检索结果-内蒙古大学图书馆

作者： Xie, Zhonghui Kong, Wa Zhou, Xinyu Zhang, Wence Zhong, Yujie Xia, Jing School of Computer Science and Communication Engineering Jiangsu University Zhenjiang China Jiangsu Key Laboratory of Security Technology for Industrial Cyberspace Jiangsu University Zhenjiang China Department of Electronic Information Engineering Hong Kong Polytechnic University Hong Kong

In the manufacturing process of power amplifier (PA), various defects on the circuit surface will seriously affect the circuit performance and its operation. To solve the above problems, this article proposes a circuit defect detection method based on improved patch-based support vector data description algorithm (Patch SVDD), which uses contrastive learning to enhance the feature extraction ability of neural network. An image calibration algorithm is used for calibration preprocessing to enhance the robustness of the model. The Euclidean distance between a query image patch and its nearest normal patch is defined to be an anomaly score. For verification, three defects in the PA circuit, including components missing, solder contamination and component orientation dislocation, were detected. The experimental results show that, compared with conventional method, the area under receiver operating characteristic (AUROC) of the improved anomaly detection model increased from 90.1% to 95.1%, which improves the detection accuracy effectively. © 2023 John Wiley & Sons Ltd.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Automatic Optimization of Guidance Guardrail Layout Based on Multi-Objective Evolutionary Algorithm

引用

Complex System Modeling and Simulation 2024年第4期4卷 353-367页

作者： Wei-Li Liu Yixin Chen Xiang Li Jinghui Zhong Rongjun Chen Hu Jin School of Computer Science Guangdong Polytechnic Normal UniversityGuangzhou 510006China School of Computer Science and Engineering South China University of TechnologyGuangzhou 510006China School of Electrical Engineering Hanyang UniversityAnsan 15588Republic of Korea

Guardrails commonly play a significant role in guiding pedestrians and managing crowd flow to prevent congestion in public ***,existing methods of the guardrail layout mainly rely on manual design or mathematical models,which are not flexible or effective enough for crowd control in large public *** address this limitation,this paper introduces a novel automated optimization framework for guidance guardrails based on a multi-objective evolutionary *** paper incorporates guidance signs into the guardrails and designs a coding-decoding scheme based on Gray code to enhance the flexibility of the guardrail *** addition to optimizing pedestrian passage efficiency and safety,the paper also considers the situation of pedestnan counterflow,making the guardrai layout more *** results have demonstrated the effectiveness of the proposed method in alleviating safety hazards caused by potential congestion,as well as its significant improvements in passage effciency and prevention of pedestrian counte rflow.

关键词： automatical guardrall layout optimization,crowd simulation multi-objective evolutionary algorithm

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approach to the Internet of Things Threat Detection

Machine Learning Approach to the Internet of Things Threat D...

引用

International Conference on Data science and Network Engineering, ICDSNE 2023

作者： Upadhyay, Alka Naaz, Sameena Thakur, Vinay Ansari, Iffat Rehman Department of Computer Science and Technology School of Engineering Sciences and Technology Jamia Hamdard New Delhi India New Delhi India Electronics Engineering Section Faculty of Engineering and Technology University Women’s Polytechnic A.M.U.UP Aligarh202002 India

ISBN: (纸本)9789819967544

The development in software, hardware and communication technologies has made the broadcasting of sensory data collected from various devices very easy and simple. Interconnected devices through Internet technology form the Internet of Things (IoT). Applying intelligent methods for the analysis of this big data is the key which develops smart IoT applications. The world today has become increasingly dependent on digitized data which raises various security concerns and the need for advanced and reliable security technologies to deal with the increasing number of cyber-attacks. The work depicted in this paper makes use of machine learning techniques to detect cyber-attacks using the UNSW-NB15 data set and the KDD CUP 1999 dataset. Decision Tree, k-means clustering, multi-layer perception (MLP), Naive Byes and Random Forest classifier are the algorithms used in this work in order to find higher level information about the data. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Application of TQWT based filter-bank for sleep apnea screening using ECG signals

