检索结果-内蒙古大学图书馆

An Efficient Attention-Based Strategy for Anomaly Detection in Surveillance Video

computer Systems science & engineering 2023年第9期46卷 3939-3958页

作者： Sareer Ul Amin Yongjun Kim Irfan Sami Sangoh Park Sanghyun Seo Department of Computer Science and Engineering Chung-Ang UniversitySeoul06974Korea Intelligent Convergence Research Lab. ETRIDaeJeon34129Korea Department of Electrical and Electronics Engineering Chung-Ang UniversitySeoul06974Korea College of Art and Technology Chung-Ang UniversityAnseong17546Korea

In the present technological world,surveillance cameras generate an immense amount of video data from various sources,making its scrutiny tough for computer vision *** is difficult to search for anomalous events manually in thesemassive video records since they happen infrequently and with a low probability in real-world monitoring ***,intelligent surveillance is a requirement of the modern day,as it enables the automatic identification of normal and aberrant behavior using artificial intelligence and computer vision *** this article,we introduce an efficient Attention-based deep-learning approach for anomaly detection in surveillance video(ADSV).At the input of the ADSV,a shots boundary detection technique is used to segment prominent ***,The Lightweight ConvolutionNeuralNetwork(LWCNN)model receives the segmented frames to extract spatial and temporal information from the intermediate *** that,spatial and temporal features are learned using Long Short-Term Memory(LSTM)cells and Attention Network from a series of frames for each anomalous activity in a *** detect motion and action,the LWCNN received chronologically sorted ***,the anomaly activity in the video is identified using the proposed trained ADSV *** experiments are conducted on complex and challenging benchmark *** addition,the experimental results have been compared to state-ofthe-artmethodologies,and a significant improvement is attained,demonstrating the efficiency of our ADSV method.

关键词： Attention-based anomaly detection video shots segmentation video surveillance computer vision deep learning smart surveillance system violence detection attention model

来源：评论

学校读者我要写书评

暂无评论

Hd-Fuzz: Hardware Dependency-Aware Firmware Fuzzing Via Hybrid Mmio Modeling

SSRN

引用

SSRN 2023年

作者： Kim, Juhwan Yu, Jihyeon Lee, Youngwoo Kim, Dan Dongseong Yun, Joobeom Department of Computer and Information Security and Convergence Engineering for Intelligent Drone Sejong University Seoul05006 Korea Republic of School of Information Technology and Electrical Engineering University of Queensland BrisbaneQLD4067 Australia

Numerous interconnected small embedded systems, such as Internet of Things (IoT) devices, are pervasive in our daily lives;however, their security lags behind. In particular, firmware vulnerabilities in low-level infrastructure have a more severe impact than application-level vulnerabilities. Fuzzing is the most effective technique for detecting vulnerabilities in firmware, but it encounters several challenges such as hardware-dependency, input channel, and instrumentation. Existing works attempt to overcome these challenges by combining firmware re-hosting and fuzzing. However, they only explore worthwhile paths based on heuristics and human assistance, which leaves many parts of the firmware’s functionality unreachable by fuzzing. In this work, we propose a novel hardware dependency-aware system named HD-FUZZ that combines low-level firmware re-hosting with fuzzing to explore all paths in the firmware and find bugs efficiently. The key ideas of HD-FUZZ are: 1) to propose a hybrid memory-mapped I/O (MMIO) modeling;2) to achieve high efficiency by performing MMIO modeling through fuzzing for most cases;and 3) to achieve completeness by performing MMIO modeling through symbolic execution only to satisfy complex checks affecting the execution flow. HD-FUZZ has been extensively evaluated on both unit test cases and real-world targets, covering 12 hardware platforms and 67 firmware images. Compared to state-of-the-art works, HD-FUZZ achieves the highest passing rate in unit test benchmarks, reaches up to 2.62 times higher code coverage in fuzzing benchmarks, and generates initial access models up to 11.6 times faster. Notably, HD-FUZZ finds two new bugs, including ones in targets that were previously analyzed by other works. © 2023, The Authors. All rights reserved.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Background Debiased Class Incremental Learning for Video Action Recognition

SSRN

引用

SSRN 2023年

作者： Nguyen, Le Quan Choi, Jinwoo Minh, L. Dang Moon, Hyeonjoon Department of Computer Science and Engineering Sejong University Sejong University Seoul Seoul05006 Korea Republic of Department of Information and Communication Engineering and Convergence Engineering for Intelligent Drone Seoul 05006 Sejong University Seoul Korea Republic of School of Computing Kyung Hee University Yongin Korea Republic of

