检索结果-内蒙古大学图书馆

Deep Learning Based Face Detection and Identification of Criminal Suspects

computers, Materials & Continua 2023年第2期74卷 2331-2343页

作者： S.Sandhya A.Balasundaram Ayesha Shaik School of Computer Science and Engineering Vellore Institute of Technology(VIT)Chennai600127India School of Computer Science and Engineering Center for Cyber Physical SystemsVellore Institute of Technology(VIT)Chennai600127India

Occurrence of crimes has been on the constant rise despite the emerging discoveries and advancements in the technological field in the past *** of the most tedious tasks is to track a suspect once a crime is *** most of the crimes are committed by individuals who have a history of felonies,it is essential for a monitoring system that does not just detect the person’s face who has committed the crime,but also their ***,a smart criminal detection and identification system that makes use of the OpenCV Deep Neural Network(DNN)model which employs a Single Shot Multibox Detector for detection of face and an auto-encoder model in which the encoder part is used for matching the captured facial images with the criminals has been *** detection and extraction of the face in the image by face cropping,the captured face is then compared with the images in the *** comparison is performed by calculating the similarity value between each pair of images that are obtained by using the Cosine Similarity *** plotting the values in a graph to find the threshold value,we conclude that the confidence rate of the encoder model is 0.75 and above.

关键词： Deep learning opencv deep neural network single shot multi-box detector auto-encoder cosine similarity

来源：评论

学校读者我要写书评

暂无评论

supported by the National Natural science Foundation of China(Nos.62172051,61772085,and 61877005)and Jiangsu Agriculture science and Technology Innovation Fund(***(18)3054).

引用

Tsinghua science and Technology 2023年第1期28卷 82-92页

作者： Jinghui Zhang Yuchen Wang Tianyu Huang Fang Dong Wei Zhao Dian Shen School of Computer Science and Engineering Southeast UniversityNanjing 211189China Hefei Comprehensive National Science Center Hefei 231299China School of Computer Science and Technology Anhui University of TechnologyHefei 230026China Department of Computer Science&Engineering The Chinese University of Hong KongHong Kong 999077China

Numerous neural network(NN)applications are now being deployed to mobile *** applications usually have large amounts of calculation and data while requiring low inference latency,which poses challenges to the computing ability of mobile ***,devices’life and performance depend on ***,in many scenarios,such as industrial production and automotive systems,where the environmental temperatures are usually high,it is important to control devices’temperatures to maintain steady *** this paper,we propose a thermal-aware channel-wise heterogeneous NN inference *** contains two parts,the thermal-aware dynamic frequency(TADF)algorithm and the heterogeneous-processor single-layer workload distribution(HSWD)*** on a mobile device’s architecture characteristics and environmental temperature,TADF can adjust the appropriate running speed of the central processing unit and graphics processing unit,and then the workload of each layer in the NN model is distributed by HSWD in line with each processor’s running speed and the characteristics of the layers as well as heterogeneous *** experimental results,where representative NNs and mobile devices were used,show that the proposed method can considerably improve the speed of the on-device inference by 21%–43%over the traditional inference method.

关键词： neural network inference mobile device temperature adjustment channel-wise parallelization

来源：评论

学校读者我要写书评

暂无评论

Design of an Automatic Price Tag System for Web-Based Retail Business 9

Design of an Automatic Price Tag System for Web-Based Retail...

引用

9th International Conference on Information Management and Technology, ICIMTech 2024

作者： Liawatimena, Suryadiputra Gunawan, Devina Bina Nusantara University Automotive & Robotics Program Computer Engineering Department BINUS ASO School of Engineering Computer Science Deparment BINUS Graduate Program Master of Computer Science Jakarta11480 Indonesia Bina Nusantara University Automotive & Robotics Program Computer Engineering Department BINUS ASO School of Engineering Jakarta11480 Indonesia

