检索结果-内蒙古大学图书馆

An optimized multi-scale convolutional autoencoder for efficient abnormal event detection using rgb, depth and optical flow data

引用

Multimedia Tools and Applications 2025年 1-35页

作者： Alqahtani, Abdullah Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University KSA Al-Kharj Saudi Arabia

In this study, we propose a novel framework for detecting abnormal events in surveillance videos, a critical yet challenging task in security applications. This research introduces a robust and efficient solution for video anomaly detection, offering substantial improvements in surveillance systems' ability to detect abnormal events, thereby contributing to enhanced security measures in public spaces. The proposed framework utilizes a Multiscale Convolutional Autoencoder (MSCAE) that processes inputs from RGB, depth, and optical flow video clips, enhancing the detection accuracy in complex scenes characterized by varying object scales, aspect ratios, and occlusions. To address the challenge of noise and preserve edges in video data, we implement a two-pass bilateral smooth filtering method, which is effective for noise-invariant, edge-preserving image smoothing. For object detection within these complex scenes, an enhanced Faster R-CNN model is employed. This model's performance is further refined through transfer learning on a dataset specifically composed of abnormal event videos. We also introduce significant improvements to the region proposal network (RPN) of the Faster R-CNN, particularly in non-maximum suppression (NMS) and anchor generation techniques, to better detect anomalies in diverse and complex environments. Furthermore, the MSCAE is integrated with Long Short-Term Memory (LSTM) neural networks to classify the detected anomalies, creating an end-to-end solution for video anomaly detection. Hyperparameter optimization for our deep learning models is performed using the Chameleon Swarm Algorithm, ensuring optimal model performance. Our framework was rigorously tested on the CUHK Avenue dataset, where it achieved a remarkable 99.5% accuracy, significantly outperforming existing methods and demonstrating the effectiveness of our approach. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2025.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Ensemble of deep learning techniques to human activity recognition using smart phone signals

引用

Multimedia Tools and Applications 2024年第42期83卷 89635-89664页

作者： Imanzadeh, Soodabeh Tanha, Jafar Jalili, Mahdi Electrical and Computer Engineering Department University of Tabriz Tabriz Iran School of Engineering RMIT University Melbourne Australia

Human Activity Recognition (HAR) has become a significant area of study in the fields of health, human behavior analysis, the Internet of Things, and human–machine interaction in recent years. Smartphones are a popular choice for HAR as they are common devices used in daily life. However, most available HAR datasets are gathered in laboratory settings, which do not reflect real-world scenarios. To address this issue, a real-world dataset using smartphone inertial sensors, involving 62 individuals, is collected. The collected dataset is noisy, small, and has variable frequency. On the other hand, in the context of HAR, algorithms face additional challenges due to intra-class diversity (which refers to differences in the characteristics of performing an activity by different people or by the same individual under different conditions) and inter-class similarity (which refers to different activities that are highly similar). Consequently, it is essential to extract features accurately from the dataset. Ensemble learning, which combines multiple models, is an effective approach to improve generalization performance. In this paper, a weighted ensemble of hybrid deep models for HAR using smartphone sensors is proposed. The proposed ensemble approach demonstrates superior performance compared to current methods, achieving impressive results across multiple evaluation metrics. Specifically, the experimental analysis demonstrates an accuracy of 97.15%, precision of 96.41%, recall of 95.62%, and an F1-score of 96.01%. These results demonstrate the effectiveness of our ensemble approach in addressing the challenges of HAR in real-world scenarios. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

DGeC: Dynamically and Globally Enhanced Convolution

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2025年第4期6卷 921-933页

作者： Zhang, Zihang Liu, Yuling Zhou, Zhili Yang, Gaobo Liao, Xin Wu, Q. M. Jonathan Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Guangzhou University Institute of Artificial Intelligence and Blockchain Guangzhou510006 China University of Windsor Department of Electrical and Computer Engineering WindsorON250101 Canada

