2690-6791ISSN (Online)
2769-786XISSN (Print)
The fast advancement of technology has contributed to a rise in everyone's demand to be connected to the internet. The Internet of Things is a notion that emerged with the fourth industrial revolution as a result of the finding that things that were born of the Internet can connect without the need for external causes (IoT). The communication of items with one another ensures that firms will spend as little time and money as possible on labor. Businesses that want to make the switch to the Internet of Things are going to run across a lot of challenges. The process of identifying and fixing these issues may result in both time and financial waste. Within the scope of this research, we looked at the challenges that are associated with the IoT. As a consequence of the research, the level of relevance of the elements that are generating these challenges was figured out using multi-criteria decision-making (MCDM) procedures, and the findings were given to the businesses. We decided on the primary criteria, as well as the secondary criteria that are connected to these primary criteria. The communication of different objects with one another is the primary goal of businesses that are making the shift to Industry 4.0. The purpose of this research was to identify the factors that contributed to the challenges encountered throughout the evolution to Industry 4.0. In the next step of the MCDM process, the DEMATEL approach was used to evaluate the level of significance associated with each of the factors. As a result of the research, we were able to establish which factors should be regarded as important for businesses that are interested in making the shift to the IoT. In this approach, businesses will be able to speed up the transition while limiting the amount of time and money lost in the process.
Read MoreDoi: https://doi.org/10.54216/JISIoT.070202
Vol. 7 Issue. 2 PP. 22-29, (2022)
The Internet of Medical Things (IoMT) offers numerous advantages in the diagnosis, monitoring, and treatment of a wide variety of illnesses for both patients. COVID-19 has caused a global pandemic and turned out to be the utmost crucial danger threatening the whole world. Thus, scholars’ attention moved toward Deep learning (DL) and IoMT for developing automated systems for COVID-19 diagnosis and/or prognosis based on chest computed tomography (CT) scans, and it has shown great success in several tasks, including classification and segmentation. Nevertheless, developing and training a superior DL approach necessitates accumulating a substantial amount of patients’ CT scans together with their labels. This is an expensive and time-consuming task that restricts attaining large enough data from a single site/institution, However, owing to the necessity for protecting data privacy, it is difficult to accumulate the data from several sites and store them at a centralized server. Federated learning (FL) alleviates the need for centralized data by spreading the public segmentation model to different institutional models, training the segmentation model at the institution, and followingly calculating the mean of the parameters in the public model. Nevertheless, researchers advocated that private information could be restored using the parameters of the model. This study presents a privacy-protection technique for the challenge of multi-site COVID-19 segmentation. To tackle the challenge, we introduce the FL technique, in which a distributed optimization procedure is developed, and randomization techniques are proposed to change the joint parameters of private institutional segmentation models. Bearing in mind the complete heterogeneity of COVID-19 distributions from diverse institutions, we develop two domain adaptation (DA) techniques in the proposed FL design. We explore several applied characteristics of optimizing the FL approach and analyze the FL approach in comparison with alternate training approaches. Finally, the results validate that it is auspicious to employ multi-site non-shared CT scans to improve the COVID-19 infection segmentation.
Read MoreDoi: https://doi.org/10.54216/JISIoT.070201
Vol. 7 Issue. 2 PP. 08-21, (2022)
The discipline of Supply Chain Management (SCM) is getting more difficult to master. It is necessary to address information silos on the demand and production frontiers of goods in order to execute the de-coupling factor in the preferences of customers who are engaged in a supply chain to optimize business performance, which in today's world has become a difficulty. The so-called "Amazon Effect" has, once again, compelled competitors to rethink their approaches to achieving maximum efficiency. The Analytic Hierarchy Process (AHP), which is part of the Multi-Criteria Decision Making (MCDM) Approaches, has been used to offer the preferences of clients of various criteria versus various features (products). AHP is used to compute the weights of criteria, then rank the various alternatives. The AHP method is used to build the pairwise comparison between criteria to check the importance of these criteria. The AHP method checks the consistency of the experts to ensure all data is consistent.
