检索结果-内蒙古大学图书馆

19th International Conference on Web Information systems and Technologies, WEBIST 2023

作者： Borges, Victor Emanuel F.C. Santos, Danilo F.S. Valadares, Dalton C.G. Future Connected Systems Embedded Systems and Pervasive Computing Laboratory Brazil

ISBN: (纸本)9789897586729

The Internet of Vehicles (IoV) ecosystem is well-regarded for its overall security, yet authentication remains a critical concern due to existing vulnerabilities that expose users to potential malicious attacks. Although researchers have devised authentication mechanisms and protocols to address these issues, there are two significant risk factors often overlooked by prevalent solutions. The first is trust in out-of-coverage mode, which can leave vehicles vulnerable to receiving forged messages. The second is the centralization of the standard authentication mechanism, where reliance on a centralized third-party service introduces authentication vulnerabilities that can result in access loss. In this article, we propose an innovative solution that incorporates the Self-Sovereign Identity (SSI) decentralized identity model within the Trust Over IP architecture to provide vehicular authentication. This integration establishes decentralized identification mechanisms suitable for various contexts within the IoV ecosystem. Our primary focus is enhancing security in the Advanced Driver-Assistance System (ADAS) context. We leverage the SSI model to design a specialized authentication scheme, aiming to effectively mitigate associated security risks through decentralization. This approach strengthens authentication security within the IoV ecosystem, addressing the mentioned vulnerabilities. Copyright © 2023 by SCITEPRESS - Science and Technology Publications, Lda. Under CC license (CC BY-NC-ND 4.0)

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Optimizing AutoML for Tiny Edge systems: A Baldwin-effect Inspired Genetic Algorithm

Optimizing AutoML for Tiny Edge Systems: A Baldwin-effect In...

引用

IEEE Annual Conference on pervasive computing and Communications Workshops (PerCom)

作者： Yiran Huang Yexu Zhou Haibin Zhao Till Riedel Michael Beigl Pervasive Computing Systems-TECO Karlsruhe Institute of Technology Karlsruhe Germany

Tiny edge systems used in IoT devices, wearables or smart textiles are characterized by the need of processing complex sensor data streams under various device constraints. Due to the high number of constraints and the complexity of the optimization of the hyper-parameter space for machine learning based processing, genetic algorithms (GAs) seem to be a perfect fit to enable AutoML for those embedded devices. However, due to aspects such as the high interdependence between optimization parameters, the simultaneous existence of multiple conflicting objectives and complex effects of embedded feature engineering, we made the experience that GA approaches fail to converge within this high dimensional design space. We introduce a novel Genetic Algorithm (GA) customized for AutoML tasks, addressing the unique challenges posed by highly embedded machine learning domains. The proposed approach addresses parameter interdependencies through utilizing the Baldwin-effect in biological evolution, enhances resource utilization by early elimination of less promising individuals, and augments the insufficient capabilities of existing machine learning features via the integration of carefully designed neural network features. Empirical evaluations conducted on two benchmark datasets support the superiority of our proposed method over conventional genetic algorithms. Furthermore, we demonstrate the effect of the different components introduced by our algorithms through an ablation study.

关键词：

来源：评论

学校读者我要写书评

暂无评论

randomHAR: Improving Ensemble Deep Learners for Human Activity Recognition with Sensor Selection and Reinforcement Learning

arXiv

引用

arXiv 2023年

作者： Huang, Yiran Zhou, Yexu Riedel, Till Fang, Likun Beigl, Michael Pervasive Computing Systems-TECO Karlsruhe Institute of Technology Karlsruhe Germany

Deep learning has proven to be an effective approach in the field of Human activity recognition (HAR), outperforming other architectures that require manual feature engineering. Despite recent advancements, challenges inherent to HAR data, such as noisy data, intra-class variability and inter-class similarity, remain. To address these challenges, we propose an ensemble method, called randomHAR. The general idea behind randomHAR is training a series of deep learning models with the same architecture on randomly selected sensor data from the given dataset. Besides, an agent is trained with the reinforcement learning algorithm to identify the optimal subset of the trained models that are utilized for runtime prediction. In contrast to existing work, this approach optimizes the ensemble process rather than the architecture of the constituent models. To assess the performance of the approach, we compare it against two HAR algorithms, including the current state of the art, on six HAR benchmark datasets. The result of the experiment demonstrates that the proposed approach outperforms the state-of-the-art method, ensembleLSTM. © 2023, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Neural Evolutionary Architecture Search for Compact Printed Analog Neuromorphic Circuits

