检索结果-内蒙古大学图书馆

2022 International Conference on Information Technology Research and Innovation, ICITRI 2022

作者： Tutiani Wati, Sutresna Information System Gunadarma University Jakarta Indonesia Gunadarma University Computer Engineering Jakarta Indonesia

ISBN: (数字)9781665461849

ISBN: (纸本)9781665461849

Acne is a skin disorder caused by the overproduction of oil glands that causes infection and inflammation of the skin and is one of the most common conditions in the world. The Convolutional Neural Network (CNN) approach method of convolution operation is used to detect objects in the assessment of acne and the correct handling solutions to overcome them in the form of an android-based application. Data processing is carried out in several stages. The initial phase of data processing use LabeIImg software to label the image object, producing a file with an XML extension. The Efficientdet-lite model is a model that has been optimized to run on mobile devices with the Efficientdet-lite0 model architecture in the modeling process that has been trained using the hyperparameter model, which has a detection loss of 0.056 and produces an Average Precision value of 0.1256. The androidbased acne detection application was successfully created using the CNN method and the Efficientdet-lite model, the application work on smartphones with a minimum version of nougat 7.1. The results of the Average Precision values from the labeling of seven classes are 0.0627, 0.0027, 0.1575, 0.0217, 0.0038, 0.01224, and 0.014, so it can be concluded that the average precision value in each category is quite good but must be developed to achieve more accurate detection performance. © 2022 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Multi-Task Learning with Convolutional Neural Network Approach for Packet Collision Avoidance in 802.11 WLAN 9

Multi-Task Learning with Convolutional Neural Network Approa...

引用

9th NAFOSTED Conference on Information and computer Science, NICS 2022

作者： Putra, Dody Ichwana Pratama, Harry Bintang Nakashima, Tomoki Nagao, Yuhei Kurosaki, Masayuki Ochi, Hiroshi Grad. School of Computer Science and System Engineering Kyushu Institute of Technology Iizuka Japan

ISBN: (纸本)9781665454223

Packet collision can degrade wireless network performance. The IEEE 802.11 Wireless Local Area Network (WLAN) uses the Clear Channel Assessment (CCA) mechanism to monitor channel availability to avoid interference of the presence signal. CCA successfully detects 802.11 signals if it obtains the packet preamble information or detects the threshold ambient power on the channel to determine the channel state. This paper proposes multi-task learning (MTL) with convolutional neural network (CNN) approach to detect WLAN packet formats and modulation types without preamble part information as a supplement to enhance CCA sensitivity. The main advantages of this method over single-task training are high classification accuracy and rapid learning with a lightweight neural network model. Shared knowledge of representation layers, such as model weights or gradients, improves the efficiency of training data and reduces redundancy. WLAN signals generated by the Matlab waveform simulator are used to verify the accuracy of the proposed method, which is then implemented on a real-time SDR-based hardware testbed. Although different time offsets affect the classifications, the proposed method proves superior in classifying the packet format and modulation of WLAN signals with an accuracy of 98.93% and 88.53% at SNR = 24 dB, respectively. The proposed method improves channel utilization and throughput of the WLAN network, as demonstrated by an NS-3 simulation. © 2022 IEEE.

关键词： MATLAB

来源：评论

学校读者我要写书评

暂无评论

FedMoS: Taming Client Drift in Federated Learning with Double Momentum and Adaptive Selection 42

FedMoS: Taming Client Drift in Federated Learning with Doubl...

引用

42nd IEEE International Conference on computer Communications, INFOCOM 2023

作者： Wang, Xiong Chen, Yuxin Li, Yuqing Liao, Xiaofei Jin, Hai Li, Bo Cluster and Grid Computing Lab School of Computer Science and Technology Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Wuhan China Wuhan University School of Cyber Science and Engineering Wuhan China Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong

