Department of Computer Science & Engineering

From the month of December-19, the outbreak of Coronavirus (COVID-19) triggered several deaths and overstated every aspect of individual health. COVID-19 has been designated as a pandemic by World Health Organization. The circumstances placed serious trouble on every country worldwide, particularly with health arrangements and time-consuming responses. The increase in the positive cases of COVID-19 globally spread every day. The quantity of accessible diagnosing kits is restricted because of complications in detecting the existence of the illness. Fast and correct diagnosis of COVID-19 is a timely requirement for the prevention and controlling of the pandemic through suitable isolation and medicinal treatment. The significance of the present work is to discuss the outline of the deep learning techniques with medical imaging such as outburst prediction, virus transmitted indications, detection and treatment aspects, vaccine availability with remedy research. Abundant image resources of medical imaging as X-rays, Computed Tomography Scans, Magnetic Resonance imaging, formulate deep learning high-quality methods to fight against the pandemic COVID-19. The review presents a comprehensive idea of deep learning and its related applications in healthcare received over the past decade. At the last, some issues and confrontations to control the health crisis and outbreaks have been introduced. The progress in technology has contributed to developing individual's lives. The problems faced by the radiologists during medical imaging techniques and deep learning approaches for diagnosing the COVID-19 infections have been also discussed.

Diabetic retinopathy (DR) is an eye oddity where the human retina is afflicted because of the everincreasing quantity of insulin in the blood. It leads to the loss of sight. Preliminary diagnosis of DR assists to improve to inhibit future injury. Proper DR screening has been recognized as an economical way to accumulate health services. Automated retinal analysis become known as the most significant screening approach for primitive DR diagnosis, which leads to diminishing the workload related to manual screening and also, cost-effective and less time-consuming efforts. In the proposed work, the preprocessing, removal of applicant lesion pixels, and formulation of feature set have been examined which is fully appropriate for the classification task. In preprocessing approach, the framework removes the unwanted pixels, eliminates the optic disc, and extraction of the blood vessels from the retinal images. Morphological operations are applied to extract the boundaries of the blood vessels and then 2D discrete wavelet decomposition is applied to estimate the horizontal, vertical and diagonal coefficients. The candidate lesion pixels i.e. dark and bright DR pixels are detected using an adaptive threshold that uses local statistical, geometrical, and locationbased characteristics of the background image. The extracted feature set is processed using a Knearest neighbor (KNN) classifier with 80% of training data and 20% of testing data to diagnose the severity level of the disease. The proposed scheme is evaluated by the DIARETDB1 benchmark dataset with the performance parameters, i.e. 95% of accuracy, 92.6% of sensitivity and 87.56% specificity achieved with less computation time required.

Segmentation of diabetic retinopathy is a significant requirement for correct severity estimation level. Due to dissimilarity in shapes, size, and quantity of retinal lesions, the procedure of labor-intensive type of grading becomes a more time-consuming and challenging task. It imposes the prerequisite for an automated segmentation framework that can accurately identify the regions with margins and aid ophthalmologists in the early detection and monitoring of the severity level. The proposed work introduces a customized U-Net model based on the InceptionV3 pre-trained CNN network. It uses a periodic shuffling approach along with sub-pixel convolution initialized to convolution nearest-neighbor resize. The model performed training and validation for non-proliferative diabetic retinopathy that is, microaneurysms, hemorrhages, hard and soft exudates on two standard datasets such as IDRiD and DIARETDB1. The proposed model achieves 99.82% accuracy, 88.39% sensitivity, and 99.94% specificity for hemorrhages, 99.95% accuracy, 70.76% sensitivity, and 99.98% specificity for microaneurysms, 99.83% accuracy, 85.9% sensitivity, and 99.95% specificity for hard exudates, along with 99.62% accuracy, 85.38% sensitivity, and 99.71% specificity for soft exudates segmentation on the IDRID dataset. In comparison with both datasets, the proposed system on the IDRID dataset performed accurately with superior state-of-the-art outcomes for segmentation of the retinal lesions.

The epidemic COVID-19 has shaken the globe through its cruelty, and its spread rate continues to rise daily. This paper highlights the clinical stance in the COVID-19 research studies, where time-series statistical analysis has been performed by using Prophet Model. It is widely used to understand the trend of the current epidemic after 2 nd May 2020 with data at the worldwide state. The prophet model is an open-source model obtained by the data science panel on Facebook for performing predicting operations. It assists to make fast and accurate predictions for existing data samples. The Prophet model is simple to implement because its open authorized repository exists on GitHub. The time-series data analysis refers to the confirmed, recovered, and death rates for the time of 2 nd May 2021 to 17 th January 2022. The statistical validation strategy is followed by the implementation of a T-test on the evaluated time-series data. The expected data generated by the predictive model can be further used by the official authorities, medical departments of various countries. Moreover, the model is used to provide new graphical insights into past, present, and future trends.