引用

IEEE Transactions on Computer-Aided Design of Integrated Circuits and systems 2024年

作者： Zhao, Haibin Pal, Priyanjana Hefenbrock, Michael Wang, Yuhong Beigl, Michael Tahoori, Mehdi B. Chair for Pervasive Computing Systems Institute of Telematics Germany Chair of Dependable Nano Computing Institute of Computer Engineering Department of Informatics Germany RevoAI GmbH Germany

Printed electronics (PE) is an additive fabrication technology for manufacturing electronic circuits which not only allows for a highly flexible printing of arbitrary circuit patterns, but also produce soft, non-Toxic, and degradable electronics at an extremely low cost. These properties are unmatched by silicon based electronics, making PE an enabler of new application domains, e.g., fast moving consumer goods, wearables, and disposable healthcare devices. A particularly promising class of circuits in this technology is the printed analog neuromorphic circuits, offering efficient and highly tailored computational functionalities. In this work, we leverage the highly flexible fabrication process of PE to address the bottleneck of PE, i.e., the large feature sizes and low device counts. This issue is crucial, as it impairs the integration of printed circuits into target applications with limited footprint, such as smart band aids. We also propose an evolutionary algorithm (EA) to improve the circuit compactness through circuit architecture optimization. As baseline, we compare the proposed EA method with a state-of-The-Art pruning method and a modified area-Aware pruning method. All of them are able to optimize circuit architecture alongside the component values of printed neuromorphic circuits. Experimental simulation reveals that the proposed EA approach can effectively achieve compact circuits and outperform the pruning method by 3.1× lower area with no loss of accuracy. As a byproduct, the power is reduced by 3.0×, paving the way to energy-harvested printed systems. © 1982-2012 IEEE.

关键词： Flexible electronics

来源：评论

学校读者我要写书评

暂无评论

McXai: Local Model-Agnostic Explanation As Two Games

McXai: Local Model-Agnostic Explanation As Two Games

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Yiran Huang Nicole Schaal Michael Hefenbrock Yexu Zhou Till Riedel Michael Beigl Pervasive Computing Systems-TECO Karlsruhe Institute of Technology Karlsruhe Germany

To this day, various approaches for providing local explanation of black box machine learning models have been introduced. Despite these efforts, existing methods suffer from deficiencies such as being difficult to comprehend, only considering one feature at a time and disregarding inter-feature dependencies, lacking meaningful values for each feature, or only highlighting features that support the model's decision. To overcome these drawbacks, this study presents a new approach to explain the predictions of any black box classifier, called Monte Carlo tree search for eXplainable Artificial Intelligence (McXai). It employs a reinforcement learning strategy and models the explanation generation as two distinct games. In the first game, the objective is to identify feature sets that support the model's decision, while in the second game, the aim is to find feature sets that lead to alternative decisions. The output is a human-friendly representation in the form of a tree structure, where each node represents a set of features to be examined, with less specific interpretations at the top of the tree. Our experiments demonstrate that the features identified by McXai are more insightful with regard to the classifications compared to traditional algorithm like LIME and Gram-cam. Furthermore, the ability to identify misleading features provides guidance towards improved robustness of the black box classifier.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Auto-Augmentation Contrastive Learning for Wearable-based Human Activity Recognition

Auto-Augmentation Contrastive Learning for Wearable-based Hu...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Wu, Qingyu Shen, Jianfei Fan, Feiyi Gu, Yang Xu, Chenyang Chen, Yiqiang Chinese Academy of Sciences Institute of Computing Technology Beijing China University of Chinese Academy of Sciences Beijing China The Beijing Key Laboratory of Mobile Computing and Pervasive Device Beijing China Shandong Academy of Intelligent Computing Technology ShanDong China Peng Cheng Laboratory Shenzhen China Tianjin University Institute of Robotics and Autonomous Systems Tianjin China

