检索结果-内蒙古大学图书馆

47th International Conference on Telecommunications and Signal Processing, TSP 2024

作者： Mekruksavanich, Sakorn Phaphan, Wikanda Jitpattanakul, Anuchit School of Information and Communication Technology University of Phayao Department of Computer Engineering Phayao Thailand Research Group in Statistical Learning and Inference King Mongkut's University of Technology North Bangkok Faculty of Applied Science Department of Applied Statistics Bangkok Thailand Intelligent and Nonlinear Dynamic Innovations Research Center King Mongkut's University of Technology North Bangkok Faculty of Applied Science Department of Mathematics Bangkok Thailand

ISBN: (纸本)9798350365597

Recognizing individuals continuously using wearable devices has several applications in personalized services and security. This paper presents a hybrid deep network architecture called SE-ResBiLSTM that integrates a squeeze-and-excitation (SE) mechanism with residual bidirectional LSTM layers. The goal is to enhance the accuracy of person identification using data from wearable motion sensors. The SE blocks facilitate channel-wise feature refinement, highlighting helpful information. Residual connections enable the training of deeper LSTM architectures. The proposed method's accuracy in identifying individuals across increasing periods between training and testing is evaluated using the SP-SW HAR dataset, which contains activity data collected from wristwatch sensors. By leveraging representation learning and exhibiting resilience against sensor noise and temporal fluctuations, SE-ResBiLSTM improves recognition accuracy compared to regular and convolutional LSTM networks. According to the trial data, SE-ResBiLSTM achieved a maximum identification accuracy of 98.71 %. The experimental results demonstrate that this approach significantly boosts the performance of user identification using wristwatch sensors. © 2024 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Problems in Video Conferencing-Mediated Teaching: Experiences of Three User Roles of a University in Bangladesh

Problems in Video Conferencing-Mediated Teaching: Experience...

引用

Advances in Computing,Communication, Electrical, and Smart Systems (iCACCESS), International Conference on

作者： Nafees Mansoor Anatte Rozario Muhammad Golam Kibria Md Saifuddin Khalid Department of Computer Science and Engineering University of Liberal Arts Bangladesh Department of Applied Mathematics and Computer Science Technical University of Denmark (DTU) Kongens Lyngby Denmark

Video-conferencing systems (VCS) became a defacto tool for online and hybrid teaching during COVID-19 and the gradual return to physical classrooms. As part of the EdViCon Erasmus+ project, towards defining the scenarios for improving teaching with additional portable tools by university teachers, this study reports users' problems in the context of the University of Liberal Arts Bangladesh (ULAB). Classroom observations, problem-tree analysis, interviews, and focus-group discussions with academics, e-learning and IT consultants, and students provide different perspectives on the central problems, underlying causes, and the effects of VCS use during live teaching sessions. While teachers emphasized the lack of resources and technical barriers, students' problem statement focused on the reduced quality of interactions due to the differences between VCS-mediated and physical classrooms, and the IT & e-learning professionals emphasized technological issues (audio, tone, lack of facial expression etc.), lack of collaboration, and differences in expectations among participants. The central contribution of this paper is three diagrams showing problem tree analysis from the perspectives of the three roles. Each of the causes, effects, and problem statements will be considered as point-of-view statements for generating ideas for supporting hardware and software tools and training on technology and pedagogy,

关键词：

来源：评论

学校读者我要写书评

暂无评论

Squeeze-and-Excitation Hybrid Network for Biometric Identification via Photoplethysmography 5

Squeeze-and-Excitation Hybrid Network for Biometric Identifi...

引用

5th Research, Invention, and Innovation Congress: Innovative Electricals and Electronics, RI2C 2024

作者： Mekruksavanich, Sakorn Phaphan, Wikanda Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand King Mongkut's University of Technology North Bangkok Faculty of Applied Science Research Group in Statistical Learning and Inference Department of Applied Statistics Bangkok Thailand King Mongkut's University of Technology North Bangkok Faculty of Applied Science Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Bangkok Thailand

ISBN: (纸本)9798331505998

Biometric identity verification is critical in security, healthcare, and personalized services. Photoplethysmography (PPG) signals, measuring blood volume changes in small vessels, offer a promising, non-invasive biometric method but often need more accuracy and robustness. To address this, we propose the ResNet-BiGRU-SE framework, which enhances PPG-based biometric identification through a s queeze-and-excitation (SE) attention mechanism. This architecture integrates convolutional neural networks (CNNs), bidirectional gated recurrent units (BiGRUs), and SE attention modules to extract spatial and temporal features from PPG signals. ResNet architecture in CNN layers extracts local patterns and mitigates vanishing gradients with residual connections, while BiGRU layers capture temporal dependencies and contextual information. The SE attention mechanism enhances focus on informative PPG signal parts by adjusting feature responses per channel. Evaluated on a standardized dataset of PPG signals from various patients, the ResNet-BiGRU-SE model demonstrates superior accuracy (95.26%), low loss (0.24), and a high F1-score (95.25 %), outper-forming recent methods. Comprehensive ablation studies confirm the model's robust and reliable performance. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Detecting Face-Touching Gestures with Smartwatches and Deep Learning Networks 47

Detecting Face-Touching Gestures with Smartwatches and Deep ...

