检索结果-内蒙古大学图书馆

Looking Backwards (and Forwards): NSF Secure and Trustworthy Computing 20-Year Retrospective Panel Transcription

IEEE Security and Privacy 2023年第2期21卷 32-42页

作者： Landwehr, Carl Reiter, Michael K. Williams, Laurie Tsudik, Gene Jaeger, Trent Kohno, Tadayoshi Kapadia, Apu University of Michigan Electrical Engineering Ann ArborMI48109-2122 United States Duke University Computer Science and Electrical and Computer Engineering DurhamNC27708 United States North Carolina State University Computer Science Department of the College of Engineering RaleighNC27513 United States University of California Computer Science Irvine United States The Pennsylvania State University Computer Science and Engineering University ParkPA16802 United States University of Washington Paul G. Allen School of Computer Science and Engineering SeattleWA98195 United States Indiana University Bloomington Department of Computer Science BloomingtonIN47408 United States

The U.S. National science Foundation (NSF) celebrated the 20th anniversary of its research funding programs in cybersecurity, and more generally, secure and trustworthy computing, with a panel session at its conference held in June, 2022. The panel members, distinguished researchers in different research areas of trustworthy computing, were asked to comment on what has been learned, what perhaps should be 'unlearned what still needs to be learned, and the status of education and training in their respective areas of expertise. Laurie Williams covered enterprise security and measuring security, Gene Tsudik commented on cryptographic security, Trent Jaeger addressed computing infrastructure security, Tadayoshi Kohno reviewed security in cyberphysical systems, and Apu Kapadia provided insights on human-centered security. Michael K. Reiter chaired the panel and moderated questions from the audience. This report provides a brief summary of NSF's research programs in the area and an edited transcript of the panel discussion. © 2003-2012 IEEE.

关键词： Personnel training

来源：评论

学校读者我要写书评

暂无评论

LLM-based Skill Diffusion for Zero-shot Policy Adaptation 38

LLM-based Skill Diffusion for Zero-shot Policy Adaptation

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Kim, Woo Kyung Lee, Youngseok Kim, Jooyoung Woo, Honguk Department of Computer Science and Engineering Sunkyunkwan University Korea Republic of Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of

Recent advances in data-driven imitation learning and offline reinforcement learning have highlighted the use of expert data for skill acquisition and the development of hierarchical policies based on these skills. However, these approaches have not significantly advanced in adapting these skills to unseen contexts, which may involve changing environmental conditions or different user requirements. In this paper, we present a novel LLM-based policy adaptation framework LDuS which leverages an LLM to guide the generation process of a skill diffusion model upon contexts specified in language, facilitating zero-shot skill-based policy adaptation to different contexts. To implement the skill diffusion model, we adapt the loss-guided diffusion with a sequential in-painting technique, where target trajectories are conditioned by masking them with past state-action sequences, thereby enabling the robust and controlled generation of skill trajectories in test-time. To have a loss function for a given context, we employ the LLM-based code generation with iterative refinement, by which the code and controlled trajectory are validated to align with the context in a closed-loop manner. Through experiments, we demonstrate the zero-shot adaptability of LDuS to various context types including different specification levels, multi-modality, and varied temporal conditions for several robotic manipulation tasks, outperforming other language-conditioned imitation and planning methods. © 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

A ShuffleNet Architecture-Based Multi-Layer Feature Scaling and Fusion Approach for Underwater Net Cage Damage Detection in Aquaculture

A ShuffleNet Architecture-Based Multi-Layer Feature Scaling ...

引用

2024 IEEE International Conference on Consumer Electronics-Asia, ICCE-Asia 2024

作者： Huang, Xiang-Rui Chen, Yi-Cheng Chen, Liang-Bi Hu, Wu-Chih National Penghu University of Science and Technology Master Program in Electrical Engineering and Computer Science Department of Electrical Engineering Penghu Taiwan National Penghu University of Science and Technology Department of Computer Science and Information Engineering Penghu Taiwan

ISBN: (纸本)9798331530839

In offshore aquaculture operations, personnel equipped with diving gear are often necessary to inspect the underwater net cages for damage, particularly on the sea floor. This manual inspection process is time-consuming and complex. To overcome this problem, this paper proposes a computer vision solution for identifying damage in underwater net cages to address the inefficiencies and challenges of traditional manual inspections. The proposed scheme utilizes a high-performance multi-branch computational architecture designed based on ShuffleNet architecture to detect net cage damage more efficiently. Experimental results demonstrate that this work performs well on the ImageNet ILSVRC-2010 dataset and achieves an accuracy of 88.54% in underwater net damage detection. © 2024 IEEE.