ISBN: (纸本)9798350337488

For low-semantic sensor signals from human activity recognition (HAR), contrastive learning (CL) is essential to implement novel applications or generic models without manual annotation, which is a high-performance self-supervised learning (SSL) method. However, CL relies heavily on data augmentation for pairwise comparisons. Especially for low semantic data in the HAR area, conducting good performance augmentation strategies in pretext tasks still rely on manual attempts lacking generalizability and flexibility. To reduce the augmentation burden, we propose an end-to-end auto-augmentation contrastive learning (AutoCL) method for wearable-based HAR. AutoCL is based on a Siamese network architecture that shares the parameters of the backbone and with a generator embedded to learn auto-augmentation. AutoCL trains the generator based on the representation in the latent space to overcome the disturbances caused by noise and redundant information in raw sensor data. The architecture empirical study indicates the effectiveness of this design. Furthermore, we propose a stop-gradient design and correlation reduction strategy in AutoCL to enhance encoder representation learning. Extensive experiments based on four wide-used HAR datasets demonstrate that the proposed AutoCL method significantly improves recognition accuracy compared with other SOTA methods. © 2023 IEEE.

关键词： Contrastive Learning Human Activity Recognition Self-Supervised Learning

来源：评论

学校读者我要写书评

暂无评论

OpenEarable: Open Hardware Earable Sensing Platform

OpenEarable: Open Hardware Earable Sensing Platform

引用

Adjunct Proceedings of the 2022 ACM International Joint Conference on pervasive and Ubiquitous computing and the 2022 ACM International Symposium on Wearable Computers

作者： Tobias Röddiger Tobias King Dylan Ray Roodt Christopher Clarke Michael Beigl TECO / Pervasive Computing Systems Karlsruhe Institute of Technology (KIT) Germany University of Bath United Kingdom

ISBN: (纸本)9781450394239

Earables are ear-worn devices that offer functionalities beyond basic audio in- and output. In this paper we present the ongoing development of a new, open-source, Arduino-based earable platform called OpenEarable. It is based on standard components, is easy to manufacture and costs roughly $40 per device at batch size ten. We present the first version of the device which is equipped with a series of sensors and actuators: a 3-axis accelerometer and gyroscope, an ear canal pressure and temperature sensor, an inward facing ultrasonic microphone as well as a speaker, a push button, and a controllable LED. We demonstrate the versatility of the prototyping platform through three different example application scenarios. In sum, OpenEarable offers a general-purpose, open sensing platform for earable research and development.

关键词： earables open hardware hearables

来源：评论

学校读者我要写书评

暂无评论

Development of a low-cost EMG-data acquisition armband to control an above-elbow prosthesis

Development of a low-cost EMG-data acquisition armband to co...

引用

2021 International Conference on Control Theory and Applications, ICoCTA 2021

作者： Schlüter, Christoph Caraguay, Washington Ramos, Doris Cáliz Faculty of Mechanical Engineering Karlsruher Institut fur Technologie Germany Faculty of Electronic Computer and Telecommunication Engineering Espiritu Santo University Ecuador Pervasive Computing Systems / TECO Karlsruher Institut für Technologie Germany

