Article
Computer Science, Information Systems
Fei Luo, Salabat Khan, Yandao Huang, Kaishun Wu
Summary: Wearable devices with various sensors can measure physiological and behavioral characteristics. Activity-based person identification is a growing technology in security and access control. Smartphones, Apple Watch, and Google Glass can collect activity-related information for differentiating individuals. This article implemented eight classifiers, including MSENet, TST, TCN, CNN-LSTM, ConvLSTM, XGBoost, decision tree, and k-nearest neighbor, achieving high person identification accuracies on public datasets.
IEEE INTERNET OF THINGS JOURNAL
(2023)
Article
Computer Science, Information Systems
Ensar Arif Sagbas, Serdar Korukoglu, Serkan Balli
Summary: Stress is a mood of pressure and tension that a person experiences. Real-time stress detection is important in medical systems, but acquiring physiological data is challenging. This study developed a stress detection system using behavioral data from smartphone typing behaviors. Features were extracted from sensor data and reduced using techniques like filter-based methods and genetic algorithms. The kNN method achieved the best classification accuracy of 89.61% and F-Measure of 0.9052. A mobile service and relaxation application were also developed for stress detection and reduction.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Construction & Building Technology
Zeynep Duygu Tekler, Adrian Chong
Summary: This study performs occupancy prediction based on a minimum sensing strategy using a comprehensive set of sensor data and a proposed feature selection algorithm. The findings highlight the crucial features for predicting occupancy across all space types as indoor CO2 levels and Wi-Fi connected devices.
BUILDING AND ENVIRONMENT
(2022)
Article
Computer Science, Artificial Intelligence
Irem Tasci, Burak Tasci, Prabal D. Barua, Sengul Dogan, Turker Tuncer, Elizabeth Emma Palmer, Hamido Fujita, U. Rajendra Acharya
Summary: This study presents a large EEG signal dataset and investigates the detection ability of a new hypercube pattern-based framework for epilepsy. A total of 245 feature vectors were extracted and fed to a kNN classifier, achieving high classification accuracy.
INFORMATION FUSION
(2023)
Article
Chemistry, Analytical
Maryam Assafo, Jost Philipp Staedter, Tenia Meisel, Peter Langendoerfer
Summary: Feature selection plays a crucial role in machine learning-based predictive maintenance applications. However, the stability of feature selection methods under data variations has not been fully addressed in the field of PdM. This paper investigates the stability and performance of three popular filter-based FS methods in tool condition monitoring.
Article
Computer Science, Artificial Intelligence
Jiaxin Wang, Zhelong Wang, Sen Qiu, Jian Xu, Hongyu Zhao, Giancarlo Fortino, Masood Habib
Summary: Motion phase is important in human motion analysis. The proposed framework for sensor combination feature subset selection effectively selects a specified number of sensors without human intervention, and the number of sensors has a minor impact on the recognition rate of the classifier.
INFORMATION FUSION
(2021)
Article
Chemistry, Analytical
Ahmad Almadhor, Gabriel Avelino Sampedro, Mideth Abisado, Sidra Abbas
Summary: This research aimed to detect stress using a stacking model based on machine learning algorithms using chest-based features from the Wearable Stress and Affect Detection (WESAD) dataset. The efficiency of the proposed model was estimated regarding accuracy, precision, recall, and F1-score. The experimental outcome illustrated the efficacy of the proposed stacking technique, achieving 0.99% accuracy, and outperforming traditional methodologies and previous studies.
Article
Engineering, Electrical & Electronic
Zian Pei, Hongtao Wang, Anastasios Bezerianos, Junhua Li
Summary: This study classified multiple classes of workload based on EEG features, finding that feature fusion and feature selection played important roles in enhancing workload identification accuracy. Feature combination improved classification performance, with the highest accuracy achieved when graph metric features were fused.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2021)
Article
Chemistry, Medicinal
Michael Garrigou, Berengere Sauvagnat, Ruchia Duggal, Nicole Boo, Pooja Gopal, Jennifer M. Johnston, Anthony Partridge, Tomi Sawyer, Kaustav Biswas, Nicolas Boyer
Summary: Macrocyclic peptides can disrupt intractable protein-protein interactions relevant to oncology targets, but early hits require improvement. The use of the Automated Ligand Identification System (ALIS) to screen macrocyclic peptides accelerates structure-activity relationship (SAR) exploration. Premixing various unnatural amino acids to generate mixture libraries without purification enables efficient hit-to-lead optimization of protein-protein interaction peptide inhibitors.
JOURNAL OF MEDICINAL CHEMISTRY
(2022)
Article
Instruments & Instrumentation
Xiaolong Hou, Zhaowei Jie, Jifen Wang, Xinyu Liu, Naifu Ye
Summary: In this paper, a terahertz time-domain spectroscopy-based pattern recognition method is proposed to detect adulterated rice seeds in order to combat the adulteration behavior for illegal profits. Terahertz time-domain spectral data is collected, and the Relief algorithm, random forest (RF) algorithm, and maximum correlation minimum redundancy (mRMR) algorithm are employed to select characteristic frequencies. Two signal processing methods, Hilbert transform and Butterworth Low-Pass Filter, are used to process the spectral data and fuse them with the original data. Two machine learning models, support vector machine (SVM) and extreme learning machine (ELM), are applied for classification. The results show that the ELM model achieves an accuracy of 100% with the mRMR feature selection algorithm and Hilbert transform. This study is of reference significance for detecting adulterated rice seeds.
