Redirigiendo al acceso original de articulo en 17 segundos...
Inicio  /  Algorithms  /  Vol: 14 Par: 8 (2021)  /  Artículo
ARTÍCULO
TITULO

SVSL: A Human Activity Recognition Method Using Soft-Voting and Self-Learning

Aiiad Albeshri    

Resumen

Many smart city and society applications such as smart health (elderly care, medical applications), smart surveillance, sports, and robotics require the recognition of user activities, an important class of problems known as human activity recognition (HAR). Several issues have hindered progress in HAR research, particularly due to the emergence of fog and edge computing, which brings many new opportunities (a low latency, dynamic and real-time decision making, etc.) but comes with its challenges. This paper focuses on addressing two important research gaps in HAR research: (i) improving the HAR prediction accuracy and (ii) managing the frequent changes in the environment and data related to user activities. To address this, we propose an HAR method based on Soft-Voting and Self-Learning (SVSL). SVSL uses two strategies. First, to enhance accuracy, it combines the capabilities of Deep Learning (DL), Generalized Linear Model (GLM), Random Forest (RF), and AdaBoost classifiers using soft-voting. Second, to classify the most challenging data instances, the SVSL method is equipped with a self-training mechanism that generates training data and retrains itself. We investigate the performance of our proposed SVSL method using two publicly available datasets on six human activities related to lying, sitting, and walking positions. The first dataset consists of 562 features and the second dataset consists of five features. The data are collected using the accelerometer and gyroscope smartphone sensors. The results show that the proposed method provides 6.26%, 1.75%, 1.51%, and 4.40% better prediction accuracy (average over the two datasets) compared to GLM, DL, RF, and AdaBoost, respectively. We also analyze and compare the class-wise performance of the SVSL methods with that of DL, GLM, RF, and AdaBoost.

 Artículos similares

       
 
María Zamarreño Suárez, Juan Marín Martínez, Francisco Pérez Moreno, Raquel Delgado-Aguilera Jurado, Patricia María López de Frutos and Rosa María Arnaldo Valdés    
The use of electroencephalography (EEG) techniques has many advantages in the study of human performance in air traffic control (ATC). At present, these are non-intrusive techniques that allow large volumes of data to be recorded on a continuous basis us... ver más
Revista: Aerospace

 
Vijeta Sharma, Manjari Gupta, Ajai Kumar and Deepti Mishra    
The video camera is essential for reliable activity monitoring, and a robust analysis helps in efficient interpretation. The systematic assessment of classroom activity through videos can help understand engagement levels from the perspective of both stu... ver más
Revista: Information

 
Varsha S. Lalapura, Veerender Reddy Bhimavarapu, J. Amudha and Hariram Selvamurugan Satheesh    
The Recurrent Neural Networks (RNNs) are an essential class of supervised learning algorithms. Complex tasks like speech recognition, machine translation, sentiment classification, weather prediction, etc., are now performed by well-trained RNNs. Local o... ver más
Revista: Algorithms

 
Drago? Moraru, Ersilia Alexa, Ileana Cocan, Diana Obi?tioiu, Isidora Radulov, Eliza Simiz, Adina Berbecea, Adrian Grozea, Monica Dragomirescu, Teodor Vintila and Silvia Patruica    
Bee products have a millennia-old tradition in human apitherapy, thanks to their numerous curative properties. The aim of this study was to perform a physicochemical characterization, including the percentage of water content, dry matter, pH, acidity, im... ver más
Revista: Applied Sciences

 
Loredana Stabili, Stefano Piraino and Lucia Rizzo    
Marine bioprospecting is a dynamic research field that explores the oceans and their biodiversity as noteworthy sources of new bioactive compounds. Anthozoans are marine animals belonging to the Cnidaria phylum characterized by highly specialized mechano... ver más