MIT-World Peace University (MIT-WPU) is a top educational institute located in Pune, India. It is recognized within&nbsp;UGC under Government of Maharashtra Act No. XXXV 2017.&nbsp;

It is part of the MIT group of institutions (established in 1983) which covers 10+ campuses across India and has more than 50,000+ students enrolled across various disciplines at a given point of time. The institute houses 15 schools ranging from Engineering &amp; Technology, Design, Pharmacy, Commerce, Governance among others. It offers undergraduate, postgraduate and PhD programs among different disciplines.&nbsp;

&nbsp;

MIT World Peace University

School of Computer Engineering & Technology

Energy usage increased in tandem with the growth of cloud computing. This proliferation in energy usage has consequently resulted in a humongous increase in the surrounding carbon footprint. Furthermore, the exponential rise of 'data servers' and other infrastructure is driving up energy consumption. As a result, a reduction in energy use will result in a lesser carbon footprint in the surrounding environment. Green-computing in "cloud computing"is the finding and development of energy-saving digital solutions for reducing carbon pollution in the atmosphere. Green Cloud computing intends to accomplish effective processing and computing infrastructure use and reduce energy usage. In this paper, the carbon footprint produced by cloud infrastructures is analyzed and the compelling need for Green cloud computingis suggested. It is critical to ensure that the foreseeable growth of cloud computing is economically sound. © 2022 IEEE.

World University root node

Engineering and Technology

Proceedings of the International Conference on Electronics and Renewable Systems, ICEARS 2022

Carbon Footprint Analysis: Need for Green Cloud Computing

Data Storage security is one of the highest concerns for any organisation. Even if the organisation maintains its own infrastructure or hires cloud storage to store its data, privacy of the data and its protection in any mode is always the highest priority for any organisation. The cloud provides with a huge amount of storage space and also with various resources to the different organisations as per their requirements. In this paper, four different techniques that are proposed for data protection and recovery of the data in case of loss due to any eventuality or failure of the functioning of cloud are reviewed. The first technique to be studied is the Seed based algorithm that is used for recovery of data which is remotely stored at any geographical location in a cloud. The technique can restore the data which even if unfortunately is lost can be still recovered. The second technique reviewed is the attribute based access control algorithm which is used to secure the data thereby maintaining the safety and sanctity of the stored data in the cloud. Another technique which is quite novel is a hybrid technique of using MRADO data obfuscation method along with LSB. This provides with data masking wherein the original data remains totally camouflaged under the image that get obfuscated without the attacker coming to know about its existence. Another data protection model mentioned in the paper is the model that is based on an encryption attribute access control. This model proposes a data detection algorithm which detects the access record of the data. Post analysis of the four different algorithms, the use of two of the techniques is proposed for the protection of the data in cloud. © 2022 IEEE.

Proceedings - 6th International Conference on Computing Methodologies and Communication, ICCMC 2022

Protection of Data in Cloud based on Seed based Algorithm and Encrypted Access Control

Breast Cancer is a common cancer occuring among women throughout the entire world. This attributes to a majority of deaths and cases in the global statistics, which makes it a significant health problem in our society. This paper showcases the classification of breast cancer tumors and the different boosting/ensemble techniques which are used for a more accurate classification. This research presents the working and comparison between classifiers such as Bagging Meta-Estimator, ADA-Boost and XGBM. We will also be showcasing the comparison between the results of these classifiers/techniques and conclude which one is the most accurate in the classification process. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Lecture Notes on Data Engineering and Communications Technologies

Classification of Breast Tumor Using Ensemble Learning

Visual cryptography (VC) is a secret sharing cryptographic technique, which permits visual information that is encrypted in such a way that the decrypted information shows the visual image. Security is the common problem that arises in the general VC technique. To secure the visual information, an effective method is proposed using a developed sailfish invasive weed optimization (SIWO) algorithm. At first, the grayscale image is shared with multiple parties, and here the shared images are encrypted and decrypted to reconstruct the original image back. The key generation is done using the developed SIWO-based data sharing approach. Here, the developed approach offered the peak signal-to-noise ratiof 34.870 and 33.711 dB for Lena and Cameraman images, respectively, and it attains better performance in terms of secret image sharing. © 2021 Wiley Periodicals LLC.

