2690-6791ISSN (Online)
2769-786XISSN (Print)
As service-oriented architecture gains in popularity and grows in popularity, Web service recommendation and composition have become more important topics for research. Accurately predicting individualized QoS recommendations for recommending web services is a difficult task because of the inconsistency of the Internet and the scarcity of information regarding QoS history. Our team suggests a new framework for QoS values’ prediction and also presents two methods for clustering, User_BC and Service_BC, to support QoS prediction accuracy. Hierarchical clustering is used, based on the QoS dataset of PlanetLab1 (that) contains 200 service-user response time values, with 1,597 service values overall. In our research, we've found that our clustering-based methods beat other popular algorithms in detailed experimental comparisons and analyses.
Read MoreDoi: https://doi.org/10.54216/JISIoT.000101
Vol. 0 Issue. 1 PP. 05-14, (2019)
Recently, information security in the healthcare sector has become essential to ensure confidentiality in medical data. At the same time, automated disease diagnosis using deep learning (DL) models also gained considerable attention to accomplish enhanced classification performance. This paper designs an intelligent neighborhood indexing sequence based on encoding with a classification model for healthcare information security (INISEC-HIS). The proposed INISEC-HIS technique aims to accomplish security in medical data transmission and diagnosis. The neighborhood indexing sequence (NIS) technique is applied to securely transmit the data, which transforms the medical data into an encoded format. Besides, a novel artificial fish swarm algorithm (AFSA) with deep neural networks (DNN) model is used for the classification process. The design of AFSA to optimally adjust the hyperparameters of the DNN model shows the study's novelty. An extensive simulation analysis takes place to examine the improved outcomes of the INISEC-HIS technique, and the obtained results highlighted the supremacy over the other techniques.
Read MoreDoi: https://doi.org/10.54216/JISIoT.000102
Vol. 0 Issue. 1 PP. 15-25, (2019)
Digital image security plays an essential role in the shared communication model. Encryption and decryption process is commonly applied to securely transmit the images in various real-time applications. In addition, the generation of encryption/decryption keys is also essential to achieve enhanced image security. This study presents a multiple share creation scheme with an optimal signcryption (MSS-OSC) technique for digital image security. The MSS-OSC technique primarily generates a set of various shares for every digital image that needs to be transmitted. In addition, the encryption of generated shares takes place via the optimal signcryption (OSC) technique. Moreover, genetic programming (GP) is employed to optimally choose the keys involved in the encryption and decryption process. The detailed experimental validation of the MSS-OSC technique is investigated using a set of benchmark test images. The results analysis demonstrated that the MSS-OSC technique had a superior performance by accomplishing maximum digital image security.
Read MoreDoi: https://doi.org/10.54216/JISIoT.000103
Vol. 0 Issue. 1 PP. 26-36, (2019)
The logistics industry is a complex and dynamic ecosystem that requires efficient and reliable asset tracking systems (IATS) to optimize operations and reduce costs. To address these challenges, an IATS is proposed in this paper that leverages the power of IoT and big data technologies to collect real-time data on the location, condition, and status of assets such as trucks, containers, and shipments. The system is designed to provide end-to-end visibility and control of assets throughout the logistics value chain. It uses a combination of RFID, GPS, and other tracking technologies to collect data on asset location, temperature, humidity, vibration, and other relevant parameters. The data is then transmitted to a cloud-based platform for storage, processing, and analysis using big data analytics and machine learning algorithms. The platform enables logistics companies to monitor and manage their assets in real-time, optimize routes and schedules, and improve delivery times. It also provides machine learning tools for predictive modeling of asset price movement, enabling companies to identify potential price changes before they occur and minimize loss. The efficiency and effectiveness of our system were shown through simulation studies using data from real-world assets; as a result, it is an attractive option for the tracking and management of assets in real-world logistic businesses.
Read MoreDoi: https://doi.org/10.54216/JISIoT.000104
Vol. 0 Issue. 1 PP. 37-47, (2019)