ISBN: (纸本)9798350334142

Federated learning (FL) enables massive clients to collaboratively train a global model by aggregating their local updates without disclosing raw data. Communication has become one of the main bottlenecks that prolongs the training process, especially under large model variances due to skewed data distributions. Existing efforts mainly focus on either single momentum-based gradient descent, or random client selection for potential variance reduction, yet both often lead to poor model accuracy and system efficiency. In this paper, we propose FedMoS, a communication-efficient FL framework with coupled double momentum-based update and adaptive client selection, to jointly mitigate the intrinsic variance. Specifically, FedMoS maintains customized momentum buffers on both server and client sides, which track global and local update directions to alleviate the model discrepancy. Taking momentum results as input, we design an adaptive selection scheme to provide a proper client representation during FL aggregation. By optimally calibrating clients' selection probabilities, we can effectively reduce the sampling variance, while ensuring unbiased aggregation. Through a rigid analysis, we show that FedMoS can attain the theoretically optimal O(T - 2/3) convergence rate. Extensive experiments using real-world datasets further validate the superiority of FedMoS, with 58%-87% communication reduction for achieving the same target performance compared to state-of-the-art techniques. © 2023 IEEE.

关键词： Momentum

来源：评论

学校读者我要写书评

暂无评论

Semantic Segmentation and YOLO Detector over Aerial Vehicle Images

引用

computers, Materials & Continua 2024年第8期80卷 3315-3332页

作者： Asifa Mehmood Qureshi Abdul Haleem Butt Abdulwahab Alazeb Naif Al Mudawi Mohammad Alonazi Nouf Abdullah Almujally Ahmad Jalal Hui Liu Faculty of Computing and AI Air UniversityIslamabad44000Pakistan Department of Computer Science College of Computer Science and Information SystemNajran UniversityNajran55461Saudi Arabia Department of Information Systems College of Computer Engineering and SciencesPrince Sattam bin Abdulaziz UniversityAl-Kharj16273Saudi Arabia Department of Information Technology College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityP.O.Box 84428Riyadh11671Saudi Arabia Cognitive Systems Lab University of BremenBremen28359Germany

Intelligent vehicle tracking and detection are crucial tasks in the realm of highway ***,vehicles come in a range of sizes,which is challenging to detect,affecting the traffic monitoring system’s overall *** learning is considered to be an efficient method for object detection in vision-based *** this paper,we proposed a vision-based vehicle detection and tracking system based on a You Look Only Once version 5(YOLOv5)detector combined with a segmentation *** model consists of six *** the first step,all the extracted traffic sequence images are subjected to pre-processing to remove noise and enhance the contrast level of the *** pre-processed images are segmented by labelling each pixel to extract the uniform regions to aid the detection phase.A single-stage detector YOLOv5 is used to detect and locate vehicles in *** detection was exposed to Speeded Up Robust Feature(SURF)feature extraction to track multiple *** on this,a unique number is assigned to each vehicle to easily locate them in the succeeding image frames by extracting them using the feature-matching ***,we implemented a Kalman filter to track multiple *** the end,the vehicle path is estimated by using the centroid points of the rectangular bounding box predicted by the tracking *** experimental results and comparison reveal that our proposed vehicle detection and tracking system outperformed other state-of-the-art *** proposed implemented system provided 94.1%detection precision for Roundabout and 96.1%detection precision for Vehicle Aerial Imaging from Drone(VAID)datasets,respectively.

关键词： Semantic segmentation YOLOv5 vehicle detection and tracking Kalman filter SURF

来源：评论

学校读者我要写书评

暂无评论

AccelES: Accelerating Top-K SpMV for Embedding Similarity via Low-bit Pruning 31

AccelES: Accelerating Top-K SpMV for Embedding Similarity vi...

引用

31st IEEE International Symposium on High Performance computer Architecture, HPCA 2025

作者： Zhai, Jiaqi Shi, Xuanhua Huang, Kaiyi Ye, Chencheng Hu, Weifang He, Bingsheng Jin, Hai Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Cluster and Grid Computing Lab School of Computer Science and Technology Wuhan430074 China National University of Singapore School of Computing 119077 Singapore

ISBN: (纸本)9798331506476

In the realm of recommendation systems, achieving real-time performance in embedding similarity tasks is often hindered by the limitations of traditional Top-K sparse matrix-vector multiplication (SpMV) methods, which suffer from high latency due to inefficient memory access patterns. This paper identifies these critical gaps and introduces AccelES, a novel approach that significantly enhances the efficiency of Top-K SpMV. Our method employs a two-stage calculation scheme: the first stage utilizes a compact, low-bit dataset to quickly identify the most relevant entries, while the second stage performs full-precision calculations solely on this pruned subset, thereby minimizing computational overhead. Furthermore, AccelES incorporates innovative matrix representations, Ultra-CSR and Random-CSR, which optimize memory bandwidth utilization. Experimental results demonstrate that AccelES accelerates performance, surpassing state-of-the-art FPGA, GPU, and CPU solutions by factors of 3.4×, 2.5×, and 153.3×, respectively, under controlled conditions. These advancements not only enhance processing speed but also significantly improve real-time performance in recommendation systems, establishing AccelES as a pivotal contribution to the field of Top-K sparse matrix-vector multiplication. © 2025 IEEE.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Up to 320-GBaud Coherent Optical system Based on Broadband Segmented TFLN I/Q Modulator

Up to 320-GBaud Coherent Optical System Based on Broadband S...

