Transforming Healthcare Infrastructure for Enhanced Energy Efficiency and Privacy

Sudeshna; Akanksha

doi:https://doi.org/10.54216/JCIM.120204

Fusion: Practice and Applications | 2023

Blockchain-Based E-Voting System with Face Recognition

Given the increasing importance of technology in meeting human needs, its utilization has become crucial. In contemporary democracies, where public trust in governments is declining and elections play a pivotal role, the widespread adoption of technology has led to new challenges. Elections hold significant importance as they determine the future leaders of countries or organizations. However, certain computerized voting systems have faced criticism for their lack of transparency. Establishing public trust in the government is a formidable task due to the lack of transparency and susceptibility to exploitation in existing voting procedures. Both traditional and current digital voting systems are ineffective due to their vulnerabilities. The main objective is to address issues in conventional and electronic voting systems, including errors and unfairness that may arise during the voting process. Integrating blockchain technology into the electoral process can ensure fair elections and reduce unfair practices. The computerized voting methods do not meet the necessary standards for widespread usage, and the physical voting systems also face numerous issues. This underscores the importance of finding a solution to protect the democratic principles of citizens. By offering a fast and secure voting method, this system has the potential to bring about a revolutionary change in the electoral process. It could lead to higher voter participation and more accurate election results. The proposed approach presents a framework for digital voting using blockchain technology, eliminating the need for physical polling locations. Our suggested design incorporates adaptable consensus algorithms to support a scalable blockchain. Smart contracts ensure secure interactions between users and the network during transaction execution. The security aspects of the blockchain-based voting mechanism have also been addressed, including the use of cryptographic hashes for transaction encryption and prevention of 51% attacks. Furthermore, blockchain technology has been utilized to establish transaction systems throughout the voting process. Performance studies of the proposed system demonstrate its feasibility for deployment in large populations.

groups

V. Sathya Preiya mail -

V. D. Ambeth Kumar mail -

R. Vijay mail -

Vijay K. mail -

N. Kirubakaran mail

link https://doi.org/10.54216/FPA.120104

Volume & Issue

Vol. Volume 12 / Iss. Issue 1

Details open_in_new

Journal of Artificial Intelligence and Metaheuristics | 2023

Design of Antenna Parameters Using Optimization Techniques: A Review

The use of machine learning (ML) and deep learning (DL) algorithms to solve mathematical issues in wireless communications has propelled AI-assisted communications to the forefront in recent years. Beginning with an overview of AI, CEM, and the function of AI/ML/DL in antennas, this paper moves on to discuss the topic in more depth. In this article, we show the results of our research into ML/DL algorithms and the methods we used to optimize antenna settings using these algorithms. Finally, we show several examples of how AI can be used in antennas.

groups

Nima Khodadadi mail -

Mostafa Abotaleb mail -

Pushan Kumar Dutta mail

link https://doi.org/10.54216/JAIM.030101

Volume & Issue

Vol. Volume 3 / Iss. Issue 1

Details open_in_new

Journal of Artificial Intelligence and Metaheuristics | 2023

Auto-ASD Detector: Exploiting Computational Intelligence for autism spectrum disorders Detection in Children via Facial Analysis

Asperger's syndrome, difficulties with disintegration in children, and autism are all included in the category of complex neurodevelopmental diseases known as autism spectrum disorders (ASD). Individuals who are autistic struggle greatly to keep up with society's speed, have poor communication skills, and struggle to express their emotions in the right ways. Early diagnosis and intervention can greatly improve the long-term outcomes for children with ASD. Several studies have identified key characteristics of autism using a variety of methods, including feature extraction, eye tracking, and speech recognition. As opposed to a person's emotional condition, facial recognition is more crucial in identifying autism. Early diagnosis and intervention can greatly improve the long-term outcomes for children with ASD. Hence, cutting-edge information technology that employs artificial intelligence (AI) techniques has assisted in the early diagnosis of ASD based on face pattern recognition. Among these techniques are deep learning (DL) have been utilized or suggested for detecting autism in youngsters. Herein, we applied a technique for accurate autism detection in children using facial analysis with the aid of computational intelligence. The proposed approach involves analyzing facial features and expressions to identify patterns which are associated with ASD. This is achieved by leveraging application of convolutional neural network (CNNs) to extract meaningful features from facial images. The extracted features are used to accurately classify children as either having or not having ASD. To evaluate the proposed approach, a dataset of facial images of children with and without ASD is used to train and validate the proposed technique. Also, to assess their performance in accurately detecting ASD. The proposed technique has the potential to revolutionize the way ASD is diagnosed by providing an objective and reliable tool for early detection and intervention.

groups

Mona Mohamed mail -

Samah Ibrahim Abdelaal mail

link https://doi.org/10.54216/JAIM.030104

Volume & Issue

Vol. Volume 3 / Iss. Issue 1

Details open_in_new

Journal of Artificial Intelligence and Metaheuristics | 2023

Metaheuristic Optimization Review: Algorithms and Applications

Metaheuristic optimisation algorithms have become more well liked in recent years due to their success in solving challenging optimisation problems. Only a few of the metaheuristic optimisation techniques covered in this work include genetic algorithms, particle swarm optimisation, simulated annealing, ant colony optimisation, and many others. This paper discusses the history, operation, and applications of each method, including applications in engineering, finance, and bioinformatics.

