检索结果-内蒙古大学图书馆

Preface: Security and safety in artificial intelligence

Security and Safety 2024年第4期3卷 4-5页

作者： Hao Zhang Yu-Gang Jiang Claudio Melchiorri Gerhard Rigoll Department of Control Science and Engineering Tongji UniversityShanghai 200092China Shanghai Institute of Intelligent Science and Technology Shanghai 201210China School of Computer Science Fudan UniversityShanghai 200433China Department of Electrical Electronic and Information EngineeringUniversity of BolognaBologna 40136Italy Institute for Human-Machine Communication Technical University of MunichMunich 80539Germany

This special topic centers on cutting-edge advancements in the security and safety of artificial intelligence(AI),with a focus on critical applications across domains such as autonomous systems,federated learning,and network *** rapid evolution of AI algorithms,enabled by advances in hardware and software,has led to transformative applications but also revealed significant vulnerabilities and security risks.

关键词： artificial hardware autonomous

来源：评论

学校读者我要写书评

暂无评论

Custom-made Near Infrared Spectroscope as a Tool for Obtaining Information Regarding the Brain Condition

Custom-made Near Infrared Spectroscope as a Tool for Obtaini...

引用

International Conference on Methods and Models in Automation and Robotics (MMAR)

作者： Anna Wieczorek Edward Jacek Gorzelańczyk Mariusz Pelc Saravanakumar Duraisamy Luis A. Leiva Aleksandra Kawala-Sterniuk Faculty of Electrical Engineering Automatic Control and Informatics Opole University of Technology Opole Poland Institute of Philosophy Kazimierz Wielki University Bydgoszcz Poland Department of Computer Science University of Luxembourg Luxembourg Luxembourg

We can obtain valuable information about the human brain using functional Near Infrared Spectroscopy (fNIRS). This paper describes the theoretical basis associated with this neuroimaging method through a custom-made prototype of a single-channel fNIRS device. The optodes were soldered to a milled Printed Circuit Board (PCB) and enclosed in a 3D printed housing. Using this fNIRS device, we performed a preliminary study to measure emotional responses from participants. Our results suggest that fNIRS allows for accurate measurement of emotions evoked by positive and negative images.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Game Theory for Autonomy: From Min-Max Optimization to Equilibrium and Bounded Rationality Learning

Game Theory for Autonomy: From Min-Max Optimization to Equil...

引用

American control Conference (ACC)

作者： Kyriakos G. Vamvoudakis Filippos Fotiadis João P. Hespanha Raphael Chinchilla Guosong Yang Mushuang Liu Jeff S. Shamma Lacra Pavel Daniel Guggenheim School of Aerospace Engineering Georgia Institute of Technology Atlanta GA USA Center for Control Dynamical Systems and Computation University of California Santa Barbara CA Department of Electrical and Computer Engineering Rutgers University Piscataway NJ USA Department of Mechanical and Aerospace Engineering University of Missouri Columbia MO USA Department of Industrial and Enterprise Systems Engineering University of Illinois at Urbana-Champaign IL USA Department of Electrical and Computer Engineering University of Toronto Canada

Finding Nash equilibria in non-cooperative games can be, in general, an exceptionally challenging task. This is owed to various factors, including but not limited to the cost functions of the game being nonconvex/nonconcave, the players of the game having limited information about one another, or even due to issues of computational complexity. The present tutorial draws motivation from this harsh reality and provides methods to approximate Nash or min-max equilibria in non-ideal settings using both optimization- and learning-based techniques. The tutorial acknowledges, however, that such techniques may not always converge, but instead lead to oscillations or even chaos. In that respect, tools from passivity and dissipativity theory are provided, which can offer explanations about these divergent behaviors. Finally, the tutorial highlights that, more frequently than often thought, the search for equilibrium policies is simply vain; instead, bounded rationality and non-equilibrium policies can be more realistic to employ owing to some players’ learning imperfectly or being relatively naive – "bounded rational." The efficacy of such plays is demonstrated in the context of autonomous driving systems, where it is explicitly shown that they can guarantee vehicle safety.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design of Nanorobots for an Early Detection of Alzhimer's Disease

Design of Nanorobots for an Early Detection of Alzhimer's Di...

