检索结果-内蒙古大学图书馆

Evolutionary Computing Empowered Community detection in Attributed Networks

IEEE COMMUNICATIONS MAGAZINE 2024年第5期62卷 22-26页

作者： Guo, Kun Chen, Zhanhong Yu, Zhiyong Chen, Kai Guo, Wenzhong Fuzhou Univ Coll Comp & Data Sci Fuzhou Peoples R China Fuzhou Univ Engn Res Ctr Big Data Intelligence Minist Educ China Fuzhou Peoples R China Fuzhou Univ Fujian Key Lab Network Comp & Intelligent Informat Fuzhou Peoples R China Hong Kong Univ Sci & Technol Dept Comp Sci & Engn Hong Kong Peoples R China

Discovering communities in attributed networks is an important research topic in complex network analysis. Community detection based on multi-objective evolutionary computing (MOEA) models community detection as a multi-objective optimization problem and searches the optimal solutions by simulating the evolution of a biological population. However, the existing multi-objective evolutionary algorithms for community detection faces two challenges: their encoding schemes are designed based on network topology and neglects the information in node attributes;and they are easy to fall into local optimum. In this article, we propose a community detection algorithm empowered by multi-objective evolutionary computing, named ECEVO-MOEA, which conducts edge closeness encoding and embedding vector optimization alternately. On the one hand, the evolution of a biological population is completed by employing a new edge closeness encoding scheme and multiple attribute-aware objective functions. On the other hand, the update of embedding vectors is used to calculate similarity matrix and communities to improve solution quality, avoiding it from early convergence. Experiments on real networks demonstrate that ECEVO-MOEA achieves higher accuracy than the baseline algorithms.

关键词： Evolutionary computation Encoding Statistics Social factors Image edge detection Search problems Pareto optimization Complex networks detection algorithms Community networks

来源：评论

学校读者我要写书评

暂无评论

Toward Early detection of Depression: Detecting Depression Symptoms in Arabic Tweets Using Pretrained Transformers

引用

IEEE ACCESS 2024年 12卷 88134-88145页

作者： Elmajali, Suzan Ahmad, Irfan King Fahd Univ Petr & Minerals Dept Informat & Comp Sci Dhahran 31261 Saudi Arabia KFUPM SDAIA KFUPM Joint Res Ctr Artificial Intelligence Dhahran 31261 Saudi Arabia

The COVID-19 pandemic and its associated setbacks have significantly impacted human mental health. Depression of various intensities has resulted due to a wide variety of losses that people have experienced. However, unlike physical illness, mental illness is still underestimated by patients themselves and by society due to various factors, such as the societal stigma of visiting a psychotherapist and being diagnosed with a mental health disorder. On the other hand, general practitioners can recognize signs of depression using the Patient Health Questionnaire (PHQ-9), which is used as a screening test for depression. The PHQ-9 questionnaire comprises nine questions that correspond to the nine symptoms of depression outlined in the Diagnostic and Statistical Manual of Mental Disorders, Fifth Edition (DSM-5). In this paper, we aim to detect the nine depression symptoms stated by DSM-5 from Arabic tweets, as recognizing the type of depression symptom is crucial in diagnosing depression. We used AraBERT and MARBERT pretrained transformers to classify tweets with depression symptoms. We also performed data augmentation using ChatGPT to balance the training set. The model was applied to a dataset consisting of 1,290 samples labeled with nine different symptoms, in addition to a 'normal' class which was also generated using ChatGPT. This work used four performance metrics to evaluate the models' performance, which are accuracy, precision, recall, and F1 scores. The AraBERT and MARBERT transformers have yielded promising results, achieving accuracy, precision, recall, and F1 scores of 99.3%, 99.1%, 98.8%, and 98.9%, respectively, using the AraBERT transformer. While using the MARBERT transformer achieved accuracy, recall, precision, and F1 scores of 98.3%, 97.9%, 98.2%, and 98%, respectively.