关键词： Aquaculture

来源：评论

学校读者我要写书评

暂无评论

Incomplete and Asymmetric Information in General Lotto Games

引用

IEEE Transactions on Automatic Control 2024年第6期70卷 3617-3632页

作者： Paarporn, Keith Chandan, Rahul Alizadeh, Mahnoosh Marden, Jason R. University of Colorado Department of Computer Science Colorado Springs United States Amazon Robotics United States University of California Department of Electrical and Computer Engineering Santa BarbaraCA United States

In this paper, we consider incomplete and asymmetric information formulations of the General Lotto game, which describes two opposing players that strategically allocate limited resources over multiple contests. In particular, we consider scenarios where one of the player's resource budget is common knowledge while the other player's is private. Our main contribution provides complete equilibrium characterizations in the scenario where the private resource budget is drawn from a Bernoulli distribution. We then leverage these characterizations to analyze a resource assignment problem where a commander must decide how to assign resources to sub-colonels that compete against opponents in separate General Lotto games. While optimal deterministic policies have previously been characterized in the literature, we broaden the context by deriving optimal randomized policies, which induce asymmetric information General Lotto games. Leveraging our equilibrium characterizations, we demonstrate that randomization can offer a four-fold improvement in the commander's performance over the optimal deterministic assignments. © 1963-2012 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Intelligent Actor-Critic Learning Control for Collison-Free Trajectory Tracking of Mecanum-Wheeled Mobile Robots

引用

International Journal of Fuzzy Systems 2024年第4期26卷 1133-1142页

作者： Tsai, Ching-Chih Chen, Hsing-Yi Chan, Chun-Chieh Hung, Chi-Chih Chen, Guan-Ming Department of Electrical Engineering National Chung Hsing University Taichung Taiwan Department of Computer Science and Information Engineering National Formosa University Yunlin Taiwan

In the paper, an intelligent actor-critic learning control method augmented by a fuzzy broad learning system with output recurrent feedback (abbreviated as ORFBLS) is proposed for obstacle-avoiding trajectory tracking of heterogeneous Mecanum-wheeled omnidirectional mobile robots (HMOMRs) augmented with un-modeled errors and the learning control system’s parameters are changed with the working environment. By using actor-critic learning algorithms and the ORFBLS online function approximation, a new ORFBLS-based actor-critic learning control approach, dubbed as ORFBLS-ACLC, is presented to accomplish stable trajectory tracking of such uncertain HMOMRs. The ORFBLS-ACLC method combined with an obstacle avoidance scheme is presented to follow the desired collision-free trajectory tracking more closely than the existing methods do. The merits, superiority, and practicality of the raised control approach are well verified by carrying out three simulation comparisons and two experiments on an uncertain HMOMR. © The Author(s) under exclusive licence to Taiwan Fuzzy Systems Association 2024.

关键词： Learning systems

来源：评论

学校读者我要写书评

暂无评论

Developed an IoT-based smart solar energy monitoring system for environmental sustainability 3

Developed an IoT-based smart solar energy monitoring system ...

引用

3rd International Conference on Advancement in electrical and Electronic engineering, ICAEEE 2024

作者： Mamun, Abdullah Al Shuvo, Mehedi Hasan Islam, Towhidul Islam, Dwin Islam, Md. Jakirul Tanvir, Faysal Amin DUET Department Of Computer Science and Engineering Gazipur Bangladesh Lamar University Department of Electrical and Computer Engineering TX United States