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 893-904页

作者： Nishad, Anurag Pachori, Ram Bilas Acharya, U. Rajendra Discipline of Electrical Engineering Indian Institute of Technology Indore Indore453552 India Department of Electronics and Computer Engineering Ngee Ann Polytechnic Singapore599489 Singapore Department of Biomedical Engineering School of Science and Technology SIM University Singapore599491 Singapore Department of Biomedical Engineering Faculty of Engineering University of Malaya Kuala Lumpur50603 Malaysia

The sleep apnea is a disease in which there is the absence of airflow during respiration for at least 10 s. It may occur several times during the night sleep. This disease can lead to many types of cardiovascular diseases. To detect this disease, signals obtained from many channels of polysomnography are to be observed visually by physicians for the long duration. This procedure is expensive, time-consuming, and subjective. Hence, it is required to build an automated system to detect the sleep apnea with few channels. This paper uses single-lead electrocardiogram (ECG) signal to detect apneic and non-apneic events. The proposed method uses tunable-Q wavelet transform (TQWT) based filter-bank instead of TQWT to decompose the segment of ECG signal into several constant bandwidth sub-band signals. Then centered correntropies are computed from the various sub-band signals. The obtained features are then fed to the various classifiers to select the optimum performing classifier. In this work, we have obtained the highest classification accuracy, specificity, and sensitivity of 92.78%, 93.91%, and 90.95% respectively using random forest classifier. Hence, our developed prototype is ready for validation with the huge database and clinical usage. © Springer-Verlag GmbH Germany, part of Springer Nature 2018.

关键词： Filter banks

来源：评论

学校读者我要写书评

暂无评论

Effective Density-Based Concept Drift Detection for Evolving Data Streams 24th

Effective Density-Based Concept Drift Detection for Evolving...

引用

24th International Conference on Parallel and Distributed Computing, Applications and Technologies, PDCAT 2023

作者： Cui, Zelin Tian, Hui Shen, Hong Institute of Information Security Engineering Chinese Academy of Sciences Beijing China School of Information and Communication Technology Griffith University Brisbane Australia Faculty of Applied Sciences Macao Polytechnic University China School of Computer Science and Engineering Sun Yat-Sen University Guangzhou China

ISBN: (纸本)9789819982103

Concept drift is a common phenomenon appearing in evolving data streams of a wide range of applications including credit card fraud protection, weather forecast, network monitoring, etc. For online data streams it is difficult to determine a proper size of the sliding window for detection of concept drift, making the existing dataset-distance based algorithms not effective in application. In this paper, we propose a novel framework of Density-based Concept Drift Detection (DCDD) for detecting concept drifts in data streams using density-based clustering on a variable-size sliding window through dynamically adjusting the size of the sliding window. Our DCDD uses XGBoost (eXtreme Gradient Boosting) to predict the amount of data in the same concept and adjusts the size of the sliding window dynamically based on the collected information about concept drifting. To detect concept drift between two datasets, DCDD calculates the distance between the datasets using a new detection formula that considers the attribute of time as the weight for old data and calculates the distance between the data in the current sliding window and all data in the current concept rather than between two adjacent windows as used in the exiting work DCDA [2]. This yields an observable improvement on the detection accuracy and a significant improvement on the detection efficiency. Experimental results have shown that our framework detects the concept drift more accurately and efficiently than the existing work. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Data mining

来源：评论

学校读者我要写书评

暂无评论

A Bandwidth Prediction Method Based on Hybrid LSTM for Content Delivery Network 7

A Bandwidth Prediction Method Based on Hybrid LSTM for Conte...

