Performance-enhanced real-time lifestyle tracking model based on human activity recognition (PERT-HAR) model through smartphones

Ishwarya, K.; Nithya, A.

doi:10.1007/s11227-021-04065-z

Cited by 6 publications

(3 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…, n − 1}. The BF technique substitutes the middle pixel of every filter window via a weighted average of the nearby color pixels [19,20]. The weight function can be defined for smoothening the regions of identical colors by maintaining the edges together by deeply weighting the pixels which are spatially close and photometrically comparable to the intermediate pixel.…”

Section: Pre-processingmentioning

confidence: 99%

Squirrel Search Optimization with Deep Convolutional Neural Network for Human Pose Estimation

Ishwarya¹,

Nithya²

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

Human pose estimation (HPE) is a procedure for determining the structure of the body pose and it is considered a challenging issue in the computer vision (CV) communities. HPE finds its applications in several fields namely activity recognition and human-computer interface. Despite the benefits of HPE, it is still a challenging process due to the variations in visual appearances, lighting, occlusions, dimensionality, etc. To resolve these issues, this paper presents a squirrel search optimization with a deep convolutional neural network for HPE (SSDCNN-HPE) technique. The major intention of the SSDCNN-HPE technique is to identify the human pose accurately and efficiently. Primarily, the video frame conversion process is performed and pre-processing takes place via bilateral filtering-based noise removal process. Then, the EfficientNet model is applied to identify the body points of a person with no problem constraints. Besides, the hyperparameter tuning of the EfficientNet model takes place by the use of the squirrel search algorithm (SSA). In the final stage, the multiclass support vector machine (M-SVM) technique was utilized for the identification and classification of human poses. The design of bilateral filtering followed by SSA based EfficientNet model for HPE depicts the novelty of the work. To demonstrate the enhanced outcomes of the SSDCNN-HPE approach, a series of simulations are executed. The experimental results reported the betterment of the SSDCNN-HPE system over the recent existing techniques in terms of different measures.

show abstract

Section: Pre-processingmentioning

confidence: 99%

Squirrel Search Optimization with Deep Convolutional Neural Network for Human Pose Estimation

Ishwarya¹,

Nithya²

2023

Computers, Materials &Amp; Continua

View full text Add to dashboard Cite

show abstract

“…erefore, when selecting the historical data file for playback, the system decompresses the selected data file to generate a temporary file and restore it to the original readable state, so that the system can read the contents of the file for data playback. When the user selects the next history file to open, or when the user exits the module, the temporary file will be deleted [20]. e flowchart of single machine/multimachine mode historical data playback is shown in Figure 12.…”

Section: Single Machine Multimachine Mode and Historicalmentioning

confidence: 99%

Improvement of English Classroom Teaching Effect Based on Real-Time Supervision of Student Status

Yin

2022

Mobile Information Systems

View full text Add to dashboard Cite

For English courses, the interaction between teachers and students in the classroom teaching process has a crucial impact on the improvement of classroom teaching effects, and through real-time supervision of students’ classroom learning status, students’ learning dynamics and learning effects can be grasped in time. For this reason, this paper proposes a learning state semisupervised learning method and real-time state monitoring system based on a clustering algorithm and a self-training SVM classification algorithm. At the same time, combined with the reform of English classroom teaching, the teaching effect can be improved to the greatest extent through the supervision of students’ learning state. The experimental results show that monitoring the primary school English classroom teaching quality subject and providing skill training can help the primary school English classroom teaching quality subject predict the possible situation in the monitoring and prepare in advance in terms of thinking and skill teaching. Schools can urge primary school English classroom teaching quality monitoring subjects to have basic monitoring knowledge literacy, monitoring ability literacy, and monitoring moral literacy through primary school English classroom teaching quality monitoring knowledge training, skill training, and moral training. On the basis, the main body of primary school English classroom teaching quality monitoring can give full play to the role of the main body of monitoring when it organizes and implements monitoring. It is proved that real-time supervision of students’ status can effectively improve the effect of English classroom teaching.

show abstract

“…Human Activity Recognition (HAR) has garnered significant attention due to its potential to improve the quality of life in daily tasks by providing real-time monitoring and feedback across various fields. These applications range from activity and healthcare assistance [ 1 , 2 ], fitness [ 3 ], muscular rehabilitation [ 4 ], occupational safety [ 5 ], smart home monitoring [ 6 ], and driver monitoring [ 7 ]. For HAR, traditional machine learning techniques, such as support vector machines (SVM), K-Nearest Neighbors (KNN), and random forest trees [ 8 , 9 ], have been used in these applications.…”

Section: Introductionmentioning

confidence: 99%

Human Activity Prediction Based on Forecasted IMU Activity Signals by Sequence-to-Sequence Deep Neural Networks

Jaramillo

Chola

Jeong

et al. 2023

Sensors

View full text Add to dashboard Cite

Human Activity Recognition (HAR) has gained significant attention due to its broad range of applications, such as healthcare, industrial work safety, activity assistance, and driver monitoring. Most prior HAR systems are based on recorded sensor data (i.e., past information) recognizing human activities. In fact, HAR works based on future sensor data to predict human activities are rare. Human Activity Prediction (HAP) can benefit in multiple applications, such as fall detection or exercise routines, to prevent injuries. This work presents a novel HAP system based on forecasted activity data of Inertial Measurement Units (IMU). Our HAP system consists of a deep learning forecaster of IMU activity signals and a deep learning classifier to recognize future activities. Our deep learning forecaster model is based on a Sequence-to-Sequence structure with attention and positional encoding layers. Then, a pre-trained deep learning Bi-LSTM classifier is used to classify future activities based on the forecasted IMU data. We have tested our HAP system for five daily activities with two tri-axial IMU sensors. The forecasted signals show an average correlation of 91.6% to the actual measured signals of the five activities. The proposed HAP system achieves an average accuracy of 97.96% in predicting future activities.

show abstract

Performance-enhanced real-time lifestyle tracking model based on human activity recognition (PERT-HAR) model through smartphones

Cited by 6 publications

References 33 publications

Squirrel Search Optimization with Deep Convolutional Neural Network for Human Pose Estimation

Squirrel Search Optimization with Deep Convolutional Neural Network for Human Pose Estimation

Improvement of English Classroom Teaching Effect Based on Real-Time Supervision of Student Status

Human Activity Prediction Based on Forecasted IMU Activity Signals by Sequence-to-Sequence Deep Neural Networks

Contact Info

Product

Resources

About