fusing SST data could significantly enhance in generating more realistic and physically plausible results.
48
Ramírez-Carvajal, L. E., K. Puerto-López e S. Castro-Casadiego. "Computational tool for learning electrostatic physics through the development of a disruptive methodology". Journal of Physics: Conference Series 2159, n.º 1 (1 de janeiro de 2022): 012005. http://dx.doi.org/10.1088/1742-6596/2159/1/012005.
Texto completo da fonteResumo:
Abstract A computational tool for learning electrostatic physics is presented through the development of a disruptive methodology. The tool allows the analysis of case studies based on Coulomb’s law, Gauss’s law, Poisson’s equation, and Laplace’s equation with boundary value. The tool was tested using reference exercises for each case study, making use of quantitative and qualitative comparative analysis between the traditional mathematical development and the computational tool. Errors were measured using Likert scale. The quantitative results showed errors of less than 1.8% in all the cases studied, concluding that the tool is effective. The qualitative results showed that the methodology allows a better development of the electrostatics learning process, dynamizing the study of complex topics such as electromagnetic physics theories through interactivity and technological resources, in addition to having a theoretical module developed using agile methodologies that provide dynamism and an intuitive environment to the interface.
49
Teixeira, Joaquim V., Hai Nguyen, Derek J. Posselt, Hui Su e Longtao Wu. "Using machine learning to model uncertainty for water vapor atmospheric motion vectors". Atmospheric Measurement Techniques 14, n.º 3 (9 de março de 2021): 1941–57. http://dx.doi.org/10.5194/amt-14-1941-2021.
Texto completo da fonteResumo:
Abstract. Wind-tracking algorithms produce atmospheric motion vectors (AMVs) by tracking clouds or water vapor across spatial–temporal fields. Thorough error characterization of wind-tracking algorithms is critical in properly assimilating AMVs into weather forecast models and climate reanalysis datasets. Uncertainty modeling should yield estimates of two key quantities of interest: bias, the systematic difference between a measurement and the true value, and standard error, a measure of variability of the measurement. The current process of specification of the errors in inverse modeling is often cursory and commonly consists of a mixture of model fidelity, expert knowledge, and need for expediency. The method presented in this paper supplements existing approaches to error specification by providing an error characterization module that is purely data-driven. Our proposed error characterization method combines the flexibility of machine learning (random forest) with the robust error estimates of unsupervised parametric clustering (using a Gaussian mixture model). Traditional techniques for uncertainty modeling through machine learning have focused on characterizing bias but often struggle when estimating standard error. In contrast, model-based approaches such as k-means or Gaussian mixture modeling can provide reasonable estimates of both bias and standard error, but they are often limited in complexity due to reliance on linear or Gaussian assumptions. In this paper, a methodology is developed and applied to characterize error in tracked wind using a high-resolution global model simulation, and it is shown to provide accurate and useful error features of the tracked wind.
50
Fayaz, Muhammad, Israr Ullah e DoHyeun Kim. "An Optimized Fuzzy Logic Control Model Based on a Strategy for the Learning of Membership Functions in an Indoor Environment". Electronics 8, n.º 2 (28 de janeiro de 2019): 132. http://dx.doi.org/10.3390/electronics8020132.
Texto completo da fonteResumo:
The Mamdani fuzzy inference method is one of the most important fuzzy logic control (FLC) techniques and has several applications in different fields. Despite its applications, the Mamdani fuzzy inference method has some core issues which still require solutions. The most critical issue is the selection of accurate shape and boundaries of membership functions (MFs) in the universe of discourse. In this work, we introduced a methodology called learning to control (LtC) to resolve the problem. The proposed methodology consisted of two main modules, namely, a control algorithm (CA) module and a learning algorithm (LA) module. In the CA module, the Mamdani FLC method has been used, whereas, in the LA module, we have used the artificial neural network (ANN) algorithm. Inputs into the ANN were the error difference between environmental temperature and the required temperature. The output of the ANN was the MF set to the FLC. Inputs into the fuzzy logic controller (FLC) were the error difference between environmental temperature and required temperature (D), and the output was the required power for the fan actuator. The purpose of the ANN was to tune the MFs of the FLC to improve its efficiency. The proposed learning-to-control method along with the conventional fuzzy logic controller method was applied to the data to evaluate the model’s performance. The results indicate that the proposed model’s performance is far better than that of conventional fuzzy logic techniques.