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 Electronics & Communication Engineering

World University root node

Engineering and Technology

ECS Transactions

Virtual Voice Assistant For Smart Devices

Past decade has shown an overwhelming use of social media. Inspite of multi-fold benefits of using social media platforms, it is being misused due to increasing prevalence of inappropriate content in form of hate speech and abusive language shared on these platforms. Hate speech content is one such form of content that has shown dramatic increase in recent years. Automated techniques like AI and NLP have reported significant performance in detection of hate speech content. In order to extract the textual properties from online content that help in the detection of hate speech, feature extraction and representation using NLP are essential. There is an increasing trend in academia and industry to the use of pretrained neural network language models for hate speech and offensive content detection. This paper presents the performance of important feature extraction techniques: TD-IDF, GloVe, FastText and BERT for binary classification and multiclass classification of hate speech with Convolutional Neural Network (CNN) architecture as the base network for all the techniques. © 2022 IEEE.

2022 International Conference on Signal and Information Processing, IConSIP 2022

Feature Representation Techniques for Hate Speech Detection on Social Media: A Comparative Study

With the advent of driverless car systems, automatic traffic sign recognition is must. The proposed deep learning model performs well in recognising forty-three traffic signs. The model also can be ported on Jetson-Nano device resulting into a portable standby device. © Grenze Scientific Society, 2022.

13th International Conference on Advances in Computing, Control, and Telecommunication Technologies, ACT 2022

Deep Learning Approach for Traffic Sign Recognition

The inescapable utilization of Internet and social media has opened doors of social event continuous data across the globe in an exceptionally limited capacity to focus time. Social media networks are becoming a focal point for disseminating news that take the form of fake news and rumors. A rumor refers to a statement or a post that is false and is circulated fast on social media without verifying its truthfulness. Rumors have an adverse effect not only on an individual, but also it extends to the entire society. While manual detection and screening of rumors are becoming a dire need, automatic detection of rumors is an emerging research with various machine learning algorithms. The paper summarizes the utility of various machine learning algorithms for automatic rumor detection. Various steps like feature engineering and classification are also thoroughly studied and detailed in this paper. This paper coins to further research directions. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Lecture Notes in Electrical Engineering

Machine Learning Approaches for Rumor Detection on Social Media Platforms: A Comprehensive Survey

Kinship verification based on facial images is a recent and challenging problem in computer vision and machine learning. It has many real-world potential applications including tracing of missing children cases, social media image analysis, and image annotation. The existing methods do not focus on probability distribution differences between kinship facial images; that is why the performance of these methods is poor. The deep learning methods required a large amount of data. Practically, parents and their children share common features. To take into account this transfer learning based framework is proposed. The extracted hand-crafted features are given to a transfer learning framework that transfers the knowledge acquired from facial images of parents to children and vice versa. We evaluated the proposed methods on standard kinship datasets and experimental results showed that the proposed method outperforms in terms of accuracy and computational efficiency as compared to state of art methods. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Smart Innovation, Systems and Technologies

Feature Based Transfer Learning for Kinship Verification

Social Media has become a vital component of every individual's life in society opening a preferred spectrum of virtual communication which provides an individual with a freedom to express their views and thoughts. While virtual communication through social media platforms is highly desirable and has become an inevitable component, the dark side of social media is observed in form of detrimental/objectionable content. The reported detrimental contents are fake news, rumors, hate speech, aggressive, and cyberbullying which raise up as a major concern in the society. Such detrimental content is affecting person’s mental health and also resulted in loss which cannot be always recovered. So, detecting and moderating such content is a prime need of time. All social media platforms including Facebook, Twitter, and YouTube have made huge investments and also framed policies to detect and moderate such detrimental content. It is of paramount importance in the first place to detect such content. After successful detection, it should be moderated. With an overflowing increase in detrimental content on social media platforms, the current manual method to identify such content will never be enough. Manual and semi-automated moderation methods have reported limited success. A fully automated detection and moderation is a need of time to come up with the alarming detrimental content on social media. Artificial Intelligence (AI) has reached across all sectors and provided solutions to almost all problems, social media content detection and moderation is not an exception. So, AI-based methods like Natural Language Processing (NLP) with Machine Learning (ML) algorithms and Deep Neural Networks is rigorously deployed for detection and moderation of detrimental content on social media platforms. While detection of such content has been receiving good attention in the research community, moderation has received less attention. This research study spans into three parts wherein the first part emphasizes on the methods to detect the detrimental components using NLP. The second section describes about methods to moderate such content. The third part summarizes all observations to provide identified research gaps, unreported problems and provide research directions. © 2022, The Author(s), under exclusive licence to Springer-Verlag GmbH Austria, part of Springer Nature.

