检索结果-内蒙古大学图书馆

Forgive and forget: Self-stabilizing swarms in spite of Byzantine robots

学校读者我要写书评

暂无评论

Forgive and forget: Self-stabilizing swarms in spite of Byza...

作者： Ashkenazi, Yotam Dolev, Shlomi Kamei, Sayaka Ooshita, Fukuhito Wada, Koichi Department of Computer Science Ben-Gurion University of the Negev Beersheba Israel Graduate School of Advanced Science and Engineering Hiroshima University Hiroshima Japan Graduate School of Science and Technology Nara Institute of Science and Technology Nara Japan Department of Applied Informatics Faculty of Science and Engineering Hosei University Tokyo Japan

In this article, we consider the case in which a swarm of robots collaborates in a mission, where a few of the robots behave maliciously. These malicious Byzantine robots may be temporally or constantly controlled by an adversary. The scope is synchronized full information robot operations, where a robot that does not follow the program/policy of the swarm is immediately identified and can be remembered as Byzantine. As robots may be suspected of being Byzantine due to benign temporal malfunctions, it is imperative to forgive and forget, otherwise, a robot cannot assume collaborative actions with any other robot in the swarm. Still, remembering for a while may facilitate a policy of surrounding, isolating and freezing the movement of the misbehaving robots, by several robots, allowing the rest to perform the swarm task with no intervention. We demonstrate the need to periodically forgive and forget to realize swarm several tasks including patrolling/cleaning in the presence of possible Byzantine robots. The policy for achieving the task consists of blocking the movement of the Byzantine robot(s) by some of the robots, while the rest patrol/clean the plane. © 2020 John Wiley & Sons, Ltd.

关键词： Robots

Awake at the Wheel: Enhancing Automotive Safety through EEG-Based Fatigue Detection

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Siddhad, Gourav Dey, Sayantan Roy, Partha Pratim Iwamura, Masakazu Department of Computer Science and Engineering Indian Institute of Technology Uttarakhand Roorkee247667 India Department of Core Informatics Graduate School of Informatics Osaka Metropolitan University Sakai Osaka599-8531 Japan

Driver fatigue detection is increasingly recognized as critical for enhancing road safety. This study introduces a method for detecting driver fatigue using the SEED-VIG dataset, a well-established benchmark in EEG-based vigilance analysis. By employing advanced pattern recognition technologies, including machine learning and deep neural networks, EEG signals are meticulously analyzed to discern patterns indicative of fatigue. This methodology combines feature extraction with a classification framework to improve the accuracy of fatigue detection. The proposed NLMDA-Net reached an impressive accuracy of 83.71% in detecting fatigue from EEG signals by incorporating two novel attention modules designed specifically for EEG signals, the channel and depth attention modules. NLMDA-Net effectively integrate features from multiple dimensions, resulting in improved classification performance. This success stems from integrating temporal convolutions and attention mechanisms, which effectively interpret EEG data. Designed to capture both temporal and spatial characteristics of EEG signals, deep learning classifiers have proven superior to traditional methods. The results of this study reveal a substantial enhancement in detection rates over existing models, highlighting the efficacy of the proposed approach for practical applications. The implications of this research are profound, extending beyond academic realms to inform the development of more sophisticated driver assistance systems. Incorporating this fatigue detection algorithm into these systems could significantly reduce fatigue-related incidents on the road, thus fostering safer driving conditions. This paper provides an exhaustive analysis of the dataset, methods employed, results obtained, and the potential real-world applications of the findings, aiming to contribute significantly to advancements in automotive safety. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep neural networks

A Hybrid Model of Query Expansion using Word2Vec

学校读者我要写书评

暂无评论

A Hybrid Model of Query Expansion using Word2Vec

2021 IEEE International Conference on technology, Research, and Innovation for Betterment of Society, TRIBES 2021

作者： Shukla, Abhishek Kumar Das, Sujoy Maulana Azad National Institute of Technology Department of Mathematics Bio-informatics and Computer Applications Bhopal India

ISBN: (纸本)9781665433426

Query expansion method is one of the most popular methods to reduce the vocabulary mismatch in Information retrieval tasks. Traditional methods of query expansion that use Pseudo relevance feedback are not much efficient for document retrieval from a large collection of documents. In the proposed method we will try to minimize the vocabulary mismatch using a hybrid method of query expansion using the word embedding technique. The proposed method uses both Word2Vec and a local method to predict the expansion terms. The mean average precision of the proposed method is 0.2992. The proposed model also compares with the original query and BM25 model. © 2021 IEEE.

