The primary cause of injury-related death for the elders is represented by falls. The scientific community devoted them particular attention, since injuries can be limited by an early detection of the event. The solution proposed in this paper is based on a combined One-Class SVM (OCSVM) and template-matching classifier that discriminate human falls from nonfalls in a semisupervised framework. Acoustic signals are captured by means of a Floor Acoustic Sensor; then Mel-Frequency Cepstral Coefficients and Gaussian Mean Supervectors (GMSs) are extracted for the fall/nonfall discrimination. Here we propose a single-sensor two-stage user-aided approach: in the first stage, the OCSVM detects abnormal acoustic events. In the second, the template-matching classifier produces the final decision exploiting a set of template GMSs related to the events marked as false positives by the user. The performance of the algorithm has been evaluated on a corpus containing human falls and nonfall sounds. Compared to the OCSVM only approach, the proposed algorithm improves the performance by 10.14% in clean conditions and 4.84% in noisy conditions. Compared to Popescu and Mahnot (2009) the performance improvement is 19.96% in clean conditions and 8.08% in noisy conditions.
Download full-text PDF |
Source |
|---|---|
| http://www.ncbi.nlm.nih.gov/pmc/articles/PMC5468803 | PMC |
| http://dx.doi.org/10.1155/2017/1512670 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Genome-wide identification and characterization of BASIC PENTACYSTEINE transcription factors and their binding motifs in coconut palm.
Front Plant Sci
December 2024
National Key Laboratory for Tropical Crop Breeding, School of Breeding and Multiplication (Sanya Institute of Breeding and Multiplication)/College of Tropical Agriculture and Forestry, Hainan University, Sanya, Hainan, China.
Introduction: () is a small transcription factor family known for its role in various developmental processes in plants, particularly in binding GA motifs and regulating flower and seed development. However, research on the functional characteristics and target genes of in coconut () is limited.
Methods: In this study, we systematically characterized the gene structure, conserved protein domains, gene expansion, and target genes of in the coconut genome.
Structure-Based Development of Novel Spiro-Piperidine ASH1L Inhibitors.
J Med Chem
December 2024
Department of Pathology, University of Michigan, Ann Arbor, Michigan 48109, United States.
The absent, small, or homeotic-like 1 (ASH1L) protein is a histone lysine methyltransferase that plays a crucial role in various cancers, including leukemia. Despite representing an attractive therapeutic target, only one class of ASH1L inhibitors was identified to date. Herein, we report development of advanced ASH1L inhibitors targeting the catalytic SET domain, which were designed to access previously unexplored binding pocket on ASH1L.
View Article and Find Full Text PDFElevated frequencies of activated memory B cells in multiple sclerosis are reset to healthy control levels after B cell depletion with Ocrelizumab.
J Neuroimmunol
December 2024
Versiti Blood Research Institute, Milwaukee, WI, USA; Department of Microbiology and Immunology, Medical College of Wisconsin, Milwaukee, WI, USA. Electronic address:
In multiple sclerosis (MS) the B cell depleting drug ocrelizumab has shown high efficacy in reducing inflammatory activity. Its mechanism of action is unclear due to B cell subset complexity and unknown roles in pathogenesis. Here, we comprehensively phenotyped and quantitated peripheral blood B cell subsets before and after ocrelizumab infusion to gain insight into the fate of B cell subsets with pathogenic potential.
View Article and Find Full Text PDFApplication of one-class classification using deep learning technique improves the classification of subvisible particles.
J Pharm Sci
November 2024
Laboratory of Clinical Science and Biomedicine, Graduate School of Pharmaceutical Sciences, Osaka University, Suita, Osaka, Japan; Integrated Frontier Research for Medical Science Division, Institute for Open and Transdisciplinary Research Initiatives, Osaka University, Suita, Japan.
Article Synopsis
- Capturing subvisible particles with flow imaging microscopy helps evaluate protein aggregates that could cause immunogenic reactions, requiring effective differentiation of harmless components like silicone oil from these particles.
- One-class classifiers, which use only data from the target class, can be utilized in machine learning to distinguish heterogeneous distributions, but their effectiveness on subvisible particles was previously uncertain.
- This study explores deep learning's role in enhancing classification accuracy for protein aggregates, finding that it significantly improves one-class classification, particularly for immunoglobulin G-derived aggregates.
One-class classification with confound control for cognitive screening in older adults using gait, fingertapping, cognitive, and dual tasks.
Comput Methods Programs Biomed
February 2025
Faculty of Engineering, University of Porto, 4200-465, Porto, Portugal; INESC TEC (Institute for Systems and Computer Engineering, Technology and Science), 4200-465, Porto, Portugal. Electronic address:
Background And Objectives: Early detection of cognitive impairment is crucial for timely clinical interventions aimed at delaying progression to dementia. However, existing screening tools are not ideal for wide population screening. This study explores the potential of combining machine learning, specifically, one-class classification, with simpler and quicker motor-cognitive tasks to improve the early detection of cognitive impairment.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!