Smartphones/mobile devices are enduring all the aspects of human life. With the significant increase in demand for applications running on smartphones/mobile devices, developers and testers are anticipated to deliver high quality, on time and within budget applications. The estimation of development and testing provides a baseline and act as a tracking gear for stakeholders and developers. There are various approaches for estimation of traditional software development. But mobile applications are considered different from traditional software such as those running on desktop, laptop or on the web. Many traditional estimation techniques used for this software are adapted to mobile domain. With agile software development (ASD) methodology, the scenario of development and estimation has changed drastically and so as mobile app development and estimation. This paper provides a Systematic Literature Review (SLR) on traditional estimation techniques and agile estimation techniques applied in mobile software/application. Also, effort attributes and accuracy parameters for estimation in mobile apps are presented. However, to date, there are very fewer studies done on the mobile application estimation domain using agile methodology.

Smartphones/mobile devices are enduring all the aspects of human life. With the significant increase in demand for applications running on smartphones/mobile devices, developers and testers are anticipated to deliver high quality, on time and within budget applications. The estimation of development and testing provides a baseline and act as a tracking gear for stakeholders and developers. There are various approaches for estimation of traditional software development. But mobile applications are considered different from traditional software such as those running on desktop, laptop or on the web. Many traditional estimation techniques used for this software are adapted to mobile domain. With agile software development (ASD) methodology, the scenario of development and estimation has changed drastically and so as mobile app development and estimation. This paper provides a Systematic Literature Review (SLR) on traditional estimation techniques and agile estimation techniques applied in mobile software/application. Also, effort attributes and accuracy parameters for estimation in mobile apps are presented. However, to date, there are very fewer studies done on the mobile application estimation domain using agile methodology.

With the substantial proliferation in demand for applications running on mobile devices, developers and testers are foreseen to release applications with high caliber, on time and inside budget. Mobile application testing is imperative and perilous activity in the application development lifecycle, which confirms quality and unswervingly impacts the development effort and affluence of the application. The estimation of effort for testing of apps is a key figure that helps test managers in making approximate accurate decisions for coordinating testing resources. In this study, a regression model is presented to predict test effort for mobile applications considering COSMIC Function Size Measurement (FSM), mobile app characteristics/factors and test factors. The major benefit of this model is that it tends to be utilized at the beginning of mobile app testing life cycle, and thus can assist testers to effectively lead early effort estimation. The model presented is further validated and evaluated for their effectiveness by using a k-fold crossvalidation method. MRE, MMRE, MdMRE, PRED (0.25) and PRED (0.50) indices are used for measuring the accuracy of the model and findings suggest that the proposed model gives a good prediction and can be exercised in the mobile software industry for predicting test effort.

Mobile technology has seen a steep rise in its demand and usage, which has further increased the need for specialized software for mobile devices. For developing mobile applications, existing software development process models are incorporated. But looking at the remarkable growth of mobile devices, the complexity involved in development of mobile applications needs a dedicated life cycle process model, instead of using traditional life cycle process models. Although many existing life cycle models are adapted for mobile apps development but there are certain constraints that needs to be addressed specifically, such as Performance Factor, Power Factor, Band Factor, Connectivity Factor, Context Factor, Graphic Interface Factor, Input Interface Factor, etc. It is a stimulating task to develop mobile application due to these technical constraints. In this paper, a comparative analysis of traditional software life cycle models that are widely used in software development and also discussed the strengths and weakness of using these models for mobile application development. It also emphasize on need for dedicated mobile application development life cycle process in order to provide high quality mobile apps and minimize mobile app development problems and errors that are faced at later stage.

Smartphones<em>/</em>mobile devices are enduring all the aspects of human life. With the significant increase in demand for applications running on smartphones/mobile devices, developers and testers are anticipated to deliver high quality, on time and within budget applications. The estimation of development and testing provides a baseline and act as a tracking gear for stakeholders and developers. There are various approaches for estimation of traditional software development. But mobile applications are considered different from traditional software such as from those running on desktop, laptop or on the web. Many traditional estimation techniques used for these software are adapted to mobile domain. With agile software development (ASD) methodology, the scenario of development and estimation has changed drastically and so as mobile app development and estimation. This paper provides a Systematic Literature Review (SLR) on traditional estimation techniques and agile es...

