检索结果-内蒙古大学图书馆

10th IEEE Smart World Congress, SWC 2024

作者： Guo, Zhenyang Cao, Jin Zan, Xiaoyong Yang, Jiawei Li, Ang Niu, Ben Sun, Zhe Yin, Lihua Li, Hui Xidian University School of Cyber Engineering Xi'an China The State Key Laboratory of Integrated Services Networks Xi'an China ByteDance Ltd Beijing China University of Maryland Department of Electrical & Computer Engineering College Park United States Institute of Information Engineering Chinese Academy of Sciences Beijing China Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou China

ISBN: (纸本)9798331520861

Surveillance cameras are currently widely used in public and private places to enhance area security and reduce crime rates. However, the extensive use of surveillance cameras also poses significant threats, particularly concerning the leakage of users' private information. Surveillance cameras are often installed in the corners of areas such as hotel front desks, supermarket checkout areas, or ticket offices to observe user behavior, which can lead to shoulder-surfing attacks. In these public or private settings, when users input their personal identification number (PIN) for unlocking or payment, this process may be intentionally or unintentionally exposed and recorded. If the PIN is compromised, it can result in severe privacy breaches and financial losses for users. Existing work primarily focuses on dedicated handheld recording devices such as cameras and smartphones, lacking discussion on public surveillance cameras. In this paper, we first present an attack model for such scenarios. Based on this model, we design and implement an automated attack system for PIN recognition. Experimental results demonstrate that our proposed attack model is both feasible and effective, achieving 90 % accuracy with our system. Finally, we urge users, smartphone manufacturers, and surveillance camera manufacturers to be aware of this attack vector to prevent further harm. © 2024 IEEE.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

Online Detection of Anomalies in Temporal Knowledge Graphs with Interpretability

引用

Proceedings of the ACM on Management of Data 2024年第6期2卷 1-26页

作者： Jiasheng Zhang Rex Ying Jie Shao School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu CN Department of Computer Science Yale University New Haven CT USA Shenzhen Institute for Advanced Study University of Electronic Science and Technology of China Shenzhen CN

Temporal knowledge graphs (TKGs) are valuable resources for capturing evolving relationships among entities, yet they are often plagued by noise, necessitating robust anomaly detection mechanisms. Existing dynamic graph anomaly detection approaches struggle to capture the rich semantics introduced by node and edge categories within TKGs, while TKG embedding methods lack interpretability, undermining the credibility of anomaly detection. Moreover, these methods falter in adapting to pattern changes and semantic drifts resulting from knowledge updates. To tackle these challenges, we introduce AnoT, an efficient TKG summarization method tailored for interpretable online anomaly detection in TKGs. AnoT begins by summarizing a TKG into a novel rule graph, enabling flexible inference of complex patterns in TKGs. When new knowledge emerges, AnoT maps it onto a node in the rule graph and traverses the rule graph recursively to derive the anomaly score of the knowledge. The traversal yields reachable nodes that furnish interpretable evidence for the validity or the anomalous of the new knowledge. Overall, AnoT embodies a detector-updater-monitor architecture, encompassing a detector for offline TKG summarization and online scoring, an updater for real-time rule graph updates based on emerging knowledge, and a monitor for estimating the approximation error of the rule graph. Experimental results on four real-world datasets demonstrate that AnoT surpasses existing methods significantly in terms of accuracy and interoperability. All of the raw datasets and the implementation of AnoT are provided in https://***/zjs123/ANoT.

关键词： anomaly detection graph summarization temporal knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Metal carbonyl loaded nanoparticles for breast cancer biomarker detection 21

Metal carbonyl loaded nanoparticles for breast cancer biomar...

引用

Nanoscale Imaging, Sensing, and Actuation for Biomedical Applications XXI 2024

作者： Richard, Craig Hsieh, Pei-Hsuan Confer, Matthew Bhargava, Rohit Department of Bioengineering University of Illinois at Urbana-Champaign United States Beckman Institute for Advanced Science and Technology University of Illinois at Urbana-Champaign United States Departments of Electrical and Computer Engineering Mechanical Science and Engineering Chemical and Biomolecular Engineering Chemistry United States Cancer Center at Illinois University of Illinois at UrbanaChampaign Urbana United States

ISBN: (纸本)9781510669758

The potential advantages of infrared spectroscopic imaging for examination of cells and tissue biopsies for cancer histopathology is high, however there are fundamental limitations of FTIR that must first be addressed. One limitation is that Infrared spectroscopy lacks the sensitivity to detect biomarkers of disease directly. With cancer being one of the leading causes of death and its increasing prevalence, it is important to develop tools that can rapidly screen and enable rapid and simultaneous fingerprinting of biologic content and metabolic state. To address these limitations, probed Infrared spectroscopy is being explored. We report the successful synthesis, characterization, and application of metal carbonyl loaded nanoparticle probes for the detection of breast cancer biomarkers. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Biomarkers

来源：评论

学校读者我要写书评

暂无评论

Quantum-Enhanced Zero Trust Security: Evolution, Implementation, and Application

Quantum-Enhanced Zero Trust Security: Evolution, Implementat...

