Human action recognition with deep learning and structural optimization using a hybrid heuristic algorithm

  • PDF / 1,010,450 Bytes
  • 14 Pages / 595.276 x 790.866 pts Page_size
  • 29 Downloads / 213 Views

DOWNLOAD

REPORT


(0123456789().,-volV)(0123456789(). ,- volV)

Human action recognition with deep learning and structural optimization using a hybrid heuristic algorithm Tayyip Ozcan1



Alper Basturk1

Received: 2 May 2019 / Revised: 21 November 2019 / Accepted: 6 January 2020 Ó Springer Science+Business Media, LLC, part of Springer Nature 2020

Abstract Human action recognition (HAR) is a popular subject for academic society and other stakeholders. Nowadays it has a widespread use for lots of practical applications such as for health, assistive living, elderly care, and so on. Both visual and sensor-based data can be used for HAR. Visual data includes video images, still images, skeleton images, etc., whilst sensor-based data is acquired as numerical data from devices such as accelerometer, gyroscope, and so on. Employed classification methods and data types are of crucial importance on HAR performance. In this paper, sensor data based activity recognition is performed using stacked autoencoders (SAE). Finding near optimal accuracy results with SAEs is a challenging process if structural optimization is left to user experience. The purpose of this study is to improve the accuracy of HAR classifying methods such as SAEs using heuristic optimization algorithms. Hence the structural parameters of SAEs have been optimized using artificial bee colony optimization algorithm (ABC), genetic algorithm, differential evolution algorithm, particle swarm optimization algorithm (PSO) and an afresh developed hybrid algorithm (hABCPSO) which includes PSO and ABC in its internal structure. Leave-one-out cross-validation (LOOCV) test method is used for validating the results. Each algorithm is performed for 30 runs and the results of these runs are analyzed by statistical methods in detail. According to experimental results, hABCPSO supported SAE gives the minimum error and is the most robustness algorithm among the others. Obtained success rates show that the proposed SAE achieved the best accuracy rate ever on UCI human activity recognition dataset and a close result to best on wireless sensor data mining dataset with regard to LOOCV test technique. Keywords Deep learning  Stacked autoencoders  Sensor-based human action recognition  Human computer interaction  Statistical analysis  Hybrid optimization  ABC  GA  DE  PSO

1 Introduction Human action recognition (HAR) has an important role in human behaviour analysis, human-computer, and robotcomputer interactions. Various classification models are available to perform the HAR operation. Among these models, HAR studies based on deep learning methods have become popular [1–3]. Autoencoders, which is a deep learning method, get the input, then passes it through a & Tayyip Ozcan [email protected] Alper Basturk [email protected] 1

Department of Computer Engineering, Erciyes University, Melikgazi, 38039 Kayseri, Turkey

hidden layer and tries to reconstruct the same input at the output. Auto encoders perform encode and decode stages in this process. Encoder and decoder functions are used