Neurocomputing, Год журнала: 2022, Номер 500, С. 1041 - 1051
Опубликована: Июнь 8, 2022
Язык: Английский
Journal of Systems and Software, Год журнала: 2022, Номер 195, С. 111537 - 111537
Опубликована: Окт. 12, 2022
Automated software defect prediction (SDP) methods are increasingly applied, often with the use of machine learning (ML) techniques. Yet, existing ML-based approaches require manually extracted features, which cumbersome, time consuming and hardly capture semantic information reported in bug reporting tools. Deep (DL) techniques provide practitioners opportunities to automatically extract learn from more complex high-dimensional data. The purpose this study is systematically identify, analyze, summarize, synthesize current state utilization DL algorithms for SDP literature. We selected a pool 102 peer-reviewed studies then conducted quantitative qualitative analysis using data these studies. Main highlights include: (1) most applied supervised DL; (2) two third used metrics as an input algorithms; (3) Convolutional Neural Network frequently algorithm. Based on our findings, we propose develop comprehensive that needed features; diverse artifacts other than source code; adopt augmentation tackle class imbalance problem; (4) publish replication packages.
Язык: Английский
Процитировано
82
Digital Health, Год журнала: 2023, Номер 9
Опубликована: Янв. 1, 2023
Artificial Intelligent (AI) applications in e-health have evolved considerably the last 25 years. To track current research progress this field, there is a need to analyze most recent trend of adopting AI e-health. This bibliometric analysis study covers It differs from existing literature review as journal articles are obtained Scopus database its beginning late 2021 (25 years), which depicts The employed find statistical and quantitative available specific field for particular period. An extensive global performed identify significant area, authors, or their relationship through published articles. also provides researchers with an overview work evolution fields. study's main contribution highlights essential journals, institutes, keywords, states developing
Язык: Английский
Процитировано
26
Natural Language Processing Journal, Год журнала: 2025, Номер unknown, С. 100125 - 100125
Опубликована: Янв. 1, 2025
Язык: Английский
Процитировано
1
Computers & Education, Год журнала: 2022, Номер 193, С. 104682 - 104682
Опубликована: Ноя. 17, 2022
Research shows that effective teaching behavior is important for students' learning and outcomes, scholars have developed various instruments measuring domains. Although student assessments are frequently used evaluating behavior, they mainly in Likert-scale or categorical forms, which precludes students from freely expressing their perceptions of teaching. Drawing on an open-ended questionnaire large-scale surveys, this study uses a machine tool aiming to extract topics answers test the convergent validity outcomes by comparing them with theory-driven manual coding based expert judgments. We applied latent Dirichlet allocation (LDA) topic modeling analysis, together visualization (LDAvis), qualitative data collected 173,858 secondary education Netherlands. This data-driven analysis yielded eight domains: Clear explanation, Student-centered supportive climate, Lesson variety, Likable characteristics teacher, Evoking interest, Monitoring understanding, Inclusiveness equity, objectives formative assessment. In addition, we subjected 864 randomly selected responses same dataset coding, performed content resulted nine domains 19 sub-domains. Results suggest relation between human complementary. By bottom-up (machine analysis) top-down (content analysis), found proposed approach reveals unique confirmed evident overlapping topics.
Язык: Английский
Процитировано
38
Information Processing & Management, Год журнала: 2022, Номер 60(2), С. 103145 - 103145
Опубликована: Ноя. 18, 2022
Язык: Английский
Процитировано
28
Brain Informatics, Год журнала: 2022, Номер 9(1)
Опубликована: Фев. 12, 2022
Abstract Brain informatics is a novel interdisciplinary area that focuses on scientifically studying the mechanisms of human brain information processing by integrating experimental cognitive neuroscience with advanced Web intelligence-centered technologies. intelligence, which aims to understand computational, cognitive, physical, and social foundations future Web, has attracted increasing attention facilitate study promote health. A large number articles created in recent few years are proof investment intelligence-assisted This systematically reviews academic studies regarding article trends, top journals, subjects, countries/regions, institutions, design, artificial intelligence technologies, clinical tasks, performance evaluation. Results indicate literature especially welcomed subjects such as medical health care sciences service . There several promising topics, for example, random forests, support vector machines, conventional neural networks disease detection diagnosis, semantic ontology mining, topic modeling or biomedical text logistic regression prediction, convolutional machines monitoring classification. Additionally, research should focus algorithm innovations, additional use, functionality improvement, model system generalization, scalability, evaluation, automation, data acquirement quality allowing interaction. The findings this help better what how can be applied healthcare procedures outcomes. provides important insights into effective use informatics-enabled studies.
