Trustworthy Federated Graph Learning Framework for Wireless Internet of Things

Abedallah Z.; Rasha; William

doi:https://doi.org/10.54216/IJWAC.060105

American Journal of Business and Operations Research | 2021

The CoP’s Role in Introducing New Technology in Cultural Organizations

This study assessed the problem of the development of new technology and knowledge management in cultural organizations. The specific role of the community of practice (CoP) as an instrument of change management and knowledge generation in cultural organizations was considered. In terms of the study problem, qualitative research methods were used for the analysis of the academic literature and practical cases of libraries in Florida. The outcomes of the study demonstrated that the CoP did not play a negative role in the process of new technology integration in cultural organizations. In contrast, CoPs played a serious positive role thus generating ideas for innovations and supporting the personnel of libraries in their development. Concerning sources of barriers, the lack of resources, limited capabilities of librarians, and low support of management were considered the main issues. Further research should identify specific recommendations applicable for the improvement of the situation and sharing of the best experience in the sphere of digital transformation of cultural organizations.

groups

Eman Alyousuf mail -

Faris Almansour mail

link https://doi.org/10.54216/AJBOR.050203

Volume & Issue

Vol. Volume 5 / Iss. Issue 2

Details open_in_new

Journal of Neutrosophic and Fuzzy Systems | 2025

Study of The Period of Infection With The Covid-19 Until Death Using The Triple Left Truncated Exponential Distribution

In this paper, we are concerned with truncated distributions that have multiple truncations,  due to being very useful in representing natural phenomena that cannot be studied at all intervals of their growth or development, for example, phenomena that are related to Agriculture, airplanes, health, and the environment.  left truncation is utilized in this study. The statistical characteristics, such as the rth moments, moment generating function, order statistics,  reliability function, hazard rate function, and reversed  Hazard function, have been introduced. triple left truncated exponential distribution has been applied.  Employed the maximum likelihood method to estimate. Also, the performance of triple left truncated exponential distribution was tested by calculating some statistical criteria and testing the goodness of fit for distribution, with comparisons between the distributions and testing them on real data for patients infected with covid-19.

groups

Alhasan Kawther mail -

Abad Al-Kadim Kareema mail

link https://doi.org/10.54216/JNFS.100105

Volume & Issue

Vol. Volume 10 / Iss. Issue 1

Details open_in_new

Fusion: Practice and Applications | 2021

CouponCar: An Android Based Application to Automate the Street Parking Payment

In the current system of making a street parking payment in Malaysia, citizens are using a manually paper-based parking coupon that still lacks in terms of the payment process, thus making it difficult for Malaysians to pay for their parking. Therefore, the CouponCar application is proposed to help citizens in Malaysia to pay for their parking with ease. Citizens do not need to buy a parking coupon at the city council or any agents that sell the parking coupon. Instead, the manual system will be replaced by using an android based application where they just need to install the application inside their smartphone, tablet, or any suitable device. This system will also help the officer to check many cars within a short time, whereas they can easily scan the QR code on every car's dashboard. The system was developed using a structured approach and based on activities in the system prototyping model. Overall, this system can facilitate the citizen to make a street parking payments in Malaysia.

groups

Nur Atifah Hammade mail -

Rozaida Ghazali mail -

Salama A. Mostafa mail -

Bashar Ahmed Khalaf mail

link https://doi.org/10.54216/FPA.060205

Volume & Issue

Vol. Volume 6 / Iss. Issue 2

Details open_in_new

American Journal of Business and Operations Research | 2022

Multi-criteria Decision Making based on EDAS Approach for Business Risk Assessment in Electricity Retail Companies

This paper introduce a multi- criteria decision making (MCDM) perfect to assess business risk in electricity retail company to decrease risk loss and mange risks of business. The evaluation of business risk in electricity company included many conflicting criteria such as risk of political, risk of economic, and risk of market. So, this paper presented an Evaluation based on distance from average solution (EDAS) MCDM method to compute the weights of these criteria and rank the alternatives. Distances between each option and the mean answer on each criteria form the basis of EDAS. It expedites the decision-making process by streamlining the computation of distances to the deal solution. But in this evaluation, there are many imperfect and unclear data. So, the neutrosophic sets is presented to overcome this vague information. The interval valued neutrosophic sets (IVNSs) is a type of neutrosophic sets is presented in this work. 

groups

Mahmoud Ibrahim mail -

Shereen Zaki mail -

Mahmoud M. Ismail mail

link https://doi.org/10.54216/AJBOR.080102

Volume & Issue

Vol. Volume 8 / Iss. Issue 1

Details open_in_new

Financial Technology and Innovation | 2022

Interval Valued Neutrosophic Sets and Multi-Criteria Decision Making for Sustainable Mobile Healthcare Promotion