关键词： Depression Accuracy Transformers Mental health Social networking (online) Chatbots Task analysis Natural language processing detection algorithms Text categorization Arabic tweets depression detection model finetuning text classification transformer models

来源：评论

学校读者我要写书评

暂无评论

Automatic detection of Abnormal Drone Flight State by Measuring Changes in Images Captured by a Drone-Mounted Camera

引用

IEEE AEROSPACE AND ELECTRONIC SYSTEMS MAGAZINE 2024年第3期39卷 4-14页

作者： Premachandra, Chinthaka Ichikawa, Shintaro Shibaura Inst Technol Grad Sch Engn & Sci Dept Elect Engn Tokyo 1358548 Japan

While in flight, drones can be adversely affected by strong gusts of wind. Currently, drones are equipped with hardware such as accelerometers and speed sensors to mitigate these effects. However, these measures may be inadequate, and intense disturbances can lead to crashes. For instance, a remotely piloted drone blown off course by wind may become uncontrollable, and any delay in correcting its trajectory could result in an accident. Therefore, in this study, we analyze images captured by cameras mounted on drones during autonomous flight to detect unusual movements. This enables the control center to promptly address anomalies, independent of the already equipped internal sensors for anomaly detection, thus enhancing the rapid detection of flight anomalies. Additionally, it acts as a system backup in case these equipped sensors for anomaly detection become nonfunctional. In this article, we assess the drone's speed and direction by analyzing changes in successive images taken by the onboard camera. Based on these assessments, we determine the normalcy of the flight state. For this, we introduce a novel method for detecting abnormal flight conditions, utilizing the observed variations in speed and direction. Extensive experimental testing demonstrates the effectiveness of our proposed method in identifying abnormal flight conditions during drone operations.

关键词： Drones Cameras Sensor systems Trajectory Accidents Mathematical models detection algorithms Object detection Current measurement Anomaly detection Accelerometers Vehicle crash testing Autonomous robots UAV abnormal flight detection inter-frame differencing on-drone camera exponentially weighted moving average

来源：评论

学校读者我要写书评

暂无评论

PFW-YOLO Lightweight Helmet detection Algorithm

引用

IEEE ACCESS 2025年 13卷 70752-70759页

作者： Hong, Yue Wang, Hao Guo, Shuo Shenyang Univ Chem Technol Coll Informat Engn Shenyang 110020 Peoples R China

Helmet recognition, as an important means to ensure personnel safety in high-risk operating environments, requires the deployment of recognition models to edge-end devices to achieve real-time and portability. However, due to the limited arithmetic and storage resources of edge-end devices, and the traditional detection algorithms have problems such as the number of parameters and large computational volume, the detection algorithms are difficult to be deployed practically. Therefore, a lightweight helmet detection algorithm PFW YOLO is proposed in this paper. Firstly, a multi-scale feature fusion module is designed to reconstruct the Bottleneck structure in C2f, which finally forms the C2f-PMSFF module to enhance the feature expression ability of the model and optimize the computational efficiency. Second, in order to further reduce the size of the model while ensuring the detection accuracy, Feature Interaction Shared detection Head (FISH) is introduced. Finally, Wise-Inner-Shape-IoU is used to optimize the bounding box regression loss function, which is used to enhance the detection accuracy and accelerate the convergence speed. The final experimental results indicate that, compared to the original YOLOv8n algorithm, the PFW-YOLO algorithm achieves a 53% reduction in parameters, a 42% decrease in computational effort, and a 51% reduction in model size, while enhancing the mean average precision (mAP) by 0.4%.

关键词： Feature extraction Accuracy Safety Head Computational modeling detection algorithms Convolution Computational efficiency Fish YOLO Helmet detection YOLOv8 light weight loss function

来源：评论

学校读者我要写书评

暂无评论

A study on compare pitch detection algorithms

A study on compare pitch detection algorithms

引用

IEEE Signal Processing and Communications Applications (SIU)

作者： Cansu Kadı Seda Gökhüseyin Yard.Doç.Umut Arıöz Bilgisayar Mühendisliği Bölümü Gazi Üniversitesi Ankara Türkiye

In this paper, three algorithms were choosen by reviewing the literature about pitch detection and implemented on the Matlab environment. Runtimes and error rates of these algorithms were compared with each other. These algorithms are Harmonic Product Spectrum (HPS), Cepstral Pitch Tespit (CPD) and Autocorrelation Method. the observed results showed that the fastest algorithm is CPD and the slowest algorithm is HPS. The least error was achieved at 44.1 kHz sample rate for all algorithms. HPS algorithm become more successful with %99 success ratio in noiseless environment.

