AN EVOLUTIONARY APPROACH TO THE DESIGN OF CONVOLUTIONAL NEURAL NETWORKS FOR HUMAN ACTIVITY RECOGNITION

Abstract Automated human activity recognition has a number of applications such as in elderly healthcare monitoring, fitness tracking and in various smart home systems that can adapt to the inhabitants’ behavior. Deep learning using Convolutional Neural Networks (CNNs) is increasingly being used for recognition of human activities. However, the CNNs performance is highly dependent on the network architecture and usually the hyper-parameters are manually selected. Various approaches have been used to automate the design of CNN architectures. The paper proposes an evolutionary based approach for optimizing the architecture of one dimensional CNNs for human activity recognition. The suggested approach is tested on three accelerometric data sets. The experimental results show that the CNNs designed using the evolutionary based approach have comparable accuracy on the WISDM Actitracker data set and significantly better performance on the Smartphone-Based Recognition of Human Activities and Postural Transitions data set compared to other deep CNNs.

[1]  Ying Wah Teh,et al.  Deep learning algorithms for human activity recognition using mobile and wearable sensor networks: State of the art and research challenges , 2018, Expert Syst. Appl..

[2]  Ben Fielding,et al.  Evolving and Ensembling Deep CNN Architectures for Image Classification , 2019, 2019 International Joint Conference on Neural Networks (IJCNN).

[3]  Frank Hutter,et al.  CMA-ES for Hyperparameter Optimization of Deep Neural Networks , 2016, ArXiv.

[4]  Bin Wang,et al.  Evolving Deep Convolutional Neural Networks by Variable-Length Particle Swarm Optimization for Image Classification , 2018, 2018 IEEE Congress on Evolutionary Computation (CEC).

[5]  Li Zhang,et al.  Evolving Image Classification Architectures With Enhanced Particle Swarm Optimisation , 2018, IEEE Access.

[6]  Alejandro Baldominos Gómez,et al.  Evolutionary convolutional neural networks: An application to handwriting recognition , 2017, Neurocomputing.

[7]  Tobias Senst,et al.  Hyper-parameter optimization for convolutional neural network committees based on evolutionary algorithms , 2017, 2017 IEEE International Conference on Image Processing (ICIP).

[8]  Bo Yu,et al.  Convolutional Neural Networks for human activity recognition using mobile sensors , 2014, 6th International Conference on Mobile Computing, Applications and Services.

[9]  Moosa Ayati,et al.  Magnetic resonance imaging-based brain tumor grades classification and grading via convolutional neural networks and genetic algorithms , 2019, Biocybernetics and Biomedical Engineering.

[10]  Bart de Boer,et al.  Proceedings of the Genetic and Evolutionary Computation Conference , 2019, GECCO.

[11]  Anton Kummert,et al.  Activity recognition using inertial sensors and a 2-D convolutional neural network , 2017, 2017 10th International Workshop on Multidimensional (nD) Systems (nDS).

[12]  Didier Stricker,et al.  Introducing a New Benchmarked Dataset for Activity Monitoring , 2012, 2012 16th International Symposium on Wearable Computers.

[13]  Steven R. Young,et al.  Optimizing deep learning hyper-parameters through an evolutionary algorithm , 2015, MLHPC@SC.

[14]  Nuno Lourenço,et al.  Evolving the Topology of Large Scale Deep Neural Networks , 2018, EuroGP.

[15]  Milan Tuba,et al.  Optimizing Convolutional Neural Network Hyperparameters by Enhanced Swarm Intelligence Metaheuristics , 2020, Algorithms.

[16]  Ulas Bagci,et al.  Automatically Designing CNN Architectures for Medical Image Segmentation , 2018, MLMI@MICCAI.

[17]  Sung-Bae Cho,et al.  Deep Convolutional Neural Networks for Human Activity Recognition with Smartphone Sensors , 2015, ICONIP.

[18]  Alan L. Yuille,et al.  Genetic CNN , 2017, 2017 IEEE International Conference on Computer Vision (ICCV).

[19]  Victoria Bibaeva,et al.  Using Metaheuristics for Hyper-Parameter Optimization of Convolutional Neural Networks , 2018, 2018 IEEE 28th International Workshop on Machine Learning for Signal Processing (MLSP).

[20]  Quoc V. Le,et al.  Large-Scale Evolution of Image Classifiers , 2017, ICML.

[21]  Oriol Vinyals,et al.  Hierarchical Representations for Efficient Architecture Search , 2017, ICLR.

[22]  Quoc V. Le,et al.  Neural Architecture Search with Reinforcement Learning , 2016, ICLR.

[23]  Mengjie Zhang,et al.  Automatically Evolving CNN Architectures Based on Blocks , 2018, ArXiv.

[24]  Frank Hutter,et al.  Simple And Efficient Architecture Search for Convolutional Neural Networks , 2017, ICLR.

[25]  Mengjie Zhang,et al.  Evolving Deep Convolutional Neural Networks for Image Classification , 2017, IEEE Transactions on Evolutionary Computation.

[26]  Yulong Wang,et al.  cPSO-CNN: An efficient PSO-based algorithm for fine-tuning hyper-parameters of convolutional neural networks , 2019, Swarm Evol. Comput..

[27]  Davide Anguita,et al.  Transition-Aware Human Activity Recognition Using Smartphones , 2016, Neurocomputing.

[28]  Yoshua Bengio,et al.  Random Search for Hyper-Parameter Optimization , 2012, J. Mach. Learn. Res..

[29]  Masanori Suganuma,et al.  A genetic programming approach to designing convolutional neural network architectures , 2017, GECCO.

[30]  Hwee Pink Tan,et al.  Deep Activity Recognition Models with Triaxial Accelerometers , 2015, AAAI Workshop: Artificial Intelligence Applied to Assistive Technologies and Smart Environments.

[31]  Yong Yu,et al.  Efficient Architecture Search by Network Transformation , 2017, AAAI.

[32]  Grazziela Patrocinio Figueredo,et al.  Evolving Deep CNN-LSTMs for Inventory Time Series Prediction , 2019, 2019 IEEE Congress on Evolutionary Computation (CEC).

[33]  Xin-She Yang,et al.  Handling dropout probability estimation in convolution neural networks using meta-heuristics , 2018, Soft Comput..

[34]  Gary M. Weiss,et al.  Activity recognition using cell phone accelerometers , 2011, SKDD.

[35]  Ramesh Raskar,et al.  Designing Neural Network Architectures using Reinforcement Learning , 2016, ICLR.

[36]  Guang-Zhong Yang,et al.  Deep learning for human activity recognition: A resource efficient implementation on low-power devices , 2016, 2016 IEEE 13th International Conference on Wearable and Implantable Body Sensor Networks (BSN).

[37]  Alok Aggarwal,et al.  Regularized Evolution for Image Classifier Architecture Search , 2018, AAAI.

[38]  Elliot Meyerson,et al.  Evolving Deep Neural Networks , 2017, Artificial Intelligence in the Age of Neural Networks and Brain Computing.