International Journal of Intelligent Systems

Sailfish invasive weed optimization algorithm for multiple image sharing in cloud computing

Lecture Notes in Networks and Systems

Hip-Hop Culture Incites Criminal Behavior: A Deep Learning Study

Communications in Computer and Information Science

Machine Learning-Based Psychology: A Study to Understand Cognitive Decision-Making

Music enthusiasts are growing exponentially and based on this, many songs are being introduced to the market and stored in signal music libraries. Due to this development emotion recognition model from music contents has received increasing attention in today’s world. Of these technologies, a novel Music Emotion Recognition (MER) system is introduced to meet the ever-increasing demand for easy and efficient access to music information. Even though this system was well-developed it lacks in maintaining accuracy of the system and finds difficulty in predicting multi-label emotion type. To address these shortcomings, in this research article, a novel MER system is developed by inter-linking the pre-processing, feature extraction and classification steps. Initially, pre-processing step is employed to convert larger audio files into smaller audio frames. Afterwards, music related temporal, spectral and energy features are extracted for those pre-processed frames which are subjected to the proposed gradient descent based Spiking Neural Network (SNN) classifier. While learning SNN, it is important to determine the optimal weight values for reducing the training error so that gradient descent optimization approach is adopted. To prove the effectiveness of proposed research, proposed model is compared with conventional classification algorithms. The proposed methodology was experimentally tested using various evaluation metrics and it achieves 94.55% accuracy. Hence the proposed methodology attains a good accuracy measure and outperforms well than other algorithms. © 2022, The Author(s), under exclusive licence to Springer Science+Business Media, LLC, part of Springer Nature.

Multimedia Tools and Applications

Multi-label emotion recognition from Indian classical music using gradient descent SNN model

Covid19 has had a widespread influence on health services and the way of life. A prompt diagnosis is crucial for curbing the development of the disease and lowering the number of fatalities. It is customary and standard routine to employ blood tests to detect presence of pathogen, but because of the time and expense involved, it is often necessary to turn to other rapid and affordable options. We implemented two distinct transference based deep layered architectures in this study i.e., ResidualNet50 along with VGG16, to classify X-rays as COVID19, pneumonia, or normal. ResidualNet50 trained with transference approach outperformed the other deep-learning model i.e., VGG16, in the planned execution. Our proposed transfer deep-learning based model obtained an overall high classification accuracy of 98.5 percent. Result analysis and interpretation via performance curves have been comprehensively discussed in this paper. © 2022 IEEE.

8th International Conference on Advanced Computing and Communication Systems, ICACCS 2022

Efficient Diagnosis of Covid19 by Employing Deep Transfer Learning on Pretrained VGG and ResidualNet Architectures

In Sensor Networks (SNs), Network Lifetime (NL) enhancement using Data Aggregation Trees (DATs) is an extensively studied NP complete problem. The study in this paper investigates the existing DAT scheduling heuristics and proposes a metric termed as Brevis Factor ρ to evaluate the merit of the employed heuristics. Then, the ρ metric is applied to the state-of-art DAT scheduling heuristics which are typically based on Residual Energy (RE) parameter of the sensor nodes. Further, this paper proposes a new heuristics parameter for DAT scheduling based on the Number of Neighboring nodes (NN). Performance of NN-based heuristics is evaluated with rigorous simulations, and the results demonstrate improvement in NL as compared with the state-of-art. The values of ρ are observed for the existing RE-based heuristics as well as the proposed NN-based heuristics. The results demonstrate how ρ metric values evaluate the DAT scheduling heuristics. In addition, the results facilitate to understand the trade-off associated with the overheads to reconstruct DATs while improving NL. © 2021 John Wiley & Sons Ltd.

International Journal of Communication Systems

Brevis factor ρ to evaluate data aggregation tree scheduling heuristics in sensor networks

For cancer prediction, the prognostic stage is the main factor that helps medical experts to decide the optimal treatment for a patient. The main objective of this study is to predict prognostic stage from the medical records of various health institutions. Total 465 pathological and clinical reports of people living with breast cancer has been collected from India's reputed treatment institutions. Different anatomic and biologic factors are extracted from unstructured medical records using a novel combination of natural language processing (NLP) and fuzzy decision tree (FDT) for prognostic stage detection. This study has extracted the anatomic and biologic factors from medical reports with high accuracy. The average accuracy of the prognostic stage prediction found 93% and 83% in rural and urban regions, respectively. A generalized method for cancer staging with great accuracy in a different medical institution from dissimilar regional areas suggest that the proposed research improves the prognosis of breast cancer. © 2021 Informa UK Limited, trading as Taylor & Francis Group.