groups

Mohamed Saber mail -

Abdelaziz A. Abdelhamid mail -

Abdelhameed Ibrahim mail

link https://doi.org/10.54216/JAIM.030102

Volume & Issue

Vol. Volume 3 / Iss. Issue 1

Details open_in_new

Journal of Artificial Intelligence and Metaheuristics | 2023

Solar Tracking System Using pixel identification algorithm

On cloudy days, an intelligent technique to optimizing the direction of continuous sun tracking devices is proposed in this research. When it comes to weather, direct sunlight is more essential than diffuse radiation in a clear sky. As a result, the panel is always pointing towards the sun. When the sky is overcast, the solar beam is near to zero, and the panel is positioned horizontally to receive the most dispersed radiation. Under partially covered conditions, the panel must be aimed at the source emitting the most solar energy, which can be located anywhere in the sky dome. Thus, the idea behind our technique is to analyze images taken by a ground-based sky camera system in order to identify the zone in the sky dome that is thought to be the best source of energy under foggy situations. The proposed method is put into practice utilizing an experimental setup built at Mansoura city in north Egypt. The findings were quite good under overcast situations, and the intelligent technique gave efficiency gains of up to 9% compared to typical continuous sun tracking systems.

groups

Nader Behdad mail -

Sunil Kumar mail

link https://doi.org/10.54216/JAIM.030103

Volume & Issue

Vol. Volume 3 / Iss. Issue 1

Details open_in_new

Journal of Artificial Intelligence and Metaheuristics | 2023

From Data to Diagnosis: Applied Machine Learning for Stroke Prediction in Computational Healthcare

  Stroke is a leading cause of disability and mortality worldwide, emphasizing the need for accurate and timely prediction methods. In recent years, advancements in machine learning and computational healthcare have shown promising results in various medical domains. This paper presents a comprehensive study on the application of machine learning techniques for stroke prediction in computational healthcare. The objective of this research is to develop a robust and accurate stroke prediction model that can assist healthcare professionals in identifying individuals at high risk of stroke. Leveraging a diverse dataset consisting of demographic information, medical history, and clinical measurements, a range of machine learning algorithms is employed to extract meaningful patterns and relationships. Feature selection techniques are utilized to identify the most relevant predictors, ensuring optimal model performance. Through rigorous experimentation and evaluation, the proposed machine learning model demonstrates superior performance in stroke prediction compared to traditional risk assessment methods. The implications of this research extend beyond stroke prediction, with the proposed methods serving as a foundation for the development of similar predictive models in other healthcare domains.

groups

Amal F. Abdel-Gawad mail -

Salwa El-Sayed mail -

Mahmoud M. Ismail mail

link https://doi.org/10.54216/JAIM.030105

Volume & Issue

Vol. Volume 3 / Iss. Issue 1

Details open_in_new

Journal of Cybersecurity and Information Management | 2023

An Effective FOG Computing Based Distributed Forecasting of Cyber-Attacks in Internet of Things

Existing cloud based security procedures are insufficient to manage the ever-increasing assaults in IoT due to the volume of data generated and the processing latency. IoT applications are vulnerable to cyberattacks, and some of these assaults might have catastrophic results if not stopped or mitigated quickly enough. As a result, IoT calls for self-protect security systems that can automatically interpret attacks in IoT traffic and efficiently handle the attack situation by activating the proper response quickly. Fog computing satisfies this need because it can embed the intelligent self-protection mechanism in the distributed fog nodes, allowing them to swiftly deal with the assault scenario and safeguard the IoT application with little in the way of human interaction. At the fog nodes, the forecasting method employs distributed Gaussian process regression. The cyber-attack may be predicted more quickly and with less mistake for both low- and high-rate attacks thanks to the local forecasting about the IoT traffic characteristics at fog node. One of the fundamental necessities of an IoT security mechanism is the ability to forecast attacks in a timely manner with a high degree of accuracy, and the simulation results highlight this fact.

groups

Vandana Roy mail

link https://doi.org/10.54216/JCIM.120201

Volume & Issue

Vol. Volume 12 / Iss. Issue 2

Details open_in_new

Journal of Cybersecurity and Information Management | 2023

Improved Method for Enhanced Quality of Service in IoHT Task Dependency Optimization

