检索结果-内蒙古大学图书馆

4th research, Invention, and Innovation Congress: Innovative Electricals and Electronics, RI2C 2023

作者： Mekruksavanich, Sakorn Jantawong, Ponnipa Jitpattanakul, Anuchit Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science King Mongkut’s University of Technology North Bangkok Bangkok Thailand

ISBN: (纸本)9798350330618

The prevalence of intelligent wearable devices has significantly increased, offering advantages to individuals of all age groups. In the field of human activity recognition (HAR) research, wearable sensor data plays a crucial role in classifying various human actions. Sensor-based assessments are commonly employed in hazard analysis and risk assessments. However, traditional machine learning (ML) algorithms have faced challenges when applied to sports activities due to their unpredictable nature. These challenges have prompted the need for manual feature extraction, limiting the efficacy of ML methodologies in data categorization. To address this, our study introduces ResNet, a deep residual network, for effectively categorizing sports activities using wearable sensor data. To evaluate our proposed approach, we utilized a publicly available benchmark dataset consisting of sensor data collected from the dominant wrist, neck, and thigh of each study participant. The experimental results demonstrated the exceptional performance of the ResNet model, achieving an impressive accuracy rate of 99.83% in recognizing sport activities. Additionally, we compared the efficacy of our suggested model with five fundamental deep learning models, namely CNN, LSTM, BiLSTM, GRU, and BiGRU. The comparative analysis revealed that the ResNet model outperformed the other deep learning models, demonstrating superior performance in sport activity recognition. ©2023 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Ultrasensitive Surface-Enhanced Raman Scattering Platform for Protein Detection via Active Delivery to Nanogaps as a Hotspot

引用

ACS Nano 2024年第32期18卷 21593-21606页

作者： Gao, Tianxu Yachi, Takehiro Shi, Xu Sato, Rina Sato, Chikara Yonamine, Yusuke Kanie, Kiyoshi Misawa, Hiroaki Ijiro, Kuniharu Mitomo, Hideyuki Graduate School of Life Science Hokkaido University Sapporo060-0810 Japan Research Institute for Electronic Science Hokkaido University Sapporo001-0021 Japan Creative Research Institution Hokkaido University Sapporo001-0021 Japan Institute of Multidisciplinary Research for Advanced Materials Tohoku University Sendai980-8577 Japan Ibaraki Tsukuba305-8568 Japan Graduate School of Science and Engineering Aoyama Gakuin University Kanagawa Sagamihara252-5258 Japan University of Tsukuba 1-1-1 Tennodai Ibaraki Tsukuba305-8577 Japan Division of Immune Homeostasis Microbiology Department of Pathology and Microbiology Nihon University School of Medicine Itabashi173-8610 Japan International Center for Synchrotron Radiation Innovation Smart Tohoku University Sendai980-8577 Japan Research Institute for Interdisciplinary Science Okayama University Okayama770-8530 Japan Center for Emergent Functional Matter Science National Yang Ming Chiao Tung University Hsinchu30010 Taiwan

Surface-enhanced Raman scattering (SERS) is an attractive technique in molecular detection with high sensitivity and label-free characteristics. However, its use in protein detection is limited by the large volume of proteins, hindering its approach to the narrow spaces of hotspots. In this study, we fabricated a Au nanoTriangle plate Array on Gel (AuTAG) as an SERS substrate by attaching a Au nanoTriangle plate (AuNT) arrangement on a thermoresponsive hydrogel surface. The AuTAG acts as an actively tunable plasmonic device, on which the interparticle distance is altered by controlling temperature via changes in hydrogel volume. Further, we designed a Gel Filter Trapping (GFT) method as an active protein delivery strategy based on the characteristics of hydrogels, which can absorb water and separate biopolymers through their three-dimensional (3D) polymer networks. On the AuTAGs, fabricated with AuNTs modified with charged surface ligands to prevent the nonspecific adsorption of analytes to particles, the GFT method helped the delivery of proteins to hotspot areas on the AuNT arrangement. This combination of a AuTAG substrate and the GFT method enables ultrahigh sensitivity for protein detection by SERS up to a single-molecule level as well as a wide quantification concentration range of 6 orders due to their geometric advantages. © 2024 The Authors. Published by American Chemical Society.

关键词： Self assembly

来源：评论

学校读者我要写书评

暂无评论

A Deep Multi-Task Learning Network for Activity Recognition and User Identification Using Smartphone Sensors 16

A Deep Multi-Task Learning Network for Activity Recognition ...