In this work, we tackle class incremental learning (CIL) for video action recognition, a relatively under-explored problem despite its practical importance. Directly applying image-based CIL methods does not work well in the video action recognition setting. We hypothesize the major reason is the spurious correlation between the action and background in video action recognition datasets/models. Recent literature shows that the spurious correlation hampers the generalization of models in the conventional action recognition setting. The problem is even more severe in the CIL setting due to the limited exemplars available in the rehearsal memory. We empirically show that mitigating the spurious correlation between the action and background is crucial to the CIL for video action recognition. We propose to learn background invariant action representations in the CIL setting by providing training videos with diverse backgrounds generated from background augmentation techniques. We validate the proposed method on public benchmarks: HMDB-51, UCF-101, and Something-Something-v2. © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Survey on Integrated Navigation System Based on Inertial Technology

引用

Journal of Institute of Control, Robotics and Systems 2024年第4期30卷 448-463页

作者： Park, Chan Gook Cha, Jaehyuck Choe, Yeongkwon Lee, Jaehong Lee, Hanyeol Kim, Kwangjin Cho, Seong Yun Song, Jin Woo Department of Aerospace Engineering/Automation and Systems Research Institute Seoul National University Korea Republic of Department of Mechatronics Engineering/Department of Smart Health Science and Technology Kangwon National University Korea Republic of Navigation Business Center Hanwha Aerospace Korea Republic of Department of mechanical automotive engineering Kyungil University Korea Republic of Department of Intelligent Mechatronics Engineering and Convergence Engineering for Intelligent Drone Sejong University Korea Republic of

In this paper, we summarize the results of inertial navigation-based integrated navigation systems that have been researched for over 30 years. First, we introduce the core technologies for operating inertial navigation systems (INS) and discuss the technological advances in pedestrian navigation using small and low-cost inertial sensors for mobile devices. Second, we present the integrated navigation systems with other sensors to overcome the limitations of the INS, which degrades over time. The fundamental principles of, and major research on the inertial-based integrated navigation system with global navigation satellite system, database, or camera/LiDAR are discussed. Finally, the major achievements in recent advances in artificial intelligence-assisted navigation are addressed. © ICROS 2024.

关键词： Inertial navigation systems

来源：评论

学校读者我要写书评

暂无评论

A hybrid explainable ensemble transformer encoder for pneumonia identification from chest X-ray images

引用

Journal of Advanced Research 2023年 48卷 191-211页

作者： Ukwuoma, Chiagoziem C. Qin, Zhiguang Belal Bin Heyat, Md Akhtar, Faijan Bamisile, Olusola Muaad, Abdullah Y. Addo, Daniel Al-antari, Mugahed A. School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan Chengdu China IoT Research Center College of Computer Science and Software Engineering Shenzhen University Guangdong Shenzhen 518060 China Centre for VLSI and Embedded System Technologies International Institute of Information Technology Telangana Hyderabad 500032 India Department of Science and Engineering Novel Global Community Educational Foundation Hebersham 2770 NSW Australia School of Computer Science and Engineering University of Electronic Science and Technology of China Sichuan Chengdu 611731 China Sichuan Industrial Internet Intelligent Monitoring and Application Engineering Technology Research Center Chengdu University of Technology Chengdu China Department of Studies in Computer Science University of Mysore Manasagangothri Mysore India Department of Artificial Intelligence College of Software & Convergence Technology Daeyang AI Center Sejong University Seoul 05006 South Korea