引用

2024 Asia Communications and Photonics Conference, ACP 2024 and International Conference on Information Photonics and Optical Communications, IPOC 2024

作者： Zhou, Lingjun Fang, Xiansong Zhu, Yixiao Zhu, Junbo Li, Yunchen Nie, Xiaomin Zhou, Xian Yang, Chuanchuan Wang, Lei Hu, Weisheng Li, Ke He, Zhixue Zhang, Fan School of Electronic and Computer Engineering Peking University Shenzhen China Peng Cheng Laboratory Shenzhen China State Key Laboratory of Advanced Optical Communication System and Networks School of Electronics Peking University Beijing China State Key Laboratory of Advanced Optical Communication System and Networks Shanghai Jiao Tong University Shanghai China School of Computer & Communication Engineering University of Science and Technology Beijing Beijing China

We demonstrate the record 320-GBd single-polarization QPSK and 300-GBd dual-polarization QPSK signal generation and intradyne coherent detection. This result is achieved with a novel broadband segmented TFLN I/Q modul... 详细信息

ISBN: (纸本)9798350379266

关键词： Quadrature phase shift keying

来源：评论

学校读者我要写书评

暂无评论

Remaining Useful Life Prediction of Turbofan Engines based on CNN-LSTM Hybrid Model

Remaining Useful Life Prediction of Turbofan Engines based o...

引用

Cloud Computing, Big Data Applications and Software engineering (CBASE), International Conference on

作者： Jianfang Wei Linggang Meng Junrong Du Zhifeng Yin National Computer System Engineering Research Institute of China Beijing China

ISBN: (数字)9798331506582

ISBN: (纸本)9798331506599

Good working condition of mechanical facility is necessary to ensure orderly industrial production, and remaining useful life (RUL) estimation of mechanical facility via current monitoring parameters is an important issue for condition-based maintenance. Deep learning has good capacity of nonlinear feature extraction, high dimension time series modeling and complex pattern recognition, and has good application prospect in the field of RUL prediction of mechanical facility. A hybrid model with CNN-LSTM structure for RUL prediction of mechanical facility is proposed, and a multivariate time series model with optimal length based sliding window is established to extract inner features. The method is validated on NASA's public turbofan engines dataset, achieving accurate remaining useful life prediction of turbofan engines.

关键词： Computational modeling Time series analysis Production Predictive models Feature extraction Maintenance Convolutional neural networks Engines Predictive maintenance Software engineering

来源：评论

学校读者我要写书评

暂无评论

An end-to-end repair-based joint training framework for weakly supervised pavement crack segmentation

引用

Multimedia Tools and Applications 2025年第16期84卷 16281-16299页

作者： Zhou, Hui Tao, Huanjie Duan, Qianyue Hu, Zhenwu Deng, Yishi School of Computer Science Northwestern Polytechnical University Xi’an710129 China School of Cyberspace Security Northwestern Polytechnical University Xi’an710129 China Engineering Research Center of Embedded System Integration Ministry of Education Xi’an710129 China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Xi’an710129 China