关键词： detection algorithms Cepstrum Speech Speech processing Speech recognition Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Two-Stage detection of Incident-Induced Congestion at the Cycle and Movement Levels on Signalized Urban Roads Using Spatially Sparse Trajectory Data

引用

IEEE TRANSACTIONS ON INTELLIGENT TRANSPORTATION SYSTEMS 2025年第6期26卷 8297-8307页

作者： Sun, Yuxuan Yu, Chunhui Wang, Ling Su, Zicheng Ma, Wanjing Tongji Univ Key Lab Rd & Traff Engn Minist Educ Shanghai 201804 Peoples R China

Accurate and timely detection of incident-induced congestion (IIC) is essential for mitigating its negative impact on traffic efficiency. Existing studies on IIC detection mainly focus on traffic flow on freeways and face challenges on urban roads due to the impacts of signal lights at intersections and diverse road networks. Additionally, the low penetration rate of probe vehicle trajectories poses another challenge. This study proposes a probe-vehicle-trajectory-based algorithm for IIC detection on urban roads at the movement and cycle levels. Two critical features (i.e., the average speed and the entrance time into the road segment) are defined to capture the characteristics of trajectory segments. A Vehicle Trajectory Polar Coordinate Transformation (VTPCT) method is proposed to differentiate anomalous trajectory segments (ATS) affected by IIC from normal ones, considering the periodicity of fixed signal timing at the intersections. Anomaly rates calculated from the identified ATS within a spatiotemporal window are introduced to reflect the movement-cycle-level traffic states. A two-stage algorithm framework is designed to enhance the algorithm's adaptability to spatially sparse trajectories and diverse road networks. Experimental studies show that the proposed algorithm is applicable to trajectory data with low penetration rates and outperforms benchmarks of typical statistical and AI-based algorithms.

关键词： Roads Trajectory Classification algorithms Clustering algorithms Traffic control detection algorithms Prediction algorithms Heuristic algorithms Detectors Feature extraction Incident-induced congestion detection signalized urban road vehicle trajectory data density-based clustering decision tree

来源：评论

学校读者我要写书评

暂无评论

THE EMBEDDABILITY OF LANE detection algorithms ON HETEROGENEOUS ARCHITECTURES

THE EMBEDDABILITY OF LANE DETECTION ALGORITHMS ON HETEROGENE...

引用

IEEE International Conference on Image Processing

作者： Romain Saussard Boubker Bouzid Marius Vasiliu Roger Reynaud Renault S.A.S. Institut d'Electronique Fondamentale - Universite Paris Sud

ISBN: (纸本)9781479983407

Lane detection plays a crucial role for Advanced Driver Assitance System (ADAS) or autonomous driving applications. Literature shows a lot of lane detection algorithms can work in real time with good results. However, they require much computer processing and cannot be embedded in a vehicle ECU without deep software optimizations. In this paper, we discuss the embeddability of lane detection algorithms by comparing state-of-the-art algorithms in terms of functional performance and computational timing. We identify what essential parts of lane detection are time consuming, and show these parts can be computed in real time on embedded systems.

关键词： ADAS Lane detection Embedded Processing advanced driver assistance systems (ADAS) detection algorithms Lanes COMPUTER PROCESSING ARCHITECTURE functional performance Embedded systems

来源：评论

学校读者我要写书评

暂无评论

Using Explainable AI for Neural Network-Based Network Attack detection

引用

COMPUTER 2024年第5期57卷 78-85页

作者： Zou, Qingtian Zhang, Lan Sun, Xiaoyan Singhal, Anoop Liu, Peng Penn State Univ State Coll PA 16803 USA No Arizona Univ Flagstaff AZ 86011 USA Worcester Polytech Inst Dept Comp Sci Worcester MA 01609 USA NIST Comp Secur Div Gaithersburg MD 20899 USA Penn State Univ CyberSecur State Coll PA 16803 USA Penn State Univ Cyber Secur Lab State Coll PA 16803 USA

