Data Mining - Concepts and Techniques.

SARS-CoV-2 is a novel virus, responsible for causing the COVID-19 pandemic that has emerged as a pandemic in recent years. Humans are becoming infected with the virus. In 2019, the city of Wuhan reported the first-ever incidence of COVID-19. COVID-19 infected people have symptoms that are related to pneumonia, and the virus affects the body's respiratory organs, making breathing difficult. A real-time reverse transcriptase-polymerase chain reaction (RT-PCR) kit is used to diagnose the disease. Due to a shortage of kits, suspected patients cannot be treated promptly, resulting in disease spread. To develop an alternative, radiologists looked at the changes in radiological imaging, like CT scans, that produce comprehensive pictures of the body of excellent quality. The suspected patient's computed tomography (CT) scan is used to distinguish between a healthy individual and a COVID-19 patient using deep learning algorithms. A lot of deep learning methods have been proposed for COVID-19. The proposed work utilizes CNN architectures like VGG16, DeseNet121, MobileNet, NASNet, Xception, and EfficientNet. The dataset contains 3873 total CT scan images with “COVID” and “Non-COVID.” The dataset is divided into train, test, and validation. Accuracies obtained for VGG16 are 97.68%, DenseNet121 is 97.53%, MobileNet is 96.38%, NASNet is 89.51%, Xception is 92.47%, and EfficientNet is 80.19%, respectively. From the obtained analysis, the results show that the VGG16 architecture gives better accuracy compared to other architectures.

/pdf/covid-19-detection-based-on-lung-ct-scan-using-deep-learning-3822d034.pdf

COVID-19 Detection Based on Lung Ct Scan Using Deep Learning Techniques


Purpose
The purpose of this paper is to give an overview of artificial intelligence (AI) and other AI-enabled technologies and to describe how COVID-19 affects various industries such as health care, manufacturing, retail, food services, education, media and entertainment, banking and insurance, travel and tourism. Furthermore, the authors discuss the tactics in which information technology is used to implement business strategies to transform businesses and to incentivise the implementation of these technologies in current or future emergency situations.


Design/methodology/approach
The review provides the rapidly growing literature on the use of smart technology during the current COVID-19 pandemic.


Findings
The 127 empirical articles the authors have identified suggest that 39 forms of smart technologies have been used, ranging from artificial intelligence to computer vision technology. Eight different industries have been identified that are using these technologies, primarily food services and manufacturing. Further, the authors list 40 generalised types of activities that are involved including providing health services, data analysis and communication. To prevent the spread of illness, robots with artificial intelligence are being used to examine patients and give drugs to them. The online execution of teaching practices and simulators have replaced the classroom mode of teaching due to the epidemic. The AI-based Blue-dot algorithm aids in the detection of early warning indications. The AI model detects a patient in respiratory distress based on face detection, face recognition, facial action unit detection, expression recognition, posture, extremity movement analysis, visitation frequency detection, sound pressure detection and light level detection. The above and various other applications are listed throughout the paper.


Research limitations/implications
Research is largely delimited to the area of COVID-19-related studies. Also, bias of selective assessment may be present. In Indian context, advanced technology is yet to be harnessed to its full extent. Also, educational system is yet to be upgraded to add these technologies potential benefits on wider basis.


Practical implications
First, leveraging of insights across various industry sectors to battle the global threat, and smart technology is one of the key takeaways in this field. Second, an integrated framework is recommended for policy making in this area. Lastly, the authors recommend that an internet-based repository should be developed, keeping all the ideas, databases, best practices, dashboard and real-time statistical data.


Originality/value
As the COVID-19 is a relatively recent phenomenon, such a comprehensive review does not exist in the extant literature to the best of the authors’ knowledge. The review is rapidly emerging literature on smart technology use during the current COVID-19 pandemic.


Artificial Intelligence Adoption in the Post COVID-19 New-Normal and Role of Smart Technologies in Transforming Business: a Review

Machine Learning is a predominantly developing field in the current scenario due to spontaneous growth in size of data. Dimensionality Reduction is significant step used in machine learning. The Imprecation of dimensionality refers to the difficulty that comes up when working with high dimensional data. The Proposed work developed to reduce the risk of high dimensional data representation in the form of low dimensional data representation. This paper presents the dimensionality reduction practices such as Principal Component Analysis (PCA), Kernel PCA and Locally Linear Embedded (LLE).

https://iopscience.iop.org/article/10.1088/1757-899X/1084/1/012005/pdf

Performance Analysis of Dimensionality Reduction using PCA, KPCA and LLE for ECG Signals

Reinforcement learning (RL) methods can successfully solve complex optimization problems. Our article gives a systematic overview of major types of RL methods, their applications at the field of Industry 4.0 solutions, and it provides methodological guidelines to determine the right approach that can be fitted better to the different problems, and moreover, it can be a point of reference for R&D projects and further researches.

/pdf/the-applicability-of-reinforcement-learning-methods-in-the-ca08oa2wwf.pdf

The Applicability of Reinforcement Learning Methods in the Development of Industry 4.0 Applications

Education institutions like Schools, colleges, and universities in India are currently based on traditional learning methods and follow the conventional setting of face-to-face interaction/lectures in a classroom. Most of the academic sector started unified learning, still most of them struct with old steps. The unexpected Plague of a deadly infection called COVID-19 caused by (SARS-Cov-2) trembled the whole world. The WHO announced it as a disease outbreak. This circumstance challenged the whole education system worldwide and compelled educators to change to an online mode immediately. Many educational organizations that were earlier unwilling to change their traditional didactic practice had no choice but to move exclusively to online teaching–learning. This article provides an elaborate discussion about the education sector's impact during a disease outbreak in India. It offers a detailed discussion regarding how India adopts the e-learning approach in this critical situation. Further, it describes how to cope with the challenges related to e-learning.