引用

16th International Conference on ENTERprise Information Systems, centerIS 2024 - 12th International Conference on Project MANagement, ProjMAN 2024 - 14th International Conference on Health and Social Care Information Systems and Technologies, HCist 2024

作者： Mekruksavanich, Sakorn Phaphan, Wikanda Jitpattanakul, Anuchit Department of Computer Engineering School of Information and Communication Technology University of Phayao Phayao56000 Thailand Research Group in Statistical Learning and Inference Department of Applied Statistics Faculty of Applied Science King Mongkut's University of Technology North Bangkok Bangkok10800 Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science King Mongkut's University of Technology North Bangkok Bangkok10800 Thailand

Human activity recognition (HAR) and user identification utilizing smartphone sensors are crucial in domains such as wellness tracking, tailored services, and security. Conventional approaches handle these activities as distinct entities, leading to less-Than-ideal performance and restricted applicability. This research presents a novel deep multi-Task learning network that simultaneously performs activity recognition and user identification using smartphone sensor data. By leveraging shared representations and task-specific information, the network enhances accuracy. It combines a shared convolutional neural network (CNN) with bidirectional long short-Term memory (BiLSTM) layers to extract features from raw sensor data. The CNN identifies patterns, while the BiLSTM captures sequential dependencies and contextual information. These features are processed by fully connected layers for both activity recognition and user identification. A multi-Task loss function is proposed to optimize both tasks based on their complexity and importance. The approach is tested on the UCI-HAR dataset, containing diverse activities from multiple users. Experimental results show that the proposed CNN-BiLSTM model achieves 97.64% accuracy in activity recognition and 82.59% in user identification, surpassing current state-of-The-Art methods. This demonstrates the effectiveness of the multi-Task learning framework and the advantage of using the shared CNN-BiLSTM architecture for improving both tasks. © 2025 The Author(s).

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Improving Inertial Sensor-based Human Activity Recognition using Ensemble Deep Learning 8

Improving Inertial Sensor-based Human Activity Recognition u...

引用

Joint 8th International Conference on Digital Arts, Media and Technology and 6th ECTI Northern Section Conference on Electrical, Electronics, computer and Telecommunications engineering, ECTI DAMT and NCON 2023

作者： Rojanavasu, Pornthep Jantawong, Ponnipa Jitpattanakul, Anuchit Mekruksavanich, Sakorn School of Information and Communication Technology Department of Computer Engineering University of Phayao Phayao Thailand Intelligent and Nonlinear Dynamic Innovations Research Center Faculty of Applied Science King Mongkut's University of Technology North Bangkok Department of Mathematics Bangkok Thailand

ISBN: (纸本)9798350396546

Sensor-based human activity recognition (S-HAR) is a famous study focusing on detecting human physiological actions by interpreting various sensors, especially one-dimensional time series information. Typically, S-HAR machine learning methods were developed using handcrafted characteristics. Unfortunately, this is a complicated process that involves feature engineering and a high level of domain knowledge. Due to the development of deep neural networks, classification techniques could efficiently handle relevant characteristics from raw sensor data, resulting in enhanced classification outcomes. In this study, we describe a unique method for S-HAR based on ensemble deep learning with sensor nodes connected to the waist, chest, leg, and arm. Implementing and training three deep learning networks is performed using a publically available dataset, including wearable sensors from eight human actions. The findings demonstrate that the proposed Ens-ResNeXt model provides the maximum accuracy and F1-score, which is superior to existing techniques. © 2023 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Approaches for Epileptic Seizures Recognition based on EEG Signal 46

Deep Learning Approaches for Epileptic Seizures Recognition ...

引用

46th International Conference on Telecommunications and Signal Processing, TSP 2023

作者： Mekruksavanich, Sakorn 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 Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9798350303964

Recognition system of human actions is a popular research field in healthcare which is essential in identifying abnormal patient activities to estimate their psychological state. Epileptic seizures are a common neurological disorder affecting millions of individuals globally. Early and accurate diagnosis of epilepsy can lead to up to 70% of seizure-free patients. There is a requirement for smart and automated HAR systems to aid clinicians in accurately diagnosing neurological disorders. This study examines the latest deep learning networks for time-series classification to detect epileptic seizures using EEG signal data. To enhance recognition performance, a hybrid residual network called Inception-ResNet is presented for the binary classification of epileptic activities. Through thorough analysis, the Inception-ResNet model was observed to provide the best results, with an average accuracy and F1-score of 99.61%. © 2023 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Flexible adaptive sensing tonometry for medical-grade multi-parametric hemodynamic monitoring