引用

Quantum Communications, Networking, and Computing (QCNC), International Conference on

作者： Jun Lin Qiu Jiang Weiyong Zhang Zihao Lin Xiaojiang Du Cyberspace Institute of Advanced Technology Guangzhou University Guangzhou China Department of Electrical and Computer Engineering Stevens Institute of Technology Hoboken NJ USA

ISBN: (数字)9798350366778

ISBN: (纸本)9798350366785

In today's fast-paced digital economy, the widespread adoption of new technologies brings about significant challenges in network security. This paper delves into the evolution of Zero Trust network architecture, marking a significant shift from traditional perimeter-centric security methods. It embraces the “never trust, always verify” philosophy, moving away from conventional approaches. Subsequently, the paper explores the strategic implementation of Zero Trust, focusing on essential components such as Policy Enforcement Points (PEP) and Identity and Access Management (IAM). It also addresses the challenges in deploying Zero Trust architectures, including the high demands for real-time detection, and suggests viable solutions to these challenges. An important aspect of this study is the emerging role of quantum technology in enhancing network security. The integration of quantum technology with Zero Trust principles is poised to offer more robust network protection, particularly with the advancements in quantum key research. Current research in quantum keys opens new avenues for applying the Zero Trust philosophy in practical scenarios. This fusion is instrumental in laying the foundation for a more secure and innovative network security framework, aiming to effectively counter the evolving digital threats and strengthen the infrastructure of the digital economy against potential vulnerabilities.

关键词： Philosophical considerations Organizations Network security Propulsion Regulation Real-time systems Zero Trust

来源：评论

学校读者我要写书评

暂无评论

TOWARDS DIVERSE EVALUATION OF CLASS INCREMENTAL LEARNING: A REPRESENTATION LEARNING PERSPECTIVE 3

TOWARDS DIVERSE EVALUATION OF CLASS INCREMENTAL LEARNING: A ...

引用

3rd Conference on Lifelong Learning Agents, CoLLAs 2024

作者： Cha, Sungmin Kwak, Jihwan Shim, Dongsub Kim, Hyunwoo Lee, Moontae Lee, Honglak Moon, Taesup Computer Science Department Courant Institute of Mathematical Sciences New York University United States Department of Electrical and Computer Engineering Seoul National University Korea Republic of Advanced Machine Learning Lab LG AI Research Korea Republic of Zhejiang Lab China Department of Information and Decision Sciences University of Illinois Chicago United States ASRI INMC IPAI AIIS Seoul National University Korea Republic of

Class incremental learning (CIL) algorithms aim to continually learn new object classes from incrementally arriving data while not forgetting past learned classes. The common evaluation protocol for CIL algorithms is to measure the average test accuracy across all classes learned so far - however, we argue that solely focusing on maximizing the test accuracy may not necessarily lead to developing a CIL algorithm that also continually learns and updates the representations, which may be transferred to the downstream tasks. To that end, we experimentally analyze neural network models trained by CIL algorithms using various evaluation protocols in representation learning and propose new analysis methods. Our experiments show that most state-of-the-art algorithms prioritize high stability and do not significantly change the learned representation, and sometimes even learn a representation of lower quality than a naive baseline. However, we observe that these algorithms can still achieve high test accuracy because they enable a model to learn a classifier that closely resembles an estimated linear classifier trained for linear probing. Furthermore, the base model learned in the first task, which involves single-task learning, exhibits varying levels of representation quality across different algorithms, and this variance impacts the final performance of CIL algorithms. Therefore, we suggest that the representation-level evaluation should be considered as an additional recipe for more diverse evaluation for CIL algorithms. © 2024 CoLLAs. All Rights Reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An Interpretable AI for Smart Homes: Identifying Fall Prevention Strategies for Older Adults Using Multimodal Deep Learning

引用

IEEE Journal of Biomedical and Health Informatics 2025年

作者： Baek, Jeongyeop Li, Yifan Lim, Lisa Chong, Jo Woon Korea Advanced Institute of Science and Technology Department of Civil and Environmental Engineering Daejeon34141 Korea Republic of Texas Tech University Department of Electrical and Computer Engineering LubbockTX79409 United States Sungkyunkwan University Department of Electrical and Computer Engineering Suwon16419 Korea Republic of

