Human Activity Recognition Using Cell Phone-Based Accelerometer and Convolutional Neural Network

Abstract

Human Activity Recognition (HAR) has become an active field of research in the computer vision community. Recognizing the basic activities of human beings with the help of computers and mobile sensors can be beneficial for numerous real-life applications. The main objective of this paper is to recognize six basic human activities, viz., jogging, sitting, standing, walking and whether a person is going upstairs or downstairs. This paper focuses on predicting the activities using a deep learning technique called Convolutional Neural Network (CNN) and the accelerometer present in smartphones. Furthermore, the methodology proposed in this paper focuses on grouping the data in the form of nodes and dividing the nodes into three major layers of the CNN after which the outcome is predicted in the output layer. This work also supports the evaluation of testing and training of the two-dimensional CNN model. Finally, it was observed that the model was able to give a good prediction of the activities with an average accuracy of 89.67%. Considering that the dataset used in this research work was built with the aid of smartphones, coming up with an efficient model for such datasets and some futuristic ideas pose open challenges in the research community.

Recognition of Hand Gesture Using Electromyography Signal: Human-Robot Interaction

“…Precision, recall, and F1 score are the assessment measures used to assess the model's concert as illus-trated in Figure4. When dealing with erratic data, accuracy performance measures are crucial[35,[39][40][41][42][43][44].Precision states what percentage of all the optimistic predictions is genuinely positive:precision = True positive True positive + False positive : ð4Þ…”

Artificial Intelligence Based Approach for Classification of Human Activities Using MEMS Sensors Data

“…Modern devices are packed with a variety of sensors, like Accelerometer, Gyroscope, Magnetometer, but the accelerometer is still the most reliable. The work by Prasad et al [ 12 ] using just an accelerometer and still getting good accuracy explains how powerful results can be achieved using just a simple sensor. The aim was to identify the six basic fundamental human activities, namely, walking, brisk walking, standing, sitting, and going upstairs or downstairs.…”

“…Data collected from sensors can be used to train a number of ML classifiers [ 12 ] which include Support Vector Machines (SVMs), Hidden Markov Models (HMMs), Dynamic Bayesian Models (DBMs), Random Forests (RFs), Decision Trees (DTs), etc. In order to utilize ML algorithms features need to be extracted from the collected data, even though the data size need not be enormous [ 13 ].…”

Semi-Supervised Adversarial Learning Using LSTM for Human Activity Recognition

“…To extract task-independent feature representations from early generative models, deep learning approaches have been employed on Boltzman machines [24]. More sophisticated models like CNN [25,26] were effectively utilized in complex HAR tasks. Likewise, some suitable methods are employed to categorize certain sorts of activity, such as multilayer perceptrons [27], vector support machine [28], Random forest [29], decisionmaking tree [30], and an updated HMM [31].…”