ISBN: (纸本)9798350388282

Currently, electricity demand is constantly increasing all over the world, and the demand for this electricity is much higher than the production. As a result, the whole world is facing a global problem. In this decade, many researchers have been concerned about it and have suggested many ways to generate electricity in several ways, but they are not all concerned about low-cost, user-friendly, reliable data loggers and monitoring systems. To resolve the issue, we proposed an intelligent and environment-friendly way to generate electricity in all areas of a developing country. Initially, heat is generated either through household cooking activities or by burning excess or unnecessary garbage. After that, the solar panels are charged from the generated heat, and the charge is stored in a battery from the solar panel. The data logger, which is based on the ESP32 microcontroller, records all monitoring parameters on the cloud and presents them in the Android application. All the processes are completed automatically without any human interaction, and burning unnecessary garbage establishes environmental sustainability. The data logger hardware prototype that has been created incorporates four sensors to measure temperature, humidity, voltage, and current, which show up on an Android application with real-time data on many metrics. Additionally, it provides maintenance professionals with crucial information about any problems related to battery charging. To complete the work, we have created the hardware implementation of photovoltaic systems that use the IoT for remote data collection to provide us sustainability, and this prototype's total cost is affordable. © 2024 IEEE.

关键词： Sustainable development

来源：评论

学校读者我要写书评

暂无评论

Absorb and Repel: Pseudo-Label Refinement for Intra-Camera Supervised Person Re-Identification

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第6期5卷 2884-2896页

作者： Li, Wei Chen, Chuyi Huang, Kaizhu Southeast University School of Instrument Science and Engineering Nanjing210096 China Duke Kunshan University Department of Electrical and Computer Engineering Kunshan215316 China

Person re-identification (ReID) aims to identify pedestrian images with the same identity across non-overlapping camera views. Intra-camera supervised person re-identification (ICS-ReID) is a new paradigm that trains a model using only intra-camera labels, thus reducing the cost of inter-camera identity association. Pseudo-label-based clustering algorithms perform well in the unsupervised ReID task, whereas they inevitably generate noisy pseudo labels through clustering, especially in the early training stage. Given this, we propose an unsupervised pseudo-labeling method to help in the semi-supervised ICS-ReID task. This method improves the clustering results by reassigning pseudo labels for the training data and consists of two modules, Absorb and Repel. The Absorb module aims to group all data with the same intra-camera identity into one cluster. The Repel module ensures that images under the same camera view but with different identities do not appear in the same cluster. Both modules are independent yet complementary to reduce the error rate of pseudo labels generated in each epoch. To our knowledge, this is the first attempt to refine pseudo labels for ICS-ReID. Our method is a simple, nonparametric, and effective strategy that can be easily integrated into existing clustering-based unsupervised ReID tasks. Extensive experiments demonstrate that our proposed method outperforms the state-of-the-art ICS-ReID approaches on three large-scale benchmark person ReID datasets. © 2020 IEEE.

关键词： Cameras

来源：评论

学校读者我要写书评

暂无评论

Improving Badminton Action Recognition Using Spatio-Temporal Analysis and a Weighted Ensemble Learning Model

引用

computers, Materials & Continua 2024年第11期81卷 3079-3096页

作者： Farida Asriani Azhari Azhari Wahyono Wahyono Department of Computer Science and Electronics Universitas Gadjah MadaYogyakarta55281Indonesia Electrical Engineering Department Universitas Jenderal SoedirmanPurbalingga53371Indonesia

Incredible progress has been made in human action recognition(HAR),significantly impacting computer vision applications in sports ***,identifying dynamic and complex movements in sports like badminton remains challenging due to the need for precise recognition accuracy and better management of complex motion *** learning techniques like convolutional neural networks(CNNs),long short-term memory(LSTM),and graph convolutional networks(GCNs)improve recognition in large datasets,while the traditional machine learning methods like SVM(support vector machines),RF(random forest),and LR(logistic regression),combined with handcrafted features and ensemble approaches,perform well but struggle with the complexity of fast-paced sports like *** proposed an ensemble learning model combining support vector machines(SVM),logistic regression(LR),random forest(RF),and adaptive boosting(AdaBoost)for badminton action *** data in this study consist of video recordings of badminton stroke techniques,which have been extracted into spatiotemporal *** three-dimensional distance between each skeleton point and the right hip represents the spatial *** temporal features are the results of Fast Dynamic Time Warping(FDTW)calculations applied to 15 frames of each video *** weighted ensemble model employs soft voting classifiers from SVM,LR,RF,and AdaBoost to enhance the accuracy of badminton action *** E2 ensemble model,which combines SVM,LR,and AdaBoost,achieves the highest accuracy of 95.38%.