Neural network (NN)-based network intrusion detection systems (NIDSs) are becoming popular these days due to their notable advantages. This article reviews the current application of explainable artificial intelligenc... 详细信息

关键词： Neural Networks Explainable AI Cyberattack Network Security Intrusion detection detection algorithms Artificial Intelligence Neural Network Explainable Machine Learning Network Attacks Deep Learning Decision Making Process Support Vector Machine Random Forest Decision Tree Second Category First Category Denial Of Service Local Translation Domain Name Neural Network Output Intrusion detection System S Hapley Additive Ex Planations Security Analysts Convolutional Neural Network Classification Results Shapley Value Benign Samples Traditional Machine Learning Techniques Root Node AI Models Neural Network Prediction Subset Of Samples Major Path Class Distribution

来源：评论

学校读者我要写书评

暂无评论

Comparing Community detection algorithms on Neuroimaging Data from Multiple Subjects

Comparing Community Detection Algorithms on Neuroimaging Dat...

引用

International IEEE Conference on Signal-Image Technologies and Internet-Based System

作者： Joshua De Souza Fumihiko Taya Nitish V. Thakor Anastasios Bezerianos Singapore Institute Neurotechnology National University of Singapore Singapore SG Singapore Institute Neurotechnology National University of Singapore Singapore

It is well-known that the brain is a complex network""brain areas dedicated to different functions. As such,""consisting of""it is natural to shift toward brain network from brain mapping for deeper understanding of brain functions. Although graph theoretical network metrics measuring global or local properties of network topology have been used to investigate the brain network, they do no provide any information about intermediate scale of the brain network, which is provided by the community structure analysis.""In this paper, we propose a method to compare different community detection algorithms for multiple subjects data in terms of the agreement of a group-based community structure with individual community structures. As it is crucial to find a single group-based community structure for a group of subjects to discuss about brain areas and connections, a number of algorithms based on different approaches have been proposed. To show the feasibility of the method for comparing different algorithms, two community detection algorithms based on different approaches ("virtual-typical-subject" and "group analysis") were examined. The Normalized Mutual Information was computed to measure similarity between the group-based community structure and individual community structures derived from resting-state fMRI functional network, and was used for comparing the two algorithms. Our method demonstrated that the algorithm based on the group-analysis approach detected a group-based community structure with greater agreement with individual community structures.

关键词： detection algorithms Brain Neuroimaging Correlation Periodic structures Mutual information Indexes

来源：评论

学校读者我要写书评

暂无评论

Evaluation and Implementation of Optimal Classification algorithms for Credit Card Fraud detection

Evaluation and Implementation of Optimal Classification Algo...

引用

International Conference on Computational and Characterization Techniques in Engineering & Sciences (CCTES)

作者： Sampath Kini K Pushpakumar. R R. Senthamil Selvan Praveenkumar G D Basi Reddy. A Department of Computer Science and Engineering Nitte Deemed To be University Karkala India Department of Information Technology Vel Tech Rangarajan Dr .Sangunthala R&D Institute of Science and Technology Avadi India Department of Electronics and Communication Engineering Annamacharya Institute of Technology and Sciences Tirupati India Department of Computer Technology Kongu Engineering College Erode India Department of Computer Science and Engineering School of Computing Mohan Babu University Tirupati India

ISBN: (数字)9798350364699

ISBN: (纸本)9798350364705

Nowadays, the credit card industry is more concerned about credit card fraud than any other problem. The main idea is to examine optional techniques used for fraud detection and to identify the different types of credit card fraud. Numerous strategies exist for lowering the prevalence of credit card fraud, each tailored to the specific threats faced by banks and the credit card industry. Credit card fraud prevention is the primary goal of implementing these measures. Existing methods have several unresolved issues that cause legitimate credit card customers to be mistakenly labelled as fraudulent. The amount of fraud in the financial sphere may be inferred from this paper's emphasis on integrating the best classification algorithm out of four distinct methods.

关键词： Industries Privacy Costs Prevention and mitigation Logic gates Credit cards Fraud Classification algorithms Data mining detection algorithms

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：