An exploration of the key determinants for the application of AI-enabled higher education based on a hybrid Soft-computing technique and a DEMATEL approach

• AI promotes the sustainability development in higher education. • A soft-computing technique extracts key factors from large amounts of data. • DEMATEL analysis accounts for dependence and feedback among factors. • A framework of AI-enabled Higher Education was proposed. • "Intelligent instructional systems" is the most important criterion. The application of AI in higher education has greatly increased globally in the dynamic digital age. The adoption of developmentally appropriate practices using AI-enabled techniques for facilitating the performance of teaching and learning in the higher education domain is thus a necessary task, especially in the COVID 19 pandemic era. The development and implementation of such techniques involve many factors and are related to the classical multiple criteria decision-making (MCDM) issue;however, these factors surrounding supervisors will confuse them and may result in misjudgment. To clarify the relevant issues and illustrate the cause-and-effect relationships among factors, a hybrid soft-computing technique (i.e., the fuzzy rough set theory (FRST) with ant colony optimization (ACO)) and a DEMATEL approach was proposed in this study, which can help decision makers capture the best model necessary for achieving aspiration-level in a higher education management strategy. In the results submitted, the improvement priority for dimensions is based on the measurement of the influences, running in order of tutors for learners (A), skills and competences (B), interaction data to support learning (C), and universal access to global classrooms (D), and which can serve as a reference for the plan of AI-enabled teaching/learning for higher education. [ FROM AUTHOR]

Blockchain-Based Secure Authentication for an Intelligent e-Learning Framework with Optimized Learning Objects

As education field has become online due to covid in both schools and colleges, e-learning security has become an important issue. An e-Learning framework provides a collection of online services that are helpful for the learners, resource persons and others who are involved in enhancing the management and delivery of education to all sections of people. The two most important aspects of an e-Learning system are better search of learning resources and the secure authentication between the learner and the trainer. This chapter introduces two novel methods: (i) optimization of Learning Object (LO) search based on learners' characteristics, (ii) secure authentication of trainers and learners using visual cryptography. Storage and delivery of optimal resources that are well suited for individual learner is always a challenging task. To find the best learning objects, an enhanced attribute-based Ant Colony Optimization (ACO) algorithm that provides flexibility for the learners based on learner characteristics is proposed. A novel visual cryptography-based technique with kite-based partition technique is designed to perform file sharing and blockchain-based secure authentication and verification of valid learners is proposed for the framework. Several measures like match ratio, relevancy factor, and heuristic values show the efficiency of the proposed ACO search technique in the context of an e-Learning framework. © 2022 by World Scientific Publishing Co. Pte. Ltd.

Research on logistics UAV task assignment based on improved ant colony algorithm

Logistics UAV delivery has been well developed in the fight against COVID-19 pneumonia, and attracts more and more scholars to research. Ant Colony Optimization (ACO) is one of the effective solutions to solve the UAV task assignment problem. The algorithm adopts the principle of positive feedback to speed up the evolution process. However, the algorithm has some defects, such as long search time, easy to fall into local optimum and so on. Aiming at the defects of ACO, we put forward two improvements in this paper: On the one hand, differential distribution of initial pheromone is proposed to avoid blind search in the initial stage and improve the convergence speed. On the other hand, we will reduce the number of candidate nodes in the dynamic strategy, and ants choose the next node in the dynamic candidate list to reduce the calculation of local exploitation. Simulation results show that the improved ACO can significantly improve the convergence speed and has a good effect on solving the task assignment problem of logistics UAV. © 2022 SPIE.

Suicide Ideation Detection of Covid Patients Using Machine Learning Algorithm

During Covid pandemic, many individuals are suffering from suicidal ideation in the world. Social distancing and quarantining, affects the patient emotionally. Affective computing is the study of recognizing human feelings and emotions. This technology can be used effectively during pandemic for facial expression recognition which automatically extracts the features from the human face. Monitoring system plays a very important role to detect the patient condition and to recognize the patterns of expression from the safest distance. In this paper, a new method is proposed for emotion recognition and suicide ideation detection in COVID patients. This helps to alert the nurse, when patient emotion is fear, cry or sad. The research presented in this paper has introduced Image Processing technology for emotional analysis of patients using Machine learning algorithm. The proposed Convolution Neural Networks (CNN) architecture with DnCNN preprocessing enhances the performance of recognition. The system can analyze the mood of patients either in real time or in the form of video files from CCTV cameras. The proposed method accuracy is more when compared to other methods. It detects the chances of suicide attempt based on stress level and emotional recognition. © 2023 CRL Publishing. All rights reserved.

