检索结果-内蒙古大学图书馆

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

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

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

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

Spatial Interpolation of Air Quality Data with Multidimensional Gaussian Processes 51

Spatial Interpolation of Air Quality Data with Multidimensio...

引用

Die 51. Jahrestagung der Gesellschaft fur Informatikin, INFORMATIK 2021 - 51st Annual Conference of the German Informatics Society, INFORMATIK 2021

作者： Tremper, Paul Riedel, Till Budde, Matthias TECO/Pervasive Computing Systems Vincenz-Prießnitz-Straße 1 Karlsruhe76131 Germany Disy Informationsssysteme GmbH Ludwig-Erhard-Allee 6 Karlsruhe76131 Germany

ISBN: (纸本)9783885797081

The central question of this paper is whether interpolation techniques applied to a distributed sensor network can indeed provide more information than using the constant background of an urban reference station to measure air pollution. We compare different interpolation techniques based on temporal-spatial machine learning in terms of their applicability for correctly predicting personal exposure. Using a dataset of stationary low-cost sensors, we estimate exposure on a route through the city and compare it to mobile measurements. The results show that while different machine learning-based interpolation methods yield quite different results, validation of machine learning-based approaches is still challenging. © 2021 Gesellschaft fur Informatik (GI). All rights reserved.

关键词： Air quality

来源：评论

学校读者我要写书评

暂无评论

Enhancing Force Sensing Capabilities in Exoskeleton Interfaces Using Compliant Actuator-Sensor Units - A User Study

Enhancing Force Sensing Capabilities in Exoskeleton Interfac...

引用

IEEE/RAS-EMBS International Conference on Biomedical Robotics and Biomechatronics (BioRob)

作者： Hosam Alagi Nikola Fischer Kai Behrends Iris Ftirst-Walter Jürgen Becker Michael Beigl Franziska Mathis-Ullrich Björn Hein Intelligent Process Automation and Robotics Laboratory (IPR) Institute for Anthropomatics and Robotics (IAR) Karlsruhe Institute of Technology (KIT) Karlsruhe Germany Institute of Telematics (TM) - Pervasive Computing Systems (TECO) at Karlsruhe Institute of Technology (KIT) Karlsruhe Germany Institut fuer Technik der Informationsverarbeitung (ITIV) at Karlsruhe Institute of Technology (KIT) Karlsruhe Germany Department Artificial Intelligence in Biomedical Engineering (AIBE) Friedrich-Alexander University Erlangen-Nürnberg (FAU) Erlangen Germany Karlsruhe University of Applied Sciences Karlsruhe Germany

ISBN: (数字)9798350386523

ISBN: (纸本)9798350386530

Reliable interaction force sensing between an exoskeleton and the human body is crucial for personalized support and efficient control. Poor donning and disturbances during movement lead to lower force measurement quality and thus to unfavorable use. In this work, we present an active smart human-robot interface by utilizing compliant actuator-sensor units (CASUs) that can be worn over clothing. These units combine capacitive force sensing and actuation using Shape-Memory Alloy (SMA) to actively compensate disturbances and improve force measurement by tightening the interface and reestablishing optimal contact. We present a pilot user study with five subjects, investigating the performance of an exoskele-ton interface featuring three integrated CASUs to compensate for non-ideal donning configurations and displacements during daily activities of walking, sitting down, and climbing the stairs. The results for a passive interface show a decrease in holding forces and force signal quality during activities. Our active interface, on the other hand, effectively compensates for disturbances, restoring high signal quality by the mean of peak-to-peak value up to 300% which leads to more distinct signals.

关键词： Legged locomotion Force measurement Cooling Force Exoskeletons Metals Stairs Robot sensing systems Sensors Reliability

来源：评论

学校读者我要写书评

暂无评论

Examining the usability of touchscreen gestures for adults with DS

引用

Journal of Reliable Intelligent Environments 2021年第4期7卷 355-380页

作者： Cáliz, Doris Ravivanpong, Ployplearn Schankin, Andrea Jadán-Guerrero, Janio Caraguay, Washington Arellano, Leonardo TECO Department Pervasive Computing Systems Karlsruhe Institute of Technology Vincenz-Prießnitz-Straße 1 Karlsruhe76131 Germany FOM Hochschulzentren Karlsruhe Institute of Technology Vincenz-Prießnitz-Straße 1 Karlsruhe76131 Germany Universidad Tecnológica Indoamérica Carrera de Ingeniería en Ciencias de La Computación Av. Machala y Sabanilla Quito170301 Ecuador Facultad de Sistemas y Telecomunicaciones Universidad Tecnológica Espíritu Santo Km 2.5 Via Samborondon Guayaquil Ecuador Rumipamba y Bourgeois Universidad UTE Quito170147 Ecuador