Weakly supervised pavement crack segmentation aims to assign each pixel of pavement surface images a category label (crack or non-crack) using limited annotation information. Most existing methods adopt the multi-stage approach based on the class activation map (CAM), which outputs from a pre-trained crack classification model, to generate the pixel-level pseudo labels, and then train a segmentation model using these pseudo labels. However, these methods have two notable drawbacks: (i) CAM focuses primarily on the most discriminative regions of the image, potentially resulting in an incomplete estimation of crack regions, and (ii) the process of obtaining pixel-level pseudo labels from CAM is complex and may introduce noise. To avoid these issues, we propose an end-to-end repair-based joint training framework for weakly supervised pavement crack segmentation. Specifically, to better guide the model to pay more attention to the repair process of crack regions, we introduce the segmentation loss, which assigns different weights for crack regions and background regions, through the Residual Project Network. Additionally, to alleviate the impact of the domain gap between synthetic and real datasets, we introduce the consistency loss through the joint training paradigm of unpaired data that incorporates both crack and non-crack images into the training process simultaneously. Furthermore, to enable the model to effectively extract local features and reduce the model's computational complexity, we introduce the Lightweight Multi-head Self-attention module. The experiment results on the CRACK500 Dataset, the CFD Dataset, and the AEL Dataset demonstrate that our model achieves better performance than some existing weakly supervised pavement segmentation methods. © The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature 2024.

关键词： Repair

来源：评论

学校读者我要写书评

暂无评论

A Model Predictive Current Control for a Three-Phase Modular Matrix Converter

A Model Predictive Current Control for a Three-Phase Modular...

引用

2024 IEEE Energy Conversion Congress and Exposition, ECCE 2024

作者： Sarebanzadeh, Maryam Hosseinzadeh, Mohammad Ali Kennel, Ralph Babaei, Ebrahim Rivera, Marco Wheeler, Patrick Technical University of Munich High-Power Converters System Munich Germany University of Tabriz Faculty of Electrical and Computer Engineering Tabriz Iran Research Group Department of Electrical and Electronic Engineering Faculty of Engineering Nottingham United Kingdom Vicerrectoría Academica Talca Chile

ISBN: (纸本)9798350376067

The modular matrix converter (MMC) integrates a multi-winding transformer with a three-phase-to-single-phase matrix converter for each phase, making it suitable for high-power, high-voltage applications. Predictive control is an advanced control technique widely applied to power converters due to its numerous advantages, including fast dynamic response, the elimination of the need for proportional gain, and straightforward implementation. This study proposes a model predictive control (MPC) strategy to regulate load currents, reactive power, and common-mode voltage in a three-phase modular matrix converter. The proposed MPC algorithm selects the optimal switching states from all valid options for the modular matrix converter to apply in the next control step. A cost function is then used to minimize the error between the predicted system variables and their reference values, ensuring that the best states are applied to the modular matrix converter. The proposed MPC technique effectively controls the load currents to follow the desired reference signals, maintains sinusoidal source current waveforms by regulating reactive power, and reduces the magnitude of the common-mode voltage. The performance of the proposed approach is demonstrated through simulation results obtained in the MATLAB/Simulink environment. © 2024 IEEE.

关键词： Predictive control systems

来源：评论

学校读者我要写书评

暂无评论

Detecting Pain During Cognitive Tasks via Visibility Graphs of Cortical Signals

Detecting Pain During Cognitive Tasks via Visibility Graphs ...

引用

IEEE International Symposium on Biomedical Imaging

作者： Ashwini Subramanian Laleh Najafizadeh Department of Electrical and Computer Engineering Integrated System and NeuroImaging Laboratory Rutgers University

ISBN: (数字)9798331520526

ISBN: (纸本)9798331520533

Detecting pain is critical for developing adaptive systems in clinical and assistive settings, allowing for timely interventions. This work presents an approach to detect the presence of physical pain during the performance of cognitive tasks from cortical signals. Cortical signals from the motor and prefrontal cortices are acquired using functional near in-frared spectroscopy (fNIRS) during two cognitive tasks, per-formed in the absence and presence of physical pain. Visibil-ity graphs (VGs) of these signals are constructed, and graph metrics of averaged clustering coefficient $(C)$ and edge den-sity $(D)$ are extracted. Statistical analysis reveals differences in these metrics for graphs corresponding to tasks performed under no-pain (NP) versus with-pain (WP) conditions, partic-ularly for signals obtained from the motor cortex. The graph metrics were then used as features to a support vector machine (SVM), achieving an accuracy exceeding 80% in distinguishing between tasks performed with and without pain. Our findings suggest that metrics from VGs of cortical sig-nals may serve as potential biomarkers for pain during cog-nitive tasks. This approach could be especially beneficial for non-verbal patients using assistive brain-computer interfaces.

关键词： Measurement Support vector machines Deep learning Pain Statistical analysis Image edge detection Motors Feature extraction Complexity theory Functional near-infrared spectroscopy

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：