Introduction: Pneumonia is a microorganism infection that causes chronic inflammation of the human lung cells. Chest X-ray imaging is the most well-known screening approach used for detecting pneumonia in the early stages. While chest-Xray images are mostly blurry with low illumination, a strong feature extraction approach is required for promising identification performance. Objectives: A new hybrid explainable deep learning framework is proposed for accurate pneumonia disease identification using chest X-ray images. Methods: The proposed hybrid workflow is developed by fusing the capabilities of both ensemble convolutional networks and the Transformer Encoder mechanism. The ensemble learning backbone is used to extract strong features from the raw input X-ray images in two different scenarios: ensemble A (i.e., DenseNet201, VGG16, and GoogleNet) and ensemble B (i.e., DenseNet201, InceptionResNetV2, and Xception). Whereas, the Transformer Encoder is built based on the self-attention mechanism with multilayer perceptron (MLP) for accurate disease identification. The visual explainable saliency maps are derived to emphasize the crucial predicted regions on the input X-ray images. The end-to-end training process of the proposed deep learning models over all scenarios is performed for binary and multi-class classification scenarios. Results: The proposed hybrid deep learning model recorded 99.21% classification performance in terms of overall accuracy and F1-score for the binary classification task, while it achieved 98.19% accuracy and 97.29% F1-score for multi-classification task. For the ensemble binary identification scenario, ensemble A recorded 97.22% accuracy and 97.14% F1-score, while ensemble B achieved 96.44% for both accuracy and F1-score. For the ensemble multiclass identification scenario, ensemble A recorded 97.2% accuracy and 95.8% F1-score, while ensemble B recorded 96.4% accuracy and 94.9% F1-score. Conclusion: The proposed hybrid deep learning framewo

关键词： Chest X-ray imaging Explainable artificial intelligence (XAI) Pneumonia identification Self-attention network Transfer ensemble learning Transformer encoder (TE)

来源：评论

学校读者我要写书评

暂无评论

Towards Privacy-Preserving Cloud Storage:A Blockchain Approach

引用

computers, Materials & Continua 2021年第12期69卷 2903-2916页

作者： Jia-Shun Zhang Gang Xu Xiu-Bo Chen Haseeb Ahmad Xin Liu Wen Liu Information Security Center State Key Laboratory of Networking and Switching TechnologyBeijing University of Posts and TelecommunicationsBeijing100876China School of Information Science and Technology North China University of TechnologyBeijing100144China Department of Computer Science National Textile UniversityFaisalabad37610Pakistan Inner Mongolia University of Science&Technology School of Information EngineeringBaotou014010China State Key Laboratory of Media Convergence and Communication Communication University of China School of Computer Science and Cybersecurity Communication University of China Key Laboratory of Convergent Media and Intelligent Technology Communication University of China Ministry of EducationBeijing102204China

With the rapid development of cloud computing technology,cloud services have now become a new business model for information *** cloud server provides the IT resources required by customers in a selfservice manner through the network,realizing business expansion and rapid ***,due to the insufficient protection of data privacy,the problem of data privacy leakage in cloud storage is threatening cloud *** address the problem,we propose BC-PECK,a data protection scheme based on blockchain and public key searchable ***,all the data is protected by the encryption *** privacy data is encrypted and stored in a cloud server,while the ciphertext index is established by a public key searchable encryption scheme and stored on the ***,based on the characteristics of trusted execution of smart contract technology,a control mechanism for data accessing and sharing is *** transaction is automatically recorded on the blockchain,which is fairer under the premise of ensuring the privacy and security of the data sharing ***,we analyzed the security and fairness of the current *** the comparison with similar schemes,we have shown the advantages of the proposed scheme.

关键词： Blockchain privacy protection smart contract public encryption keyword search

来源：评论

学校读者我要写书评

暂无评论

Transport Capacity Optimization for Resource Allocation in Tera-IoT Networks

arXiv

引用

arXiv 2022年

作者： Jeong, Cheol Chun, Chang-Jae Shin, Won-Yong Kim, Il-Min The Department of Intelligent Mechatronics Engineering The Department of Convergence Engineering for Intelligent Drone Sejong University Seoul05006 Korea Republic of The Department of Artificial Intelligence Sejong University Seoul05006 Korea Republic of Yonsei University Seoul03722 Korea Republic of The Department of Electrical and Computer Engineering Queen's University KingstonONK7L 3N6 Canada

We present a new adaptive resource optimization strategy that jointly allocates the subwindow and transmit power in multi-device terahertz (THz) band Internet of Things (Tera-IoT) networks. Unlike the prior studies focusing mostly on maximizing the sum distance, we incorporate both rate and transmission distance into the objective function of our problem formulation with key features of THz bands, including the spreading and molecular absorption losses. More specifically, as a performance metric of Tera-IoT networks, we adopt the transport capacity (TC), which is defined as the sum of the rate-distance products over all users. This metric has been widely adopted in large-scale ad hoc networks, and would also be appropriate for evaluating the performance of various Tera-IoT applications. We then formulate an optimization problem that aims at maximizing the TC. Moreover, motivated by the importance of the transmission distance that is very limited due to the high path loss in THz bands, our optimization problem is extended to the case of allocating the subwindow, transmit power, and transmission distance. We show how to solve our problems via an effective two-stage resource allocation strategy. We demonstrate the superiority of our adaptive solution over benchmark methods via intensive numerical evaluations for various environmental setups of large-scale Tera-IoT networks. © 2022, CC BY.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

UPnP remote UI and sensor collaboration framework for cloud AV service in smart home

UPnP remote UI and sensor collaboration framework for cloud ...