The use of health mobile websites or apps on smartphones like mobile-phones has made it possible for users to have quick, inexpensive access to the services of licensed medical professionals. As a result, mobile health care has the potential to lessen the burden on the healthcare system by lowering costs, decreasing wait times, and maximizing the effectiveness of available resources. In order to foster the long-term growth of healthcare infrastructure. This paper introduce the interval valued neutrosophic sets (IVNSs) to overcome the uncertainty. The IVNSs is combined with the MCDM methodology such as TOPSIS method. The TOPSIS technique is used to order the options. In addition to assisting with the selection of the best mobile health care option, this methodology may be used to close the performance gap between competing products and meet customer expectations. There were four distinct categories of mobile health care products investigated.

groups

Mahmoud M. Ismail mail

link https://doi.org/10.54216/FinTech-I.010101

Volume & Issue

Vol. Volume 1 / Iss. Issue 1

Details open_in_new

International Journal of Wireless and Ad Hoc Communication | 2023

Spam Detection in Connected Networks Using Particle Swarm and Genetic Algorithm Optimization: Youtube as a Case study

Although there are many networks security tools, both wire and wireless connected networks are still suffering from many types of attacks. YouTube's meteoric rise to prominence as a social platform speaks for itself. The sheer volume of comments on YouTube has made it an ideal medium for spammers to spread their malicious software. Phishing attacks, in which anyone who clicks on a bad link might be a victim, have contributed to this problem. Classification systems may be used to examine spam for its unique characteristics and identify it. This is why it is suggested that YouTube already has built-in mechanisms for identifying spam. A YouTube Spam detection framework was designed with the five stages of data collection, pre-processing, features extraction, classification, and detection, allowing for the execution of the tests. To analyze and validate each stage of the YouTube detection methodology presented in this study, two metaheuristic optimization methods are employed to optimize the parameters of a new voting ensemble classifier. These methods are the particle swarm optimization (PSO) and the Genetic Algorithm (GA). The ensemble model is based on three classifiers: neural. Results indicate that the proposed approach is accurate. In addition, statistical analysis is performed to emphasize the superiority and effectiveness of the proposed methodology.

groups

Amel Ali Alhussan mail -

Hassan K. Ibrahim Al-Mahdawi mail -

Ammar Kadi mail

link https://doi.org/10.54216/IJWAC.060101

Volume & Issue

Vol. Volume 6 / Iss. Issue 1

Details open_in_new

International Journal of Wireless and Ad Hoc Communication | 2023

Natural Disaster Detection for Smart IoT Communication using LoRA model

There is annual financial loss, mental pain, bodily injury, and loss of life due to natural and artificial disasters. Unfortunately, natural disasters are becoming much deadlier due to climate change. Consequently, IoT-based catastrophe detection and response systems have been developed to improve the handling of catastrophic disasters and other times of extreme urgency. As a consequence, information gathered from Internet-connected devices is utilized to aid in the categorization of several types of disasters, both natural and artificial. A determination of the nature of the crisis and notification of the relevant command center is accomplished using preexisting methods. We have shown how to modify an existing system into a particular early warning system for natural disasters using two Internet of Things (IoT) devices: the Arduino Uno and the Nodemcu. Using this data, we can pinpoint the exact position of every person whose phone is within range of the disaster and send them warnings before the situation worsens. The botmasters have shifted their paradigm away from IRC and toward an HTTP-based C&C server due to the widespread use of HTTP services. Like HTTP bots, IRC bots have a single point of failure. HTTP bots, however, are harder to stop. It is also challenging to detect HTTP botnets while keeping the false positive rate low since every service on the Internet utilizes the HTTP protocol. This chapter provides a host-based HTTP botnet detection approach that uses Hidden semi-Markov Model (HsMM) variables and the Simple Network Management Protocol-Management Information Base (SNMP-MIB). The device operates following the specifications established by the LoRa network. In this project, we used a device called Nodemcu, which was made to be configured explicitly on the receiving end to identify the users at the place where the catastrophe was detected. At that point, everyone connected to the gadget would receive a geolocation-based alert. MQTT is used to notify the right people when an issue arises. We saw better and more beneficial results from the IoT project after including LoRa.