Язык: Английский
Процитировано
23
Electronics, Год журнала: 2024, Номер 13(13), С. 2537 - 2537
Опубликована: Июнь 28, 2024
This paper presents a comprehensive survey of knowledge graphs in education. It covers the patterns and prospects research this area. A total 48 relevant publications between 2011 2023 were collected from Web Science, Scopus, ProQuest for review. The findings reveal sharp increase recent years body into educational which was mainly conducted institutions China. Most work adopted quantitative method, such as performance evaluation, user surveys, controlled experiments, to assess effectiveness graph approaches. also suggest that approaches primarily researched implemented higher education institutions, with focus on computer science, mathematics, engineering. most frequently addressed objectives included enhancing representation providing personal learning recommendations, common applications concept instruction recommendations. Diverse data resources, course materials, student behaviours, online encyclopaedia, processed implement different scenarios. Relevant technical means employed implementation dealt purposes building ontology, achieving creating graphs. Various pedagogies personalised collaborative are supported by identified key limitations work, including insufficient information construction, difficulty extending across subject areas, restricted scale scope lack feedback evaluation processes.
Язык: Английский
Процитировано
5
Digital Health, Год журнала: 2024, Номер 10
Опубликована: Янв. 1, 2024
The modern era of cognitive intelligence in clinical space has led to the rise 'Medical Cognitive Virtual Agents' (MCVAs) which are labeled as intelligent virtual assistants interacting with users a context-sensitive and ambient manner. They aim augment users' capabilities thereby helping both patients medical experts providing personalized healthcare like remote health tracking, emergency robotic diagnosis critical illness, among others. objective this study is explore technical aspects MCVA their relevance healthcare.
Язык: Английский
Процитировано
5
ISPRS International Journal of Geo-Information, Год журнала: 2024, Номер 13(7), С. 255 - 255
Опубликована: Июль 16, 2024
The geoscience knowledge graph (GeoKG) has gained worldwide attention due to its ability in the formal representation of spatiotemporal features and relationships knowledge. Currently, a quantitative review state trends GeoKG is still scarce. Thus, bibliometric analysis was performed this study fill gap. Specifically, based on 294 research articles published from 2012 2023, we conducted analyses terms (1) publications citations; (2) identification major papers, sources, researchers, institutions, countries; (3) scientific collaboration analysis; (4) detection topics tendencies. results revealed that interest rapidly increased after 2019 continually expanding. China most productive country field. Co-authorship shows inter-national inter-institutional should be reinforced. Keyword indicated representation, information extraction, construction, GeoKG-based multi-source data integration were current hotspots. In addition, several important but currently neglected issues, such as Large Language Models, are highlighted. findings provide systematic overview development valuable reference for future research.
Язык: Английский
Процитировано
4
International Journal of Molecular Sciences, Год журнала: 2025, Номер 26(2), С. 477 - 477
Опубликована: Янв. 8, 2025
Due to advances in big data technology, deep learning, and knowledge engineering, biological sequence visualization has been extensively explored. In the post-genome era, enables visual representation of both structured unstructured data. However, a universal method for all types sequences not reported. Biological are rapidly expanding exponentially acquisition, extraction, fusion, inference from critical supporting technologies research. These areas important require in-depth exploration. This paper elaborates on comprehensive overview methods DNA four different perspectives-two-dimensional, three-dimensional, four-dimensional, dynamic approaches-and discusses strengths limitations each detail. Furthermore, this proposes two potential future research directions response challenges inefficient graphical feature extraction association network generation existing methods. The first direction is construction graphs data, second cross-modal using machine learning review anticipated provide valuable insights contributions computational biology, bioinformatics, genomic computing, genetic breeding, evolutionary analysis, other related disciplines fields medicine, chemistry, statistics, computing. It an reference value recommendation systems question answering systems.
Язык: Английский
Процитировано
0