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

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

Digital-Twin Architecture of a Spiking Neuron using Carbon Nanotube Field Effect Transistors

Digital-Twin Architecture of a Spiking Neuron using Carbon N...

引用

IEEE International Conference on Performance, Computing and Communications (IPCCC)

作者： Shelby Williams Prosen Kirtonia Kasem Khalil Magdy Bayoumi Center for Advanced Computer Studies Univ. of Louisiana at Lafayette Lafayette LA USA Dept. of Electrical and Computer Engr. University of Louisiana at Lafayette Lafayette LA USA Department of Electrical and Computer Engineering Univ. of Mississippi Oxford MS USA Department of Electrical Engineering Assiut University Assiut Egypt

ISBN: (数字)9798350367942

ISBN: (纸本)9798350367959

The rapid advancements in nanotechnology and neuromorphic engineering have paved the way for developing high-performance computational models that mimic biological neural networks. This paper presents a novel digital-twin architecture for a spiking neuron, leveraging the exceptional properties of Carbon Nanotube Field Effect Transistors (CNFETs). The proposed architecture aims to emulate the dynamic behavior of biological neurons with high fidelity, providing a robust platform for simulation and analysis. By integrating CNFETs, we achieve significant improvements in lowest-energy usage and highest-spiking frequency, compared to traditional silicon-based technologies. Furthermore, the digital twin not only replicates the electrical characteristics of a spiking neuron but also facilitates advanced functionalities such as adaptive learning, fault tolerance, and self-optimization. Experimental results demonstrate the potential of CNFET-based neurons in enhancing the performance of neuromorphic systems, offering promising applications in artificial intelligence, cognitive computing, and complex system modeling. Integrating digital twin technology with CNFETs allows for precise control and manipulation of spiking behavior, enabling the development of more sophisticated and efficient neural models. This research underscores the transformative impact of combining digital twin technology with cutting-edge nanomaterials, setting a new benchmark for future explorations in the field. The findings highlight the importance of continued research and development in this area, as it holds the promise of revolutionizing the way we design and implement neuromorphic systems, pushing the boundaries of what is possible in artificial intelligence and beyond.

关键词： Training Energy consumption Neuromorphic engineering Computational modeling Neurons computer architecture CNTFETs Digital twins Optimization Biological neural networks

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

Synthesizing Supervisors with a Minimum Control Base for Discrete-Event Systems

Synthesizing Supervisors with a Minimum Control Base for Dis...

引用

2022 American Control Conference, ACC 2022

作者： Hugh Moulton, Richard Scott, Stephen H. Rudie, Karen Queen's University Department of Electrical and Computer Engineering Kingston Canada Queen's University Department of Biomedical and Molecular Science The Centre for Neuroscience Studies and the Department of Medicine Kingston Canada Queen's University Department of Electrical and Computer Engineering The School of Computing and the Ingenuity Labs Research Institute Kingston Canada

ISBN: (数字)9781665451963

ISBN: (纸本)9781665451963

Controlling a discrete-event system commonly entails synthesizing a supervisor to ensure that the plant's closed-loop behaviour respects a certain specification. In the traditional approach to this problem, if the desired behaviour is not controllable then the specification's supremal controllable sublanguage is enforced instead. Here we invert the problem and formulate the Minimum Control Base Problem, with the goal of finding the minimum set of controllable events that guarantees controllability for the desired behaviour. We show that the sets of controllable events that maintain controllability for the desired behaviour form a complete lattice with respect to subset inclusion and that there is therefore a minimum capability supervisor for any desired sublanguage of the plant's behaviour. We apply our techniques to the Small Factory problem and discuss further applications including systems design, dynamic discrete-event systems, and biological systems. © 2022 American Automatic Control Council.

关键词： Supervisory personnel

来源：评论

学校读者我要写书评

暂无评论

Gastrointestinal Disease Prediction Using Transfer Learning

Gastrointestinal Disease Prediction Using Transfer Learning

引用

International Conference on computer Vision and Internet of Things 2023, ICCVIoT 2023

作者： Sujatha, R. Helen, D. Hemamalini, U. Divya, V. Dharshini, A. Priya School of Information Technology & Engineering Vellore Institute of Technology Tamil Nadu Vellore India Department of Computer Applications Faculty of Science and Humanities SRM Institute of Science and Technology Kattankulathur Chennai India Department of Information Technology VELS Institute of Science Technology and Advanced Studies Pallavaram Chennai India