关键词： Weighted ensemble learning badminton action soft voting classifier joint skeleton fast dynamic time warping spatiotemporal

来源：评论

学校读者我要写书评

暂无评论

Blockchain privacy: Fundamental aspects and challenges for the future Internet data sharing

IET Blockchain

引用

IET Blockchain 2024年第2期4卷 152-168页

作者： Kapsoulis, Nikolaos Psychas, Alexandros Litke, Antonios Varvarigou, Theodora School of Electrical and Computer Engineering National Technical University of Athens Athens Greece Division of Mathematics and Engineering Science Hellenic Army Academy Athens Greece

Privacy concerns the majority of individuals, governments, and organizations that share data over dissimilar networks of nodes. Every kind of participant requires awareness of the data journey that unfolds inside a blockchain network with its own trustworthy rules of data management and accessibility. This paper provides a methodological approach on privacy for data sharing within blockchain environments. Specific technological aspects of blockchains that relate to on-chain privacy such as network nature, party join, smart contracts, blockchain states, transactions, and ledger flows, are analysed with respect to the involvement and impact of privacy in distributed ledgers. A high-level architectural approach is suggested that is intended to address significant privacy concerns on data sharing among different kinds of users in the context of blockchain networks deployment and the broader Web 3.0 ecosystem building. Simultaneously, many pertinent challenges are discussed regarding network nature, configurable privacy, ownership, confidentiality, secured computation, and data monetization that appear in the field and ought to be carefully tackled for the future mass adoption of privacy-matured distributed ledgers that interconnect delivering the future Internet. © 2023 The Authors. IET Blockchain published by John Wiley & Sons Ltd on behalf of The Institution of engineering and Technology.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based human activity recognition using CNN, ConvLSTM, and LRCN

引用

International Journal of Cognitive Computing in engineering 2024年第1期5卷 259-268页

作者： Uddin, Md. Ashraf Talukder, Md. Alamin Uzzaman, Muhammad Sajib Debnath, Chandan Chanda, Moumita Paul, Souvik Islam, Md. Manowarul Khraisat, Ansam Alazab, Ammar Aryal, Sunil School of Information Technology Deakin University Waurn Ponds Campus Geelong Australia Department of Computer Science and Engineering International University of Business Agriculture and Technology Dhaka Bangladesh Department of Computer Science and Engineering Jagannath University Dhaka Bangladesh Centre for Artificial Intelligence and Optimization Torrens University Australia Department of Electrical and Computer Engineering University of Ottawa Canada

Human activity recognition (HAR) plays a crucial role in assisting the elderly and individuals with vascular dementia by providing support and monitoring for their daily activities. This paper presents a deep learning (DL)-based approach to HAR, leveraging convolutional neural network (CNN), convolutional long short-term memory (ConvLSTM), and long-term recurrent convolutional network (LRCN) architectures. These models are designed to extract spatial features and capture temporal dependencies in video data, enhancing the accuracy of activity classification. We conducted experiments on the UCF50 and HMDB51 video datasets, encompassing diverse human activities. Our evaluation demonstrates that the ConvLSTM model achieves an accuracy of 82% on UCF50 and 68% on HMDB51, while the LRCN model gives accuracies of 93.44% and 71.55%, respectively. Finally, the CNN model outperforms with an accuracy rate of 99.58% for the UCF50 and 92.70% for the HMDB51 datasets. These significant improvements showcase the effectiveness of integrating convolutional and recurrent neural networks for HAR tasks. Our research contributes to advancing HAR systems with potential applications in healthcare, assisted living, and surveillance. By accurately recognizing human activities, our models can assist in remote patient monitoring, fall detection, and public safety initiatives. These findings underscore the importance of DL in enhancing the quality of life and safety for individuals in various contexts. © 2024 The Authors

关键词： Long short-term memory

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：