检索结果-内蒙古大学图书馆

Internet of thing-based hand tremor monitoring system and automated detection of hand tremor frequency

COMPUTERS & ELECTRICAL ENGINEERING 2025年 122卷

作者： Onder, Mithat Daldal, Nihat Polat, Kemal Dogan, Muhsin Ugur Bolu Abant Izzet Baysal Univ Fac Engn Dept Elect & Elect Engn TR-14280 Bolu Turkiye Bolu Abant Izzet Baysal Univ Bolu Tech Sci High Sch Dept Elect & Automat TR-14200 Bolu Turkiye

Parkinson's disease (PD) is a progressive neurological disorder caused by the degeneration of dopamine-producing neurons in the brain. Early PD detection is key to improving the quality of life for people with the condition. For this purpose, an experimental setup has been created to classify hand tremors, diagnose PD, and estimate hand tremor frequency with an artificial neural network (ANN). Next, to create the hand tremor dataset, the hand in the experimental setup was allowed to vibrate at frequencies in the 3-16 Hz range, and the data of hand tremors at frequencies in the 3-16 Hz range were obtained. In the current literature, no single comprehensive dataset includes all types of tremors. Each type of tremor has its own separate dataset. Because these datasets originate from different sources, combining them into a unified wide-spectrum dataset is challenging. Therefore, a test setup was developed to generate a wide-spectrum data- set encompassing all types of tremors. Later, the atypical tremor, Parkinson tremor, essential tremor, psychology tremor, slow orthostatic tremor, and primary orthostatic tremor are classified by using three classifiers such as fine Gaussian support vector machine (SVM), bagged trees, and weighted k-nearest neighbor (KNN). Then, the ANN model has been produced to predict the frequency of hand tremors. The dataset was divided into testing and training datasets before the classification process. Five different methods were utilized for this division: 5-fold cross- validation (FVC), 10 FVC, and the holdout methods with ratios of 50-50 %, 70-30 %, and 90-10 %. The fine Gaussian SVM, bagged trees, and weighted KNN models achieved the best multi-class classification accuracy with 10-fold cross-validation, reaching 92.3 %, 91.4 %, and 91.3 %, respectively. The fine Gaussian SVM bagged trees, and weighted KNN models achieved the Parkinsonian tremor classification accuracy with a holdout (90-10 %) method, reaching 99.33 %, 99.25 %, and 99.35 %

关键词： Artificial neural networks Classification Hand tremor Internet of things Parkinson's diagnosis Prediction sensor data processing Multi-class classification Neurological disorder

来源：评论

学校读者我要写书评

暂无评论

Variational Mode Decomposition-Based Identification of Pygmy Blue Whales Song Units

引用

IEEE sensorS JOURNAL 2024年第11期24卷 17963-17973页

作者： Liang, Yue Al-Badrawi, Mahdi H. Seger, Kerri D. Kirsch, Nicholas J. Univ New Hampshire Dept Elect & Comp Engn Durham NH 03824 USA Univ Maine Dept Elect & Comp Engn Orono ME 04469 USA Appl Ocean Sci Seattle WA 98107 USA

Detection and classification of cetacean vocalizations in acoustic datasets play critical roles in understanding the impacts of various human-made sound sources on cetaceans. Knowing migration route locations, feeding success rates, and population densities can help reduce our impacts on their life functions and aids in conservation efforts for these mammals. However, due to the amount of data that need to be processed and the amount of variance that exists in ocean noise, identification of large marine mammals is challenging. The proposed method relies on modeling and generating noise-only copies of a given data sample and uses that noise-only copy to determine whether a signal is contained in the sample or not. With the aid of this noise modeler, a variational mode decomposition (VMD) technique is then applied to detect signals and extract their features. Finally, the extracted features are used to group detected signals into four different types of blue whale units, namely, Units 1-3 of the Sri Lankan pygmy blue whale song and the Diego Garcia downsweep (Chagos) song, which is thought to be from a different pygmy blue whale population. The evaluation of statistical indices revealed the efficacy of the proposed system, since overall precision was 99.5%, and recall was 87%. With this automated detection/classification system that adjusts for changing background noise conditions, analyzing the many datasets containing multiple blue whale songs can be more efficiently accomplished.