We explore the reasons for the poorer feature extraction ability of vanilla convolution and discover that there mainly exist three key factors that restrict its representation capability, i.e., regular sampling, static aggregation, and limited receptive field. With the cost of extra parameters and computations, existing approaches merely alleviate part of the limitations. It drives us to seek a more lightweight operator to further improve the extracted image features. Through a closer examination of the convolution process, we discover that it is composed of two distinct interactions: spatial-wise interaction and channel-wise interaction. Based on this discovery, we decouple the convolutional blocks into these two interactions which not only reduces the parameters and computations but also enables a richer ensemble of interactions. Then, we propose the dynamically and globally enhanced convolution (DGeC), which includes several components as follows: a dynamic area perceptor block (DAP) that dynamically samples spatial cues, an adaptive global context block (AGC) that introduces the location-aware global image information, and a channel attention perceptor block (CAP) that merges different channel-wise features. The experiments on ImageNet for image classification and on COCO-2017 for object detection validate the effectiveness of DGeC. As a result, our proposed method consistently improves the performance with fewer parameters and computations. In particular, DGeC achieves a 3.1% improvement in top-1 accuracy on ImageNet dataset compared to ResNet50. Moreover, with Faster RCNN and RetinaNet, our DGeC-ResNet50 also consistently outperforms ResNet and ResNeXt. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

AI-Based Automatic System for Assessing Upper-Limb Spasticity of Patients With Stroke Through Voluntary Movement

引用

IEEE Journal of Biomedical and Health Informatics 2024年第2期28卷 742-752页

作者： Lee, I-Jung Hu, Yu Hen Hsiao, Pei-Chi Yang, Shu-Yu Lin, Hsin-Te Chen, Yu-Chung Lin, Bor-Shing National Taipei University College of Electrical Engineering and Computer Science New Taipei City237303 Taiwan University of Wisconsin-Madison Department of Electrical and Computer Engineering MadisonWI53706 United States Chi-Mei Medical Center Department of Physical Medicine and Rehabilitation Tainan71004 Taiwan Chi Mei Hospital Department of Physical Medicine and Rehabilitation Tainan73657 Taiwan National Taipei University Department of Computer Science and Information Engineering New Taipei City237303 Taiwan

Spasticity is a common complication for patients with stroke, but only few studies investigate the relation between spasticity and voluntary movement. This study proposed a novel automatic system for assessing the severity of spasticity (SS) of four upper-limb joints, including the elbow, wrist, thumb, and fingers, through voluntary movements. A wearable system which combined 19 inertial measurement units and a pressure ball was proposed to collect the kinematic and force information when the participants perform four tasks, namely cone stacking (CS), fast flexion and extension (FFE), slow ball squeezing (SBS), and fast ball squeezing (FBS). Several time and frequency domain features were extracted from the collected data, and two feature selection approaches based on recursive feature elimination were adopted to select the most influential features. The selected features were input into five machine learning techniques for assessing the SS for each joint. The results indicated that using CS task to assess the SS of elbow and fingers and using FBS task to assess the SS of thumb and wrist can reach the highest weighted-average F1-score. Furthermore, the study also concluded that FBS is the optimal task for assessing all the four upper-limb joints. The overall result shown that the proposed automatic system can assess four upper-limb joints through voluntary movements accurately, which is a breakthrough of finding the relation between spasticity and voluntary movement. © 2013 IEEE.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Jamming Attack Mitigation in Wireless Federated Learning Networks Using Bayesian Games

IEEE Networking Letters

引用

IEEE Networking Letters 2024年第4期6卷 247-251页

作者： Barkatsa, Sofia Diamanti, Maria Charatsaris, Panagiotis Tsiropoulou, Eirini Eleni Papavassiliou, Symeon Institute of Communication and Computer Systems School of Electrical and Computer Engineering National Technical University of Athens Zografou15780 Greece University of New Mexico Department of Electrical and Computer Engineering AlbuquerqueNM87131 United States

Federated Learning (FL), an emerging distributed Artificial Intelligence (AI) technique, is susceptible to jamming attacks during the wireless transmission of trained models. In this letter, we introduce a jamming attack mitigation mechanism for the uplink of wireless FL networks using the power-domain Non-Orthogonal Multiple Access (NOMA) technique. The problem of transmission power allocation for all clients (legitimate and malicious) is formulated and solved distributively as a Bayesian game with incomplete information. The clients aim to successfully transmit their model parameters, minimizing transmission time and consumed power, while having probabilistic knowledge about the malicious behavior of the other clients in the game. © 2019 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing MIMO-OFDM Communication Systems: A Comparative Analysis of LMMSE and LZF Equalizers under Varying Antenna Configurations

Optimizing MIMO-OFDM Communication Systems: A Comparative An...

