检索结果-内蒙古大学图书馆

CapsNet-FR: Capsule Networks for Improved Recognition of Facial Features

computers, Materials & Continua 2024年第5期79卷 2169-2186页

作者： Mahmood Ul Haq Muhammad Athar Javed Sethi Najib Ben Aoun Ala Saleh Alluhaidan Sadique Ahmad Zahid farid Department of Computer System Engineering University of Engineering&TechnologyPeshawar25000Pakistan College of Computer Science and Information Technology Al-Baha UniversityAlaqiq65779-7738Saudi Arabia REGIM-Lab:Research Groups in Intelligent Machines National School of Engineers of Sfax(ENIS)University of SfaxSfax3038Tunisia Department of Information Systems College of Computer and Information SciencesPrincess Nourah bint Abdulrahman UniversityRiyadh84428Saudi Arabia EIAS:Data Science and Blockchain Laboratory College of Computer and Information SciencesPrince Sultan UniversityRiyadh11586Saudi Arabia Department of Computer Sciences Bahria University Karachi CampusKarachi541004Pakistan Department of Electrical Engineering Abasyn UniversityPeshawar25000Pakistan

Face recognition (FR) technology has numerous applications in artificial intelligence including biometrics, security,authentication, law enforcement, and surveillance. Deep learning (DL) models, notably convolutional neuralnetworks (CNNs), have shown promising results in the field of FR. However CNNs are easily fooled since theydo not encode position and orientation correlations between features. Hinton et al. envisioned Capsule Networksas a more robust design capable of retaining pose information and spatial correlations to recognize objects morelike the brain does. Lower-level capsules hold 8-dimensional vectors of attributes like position, hue, texture, andso on, which are routed to higher-level capsules via a new routing by agreement algorithm. This provides capsulenetworks with viewpoint invariance, which has previously evaded CNNs. This research presents a FR model basedon capsule networks that was tested using the LFW dataset, COMSATS face dataset, and own acquired photos usingcameras measuring 128 × 128 pixels, 40 × 40 pixels, and 30 × 30 pixels. The trained model outperforms state-ofthe-art algorithms, achieving 95.82% test accuracy and performing well on unseen faces that have been blurred orrotated. Additionally, the suggested model outperformed the recently released approaches on the COMSATS facedataset, achieving a high accuracy of 92.47%. Based on the results of this research as well as previous results, capsulenetworks perform better than deeper CNNs on unobserved altered data because of their special equivarianceproperties.

关键词： CapsNet face recognition artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Improved YOLOv5s for Object Detection 1

Improved YOLOv5s for Object Detection

引用

1st International Conference on Engineering and Advanced Technology, ICEEAT 2023

作者： Krolkral, Narimane Wafaa Mohamed Faraoun, Kamel Bousahba, Nassima Rezzouk, Belkacem Hamouda, Ikram Ait Djillali Liabes University Eedis Laboratory Sidi Bel Abbes Computer Science Department Hassiba Benbouali University Chlef Algeria Hassiba Benbouali University Sidi Bel Abbes Computer Science Department Chlef Algeria Djillali Liabes University Eedis Laboratory Computer Science Department Sidi Bel Abbes Algeria Hassiba Benbouali University Computer Science Department Chlef Algeria

ISBN: (纸本)9798350383485

The utilization of deep learning technology for object detection offers the notable benefit of attaining high levels of accuracy. The level of accuracy attained is contingent upon the duration of processing time required by the deep learning technology. The algorithm for object detection is commonly referred to as You Only Look Once (YOLO). This study presents a novel object detection algorithm utilizing the Yolov5 framework, coupled with a substantial dataset. The improvement of YOLOv5 commenced with the incorporation of the Spatial Pyramid Pooling Fast module (SPPF) into the yolov5s neck network to extract multiple scale image features. Then, the depth of the backbone SPPF module has been raised from 1024 to 2048 to improve accuracy. The modified YOLOV5 model was utilized for object detection, resulting in the extraction of object information categorized into seven distinct classes. The achieved results include a mean average precision (mAP) of 0.821 at an intersection over union (IoU) threshold of 0.5, and a mAP of 0.386 within the IoU range of 0.5 to 0.95, with a precision value of 0.761. Additionally, a recall value of 0.769 was obtained. The application of our research framework has demonstrated its effectiveness in enhancing the performance of object detection algorithms. © 2023 IEEE.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Ultra-low power MoS2 optoelectronic synapse with wavelength sensitivity for color target recognition