关键词： Whales Noise Feature extraction sensors Background noise Sociology Electronic mail Adaptive noise modeling pygmy blue whale sensor data processing variational mode decomposition (VMD)

来源：评论

学校读者我要写书评

暂无评论

Efficient Embedded Fixed-Point Direction of Arrival Method

引用

IEEE sensorS JOURNAL 2024年第6期24卷 8563-8584页

作者： Troccoli, Tiago Pirskanen, Juho Morte, Jorge Ometov, Aleksandr Lohan, Elena Simona Kaseva, Ville Nurmi, Jari Tampere Univ Fac Informat Technol & Commun Sci Tampere 33720 Finland WIREPAS Ltd Tampere 33720 Finland

Radio direction finding, traditionally used for localizing radio signal sources, has been adapted for Bluetooth to enable indoor localization of wireless devices. This adaptation is particularly relevant for achieving accurate indoor localization within Internet-of-Things (IoT) networks, especially in battery-powered and resource-limited embedded systems. However, the intricacies of implementing direction of arrival (DOA) methods in such systems, notably those lacking a floating-point unit (FPU), present significant computational challenges. This article addresses these challenges by introducing an innovative fixed-point DOA method, rooted in the estimation of signal parameters via rotation invariance techniques (ESPRIT). Diverging from traditional complex eigenvalue decomposition, our approach employs a simpler power method for DOA estimation and phase offset compensation, utilizing a straightforward trigonometric equation. It also integrates an improved carrier frequency estimator, also based on ESPRIT, which is tens of times more accurate than the conventional method of averaging phase differences. We conducted bare-metal level experiments on an nRF52840 system on chip to evaluate execution time, memory footprint, angle accuracy, and energy consumption. The fixed-point implementation demonstrated an execution time of 2.3 ms and an energy consumption of just 0.348 nWh. These figures represent a 5.9-fold increase in energy efficiency and a 4.4-fold improvement in speed compared to the conventional software-based floating-point approach while maintaining an angle accuracy ranging from nearly 2 degrees to under 0.5 degrees, depending on the signal-to-noise ratio. However, in IoT devices equipped with an FPU, the hardware-based floating-point technique still edges out, being 0.8 ms faster and slightly more energy efficient at 0.319 nWh.

关键词： Array signal processing direction of arrival (DOA) embedded systems sensor arrays sensor data processing

来源：评论

学校读者我要写书评

暂无评论

sensor-Based Gymnastics Action Recognition Using Time-Series Images and a Lightweight Feature Fusion Network

引用

IEEE sensorS JOURNAL 2024年第24期24卷 42573-42583页

作者： Wang, Wanyue Lian, Chao Zhao, Yuliang Zhan, Zhikun Northeastern Univ Qinhuangdao Sch Business Qinhuangdao 066004 Peoples R China Northeastern Univ Sch Informat Sci & Engn Shenyang 110819 Peoples R China Hebei Key Lab Micronano Precis Opt Sensing & Measu Qinhuangdao 066004 Peoples R China

With the development of micro-electromechanical systems (MEMSs) and artificial intelligence technology, the application of wearable devices in human motion capture and recognition has gradually become a research hotspot. However, existing action recognition methods based on wearable sensors still face issues such as limited feature extraction capability and insufficient information utilization, leaving significant room for improvement in recognition accuracy. To address these challenges, this article proposes a motion recognition method based on time-series images and a lightweight feature fusion network. First, two time-series-to-image conversion methods, raw sequence image (RI) and raw sequence change image (RCI), are proposed, which fully leverage the advantages of convolutional neural networks (CNNs) in image processing. Second, a dual-channel feature fusion network is designed, enhancing the ability to extract features of gymnastic movements through the selection of backbone networks and the design of feature fusion modules. Finally, the effectiveness of the proposed method in gymnastics action recognition is validated. The experimental results show that the proposed method achieves an accuracy of 99.35%, which is at least 4.77% higher than existing machine learning methods and at least 2.03% higher than advanced deep learning methods. This demonstrates a significant improvement in recognition accuracy, proving the effectiveness and superiority of the proposed method in human action recognition. This method is expected to be extended to more application scenarios and provide technical support for the development of wearable devices.