关键词： Information retrieval

TransAxx: Efficient Transformers with Approximate Computing

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Danopoulos, Dimitrios Zervakis, Georgios Soudris, Dimitrios Henkel, Jörg The School of Electrical and Computer Engineering National Technical University of Athens Athens15780 Greece The Department of Computer Engineering & Informatics University of Patras Patras Greece Karlsruhe Institute of Technology Karlsruhe76131 Germany

Vision Transformer (ViT) models which were recently introduced by the transformer architecture have shown to be very competitive and often become a popular alternative to Convolutional Neural Networks (CNNs). However, the high computational requirements of these models limit their practical applicability especially on low-power devices. Current state-of-the-art employs approximate multipliers to address the highly increased compute demands of DNN accelerators but no prior research has explored their use on ViT models. In this work we propose TransAxx, a framework based on the popular PyTorch library that enables fast inherent support for approximate arithmetic to seamlessly evaluate the impact of approximate computing on DNNs such as ViT models. Using TransAxx we analyze the sensitivity of transformer models on the ImageNet dataset to approximate multiplications and perform approximate-aware finetuning to regain accuracy. Furthermore, we propose a methodology to generate approximate accelerators for ViT models. Our approach uses a Monte Carlo Tree Search (MCTS) algorithm to efficiently search the space of possible configurations using a hardware-driven hand-crafted policy. Our evaluation demonstrates the efficacy of our methodology in achieving significant trade-offs between accuracy and power, resulting in substantial gains without compromising on performance. Copyright © 2024, The Authors. All rights reserved.

关键词： Economic and social effects

TSO-DSO Interaction: Privacy-Preserving Optimal Power Flow with Distributed Generators Using a Machine Learning-Based Approach

学校读者我要写书评

暂无评论

TSO-DSO Interaction: Privacy-Preserving Optimal Power Flow w...

IEEE PES Asia-Pacific Power and Energy Engineering Conference (APPEEC)

作者： Burak Dindar Can Berk Saner Hüseyin Kemal Çakmak Veit Hagenmeyer Institute for Automation and Applied Informatics Karlsruhe Institute of Technology Germany Department of Electrical and Computer Engineering National University of Singapore Singapore

ISBN: (数字)9798350318098

ISBN: (纸本)9798350318104

The integration of distributed generators (DGs) into the electrical grid has introduced new dimensions in power system management: Enhancing efficiency and operational flexibility of the grid requires taking into account the DGs located at the distribution level in dispatch decisions, while also considering the operational constraints of both distribution and transmission levels. However, the centralization of cooperation between transmission system operators (TSOs) and distribution system operators (DSOs) is troublesome due to privacy concerns of both parties. In present paper, we introduce a Machine Learning-Based Privacy-Preserving Optimal Power Flow (MLB-PP-OPF) framework. This method enables the seamless inclusion of DGs at the distribution level in optimal power flow calculations, all while adhering to the operational limits of both systems and maintaining data privacy. The proposed approach leverages three machine learning models to map the distribution system variables to active and reactive power flows at the point of common coupling, and to determine the feasible operating region of the distribution system in a privacy-preserving manner. Comparative case studies, performed on the coupled IEEE 30-bus transmission and 33-bus distribution test systems, demonstrate that the results achieved using MLB-PP-OPF align almost perfectly with those obtained through classical OPF, while maintaining data privacy.

关键词： Couplings Data privacy Reactive power Privacy Machine learning Generators Data models

Enhancing EEG Signal-Based Emotion Recognition with Synthetic Data: Diffusion Model Approach

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Siddhad, Gourav Iwamura, Masakazu Roy, Partha Pratim Department of Computer Science and Engineering Indian Institute of Technology Uttarakhand Roorkee247667 India Department of Core Informatics Graduate School of Informatics Osaka Metropolitan University Sakai Osaka599-8531 Japan

Emotions are crucial in human life, influencing perceptions, relationships, behaviour, and choices. Emotion recognition using Electroencephalography (EEG) in the Brain-computer Interface (BCI) domain presents significant challenges, particularly the need for extensive datasets. This study aims to generate synthetic EEG samples that are similar to real samples but are distinct by augmenting noise to a conditional denoising diffusion probabilistic model, thus addressing the prevalent issue of data scarcity in EEG research. The proposed method is tested on the DEAP dataset, showcasing upto 4.21% improvement in classification performance when using synthetic data. This is higher compared to the traditional GAN-based and DDPM-based approaches. The proposed diffusion-based approach for EEG data generation appears promising in refining the accuracy of emotion recognition systems and marks a notable contribution to EEG-based emotion recognition. Our research further evaluates the effectiveness of state-of-the-art classifiers on EEG data, employing both real and synthetic data with varying noise levels. © 2024, CC BY.

关键词： Emotion Recognition

Sensorimotor Devices: Coupling Sensing and Actuation to Augment Bodily Experience

学校读者我要写书评

暂无评论

Sensorimotor Devices: Coupling Sensing and Actuation to Augm...

