Comparative analysis of HAR datasets using classification algorithms

Abstract

In the current research and development era, Human Activity Recognition (HAR) plays a vital role in analyzing the movements and activities of a human being. The main objective of HAR is to infer the current behaviour by extracting previous information. Now-a-days, the continuous improvement of living condition of human beings changes human society dramatically. To detect the activities of human beings, various devices, such as smartphones and smart watches, use different types of sensors, such as multi modal sensors, non-video based and video-based sensors, and so on. Among the entire machine learning approaches, tasks in different applications adopt extensively classification techniques, in terms of smart homes by active and assisted living, healthcare, security and surveillance, making decisions, tele-immersion, forecasting weather, official tasks, and prediction of risk analysis in society. In this paper, we perform three classification algorithms, Sequential Minimal Optimization (SMO), Random Forest (RF), and Simple Logistic (SL) with the two HAR datasets, UCI HAR and WISDM, downloaded from the UCI repository. The experiment described in this paper uses the WEKA tool to evaluate performance with the matrices, Kappa statistics, relative absolute error, mean absolute error, ROC Area, and PRC Area by 10-fold cross validation technique. We also provide a comparative analysis of the classification algorithms with the two determined datasets by calculating the accuracy with precision, recall, and F-measure metrics. In the experimental results, all the three algorithms with the UCI HAR datasets achieve nearly the same accuracy of 98%.The RF algorithm with the WISDM dataset has the accuracy of 90.69%,better than the others.

Ensemble Empirical Mode Decomposition for Automated Denoising of Pulse Signals

“…The approach outlined in this paper is employed to segment the noise region within the weak pulse signal, with the resulting divisions illustrated in Fig. Denoising tests on the weak pulse signal are conducted, with the method from reference [19], the approach from reference [20], and the method detailed in [21] serving as the comparative methods. The weak pulse signal containing noise is depicted in Fig.…”

Class probability distribution based maximum entropy model for classification of datasets with sparse instances

“…Classification and prediction are the most common methods that researchers use in all areas to find solutions to various problems. A few of the domain applications where classification and prediction are used frequently include the educational field (students' performance classification, result prediction) [4], bank and financial sectors (customers classification based on their credit risk, fraud detection) [5], health care industries (diagnosing the disease based on the past data containing symptoms) [6], agricultural field (analysing soil nutrients and crop prediction) [7], retail industries (customer churn and sales prediction) [8], classifying spam or junk emails [9], weather forecasting and rainfall prediction [10], predicting current behaviour by analyzing the human activities [11], classifying customer segment [12], classifying attack traffic from normal network traffic [13], software defect prediction [14] and even more.…”

Defending Against Local Adversarial Attacks through Empirical Gradient Optimization

“…Local adversarial attacks refer to targeted methods that introduce small, imperceptible perturbations to input samples to deceive the models and cause misclassification or incorrect outputs. Deep learning models have achieved remarkable success in tasks such as image classification [21][22][23][24], object detection [25], natural language processing [26], and speech recognition. However, they have also exhibited a high sensitivity to input data.…”