ISBN: (纸本)9798350390025

Modern retail businesses face a significant challenge with the inefficiency of manually changing price labels on shelves. This manual process not only consumes valuable time and resources but also increases the likelihood of errors, leading to potential inaccuracies in pricing and a less streamlined shopping experience for customers. The proposed solution is the implementation of an Electronic Shelf Label (ESL) system that automatically displays the prices of goods on retail business shelves. This system connects a website (front end and back end) to e-paper via a Wi-Fi network and microcontroller, allowing retail business owners to update prices more easily. Additionally, buyers can search for desired items through the website. The results are the time to send data from the website to the e-paper, namely, to know the performance of the e-paper used. The average time required from 10 attempts to send data from the website to the e-paper is 20.935 seconds. Since the data is connected to the server and will be updated automatically, using this system will be more efficient than manually changing the price label, although it takes time to transfer data from the website to the e-paper. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

RE-SEGNN:recurrent semantic evidence-aware graph neural network for temporal knowledge graph forecasting

引用

science China(Information sciences) 2025年第2期68卷 103-119页

作者： Wenyu CAI Mengfan LI Xuanhua SHI Yuanxin FAN Quntao ZHU Hai JIN National Engineering Research Center for Big Data Technology and System Services Computing Technology and System LabCluster and Grid Computing LabSchool of Computer Science and TechnologyHuazhong University of Science and Technology

Temporal knowledge graph(TKG) reasoning, has seen widespread use for modeling real-world events, particularly in extrapolation settings. Nevertheless, most previous studies are embedded models, which require both entity and relation embedding to make predictions, ignoring the semantic correlations among different entities and relations within the same timestamp. This can lead to random and nonsensical predictions when unseen entities or relations occur. Furthermore, many existing models exhibit limitations in handling highly correlated historical facts with extensive temporal depth. They often either overlook such facts or overly accentuate the relationships between recurring past occurrences and their current counterparts. Due to the dynamic nature of TKG, effectively capturing the evolving semantics between different timestamps can be *** address these shortcomings, we propose the recurrent semantic evidenceaware graph neural network(RE-SEGNN), a novel graph neural network that can learn the semantics of entities and relations simultaneously. For the former challenge, our model can predict a possible answer to missing quadruples based on semantics when facing unseen entities or relations. For the latter problem, based on an obvious established force, both the recency and frequency of semantic history tend to confer a higher reference value for the current. We use the Hawkes process to compute the semantic trend, which allows the semantics of recent facts to gain more attention than those of distant facts. Experimental results show that RE-SEGNN outperforms all SOTA models in entity prediction on 6 widely used datasets, and 5 datasets in relation prediction. Furthermore, the case study shows how our model can deal with unseen entities and relations.

关键词： knowledge graph reasoning temporal knowledge graph Hawkes process semantic evidence

来源：评论

学校读者我要写书评

暂无评论

Hardware and Software Integration of Machine Learning Vision System Based on NVIDIA Jetson Nano 1

引用

Future of Information and Communication Conference, FICC 2024

作者： Manolescu, Denis Reid, David Secco, Emanuele Lindo Robotics Lab School of Mathematics Computer Science and Engineering Liverpool Hope University Liverpool United Kingdom

ISBN: (数字)9783031540530

ISBN: (纸本)9783031540523

This study investigates the capabilities and flexibility of edge devices for real-time data processing near the source. A configurable Nvidia Jetson Nano system is used to deploy nine pre-trained computer vision models, demonstrating proficiency in local data processing, analysis and providing real-time feedback. Additionally, the system offers deployment control via a customized Graphical User Interface (GUI) and proves very low-latency inference re-stream to other local devices using the G-Streamer framework. The Machine Learning models which cover a wide range of applications, including image classification, object recognition or detection, depth estimation and semantic segmentation, show potential for IoT and industrial applications. Further, the fusion of these capabilities with AI and machine learning algorithms unveils a promising perspective for substantial industrial redevelopment. This research underscores the strategic significance of edge devices in modern computational frameworks and their potential role in future technological advancements. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Multi-Dimensional Training Optimization for Efficient Federated Synergy Learning