groups

Piyush Kumar Shukla mail

link https://doi.org/10.54216/IJWAC.060102

Volume & Issue

Vol. Volume 6 / Iss. Issue 1

Details open_in_new

International Journal of Wireless and Ad Hoc Communication | 2023

Improving the perfoamnce of Fog-assisted Internet of Things Networks using Bipolar Trapezoidal Neutrosophic sets

Large numbers of devices with varying hardware capabilities and data traffic patterns make up what we call the Internet of Things (IoT). Furthermore, various IoT services, like knowledge economy, e-health, e-business, parking management, etc., display dynamically varying QoS (Quality of Service) needs inside the IoT network. As a consequence of the inconsistency in service delivery, it is difficult to attain spectrum efficiency in the Internet of Things (IoT). There will be a shortage of spectrum for critical IoT services as a result. In this study, we suggest using a Multi-Criteria Decision Making (MCDM) technique to coordinate spectrum sharing across IoT devices. To ensure that the capacity and quality-of-service requirements of IoT devices are met, this framework prioritizes the accessible spectrum bands based on their numerous spectral properties. When all relevant information for reaching a choice is supplied by decision-makers, as is the case in both the trapezoidal and bipolar neutrosophic environments, this research presents a novel, effective approach to tackling these challenges. Conceptually related, the bipolar trapezoidal neutrosophic set's governing principles and rules of operation are laid forth. We cover several important accumulation operations for accumulating bipolar trapezoidal neutrosophic data. The ARAS technique is combined with the bipolar trapezoidal neutrosophic sets to compute the weights of principles and rank the substitutions.

groups

Abedallah abualkishik mail -

Rasha Almajed mail -

Watson Thompson mail

link https://doi.org/10.54216/IJWAC.060103

Volume & Issue

Vol. Volume 6 / Iss. Issue 1

Details open_in_new

International Journal of Wireless and Ad Hoc Communication | 2023

Generative Edge Intelligence for Securing IoT-assisted Smart Grid against Cyber-Threats

The critical dependence of industrial smart grid systems on cutting-edge Internet of Things (IoT) technologies has made these systems more susceptible to a diverse array of assaults. This consequently puts at risk the integrity of energy data as well as the safety of energy management activities that depend on those data. This study offers a generative federated learning framework for semi-supervised threat detection in an IoT-assisted smart grid system. We refer to this framework as FSEI-Net. A unique semi-supervised edge intelligence network (SEI-Net) is presented in the FSEI-Net to enable semi-supervised training using labeled and unlabeled data in the edge tier. The design of SEI-Net is based on with bidirectional generative convolutional network that can intelligently capture the patterns of threat data from partially labeled smart grid data.  We present federated training to enable remote edge servers to work together on training a semi-supervised detector without disclosing their own private local data. This is accomplished through cooperative training. To facilitate communication between cloud and edge layers that is both secure and respectful of users' privacy, a reputation-based block chain is introduced in the FSEI-Net. The outcomes from the practical applications demonstrate that the effectiveness of the proposed FSEI-Net over the most recent cutting-edge detection approaches are valid

groups

Gopal Chaudhary mail -

Smriti Srivastava mail -

Manju Khari mail

link https://doi.org/10.54216/IJWAC.060104

Volume & Issue

Vol. Volume 6 / Iss. Issue 1

Details open_in_new

International Journal of Wireless and Ad Hoc Communication | 2023

Trustworthy Federated Graph Learning Framework for Wireless Internet of Things

As computational power has increased rapidly in recent years, deep learning techniques have found widespread use in wireless internet of things (IoT) networks, where they have shown remarkable results. In order to make the most of the data contained in graphs and their surrounding contexts, graph intelligence has seen extensive use in a wide variety of tailored wireless applications. However, the sensitive nature of client data poses serious challenges to conventional customization approaches, which depend on centralized graph learning on globe graphs. In this work, we introduce federated graph learning, dubbed FGL, that is capable of producing accurate personalization while still protecting clients' anonymity. To train graph intelligence models jointly based on distributed graphs inferred from local data, we employ a trustworthy model updating technique. In order to make use of graph knowledge beyond the scope of dynamic interplay, we present a trustworthy graph extension mechanism for incorporating high-level knowledge while yet maintaining confidentiality. Six customization datasets were used to show that with excellent trustworthy protection, FGL achieves 2.0% to 5.0% lower errors than the state-of-the-art federated customization approaches. For ethical and insightful personalization, FGL offers a potential path forward for mining distributed graph data.

groups

Abedallah Z. Abualkishik mail -

Rasha Almajed mail -

William Thompson mail

link https://doi.org/10.54216/IJWAC.060105

Volume & Issue

Vol. Volume 6 / Iss. Issue 1

Details open_in_new