Article
Engineering, Biomedical
Garima Sharma, Karthikeyan Umapathy, Sri Krishnan
Summary: In this paper, a method of performing the initial screening of COVID-19 using audio texture analysis of COVID-19 sounds is proposed. The texture analysis is done on cough, breath, and speech signals, and achieved high accuracy in classifying different samples.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Computer Science, Information Systems
Madhurananda Pahar, Igor Miranda, Andreas Diacon, Thomas Niesler
Summary: In this study, an automatic non-invasive cough detection method based on both accelerometer and audio signals was proposed. Deep neural networks outperformed shallow classifiers in distinguishing coughing from other activities, with Resnet50 achieving the best performance. The accelerometer-based method may represent a more convenient and readily accepted approach for long-term cough monitoring.
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY
(2022)
Article
Engineering, Biomedical
Jiali Xie, Pedro Fonseca, Johannes van Dijk, Sebastiaan Overeem, Xi Long
Summary: By adding audio-based snoring features, the non-obtrusive assessment of obstructive sleep apnea (OSA) can be improved by estimating the apnea-hypopnea index (AHI) and classifying OSA severity. Novel features were proposed to quantify temporal changes between snores (snore rate variability) and trends in snore energy, based on the assessment of snore sounds from audio signals over the full night. These features, combined with age, body mass index (BMI), and features from literature, were used to train an extreme gradient boosting algorithm for AHI estimation and OSA severity classification.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Public, Environmental & Occupational Health
Wenlong Xu, Guoqiang He, Chen Pan, Dan Shen, Ning Zhang, Peirong Jiang, Feng Liu, Jingjing Chen
Summary: This study proposed a new method for accurately assessing pulmonary function by analyzing forced cough sounds recorded by a mobile device. Experimental results showed that the support vector regression (SVR) model performed well in certain parameter assessments, while the gradient boosting regression (GBR) model excelled in others.
FRONTIERS IN PUBLIC HEALTH
(2022)
Article
Engineering, Biomedical
Mingyu You, Weihao Wang, You Li, Jiaming Liu, Xianghuai Xu, Zhongmin Qiu
Summary: The paper presents a deep convolutional bidirectional long short-term memory (C-BiLSTM) model with boundary regression for cough detection, achieving higher detection accuracy and more accurate boundaries. The authors designed, collected and labeled a realistic audio dataset, demonstrating significantly improved detection criteria on cough detection.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Chemistry, Multidisciplinary
Rim Louhichi, Jacques Pelletan, Mohamed Sallak
Summary: This article proposes a methodology that tackles both maintenance optimization and estimation of failure risks simultaneously. The methodology utilizes prospect theory to model decision outcomes and demonstrates its advantages through a case study.
APPLIED SCIENCES-BASEL
(2022)
Article
Respiratory System
Seung-Eun Lee, Matthew Rudd, Tae-Hwa Kim, Ji-Yoon Oh, Ji-Hyang Lee, Lola Jover, Peter M. Small, Kian Fan Chung, Woo-Jung Song
Summary: This study evaluated the feasibility and utility of longitudinal cough frequency monitoring with the Hyfe Cough Tracker in patients with chronic cough. The results showed that monitoring cough frequency using this mobile application was feasible and patients had a high adherence rate. The study also highlighted the substantial day-to-day variability in cough frequency among individuals.
Article
Computer Science, Artificial Intelligence
Ghazaala Yasmin, Asit Kumar Das, Janmenjoy Nayak, S. Vimal, Soumi Dutta
Summary: Speech is a delicate medium for identifying the gender of speakers. Deep learning has provided a good research area to explore gender discrimination deficiencies in traditional machine learning techniques. The combination of automatically generated features and human-generated features can enhance gender recognition performance, especially when considering transgender individuals.
Article
Psychology, Multidisciplinary
Anna Banki, Martina de Eccher, Lilith Falschlehner, Stefanie Hoehl, Gabriela Markova
Summary: Online data collection with infants using eye-tracking poses unique opportunities and challenges. This study compared in-lab and webcam-based eye-tracking data in infants and found no differences in technical issues and participant attrition rates between the two settings. Video data quality was comparable, while eye-tracking data quality was higher in the lab. Further improvements are needed to ensure the precision of online eye-tracking with infants.
FRONTIERS IN PSYCHOLOGY
(2022)
Article
Telecommunications
Zahoor Uddin, Aamir Qamar, Farooq Alam
Summary: Independent component analysis (ICA) is a blind source separation technique widely applied in various fields such as speech, biomedical and communication. Faulty sensors can hinder signal separation, highlighting the importance of fault diagnosis techniques.
WIRELESS PERSONAL COMMUNICATIONS
(2021)
Article
Mathematics, Interdisciplinary Applications
Jianfei Zheng
Summary: This study successfully constructed a multilevel music audio database using Big Data and collaborative filtering algorithm, and experimental results showed that the database has faster search rate and higher accuracy.
DISCRETE DYNAMICS IN NATURE AND SOCIETY
(2022)
Article
Metallurgy & Metallurgical Engineering
Wa Gao, Yue Kan, Fu-sheng Zha
Summary: This study proposed a filter algorithm based on cochlear mechanics and neuron filter mechanism to address the problem of non-linear amplification being rarely considered in studying auditory filters. Through modeling and mathematical description, the algorithm successfully divided audio signals into different frequencies, enhanced high frequency parts, and showed positive impacts on speech enhancement in noise environments.
JOURNAL OF CENTRAL SOUTH UNIVERSITY
(2021)
Article
Computer Science, Information Systems
Ruojing Zhao, Fengbao Yang, Linna Ji
Summary: This study proposes an extended CPT-TODIM method based on possibility theory to solve the issue of dynamic target threat assessment. By using triangular fuzzy numbers to describe the imprecise and fuzzy information in target threat assessment, the changing trend of target detection information and the influence of commanders' psychological factors are considered, leading to more rational assessment results.
Article
Engineering, Electrical & Electronic
Ondrej Mokry, Pavel Rajmic
Summary: This article proves the mapping used by Lieb and Stark is indeed a proximal operator and introduces its approximation which shows better numerical results in audio inpainting while being more computationally effective.
Article
Energy & Fuels
Hao Lu, Lei Zhao, Xuejie Wang, Huiru Zhao, Jiangjiang Wang, Bingkang Li
Summary: This paper proposes an integrated fuzzy-GMCDM method for assessing the applicability of different energy storage systems in various scenarios. The method uses a comprehensive performance assessment index system, determines optimal weights, and considers decision-makers' risk preferences to optimize energy storage selection and ranking. The results show that this method provides decision-makers with optimal solutions for different scenarios such as renewable energy consumption and ancillary services.
JOURNAL OF ENERGY STORAGE
(2023)