Intelligent Media - Wearable Smart Home Activities (IM-WSHA) Dataset
Abstract
We have introduced a smart home dataset using three triaxial IMU(inertial measurement unit) sensors attached to the subject wrist, chest, and thigh region to capture important aspects of human motion. The dataset represents motion data captured while subjects are involved in performing 11 different (static and dynamic) smart home activities: Using Computer (1min), phone conversation (1 min), vacuum cleaning (1min), reading book (1 min), watching tv(1 min) , ironing (1 min), walking (1 min), exercise (1 min), cooking (1 min), drinking (20 times), brushing hair (20 times). The subjects involved both young and old volunteers who aged between 19-60 with having weight ranging between 55-85 kgs. Due to multi-sensor environment, most of the movements in activities are highly similar to each other, which make this dataset quite challenging.
― Dataset includes 220 sequences of inertial data from three body worn inertial measurement unit sensors with variable time duration (between 45s to 60s).
― For training the system, we used 10 subjects who performed activities in repetitive in nature.
― In testing sets, we used a combination of repetitive and passive movement from each activity set.
This dataset is freely available to academic or research activities. Please feel free to visit
portals.au.edu.pk/imc
File (1)
Content uploaded by Sheikh Badar ud din Tahir
Author content
... The first benchmark dataset-the IM-Wearable Smart Home Activities (IM-WSHA) [42] database-contains signal data from five IMU sensors, including three-axis accelerometers, gyroscopes, and magnetometers. Additionally, these IMU sensors were incorporated into three separate bodily regions, the chest, thigh, and wrist, to extract real-time human motion features of daily living activities. ...
Human physical activity recognition from inertial sensors is shown to be a successful approach for monitoring elderly individuals and children in indoor and outdoor environments. As a result, researchers have shown significant interest in developing state-of-the-art machine learning methods capable of utilizing inertial sensor data and providing key decision support in different scenarios. This paper analyzes data-driven techniques for recognizing human daily living activities.
Therefore, to improve the recognition and classification of human physical activities (for example, walking, drinking, and running), we introduced a model that integrates data preprocessing methods (such as denoising) along with major domain features (such as time, frequency, wavelet, and time–frequency features). Following that, stochastic gradient descent (SGD) is used to improve the performance of the extracted features. The selected features are catered to the random forest classifier to detect and monitor human physical activities. Additionally, the proposed HPAR system was
evaluated on five benchmark datasets, namely the IM-WSHA, PAMAP-2, UCI HAR, MobiAct, and MOTIONSENSE databases. The experimental results show that the HPAR system outperformed the present state-of-the-art methods with recognition rates of 90.18%, 91.25%, 91.83%, 90.46%, and 92.16% from the IM-WSHA, PAMAP-2, UCI HAR, MobiAct, and MOTIONSENSE datasets, respectively. The proposed HPAR model has potential applications in healthcare, gaming, smart homes, security, and surveillance.
... The second dataset IM-SB [55][56][57][58], embodies motion data from three wearable accelerometers. These sensors are placed at different body positions such as the wrist, neck, and knee to record different human motion patterns. ...
Wearable inertial based sensors are strong enablers for the acquisition of human daily life-log data. Eventually, many motion devices have often degraded the performance of wearable sensors due to inner/outer environmental effects. In addition, key decisions are made based on human life-log recognition results and precise recognition of human life-logs with lower limits of uncertainty is significantly important. For this purpose, many motion devices have been used in last decade, in order to recognize daily life activities. In this paper, we proposed an efficient model for better recognition results for healthcare patient's daily life-log patterns. We designed a 1D Haar based extraction algorithm and different statistical features to extract valuable features. For activity classification, we used Quadratic Discrimination Analysis (QDA) optimized by Artificial Neural Network (ANN) on two benchmarks PAMAP2 dataset and our self-annotated IM-SB database. The outcome of our system illustrates that our proposed model competes with other advanced methods in term of exactness and effectiveness.
... The second dataset IM-SB [55][56][57][58], embodies motion data from three wearable accelerometers. These sensors are placed at different body positions such as the wrist, neck, and knee to record different human motion patterns. ...
Wearable inertial based sensors are strong enablers for the acquisition of human daily life-log data. Eventually, many motion devices have often degraded the performance of wearable sensors due to inner/outer environmental effects. In addition, key decisions are made based on human life-log recognition results and precise recognition of human life-logs with lower limits of uncertainty is significantly important. For this purpose, many motion devices have been used in last decade, in order to recognize daily life activities. In this paper, we proposed an efficient model for better recognition results for healthcare patient's daily life-log patterns. We designed a 1D Haar based extraction algorithm and different statistical features to extract valuable features. For activity classification, we used Quadratic Discrimination Analysis (QDA) optimized by Artificial Neural Network (ANN) on two benchmarks PAMAP2 dataset and our self-annotated IM-SB database. The outcome of our system illustrates that our proposed model competes with other advanced methods in term of exactness and effectiveness.
ResearchGate has not been able to resolve any references for this publication.