引用

IEEE SSD International Multi-Conference on Systems, Signals and Devices

作者： Yosra Ben Fadhel Khawla Kachroudi Achraf Derbel Hedi Trabelsi Nabil Derbel University of Tunis El Manar Higher Institute of Medical Technologies Tunisia Departement of Computer Systems Eng. Mediterranean Institute of Technology South Mediterranean University Tunisia University of Sfax National Engineering School of Sfax Control & Energy Management Laboratory Tunisia

ISBN: (数字)9798331542726

ISBN: (纸本)9798331542733

In this study, we propose a novel nanorobot model for the early detection of Alzheimer's disease. As a first step, we explored the polymorphism of the TREM2 gene's exons to assess its association with Alzheimer's. Our case-control study involved 124 Tunisian participants-64 Alzheimer's patients and 60 age-matched controls, averaging 67 years. Each participant underwent neurological evaluation, neuropsychological testing, brain imaging, and molecular analysis. Using Polymerase Chain Reaction (PCR) and sequencing techniques, we identified the rs2234253 variant in exon 2 and a novel intronic variant in intron 4, both of which were significantly correlated with Alzheimer's risk. Based on these genetic findings, we designed a nanorobot capable of detecting early biomarkers of Alzheimer's disease, such as amyloid plaques and tau tangles. The nanorobots are approximately 100 nm in size, enabling them to navigate the blood-brain barrier and specifically target regions of the brain affected by Alzheimer's pathology. They are constructed from biocompatible materials, such as gold nanoparticles and silica, and functionalized with surface receptors that selectively bind to Alzheimer's-related biomarkers. Equipped with nanosensors, the nanorobots are designed to detect binding events and transmit data to an external monitoring system in real time, facilitating early diagnosis and continuous monitoring of disease progression. These technological advancements offer a promising approach to enhancing Alzheimer's detection and improving patient out-comes.

关键词： Pathology Sequential analysis Biomarkers Real-time systems Safety Polymers Alzheimer's disease Monitoring Silicon dioxide Testing

来源：评论

学校读者我要写书评

暂无评论

Estimating the Reliability of a DApps-Based Files Storage System

Estimating the Reliability of a DApps-Based Files Storage Sy...

引用

International Russian Automation Conference (RusAutoCon)

作者： Obadah Hammoud Ivan A. Tarkhanov Engineering Cybernetics Research Faculty National University of Science and Technology Moscow Russia Federal Research Center “Computer Science and Control” of Russian Academy of Sciences State Academic University for Humanities Moscow Russia

One of the key features of blockchain is high reliability, due to its high redundancy nature. While creating many replications across nodes serves well for storing relatively small data entries, this cannot be used with big files, as it might be impossible to replicate many huge files across many nodes. Here we present a DApps-based system that can lead to improving the total reliability of distributed files storage systems by managing the internal processes using DApps instead of a classical centralized load balancer. For the same reason, known reliability calculation methods for distributed file storage systems are not suitable for assessing the reliability of DApps-based systems. They do not take into account the automatic recovery time of files. In this article, we will deduce the reliability method for DApps-based system, then compare the resulting reliability with other existing systems, and discuss the benefits gained in total.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Computational issues in Optimization for Deep networks

arXiv

引用

arXiv 2024年

作者： Coppola, Corrado Papa, Lorenzo Boresta, Marco Amerini, Irene Palagi, Laura Sapienza University of Rome Department of Computer Control and Management Engineering Antonio Ruberti Via Ariosto 25 Roma Italy Istituto di Analisi dei Sistemi ed Informatica Antonio Ruberti - CNR Via dei Taurini Roma Italy

The paper aims to investigate relevant computational issues of deep neural network architectures with an eye to the interaction between the optimization algorithm and the classification performance. In particular, we aim to analyze the behaviour of state-of-the-art optimization algorithms in relationship to their hyperparameters setting in order to detect robustness with respect to the choice of a certain starting point in ending on different local solutions. We conduct extensive computational experiments using nine open-source optimization algorithms to train deep Convolutional Neural Network architectures on an image multi-class classification task. Precisely, we consider several architectures by changing the number of layers and neurons per layer, in order to evaluate the impact of different width and depth structures on the computational optimization performance. © 2024, CC BY-NC-ND.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Lazy Probabilistic Roadmaps Revisited

arXiv

引用

arXiv 2022年

作者： Ramirez, Miquel Selvaratnam, Daniel Manzie, Chris School of Electric and Electronic Engineering University of Melbourne Australia Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden

This paper describes a revision of the classic Lazy Probabilistic Roadmaps algorithm (Lazy PRM), that results from pairing PRM and a novel Branch-and-Cut (BC) algorithm. Cuts are dynamically generated constraints that are imposed on minimum cost paths over the geometric graphs selected by PRM. Cuts eliminate paths that cannot be mapped into smooth plans that satisfy suitably defined kinematic constraints. We generate candidate smooth plans by fitting splines to vertices in minimum-cost path. Plans are validated with a recently proposed algorithm that maps them into finite traces, without need to choose a fixed discretization step. Trace elements exactly describe when plans cross constraint boundaries modulo arithmetic precision. We evaluate several planners using our methods over the recently proposed BARN benchmark, and we report evidence of the scalability of our approach. Copyright © 2022, The Authors. All rights reserved.

关键词： Combinatorial optimization

来源：评论

学校读者我要写书评

暂无评论

Privacy-Aware Crowd Monitoring and WiFi Traffic Emulation for Effective Crisis Management

Privacy-Aware Crowd Monitoring and WiFi Traffic Emulation fo...