Social Network Analysis and Mining

Detection and moderation of detrimental content on social media platforms: current status and future directions

Visual Pattern Recognition Networks (VPRN) delivers high performance using deep neural networks. With the advancements in deep neural networks VPR network has gained wide popularity. Continuous advancements will be nurtured with the availability of big data and enormous computing powers. However, such DNN based VPRN models are plunged with computational complexities, intense memory requirements, huge energy expenses which impedes its deployment in resource constrained, strict latency required environments such as edgeAI. For instance, the VGG-16 model needs 500 MB of storage space, has 138 million parameters and involves 15.5 billion Floating Point Operations (FLOPs) to classify a single image with a 32 bit floating point addition that consumes 0.9 pJ. Such overheads demand for compression of VPRN models without impairing its performance. Various compression methods are reported in literature. This survey paper presents a survey on pruning, a popular compression technique for DNN as applied for VPRN. This paper presents comprehensive survey, comparison and points further research direction. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

Pruning for Compression of Visual Pattern Recognition Networks: A Survey from Deep Neural Networks Perspective

The Internet of Vehicles is considered an adaptation to the current transportation system's severe position, thanks to advancements in wireless communication systems and intelligent mobility technologies. The autos in the Network of Vehicles system generate Vehicular Networks and constantly deliver additional functionality inspired by real driving data transmitted by the vehicles using wireless communication technology. Drivers may modify the distance between automobiles while planning their route depending on current traffic conditions, positively affecting the efficiency and safety of the transport network. Because of the unique capabilities of a Technology of Devices service platform, automobiles must transmit their position information often. Assailants can gather and analyze automobile transmit data to acquire personal information and perhaps even track the customer's vehicle path, creating new security challenges. This article offers a Blockchain-based confidentiality solution for such Vehicular networks. This same solution incorporates blockchain technology with the Website of Vehicles network to provide a secure and convenient two-way authentication mechanism procedure based on encryption, as well as removing the conventional Internet of Vehicles system's centralized dependency issue. © 2022 IEEE.

2022 IEEE International Conference on Blockchain and Distributed Systems Security, ICBDS 2022

Internet of Vehicles System Based on Blockchain

Lung diseases are a major concern nowadays. The human body consists of diverse fundamental organs, out of which Lung is one of them. The Lungs are made up of two sections, right lung and left lung and the main function of lungs is to facilitate exchange of gas which is called as breathing or respiration. Our present modern lifestyle, ecological contamination, adulteration is helping in expanding the Human Lungs issue. What's more, simultaneously there are various Image processing techniques that are blending the tremendous answer for the medical field to identify and analyze the Lung's illnesses. A system development which is based on Deep learning is proposed to get better and accurate result which includes Image Processing techniques like image pre-processing, segmentation, thresholding, image enhancement and classification. Computer Tomography (CT) scan images takes from LIDC database as an input to examine the Lungs disorders in human body. Convolution Neural Network is practiced to perform classification of input lung images into cancerous and noncancerous classes. This technique will assist to oncologists as second opinion and will develop the accurate quality of lung cancer detection. With the proposed system, lung cancer detection is done with 98.44% of accuracy. © 2022 IEEE.

2022 6th International Conference on Computing, Communication, Control and Automation, ICCUBEA 2022

Machine learning application for Lung Cancer Detection

We investigate methodologies for improving the results of Physics Informed Neural Networks-Neural Networks that are trained with the supervision of relevant physical laws to solve specific problems. The methods we look into in this work are implementing the ResNet architecture and implementing Fourier Feature Mapping to allow the network to learn high-frequency features. We implement these methods to train a PINN on the 1D Burger's Equation. The predictions of the PINNs are compared against the solution from a Finite Difference Method based solver along with a baseline performance of a simple densely connected network. © 2022 IEEE.