关键词： Feature extraction sensors Accuracy Image recognition Deep learning Convolutional neural networks Machine learning algorithms Time-domain analysis Hidden Markov models Wearable sensors Action recognition deep learning image representation sensor data processing wearable sensors

来源：评论

学校读者我要写书评

暂无评论

Degree of Stenosis Quantification From Phonoangiography Signal Analysis for Diagnosing Carotid Artery Disease

引用

IEEE sensorS JOURNAL 2024年第24期24卷 40221-40230页

作者： Achmamad, Abdelouahad M'Hammedi, Taoufik Yaakoubi, Nourdin Errachid, Abdelhamid Fezazi, Mohamed El Jbari, Atman Bellarbi, Larbi Le Mans Univ Lab Acoust Univ Mans LAUM Inst Acoust Grad Sch IA GS UMR CNRS 6613CNRS F-72000 Le Mans France Univ Lyon CNRS Inst Sci Analyt UMR 5280 Lyon France Mohammed V Univ Rabat Elect Syst Sensors & Nanobiotechnol Lab ENSAM Rabat Morocco

Carotid artery stenosis (CAS) is one of the most serious forms of stenosis, which can potentially lead to brain stroke if left untreated. Timely detection of CAS is therefore indispensable so that specialists can formulate better treatment strategies for their patients to avoid fatal neurological deficits. The primary objective of this research is to build an effective experimental protocol mimicking the human cardiovascular system to accurately detect phonoangiography (PAG) signal. Second, we aim to develop a powerful approach for quantifying the degree of stenosis (DOS) from PAG signal analysis. In the present study, we simulate the pulsatile fluid flow through 3D-model of a stenosed vessel. It generates flow sounds, which we capture using acoustic sensor. By varying the severity of stenosis, we detect a range of PAG signals associated with each well-defined DOS. Signal processing methods are then applied to pave the way for DOS quantification. For this purpose, time- and frequency-based methods are first involved to assess the DOS in the PAG signal in terms of global aspect. Thereafter, we leverage the Poincar & eacute;plot and wavelet packet (WP) decomposition to bring out the local features that are most relevant to quantify the severity of stenosis. Experimental results demonstrate the effectiveness of these localization methods in distinguishing between mild and severe stenoses. In conclusion, the study confirms that our proposed noninvasive system is very promising and can provide an easy-to-access and affordable solution for detecting and quantifying CAS disease in clinical settings.

关键词： sensors Fluids Carotid arteries Protocols Monitoring Blood Acoustic sensors Acoustic sensor brain stroke carotid artery stenosis (CAS) degree of stenosis (DOS) nonlinear analysis phonoangiography (PAG) signal sensor data processing time-frequency representation

来源：评论

学校读者我要写书评

暂无评论

A Reliable Virtual Sensing Architecture With Zero Additional Deployment Costs for SHM Systems

引用

IEEE sensorS JOURNAL 2024年第22期24卷 38527-38539页

作者： Zhang, Chong Lei, Ke Shi, Xin Wang, Yang Wang, Ting Wang, Xin Zhou, Lihu Zhang, Chuanhui Zeng, Xingjie Southwest Petr Univ SWPU Sch Comp Sci & Software Engn Chengdu 610500 Sichuan Peoples R China Mianyang Teachers Coll Mianyang 621000 Sichuan Peoples R China Chengdu Univ Informat Technol Sch Comp Sci Chengdu 610225 Sichuan Peoples R China

Structural health monitoring (SHM) serves to safeguard the operational safety of building structures;however, the high cost of SHM nodes limits its large-scale applications. In this article, we propose a novel computational model that integrates the physical model of SHM sensing to generate "virtual" sensor nodes with reliable data output at zero additional deployment cost, thereby enabling cost-efficient sensing for SHM systems. To achieve this, we build a generative adversarial network (GAN) combined with the physical model and design a discriminator to ensure that the generated virtual sensor node data aligns with the authentic physical characteristics. The generator employs a 1-D convolutional layer in a convolutional neural network (CNN) and a bi-long short-term memory network (LSTM) model to capture spatial-temporal correlations, along with a weighted smoothing algorithm to reduce noise while preserving data integrity. To support the model, we design a spatial-channel attention mechanism to enhance robustness. We conduct tests on the real-world dataset of the Belgian railway bridge KW51, and the results indicate that our system can generate virtual sensor nodes with 98.2% accuracy toward the ground truth without the need to deploy new devices (with no additional deployment cost). Hence, with its reliable sensing and cost-efficient features, we believe that our system could be helpful in facilitating the large-scale application of SHM systems, thereby providing effective safety monitoring for a wider range of buildings.