引用

IEEE Transactions on Mobile Computing 2025年第7期24卷 6243-6258页

作者： Fu, Shucun Dong, Fang Chen, Runze Shen, Dian Zhang, Jinghui He, Qiang Southeast University School of Computer Science and Engineering Nanjing China 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 Wuhan China

Edge learning (EL) is an end-to-edge collaborative learning paradigm enabling devices to participate in model training and data analysis, opening countless opportunities for edge intelligence. As a promising EL framework, federated synergy learning (FSyL) mitigates the computation and communication overhead on resource-constrained devices by offloading partial model layers to the edge server for synergistic training. Nevertheless, due to the system and statistical heterogeneity, naively using existing FSyL methods is significantly time-consuming and causes accuracy degradation. Motivated by this issue, this paper introduces a novel FSyL framework that integrates multi-dimensional training optimization and formulates the edge learning cost minimization (ELCM) problem. To tackle the ELCM efficiently, we design OL-MG, an OnLine Model Splitting and Resource Provisioning Game. Specifically, we first reformulate and decompose the original ELCM based on data quality evaluation. Then, given a model splitting decision, we determine the optimal resource provisioning in Sub-problem1, based on which optimal model splitting in Sub-problem2 is modeled as a potential game. Subsequently, we introduce a decentralized algorithm to find a Nash equilibrium (NE) solution. Furthermore, we further extend OL-MG to support a budget-aware multi-edge scenario. Extensive experiments demonstrate that the proposed mechanism significantly outperforms state-of-the-art methods in cost-saving and accuracy improvement. © 2025 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Flexible servo riveting system control strategy based on the RBF network and self-pierce riveting process

引用

Advances in Manufacturing 2023年第1期11卷 39-55页

作者： Yan Liu Qiu Tang Xin-Cheng Tian Long Cui Center for Robotics School of Control Science and EngineeringShandong UniversityJinan250061People’s Republic of China Engineering Research Center of Intelligent Unmanned System Ministry of EducationJinan250061People’s Republic of China

As more and more composite materials are used in lightweight vehicle white bodies,self-pierce riveting(SPR)technology has attracted great ***,the existing riveting tools still have the disadvantages of low efficiency and *** improve these disadvantages and the riveting qualification rate,this paper improves the control scheme of the existing riveting tools,and proposes a novel controller design approach of the flexible servo riveting system based on the RBF network and SPR ***,this paper briefly introduces the working principle and SPR procedure of the servo riveting *** a moving component force analysis is performed,which lays the foundation for the motion ***,the riveting quality inspection rules of traditional riveting tools are used for reference to plan the force-displacement curve *** control this process,the riveting force is fed back into the closed-loop control of the riveting tool and the riveting speed is computed based on the admittance control ***,this paper adopts the permanent magnet synchronous motor(PMSM)as the power of riveting tool,and proposes an integral sliding mode control approach based on the improved reaching law and the radial basis function(RBF)network friction compensation for the PMSM speed ***,the proposed control approach is simulated by Matlab,and is applied to the servo riveting system designed by our *** simulation and riveting results show the feasibility of the designed controller.

关键词： Lightweight vehicle body connection Self-pierce riveting(SPR)process Flexible servo riveting tool Riveting force planning and control

来源：评论

学校读者我要写书评

暂无评论

Gaze Betray You: Abnormal Attention Detection from Human-Robot Interaction Dynamics

Gaze Betray You: Abnormal Attention Detection from Human-Rob...