引用

47th International Conference on Telecommunications and Signal Processing, TSP 2024

作者： Mekruksavanich, Sakorn Phaphan, Wikanda Jitpattanakul, Anuchit School of Information and Communication Technology University of Phayao Department of Computer Engineering Phayao Thailand King Mongkut's University of Technology North Bangkok Research Group in Statistical Learning and Inference Faculty of Applied Science Department of Applied Statistics Bangkok Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Faculty of Applied Science Department of Mathematics Bangkok Thailand

ISBN: (纸本)9798350365597

Everyday actions like scratching one's nose or resting the chin on one's hand may facilitate the spread of germs and diseases. Detecting these gestures holds the potential for innovative health monitoring and disease prevention applications. However, the identification of face-touching poses challenges due to the variety of human gestures and the limitations in accuracy associated with wearable sensors. This study introduces an original deep-learning system to identify face-touching gestures using standard smartwatches' inertial measurement unit sensors. The system on the smartwatch captures and pre-processes multi-channel time-series data from the accelerometer to generate robust input features. We utilize a benchmark, the Face Touching dataset, to evaluate the recognition performance of deep learning networks, including our proposed network. Our approach proposes a hybrid deep residual network architecture tailored for sequence-based gesture classification using signals from the smartwatch sensors. In our experiments, the developed deep learning framework achieves an impressive F1-score of 97.53% in detecting face-touch gestures. The suggested system takes a step forward in advancing the practical applications of face-touch gesture detection to smartwatch-based health sensing and disease prevention. © 2024 IEEE.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Enhancing Sensor-based Human Activity Recognition Using Hybrid Deep Learning and Data Augmentation 5

Enhancing Sensor-based Human Activity Recognition Using Hybr...

引用

5th Research, Invention, and Innovation Congress: Innovative Electricals and Electronics, RI2C 2024

作者： Mekruksavanich, Sakorn Phaphan, Wikanda Jitpattanakul, Anuchit School of Information and Communication Technology University of Phayao Department of Computer Engineering Phayao Thailand King Mongkut's University of Technology North Bangkok Research Group in Statistical Learning and Inference Faculty of Applied Science Department of Applied Statistics Bangkok Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Faculty of Applied Science Department of Mathematics Bangkok Thailand

ISBN: (纸本)9798331505998

Human Activity Recognition (HAR) is essential in various applications, including wellness tracking, automated residences, and fitness monitoring. In the past few decades, sensor-based HAR has become increasingly popular due to advancements in technologies for sensors. Nevertheless, HAR networks' effectiveness dramatically depends on the caliber and volume of the training data, which is frequently restricted and unevenly distributed. This research introduces a novel deep learning method called Multihead-CNN-BiGRU, which integrates one-dimensional convolutional neural networks with bidirectional gated recurrent units (BiGRU) to improve the accuracy of sensor-based HAR. To tackle the problem of insufficient a nd uneven training data, we utilize the synthetic minority over-sampling technique (SMOTE) to augment the data. The suggested model is assessed using the publicly accessible WISDM dataset, which comprises sensor data from diverse human actions. The ID-CNN is employed for extracting localized characteristics from the sensor data, while the BiGRU gathers temporal dependencies and contextual information. The hybrid architecture allows the model to acquire spatial and temporal patterns efficiently. In addition, the SMOTE technique is utilized to create artificial samples of the underrepresented classes, thus equalizing the distribution of classes and enhancing the model's capacity to generalize. The experimental findings show that our hybrid strategy provides exceptional outcomes when paired with SMOTE data augmentation. It obtains the most excellent accuracy of 99.51 % and the highest F1-score of 99.49% compared to the most advanced approaches. The suggested framework provides a reliable and precise solution for sensor-based HAR, which opens up opportunities for improved applications in other fields. © 2024 IEEE.