引用

International Conference on Information and Communication Technologies for Disaster Management (ICT-DM)

作者： Riccardo Rusca Alex Carluccio Diego Gasco Paolo Giaccone Department of Control and Computer Engineering Politecnico di Torino Italy Consorzio Nazionale Interuniversitario per le Telecomunicazioni (CNIT) Parma (PR) Italy Department of Electronics and Telecommunications Politecnico di Torino Italy

Estimating the number of people in a given area, denoted as “people counting” process, plays a vital role in crisis management and disaster response, enabling accurate monitoring of crowd dynamics and facilitating effective decision-making. In this work, we focus on WiFi fingerprint technique which exploits the MAC address of the mobile devices as proxy for people counting. Due to the European GDPR regulation and the strict actions undertaken by the major smart-devices vendors to enhance users' privacy (e.g., MAC randomization), most of the techniques investigated in the past must be redesigned and rethought. Here, we propose an ad-hoc WiFi traffic generator, tailored to emulate a realistic behaviour of the WiFi cards and to provide the ground truth for the counting algorithms. Furthermore, we propose a technique for crowd monitoring that leverages Bloom filters to guarantee a formal “deniability” property, which preserves users' privacy. Our solution is also compatible with trajectory-based crowd monitoring.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Enhancing Effluent Quality Predictions in Wastewater Treatment with LSTM Neural Network

Enhancing Effluent Quality Predictions in Wastewater Treatme...

引用

International Conference on System Theory, control, and Computing (ICSTCC)

作者： Daniel Voipan Iulian Vasiliev Larisa Diaconu Andreea-Elena Voipan Marian Barbu Department of Computer Science and Information Technology "Dunărea de Jos" University of Galați Galați Romania Department of Automatic Control and Electrical Engineering "Dunărea de Jos" University of Galați Galați Romania

ISBN: (数字)9798350364293

ISBN: (纸本)9798350364309

This research paper delves into the application of Long Short-Term Memory (LSTM) neural networks within the Benchmark Simulation Model No. 2 (BSM2) to enhance the predictability and efficiency of wastewater treatment processes. The study aims to develop advanced predictive models that can simulate the dynamics of wastewater treatment more accurately and adjust operational strategies dynamically. By integrating LSTM networks, the research enables continuous prediction of Effluent Quality Index (EQI) variables under stochastic and deterministic scenarios, thereby improving the accuracy and efficiency of predicting pollutant levels. The research uses an LSTM model to learn from a comprehensive dataset derived from historical simulations of BSM2, where key parameters such as the oxygen transfer coefficient (K L a) are systematically varied to measure their impact on effluent quality. The LSTM's capability to handle complex, nonlinear data and its adaptability to time series forecasting significantly enhances model performance, offering a robust tool for real-time decision-making and process optimization in wastewater treatment facilities. This approach not only improves the accuracy and efficiency of predicting pollutant levels but also supports environmental compliance and operational sustainability, making it a valuable tool for environmental engineers and professionals in the field of wastewater treatment.

关键词： Adaptation models Accuracy Time series analysis Stochastic processes Effluents Predictive models Real-time systems Wastewater Wastewater treatment Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Image Definition Evaluation Function Based on Improved Maximum Local Variation and Focusing Window Selection 1

引用

6th International Conference on Data Mining and Big Data, DMBD 2021

作者： Li, Shiyun Chen, Jian Wan, Jiaze Li, Zuoyong Lin, Li School of Electronic Electrical Engineering and Physics Fujian University of Technology Xueyuan Road Fujian Fuzhou350118 China College of Computer and Control Engineering Minjiang University No. 200 Xiyuangong Road Fujian Fuzhou350121 China Fujian Provincial Key Laboratory of Information Processing and Intelligent Control Minjiang University Fuzhou350121 China

ISBN: (数字)9789811675027

ISBN: (纸本)9789811675010

Aiming at the problem that commonly used image definition evaluation functions in the focusing process are sensitive to noise, we propose a new image definition evaluation function based on improved maximum local variation and focusing window selection. Firstly, the focusing window is selected by gradient accumulation of a 4-directional Scharr operator in order to reduce the calculation complexity and improve the accuracy of evaluation results. Secondly, an improved 3-neighbors method based on the maximum local variation is proposed to decrease the change in scores for noisy images. Finally, the standard deviation of the improved maximum local variation distribution is used as the measure of clarity. The experimental results show that compared with the method using maximum local variation, the proposed method has better unbiasedness and sensitivity. Compared with the commonly used evaluation functions, the proposed method has better noise immunity and high sensitivity. Compare with other no-reference image quality assessment algorithms, it has better monotonicity, unimodality, unbiasedness, sensitivity and real-time performance as well. The proposed method is suitable for the fine focusing stage with high real-time performance. © 2021, Springer Nature Singapore Pte Ltd.

关键词： computer vision

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：