In this paper we investigate the usage of machine learning for interpreting measured sensor values in sensor modules. In particular we analyze the potential of artificial neural networks (ANNs) on low-cost micro-controllers with a few kilobytes of memory to semantically enrich data captured by sensors. The focus is on classifying temporal data series with a high level of reliability. Design and implementation of ANNs are analyzed considering Feed Forward Neural Networks (FFNNs) and Recurrent Neural Networks (RNNs). We validate the developed ANNs in a case study of optical hand gesture recognition on an 8-bit micro-controller. The best reliability was found for an FFNN with two layers and 1493 parameters requiring an execution time of 36 ms. We propose a workflow to develop ANNs for embedded devices.
Building robust prediction models for defective sensor data using Artificial Neural Networks
Robert Bosch GmbH(罗伯特·博世有限公司);LIACS, Leiden University(莱顿大学高级计算机科学研究所);INESC TEC(葡萄牙工程与技术研究所);Faculdade de Engenharia, Universidade do Porto(波尔图大学工程学院)
Using Phone Sensors and an Artificial Neural Network to Detect Gait Changes During Drinking Episodes in the Natural Environment
University of Pittsburgh(匹兹堡大学)
手机传感器可能有助于评估饮酒引起的步态变化。这项研究确定了(1)在自然环境中饮酒时收集步态相关数据的可行性,以及(2)手机传感器测量的步态相关特征与估计的血液酒精浓度(eBAC)的关系。10名年轻的成年重度饮酒者被要求在连续四个周末的晚上8点到凌晨12点之间每小时完成一项5步步态任务。我们从手机传感器收集了3轴加速度计、陀螺仪和磁力计数据,并使用滑动窗口技术计算了24个步态相关特征。基于酒精使用的生态瞬时评估(EMA)计算每个时间点的eBAC水平。我们使用人工神经网络模型来分析训练(70%的数据)和验证和测试(30%的数据)数据集中传感器特征与eBAC之间的关联。我们分析了128个数据点,其中eBAC和步态相关的传感器数据都被捕获,无论是在不喝酒时(n=60),而eBAC上升(n=55)或eBAC下降(n=13)。在eBAC大于法定限值(0.08 mg/dl)时采集了21个数据点。使用贝叶斯正则化神经网络,步态相关的手机传感器特征显示出与eBAC的高度相关性(Pearson's r > 0.9),并且>95%的估计eBAC将落在实际eBAC的-0.012和+0.012之间。在自然环境中的饮酒场合,从智能手机传感器收集步态相关数据是可行的。基于传感器的特征可用于推断与血液酒精含量升高相关的步态变化。
Embedded Inter-Subject Variability in Adversarial Learning for Inertial Sensor-Based Human Activity Recognition
1 Centre for Applied Autonomous Sensor Systems (AASS), Örebro University, Örebro, Sweden 2 Faculty of Information Science \& Electrical Engineering, Kyushu University, Fukuoka, Japan 3 RPTU, Kaiserslautern, Germany 4 DFKI, Kaiserslautern, Germany 5 Escuela T\'ecnica Superior de Ingenier\'ia y Diseño Industrial, Universidad Polit\'ecnica de Madrid, Madrid, Spain
Model Input-Output Configuration Search with Embedded Feature Selection for Sensor Time-series and Image Classification
HUN-REN Institute for Computer Science and Control(HUN-REN计算机科学与控制研究所);Hungarian Academy of Sciences (MTA)(匈牙利科学院);Doctoral School of Informatics, Eötvös Loránd University (ELTE)(厄特沃什·罗兰大学信息学博士学院);Faculty of Economics and Business, John von Neumann University(约翰·冯·诺依曼大学经济与商学院)
Motif-topology improved Spiking Neural Network for the Cocktail Party Effect and McGurk Effect
Institute of Automation, Chinese Academy of Sciences(中国科学院自动化研究所);School of Artificial Intelligence, University of Chinese Academy of Sciences(中国科学院大学人工智能学院);School of Information and Electronics, Beijing Institute of Technology(北京理工大学信息与电子学院);Center for Excellence in Brain Science and Intelligence Technology, Chinese Academy of Sciences(中国科学院脑科学与智能技术卓越创新中心)
Adaptive Pruning of Deep Neural Networks for Resource-Aware Embedded Intrusion Detection on the Edge
Computer Science University of Massachusetts Dartmouth(计算机科学大学马萨诸塞大学达特茅斯分校);United States Military Academy(美国军事学院);University of Massachusetts Dartmouth(马萨诸塞大学达特茅斯分校)
Data-driven Bi-level Optimization of Thermal Power Systems with embedded Artificial Neural Networks
Department of Mechanical Engineering, University of Engineering and Technology Lahore(拉合尔工程与技术大学机械工程系);University of Engineering and Technology Lahore(拉合尔工程与技术大学);Collective Intelligence & Design Group, University of Cambridge(剑桥大学集体智能与设计组);The Sargent Centre for Process Systems Engineering, Department of Chemical Engineering, University College London(伦敦大学学院化工系统工程中心);University College London(伦敦大学学院)
Virtualization of Tiny Embedded Systems with a robust real-time capable and extensible Stack Virtual Machine REXAVM supporting Material-integrated Intelligent Systems and Tiny Machine Learning
University of Bremen(不来梅大学);University of Siegen(锡根大学);Institute for Microsensors, -actuators and -systems(微传感器、微执行器与微系统研究所)
Cross-Validation and Uncertainty Determination for Randomized Neural Networks with Applications to Mobile Sensors
Institute of Statistics, RWTH Aachen University(亚琛工业大学统计研究所);Forschungszentrum Jülich, Institut für Energie- und Klimaforschung, IEK-5(于利希研究中心能源与气候研究所 IEK-5)