INFRARED PHYSICS & TECHNOLOGY
(2023)
Article
Food Science & Technology
Wenchao Wang, Wenqian Huang, Huishan Yu, Xi Tian
Summary: By accurately dividing maize samples into four moldy grades based on catalase activity, and using feature-level fusion within Vis-SWNIR and LWNIR hyperspectral images, this study achieved an overall prediction accuracy of 95.00% for each moldy level. The complementary spectral ranges of two hyperspectral image systems, combined with feature selection and data fusion strategies, synergistically improved the classification accuracy of maize with different moldy levels.
Article
Ergonomics
Shabnam Pejhan, Martin Agelin-Chaab, Munib Yusuf, Donald Eng
Summary: The significance of ebikes in future urban mobility cannot be ignored, and reducing cyclists' anxiety levels is crucial for their safety and interaction with other road users. Despite differences in acceleration, ebikes do not change cyclists' perception of safety. Additionally, mental workload and heart rate increase at lower speeds in congested traffic or intersections.
ACCIDENT ANALYSIS AND PREVENTION
(2021)
Article
Geriatrics & Gerontology
Bin Yang, Wenzheng Bao, Shichai Hong
Summary: A novel algorithm was proposed to identify Alzheimer-related compounds, and the experimental results showed that this method outperformed other classical classifiers.
FRONTIERS IN AGING NEUROSCIENCE
(2022)
Article
Agriculture, Multidisciplinary
Shizhuang Weng, Kaixuan Han, Zhaojie Chu, Gongqin Zhu, Cunchuan Liu, Zede Zhu, Zixi Zhang, Ling Zheng, Linsheng Huang
Summary: This study proposed a method for identifying the degree of FHB infection in wheat kernels using HSI and deep learning networks, achieving optimal classification accuracy with RACNN and RIs at different wavelengths. The method can efficiently extract distinctive features of different kernel classes and enable rapid, accurate and massive analysis of FHB infection degree in wheat kernels.
COMPUTERS AND ELECTRONICS IN AGRICULTURE
(2021)
Article
Green & Sustainable Science & Technology
Alena Lohrmann, Christoph Lohrmann, Pasi Luukka
Summary: The water-energy nexus is an important area of study that aims to understand the connection between power generation and water demand. This study focuses on the lack of information on cooling systems in power plants, which hinders the assessment of water use and decision-making in water management. The researchers propose a machine learning model that can identify cooling technologies globally, with an average accuracy of 85.42%. The model also performs well in water-stressed regions, where mistakes in water policy planning can have significant consequences. This study provides a valuable method for identifying cooling systems in power plants and highlights the importance of considering water stress in water management.
JOURNAL OF CLEANER PRODUCTION
(2022)
Article
Computer Science, Information Systems
Bing Liu, Chao-Hsien Chu
COMPUTERS & SECURITY
(2015)
Article
Computer Science, Hardware & Architecture
Ding Wang, Debiao He, Ping Wang, Chao-Hsien Chu
IEEE TRANSACTIONS ON DEPENDABLE AND SECURE COMPUTING
(2015)
Article
Computer Science, Information Systems
Meng Ma, Ping Wang, Chao-Hsien Chu, Ling Liu
IEEE INTERNET OF THINGS JOURNAL
(2015)
Article
Engineering, Electrical & Electronic
Jung-Yoon Kim, Chao-Hsien Chu
IEEE SENSORS JOURNAL
(2016)
Article
Computer Science, Information Systems
Rachida Parks, Heng Xu, Chao-Hsien Chu, Paul Benjamin Lowry
EUROPEAN JOURNAL OF INFORMATION SYSTEMS
(2017)
Article
Engineering, Electrical & Electronic
Jung-Yoon Kim, Na Liu, Hwee-Xian Tan, Chao-Hsien Chu
IEEE SENSORS JOURNAL
(2017)
Article
Computer Science, Information Systems
Meng Ma, Ping Wang, Chao-Hsien Chu
IEEE INTERNET OF THINGS JOURNAL
(2018)
Article
Engineering, Electrical & Electronic
Jung-Yoon Kim, Chao-Hsien Chu, Sang-Moon Shin
IEEE SENSORS JOURNAL
(2014)
Article
Computer Science, Theory & Methods
Fengjun Li, Bo Luo, Peng Liu, Dongwon Lee, Chao-Hsien Chu
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
(2013)
Article
Computer Science, Hardware & Architecture
Zang Li, Chao-Hsien Chu, Wen Yao
JOURNAL OF NETWORK AND COMPUTER APPLICATIONS
(2014)
Proceedings Paper
Computer Science, Information Systems
Meng Ma, Ping Wang, Chao-Hsien Chu
2015 IEEE INTERNATIONAL CONFERENCE ON DATA SCIENCE AND DATA INTENSIVE SYSTEMS
(2015)
Proceedings Paper
Computer Science, Theory & Methods
Xiaodan Wu, Chao-Hsien Chu, Dianmin Yue, Jungyoon Kim, Shuai Li
2014 IEEE WORKSHOP ON ELECTRONICS, COMPUTER AND APPLICATIONS
(2014)
Proceedings Paper
Engineering, Biomedical
Jungyoon Kim, Chao-Hsien Chu
2014 36TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC)
(2014)
Proceedings Paper
Computer Science, Information Systems
Jung-Yoon Kim, Chao-Hsien Chu, Sang-Moon Shin
2014 INTERNATIONAL CONFERENCE ON INFORMATION SCIENCE AND APPLICATIONS (ICISA)
(2014)
Proceedings Paper
Computer Science, Information Systems
Meng Ma, Ping Wang, Chao-Hsien Chu
2013 IEEE INTERNATIONAL CONFERENCE ON RFID-TECHNOLOGIES AND APPLICATIONS (RFID-TA)
(2013)