引用

2024 Cognitive Models and Artificial Intelligence Conference, AICCONF 2024

作者： Al-Aanbagi, Sarah Koyuncu, Hakan Altinbas University Electrical and Computer Engineering Department Turkey Computer Engineering Department Altinbas university Turkey

ISBN: (纸本)9798400716928

Orthogonal Frequency Division Multiplexing (OFDM) has emerged as a fundamental modulation technique in modern broadband wireless communication systems, effectively addressing challenges arising from dispersive channels and random fading phenomena. By employing orthogonal subcarrier frequencies, OFDM enables the simultaneous transmission of multiple in-formation symbols, thereby mitigating Inter-Symbol Interference (ISI) often encountered in scenarios characterized by multi-path propagation. In contrast to traditional Frequency Division Multiplexing (FDM) methods, OFDM eliminates the need for guard bands between adjacent frequency bands, thereby improving spectral efficiency for high-speed data transmission. This paper conducts an extensive analysis of Zero Forcing (ZF) and Minimum Mean Squared Error (MMSE) equalizers in wireless Multi-Input Multi-Output (MIMO) systems employing BPSK, QPSK, and 16-PSK modulations. Lever-aging MATLAB-based simulations, diverse configurations involving multiple transmit and receive antennas are explored, yielding insightful findings concerning output Signal-to-Noise Ratio (SNR) and Bit Error Rate (BER). Our study underscores the efficacy of OFDM-MIMO systems with equalizers in enhancing communication performance across a spectrum of wireless scenarios, offering valuable insights for both theoretical exploration and practical implementation. © 2024 ACM.

关键词： Orthogonal frequency division multiplexing

来源：评论

学校读者我要写书评

暂无评论

A New Method for Stealthy False Data Injection Attack Detection Using Advanced Feasibility Areas Considering Spatial Distribution

引用

IEEE Transactions on Smart Grid 2025年第4期16卷 3346-3358页

作者： Elsayed, Ahmed Abd Elaziz Khani, Hadi Farag, Hany E. Z. Department Lassonde School of Engineering Engineering and Computer Science York University Toronto ON Canada

The Feasibility Area (FA) in power system applications defines the region within which Power System State Variables (PSSVs) typically exist under normal operating conditions. Accurate characterization of the FA helps enhancing optimal power flow, detecting anomalies, and identifying stealthy False Data Injection Attacks (FDIAs). Traditional FA-based approaches assess the location of PSSVs based on discrete time instances, using a binary flag to indicate whether the PSSVs lie inside or outside the FA. This paper introduces an advanced FA-based stealthy FDIAs detection method that improves upon this by incorporating the spatial distribution of PSSVs relative to the estimated FA. Unlike conventional methods, the advanced FA incorporates spatial distribution to evaluate the proximity of the current PSSV to the expected FA in the complex plane. A sigmoid-expansion flag is employed to represent the probability of the current PSSVs belonging to the expected FA, replacing the conventional binary flag. This sigmoid-expansion flag is then used as an input to a Deep Neural Network (DNN), where both the sigmoid-expansion flag and DNN model parameters are fine-tuned during training to ensure optimal compatibility, thereby improving detection accuracy. The proposed method significantly improves the detection of stealthy FDIAs, offering superior performance over traditional FA. Additionally, it enables the extraction of key attack characteristics, such as type, nature, and magnitude, further strengthening the system’s defense capabilities. © 2010-2012 IEEE.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

An Analog Front-End for EEG Data Retrieval with High Noise Rejection 15

An Analog Front-End for EEG Data Retrieval with High Noise R...

