检索结果-内蒙古大学图书馆

3rd International Conference on Electronic information engineering and Data Processing, EIEDP 2024

作者： Zheng, Fengling Li, Wei Cui, Xiaohui Rajaboevich, G.S. School of Artificial Intelligence and Computer Science Jiangsu Key Laboratory of Media Design and Software Technology Jiangnan University Jiangsu China School of Cyber Science and Engineering Wuhan University Wuhan China Tashkent University of Information Technologies named after Muhammad al –Khwarizmi Yunusobod district 108 Amir Temur str Tashkent100202 Uzbekistan

ISBN: (纸本)9781510680531

The accelerometer signal is capable of providing crucial information regarding object motion, posture, and vibration. Therefore, it is of great significance to investigate noise suppression techniques for accelerometer signals. However, in complex industrial environments and under various equipment conditions, the noise generated exhibits a diverse nature, leading to suboptimal noise reduction outcomes when employing conventional denoising algorithms. This paper proposes a neural network model (AgentUNet) for denoising accelerometer signals. The network consists of a combination of UNet and Agent Attention, enhancing its ability to learn contextual information and achieve superior denoising performance. Additionally, instead of using clean signals as labeled data, we train the neural network using pairs of noisy data, thereby alleviating the challenge of collecting clean signals in industrial environments. Finally, we conduct experiments on experiment dataset. The experimental results indicate that AgentUNet achieves superior denoising performance compared to other baseline models. Furthermore, the denoising effectiveness of the neural network trained without using clean signals as labeled data is similar to that of the network trained using supervised learning methods. © 2024 SPIE.

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

Yolo Based License Plate Detection Of Triple Riders And Violators

Yolo Based License Plate Detection Of Triple Riders And Viol...

引用

International Conference on computer Communication and Informatics (ICCCI)

作者： R G Nandhakumar K. Nirmala Devi N. Krishnamoorthy S. Shanthi V R Pranesh S Nikhalyaa Department of Computer Science and Engineering Kongu Enginering College Perundurai Erode Tamilnadu India Department of Software Systems and Engineering School of Information and Engineering Vellore Institutte of Technology Vellore India

Road safety is of prime importance as road accidents are among the biggest causes of deaths in the country. Road Accidents are majorly due to violators and lawbreakers of road safety rules like not wearing helmets, triple riding etc. Even though there are many smart systems to monitor these violations, it is complicated to keep a track of the data and view it efficiently anywhere. Also monitoring the permit details of other state vehicles is hard. A method was proposed to address this issue. based on Deep learning and Optical Character Recognition (OCR). Here we detect the riders not wearing helmet and triple riders using object detection by comparing YOLOv2 and YOLOv3. This simplifies the task of traffic police who can’t continuously and efficiently monitor all the violators. We gathered our data from three different sources. Kaggle was used to collect the data set. A number of items can be recognized by the real-time object recognition system YOLO in a single frame. It recognizes object more precisely and faster than other recognition systems. It can predict up to 9000 classes and even unseen classes. It divides the image into m*m matrix and each grid detects objects within itself. The trained model is tested using a test dataset set after training in order to measure the performance. For Number plate detection we use OCR based character recognition. The recognized license plate images of violators are captured and stored in a database which is then sent to the concerned department. The stored data can be easily accessed using the developed mobile app. Metrics considered for evaluation is Accuracy. The average is utilized to assess object detection models like R-CNN and YOLO. The average calculates a score by comparing the detected box to the ground-truth bounding box. The better the score, the more precise the model’s detections are. When compared to YOLOv2, YOLOv3 exhibits strong performance in terms of accuracy with 95.5%. Keywords—Deep learning; Object detecti

关键词： Head Road accidents Databases Computational modeling Object detection Road safety Safety

来源：评论

学校读者我要写书评

暂无评论

PAM-4 optical transmission beyond 224 Gbps based on an ultrahigh-bandwidth slow-light silicon modulator

PAM-4 optical transmission beyond 224 Gbps based on an ultra...

