Dec' 22
The IUP Journal of Information Technology
Focus
Artificial Intelligence (AI) and Machine Learning (ML) played a brilliant role in controlling the Covid-19 pandemic. The technologies successfully helped in contact tracing of the individuals infected with the virus, identifying the clusters and hot spots, and monitoring them. Early detection and diagnosis of the infection with the help of medical imaging and ML algorithms was very successful. Detecting Covid-19 illness from chest CT-Scan and X-ray images using ML algorithm has been cost-effective compared to RT-PCR testing and was strategically implemented in rural areas. AI and ML technologies were successfully used in the projection of positive cases and mortality rates to help the government in planning and management of the pandemic. They were used to monitor patients and provide day-to-day developments for better treatment of the patients. The Covid-19 drugs and vaccines were developed in record times. AI and ML technologies notably became powerful tools in identifying useful drugs, diagnostic tests, vaccine development and clinical trials.
Work-from-Home (WFH) became a norm during the pandemic due to lockdowns imposed by most of the countries as a preventive measure to stop the spread of the virus. The first paper, "An Ensemble Learning Approach to Predict Employees' Preference for E-Working in the Post-Pandemic World" by S A D D Abesiri and R A H M Rupasingha, examines employee preferences towards WFH after the pandemic. The authors used several ML algorithms and ensemble method to predict the employee preference for e-working and found that the ensemble method surpasses the other algorithms.
The second paper, "Blockchain Solutions for IoT Devices Against DDoS Attacks: A Review" by G Mahalaxmi, R Varaprasad and T Aditya Sai Srinivas, reviews blockchain technology solutions and offers an optimistic note that they have the potential to handle DDoS attacks successfully.
The last paper, "Black Lives Matter: Exploratory Analysis of Social Media Disclosures" by A C Nanayakkara and G A D M Thennakoon, presents an analysis of the social media comments on a well-known YouTube video narrating George Floyd's death in the United States. The authors believe that such studies can help examine the behavior of netizens and their influence over the society. They also provide pointers for future research on the same.
Consulting Editor
An Ensemble Learning Approach to Predict Employees' Preference for E-Working in the Post-Pandemic World
The Covid-19 pandemic has forced a large segment of the global workforce to shift to e-working. The pandemic has convinced many organizations that e-working has benefits for a successful business. As a result, it is critical to identify employees' suggestions and evaluate their motivation to continue the e-working concept in the post-pandemic world. The study was conducted by randomly surveying employees using various Machine Learning algorithms, including Naive Bayes, Decision Tree, Random Forest, Multilayer perceptron (MLP), Support Vector Machine (SVM) and logistic regression. The ensembling algorithm uses 66% of the percentage split method in the Waikato Environment for Knowledge Analysis (WEKA) tool. Accuracy, precision, recall, f-measure values and error rates were used to compare the results. The ensemble learning algorithm shows the best results with 90% accuracy, making it easier to predict employees' preference for e-working and accordingly take decisions.
Blockchain Solutions for IoT Devices Against DDoS Attacks: A Review
Internet of Things (IoT)-connected devices are used in a wide range of applications, including smart cities, agriculture, healthcare, logistics, etc. However, the rise in the number of attacks utilizing Distributed Denial of Service (DDoS) protocols is a cause for concern. IoT devices have security holes that make it easier for fraudsters to take control of them and use them as part of botnets to launch DDoS assaults. The processing and storage capabilities of the vast majority of IoT-connected devices are quite constrained. Blockchain technology, which is still in its early stages, may be used to address concerns over the security of IoT devices. It is crucial to consider many blockchain-based defence techniques that are currently available for IoT devices in order to prevent DDoS attacks.
Black Lives Matter: Exploratory Analysis of Social Media Disclosures
Social media has become a contemporary platform for vox populi, enriched with the facilities of almost unrestricted access and versatility in terms of time and location of the users. The behaviors of social media users are creating a plethora of data, and is a fertile ground for Exploratory Data Analysis (EDA), which enables users to discover the veiled story within the datasets often using visual methods. This study focuses on the tragic incident of George Floyd's death that took place on May 25, 2020, in Minneapolis, Minnesota, US, in terms of the social media responses by analyzing the corpus of comments for a selected YouTube video. Python programming language has been used to implement the EDA process using the methods of Text statistics analysis, Sentiment analysis, Ngram exploration, Topic modeling, Parts of Speech (POS) tagging, Word cloud formation, Named Entity Recognition (NER) and Text complexity analysis. By exploring the video disclosure with relevant tools, the study provides insights on the netizens, their behavior and their influence on society. This endeavor will help in preventing the manipulation of public opinion.