An Optimized Modelling and Simulation on Task Scheduling for Multi-Processor System using Hybridized ACO-CVOA

Task allocation on the multi-processor system distributes the task according to capacity of each processor that optimally selects the best. The optimal selection of processor leads to increase performance and this also impact the makespan. In task scheduling, most of the research work focused on the objective of managing the power consumption and time complexity due to improper selection of processors for the given task items. This paper mainly focusses on the modelling of the optimal task allocation using a novel hybridization method of Ant Colony Optimization (ACO) with Corona Virus Optimization Algorithm (CVOA). There are several other methods that estimate the weight value of processors and find the best match to the task by using the traditional distance estimation method or by using standard rule-based validation. The proposed algorithm searches the best selection of machines for the corresponding parameters and weight value iteratively and finally recognizes the capacity of it. The performance of proposed method is evaluated on the parameters of elapsed time, throughput and compared with the state-of-art methods. © 2022 Institute of Information Science. All rights reserved.

An Exploration of the Key Determinants for the Application of AI-enabled Higher Education Based on a Hybrid Soft-computing Technique and a DEMATEL approach

The application of AI in higher education has greatly increased globally in the dynamic digital age. The adoption of developmentally appropriate practices using AI-enabled techniques for facilitating the performance of teaching and learning in the higher education domain is thus a necessary task, especially in the COVID 19 pandemic era. The development and implementation of such techniques involve many factors and are related to the classical multiple criteria decision-making (MCDM) issue;however, these factors surrounding supervisors will confuse them and may result in misjudgment. To clarify the relevant issues and illustrate the cause-and-effect relationships among factors, a hybrid soft-computing technique (i.e., the fuzzy rough set theory (FRST) with ant colony optimization (ACO)) and a DEMATEL approach was proposed in this study, which can help decision makers capture the best model necessary for achieving aspiration-level in a higher education management strategy. In the results submitted, the improvement priority for dimensions is based on the measurement of the influences, running in order of tutors for learners (A), skills and competences (B), interaction data to support learning (C), and universal access to global classrooms (D), and which can serve as a reference for the plan of AI-enabled teaching/learning for higher education.

Directional mutation and crossover boosted ant colony optimization with application to COVID-19 X-ray image segmentation.

This paper focuses on the study of Coronavirus Disease 2019 (COVID-19) X-ray image segmentation technology. We present a new multilevel image segmentation method based on the swarm intelligence algorithm (SIA) to enhance the image segmentation of COVID-19 X-rays. This paper first introduces an improved ant colony optimization algorithm, and later details the directional crossover (DX) and directional mutation (DM) strategy, XMACO. The DX strategy improves the quality of the population search, which enhances the convergence speed of the algorithm. The DM strategy increases the diversity of the population to jump out of the local optima (LO). Furthermore, we design the image segmentation model (MIS-XMACO) by incorporating two-dimensional (2D) histograms, 2D Kapur's entropy, and a nonlocal mean strategy, and we apply this model to COVID-19 X-ray image segmentation. Benchmark function experiments based on the IEEE CEC2014 and IEEE CEC2017 function sets demonstrate that XMACO has a faster convergence speed and higher convergence accuracy than competing models, and it can avoid falling into LO. Other SIAs and image segmentation models were used to ensure the validity of the experiments. The proposed MIS-XMACO model shows more stable and superior segmentation results than other models at different threshold levels by analyzing the experimental results.

