The increasing global population and reliance on electrical devices for daily life resulted in sharply rising energy consumption. Also, this leads to higher household electricity bills. As a result, there is a growing demand for energy monitoring systems that can accurately estimate energy usage to help save power, especially for older home appliances that are difficult or expensive to update with monitoring sensors. However, current energy monitoring systems have some drawbacks, such as the inability to detect different types of appliances and the deployment complexity. Moreover, such systems are too costly to use in older power infrastructures. To address this issue, we proposed a centralized smart energy monitoring system designed for legacy home appliances, aiming to address the limitations of current energy monitoring systems by avoiding costly infrastructure upgrades to calculate the power consumption of legacy home appliances. The proposed system employs a two-layered architecture comprising hardware (Emontx device, Analog-to-Digital Converters (ADC), and Current Transformer (CT) sensors) and a software layer that includes Artificial Intelligence (AI) predictors using a pre-defined set of rules and K Nearest Neighbours (KNN) algorithms. We conducted three experiments on real home appliances to evaluate the proposed work. The accuracy of the proposed system showed positive results after several modifications and hard tuning of several parameters in devices, specifically for Jordanian power plants.
22 August 2024 in Peer-to-Peer Networking and Applications
This study investigated the performance of various machine learning algorithms in predicting transportation modes from large datasets. The investigated algorithms include Multilayer Perceptron (MLP), K-Nearest Neighbors (KNN), Decision Tree, Long Short-Term Memory (LSTM), Recurrent Neural Network (RNN), and Logistic Regression. We rigorously evaluated each algorithm's performance using a robust set of metrics such as precision, recall, and F1-score. This study comprehensively explains the algorithm's capabilities, strengths, and potential weaknesses across seven transportation categories: 'walk', 'bike', 'bus', 'car', 'taxi', 'train', and 'subway'. The Decision Tree (DT) model consistently outperformed the others, demonstrating superior accuracy and a better balance of precision and recall across all modes of transportation. Specifically, it achieved precision, recall, and F1 scores of around 83\% to 94\% across all categories. These findings underline the suitability of the DT model for this classification task and its potential for further applications in transportation mode prediction based on large datasets. However, other algorithms like LSTM and RNN also showed promising results in certain categories, suggesting the value of continued exploration of different models depending on specific use cases.
The analysis of students’ educational achievements at a university is beneficial for the university, society and students. This study aims to search for the various attributes related to academic student’s achievements. The subjects of the study were 3509 graduated students at the Applied Science Private University in Jordan from all department programs of the Faculty of Information Technology. The study is intended to analyze students profile and find its relation to and association with their university GPA (Grade Point Average) by selecting four main attributes related to the students: department, secondary certificate grade, secondary certificate city, and gender. Then it is intended to find the high effecting value for each attribute, and create main association rules through using data mining classifier like (Decision tree, naïve bayse and association rules). Finally, the result of this study may help current and new faculty students to predict the possible obtained GPA to control their performance and try to enhance it.
1 January 2023 in International Journal of Data and Network Science
The current mobile network core is built based on a centralized architecture, including the S-GW and P-GW entities to serve as mobility anchors. Nevertheless, this architecture causes non-optimal routing and latency for control messages. In contrast, the fifth generation (5G) network will redesign the network service architecture to improve changeover management and deliver clients a better Quality-of-Experience (QoE). To enhance the design of the existing network, a distributed 5G core architecture is introduced in this study. The control and data planes are distinct, and the core network also combines IP functionality anchored in a multi-session gateway design. We also suggest a control node that will fully implement the control plane and result in a flat network design. Its architecture, therefore, improves data delivery, mobility, and attachment speed. The performance of the proposed architecture is validated by improved NS3 simulation to run several simulations, including attachment and inter- and intra-handover. According to experimental data, the suggested network is superior in terms of initial attachment, network delay, and changeover management.
1 January 2018 in International Journal of Advanced Computer Science and Applications
Steganography is a form of security technique that using ambiguity to hide a secret message within an ordinary message between senders and receivers. In this paper, we propose a new steganography technique for hiding data in Joint Photo-graphic Experts Group (JPEG) images as it is the most known type of image compression between the lossy type compressions. Our proposed work is based on lossy compression (frequency domain) in images. This type of compression is susceptible to change even for the smallest amount of change which raises a difficulty to find a proper location to embed data. This should be done without affecting the image quality and without allowing anyone to notice the hidden message. From the senders side, first, we divide the image into 8*8 blocks, then apply a Discrete Cosine Transform (DCT), Quantization, and zigzag processes respectively. Second, the secret message is embedded at the end of each selected zigzag block array using the best method of our experimental results. Third, the rest of the code applies the Run Length Code (RLC), Different Pulse Code Modularity (DPCM) and Huffman encoder to obtain the compressed image that includes the embedded message. From the receiver’s side, we will reverse the previous steps to extract the secret message using an encrypted shared key via a secure channel. Our experimental results show that the best array content size of zigzag computed coefficients are between 1 to 20. This selection allows us to utilize more than half of the image blocks to embed the secret message and the difference between the cover image that holds the secret message and the original cover image is very minimal and hard to detect.