Falls are a significant cause of mortality among older adults and are considered preventable emergencies. We developed an interpretation framework, including multimodal predictive models that capture both static and timeseries data, and analyzed global feature importance via a perturbation approach, permutation importance (PIMP), and SHapley Additive exPlanations (SHAP) to identify fall prevention strategies at home. Our predictive model utilizing the BiCrossNet architecture achieved a prediction accuracy of 98% when 12,540 data points were used. It was found that activity-related and indoor thermal environment features are important for predicting fall emergency occurrences (FEOs). Interestingly, extended active time in the living room/kitchen and outdoors decreases the FEO ratio, whereas extended active time in the bedroom and bathroom increases the FEO ratio. For example, increasing the active time in the living room/kitchen from 60−70 to 130−140 minutes reduced the FEO ratio by 32%. Furthermore, indoor temperature and humidity were found to be important depending on the outdoor conditions. Moreover, this study shows the importance of personalized prevention strategies depending on the underlying health conditions of older adults © 2013 IEEE.

关键词： Smart homes

来源：评论

学校读者我要写书评

暂无评论

A Traceable Capability-based Access Control for IoT

引用

computers, Materials & Continua 2022年第9期72卷 4967-4982页

作者： Chao Li Fan Li Cheng Huang Lihua Yin Tianjie Luo Bin Wang Cyberspace Institute of Advanced Technology Guangzhou UniversityGuangzhou510700China PCL Research Center of Cyberspace Security Peng Cheng LaboratoryShenzhen518052China Department of Electrical and Computer Engineering University of WaterlooWaterlooN2L 3G1Canada College of Electrical Engineering Zhejiang UniversityHangzhou310058China

Delegation mechanism in Internet of Things(IoT)allows users to share some of their permissions with ***-based delegation solutions require that only the user who has registered in the cloud can be delegated *** is not convenient when a permission is delegated to a large number of temporarily ***,some works like CapBAC delegate permissions locally in an offline ***,this is difficult to revoke and modify the offline delegated *** this work,we propose a traceable capability-based access control approach(TCAC)that can revoke and modify permissions by tracking the trajectories of permissions *** define a time capability tree(TCT)that can automatically extract permissions trajectories,and we also design a new capability token to improve the permission verification,revocation and modification *** experiment results show that TCAC has less token verification and revocation/modification time than those of CapBAC and *** can discover 73.3%unvisited users in the case of delegating and accessing *** provides more information about the permissions delegation relationships,and opens up new possibilities to guarantee the global security in IoT delegation *** the best of our knowledge,TCAC is the first work to capture the unvisited permissions.

关键词： IoT access control permission delegation delegation trajectory capability revocation capability modification

来源：评论

学校读者我要写书评

暂无评论

Liquid-metal micro-networks with strain-induced conductivity for soft electronics and robotic skin

引用

npj Flexible Electronics 2022年第1期6卷 799-808页

作者： Yeongmin Park Jaewoong Jung Younghoon Lee Dongwoo Lee Joost J.Vlassak Yong-Lae Park Department of Mechanical Engineering Institute of Advanced Machines and DesignInstitute of Engineering ResearchSeoul National UniversitySeoul 08826Korea Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology(MIT)CambridgeMA 02139USA School of Mechanical Engineering Sungkyunkwan UniversitySuwon 16419Korea John A.Paulson School of Engineering and Applied Sciences Harvard UniversityCambridgeMA 02138USA

Thin-film devices made of room-temperature liquid metals(LMs)have contributed to the development of electronic skin for human-robot/machine interfaces but still have limitations,including degradations of performance and robustness under repeated *** this paper,we describe an interesting phenomenon of the formation of LM microscale networks(LMMNs)and propose to use the LMMNs for fabricating thin-film conductors.A simple layer-by-layer(LBL)deposition process enables the growth of a hierarchical structure of LM microdroplets that forms a conductive network(i.e.,LMMN)when *** strain-history behavior of LMMNs allows conductivity enhancement up to 2.37×10^(6) S m^(-1) in response to increased tensile *** adjusting the number of LM layers in LBL deposition,the gauge factor(0.2≤GF≤1),the linearity,and the sheet resistance of LMMN films can be easily controlled,providing high potentials in various applications,including skin-mountable circuits,energy harvesters,and soft artificial skin.

关键词： strain networks conductivity

来源：评论

学校读者我要写书评

暂无评论

Design and Development of IoT Oriented Solar Powered Smart Home Controlling Mechanism

Design and Development of IoT Oriented Solar Powered Smart H...