A Machine Learning Approach to Predict Renal Diseases with SARS-CoV-2

Research has shown that up to a lot of people hospitalized with COVID-19 get an intense kidney injury. In some serious cases, Kidney failure occurs suddenly without any major symptoms that are totally unpredictable to identify in the early stage. The reason behind that we have a lack of knowledge and experience regarding this. The main purpose of our research is to develop a framework that will assist individuals with foreseeing the danger of constant renal sickness growing rate after being infected with COVID-19. Here we have utilized 773 raw data and trained them and we have also taken care of our missing data. In this paper, we have used KNN, Naïve Bayes, ANN model and Ant Colony Optimization (ACO) for making the system ready for assumption. We have carried out these calculations in the python language. The exactness that we acquire by utilizing KNN calculation is 95%, Naïve bayes is 98.30% ANN is 97.5% and Ant Colony Optimization (ACO) is 95.5% separately which is generally outstanding. By utilizing our proposed strategy, prediction of renal diseases after COVID-19 in the beginning phase will be conceivable. All the data are collected from our neighborhood medical clinic. This research has shown us the current situation in this COVID-19 pandemic with regards to Chronic Kidney Sickness which is known as renal disease. © 2021 IEEE.

GenACO a multi-objective cached data offloading optimization based on genetic algorithm and ant colony optimization.

BACKGROUND: Data exchange and management have been observed to be improving with the rapid growth of 5G technology, edge computing, and the Internet of Things (IoT). Moreover, edge computing is expected to quickly serve extensive and massive data requests despite its limited storage capacity. Such a situation needs data caching and offloading capabilities for proper distribution to users. These capabilities also need to be optimized due to the experience constraints, such as data priority determination, limited storage, and execution time. METHODS: We proposed a novel framework called Genetic and Ant Colony Optimization (GenACO) to improve the performance of the cached data optimization implemented in previous research by providing a more optimum objective function value. GenACO improves the solution selection probability mechanism to ensure a more reliable balancing of the exploration and exploitation process involved in finding solutions. Moreover, the GenACO has two modes: cyclic and non-cyclic, confirmed to have the ability to increase the optimal cached data solution, improve average solution quality, and reduce the total time consumption from the previous research results. RESULT: The experimental results demonstrated that the proposed GenACO outperformed the previous work by minimizing the objective function of cached data optimization from 0.4374 to 0.4350 and reducing the time consumption by up to 47%.

Accurate detection of COVID-19 using deep features based on X-Ray images and feature selection methods.

COVID-19 is a severe epidemic affecting the whole world. This epidemic, which has a high mortality rate, affects the health systems and the economies of countries significantly. Therefore, ending the epidemic is one of the most important priorities of all states. For this, automatic diagnosis and detection systems are very important to control the epidemic. In addition to the recommendation of the "reverse transcription-polymerase chain reaction (RT-PCR)" test, additional diagnosis and detection systems are required. Hence, based on the fact that the COVID-19 virus attacks the lungs, automatic diagnosis and detection systems developed using X-ray and CT images come to the fore. In this study, a high-performance detection system was implemented with three different CNN (ResNet50, ResNet101, InceptionResNetV2) models and X-ray images of three different classes (COVID-19, Normal, Pneumonia). The particle swarm optimization (PSO) algorithm and ant colony algorithm (ACO) was applied among the feature selection methods, and their performances were compared. The results were obtained using support vector machines (SVM) and a k-nearest neighbor (k-NN) classifier using the 10-fold cross-validation method. The highest overall accuracy performance was 99.83% with the SVM algorithm without feature selection. The highest performance was achieved after the feature selection process with the SVM + PSO method as 99.86%. As a result, higher performance with less computational load has been achieved by realizing the feature selection. Based on the high results obtained, it is thought that this study will benefit radiologists as a decision support system.

We Know Health Is Not Elective: Impacts of COVID-19.

Several months into the impact of the global COVID-19 pandemic, the authors use the framework of "radical uncertainty" and specific regional health care data to understand current and future health and economic impacts. Four key areas of discussion included are: (1) How did structural health care inequality manifest itself during the closure of all elective surgeries and visits?; (2) How can we really calculate the so-called untold burden that resulted from the closure, with a special emphasis on primary care?; (3) The Pennsylvania experience - using observations from the population of one major delivery ecosystem (Jefferson Health), a major accountable care organization (Delaware Valley ACO), and statewide data from Pennsylvania; and (4) What should be the priorities and focus of the delivery system of the future given the dramatic financial and clinical disruption of COVID-19?