引用

2024 IEEE International Conference on robotics and Biomimetics, ROBIO 2024

作者： Mu, Fengjun Zhang, Jingting Zou, Chaobin Huang, Zonghai Huang, Rui Cheng, Hong School of Automation Engineering University of Electronic Science and Technology of China Center for Robotics Chengdu China

ISBN: (纸本)9781665481090

Monitoring abnormal attention has a wide range of applications in Human-Robot Interaction systems, such as autonomous driving, virtual reality, and remote operation. Due to factors like fatigue, drowsiness, and distraction, human attention can deviate from tasks that require focus, resulting in abnormal attention during interactions. Monitoring for abnormal attention is essential to ensure the safety of human-robot interactions. However, existing methods often rely on un-explainable algorithms such as neural networks, making them difficult to trust in scenarios like autonomous driving, where explicit decision-making processes and mechanisms are required. This paper presents EyeAAD, an abnormal attention detection method based on dynamic system theory. This method uses gaze signals from a serious game designed to simulate human-robot interaction. We developed several attention-related features for interpretable modeling using a deterministic learning method. By analyzing the matching relationship between the gaze signal and the predicted status from the learned dynamic models, we can detect abnormal human attention patterns. To validate our approach, we designed a serious game for eye movement data acquisition in human-robot interaction. Our analysis showed that EyeAAD enables efficient, real-time monitoring of human attention. © 2024 IEEE.

关键词： Serious games

来源：评论

学校读者我要写书评

暂无评论

Towards High-Performance Graph Processing: From a Hardware/Software Co-Design Perspective

引用

Journal of computer science & Technology 2024年第2期39卷 245-266页

作者：廖小飞赵文举金海姚鹏程黄禹王庆刚赵进郑龙张宇邵志远 National Engineering Research Center for Big Data Technology and System School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China Services Computing Technology and System Laboratory School of Computer Science and Technology Huazhong University of Science and TechnologyWuhan 430074China Cluster and Grid Computing Laboratory School of Computer Science and TechnologyHuazhong University of Science and TechnologyWuhan 430074China Zhejiang Lab Hangzhou 311121China

Graph processing has been widely used in many scenarios,from scientific computing to artificial *** processing exhibits irregular computational parallelism and random memory accesses,unlike traditional ***,running graph processing workloads on conventional architectures(e.g.,CPUs and GPUs)often shows a significantly low compute-memory ratio with few performance benefits,which can be,in many cases,even slower than a specialized single-thread graph *** domain-specific hardware designs are essential for graph processing,it is still challenging to transform the hardware capability to performance boost without coupled software *** article presents a graph processing ecosystem from hardware to *** start by introducing a series of hardware accelerators as the foundation of this ***,the codesigned parallel graph systems and their distributed techniques are presented to support graph ***,we introduce our efforts on novel graph applications and hardware *** results show that various graph applications can be efficiently accelerated in this graph processing ecosystem.

关键词： graph processing hardware accelerator software system high performance ecosystem

来源：评论

学校读者我要写书评

暂无评论

LCGen: Mining in Low-Certainty Generation for View-consistent Text-to-3D 38

LCGen: Mining in Low-Certainty Generation for View-consisten...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Tao, Zeng Yang, Tong Lin, Junxiong Mai, Xinji Wang, Haoran Wang, Beining Zhou, Enyu Wang, Yan Zhang, Wenqiang Shanghai Engineering Research Center of AI & Robotics Academy for Engineering & Technology Fudan University Shanghai China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University Shanghai China School of Computer Science Fudan University Shanghai China Engineering Research Center of AI & Robotics Ministry of Education Academy for Engineering & Technology Fudan University Shanghai China

The Janus Problem is a common issue in SDS-based text-to-3D methods. Due to view encoding approach and 2D diffusion prior guidance, the 3D representation model tends to learn content with higher certainty from each perspective, leading to view inconsistency. In this work, we first model and analyze the problem, visualizing the specific causes of the Janus Problem, which are associated with discrete view encoding and shared priors in 2D lifting. Based on this, we further propose the LCGen method, which guides text-to-3D to obtain different priors with different certainty from various viewpoints, aiding in view-consistent generation. Experiments have proven that our LCGen method can be directly applied to different SDS-based text-to-3D methods, alleviating the Janus Problem without introducing additional information, increasing excessive training burden, or compromising the generation effect. Project page is [here]. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

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：