This work presents the development and implementation of an armband for EMG-data acquisition of the upper arm. The developed prototype serves for investigations on EMG-signal processing with the final objective of reliably controlling a prosthesis for a transhumeral amputee. To make the product available for a greatest possible number of people one of the main characteristics will be a design of very low cost. A focus is put on the electric circuit design. In order to manufacture the prototype without difficulties, it is exclusively designed with components, which are available on the Ecuadorian market. The development is based on previous investigations and approaches of other researchers. With help of electric circuit simulations, the design was adapted and optimized step by step and a reliable low-noise circuit was established. All components are arranged on printed circuit boards in a way to keep the device as small as possible. To optimally avoid noise the length of the connection from the electrodes to the amplifier is minimized. Compact 3D-printed housings cover all the electric components. All housings consist of only two parts and are intuitive to assemble. Holes in the bottom offer space to fix electrodes via a snap-fastener connection. 3D-printed elastic straps are designed to connect the subsystems and hold the device in place. The armband including two sensors weighs 92 g and is capable of measuring two muscles with a bipolar EMG-setting each, sharing one reference electrode, which is aligned on the side of the upper arm between the biceps and triceps muscles. The amplification of the sensors is adjustable individually by potentiometers, facilitating a gain factor range of 211 to 2016 V/V. The data is recorded by a microcontroller board and send to a computer for processing via wire or Bluetooth. For wireless operation, rechargeable batteries are integrated. Test measurements on an able-bodied human prove the functionality of the device. © Published und

关键词： Data acquisition

来源：评论

学校读者我要写书评

暂无评论

Review of Sleep Monitoring Research Based on Wireless Sensor 19th

Review of Sleep Monitoring Research Based on Wireless Sens...

引用

19th EAI International Conference on Heterogeneous Networking for Quality, Reliability, Security and Robustness, QShine 2023

作者： Hu, Yuzhu Chen, Jian Zhao, Shen Tan, Kexin Yu, Kuai Wang, Wei School of Intelligent Systems Engineering Sun Yat-sen University Shenzhen518000 China Artificial Intelligence Research Institute Shenzhen MSU-BIT University Guangdong Shenzhen518172 China Guangdong-Hong Kong-Macao Joint Laboratory for Emotion Intelligence and Pervasive Computing Shenzhen MSU-BITUniversity Guangdong Shenzhen518172 China School of Medical Technology Beijing Institute of Technology Beijing100081 China

ISBN: (纸本)9783031651250

Since sleep quality is crucial to human health, sleep monitoring has become a hot spot in the field of smart healthcare. Previous methods depend on polysomnography and wearable devices need immediate contact with the subject, which brings discomfort. Contactless sensors can address this issue. The most common contactless sensors used in sleep monitoring are wireless sensors (including radar and WiFi). To clarify the research in this area, we summarized the existing sleep monitoring methods based on WiFi sensors and wireless radar and made a comparison. The conclusion shows that the two kinds of methods have advantages and disadvantages, so the development of complementary methods is very promising for sleep monitoring. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications Engineering 2024.

关键词： Sleep research

来源：评论

学校读者我要写书评

暂无评论

Reinforcement Learning for Bio-Inspired Stochastic Robot Control

Reinforcement Learning for Bio-Inspired Stochastic Robot Con...

引用

Artificial Intelligence and Cognitive Science (AICS), Irish Conference on

作者： James Gillespie Iñaki Rañó José Santos Nazmul Siddique Intelligent Systems Research Centre Ulster University Northern Ireland UK Intelligent Systems Group University of Santiago de Compostela Spain Pervasive Computing Research Centre Ulster University Northern Ireland UK

Braitenberg vehicles serve as bio-inspired controllers for sensor-based local navigation in wheeled robots, finding applications in various real-world scenarios. Tuning the parameters of these controllers involves finding nonlinear functions typically implemented through neural networks that link sensing to motor actions. However, tuning the weights to achieve the desired closed-loop navigation behaviours poses significant challenges. Some approaches use hand tuned spiking or recurrent neural networks, while others learn the weights using evolutionary approaches. Recently, Reinforcement Learning has been successfully used to learn neural controllers for Braitenberg vehicle 3a, a bio-inspired model of target seeking in simulated scenarios with high noise levels. This paper extends the application of RL for Braitenberg Vehicle control to a real-world robot platform, introducing real sensor noise and testing the adaptability of the RL framework in attenuating for this uncertainty. Comparative analyses are drawn between the neural controller acquired through RL and a simplistic hand-tuned counterpart using the Colias micro-robot as an evaluation tool. Results are illustrated through analysis of the real robot trajectories, where the RL-based neural controller exhibits a 32.5% increase in successful trajectories compared to an empirical hand-tuned controller.

关键词：

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：