关键词： Spatio-temporal data

来源：评论

学校读者我要写书评

暂无评论

Enhanced prairie dog optimization with Levy flight and dynamic opposition-based learning for global optimization and engineering design problems

引用

Neural Computing and Applications 2024年第19期36卷 11137-11170页

作者： Biswas, Saptadeep Shaikh, Azharuddin Ezugwu, Absalom El-Shamir Greeff, Japie Mirjalili, Seyedali Bera, Uttam Kumar Abualigah, Laith Department of Mathematics National Institute of Technology Agartala Tripura Agartala India Unit for Data Science and Computing North-West University 11 Hoffman Street Potchefstroom2520 South Africa Faculty of Natural and Agricultural Sciences School of Computer Science and Information Systems North-West University Vanderbijlpark South Africa Centre for Artificial Intelligence Research and Optimization Torrens University Australia Fortitude Valley BrisbaneQLD4006 Australia Research Center University of Tabuk Tabuk71491 Saudi Arabia Computer Science Department Al al-Bayt University Mafraq25113 Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan Applied Science Research Center Applied Science Private University Amman11931 Jordan Department of Electrical and Computer Engineering Lebanese American University Byblos13-5053 Lebanon School of Engineering and Technology Sunway University Malaysia Petaling Jaya27500 Malaysia College of Engineering Yuan Ze University Taoyuan32003 Taiwan MEU Research Unit Middle East University Amman11831 Jordan

This study proposes a new prairie dog optimization algorithm version called EPDO. This new version aims to address the issues of premature convergence and slow convergence that were observed in the original PDO algorithm. To improve performance, several modifications are introduced in EPDO. First, a dynamic opposite learning strategy is employed to increase the diversity of the population and prevent premature convergence. This strategy helps the algorithm avoid falling into local optima and promotes global optimization. Additionally, the Lévy dynamic random walk technique is utilized in EPDO. This modified Lévy flight with random walk reduces the algorithm’s running time for the test function’s ideal value, accelerating its convergence. The proposed approach is evaluated using 33 benchmark problems from CEC 2017 and compared against seven other comparative techniques: GWO, MFO, ALO, WOA, DA, SCA, and RSA. Numerical results demonstrate that EPDO produces good outcomes and performs well in solving benchmark problems. To further validate the results and assess reliability, the authors employ average rank tests, the measurement of alternatives, and ranking according to the compromise solution (MARCOS) method, as well as a convergence report of EPDO and other algorithms. Furthermore, the effectiveness of the EPDO algorithm is demonstrated by applying it to five design problems. The results indicate that EPDO achieves impressive outcomes and proves its capability to address practical issues. The algorithm performs well in solving benchmark and practical design problems, as supported by the numerical results and validation methods used in the study. © The Author(s) 2024.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

A Sensor-Based Deep Learning Approach for Recognizing Daily and Work Activities in Open Environments for Sanitation Workers 9

A Sensor-Based Deep Learning Approach for Recognizing Daily ...

引用

Joint 9th International Conference on Digital Arts, Media and Technology with 7th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering, ECTI DAMT and NCON 2024

作者： Mekruksavanich, Sakorn Jantawong, Ponnipa Phaphan, Wikanda Jitpattanakul, Anuchit University of Phayao School of Information and Communication Technology Department of Computer Engineering Phayao Thailand King Mongkut's University of Technology North Bangkok Research Group in Statistical Learning and Inference Department of Applied Statistics Faculty of Applied Science Bangkok Thailand King Mongkut's University of Technology North Bangkok Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9798350318241

Sanitation workers play a crucial role in maintaining public hygiene and cleanliness. Understanding their daily routines and job responsibilities is essential for improving their work environment, task distribution, and overall supervision. However, tracking sanitation workers in open environments remains a persistent challenge. This paper introduces a deep learning model named CNN-BiGRU-CBAM, designed to recognize sanitation workers' daily and working activities using smartwatch sensors. The model leverages advanced convolutional neural networks to extract highly informative features from multi-modal sensor data, including acceleration information, collected from smartwatches. The dataset used in this study is carefully curated and collected from sanitation workers during their daily work routines, encompassing activities such as walking, running, sweeping, lifting, and driving vehicles. These activities are systematically categorized to cover both work-related tasks and non-work activities. Experimental results demonstrate that the proposed model consistently achieves an average F1-score of over 94.50% across seven activity groups, outperforming baseline deep learning methods by an impressive margin of 5.62%. The model excels in accurately identifying operations in diverse and dynamic work settings. This research highlights the potential of smartwatches and deep learning in continuously analyzing sanitation workers' duties and developing improved working regulations that consider their well-being and daily tasks. © 2024 IEEE.

关键词： Sanitation

来源：评论

学校读者我要写书评

暂无评论

Harnessing Deep Learning for Activity Recognition in Seniors' Daily Routines with Wearable Sensors 47

Harnessing Deep Learning for Activity Recognition in Seniors...