引用

science China(Information sciences) 2025年第4期68卷 187-196页

作者： Bo WEI Yabo CHEN Xiaotong HAN Yan KANG Bujia LIANG Cheng LI Xiaokuo YANG Liang FANG Yuanxi PENG Institute for Quantum Information & State Key Laboratory of High Performance Computing College of ComputerNational University of Defense Technology Fundamentals Department Air Force Engineering University College of Advanced Interdisciplinary Studies National University of Defense Technology Institute of Quantum Information Science and Technology College of ScienceNational University of Defense Technology College of Computer National University of Defense Technology

Optoelectronic synapses that integrate visual perception and pre-processing hold significant potential for neuromorphic vision systems（NVSs）. However, due to a lack of wavelength sensitivity, existing NVS mainly focuses on gray-scale image processing, making it challenging to recognize color images. Additionally, the high power consumption of optoelectronic synapses, compared to the 10 fJ energy consumption of biological synapses, limits their broader application. To address these challenges, an energy-efficient NVS capable of color target recognition in a noisy environment was developed,utilizing a MoS2optoelectronic synapse with wavelength sensitivity. Benefiting from the distinct photon capture capabilities of 450, 535, and 650 nm light, the optoelectronic synapse exhibits wavelength-dependent synaptic plasticity, including excitatory postsynaptic current（EPSC）, paired-pulse facilitation（PPF）, and long-term plasticity（LTP）. These properties can effectively mimic the visual memory and color discrimination functions of the human vision system. Results demonstrate that the NVS, based on MoS2optoelectronic synapses, can eliminate the color noise at the sensor level, increasing color image recognition accuracy from 50% to 90%. Importantly, the optoelectronic synapse operates at a low voltage spike of0.0005 V, consuming only 0.075 fJ per spike, surpassing the energy efficiency of both existing optoelectronic and biological synapses. This ultra-low power, color-sensitive device eliminates the need for color filters and offers great promise for future deployment in filter-free NVS.

关键词： optoelectronic synapse neuromorphic vision system color recognition 2D materials image pre-processing

来源：评论

学校读者我要写书评

暂无评论

An Opposition-Based Learning Archerfish Hunting Optimizer for Global Optimization 6

An Opposition-Based Learning Archerfish Hunting Optimizer fo...

引用

6th International Conference on Advanced Aspects of Software Engineering, ICAASE 2024

作者： Ferhat, Aridj Zitouni, Farouq Limanc, Abdelhadi Lakbichi, Rihab Harous, Saad Department of Computer Science and Information Technology Laboratory of Artificial Intelligence and Information Technology Kasdi Merbah University Ouargla Algeria College of Computing and Informatics Department of Computer Science University of Sharjah Sharjah United Arab Emirates

ISBN: (纸本)9798331522810

This paper introduces OBL-AHO, an enhanced Archerfish Hunting Optimizer (AHO) variant that integrates Opposition-Based Learning (OBL) to improve AHO's exploratory capabilities. By leveraging opposite solutions alongside newly generated ones, OBL-AHO broadens the search space, effectively reducing the risk of local optima entrapment-A common challenge in metaheuristic algorithms. The performance of OBL-AHO is rigorously compared with the original AHO and several prominent Metaheuristic Algorithms (MAs), including TLBO (Teaching-Learning-Based Optimization), PSO (Particle Swarm Optimization), GWO (Grey Wolf Optimizer), OOBO (OnE-To-One Based Optimizer), SSA (Salp Swarm Algorithm). Evaluations were conducted using test functions taken from CEC 2022, and the outcomes were statistically analyzed using the Friedman test. The findings demonstrate that OBL-AHO significantly improves exploration while maintaining competitive exploitation relative to its opponents. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Four Metaheuristic Algorithms for Estimating Parameters in Solar Photovoltaic Models 6

Comparative Analysis of Four Metaheuristic Algorithms for Es...

引用

6th International Conference on Advanced Aspects of Software Engineering, ICAASE 2024

作者： Lakbichi, Rihab Zitouni, Farouq Limane, Abdelhadi Ferhat, Aridj Harous, Saad Department of Computer Science and Information Technology Laboratory of Artificial Intelligence and Information Technology Kasdi Merbah University Ouargla Algeria College of Computing and Informatics University of Sharjah Department of Computer Science Sharjah United Arab Emirates

