Payman Goodarzi, D. Arendes, Christian Bur, Andreas Schuetze
{"title":"P26 - Robust Indoor Air Quality Monitoring: Out-of-Distribution Detection using Ensemble Neural Networks","authors":"Payman Goodarzi, D. Arendes, Christian Bur, Andreas Schuetze","doi":"10.5162/17dss2024/p26","DOIUrl":"https://doi.org/10.5162/17dss2024/p26","url":null,"abstract":"Data-driven indoor air quality (IAQ) monitoring systems have demonstrated strong performance; however, detecting out-of-range data is essential for reliable monitoring.This study proposes an out-of-distribution (OOD) detection method to identify out-ofrange conditions and temporal drift in real-time applications.Our approach utilizes an ensemble of convolutional neural networks (CNNs) optimized via Bayesian hyperparameter tuning.The method achieved robust results, with an area under the receiver operating characteristic curve (AUC) of 93% for out-of-range gas detection and AUCs of 95% and 99% for identifying temporal drift at six and ten weeks post-calibration, respectively.Integrating this method into real-time IAQ monitoring systems enhances model reliability under real-world conditions.","PeriodicalId":92161,"journal":{"name":"Workshops & poster abstracts : [proceedings]. IEEE Computational Systems Bioinformatics Conference","volume":"1 1","pages":"160-164"},"PeriodicalIF":0.0,"publicationDate":"2024-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ama-science.org/proceedings/getFile/AGtmZD==","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147891624","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"96 Super-partnerships vs traditional practices: a qualitative study examining general practitioners’ experiences of leadership","authors":"Elizabeth Moor","doi":"10.1136/leader-2019-fmlm.96","DOIUrl":"https://doi.org/10.1136/leader-2019-fmlm.96","url":null,"abstract":"<h3>Background</h3> General practice has been identified as the backbone of the NHS, yet it is under increasing pressure. One change occurring in general practice is the move towards larger organisations from smaller traditional practices. These new structures bring an emerging complexity regarding leadership. It is unknown how well leadership is being executed in super-partnerships. This is an important subject as there is evidence to show that good leadership in a system corresponds to better quality of care delivered. A key aspect that is being missed in current research is how the workforce feels about their leadership roles in these new super-partnerships compared to smaller traditional practices. <h3>Methodology</h3> Qualitative interviews with nine general practitioners in the west midlands were undertaken. Exclusion criteria: GPs working as locums or retired. Semi-structured telephone interviews were undertaken following a topic guide and transcribed verbatim. Thematic analysis was conducted on the transcripts using Braun & Clarke’s six-phase framework with the aid of the software NVivo. <h3>Findings</h3> Nine interviews were undertaken, and six main themes were formed: time spent on leadership, motivation, future, leadership style, current challenges and training to create change. <h3>Conclusion</h3> This research looks further in-depth at the views of general practitioners towards their leadership roles and challenges that present themselves currently and could do in the future. This research is important as understanding if good leadership is being implemented in these structures can have a positive knock-on effect to many other systems. This topic needs to be closely monitored as these structures develop.","PeriodicalId":92161,"journal":{"name":"Workshops & poster abstracts : [proceedings]. IEEE Computational Systems Bioinformatics Conference","volume":"1 1","pages":"A37.1-A37"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://bmjleader.bmj.com/content/leader/3/Suppl_1/A37.1.full.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147888614","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Irene S Gabashvili, Richard J Carter, Peter Markstein, Anne B S Giersch
{"title":"EST-BASED ANALYSIS OF GENE EXPRESSION IN THE HUMAN COCHLEA.","authors":"Irene S Gabashvili, Richard J Carter, Peter Markstein, Anne B S Giersch","doi":"10.1109/CSBW.2005.64","DOIUrl":"https://doi.org/10.1109/CSBW.2005.64","url":null,"abstract":"Hearing is one of the vital senses helping to perceive, reflect and communicate with the world around us. Genetics, developmental conditions, mechanical damage, infections, ototoxic medications, and aging are among the factors disabling or deteriorating this sense. The cochlea is a sensory organ responsible for hearing. Over 15,000 expressed sequence tags (ESTs) extracted from this organ had been previously clustered with other sequences and aligned to earlier versions of the human genome and known genes. This is especially important as more genomic and phenotypic data becomes available almost on a daily basis. Many transcripts corresponding to ESTs present in the dataset might not be expressed as proteins, but instead are degraded by nonsense-mediated mRNA decay or other cell surveillance mechanisms. Large-scale sequencing of tissue-specific genes and fast yet reliable mapping of sequences will help to identify key components of sound transduction and speed up progress in hearing research.","PeriodicalId":92161,"journal":{"name":"Workshops & poster abstracts : [proceedings]. IEEE Computational Systems Bioinformatics Conference","volume":"2005 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2005-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://sci-hub-pdf.com/10.1109/CSBW.2005.64","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"35459546","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}