引用

15th International Conference on Information, Intelligence, Systems and Applications, IISA 2024

作者： Retsinas, Konstantinos Tsipianitis, Dimitrios Souliotis, George University of the Peloponnese Department of Electrical and Computer Engineering Patras Greece University of Patras Department of Electrical and Computer Engineering Patras Greece

ISBN: (纸本)9798350368833

Electroencephalography is a technique used to evaluate and record the brain's electrical activity. It is used mostly for medical purposes, to identify various brain disorders like epilepsy, tumors, and others, but recently it has been used for developing more sophisticated sensors in everyday life. In this paper, an analog front-end circuit for electroencephalography acquisition systems with skin electrodes is proposed. Designed with simple components the circuit achieves a high gain of the electroencephalograph signals with high rejection of environmental electro-interference. Measurement results show a common mode rejection at 50 Hz is better than 33 dB and at 100Hz better than 24 dB. The overall sensitivity is ±1 u Vp-p and the output range is about ±200m Vp-p. The circuit is suitable to be used for driving analog to digital converters or other platforms for post-processing of the electroencephalograph signals. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

SEOE:an option graph based semantically embedding method for prenatal depression detection

引用

Frontiers of computer science 2024年第6期18卷 245-258页

作者： Xiaosong HAN Mengchen CAO Dong XU Xiaoyue FENG Yanchun LIANG Xiaoduo LANG Renchu GUAN College of Computer Science and Technology Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of EducationJilin UniversityChangchun 130012China Department of Electrical Engineering and Computer Science and Christopher S.Bond Life Sciences Center University of MissouriColumbiaMO 65211USA Department of Computer Science and Technology Zhuhai Laboratory of Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of EducationZhuhai College of Science and TechnologyZhuhai 519041China Jilin Provincial Institute of Population Science and Technology Changchun 130000China

Prenatal depression,which can affect pregnant women’s physical and psychological health and cause postpartum depression,is increasing ***,it is essential to detect prenatal depression early and conduct an attribution *** studies have used questionnaires to screen for prenatal depression,but the existing methods lack *** diagnose the early signs of prenatal depression and identify the key factors that may lead to prenatal depression from questionnaires,we present the semantically enhanced option embedding(SEOE)model to represent questionnaire *** can quantitatively determine the relationship and patterns between options and *** first quantifies options and resorts them,gathering options with little difference,since Word2Vec is highly dependent on *** resort task is transformed into an optimization problem involving the traveling salesman ***,all questionnaire samples are used to train the options’vector using ***,an LSTM and GRU fused model incorporating the cycle learning rate is constructed to detect whether a pregnant woman is suffering from *** verify the model,we compare it with other deep learning and traditional machine learning *** experiment results show that our proposed model can accurately identify pregnant women with depression and reach an F1 score of *** most relevant factors of depression found by SEOE are also verified in the *** addition,our model is of low computational complexity and strong generalization,which can be widely applied to other questionnaire analyses of psychiatric disorders.

关键词： questionnaire analyses text classification graph representation learning traveling salesman problem prenatal depression

来源：评论

学校读者我要写书评

暂无评论

Stackelberg Game Based Performance Optimization in Digital Twin Assisted Federated Learning over NOMA Networks 100

Stackelberg Game Based Performance Optimization in Digital T...

引用

100th IEEE Vehicular Technology Conference, VTC 2024-Fall

作者： Wu, Bibo Fang, Fang Zeng, Ming Wang, Xianbin Western University Department of Electrical and Computer Engineering London Canada Western University Department of Computer Science London Canada Laval University Department of Electric and Computer Engineering Quebec City Canada

ISBN: (纸本)9798331517786

Despite its advantage of preserving data privacy, federated learning (FL) could suffer from the limited computation resources of the distributed clients particularly when they are connected by wireless networks. By imitating the distributed resources effectively, digital twin (DT) shows great potential in eliminating the straggler issue in FL. In this paper, we leverage DT in the FL framework over non-orthogonal multiple access (NOMA) network, where DT deployed at the server can assist FL training process. To minimize the total latency and energy consumption in the proposed system, we formulate a Stackelberg game by considering clients and the server as the leader and the follower, respectively. Specifically, the leader aims to minimize the energy consumption via the optimization of DT mapping data ratio and resource allocation, while the objective of the follower is to minimize the total latency during FL training by optimally allocating DT computation resource. The Stackelberg equilibrium is considered to obtain the optimal solutions. We first derive the closed-form solution for the follower-level problem and include it in the leader-level problem which is then solved through the deep reinforcement learning (DRL) method. Simulation results verify the superior performance of the proposed scheme. © 2024 IEEE.

关键词： Federated learning

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：