Muhammad Ramzan^1,2,*, Adnan Abid¹, Shahid Mahmood Awan^1,3

CMC-Computers, Materials & Continua, Vol.70, No.1, pp. 1829-1844, 2022, DOI:10.32604/cmc.2022.017522 - 07 September 2021

Abstract In the current era, automatic surveillance has become an active research problem due to its vast real-world applications, particularly for maintaining law and order. A continuous manual monitoring of human activities is a tedious task. The use of cameras and automatic detection of unusual surveillance activity has been growing exponentially over the last few years. Various computer vision techniques have been applied for observation and surveillance of real-world activities. This research study focuses on detecting and recognizing unusual activities in an academic situation such as examination halls, which may help the invigilators observe and restrict… More >

Keshav Thapa, Zubaer Md. Abdhulla AI, Yang Sung-Hyun^*

CMC-Computers, Materials & Continua, Vol.69, No.2, pp. 1653-1670, 2021, DOI:10.32604/cmc.2021.015660 - 21 July 2021

Abstract In this era, deep learning methods offer a broad spectrum of efficient and original algorithms to recognize or predict an output when given a sequence of inputs. In current trends, deep learning methods using recent long short-term memory (LSTM) algorithms try to provide superior performance, but they still have limited effectiveness when detecting sequences of complex human activity. In this work, we adapted the LSTM algorithm into a synchronous algorithm (sync-LSTM), enabling the model to take multiple parallel input sequences to produce multiple parallel synchronized output sequences. The proposed method is implemented for simultaneous human… More >

Ahmed A. M. Jamel^1,∗, Bahriye Akay^2,†

Computer Systems Science and Engineering, Vol.35, No.6, pp. 441-456, 2020, DOI:10.32604/csse.2020.35.441

Abstract Recently, owing to the capability of mobile and wearable devices to sense daily human activity, human activity recognition (HAR) datasets have become a large-scale data resource. Due to the heterogeneity and nonlinearly separable nature of the data recorded by these sensors, the datasets generated require special techniques to accurately predict human activity and mitigate the considerable heterogeneity. Consequently, classic clustering algorithms do not work well with these data. Hence, kernelization, which converts the data into a new feature vector representation, is performed on nonlinearly separable data. This study aims to present a robust method to… More >

Sun-Taag Choe, We-Duke Cho^*, Jai-Hoon Kim, and Ki-Hyung Kim

Intelligent Automation & Soft Computing, Vol.26, No.4, pp. 679-691, 2020, DOI:10.32604/iasc.2020.010102

Abstract Recent research on activity recognition in wearable devices has identified a key challenge: k-nearest neighbors (k-NN) algorithms have a high operational time complexity. Thus, these algorithms are difficult to utilize in embedded wearable devices. Herein, we propose a method for reducing this complexity. We apply a clustering algorithm for learning data and assign labels to each cluster according to the maximum likelihood. Experimental results show that the proposed method achieves effective operational levels for implementation in embedded devices; however, the accuracy is slightly lower than that of a traditional k-NN algorithm. Additionally, our method provides More >

Abdu Gumaei^{1, 2, *}, Mabrook Al-Rakhami^{1, 2}, Hussain AlSalman², Sk. Md. Mizanur Rahman³, Atif Alamri^{1, 2}

CMC-Computers, Materials & Continua, Vol.65, No.2, pp. 1033-1057, 2020, DOI:10.32604/cmc.2020.011740 - 20 August 2020

Abstract Human activity recognition is commonly used in several Internet of Things applications to recognize different contexts and respond to them. Deep learning has gained momentum for identifying activities through sensors, smartphones or even surveillance cameras. However, it is often difficult to train deep learning models on constrained IoT devices. The focus of this paper is to propose an alternative model by constructing a Deep Learning-based Human Activity Recognition framework for edge computing, which we call DL-HAR. The goal of this framework is to exploit the capabilities of cloud computing to train a deep learning model More >

M. Humayun Kabir¹, Keshav Thapa², Jae-Young Yang², Sung-HyunYang²

Intelligent Automation & Soft Computing, Vol.25, No.4, pp. 673-681, 2019, DOI:10.31209/2018.100000035

Abstract Recognition of human activity is a key element for building intelligent and pervasive environments. Inhabitants interact with several objects and devices while performing any activity. Interactive objects and devices convey information that can be essential factors for activity recognition. Using embedded sensors with devices or objects, it is possible to get object-use sequencing data. This approach does not create discomfort to the user than wearable sensors and has no impact or issue in terms of user privacy than image sensors. In this paper, we propose a linear model for activity recognition based on the state-space More >

Juan C. Quiroz^a, Amit Banerjee^b, Sergiu M. Dascalu^c, Sian Lun Lau^a

Intelligent Automation & Soft Computing, Vol.24, No.4, pp. 785-793, 2018, DOI:10.1080/10798587.2017.1342400

Abstract We use the public Human Activity Recognition Using Smartphones (HARUS) data-set to investigate and identify the most informative features for determining the physical activity performed by a user based on smartphone accelerometer and gyroscope data. The HARUS data-set includes 561 time domain and frequency domain features extracted from sensor readings collected from a smartphone carried by 30 users while performing specific activities. We compare the performance of a decision tree, support vector machines, Naive Bayes, multilayer perceptron, and bagging. We report the various classification performances of these algorithms for subject independent cases. Our results show More >