引用

International Conference on Information and Communication Technology convergence (ICTC)

作者： Boyun Eom Choonhwa Lee Hyunwoo Lee Intelligent Convergence Technology Research Department ETRI Daejeon Rep. of Korea Division of Computer Science and Engineering Hanyang University Seoul Rep. of Korea

ISBN: (纸本)9781479906963

This paper presents a context-aware AV service framework based on cloud AV servers and UPnP Remote UI devices in smart home environments. The proposed AV service may be viewed as similar, in spirit, to N-screen services. However, our emphasis is placed on the intelligence and context-awareness enabled by various sensors deployed at smart home.

关键词： Servers Smart homes Home appliances Videos Collaboration Logic gates Cloud computing

来源：评论

学校读者我要写书评

暂无评论

Improving Indoor Positioning Systems with UWB and Filtering Techniques: A ComparativeAnalysis

Improving Indoor Positioning Systems with UWB and Filtering ...

引用

International Conference on Control, Automation and Systems ( ICCAS)

作者： First A. Rahul Ranjan Second B. Younsik Jung Shin Donggyu Third. Sanghyun Kim Chang-Hyun Kim Seungjae Lee Joongeup Kye Department of Computer Engineering and Electronics Convergence Intelligent Robot Research Institute Sun Moon University Asan Korea Department of Computer Science and Engineering Intelligent Robot Research Institute Sun Moon University Asan Korea Department of Mechanical Engineering Kyung Hee University Suwon Korea Korea Institute of Machinery & Materials Daejeon Korea Department of Mechanical Engineering Intelligent Robot Research Institute Sun Moon University Asan Korea

In today's world, indoor positioning systems(IPS) have become a fascinating research area. Accurate positioning of mobile robots in indoor environments remains challenging due to various positioning techniques and the complexities associated with dynamic environments, dense obstacles, and different material types. Indoor localization systems face challenges in reducing noise and enhancing accuracy. In this paper, an Ultra-Wideband(UWB) based localization system is under test to evaluate the efficiency of the measurement using two different methods, Low-Pass Filter(LPF) and Kalman Filter(KF), on Robot Operating System(ROS) platform. This study aims to assess and compare the effectiveness of the proposed methods in reducing noise and improving the accuracy of indoor localization systems. A set of position data was recorded in the lab environment. The proposed Filtered is applied and compared with target trajectory paths. The findings of this research contribute to the development of robust and reliable indoor localization systems crucial for various applications, including mobile robotics, automation, and human-computer interaction.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Power-Aware Remote Display Protocol for Mobile Cloud

Power-Aware Remote Display Protocol for Mobile Cloud

引用

International Conference on Information science and Applications (ICISA)

作者： Boyun Eom Hyunwoo Lee Choonhwa Lee Intelligent Convergence Media Research Department Electronics and Telecommunications Research Institute Daejeon Rep. of Korea Division of Computer Science and Engineering Hanyang University Seoul Rep. of Korea

Integrated into cloud environments, the mobile device overcomes its weakness of resource-limited settings and mobile cloud computing is expected to be the next big trend in cloud computing research. Current remote display protocols used in mobile cloud computing have been developed for desktop computers which are plugged all the time while connecting through LAN (Local Area Network) and it should be scrutinized for mobile device characteristics. Apparently, in mobile cloud computing, there is a still limit of power on the end point. However, few studies on remote protocol framework consider power constraint and much research have focused on more performance for better quality of images in the area. Motivated by this, we propose an encoding scheme to reduce energy consumption on client side in mobile cloud computing. By lowering the power consumption of a CPU and a wireless network interface card, our adaptive encoding scheme achieves gains in energy conservation.

关键词： Mobile communication Mobile handsets Cloud computing Encoding Power demand Protocols Servers

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：