引用

7th IEEE International Conference on Smart Cloud, SmartCloud 2022

作者： Wang, Xinyu Du, Xin Li, WenLi Lu, Zhihui Fudan University School of Science Computer Shanghai China Educational Technology and Information Center Shenzhen Polytechnic Shenzhen China

ISBN: (数字)9781665451796

ISBN: (纸本)9781665451796

Content Delivery Network (CDN) can store workflow content by deploying edge service nodes and realizing network optimization with reasonable scheduling strategies. Manual selection of appropriate service clusters is coupled with low timeliness and a high economic burden. Therefore, the timing prediction of bandwidth remains a persistent demand to choose service clusters that can take on a safe workload. In this study, we proposes a model which can predict the load level in the future period to optimize the content delivery network. This model uses a machine learning method (K-means) for data optimization, which discarded 3114 of 185572 pieces of data that impact subsequent prediction models. Afterward, the model uses a 4-layers Long Short-Term Memory Network(LSTM) to predict the aggregated temporal data. The model named BK-LSTM considers the execution time and accuracy, eventually learning the real-time bandwidth demand pattern of 654 servers in the specific cluster. Experiments show that our BK-LSTM model has a mean absolute percentage error(MAPE) metric of about 15.2% on the test set, demonstrating this model's ability to predict bandwidth workload well. © 2022 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Point-MSD: Jointly Mamba Self-Supervised Self-Distilling Point Cloud Representation Learning

Point-MSD: Jointly Mamba Self-Supervised Self-Distilling Poi...

引用

International Conference on Signal Processing Proceedings (ICSP)

作者： Linzhi Su Mengna Yang Jie Liu Xingxing Hao Chenyang Zhang Xin Cao School of Information Science and Technology Northwest University Shaanxi China College of Computer and Information Engineering Henan Normal University Henan China

ISBN: (数字)9798350387384

ISBN: (纸本)9798350387391

Self-supervised tasks, which extract supervisory signals from the data without human labeling, have garnered significant attention. Mask modeling, in particular, has piqued interest. To leverage unlabeled point data in self-supervised learning, we introduce a self-distilling architecture that integrates mask modeling to enhance the model's ability to extract representations and strengthen its high-level semantic feature learning on two versions of a point cloud. Recognizing that point coordinate embeddings can lead to information disclosure distinct from images and text, we incorporate mask embedding into the decoder of an encoder-decoder structure to mitigate this issue and ensure the model's learning is not overly simplistic. These backbones are typically based on CNNs or Transformers, which have limitations in local receptive field and global modeling, respectively. Drawing inspiration from Mamba, which originates from a state space model with global modeling capabilities and linear complexity, we propose a novel approach called Jointly Mamba Self-Supervised Self-Distilling Point Cloud Representation Learning (Point-MSD). Additionally, we introduce a global semantic consistency loss to enrich the overall shape understanding of 3D objects. Extensive experiments demonstrate that our method can learn superior point cloud representations. Notably, Point-MSD achieves a 93.52% accuracy on ModelNet40, outperforming PointMamba by 0.93%.

关键词： Point cloud compression Representation learning Three-dimensional displays Shape Semantics Transformers Feature extraction Data models Robustness Data mining

来源：评论

学校读者我要写书评

暂无评论

Multi-domain feature fusion for target color decoding from multichannel neural recordings of pigeons

Multi-domain feature fusion for target color decoding from m...

引用

2023 International Conference on Image, Signal Processing, and Pattern Recognition, ISPP 2023

作者： Li, Hongxun Liu, Ruiqing Niu, Xiaoke Wang, Zhizhong Henan Key Laboratory of Brain Science and Brain-Computer Interface Technology School of Electrical Engineering Zhengzhou University Zhengzhou450001 China Department of Mechanical and Electrical Engineering Henan Light Industry Vocational College Zhengzhou450000 China