2025 CHI Conference on Human Factors in Computing Systems, CHI EA 2025

作者： Strohmeier, Paul Vidal, Laia Turmo Vega, Gabriela Reed, Courtney N. Mazursky, Alex AliAbbasi, Easa Tajadura-Jiménez, Ana Steimle, Jürgen Max Planck Institute for Informatics Saarland Informatics Campus Saarbrücken Germany KTH Royal Institute of Technology Stockholm Sweden Sensorimotor Interaction Group Max Planck Institute for Informatics Saarland Informatics Campus Saarbrücken Germany Institute for Digital Technologies Loughborough University London London United Kingdom University of Chicago ChicagoIL United States Max Planck Institute for Informatics Saarbrücken Germany Department of Computer Science and Engineering Universidad Carlos III de Madrid Leganés Madrid Spain Saarland University Saarland Informatics Campus Saarbrücken Germany

ISBN: (纸本)9798400713958

An emerging space in interface research is wearable devices that closely couple their sensing and actuation abilities. A well-known example is MetaLimbs [39], where sensed movements of the foot are directly mapped to the actuation of supernumerary robotic limbs. These systems are different from wearables focused on sensing, such as fitness trackers, or wearables focused on actuation, such as VR headsets. They are characterized by tight coupling between the user’s action and the resulting digital feedback from the device, in time, space, and mode. The properties of this coupling are critical for the user’s experience, including the user’s sense of agency, body ownership, and experience of the surrounding world. Understanding such systems is an open challenge, which requires knowledge not only of computer science and HCI, but also Psychology, Physiology, Design, Engineering, Cognitive Neuroscience, and Control Theory. This workshop aims to foster discussion between these diverse disciplines and to identify links and synergies in their work, ultimately developing a common understanding of future research directions for systems that intrinsically couple sensing and action. © 2025 Copyright held by the owner/author(s).

关键词： Feedback control

Benchmarking changepoint detection algorithms on cardiac time series

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Cakmak, Ayse Selen Reinertsen, Erik Nemati, Shamim Clifford, Gari D. Department of Biomedical Informatics Emory University United States School of Electrical and Computer Engineering Georgia Institute of Technology United States Department of Biomedical Informatics University of California at San Diego United States

The pattern of state changes in a biomedical time series can be related to health or disease. This work presents a principled approach for selecting a changepoint detec- tion algorithm for a specific task, such as disease classification. Eight key algorithms were compared, and the performance of each algorithm was evaluated as a function of temporal tolerance, noise, and abnormal conduction (ectopy) on realistic artificial cardiovascular time series data. All algorithms were applied to real data (cardiac time series of 22 patients with REM-behavior disorder (RBD) and 15 healthy controls) using the parameters selected on artificial data. Finally, features were derived from the de- tected changepoints to classify RBD patients from healthy controls using a K-Nearest Neighbors approach. On artificial data, Modified Bayesian Changepoint Detection al- gorithm provided superior positive predictive value for state change identification while Recursive Mean Difference Maximization (RMDM) achieved the highest true positive rate. For the classification task, features derived from the RMDM algorithm provided the highest leave one out cross validated accuracy of 0.89 and true positive rate of 0.87. Automatically detected changepoints provide useful information about subject's phys- iological state which cannot be directly observed. However, the choice of change point detection algorithm depends on the nature of the underlying data and the downstream application, such as a classification task. This work represents the first time change point detection algorithms have been compared in a meaningful way and utilized in a classification task, which demonstrates the effect of changepoint algorithm choice on application *** Codes 92C30, 92C32, 03H10, 62H30, 68Q07, 8T07, 78-10, 92-10, 62R07, 68T09, 68T10 © 2024, CC BY-NC-SA.

关键词： Time series

IoT Device Classification in Edge-Cloud Models

学校读者我要写书评

暂无评论

IoT Device Classification in Edge-Cloud Models

IEEE International Conference on Smart Cloud (SmartCloud)

作者： Jeremy L Reed Ali Tosun Turgay Korkmaz Benjamin Topolosky Department of Computer Science The University of Texas at San Antonio San Antonio TX USA Department of Mathematics and Computer Science University of North Carolina at Pembroke Pembroke NC USA Department of Informatics New Jersey Institute of Technology Newark NJ USA

ISBN: (数字)9798331596651

ISBN: (纸本)9798331596668

IoT edge networks are constructed with Internet of Things (IoT) devices deployed near data sources at the network edge. These networks often include a middle tier of computationally robust devices designed to enhance IoT compute resources and boost network performance at an intermediary stage. By utilizing this middle tier for network capture, we introduce a novel side-channel attack through DNS pooling, AWS cloud services, and a rainbow table of AWS endpoint URLs. Our attack demonstrates the capability to correlate IoT edge devices with AWS cloud services, allowing us to determine a device’s role within the IoT edge network. This identification is crucial in reducing the time required to physically compromise the network by swapping out IoT edge devices with malicious counterparts. Furthermore, linking our attack to one or more AWS vulnerabilities amplifies the severity and scale of the exploit. Mitigating this technique is challenging as it exploits the inherent dependencies on DNS queries and the structure of AWS cloud services. Our experiment included a diverse set of IoT devices related to home automation and security. We accurately grouped IoT edge devices by analyzing traffic patterns, throughput, latency, cloud service endpoints, and human interaction patterns. Cloud service endpoint matching was achieved by utilizing AWS developer documentation, constructing EC2 pools through repeated DNS queries, and matching IP addresses to endpoints using a rainbow table of cloud service endpoints. Although AWS is highlighted in our experiment, other cloud services are similarly vulnerable due to their unique structural characteristics.

关键词： Cloud computing Accuracy Traffic control Throughput Windows Table lookup Internet of Things Object recognition Domain Name System Streams