引用

npj Flexible Electronics 2024年第1期8卷 437-452页

作者： Mengkang Deng Chentao Du Jiayuan Fang Changshun Xu Chenhui Guo Jiantao Huang Kang Li Lei Chen Yuan-Ting Zhang Yu Chang Tingrui Pan School of Biomedical Engineering Division of Life Sciences and MedicineUniversity of Science and Technology of ChinaHefeiPR China Suzhou Institute for Advanced Research University of Science and Technology of ChinaSuzhouPR China Department of Biomedical Engineering City University of Hong KongHong Kong SARPR China West China Biomedical Big Data Center West China HospitalSichuan UniversityChengduPR China Department of Neurology West China HospitalSichuan UniversityChengduPR China Hong Kong Institute of Medical Engineering Chinese University of Hong Kong(CUHK)Hong Kong SARPR China Department of Electronic Engineering Chinese University of Hong Kong(CUHK)Hong Kong SARPR China Bionic Sensing and Intelligence Center(BSIC) Institute of Biomedical and Health EngineeringShenzhen Institute of Advanced TechnologyChinese Academy of SciencesShenzhenPR China Department of Precision Machinery and Precision Instrumentation University of Science and Technology of ChinaHefeiPR China

Continuous hemodynamic monitoring in a wearable means can play a crucial role in managing hypertension and preventing catastrophic cardiovascular *** this study,we have described the fully wearable tonometric device,referred to as flexible adaptive sensing tonometry(FAST),which is capable of continuous and accurate monitoring of hemodynamic parameters within the medical-grade *** particular,the FAST system integrates a 1×8 unit array of highly sensitive and highly flexible iontronic sensing(FITS)with 1mm spatial resolution and a closed-loop motion *** flexible tonometric architecture has been used to determine the radial arterial position with high sensitivity and high conformability,which simplifies the biaxial searching process of the traditional applanation tonometry into a highly efficient uniaxial applanation while keeping the medical-precision ***,a self-calibration algorithm can be automatically implemented during the applanation process,from which the intra-arterial blood pressure wave can be continuously predicted within the medical-grade precision,and subsequently,multi-parametric hemodynamic analysis can be performed in *** validations on health volunteers have demonstrated that the FAST measurements are all within the required accuracy of the clinical standards for continuous pulse wave assessments,blood pressure monitoring as well as other key hemodynamic parameter ***,the FAST system,by integrating the flexible iontronic sensing array,provides a real-time,medical-grade hemodynamicmonitoring solution in a continuously wearable manner,from which remote patient-centered monitoring can be delivered with both medical precision and convenience.

关键词： parametric continuously monitoring

来源：评论

学校读者我要写书评

暂无评论

Improving Lower Limb Activity Recognition Based on Inertial Sensors using CNN-LSTM Network 4

Improving Lower Limb Activity Recognition Based on Inertial ...

引用

4th research, Invention, and Innovation Congress: Innovative Electricals and Electronics, RI2C 2023

ISBN: (纸本)9798350330618

The utilization of wearable sensors has gained significant popularity across various domains. This widespread adoption has driven the need for advancements in sensor technology, focusing on attributes such as lightweight design, dependability, and integration capabilities. One specific area where wearable sensor networks have faced challenges is in human activity recognition, particularly in accurately inferring movement data. The effectiveness of this process depends on several factors, such as the quality of sensor-derived features, the discriminatory power of selected features, and the chosen classification methodology. To address these challenges, this research introduces a novel hybrid deep learning architecture called CNN-LSTM. The primary goal of this architecture is to enhance the accuracy of recognizing human lower limb movement. To evaluate the effectiveness of the proposed model, a series of investigations were conducted using the publicly available HuGaDB dataset. This dataset consists of data collected from a body sensor network comprising six wearable inertial sensors, including accelerometers and gyroscopes. These sensors were positioned on both the right and left thighs, shins, and feet. The outcomes of the investigation demonstrated that the suggested model achieved an impressive precision of 97.81% and a maximum F1-score of 95.50%. These results highlight the effectiveness of the CNN-LSTM model in accurately recognizing human lower limb movement. ©2023 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Networks for Complex Activity Recognition Based on Wrist-Worn Sensor 38

Deep Learning Networks for Complex Activity Recognition Base...

