Biblio Discovery — Demo Discovery Service

27 hasil untuk "Matwin, Stan"

Menampilkan 1–20 · 0,40 detik · RSS

  1. Artikel Jurnal Teks lengkap

    A comparative case study on the performance of global sensitivity analysis methods on digit classification

    Sadeghi, Zahra; Matwin, Stan

    Discov Data · 2025 · Inggris · PubMed Central

    Global sensitivity analysis seeks to detect influential input factors contributing to a black-box model’s specific decisions. This aligns with a key objective of AI explainability: Clarifying and interpreting the behavior of machine learning algorithms by identifying the features that influence…

  2. Artikel Jurnal

    Anomaly detection for maritime navigation based on probability density function of error of reconstruction

    Sadeghi Zahra; Matwin Stan

    Journal of Intelligent Systems, Vol. 32 No. 1 · 2023 · Inggris · DOAJ Scopus

    Anomaly detection is a fundamental problem in data science and is one of the highly studied topics in machine learning. This problem has been addressed in different contexts and domains. This article investigates anomalous data within time series data in the maritime sector. Since there is no…

  3. Artikel Jurnal Teks lengkap

    Annotation concept synthesis and enrichment analysis: a logic-based approach to the interpretation of high-throughput experiments

    Jiline, Mikhail; Matwin, Stan; Turcotte, Marcel

    Bioinformatics · 2011 · Inggris · PubMed Central

    Motivation: Annotation Enrichment Analysis (AEA) is a widely used analytical approach to process data generated by high-throughput genomic and proteomic experiments such as gene expression microarrays. The analysis uncovers and summarizes discriminating background information (e.g. GO annotations)…

  4. Artikel Jurnal Teks lengkap

    deepBioWSD: effective deep neural word sense disambiguation of biomedical text data

    Pesaranghader, Ahmad; Matwin, Stan; Sokolova, Marina dkk.

    J Am Med Inform Assoc · 2019 · Inggris · PubMed Central

    OBJECTIVE: In biomedicine, there is a wealth of information hidden in unstructured narratives such as research articles and clinical reports. To exploit these data properly, a word sense disambiguation (WSD) algorithm prevents downstream difficulties in the natural language processing applications…

  5. Artikel Jurnal Teks lengkap

    Dynamics of emotion trends in Canadian Twitter users during COVID-19 confinement in relation to caseloads: Artificial intelligence-based emotion detection approach

    Weerasinghe, Swarna; Oyebode, Oladapo; Orji, Rita dkk.

    Digit Health · 2023 · Inggris · PubMed Central

    Multiple waves of COVID-19 have significantly impacted the emotional well-being of all, but many were subject to additional risks associated with forced regulations. The objective of this research was to assess the immediate emotional impact, expressed by Canadian Twitter users, and to estimate the…

  6. Artikel Jurnal Teks lengkap

    A Semi-Supervised Methodology for Fishing Activity Detection Using the Geometry behind the Trajectory of Multiple Vessels

    Ferreira, Martha Dais; Spadon, Gabriel; Soares, Amilcar dkk.

    Sensors (Basel) · 2022 · Inggris · PubMed Central

    Automatic Identification System (AIS) messages are useful for tracking vessel activity across oceans worldwide using radio links and satellite transceivers. Such data play a significant role in tracking vessel activity and mapping mobility patterns such as those found during fishing activities…

  7. Artikel Jurnal Teks lengkap

    A new algorithm for reducing the workload of experts in performing systematic reviews

    Matwin, Stan; Kouznetsov, Alexandre; Inkpen, Diana dkk.

    J Am Med Inform Assoc · 2010 · Inggris · PubMed Central

    OBJECTIVE: To determine whether a factorized version of the complement naïve Bayes (FCNB) classifier can reduce the time spent by experts reviewing journal articles for inclusion in systematic reviews of drug class efficacy for disease treatment. DESIGN: The proposed classifier was evaluated on a…

  8. Artikel Jurnal Teks lengkap

    Engineering of a Clinical Decision Support Framework for the Point of Care Use

    Wilk, Szymon; Michalowski, Wojtek; O’Sullivan, Dympna dkk.

    AMIA Annu Symp Proc · 2008 · Inggris · PubMed Central

    Computerized decision support for use at the point of care has to be comprehensive. It means that clinical information stored in electronic health records needs to be integrated with various forms of clinical knowledge (elicited from experts, discovered from data or summarized in systematic reviews…

  9. Artikel Jurnal Teks lengkap

    Improving Fishing Pattern Detection from Satellite AIS Using Data Mining and Machine Learning

    de Souza, Erico N.; Boerder, Kristina; Matwin, Stan dkk.