/pdf/adoption-of-e-learning-during-lockdown-in-india-tie3mdd0et.pdf

Adoption of E-Learning during Lockdown in India

Machine learning is the worldwide recent research technique for various systems as they are intelligent enough to find the solution for classification and prediction problems. The proposed work is about a hybrid genetic fuzzy algorithm that performs an optimal search as well as classification upon uncertain data. The data which is uncertain is suitable for fuzzy classifiers to predict the disease. The hybrid genetic fuzzy system applied on the attributes selects relevant attributes. The selected attributes are fed into the fuzzy classifier. The fuzzy rules are again generated using genetic algorithms. This algorithm is applied on three of the important and bench marking data sets taken from the UCI machine learning repository. The heart disease, Wisconsin breast cancer and Pima Indian diabetes datasets produce classification accuracy as 89.65%, 99.5% and 88.93% respectively. In this article there is a comparative study on few of the feature selection and feature reduction techniques.

/pdf/comparative-study-on-dimensionality-reduction-for-disease-3ylqc4uh8y.pdf

Comparative study on dimensionality reduction for disease diagnosis using fuzzy classifier

Decision-making has been one of the challenging tasks in solving real-world problems. Decision-making mimics human activity which in turn has noteworthy impacts. Several researches have proved that the quality of decisions has been improved by developing computer-based technologies that aid and extend the human capabilities. Decision support systems (DSS), which augment in making proper decisions, to an extent do sometimes lack intelligence. The recent advances in the field of artificial intelligence (AI) have made this possible in a wide range of multifarious applications. AI has the capability of mimicking human decision-making and has also shown that they are capable of assisting and improving human decision-making in real-time complex environments. Embedding intelligence into the DSS using the AI capabilities has been progressing, thus forming the intelligent support systems for decision-making (ISSDM). These support systems have been used in simplifying the decision-making process in several areas, namely, healthcare, cybersecurity, finance, marketing, and commerce. This chapter reviews the role of artificial intelligence tools such as artificial neural networks, fuzzy logic, bio-inspired algorithms, and intelligent agents in the decision-making process.

Decision Making Models Through AI for Internet of Things

Everything begins from a single origin with a unique point in space and time. This is the spark of innovation that fuels the most amazing breakthroughs. It is the passion for discovery that unveils the genesis of all that exists in the universe. Today the power of AI helps computer achieve superhuman capabilities in image recognition and lets scientists save our precious resources by analyzing in 1 month what used to take 10 years. Everyday devices translate even the most complex languages from voice into text and images into words helping the visually impaired recognize an old friend or letting a visually impaired woman read to her child for the first time. Autonomous vehicles give us the freedom to reimagine our city streets where there are no streets, to help the lost to find their way home. We see robots teach themselves to perform simple tasks. We even watch them all as they take their first step. And today a 2500-year-old game meets its match as a computer competes with one of the greatest human champions of all time and wins. This is a collective imagination fuelled by forward-looking technologies and the beginning of the most amazing discoveries yet to come. There are many applications of deep learning. Machine learning provides us an incredible set of tools. If there is a difficult problem in hand, we need not find an algorithm for it, it finds out by itself what is important about the problem and tries to solve it on its own. In many problem domains they perform better than human experts. One of its applications is toxicity detection for different chemical structures by means of deep learning. It is so efficient that it could find the toxic property of the chemicals. Next one is mitosis detection from large images. Mitosis means that certain nuclei are undergoing different transformations that are quite harmful and quite difficult to detect. The technique called convolution neural networks outperforms professional radiologists at their own task. Learning algorithm can read a website and find out whether fake content is discussed there as real content or not. Because of the imperfection of the 3D scanning procedures, 3D scanned furniture is too noisy to use as they are. However, there are techniques to look at these really noisy models and try to figure out how they should look by learning the symmetries and other properties of real furniture. This algorithm can also do an excellent job at predicting how different fluids behave in time and the attire for expected to be super useful in physical simulation in the following years. Another application where a computer algorithm is called deep Q learning plays pong against itself and eventually achieves expertise.

Machine Intelligence and Automation: Deep Learning Concepts Aiding Industrial Applications

The elastic optical network (EON) fulfills the upcoming generation network requirements such as high-definition videos, high bandwidth demand services, and ultra-high-definition televisions. The key issues in EON are routing spectrum assignment and spectrum fragmentation for spectrum allocation. The spectrum fragmentation issues are resultant in poor consumption of spectrum resources and an increase in the new connection blocking. A flexible defragmentation algorithm must utilize more spectrum resources with a high transmission rate. This paper presents a new multiconstrained defragmentation algorithm (MCDFA) for elastic optical networks. The MCDFA addressed two key issues: spectrum allocation for new connections and then reconfiguring the existing connections in a nondisruptive manner. The first-last-exact fit spectrum allocation policy assigns the spectrum slots during the new connection request. It splits each light path request by disjoint/ nondisjoint and by efficiently handling the small fragmented slots in spectrum resources. The simulation results are evaluated using standard metrics such as bandwidth blocking probability, bandwidth fragmentation ratio, and spectrum utilization gain. The results also demonstrated that our proposed algorithm generates promised solution to EON’s routing, spectrum assessment, and fragmentation issues.

S. Sree Dharinya

Papers

Adoption of E-Learning during Lockdown in India

Comparative study on dimensionality reduction for disease diagnosis using fuzzy classifier

Decision Making Models Through AI for Internet of Things

Machine Intelligence and Automation: Deep Learning Concepts Aiding Industrial Applications

The Effectual Spectrum Defragmentation Algorithm with Holding Time Sensitivity in Elastic Optical Network (EON)