To record and evaluate students’ physical education (PE) class participation, this study proposes using machine learning aided physical training framework (ML-PTF). Improve student achievement in PE with the help of the Multi-level Fusion System that employs machine learning strategies. The system integrates sensor data, video data, and contextual data to deliver a holistic and precise evaluation of student engagement. This study’s simulation analysis shows that the ML-PTF improves the reliability of evaluating universities’ PE programs. A important reference path and paradigm for advancing tertiary-level PE for graduates, the multi-level fusion system also provides an investigation of information technology and language education integration. The experimental findings demonstrate that the ML-PTF is superior to other approaches in terms of learning rate, f1-score, precision, and probability, as well as student engagement, involvement, and recognition accuracy.
Read MoreDoi: https://doi.org/10.54216/JISIoT.090101
Vol. 9 Issue. 1 PP. 08-23, (2023)
The DTA-LI system's fusion data method is crucial in the monitoring of appliance loads for the purposes of improving energy efficiency and management. Common home electrical devices are identified and classified from smart meter data through the analysis of voltage and current variations, allowing for the measurement of energy usage in residential buildings. A load identification system based on a decision tree algorithm may infer information about the residents of a building based on their energy usage habits. Better power savings rates, load shedding management, and overall electrical system performance are the results of the clusters' ability to capture families' purchasing patterns and geo-Demographic segmentation. The DTA-LI system's fusion data method presents a promising avenue for improving residential buildings' energy performance and lowering their carbon footprint, especially in light of the widespread use of smart meters in recent years.
Read MoreDoi: https://doi.org/10.54216/JISIoT.090102
Vol. 9 Issue. 1 PP. 24-35, (2023)
Natural computation, motivated by the organic game arrangement, is a knowledge base field that formalizes the measurements seen in living organic entities to plan machine techniques to tackle complicated issues or to plan artificial structures with additional traditional behaviors. Seeable corporations disconnected from natural wonders, reminiscent of mind demonstration, self-association, self-redundancy, Darwinian resistance, self-evaluation, discernment, and granulation, nature is crammed as a supply of motivation to advance competition. Computational devices or frameworks accustomed solve complex problems. The ideal, nature-motivated primary computation models used for such sweetening incorporate artificial neural organizations, spongy reasoning, arduous set, biological process calculations, shape mathematics, DNA registration, artificial life, And granular or insight-based processing. The granulation of information within the granular register is an innate attribute of human thought and therefore the life of thought acted call at regular daily existence. This paper illustrates the importance of normal recording in terms of granulation-based data preparation models, for example, neural organizations, soft and ugly sets, and their hybridization. we have a tendency to emphasize the bio-sensitive inspiration, designing standards, application zones, open scan problems, and testing issues for these models.
Read MoreDoi: https://doi.org/10.54216/JISIoT.090104
Vol. 9 Issue. 1 PP. 49-68, (2023)
The collection of fetures in both multispectral and hyperspectral domains is possible with Hyperspectral Image (HSI). It comprises a vast array of multispectral bands with functional relationships. However, they become more complex when dealing with small samples. To tackle this issue, researchers employed a deep learning convolutionary neural network system (DL-CNN) and implemented a temporal abstraction strategy to grade HSI. This approach is an intelligent multi-level feature fusion that combines the temporal abstraction strategy and DL-CNN for HSI grading. Researchers have introduced the impact of seven separate classifiers in implementing the Location estimation on our broad CNN framework, which plays the shallow CNN model's main training phase. PSO, Adagrad, Plans to implement, Alexnet, Adam, Environmental benefits, and Nadam are the seven distinct remained significantly included in this analysis. A detailed study of the four multispectral remote sensing techniques sets showed the deep CNN system's supremacy followed with the HSI identification AlexNet Optimizer.
Read MoreDoi: https://doi.org/10.54216/JISIoT.090103
Vol. 9 Issue. 1 PP. 36-48, (2023)
Problems in autonomous systems may be tackled with the help of the AS-FC-DL approach, which integrates autonomous fuzzy clustering and deep learning methods. The system can anticipate human behavior on crowded roadways by employing these techniques to recognize patterns and extract features from complicated unsupervised data. Each image point's membership value is associated with the cluster's epicenter using the fuzzy clustering methodology in the AS-FC-DL approach. Using least-squares methods, this approach finds the optimal position for each data point within a probability space, which may be anywhere among multiple clusters. Data points from an unlabeled dataset may be organized into distinct groups using a deep learning technique called cluster analysis. Data fusion from many sources, including sensor data and video data, can improve the AS-FC-DL method's precision and performance. The algorithm is able to deliver an all-encompassing and precise evaluation of human behavior on crowded roadways by fusing data from many sources. The AS-FC-DL approach may also be employed in autonomous vehicles to help them learn from their experiences and improve their performance. Using reinforcement learning, a model for autonomous vehicle driving may be constructed. The AS-FC-DL approach helps the self-driving car traverse the area with increased precision and efficiency by allowing it to recognize structures and extract features from complicated unsupervised data.
Read MoreDoi: https://doi.org/10.54216/JISIoT.090105
Vol. 9 Issue. 1 PP. 69-83, (2023)