ieeexplore最新文献_第8页

A Two-Stage Model Compression Framework for Object Detection in Autonomous Driving Scenarios 自动驾驶场景中目标检测的两阶段模型压缩框架

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2024-12-11 DOI: 10.1109/JSEN.2024.3498910

Qiyi He;Ao Xu;Zhiwei Ye;Wen Zhou;Yifan Zhang;Ruijie Xi

{"title":"A Two-Stage Model Compression Framework for Object Detection in Autonomous Driving Scenarios","authors":"Qiyi He;Ao Xu;Zhiwei Ye;Wen Zhou;Yifan Zhang;Ruijie Xi","doi":"10.1109/JSEN.2024.3498910","DOIUrl":"https://doi.org/10.1109/JSEN.2024.3498910","url":null,"abstract":"Recently, object detection, as a critical technology to improve the autonomous perception capabilities of optical sensors in autonomous driving systems (ADSs), has become a primary research focus in the field of ADS perception. However, the practical implementation of these networks can be challenging due to their scale and complexity, making it difficult to implement them directly on devices with limited resources. To address this issue, a universal two-stage model compression approach has been implemented. During the initial phase, ShuffDet (SD) is introduced as a lightweight network architecture to reduce the structural parameters within the network effectively. During the second phase, probability distribution distillation (PDD) techniques are applied to the network post-lightweighting to mitigate the impact of structural lightening on network precision. The algorithm was tested using two public datasets, BDD100K and KITTI. The experimental outcomes demonstrate that this method enhances precision while substantially lowering the model’s complexity. To demonstrate its universality, we replaced the base network with YOLOX, which produced satisfactory results. To determine the effectiveness of the method in real-world deployment settings, we deployed the model on an NVIDIA Jetson Nano chip. The experimental outcomes confirmed the effectiveness of our proposed approach, achieving real-time detection standards. When compared to alternative lightweighting techniques, this method is more advantageous for deployment in ADSs.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 2","pages":"3735-3749"},"PeriodicalIF":4.3,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142975778","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

CM-VGG16: ConvMixer-Enhanced VGG16 Model for Automatic Detection of Heart Valve Diseases From Phonocardiogram Signals CM-VGG16：从心音图信号自动检测心脏瓣膜疾病的ConvMixer-Enhanced VGG16模型

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2024-12-11 DOI: 10.1109/JSEN.2024.3511633

Brundavanam Satyasai;Rajeev Sharma

{"title":"CM-VGG16: ConvMixer-Enhanced VGG16 Model for Automatic Detection of Heart Valve Diseases From Phonocardiogram Signals","authors":"Brundavanam Satyasai;Rajeev Sharma","doi":"10.1109/JSEN.2024.3511633","DOIUrl":"https://doi.org/10.1109/JSEN.2024.3511633","url":null,"abstract":"The absence of medical resources at remote places prevents many patients from receiving a prompt and accurate diagnosis of cardiovascular disorders. To address this, we proposed a novel deep learning model based on partially fine-tuned VGG16 and ConvMixer for the automatic identification of various heart valve diseases (HVDs) from phonocardiogram (PCG) signals. The method involves preprocessing PCG signals and converting them into gammatone filterbank (GFB) based 2-D time–frequency images. To generate time–frequency images, we used gammatonegram, gammatone cepstral coefficients (GTCCs), and gammatone discrete wavelet coefficients (GDWCs) techniques. These time–frequency images are augmented to reduce overfitting and then fed into a VGG16 model. Partial fine-tuning of the VGG16 model accelerates convergence and further improves performance. By extending the VGG16 model with ConvMixer, Global AveragePooling, Dense, and Softmax layers, we enhance its capacity to capture intricate patterns. The ConvMixer enriches spatial and channelwise features using Depthwise and Pointwise convolutions. We also performed an ablation analysis to highlight the effect of ConvMixer with VGG16. In addition, performance evaluation based on precision, recall, F1-score, test accuracy, and validation accuracy reveals the efficacy of the proposed method. Comparisons between gammatonegram, GTCC, and GDWC show superior performance of gammatonegram, achieving a test accuracy of 99.60% and validation accuracy of 99.75%. Our approach demonstrates significant advances over existing methods, offering a promising solution for remote diagnosis of HVDs.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 2","pages":"3998-4005"},"PeriodicalIF":4.3,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993357","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Performance Enhancement of EAD Thrusters With Nonuniform Emitters Array 非均匀发射阵列对EAD推进器性能的增强

IF 1.3 4区物理与天体物理

IEEE Transactions on Plasma Science Pub Date : 2024-12-09 DOI: 10.1109/TPS.2024.3505980

Davide Usuelli;Raffaello Terenzi;Stefano Trovato;Marco Belan

{"title":"Performance Enhancement of EAD Thrusters With Nonuniform Emitters Array","authors":"Davide Usuelli;Raffaello Terenzi;Stefano Trovato;Marco Belan","doi":"10.1109/TPS.2024.3505980","DOIUrl":"https://doi.org/10.1109/TPS.2024.3505980","url":null,"abstract":"This work presents an experimental campaign to optimize the performance of electro-aerodynamic (EAD) thrusters through nonuniform emitter arrangements. The study examines the impact of emitter configurations on thrust and thrust-to-power coefficients <inline-formula> <tex-math>$boldsymbol {C}_{boldsymbol {T}}$ </tex-math></inline-formula> and <inline-formula> <tex-math>$boldsymbol {C}_{boldsymbol {TP}}$ </tex-math></inline-formula>. Different emitter arrangements, including collinear and staggered arrays, are tested using thrust, electrical, and velocity measurements as diagnostics. The tests are parametrically performed for different sizes (chords) of the collector electrodes. Results reveal that nonuniform emitter configurations outperform standard arrays, in particular, with short chord collectors, widely spaced apart. An optimal configuration for <inline-formula> <tex-math>$boldsymbol {C}_{boldsymbol {T}}$ </tex-math></inline-formula> is identified among the staggered ones. In addition, droplet collectors demonstrate competitive performance compared to airfoil collectors.","PeriodicalId":450,"journal":{"name":"IEEE Transactions on Plasma Science","volume":"52 11","pages":"5414-5421"},"PeriodicalIF":1.3,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10785549","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142993820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Blank Page 空白页