Keeping a proper level of task dependency throughout the scheduling process is critical to achieving the aim of decreasing the make-span rate in Internet of Health Things (IoHT) projects. We provide a smart model strategy for effective task scheduling in the IoHT environment for e-healthcare systems by merging hybrid moth flame optimisation (HMFO) with cloud computing. The HMFO algorithm guarantees that all available resources are distributed evenly, resulting in improved quality of service (QoS). We study the Google cluster dataset to learn about the scheduling behaviours of cloud-based jobs in order to train our model. After training, an HMFO model may be used to plan activities in real time. To assess the success of our strategy, we run simulations in the CloudSim environment, taking into account crucial parameters such as resource utilisation, reaction time, and energy consumption. According to a comparative analysis, our hybrid HMFO system surpasses the alternatives in terms of reaction time, average run duration, and cost savings. Our method has proven to be effective due to the favourable effects it has had on response rates, prices, and run times. Combining IoT and cloud computing has the potential to improve healthcare delivery in a variety of ways. One unique strategy we offer for scheduling IOHT jobs is to combine a deep neural network (DNN) algorithm with the MFO technique. Job scheduling in electronic healthcare systems can be optimised with the help of our hybrid MFO-DNN algorithm by taking into account a variety of different objectives, the most important of which are lowering response times while improving resource utilisation and maintaining consistent load balances. The MFO approach searches the search space and provides early solutions, while the DNN algorithm refines and improves those first findings. In comprehensive simulations conducted in a real-world hospital setting, the hybrid MFO-DNN technique outperformed existing scheduling algorithms in terms of reaction time, resource utilisation, and load balancing. The simulated healthcare environments were as true to life as was feasible. The suggested technique has been demonstrated to be both dependable and scalable, making it appropriate for use in large-scale IOHT deployments. This study considerably enhances the state of the art in IOHT task scheduling in E healthcare systems by developing a hybrid optimisation technique that takes advantage of the strengths of both MFO and DNN. The findings indicate that this strategy has the potential to improve the quality and efficiency of healthcare delivery, which helps patients receive care that is both effective and timely.

groups

Rumi iqbal doewes mail -

Preeti Saini mail

link https://doi.org/10.54216/JCIM.120202

Volume & Issue

Vol. Volume 12 / Iss. Issue 2

Details open_in_new

Journal of Cybersecurity and Information Management | 2023

Maximizing Anomaly Detection Performance in Next-Generation Networks

The paper discusses major components of the proposed intrusion detection system as well as associated ideas. Dimensionality reduction solutions are highly valued for their potential to improve the efficiency of anomaly detection. Furthermore, feature selection and fusion methods are applied to optimise the system's capabilities. The following summary of network control, management, and cloud-based network processing aspects highlights operations managers, cloud resources, network function virtualization (NFV), and hardware and software components. We discuss prospective Deep Autoencoders (DAEs) applications, such as their use in the dimensionality reduction module, training methodologies, and benefits. Data transformation utilising coded representations is also graphically displayed and described in the text using an encoder and decoder system. The role of the anomaly detection via virtual network function in the suggested technique is also investigated. This component leverages a deep neural network (DNN) to identify anomalies in the 5G network's peripherals. DNN design issues, optimisation methodologies, and the trade-off between model complexity and detection efficacy are also discussed. Overall, the passage provides an overview of the proposed intrusion detection scheme, its components, and the techniques employed, underscoring their contributions to improving efficiency, accuracy, and security in Next Generation Networks.

groups

Pallavi Goel mail -

Sarika Chaudhary mail

link https://doi.org/10.54216/JCIM.120203

Volume & Issue

Vol. Volume 12 / Iss. Issue 2

Details open_in_new

Journal of Cybersecurity and Information Management | 2023

Transforming Healthcare Infrastructure for Enhanced Energy Efficiency and Privacy

The Internet of Medical Things (IoMT) is a revolutionary technique for integrating the IT infrastructure of healthcare organisations with medical apps and equipment. Rapid advancements in this approach in recent years have resulted in game-changing improvements in the healthcare system, illness management, and patient care standards. Both achievements have been made possible by the Internet of Medical Things. People can use the IoMT to access a variety of cloud-based services, including file sharing, patient monitoring, data collection, information gathering, and hospital cleaning. Wireless sensor networks (WSNs), which collect and transmit data, are critical to system operation. In the healthcare system, patients’ privacy and security must be preserved at all costs. Wireless data transmission from these cutting-edge devices may have been intercepted and manipulated without consent. The hybrid and improved (Elliptic Curve Cryptography ECC) Energy-Efficient Routing Protocol (EERP) method, which is based on the elliptic curve encryption protocol, may provide enough protection for sensitive information. ECC-EERP uses pairs of public and private keys known only to each other to decode and encrypt data delivered across a network. As a result, the energy needed to sustain WSNs has dropped. To assess the efficacy of the recommended plan, we did an extensive study and compared our findings to the many other viable courses of action. We did the analysis while taking a variety of aspects into account. The study's findings and conclusion all point to the strategy's ability to significantly increase energy efficiency and security. ECC-EERP is a novel encryption method that increases data security while consuming less energy. Because of its efficacy in improving the whole healthcare system, this strategy has a lot of potential for the future of patient care, illness management, and healthcare delivery in general.

groups

Sudeshna chakraborty mail -

Akanksha Singh mail

link https://doi.org/10.54216/JCIM.120204

Volume & Issue

Vol. Volume 12 / Iss. Issue 2

Details open_in_new