Read MoreDoi: https://doi.org/10.54216/JISIoT.070203
Vol. 7 Issue. 2 PP. 30-39, (2022)
The process of making an informed decision on which Internet of Things (IoT) platform to choose is an extremely important one in the modern world. The choice procedure is made more difficult as a result of (a) the vast number of IoT platforms that are offered on the market for IoT applications and (b) the wide diversity of functions and solutions that are provided by these platforms. In this article, the multi-criteria decision-making (MCDM) methodologies for selecting the specific Internet of Things platform are taken into consideration. The TOPSIS method is used in this paper to select the best IoT platform. TOPSIS method is a common MCDM method. TOPSIS method used the idea of the best and cost criteria to compute the distance from it. During the IoT platform choice procedures, relevant aspects, such as the stability, consistency, protection, and privacy of IoT platforms, are regarded to be the most significant ones for making decisions.
Read MoreDoi: https://doi.org/10.54216/JISIoT.070204
Vol. 7 Issue. 2 PP. 40-50, (2022)
Food image recognition system has various applications now a day. In this paper, we have used a machine learning supervised approach and Support Vector Machine to classify different food images. SVM has been classified to detect and recognize food images with the least modification. By applying various filters like a texture filter, a segmentation method, clustering, and a SVM approach we have achieved more accuracy than other machine learning approaches with manually extracting features. Sustenance is an indivisible piece of people groups lives. we tend to apply a convolution neural network (CNN) to the undertakings of analyst work and perceiving sustenance pictures. Clarification for the wide decent variety of styles of nourishment, and picture acknowledgment of sustenance things are typically unpleasant difficulties. Nevertheless, profound learning has been demonstrated starting late to be a genuinely extreme picture acknowledgment framework, and CNN could be a dynamic approach to managing profound learning. CNN showed on a very basic level higher precision than did old-fashioned help vector-machine-based courses with carefully assembled decisions. For sustenance picture disclosure, CNN likewise demonstrated fundamentally count higher precision than a standard technique. Generally higher precision than standard techniques.
Read MoreDoi: https://doi.org/10.54216/JISIoT.070205
Vol. 7 Issue. 2 PP. 51-59, (2022)
This study presents a novel framework to help people with color impairment in identifying colors. The proposed framework consists of three stages. These stages are electronically performing the Ishihara test, performing the color blindness type recognition test, and guiding the person to color by voice. The first stage, the person is subjected to an electronic color blindness test, by displaying different plates containing several points of different sizes and colors. The person is required to correctly identify the number or shape in the plate and at the end, the system determines the extent to which a person is color blind. The second stage is a color recognition test to determine the type of color blindness. If there is difficulty in determining red, this is called protanopia. But the difficulty in identifying the green color is called deuteranopia. While the inability to recognize the blue color is called tritanopia. And finally, the difficulty in identifying the colored style is called achromatopsia. The third stage is assistance phase and is divided into three subsectors are: smart educational system, identifying colors and extracting the content. The proposed system differs from other systems in that it is an integrated system. It includes identifying color blindness, determining its type, and finally aiding color blindness person. Also, it is the first system that deals with the rare type of color blindness called achromatopsia in addition to its other three types. The results obtained confirmed that the proposed system as well as the smart educational system are characterized by high accuracy and effectiveness.
Read MoreDoi: https://doi.org/10.54216/JISIoT.070206
Vol. 7 Issue. 2 PP. 60-70, (2022)
The Internet of Things (IoT) has become a ubiquitous technology that enables the collection and analysis of large amounts of data. However, the limited resources of IoT devices pose challenges to enabling responsive decision-making. Many communications are required for network training, yet network updates can be very big if they include many parameters. Participants and the IoT ecosystem both bear the brunt of federated learning's high Latency due to the magnitude of its communications infrastructure requirements. In this paper, we propose a Federated Knowledge Purification (FKP) approach based on dynamic reciprocal knowledge purification and adaptive gradient compression, two strategies that allow for low-latency communication without sacrificing effectiveness, which enables responsive IoT devices with limited resources. The FKP approach leverages a collaborative learning approach to enable IoT devices to learn from each other's experiences while preserving the privacy of their data. A smaller model is trained on the aggregated knowledge of a larger model trained on a centralized server, and this smaller model can be deployed on IoT devices to enable responsive decision-making with limited computational resources. Experimental results demonstrate the effectiveness of the proposed approach in improving the performance of IoT devices while maintaining the privacy of their data. The proposed approach also outperforms existing federated learning methods in terms of communication efficiency and convergence speed.
Read MoreDoi: https://doi.org/10.54216/JISIoT.070207
Vol. 7 Issue. 2 PP. 71-80, (2022)