This document is part of a global investigation that aims to establish best practices in usability testing of mobile applications, that fit the specific needs of persons with cognitive disabilities. The motivating factor is to improve the quality of life of people with special needs. As a first step, we want to discover what are the skills of people with DS (DS) when using a mobile device. Thanks to its direct manipulation interaction style, multi-touch technology is the ideal mechanism for learning activities with a view to the social inclusion of people with DS. This paper investigates the most common touchscreen gestures on commercial existing software. A commercial analysis was carried out to discover the touch screen gestures used by 103 free software Apps running on a mobile touch screen tablet of 11 where the applications run". The commercial analysis showed that most applications support tap and drag operations on multi-touch technology. Additionally, the research sought to discover the adults with DS (19–54 years of age) ability to perform other gestures on multi-touch surfaces. A DS user skill study was performed to assess the ability of this user segment to interact with multi-touch surfaces. The analysis involved 53 participants, aged between 19 and 54 years, from two vocational training centers attended by people with DS in Madrid. Authors used the Gesture Games App for experimenting with multi-touch gestures such as tap, double tap, long press, drag, scale up, scale down, and one-finger rotation. Tap, double tap, and drag were the three gestures that the most participant could use. In contrast, participants had difficulty performing one-finger rotation and long press gesture. Our statistical analysis showed that the ability to perform each gesture was independent of gender, age group, and previous experience with touchscreen of a participant. © 2021, The Author(s), under exclusive licence to Springer Nature Switzerland AG part of Springer Nature.

关键词： Touch screens

来源：评论

学校读者我要写书评

暂无评论

Participatory sensing or participatory nonsense? - Mitigating the effect of human error on data quality in citizen science

引用

Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 2017年第3期1卷 1–23页

作者： Budde, Matthias Schankin, Andrea Hoffmann, Julien Danz, Marcel Riedel, Till Beigl, Michael Pervasive Computing Systems / TECO Vincenz-Prießnitz-Straße 1 Karlsruhe76131 Germany

Citizen Science with mobile and wearable technology holds the possibility of unprecedented observation systems. Experts and policy makers are torn between enthusiasm and scepticism regarding the value of the resulting data, as their decision making traditionally relies on high-quality instrumentation and trained personnel measuring in a standardized way. In this paper, we (1) present an empirical behavior taxonomy of errors exhibited in non-expert smartphone-based sensing, based on four small exploratory studies, and discuss measures to mitigate their effects. We then present a large summative study (N=535) that compares instructions and technical measures to address these errors, both from the perspective of improvements to error frequency and perceived usability. Our results show that (2) technical measures without explanation notably reduce the perceived usability and (3) technical measures and instructions nicely complement each other: Their combination achieves a significant reduction in observed error rates while not affecting the user experience negatively. © 2017 ACM.

关键词： Errors

来源：评论

学校读者我要写书评

暂无评论

Graph-based anomaly detection for smart cities: A survey

Graph-based anomaly detection for smart cities: A survey

引用

2017 IEEE SmartWorld Ubiquitous Intelligence and computing, Advanced and Trusted Computed, Scalable computing and Communications, Cloud and Big Data computing, Internet of People and Smart City Innovation, SmartWorld/SCALCOM/UIC/ATC/CBDCom/IOP/SCI 2017

作者： Sudrich, Simon Borges, Julio Beigl, Michael TECO / Pervasive Computing Systems Karlsruhe Germany

ISBN: (纸本)9781538604342

With increasing size, the problems a city faces (e.g., air pollution, traffic congestion or high energy consumption) increase, but so does the amount of implicitly available data. In order to leverage this data for smarter problem solutions, local authorities and businesses require sophisticated analysis preprocessing techniques. Recent work proposes modeling urban data as a graph and applying graph-based anomaly detection, which is traditionally used for fraud and intrusion detection. This demonstrates that a successful application of anomaly detection to selected sources of urban data is possible, but lacks an evaluation of the general applicability. In this survey, we discuss several homogeneous and heterogeneous graph models for urban data and suitable detection approaches. © 2017 IEEE.

关键词： Intrusion detection

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：