ISBN: (纸本)9798331522810

In the last decade, Metaheuristic Algorithms (MAs) have been widely employed to estimate parameters in photovoltaic (PV) models to maximize solar energy efficiency. This paper presents a comparative study of the performance of four novel and efficient MAs applied to solve the parameter extraction problem in three ubiquitous PV models: The Single-Diode Model (SDM), the Double-Diode Model (DDM), and the Photovoltaic Module Model (PMM). The primary objective of this study is to evaluate and compare the efficiency of these MAs and identify the most effective one based on the Root Mean Square Error (RMSE) between the simulated and the actual data. This work compares the performance of the Red-Tailed Hawk Optimizer (RTH), the One-To-One Based Optimizer (OOBO), the Sand Cat Swarm Optimization (SCSO), and the Archerfish Hunting Optimizer (AHO). The numerical results demonstrate that RTH significantly outperforms its counterparts in estimating parameters for the examined models. This exceptional performance underscores RTH's efficiency and effectiveness as a powerful tool for parameter estimation in PV models. Given these promising results, RTH stands out as a preferred method and holds the potential for further refinement and enhancement in the future. © 2024 IEEE.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Data secure transmission intelligent prediction algorithm for mobile industrial IoT networks

引用

Digital Communications and Networks 2023年第2期9卷 400-410页

作者： Lingwei Xu Hao Yin Hong Jia Wenzhong Lin Xinpeng Zhou Yong Fu Xu Yu Department of Information Science and Technology Qingdao University of Science and TechnologyQingdao266061China Fujian Key Laboratory of Sensing and Computing for Smart Cities Xiamen UniversityXiamen361005China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control(Minjiang University) Fuzhou350121China Faculty of Information Science and Engineering Ocean University of ChinaQingdao266100China Shandong Provincial Key Laboratory of Computer Networks Shandong Computer Science Center(National Supercomputer Center in Jinan)JinanChina

Mobile Industrial Internet of Things(IIoT)applications have achieved the explosive growth in recent *** mobile IIoT has flourished and become the backbone of the industry,laying a solid foundation for the interconnection of all *** variety of application scenarios has brought serious challenges to mobile IIoT networks,which face complex and changeable communication *** data secure transmission is critical for mobile IIoT *** paper investigates the data secure transmission performance prediction of mobile IIoT *** cut down computational complexity,we propose a data secure transmission scheme employing Transmit Antenna Selection(TAS).The novel secrecy performance expressions are first ***,to realize real-time secrecy analysis,we design an improved Convolutional Neural Network(CNN)model,and propose an intelligent data secure transmission performance prediction *** mobile signals,the important features may be removed by the pooling *** will lead to negative effects on the secrecy performance prediction.A novel nine-layer improved CNN model is *** of the input and output layers,it removes the pooling layer and contains six convolution ***,Back-Propagation(BP)and LeNet methods are employed to compare with the proposed *** simulation analysis,good prediction accuracy is achieved by the CNN *** prediction accuracy obtains a 59%increase.

关键词： Mobile IIoT networks Data secure transmission Performance analysis Intelligent prediction Improved CNN

来源：评论

学校读者我要写书评

暂无评论

Optimizing Wireless Sensor Network Lifespan Through Weighted Fitness Function in K-Means Clustering and Cluster Head Selection 8

Optimizing Wireless Sensor Network Lifespan Through Weighted...

引用

8th International Symposium on Multidisciplinary Studies and Innovative Technologies, ISMSIT 2024

作者： Fatima, Harrouz Mohammed, Kaddi Mohammed, Omari University of Adrar Lddi Laboratory Mathematics and Computer Science Department Adrar Algeria School of Engineering American University of Ras Al Khaimah Computer Science and Engineering Department Ras Al Khaimah United Arab Emirates

ISBN: (纸本)9798350354423

One of the primary challenges in Wireless Sensor Networks (WSNs) is the efficient management of energy con sumption and maintaining robust network connectivity over time. To address this issue, we propose a model that initially employs k-means clustering to form clusters and subsequently selects cluster heads in each round based on three critical factors: remaining energy, distance to the base station, and distance to the cluster center. By leveraging k-means clustering at the beginning, optimal cluster formation is achieved, ensuring balanced initial energy distribution. In subsequent rounds, dynamic selection of cluster heads is performed using weighted weights for each parameter to enhance network performance. Various weight values were tested to determine the most effective configuration. Our approach effectively balances energy consumption among nodes, extends network lifetime, and maintains strong connectivity, thereby addressing key challenges in the deployment and operation of WSNs. © 2024 IEEE.

关键词： K-means clustering

来源：评论

学校读者我要写书评

暂无评论

Real-Time Human Action Representation Based on 2D Skeleton Joints 6

Real-Time Human Action Representation Based on 2D Skeleton J...

