Dec'19
The IUP Journal of Information Technology
Focus
The Third Industrial Revolution, well known for Digital Revolution, lasted from the 1950s to the end of 20th century and took industrial automation to greater heights. It was characterized by the shift of mechanical and analog electronic systems to digital electronics, rapid adoption of computers and information technology, and exponential growth of the internet and mobile phones.
Built upon the previous revolution, the Forth Industrial Revolution (IR 4.0), also known as Industry 4.0, began in the 2010s with remarkable developments in artificial intelligence, machine learning techniques, robotics, and nanotechnology as well as emergence of Internet of Things (IoT), quantum computing, 3D printing and blockchain. These technologies have potential not only to increase industrial automation through smart Machine-to-Machine (M2M) communication and monitoring that reduce human intervention but also to play a very significant role in everyday life. The IR 4.0 aims at integrating computation with physical processes through sensors and actuators creating cyber-physical systems. It blurs the lines between machines and humans, and machines and physical things. It further reduces the physical, mental and emotional proximity between human and machines. Machines learn from humans and humans learn from machines. In the process, machines complement and supplement many skills of human beings, resulting in a deeper relationship.
The first paper, "Internet of Things (IoT): The New Paradigm of HRM and Skill Development in the Fourth Industrial Revolution (Industry 4.0)", by Debasis Dash, Rayees Farooq, Jyoti Sankar Panda and K V Sandhyavani, presents an elaborate discussion on IoT-enabled workforce, and its upsides and downsides.
The second paper, "Ant Colony-Based K-Mediod for Data Clustering", by Bijaya Kumar Nanda and Satchidananda Dehuri, proposes a novel ant-based K-mediod algorithm for clustering. The authors state that the algorithm significantly improves the clusters compared to K-means algorithm.
The last paper, "Time Series Forecasting Models for Predicting of Conjunctivitis Disease Cases", by Shobhit Verma and Nonita Sharma, presents a study on machine learning-based conjunctivitis disease prediction. The authors, through their experimental data, state that the neural network model produces the least error and hence is the best prediction model given the dataset at hand.
Consulting Editor
Internet of Things (IoT): The New Paradigm of HRM and Skill Development in the Fourth Industrial Revolution (Industry 4.0)
The study aims at exploring and assimilating the viewpoints regarding the new standards and challenges of IoT-enabled HRM during Industry 4.0 (ID 4.0) by placing the IoT-HRM concept in clear perspective. Theoretical evidences were examined from selected databases using keyword searches like HRM, IoT and ID 4.0. Enablement of HRM through IoT and its advantage has been vividly researched and multiple publications on these developments during the era of Fourth Industrial Revolution are available. However, most of them address just a few aspects of the HRM, and unlike available literature, the present work is a comprehensive one, where major aspects of HRM have been discussed with a future possibility of automation using IoT technologies. Organizations aspiring for taking a lead in ID 4.0 by embarking on a digital journey will be benefitted as this study highlights the key elements of HRM that include thrust on training, learning and innovations; IoT competency essentials; transformative learning solutions; hardware essentials for skill development, reskilling and retraining for bridging the skill gap; and risk and vulnerability issues can be used to overcome HRM issues by harnessing IoT and related technologies. The findings of the study are relevant for organizations, institutions and HR managers. The study proposes implementation of an IoT-based reusable framework for automating HRM system and processes that would eventually lead to comprehensive skill development through customization and seamless integration of existing HRM system by deployment of IoT sensors, actuators and devices. The study contributes to the IoT and ID 4.0 literature by providing significant insights into utilization of these technologies for skill development.
Ant Colony-Based K-Mediod for Data Clustering
The paper presents a K-mediod clustering algorithm based on ant colony optimization theory. Finding clusters in data is a challenging problem. Clustering task aims at the unsupervised classification of patterns in different clusters. Clustering with ant-based algorithm is the most promising method and has been shown to produce good results in a wide variety of problems. With this motivation, the paper proposes a novel ant-based K-mediods algorithm that modifies the ant K-means as locating the objects in a cluster with the probability, which is updated by the pheromone, while the rule of updating pheromone is according to the value, which is defined as the ratio of the total variation and within cluster variation.An experiment is conducted on both artificial and real-life databases. The experimental outcome confirms that clusters obtained through ant-based K-mediods are significantly better than clusters obtained through K-means and ant K-means in all databases.
Time Series Forecasting Models for Predicting Conjunctivitis Disease Cases
In recent times, machine learning is a powerful technique for data analysis and for making future prediction. There are many existing forecasting models that are useful in predicting different areas. Acute conjunctivitis, commonly known as "pink eye", is one of the most common eye infections, particularly among school children. Because of its highly contagious nature, everyone is susceptible, especially those in crowded places such as kindergarten, indoor amusement parks and swimming pools. Hence as a precautionary measure, there is an imperative need to predict the future possibilities of conjunctivitis cases. The paper uses machine learning-based forecasting models for predicting conjunctivitis cases in Hong Kong. The analysis is conducted on the data of past years conjunctivitis cases in Hong Kong. The mean forecast, seasonal naive, auto ARIMA and neural network techniques are used for analysis and forecasting. The surpassing model is adopted based on the accuracy factor. The accuracy of the models is compared with respect to root mean square error and auto correlation function. The results reveal that the neural network model produces the least error and hence is the best prediction model for the dataset in terms of accuracy.