2690-6791ISSN (Online)
2769-786XISSN (Print)
With the development of image handling technology, computerized technology, and the theory of image preparation, it has become clear that image processing is a crucial area of computer application. It is frequently used in many logical and designing applications, such as remote detection, medicine, meteorology, exchanges, and so on. However, with the swift development of picture preparation technology, it is becoming more and more important to precisely and successfully evaluate the quality of a picture. Recently, image quality evaluation has grown in importance as a study area in the field of developing picture data, which has attracted a lot of attention from academics. The importance of picture quality primarily takes into account two aspects: picture loyalty and picture coherence. picture quality directly depends on depending on the optical characteristics of the imaging equipment, image contrast, instrument clamor, and other factors. It may provide checking intentions to depict gaining, handling, and various connections through quality assessment. The evaluation of image quality assessment has become one of the essential breakthroughs of picture data designing to create a meaningful assessment of all components of picture preparation. People have needed to learn picture loyalty and the understandability of the quantitative estimation strategy using the picture a lot framework plan as the assessment premise for a very long time, but one of the people on the human visual characteristics is still not fully understood, in particular the description methods of psychological characteristics in human vision is also difficult to learn the quantitative evaluation of image quality, so, extensive investigation is required.
Read MoreDoi: https://doi.org/10.54216/JISIoT.070104
Vol. 7 Issue. 1 PP. 40-50, (2022)
Businesses, shops, banks, and other types of organizations all engage in cutthroat competition today. The retrieval techniques are responsible for arranging, processing, and listing the documents in the corpus in response to the user query. The strategies are distinct from one another in any of the processes stated above. As a result, the body of published work is crammed full of different retrieval theories and strategies. It is possible to combine the advantageous aspects of several different strategies to improve the retrieval systems' overall performance. Once again, the success of the merging process is dependent on the careful selection of the separate schemes that will be merged together. The selection process is carried out using optimization-seeking tools. The Genetic Algorithm is going to be used for this job. Using GA as the instrument and with the intention of evaluating both the even and the odd point crossover's effects, The odd and even point crossover is primarily employed as an exploratory tool, and its influence on the Internet of Things is evaluated throughout the information retrieval process. The enormous combination that results from the fusion function retrieval strategies and their weights may be understood as follows: The investigation is the only thing that can help us find the best answer out of all of these possible permutations. As a method of investigation, we made use of both odd and even point crossing. This exploration tool has a lack of convergence, which is a setback. It is possible to get a higher convergence rate by combining the genetic algorithm with tabu search, which is the best local search. In a scenario like this one, customer segmentation may be helpful in bringing in new customers while also helping to keep the ones you already have. An effective customer segmentation strategy for a business splits consumers into groups based on the RFM (Recency, Frequency, and Monitor) values of the Monitors. These groups have behavior in common. This will be of use to us in determining the possible customers for the firm. Following the completion of an RFM analysis, we use a conventional k-means method in order to extend the scope of the research to include clusters. Maintaining positive relationships with customers makes it much easier to market effectively to certain demographics of consumers, which in turn helps bolster a company's competitive position.
Read MoreDoi: https://doi.org/10.54216/JISIoT.070101
Vol. 7 Issue. 1 PP. 08-19, (2022)
The Internet of Things (IoT), IoT-Education, and smartness are emerging technology used in Industry 4.0 to enable smarter education systems that can be adapted to different learners. Using IoT as an acceptable and useable infrastructure is one of the leaders' innovative strategies. It is an intelligence enabler that will be integrated into many essential parts of the future world. This study looks at the key elements of smart learning structural design, such as IoT and IoB (internet of behavior), as well as the major issues that must be addressed when creating smart educational environments that allow for personalisation. To incorporate smart learning environments into the learning ecosystem and educational contexts, IoT, IoB, and cloud services for a smart education ecosystem must be used to orchestrate formal and informal learning. This study emphasizes smart learning paradigms and smart learning environments and the importance of involving future users in the design process to broaden understanding of the design and implementation of innovative systems for smart learning.