Mobile platform has taken over all aspects of human activities, and researchers are emphasising on providing efficient and bug free applications running on mobile platform. As the time to market for mobile applications are very short so there is a need for techniques which are automated and provide robust and reliable applications. Although manual testing is the most popular technique for testing graphical user interfaces, but manual testing is often cumbersome and prone to errors. This paper presents a literature review of existing Automated GUI Testing of Android Applications techniques. Because of popularity and open-source nature of android devices the focus of research paper is on techniques used in Android devices.

The Internet of Things(IoT) is a vision in which Internet outspreads into the real world espousal of daily objects. The objects no longer seems separated from the virtual world and can be controlled distantly. The term "Internet of Things" is devised from the two words "Internet" and "Things". The Internet is an interconnected computer networks that use the standard Internet. The word "Things" can be any object or person in real world from any electronic equipment to any non-electronic as well.The Internet of Things (IoT) represents the interconnection of several equipments such as smart devices and services. Presently, more than a billions of devices are connected to Internet, including PCs, embedded sensors, and mobile phones.This paper gives an overview, Architecture ,Application areas, security and privacy challenges in the Internet of Things.

Mobile Cloud Computing is an evolving technology that integrates the concept of cloud computing into the mobile environment. Smartphones are boon in the world of technology but they have certain limitations (e.g. battery life, network bandwidth, storage, energy) when running complex applications which require large computations. Using Cloud Computing in mobile phones, these limitations can be addressed. Certain frameworks have been proposed over the years that can address the issues in mobile cloud computing. These frameworks allow the computation to be offloaded in the cloud environment resulting improvementin the battery life, bandwidth, memory capacity and energy consumption in the smartphones. This paper provides the extensive surveyon the various energy efficient frameworks available to offload the computation from the mobile to the cloud environment. INTRODUCTION Smart Mobile Devices (SMDs) such as smart-phones and tablets Personal Computers (PCs) have become important part of daily life. Nowadays, mobile devices are not only used for voice calls but are efficiently able to run heavy and complicated mobile applications using internet. The volume of data being processed by smartphones and complexity of mobile applications are increasing day by day. However, these SMD has certain limitations such as network bandwidth, battery lifeand storage capacity and processor performance. With the advancement in technology over the years, SMD provide multi-core processors, large memory, bigger and sharper screens, multiple sensors as well as enormous applications. All these together put heavy burden on the battery life of smart phones. Cloud computing (CC) provides a wide variety of computing resources from servers and storage to enterprise applications. Cloud computing is a hosting environment that is immediate, flexible, scalable, secure and available. The computing resources from cloud can be easily and quickly accessed and released after use with very less management effort. The concept of CC can be used in mobile applications running on SMDs to boost up their performance. With the integration and support of CC into the complex mobile applications, the term Mobile Cloud Computing (MCC) arises. MCC provides an infrastructure where the data processing and the data storage of mobile cloud applications occur away from the mobile device and into the cloud and bringing applications and mobile computing to a much broader range of mobile subscribers [1]. One of the key features of MCC is migrating the computation intensive tasks to cloud or servers for their executionand then receiving the results from these servers which is known as Computation Offloading. Mobile Devices take advantage of resource-rich infrastructures by offloading the computation to cloud for saving battery's energy consumption and hence increasing battery lifetime of mobiles. Computation offloading allows SMDs to become more capable. In contrast to traditional client-server architecture, where clients always offloads the computation to the server and are completely dependent on it, the computational offloading migrates programs to servers which are outside of the user's computing environment. The term " surrogate computing " or " cyber foraging " is also used for computation offloading.

Mobile Cloud Computing is an evolving technology that integrates the concept of cloud computing into the mobile environment. Smartphones are boon in the world of technology but they have certain limitations (e.g. battery life, network bandwidth, storage, energy) when running complex applications which require large computations. Using Cloud Computing in mobile phones, these limitations can be addressed. Certain frameworks have been proposed over the years that can address the issues in mobile cloud computing. These frameworks allow the computation to be offloaded in the cloud environment resulting improvementin the battery life, bandwidth, memory capacity and energy consumption in the smartphones. This paper provides the extensive surveyon the various energy efficient frameworks available to offload the computation from the mobile to the cloud environment. Keywords— Mobile Cloud Computing, computation offloading, static offloading, dynamic offloading, energy consumption