引用

2023 International Conference on Sustainable Communication Networks and Application, ICSCNA 2023

作者： Tamezheneal, R. Kajendran, K. Vinitha, J.C. Hemalatha, S. Aruna, K.B. Pandi, V. Samuthira Sri Sai Ram Engineering College Department of Electronics and Communication Engineering Tamil Nadu Chennai India Panimalar Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India Rajalakshmi Engineering College Department of Electrical and Electronics Engineering Tamil Nadu Chennai India Prince Shri Venkateshwara Padmavathy Engineering College Department of Electrical and Electronics Engineering Tamil Nadu Chennai India S.A.Engineering College Department of Computer Science and Engineering Tamil Nadu Chennai India Chennai Institute of Technology Centre for Advanced Wireless Integrated Technology Tamil Nadu Chennai India

ISBN: (纸本)9798350313987

This research study addresses the need for renewable energy in residence by discussing the development and building of a solar assisted automation system for homes equipped with a wireless Internet of Things (IoT) enabled technology. The photovoltaic array powers the intelligent home using a highly efficient Maximum Power Point Tracking (MPPT) control system. The research's design, analysis, and methodology are all presented here, along with the study's findings on the market. The primary building blocks of a solar UPS are a solar panel and a custom-designed inverter circuit. The inverter circuit was designed in accordance with solar panel specs and requirements. Many other circuits served as inspiration for the present circuit's redesign. The development experts of currently available backup power supplies have also been consulted in order to plan for prospective replacements should a component fail or become unavailable. In this post, we'll look at some of the several ways a solar-powered UPS may be built and how its features might work. This suggests that solar UPSs may soon be able to compete with and even outperform their electrical counterparts. The key components of the design are an outside solar panel equipped with solar cells to convert solar energy towards electrical power and a power conversion circuit to convert the DC current into AC current for usage in household appliances. Two Energy throw electrical parts and one Arduino UNO controller with sensors were used in the development of this prototype automation system. In this paper, we propose developing and implementing a residence energy control system to help individuals and families keep tabs on their energy consumption and adjust their habits accordingly. The purpose of this project is to design, develop, and implement a residential energy optimization system that enables sensing, control, and intelligent algorithms to help clients learn more about and control their consumption of energy. © 2023 IE

关键词： Battery Power Source Home Automation Internet of Things Inverter IoT Photovoltaic PV Array Renewable Energy Solar Power

来源：评论

学校读者我要写书评

暂无评论

Neural Network Implementation for Battery Failure Detection in Electric Vehicles

Neural Network Implementation for Battery Failure Detection ...

引用

2023 International Conference on Innovative Computing, Intelligent Communication and Smart electrical Systems, ICSES 2023

作者： Vijitha, S. Hebri, Dheeraj Singh, Sangeeta Manohara, M. Ishrat, Mohammad Joseph, D Raja Vels Institute of Science Technology & Advanced Studies Department of Computer Science and Engineering Tamil Nadu Chennai600117 India Srinivas Institute of Technology Department of Master of Computer Application Karnataka Mangaluru574143 India JSS Academy of Technical Education Department of Electrical Engineering Uttar Pradesh Noida201301 India Mohan Babu University School of Engineering Andhra Pradesh Tirupati517102 India KoneruLakshmaiah Education Foundation Department of Computer Science and Engineering Guntur Andhra Pradesh Vaddeswaram522502 India Hindustan Institute of Technology and Science School of Aeronautical Sciences Tamil Nadu Chennai603103 India

ISBN: (纸本)9798350319200

Soil destruction and global warming have recently come to the forefront of discussion in industrialised nations as governments strive to accommodate the rising demands of their citizens. The demand for zero-emission electric cars has increased as a result of international competitiveness and technological advancements (EVs). Concerns about the high voltage of increasing numbers of electric cars are shared by an increasing number of individuals. Since the system of batteries may be at responsible for over 30% of EV accidents, it is vital to investigate how problems with LIBs are recognized. Many different kinds of problems make it hard to fix EV's LIB. Fast and precise diagnosis of battery pack problems is crucial for the immediate and ongoing safety of EV operation. Utilizing models of neural networks like multiple hidden layers (MLP) or nonlinear activation functions, this research provides a mechanism for identifying and fixing problems with electric vehicle batteries (RBF). To generate information for the BFD system, battery simulations are done in MATLAB. Accuracy may be improved by performing pre-processing steps on the information once it has been generated. After training, the two models are put to the test to see how well they perform. There are both positive and negative measures that may be used to determine which model is the best. © 2023 IEEE.

关键词： Accuracy Battery Electric Vehicle Fault Model Neural Network

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：