引用

CLEO: Applications and Technology in CLEO 2024, CLEO: A and T 2024 - Part of Conference on Lasers and Electro-Optics

作者： Han, Changhao Qin, Jun Yang, Qipeng Zheng, Zhao Shu, Haowen Zhang, Yunhao Wu, Yichen Sun, Yu Lu, Junde Zhou, Yan Ge, Zhangfeng Wang, Lei He, Zhixue Yu, Shaohua Hu, Weiwei Peng, Chao Bowers, John E. Wang, Xingjun State Key Laboratory of Advanced Optical Communications System and Networks School of Electronics Peking University Beijing100871 China Department of Electrical and Computer Engineering University of California Santa BarbaraCA93106 United States Key Laboratory of Information and Communication Systems Ministry of Information Industry Beijing Information Science and Technology University Beijing100192 China Frontiers Science Center for Nano-optoelectronics Peking University Beijing100871 China Peng Cheng Laboratory Shenzhen518055 China Peking University Yangtze Delta Institute of Optoelectronics Nantong226010 China

We experimentally demonstrate PAM-4 optical transmission beyond 224 Gbps based on an ultrahigh-bandwidth slow-light silicon modulator in C-band with the combination of the artificial neural network equalizers. © ... 详细信息

关键词： Light modulators

来源：评论

学校读者我要写书评

暂无评论

Semantic Heads Segmentation and Counting in Crowded Retail Environment with Convolutional Neural Networks Using Top View Depth Images

引用

SN computer Science 2023年第1期4卷 61页

作者： Abed, Almustafa Akrout, Belhassen Amous, Ikram Department of Computer Science College of Computer Engineering and Sciences Prince Sattam Bin Abdulaziz University Alkharj 11942 Saudi Arabia Multimedia Information Systems and Advanced Computing Laboratory (MIRACL) Sfax University Sfax 3021 Tunisia ENET’COM University of Sfax National School of Electronics and Telecommunications of Sfax Road Tunis City El Ons Sfax 3018 Tunisia

In recent years, researchers have developed several techniques to accurately count the number of people in a crowded retail environment for human behavior analysis, ranging from vision and feature based approaches to machine-learning and deep learning approaches. Due to the availability and affordability of recent advanced technologies such as depth sensors and high computing powers as well as the availability of big data, the need for building accurate models to detect and count people in crowded environments arises. Deep learning approaches has proven to be highly accurate especially when there is enough data to train the model and high computation powers. People detection and counting is a challenging problem. due to several issues such as occlusion, light variations, complex backgrounds to name a few. To cope with these issues, we utilize a top-view configuration depth data to train our model. We propose a convolutional encoder decoder architecture consisting of a resnet50 encoder trained on the ImageNet dataset as a transfer learning technique and we built the decoder part of the model as a novel contribution, for segmenting and counting customers heads in a crowded retail stores where there are more than 6 individuals per square meter without compromising people privacy because the camera does not record people’s faces. The objective of our method is to segment and count people using the publicly available TV-Head Dataset and People Counting DataSet (PCDS). The results demonstrate that our model is robust and can be used for real time people counting with accurate results. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： computer vision Convolutional neural networks Intelligent retail environment People counting Top-view configuration

来源：评论

学校读者我要写书评

暂无评论

Optimizing Foundation Model Inference on a Many-Tiny-Core Open-Source RISC-V Platform

IEEE Transactions on Circuits and Systems for Artificial Int...

引用

IEEE Transactions on Circuits and systems for Artificial Intelligence 2024年第1期1卷 37-52页

作者： Viviane Potocnik Luca Colagrande Tim Fischer Luca Bertaccini Daniele Jahier Pagliari Alessio Burrello Luca Benini Integrated Systems Laboratory (IIS) of ETH Zürich ETZ Züurich Switzerland Department of Control and Computer Engineering Politecnico di Torino Turin Italy Department of Electrical Electronic and Information Engineering University of Bologna Bologna Italy

Transformer-based foundation models have become crucial for various domains, most notably natural language processing (NLP) or computer vision (CV). These models are predominantly deployed on high-performance GPUs or hardwired accelerators with highly customized, proprietary instruction sets. Until now, limited attention has been given to RISC-V-based general-purpose platforms. In our work, we present the first inference results of transformer models on an open-source many-tiny-core RISC-V platform implementing distributed Softmax primitives and leveraging ISA extensions for SIMD floating-point operand streaming and instruction repetition, as well as specialized DMA engines to minimize costly main memory accesses and to tolerate their latency. We focus on two foundational transformer topologies, encoder-only and decoder-only models. For encoder-only models, we demonstrate a speedup of up to 12.8 $\times$ between the most optimized implementation and the baseline version. We reach over 79% FPU utilization and 294 GFLOPS/W, outperforming State-of-the-Art (SoA) accelerators by more than 2 $\times$ utilizing the HW platform while achieving comparable throughput per computational unit. For decoder-only topologies, we achieve 16.1 $\times$ speedup in the Non-Autoregressive (NAR) mode and up to 35.6 $\times$ speedup in the Autoregressive (AR) mode compared to the baseline implementation. Compared to the best SoA dedicated accelerator, we achieve 2.04 $\times$ higher FPU utilization.