IF 1.3 4区物理与天体物理

IEEE Transactions on Plasma Science Pub Date : 2024-12-09 DOI: 10.1109/TPS.2024.3506233

引用次数: 0

IEEE Access IEEE访问

IF 1.3 4区物理与天体物理

IEEE Transactions on Plasma Science Pub Date : 2024-12-09 DOI: 10.1109/TPS.2024.3506425

引用次数: 0

Blank Page 空白页

IF 1.3 4区物理与天体物理

IEEE Transactions on Plasma Science Pub Date : 2024-12-09 DOI: 10.1109/TPS.2024.3504907

引用次数: 0

Member ad suite 会员广告套件

IF 1.3 4区物理与天体物理

IEEE Transactions on Plasma Science Pub Date : 2024-12-09 DOI: 10.1109/TPS.2024.3506423

引用次数: 0

Development of SWCNTs/PDMS Composite Strain Sensors Integrated Smart Glove for Human-Machine Interface Applications 用于人机界面应用的SWCNTs/PDMS复合应变传感器集成智能手套的开发

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2024-12-09 DOI: 10.1109/JSEN.2024.3509494

Suraj Baloda;Sashank Krishna Sriram;Puneet Sharma;Sumitra Singh;Navneet Gupta

{"title":"Development of SWCNTs/PDMS Composite Strain Sensors Integrated Smart Glove for Human-Machine Interface Applications","authors":"Suraj Baloda;Sashank Krishna Sriram;Puneet Sharma;Sumitra Singh;Navneet Gupta","doi":"10.1109/JSEN.2024.3509494","DOIUrl":"https://doi.org/10.1109/JSEN.2024.3509494","url":null,"abstract":"Smart gloves with their multifunctional sensing capabilities, hold a promising in human-machine interface (HMI) applications. In this work, we present a smart glove based on single-walled carbon nanotubes (SWCNTs) incorporated within a polydimethylsiloxane (PDMS) matrix integrated flexible strain sensor. The flexible strain sensor is designed and fabricated to serve as a crucial sensing component for the smart glove. The integration of SWCNTs with PDMS offers a unique combination of mechanical flexibility and electrical sensitivity, making it an ideal candidate for real-time monitoring and feedback in HMI applications. The fabricated SWCNTs/PDMS strain exhibits a high sensing range, covering up to a strain range of 70%, along with high sensitivity, characterized by a gauge factor (GF) of 73. Additionally, the strain sensor demonstrates excellent linearity, reliability, and durability, enduring repeated loading and unloading for 3000 cycles under a 50% strain. Furthermore, the developed smart glove successfully extends sensing functionality, enabling real time-tasks such as finger motion detection, controlling robotic fingers and can be used in the field of smart wearable electronics and HMI applications.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 2","pages":"2400-2407"},"PeriodicalIF":4.3,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10786232","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142975842","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Guest Editorial IEEE TPS—SOFE 2023 Special Issue IEEE tps - sof2023特刊客座编辑

IF 1.3 4区物理与天体物理

IEEE Transactions on Plasma Science Pub Date : 2024-12-09 DOI: 10.1109/TPS.2024.3456849

Rhian Chapman

引用次数: 0

Online Error Compensation of Gyroscope in MWD Based on MGMA 基于MGMA的随钻测量陀螺仪在线误差补偿

IF 4.3 2区综合性期刊

IEEE Sensors Journal Pub Date : 2024-12-09 DOI: 10.1109/JSEN.2024.3508658

Jinxian Yang;Fengshuai Yin

{"title":"Online Error Compensation of Gyroscope in MWD Based on MGMA","authors":"Jinxian Yang;Fengshuai Yin","doi":"10.1109/JSEN.2024.3508658","DOIUrl":"https://doi.org/10.1109/JSEN.2024.3508658","url":null,"abstract":"To solve the problem of low accuracy of the microelectromechanical system (MEMS) gyroscope output in measurement while drilling (MWD), an online error compensation method for MEMS gyroscope based on magnetic-gravitational mayfly algorithm (MGMA) is proposed in this article. First, the source of the MEMS gyroscope error is analyzed and the error compensation model is established. Then, using the feature that the accelerometer has no cumulative error to design objective function, and the constraint conditions of the angle of gravity vector are designed by using anti-vibration magnetometer. Furthermore, on the basis of mayfly algorithm (MA), the upper and lower bounds are determined adaptively according to the relationship between the output of the gyroscope and magnetometer, aiming at the constantly changing gyroscope error parameters caused by the harsh environment in the drilling process. The relative error of gravitational modulus is used to design the inertia weight and balance the exploration and exploitation of the algorithm. Finally, according to the relative error of the magnetic-gravitational modulus, a mutation disturbance strategy is introduced in the offsprings to reduce the possibility of falling into the local optimal. The experimental results show that the gyroscope error after MGMA compensation is obviously decreased, the error of the inclination is reduced from 9.88° to 1.67°, and compared with particle swarm optimization (PSO) and MA algorithm, it has faster speed and higher accuracy.","PeriodicalId":447,"journal":{"name":"IEEE Sensors Journal","volume":"25 2","pages":"2392-2399"},"PeriodicalIF":4.3,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142975960","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"综合性期刊","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0