引用

6th International Conference on Networking and Advanced Systems, ICNAS 2023

作者： Adil, Bouguerra Mounine, Hemam Sofiane Ouassila, Hioual Abbes Laghrour University ICOSI Laboratory of Khenchela Department of Mathematics and Computer Science Khenchela Algeria Abbes Laghrour University LIRE Laboratory of Constantine 2 Department of Mathematics and Computer Science Khenchela Algeria

ISBN: (纸本)9798350319170

We present a new approach to capture human actions by using 2D skeletal joints as the foundation for the real-time representation. Our approach combines three distinct types of information, namely: (1) motion detection to identify salient regions within the action. This allows us to compute joint contribution ratios and save processing time by excluding still joints and focusing on the main joints involved in the action;(2) utilization of a predefined map for joints trajectory shapes, which encodes the temporal information and avoids noisy data using the map;and (3) incorporation of a direction map that captures the movement of the joints, in the spatial space. By integrating these elements, we have devised a comprehensive representation capable of discerning even highly similar actions. To evaluate the effectiveness of our proposed representation, we conducted experiments on the UTD-MHAD dataset [25], which encompasses a diverse range of 27 actions performed by 8 subjects (4 females and 4 males), each with 4 repetitions. The evaluation results exhibit a notable dissimilarity within the same action category (intra-class) and a significant similarity across different action categories (inter-class). Specifically, our approach achieved a commendable score of 94.81 on the UTD-MHAD dataset, thus demonstrating its efficacy and robustness. © 2023 IEEE.

关键词： Musculoskeletal system

来源：评论

学校读者我要写书评

暂无评论

Impact Machine Learning Classification And Technical Indicators Forecast The Direction Of Bitcoin 14

Impact Machine Learning Classification And Technical Indicat...

引用

14th International Conference on Intelligent Systems: Theories and Applications, SITA 2023

作者： El Badaoui, Mohamed Raouyane, Brahim El Moumen, Samira Bellafkih, Mostafa Faculty of Sciences*Ain Chock N&idp Team Department of Mathematics and Computer Science Morocco Department of Mathematics and Computer Science Raiss Laboratory Rabat Morocco

ISBN: (纸本)9798350308211

This study assesses the effectiveness of machine learning (ML) models in predicting fluctuations in the direction of Bitcoin prices using conventional technical indicators. Given the volatile nature of Bitcoin markets, achieving precise predictions is of utmost importance. The study improves machine learning models including logistic regression (LR), decision trees (DT), random forests (RF), support vector machines (SVM), Xgboost, and artificial neural networks (ANN) by integrating established technical indicators. By employing Optuna for hyperparameter optimization and the 'Time Series Split' technique for cross-validation, the study optimizes the models for time series data. The results demonstrate that ML models, when integrated with technical indicators, significantly outperform predictions based solely on those indicators. Evaluation metrics include accuracy, recall, and the F1 score. Through the incorporation of signal indicators, ML models offer a robust approach to predicting changes in Bitcoin prices. The proposed ML approach achieves a test accuracy exceeding 65.15%, highlighting the potential synergy between traditional financial prediction tools and contemporary technology. This study underscores the potential effectiveness of combining ML models with technical indicators for forecasting Bitcoin price movements. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Clustering in Wireless Sensor Networks Using Fuzzy Logic for Clusterhead Election: Review 1

引用

8th International Conference on Information System Design and Intelligent Applications, ISDIA 2024

作者： Harrouz, Fatima Omari, Mohammed Kaddi, Mohammed LDDI Laboratory Mathematics and Computer Science Department University of Adrar Adrar Algeria Computer Science and Engineering Department School of Engineering American University of Ras Al Khaimah Ras Al-Khaimah United Arab Emirates

ISBN: (数字)9789819786664

ISBN: (纸本)9789819786657

Wireless sensor networks refer to a collection of sensors strategically deployed in specific areas for purposes such as environmental monitoring, surveillance, military applications, and various other uses. These sensor nodes are responsible for detecting information and transmitting it to a central base station. The sensors are generally battery operated and cannot be rechargeable. Since monitoring and data transmission processes consume a significant amount of energy, achieving energy efficiency is a primary concern. Therefore, clustering has become the most popular approach to improving energy efficiency. This approach consists of dividing the network into clusters, each characterized by a cluster head sensor and several member sensors. The cluster head assumes the responsibility of collecting data from member sensors within its cluster, aggregating this data and then transmitting it to the central base station. The central aspect of this clustering approach lies in the selection of the optimal cluster head, as it significantly influences the performance and lifetime of the network. To address this challenge, various protocols have been introduced using fuzzy logic, which has become one of the most widely used methodologies in this context due to its ability to handle uncertain and ambiguous inputs, closely mimicking human reasoning processes. This survey paper aims to provide a comprehensive overview of clustering techniques that use fuzzy logic for selection of cluster heads, using a range of inputs such as residual energy levels, distance to node receiver, network density, and other relevant criteria. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Sensor nodes

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：