关键词： sensors Costs data models Computational modeling Reliability Predictive models Soft sensors sensor systems Generative adversarial networks Buildings Convolutional neural network (CNN) deep learning generative adversarial network (GAN) sensor data processing structural health monitoring (SHM)

来源：评论

学校读者我要写书评

暂无评论

data-Drive-Based Machine Learning and Singular Spectrum Analysis to Identify Optical Patterns in Harsh Environments

引用

IEEE sensorS JOURNAL 2024年第14期24卷 22189-22196页

作者： Miranda-Vega, Jesus E. Flores-Fuentes, Wendy Sergiyenko, Oleg Rodriguez-Quinonez, Julio C. Garcia-Gonzalez, Wendy Hernandez-Balbuena, Daniel Tecnolg Nacl Mexico IT Mexicali Dept Comp Syst Mexicali 21376 Mexico Autonomous Univ Baja Calif Fac Engn Mexicali 21100 Mexico Autonomous Univ Baja Calif Inst Engn Mexicali 21100 Baja California Mexico

This article proposes an enhancement of a singular spectrum analysis (SSA) technique based on Hilbert matrix (SSA-H) for autonomous navigation systems in a harsh environment. SSA is a technique that has caught the attention of different fields and is used to extract trends and patterns in the time series domain. In this work, SSA-H is used to transform raw optical signals into meaningful information to build machine learning (ML) models. A technical vision system (TVS) with laser scanning for depth measurements is presented. According to the implementation of the TVS outdoors, some particular issues, such as interference radiation detected by its photodiode, can affect the system's performance in determining depth measurements. This research extracts the laser beam patterns in a real environment to create ML models to solve the problem and address some of the technical challenges in a real environment. The main contribution of this work is designing an ML framework for recognizing the laser beam of the TVS based on SSA-H. Furthermore, a comparative analysis of ML techniques to discriminate sunlight interference was studied and compared with different configurations of SSA known in the literature. According to the results, the use of SSA-H can enhance the ML models such as ensemble learning (EL), feed-forward neural networks (FNNs), support vector machines (SVMs), Naive Bayes (NB) in conjunction with autocorrelation function coefficients (ACCs) as features.

关键词： Optical sensors Adaptive optics TV Measurement by laser beam Feature extraction Optical variables measurement Support vector machines Autonomous navigation depth measurement machine learning (ML) sensor data processing singular analysis spectrum technical vision system (TVS)

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Method for Cell-Wise Object Tracking, Velocity Estimation and Projection of sensor data over Time 25

Deep Learning Method for Cell-Wise Object Tracking, Velocity...

引用

IEEE 25th International Conference on Intelligent Transportation Systems (ITSC)

作者： Braun, Marco Luszek, Moritz Meuter, Mirko Spata, Dominic Kollek, Kevin Kummert, Anton Apt Serv Deutschland GmbH D-42119 Wuppertal Germany Univ Wuppertal Sch Elect Informat & Media Engn D-42119 Wuppertal Germany

ISBN: (数字)9781665468800

ISBN: (纸本)9781665468800

Current deep learning methods for environment segmentation and velocity estimation rely on Convolutional Recurrent Neural Networks to exploit spatio temporal relationships within obtained sensor data. In these approaches, scene dynamics are implicitly derived using ConvNets to correlate novel input and memorized data, which, for the task of recurrently processing sensor scans, suffer from architectural restrictions. In addition, these prior approaches lead to distorted data due to spatio temporal misalignments caused by the movement of external road users. In this work, we solve these issues with a novel Recurrent Neural Network unit. Within this unit, we track object encodings across consecutive frames on cell level by correlating key-query pairs derived from sensor inputs and memory states, respectively. We then use resulting tracking patterns to obtain scene dynamics and regress velocities. In a last step, the memory state of the Recurrent Neural Network is projected based on extracted velocity estimates to resolve the aforementioned spatio temporal misalignment.