    PLoS One · 2016 · Inggris · PubMed Central

    A key challenge in contemporary ecology and conservation is the accurate tracking of the spatial distribution of various human impacts, such as fishing. While coastal fisheries in national waters are closely monitored in some countries, existing maps of fishing effort elsewhere are fraught with…

  10. Artikel Jurnal Teks lengkap

    Examining the impact of cross-domain learning on crime prediction

    Bappee, Fateha Khanam; Soares, Amilcar; Petry, Lucas May dkk.

    J Big Data · 2021 · Inggris · PubMed Central

    Nowadays, urban data such as demographics, infrastructure, and criminal records are becoming more accessible to researchers. This has led to improvements in quantitative crime research for predicting future crime occurrence by identifying factors and knowledge from instances that contribute to…

  11. Artikel Jurnal Teks lengkap

    Enhancing global maritime traffic network forecasting with gravity-inspired deep learning models

    Song, Ruixin; Spadon, Gabriel; Pelot, Ronald dkk.

    Sci Rep · 2024 · Inggris · PubMed Central

    Aquatic non-indigenous species (NIS) pose significant threats to biodiversity, disrupting ecosystems and inflicting substantial economic damages across agriculture, forestry, and fisheries. Due to the fast growth of global trade and transportation networks, NIS has been introduced and spread…

  12. Artikel Jurnal Teks lengkap

    Association between surgical wait time and hospital length of stay in primary total knee and hip arthroplasty

    Seddigh, Shahriar; Lethbridge, Lynn; Theriault, Patrick dkk.

    Bone Jt Open · 2021 · Inggris · PubMed Central

    AIMS: In countries with social healthcare systems, such as Canada, patients may experience long wait times and a decline in their health status prior to their operation. The aim of this study is to explore the association between long preoperative wait times (WT) and acute hospital length of stay…

  13. Preprint Teks lengkap

    Joint-Centric Dual Contrastive Alignment with Structure-Preserving and Information-Balanced Regularization

    Naderi, Habibeh; Soleimani, Behrouz Haji; Matwin, Stan

    arXiv · 2026 · Inggris · arXiv

    We propose HILBERT (HIerarchical Long-sequence Balanced Embedding with Reciprocal contrastive Training), a cross-attentive multimodal framework for learning document-level audio-text representations from long, segmented sequences in low-resource data settings. HILBERT leverages frozen pre-trained…

  14. Preprint Teks lengkap

    Beyond Feature Fusion: Contextual Bayesian PEFT for Multimodal Uncertainty Estimation

    Naderi, Habibeh; Soleimani, Behrouz Haji; Matwin, Stan

    arXiv · 2026 · Inggris · arXiv

    We introduce CoCo-LoRA, a multimodal, uncertainty-aware parameter-efficient fine-tuning method for text prediction tasks accompanied by audio context. Existing PEFT approaches such as LoRA are efficient but typically deterministic, while recent Bayesian low-rank adapters model uncertainty in a…

  15. Preprint Teks lengkap

    Cross-Modal Bayesian Low-Rank Adaptation for Uncertainty-Aware Multimodal Learning

    Naderi, Habibeh; Soleimani, Behrouz Haji; Matwin, Stan

    arXiv · 2026 · Inggris · arXiv

    Large pre-trained language models are increasingly adapted to downstream tasks using parameter-efficient fine-tuning (PEFT), but existing PEFT methods are typically deterministic and unimodal, making them poorly suited for low-resource multimodal settings where predictive uncertainty and…

  16. Artikel Jurnal Teks lengkap

    deepSimDEF: deep neural embeddings of gene products and gene ontology terms for functional analysis of genes

    Pesaranghader, Ahmad; Matwin, Stan; Sokolova, Marina dkk.

    Bioinformatics · 2022 · Inggris · PubMed Central

    MOTIVATION: There is a plethora of measures to evaluate functional similarity (FS) of genes based on their co-expression, protein–protein interactions and sequence similarity. These measures are typically derived from hand-engineered and application-specific metrics to quantify the degree of shared…

  17. Artikel Jurnal Teks lengkap

    Can Anonymous Posters on Medical Forums be Reidentified?

    Bobicev, Victoria; Sokolova, Marina; El Emam, Khaled dkk.

    J Med Internet Res · 2013 · Inggris · PubMed Central

    BACKGROUND: Participants in medical forums often reveal personal health information about themselves in their online postings. To feel comfortable revealing sensitive personal health information, some participants may hide their identity by posting anonymously. They can do this by using fake…