关键词： Frequency modulation Transformers computer architecture Computational modeling Kernel Artificial intelligence Hardware

来源：评论

学校读者我要写书评

暂无评论

Mitigating Phishing Attack in IoT based Healthcare System using a Threat Modeling Approach

Mitigating Phishing Attack in IoT based Healthcare System us...

引用

Advancement in Computation & computer Technologies (InCACCT), International Conference on

作者： Zineb Nadifi Mariyam Ouaissa Mariya Ouaissa Ali Kartit Keshav Kaushik Amitava Choudhury Laboratory of Information Technologies Chouaib Doukkali University El Jadida Morocco Computer Systems Engineering Laboratory Cadi Ayyad University Marrakech Morocco Sharda School of Computer Science & Engineering Sharda University Greater Noida India Department of Computer Science and Engineering School of Technology Pandit Deendayal Energy University Gandhinagar India

ISBN: (数字)9798331543891

ISBN: (纸本)9798331543907

The healthcare sector is a very sensitive area given the information that circulates within it, which makes hackers more inclined to target this architecture. Various techniques are available to ensure illegal intrusion, including phishing, an attack that is widely used by attackers as they take advantage of users' negligence or non-technical background to get them to provide initial access to the target architecture. This paper will discuss the threats that can affect an Internet of Things (IoT) architecture for healthcare domain, more specifically the phishing attack, using the STRIDE approach with the Microsoft Threat Modeling (MTM) tool, and then proposing countermeasures and recommendations for mitigating and correcting these threats, to guarantee correct and secure communication as far as possible.

关键词： Threat modeling computer hacking Phishing Prevention and mitigation Medical services computer architecture Security Internet of Things Monitoring

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Algorithms for Intrusion Detection Performance Evaluation and Comparative Analysis 4

Machine Learning Algorithms for Intrusion Detection Performa...

引用

4th International Conference on Smart Electronics and Communication, ICOSEC 2023

作者： Irfan, B. Md. Poornima, V. Mohana Kumar, S. Aswal, Upendra Singh Krishnamoorthy, N. Maranan, Ramya Nalsar University of Law Department of Information Technology Telengana Hyderabad500101 India VISTAS Pallavaram Department of Computer Science Chennai India Ramaiah Institute of Technology Department of Computer Science and Engineering Karnataka Bengaluru560054 India Graphic Era Deemed to Be University Department of Computer Science and Engineering Uttarakhand Dehradun248002 India Vellore Institute of Technology Vellore Campus Department of Software Systems and Engineering Tamilnadu Vellore632014 India Saveetha School of Engineering Simats Department of Research and Innovation Tamil Nadu Chennai600124 India

ISBN: (纸本)9798350300888

The security of computer networks is increasingly difficult to maintain due to the rising complexity and frequency of cyber-attacks. Important tools for finding and neutralizing these dangers are intrusion detection systems. This study sets out to do a thorough examination and comparison of the efficacy of several machine learning algorithms for use in intrusion detection. This research study evaluates the efficacy of several machine learning algorithms in correctly categorizing instances of network traffic as normal or invasive via extensive experiments performed on representative datasets. Algorithms like random forests, decision trees, SVMs, DL models and NNs are all being tested and rated. Effectiveness is measured and compared using a variety of performance indicators including accuracy, recall, precision, false positive rate, and F1-score. The results of this study emphasize the potential of deep learning models and Random Forests for use in intrusion detection and add to the body of knowledge around machine learning methods for this task. Professionals in the field of network security might use the results to their advantage when building intrusion detection systems. Future research areas are also mentioned, which will hopefully lead to even greater improvements in the field and safer, more reliable intrusion detection systems. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

PAM-4 optical transmission beyond 224 Gbps based on an ultrahigh-bandwidth slow-light silicon modulator

PAM-4 optical transmission beyond 224 Gbps based on an ultra...