ISBN: (纸本)9781839539848

According to the Global Cancer Observatory's 2018 estimations, gastrointestinal cancer is the third most common cause of cancer deaths and the fifth most common cause of being diagnosed with cancer worldwide. Diagnosis is crucial, and gastroscopy is used to detect stomach cancer early to enhance patient survival. This study proposed a Deep Learning based computer-Aided Diagnostics (CADx) method to identify gastroscopy disease. The dataset is trained with an adversarial training technique. The proposed approach uses the deep convolution neural network based on VGG16, VGG19, and InceptionV3. The dataset is trained with an adversarial training technique. The Inception V3 has the best accuracy among them, with an accuracy in the training of 94.44% and a validation accuracy of 84.75%, with a minor loss compared to VGG16 and VGG19 models. © The Institution of engineering & Technology 2023.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Leveraging Artificial Intelligence in computer Science to Manage Stress and Anxiety: Applications and Innovations

Leveraging Artificial Intelligence in Computer Science to Ma...

引用

Advances in Computation, Communication and Information Technology (ICAICCIT), International Conference on

作者： Ketan Mittal Shikha Ronak Sharma Jeevesh Kumar Attri Kritika Taneja Department of Computer Science and Engineering Manav Rachna International Institute of Research and Studies Faridabad India Department of electrical and electronics engineering Manav Rachna International Institute of Research and Studies Faridabad India

ISBN: (数字)9798331541217

ISBN: (纸本)9798331541224

This study explores the effectiveness, ethical considerations, and demographic influences of AI-based interventions in managing stress and anxiety. AI technologies, including Machine Learning, Natural Language Processing (NLP), and Biometric Monitoring, have shown promising results in reducing stress and anxiety across diverse populations. Machine Learning algorithms excel in predictive analytics, enabling early detection and intervention, while NLP tools offer real-time cognitive-behavioural therapy (CBT) and emotional support through AI-powered chatbots. Biometric Monitoring provides objective physiological data, further enhancing the precision of stress management strategies. However, the effectiveness of these interventions is influenced by demographic variables such as age, gender, socio-economic status, and cultural background, with younger, tech-savvy users and those of higher socio-economic status showing greater engagement and benefit. Also, the mobile application named “sahayya” has been discussed along with its merits. Discussing how technology can be put to better use.

关键词： Biometrics Ethics Technological innovation Anxiety disorders Machine learning Real-time systems Socioeconomics Sustainable development Predictive analytics Monitoring

来源：评论

学校读者我要写书评

暂无评论

Depth-Threshold Circuits vs. Depth-(+1) AND-OR Trees 55

Depth-Threshold Circuits vs. Depth-(+1) AND-OR Trees

引用

55th Annual ACM Symposium on Theory of Computing, STOC 2023

作者： Hatami, Pooya Hoza, William M. Tal, Avishay Tell, Roei Ohio State University Department of Computer Science and Engineering ColumbusOH United States University of California Simons Institute for the Theory of Computing BerkeleyCA United States University of California Department of Electrical Engineering and Computer Sciences BerkeleyCA United States Institute for Advanced Study School of Mathematics PrincetonNJ United States Rutgers University DIMACS PiscatawayNJ United States

ISBN: (纸本)9781450399135

For any n ,• and d = o(loglog(n)), we prove that there is a Boolean function F on n bits and a value γ= 2-(d) such that F can be computed by a uniform depth-(d + 1) AC0 circuit with O(n) wires, but F cannot be computed by any depth-d TC0 circuit with n1 +-3 wires. This bound matches the current state-of-the-art lower bounds for computing explicit functions by threshold circuits of depth d > 2, which were previously known only for functions outside AC0 such as the parity function. Furthermore, in our result, the AC0 circuit computing F is a monotone∗read-once formula∗(i.e., an AND-OR tree), and the lower bound holds even in the average-case setting with respect to advantage n-3. At a high level, our proof strategy combines two prominent approaches in circuit complexity from the last decade: The celebrated∗random projections∗method of Håstad, Rossman, Servedio, and Tan (J. ACM 2017), which was previously used to show a tight average-case depth hierarchy for AC0;and the line of works analyzing the effect of∗random restrictions∗on threshold circuits. We show that under a modified version of Håstad, Rossman, Servedio, and Tan's projection procedure, any depth-d threshold circuit with n1 +-3 wires simplifies to a near-trivial function, whereas an appropriately parameterized AND-OR tree of depth d + 1 maintains structure. © 2023 Owner/Author.

关键词： Wire

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：