关键词： Deep Learning Perception Recurrent Neural Networks sensor data processing Velocity Estimation

来源：评论

学校读者我要写书评

暂无评论

EDPNet (Efficient DB and PARSeq Network): A Robust Framework for Online Digital Meter Detection and Recognition Under Challenging Scenarios

引用

sensorS 2025年第8期25卷 2603-2603页

作者： Guan, Songwen Niu, Zhitian Kong, Ming Wang, Shiling Hua, Hangbo China Jiliang Univ Coll Metrol Measurement & Instrument Hangzhou 310018 Peoples R China

Challenges such as perspective distortion, irregular reading regions, and complex backgrounds in natural scenes hinder the accuracy and efficiency of automatic meter reading systems. Current mainstream approaches predominantly utilize object-detection-based methods without optimizing for text characteristics, while enhancements in detection robustness under complex backgrounds typically focus on data preprocessing rather than model architecture. To address these limitations, a novel end-to-end framework, i.e., EDPNet (Efficient DB and PARSeq Network), is proposed to integrate efficient boundary detection and text recognition. EDPNet comprises two key components, EDNet for detection and EPNet for recognition, where EDNet employs EfficientNetV2-s as its backbone with the Multi-Scale KeyDrop Attention (MSKA) and Efficient Multi-scale Attention (EMA) mechanisms to address perspective distortion and complex background challenges, respectively. During the recognition stage, EPNet integrates a DropKey Attention module into the PARSeq encoder, enhancing the recognition of irregular readings while effectively mitigating overfitting. Experimental evaluations show that EDNet achieves an F1-score of 0.997988, outperforming DBNet++ (ResNet50) by 0.61%. In challenging scenarios, EDPNet surpasses state-of-the-art methods by 0.7 similar to 1.9% while reducing parameters by 20.03%. EPNet achieves 90.0% recognition accuracy, exceeding the current best performance by 0.2%. The proposed framework delivers superior accuracy and robustness in challenging conditions while remaining lightweight.

关键词： deep learning digital meter reading EDPNet sensor data processing smart sensor systems

来源：评论

学校读者我要写书评

暂无评论

Early detection of cardiorespiratory complications and training monitoring using wearable ECG sensors and CNN

引用

BMC MEDICAL INFORMATICS AND DECISION MAKING 2024年第1期24卷 1页

作者： Lu, HongYuan Feng, XinMiao Zhang, Jing Beijing Sport Univ Sport Coaching Coll Beijing 100084 Peoples R China Zhejiang Greentown Cardiovasc Hosp Dept Cardiol Hangzhou 310012 Peoples R China

This research study demonstrates an efficient scheme for early detection of cardiorespiratory complications in pandemics by Utilizing Wearable Electrocardiogram (ECG) sensors for pattern generation and Convolution Neural Networks (CNN) for decision analytics. In health-related outbreaks, timely and early diagnosis of such complications is conclusive in reducing mortality rates and alleviating the burden on healthcare facilities. Existing methods rely on clinical assessments, medical history reviews, and hospital-based monitoring, which are valuable but have limitations in terms of accessibility, scalability, and timeliness, particularly during pandemics. The proposed scheme commences by deploying wearable ECG sensors on the patient's body. These sensors collect data by continuously monitoring the cardiac activity and respiratory patterns of the patient. The collected raw data is then transmitted securely in a wireless manner to a centralized server and stored in a database. Subsequently, the stored data is assessed using a preprocessing process which extracts relevant and important features like heart rate variability and respiratory rate. The preprocessed data is then used as input into the CNN model for the classification of normal and abnormal cardiorespiratory patterns. To achieve high accuracy in abnormality detection the CNN model is trained on labeled data with optimized parameters. The performance of the proposed scheme is evaluated and gauged using different scenarios, which shows a robust performance in detecting abnormal cardiorespiratory patterns with a sensitivity of 95% and specificity of 92%. Prominent observations, which highlight the potential for early interventions include subtle changes in heart rate variability and preceding respiratory distress. These findings show the significance of wearable ECG technology in improving pandemic management strategies and informing public health policies, which enhances preparedness and resilience in the face o

关键词： CNN IoT Remote patient sensor data processing Predictive modeling Cardiorespiratory

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：