引用

2024 Conference on Lasers and Electro-Optics, CLEO 2024

作者： Han, Changhao Qin, Jun Yang, Qipeng Zheng, Zhao Shu, Haowen Zhang, Yunhao Wu, Yichen Sun, Yu Lu, Junde Zhou, Yan Ge, Zhangfeng Wang, Lei He, Zhixue Yu, Shaohua Hu, Weiwei Peng, Chao Bowers, John E. Wang, Xingjun State Key Laboratory of Advanced Optical Communications System and Networks School of Electronics Peking University Beijing100871 China Department of Electrical and Computer Engineering University of California Santa BarbaraCA93106 United States Key Laboratory of Information and Communication Systems Ministry of Information Industry Beijing Information Science and Technology University Beijing100192 China Frontiers Science Center for Nano-Optoelectronics Peking University Beijing100871 China Peng Cheng Laboratory Shenzhen518055 China Peking University Yangtze Delta Institute of Optoelectronics Nantong226010 China

ISBN: (纸本)9781957171395

关键词： Silicon photonics

来源：评论

学校读者我要写书评

暂无评论

Blockchain-Based Multi-Cloud Data Storage System Disaster Recovery

Blockchain-Based Multi-Cloud Data Storage System Disaster Re...

引用

2023 IEEE International Conference on systems, Man, and Cybernetics, SMC 2023

作者： Wang, Feiyu Zhou, Jian-Tao College of Computer Science Inner Mongolia University Inner Mongolia Hohhot China Engineering Research Center of Ecological Big Data Ministry of Education Natl. Loc. Jt. Eng. Research Center of Intelligent Information Processing Technology for Mongolian Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing Inner Mongolia Engineering Laboratory for Big Data Analysis Technology China

ISBN: (纸本)9798350337020

Cloud storage services have been used by most businesses and individual users. However, data loss, service interruptions and cyber attacks often lead to cloud storage services not being provided properly, and these incidents have caused financial losses to users. Second, traditional and single-cloud model disaster recovery services are no longer suitable for the current complex cloud storage systems. Therefore, a scheme to provide disaster recovery for cloud storage services in a multi-cloud storage environment is needed in real production. In this paper, we propose a disaster recovery scheme based on blockchain technology. The proposed scheme outlined in this study aims to address the issue of data availability within the cloud storage landscape. The proposed scheme achieves this goal by dividing data into hot and cold categories, verifying the integrity of copy data via blockchain technology, and utilizing blockchain networks to manage multi-cloud storage systems. Experimental findings demonstrate that the proposed scheme yields superior results in terms of computation and time overheads. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human Posture Detection with Hybrid Deep VGG16 and Attention Mechanism Network

引用

Procedia computer Science 2025年 258卷 1209-1218页

作者： Ogundokun Roseline Oluwaseun Rytis Maskeliūnas Federick Oscar Oluwakayode A. Oki Department of Software Engineering Kaunas University of Technology Kaunas 44249 Lithuania Department of Computer Science Landmark University Omu-Aran Nigeria Department of Computer Systems Engineering Tshwane University of Technology (TUT) Pretoria South Africa Adioo Technology Abuja Nigeria Department of Information Technology East London Walter Sisulu University South Africa

Human Posture Detection (HPD) and classification are the initial steps toward various computer vision applications related to security, advertisement, and healthcare. Even though more than three decades have passed, most methods have been focused only on detecting standing people. However, in real applications, human postures may be significantly different, such as standing, sitting, lying, and crouching, and the shapes of a human are varied with viewpoints, thus making detection and classification difficult. Moreover, the gradual transition from one posture to another further complicates the determination of the number of postures to be classified. This paper uses a pre-trained model to determine the number of unique human postures in activities. We approached PC as a multiclass detection problem using the very deep VGG 16 Convolutional Neural Network (CNN) empowered by an attention mechanism. Extract frames from video data recorded, followed by the derivation of features through a convolutional neural network. Classify different postures—bending, exercise, lying, sitting, and standing—with VGG 16 and attention mechanism. It is trained on the ETRI-Activity3D-LivingLab Dataset. Our proposed (VEACT-CNN) framework has shown stability in HPD with an overall accuracy of 95% and an F-measure of 98% while generating a very low level of false alarms rate (FAR) of 0.02 (2%). For comparison purposes, the accuracy obtained by other models on the same dataset is VGG 16.

关键词： Vision-based human detection Posture classification VGG 16 Deep learning Pre-trained model Human posture detection

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：