引用

47th International Conference on Telecommunications and Signal Processing, TSP 2024

作者： Mekruksavanich, Sakorn Phaphan, Wikanda Jitpattanakul, Anuchit School of Information and Communication Technology University of Phayao Department of Computer Engineering Phayao Thailand Research Group in Statistical Learning and Inference King Mongkut's University of Technology North Bangkok Department of Applied Statistics Faculty of Applied Science Bangkok Thailand Intelligent and Nonlinear Dynamic Innovations Research Center King Mongkut's University of Technology North Bangkok Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9798350365597

Wearable sensors are increasingly popular for monitoring the daily activities of older individuals, sparking significant interest in human activity recognition (HAR). Accurate and timely identification of these activities is crucial for providing personalized care and timely interventions to maintain the well-being of elderly individuals. However, existing HAR methods often need support with complex activity patterns, limited labeled data, and the need for real-time performance. To address these challenges, this study proposes a novel deep-learning approach called ResBiGRU for precisely identifying daily activities in older adults using wearable sensors. The ResBiGRU architecture combines residual connections with BiGRU networks to capture short-term and long-term dependencies in sensor data effectively. We also propose a data augmentation strategy to improve generalization performance. Evaluation of the HAR70+ dataset, consisting of activities performed by 18 elderly individuals, demonstrates superior performance of our ResBiGRU model with an accuracy of 97.39% and an F1-score of 97.74%. Furthermore, our model supports real-time inference, making it suitable for practical applications. Implementing the ResBiGRU approach could significantly enhance monitoring and care for older adults by accurately identifying their daily activities. This research advances HAR methods tailored for elderly individuals, opening new avenues for personalized healthcare and assisted living technologies. © 2024 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network with CBAM Module for Fitness Activity Recognition Using Wearable IMU Sensors 9

Convolutional Neural Network with CBAM Module for Fitness Ac...

引用

ISBN: (纸本)9798350318241

Wearable motion sensors are gaining traction for fitness activity tracking due to their utility in assisted living, wellness tracking, and fitness training applications. Such sensors typically incorporate accelerometers and gyroscopes to monitor and log physical activities. This work proposes a deep-learning approach for identifying fitness activities using wearable inertial measurement units (IMUs) signals. Specifically, a convolutional neural network (CNN) integrated with a convolutional block attention module (CBAM) provides the core framework. The CBAM module applies channel and spatial attention mechanisms to enhance CNN's capacity to discriminate salient features. Multichannel IMU time-series data, comprising accelerometer and gyroscope readings as subjects perform various exercises, supply input to the model. By learning via an attention-enhanced architecture, the model can extract robust and informative representations to categorize activities accurately. Experiments on a public IMU dataset with five exercise types across over twenty participants evaluated the approach. Results showed over 99.58% subject-independent activity recognition accuracy when augmenting the CNN with CBAM, constituting significant performance gains. The research findings indicate that an efficient deep-learning solution with attention modeling can recognize fitness activities reliably from on-body sensors. The proposed methodology holds substantial promise for applications in sports analytics and personalized health tracking. © 2024 IEEE.

关键词： Gyroscopes

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Networks for Human Knee Abnormality Detection Based on Surface EMG Signals 47

Deep Learning Networks for Human Knee Abnormality Detection ...

引用

47th International Conference on Telecommunications and Signal Processing, TSP 2024

作者： Mekruksavanich, Sakorn Phaphan, Wikanda Jitpattanakul, Anuchit School of Information and Communication Technology University of Phayao Department of Computer Engineering Phayao Thailand Research Group in Statistical Learning and Inference King Mongkut's University of Technology North Bangkok Faculty of Applied Science Department of Applied Statistics Bangkok Thailand Intelligent and Nonlinear Dynamic Innovations Research Center King Mongkut's University of Technology North Bangkok Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9798350365597

Early knee problem management relies on precise identification and classification of abnormalities. Surface electromyography (sEMG) and goniometer signals offer non-invasive screening for muscle activity and joint angle patterns, yet their complexity poses challenges in extracting critical diagnostic information. This paper proposes a novel deep-learning method using sEMG and goniometer data for knee abnormality diagnosis. The proposed ResNeXt model, employing CNNs and multi-kernel modules, is evaluated on the UCIEMG dataset. Experimental results demonstrate ResNeXt's superior accuracy, precision, recall, and F1-score compared to baseline models (CNN and LSTM). Res NeXt achieves the best performance with combined EMG and goniometer data, reaching 96.37% accuracy and 93.77% F1-score, with fewer trainable parameters, indicating computational efficiency. The findings indicate ResNeXt's effectiveness in identifying knee abnormalities using biosensor data, particularly sEM G and goniometer signals, aiding early disease detection and treatment. © 2024 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：