ISBN: (纸本)9781510666351

The entopallium is a high-level neural structure of the avian visual system that is related to the processing of color- and shape-related information during target recognition. The mechanism underlying it remains unclear and has drawn a considerable amount of research interest. Decoding has invariably been used in relevant studies to verify whether the extracted response-related features contain visual information. However, local field potentials (LFPs) often contain rich features. In this study, We combine the features of different domains to decode color information, including those in the time and frequency domains as well as features related to non-linear and functional network connectivity. To extract valuable response-related features, three types of feature selection methods are compared. The LFP data from the entopallium of a pigeon were recorded during periods of stimulus presentation in which two colors were randomly presented in each trial. The selected feature set was finally used to decode the colors by using several general classifiers. The results showed that the fusion of multi-domain features helped improve decoding performance, and the optimal feature set was a fusion of multiple domains of features. These results improve our understanding of the avian neural mechanisms involved in encoding color-related information. © 2023 SPIE.

关键词： Color

来源：评论

学校读者我要写书评

暂无评论

Achieving Noise Suppression of Multichannel Lock-In Amplifier Based on Signal Segmentation

引用

IEEE Transactions on Instrumentation and Measurement 2025年 74卷

作者： Xu, Kun Shi, Jin Chai, Di Ai, Jiangshan Wang, Li Li, Peng Henan University of Technology College of Electrical Engineering Zhengzhou450001 China University of Electronic Science and Technology of China School of Automation Engineering Chengdu611731 China Henan University of Technology Center for Complexity Science Zhengzhou450001 China Chengdu University of Information Technology College of Computer Science and Technology Chengdu610225 China

This study proposes a multichannel signal-segmented lock-in amplifier (LIA) for suppressing co-frequency noise and processing signals containing local anomalies. Signal-segmented LIAs can counteract the interference caused by co-frequency noise in different signal segments, preventing the superimposition of co-frequency noise at different times in the input signal, which ultimately reduces its impact on the output. A module for detecting localized anomalous signals was incorporated into the LIA, enhancing its anti-interference capability. Through simulation, the mean square error (MSE) of the outputs from the signal-segmented LIA and the conventional software-implemented LIA (SILIA) were compared, validating the effectiveness of signal segmentation. Furthermore, an eddy current magneto-optic (ECMO) nondestructive testing (NDT) system with signal-segmented LIA was developed for detecting defects in weakly conductive materials carbon fiber-reinforced polymer (CFRP). Comprehensive experiments demonstrated that the signal-segmented LIA significantly suppressed co-frequency noise interference in its output compared to the traditional SILIA and exhibited superior anti-interference to localized anomalous signals. These results further validate the efficacy of the signal segmentation approach. © 1963-2012 IEEE.

关键词： Multiuser detection

来源：评论

学校读者我要写书评

暂无评论

FLMP: Optimizing Training Efficiency of Federated Learning Using Model Pruning with Layer Selection

FLMP: Optimizing Training Efficiency of Federated Learning U...

引用

Information science, Parallel and Distributed Systems (ISPDS), International Conference on

作者： Yuhang Zhou Yangguang Cui Wenfen Shen Weiting Hu School of Computer Engineering and Science Shanghai University Shanghai China School of Computer and Information Technology Shanghai Polytechnic University Shanghai China

ISBN: (数字)9798350352719

ISBN: (纸本)9798350352726

Federated Learning (FL) has emerged as a privacy-preserving method for distributed clients to collaboratively train a model without exposing their raw data. However, the limited communication bandwidth and insufficient computing capacity of clients hinder the efficient deployment of FL applications. Besides, the diverse data distribution among clients may also degrade model performance. To address the aforementioned issues, we propose a novel framework called FLMP. Specifically, our FLMP dynamically identifies and eliminates redundant components within models by analyzing representation similarity and filter importance based on clients' data. This process produces multiple optimal sub-models that are tailored to client capacities. Comprehensive experiments demonstrate that, Compared with other baselines, our proposed framework achieves better performance in both i.i.d and challenging non-i.i.d data scenarios. It achieves up to a 12.31% improvement in model accuracy while maintaining similar communication and computation costs.

关键词： Training Information science Accuracy Federated learning Computational modeling Termination of employment Distributed databases

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：