引用

38th IEEE Region 10 Conference, TENCON 2023

作者： Mekruksavanich, Sakorn 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 Faculty of Applied Science Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Bangkok Thailand

ISBN: (纸本)9798350302196

Wearable smart devices, such as smartphones and smartwatches, offer great potential as platforms for automated human action identification. However, accurately monitoring complex human actions on these devices poses a challenge due to the presence of similarities in patterns across different actions. This occurs when distinct human actions exhibit comparable signal patterns or characteristics. The placement of motion sensors on the body plays a crucial role in detecting human behavior. Typically, wearable sensors placed at the trouser pocket or a similar location are used for this purpose. However, this positioning is not suitable for identifying actions involving manual gestures. To address this, wrist-worn motion sensors are employed to detect these specific behaviors. This study aims to investigate the effectiveness of deep learning models in accurately categorizing complex human actions using sensor data from wrist-worn devices. Nine deep learning models utilizing convolutional neural networks and recurrent neural networks were examined for their identification capabilities. The models were evaluated using the WHARF dataset, a publicly available benchmark dataset for human activity recognition. The investigation revealed that the proposed CNN-BiGRU model outperformed other deep learning models, achieving an accuracy rate of 87.20% and an Fl-score of 84.46%. © 2023 IEEE.

关键词： Wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Improving EEG-Based Epileptic Seizures Detection Using Self-Normalizing Neural Network 4

Improving EEG-Based Epileptic Seizures Detection Using Self-...

引用

4th International Conference on Big Data Analytics and Practices, IBDAP 2023

作者： Mekruksavanich, Sakorn Jantawong, Ponnipa 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 Intelligent and Nonlinear Dynamic Innovations Research Center Department of Mathematics Faculty of Applied Science Bangkok Thailand

ISBN: (纸本)9798350300192

Epilepsy, a neurological disorder, is typically identified by analyzing electroencephalogram (EEG) signals. However, manually inspecting epileptic seizures is a time-consuming and labor-intensive task. Previous automatic detection algorithms utilizing traditional methods have demonstrated good accuracy in specific EEG classification scenarios but have shown poor performance in others. To tackle this challenge, our study introduces a new deep learning model called the self-normalizing neural network. This model leverages convolutional neural networks and recurrent neural networks to enhance the detection of epileptic seizures using EEG signals. To evaluate our approach, we designed and assessed the proposed detection model using a publicly available Epileptic Seizures Recognition Dataset (ESRD). The experimental findings indicate that the self-normalizing neural network achieves a performance improvement of up to 1.03% accuracy and 1.78% F1-score in epileptic seizure detection, surpassing traditional convolutional neural network approaches. © 2023 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

LowResIR-Net: Lightweight Residual Network for ADL Recognition Using Low-Resolution Infrared Sensor Data 16

LowResIR-Net: Lightweight Residual Network for ADL Recogniti...

引用

Detecting activities of daily living (ADL) is crucial for supported living and medical monitoring. Traditional approaches rely on high-resolution sensors and computationally intensive algorithms, limiting their scalability and practical use in real-world settings. This research introduces LowResIR-Net, a compact deep residual network architecture specifically tailored for recognizing ADL utilizing low-resolution infrared sensor data. LowResIR-Net efficiently extracts key features from low-dimensional data by leveraging the advantages of infrared sensing, such as privacy protection and light resilience. Its architecture combines residual connections with depth-wise convolutions, enhancing feature learning while maintaining a compact model size. The model’s performance is evaluated using the Coventry-2018 dataset, containing low-resolution infrared data from three residential sensor locations. Our tests have shown that in all three cases, LowResIR-Net consistently achieves superior performance compared to other cutting-edge deep learning models, such as CNN, LSTM, BiLSTM, GRU, and BiGRU. LowResIR-Net attains the most excellent accuracies of 90.18%, 93.75%, and 93.30%, and F1-scores of 81.81%, 89.55%, and 88.92% for scenarios I, II, and III, respectively. Furthermore, it achieves these results with fewer parameters than most other models. LowResIR-Net’s strong performance highlights its ability to accurately capture complex patterns in low-resolution infrared data for ADL detection. This study demonstrates the potential of lightweight deep learning and low-resolution infrared sensors in developing privacy-focused and computationally efficient wellness monitoring systems. © 2025 The Author(s).

关键词： Infrared detectors

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：