Read MoreDoi: https://doi.org/10.54216/JISIoT.070102
Vol. 7 Issue. 1 PP. 20-29, (2022)
When assessing the quality of the grain supply chain's quality, it is essential to identify and authenticate wheat types, as this is where the process begins with the examination of seeds. Manual inspection by eye is used for both grain identification and confirmation. High-speed, low-effort options became available thanks to automatic classification methods based on machine learning and computer vision. To this day, classifying at the varietal level is still challenging. Classification of wheat seeds was performed using machine learning techniques in this work. Wheat area, wheat perimeter, compactness, kernel length, kernel width, asymmetry coefficient, and kernel groove length are the 7 physical parameters used to categorize the seeds. The dataset includes 210 separate instances of wheat kernels, and was compiled from the UCI library. The 70 components of the dataset were selected randomly and included wheat kernels from three different varieties: Kama, Rosa, and Canadian. In the first stage, we use single machine learning models for classification, including multilayer neural networks, decision trees, and support vector machines. Each algorithm's output is measured against that of the machine learning ensemble method, which is optimized using the whale optimization and stochastic fractal search algorithms. In the end, the findings show that the proposed optimized ensemble is achieving promising results when compared to single machine learning models.
Read MoreDoi: https://doi.org/10.54216/JISIoT.070103
Vol. 7 Issue. 1 PP. 30-39, (2022)
The increasing integration of traditional industrial systems with smart networking and communications technology (such as fifth-generation networks, software-defined networking, and digital twin), has drastically widened the security vulnerabilities of the industrial internet of things (IIoT). Nevertheless, owing to the lack of sufficient instances of high-quality attacks, it has been incredibly difficult to resist the cyberattacks that directed at such a substantial, complicated, and dynamic IIoT. This work introduces an intelligent federated deep learning framework, termed FED-SEC, for automatic and early identification of cyber-attacks against IIoT infrastructure. In particular, a new convolutional recurrent network designed to detect cyberattacks within IIoT data. Then, a secure federated learning scheme presented to promote making use of mobile edge computing to enable the distributed IIoT entities to cooperate together to train a unified model for cyberattack detection in a privacy-preserved manner. More, a safe communication channel constructed via an improved Homomorphic Encryption scheme aiming to keep the model parameters secure against any leakage of inferential attacks, especially throughout the training procedure. Massive experimentations on multiple public datasets of IIoT cyberattacks proved the high-level efficacy of the FED-SEC in discovering different categories of cyber-attacks against IIoT and the superiorities over cutting-edge approaches.
Read MoreDoi: https://doi.org/10.54216/JISIoT.070105
Vol. 7 Issue. 1 PP. 51-61, (2022)
By using federated learning (FL), multiple Internet-of-Things (IoT) devices can construct a shared learning model without sending raw data to a centralized server. While FL has come a long way, it still has a ways to go. Issues such as heterogeneous user equipment (UEs) and data that is not independently and uniformly distributed are still obstacles. Facilitating a numerous UEs to participate in the learning in each cycle poses a possible problem of the huge communication budget. A weighted adjoining factor is presented to the localized gradient descent, generalizing the present FedAvg to solve these concerns. At the start of each global round, the proposed FL method randomly selects a fraction of the UEs to perform stochastic gradient descent in parallel. Then, we utilize the suggested FL method in cellular IoT to reduce either total power usage or execution duration of FL, in which a straightforward but effective path-following method is constructed for its explanations. At last, obtained simulations on poorly balanced data are presented to show that the presented FL algorithm is superior to FedAvg in terms of performance with respect to fast convergence. Moreover, they show that the suggested algorithm needs significantly less time and energy to train than the FL algorithm does when users contribute heavily to the learning process. These findings provide strong support for the suggested FL algorithm as a potential paradigm change for training mobile IoT networks with limited bandwidth.
Read MoreDoi: https://doi.org/10.54216/JISIoT.070106
Vol. 7 Issue. 1 PP. 62-73, (2022)