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

Engineering and Technology

Tiredness, and sleeping of the drivers while driving is one of the main causes of traffic accidents. Observations of the drivers to detect tiredness and fatigue is a complex task which includes behavioral and physical elements. Different approaches were made, including computer vision with the ability to track and monitor the drivers behind the wheel without the intervention in the driving. The proposed system can observe the alertness or tiredness of drivers in order to prevent them from sleeping while driving. In this work, a framework is developed to detect the fatigue-ness from tracking the cornea of eyes by focusing on the face of the driver. It utilizes applying image morphological changes like dilution, erosion, image segmentation like background elimination and Circular Hough Transform (CHT) to detect cornea of an eye on the captured images on drivers. Whenever the fatigue is recognized it will buzz an alarm at the system and necessary actions can be taken. It additionally decreases incorrect outcomes of by disposing of low-quality faces that happened to a video sequence because of issues in sensible lighting, head movement, and posture variety. © 2017 IEEE.

World University root node

School of Computer Engineering & Technology

2017 International Conference on Computing, Communication, Control and Automation, ICCUBEA 2017

Fatigue Detection System for the Drivers Using Video Analysis of Facial Expressions

With the advancement of Image acquisition and storing, image retrieval has been proven as the research problem. Many approaches for image retrieval, has been stated by researchers to solve the image retrieval problem. In this paper we state DFT transform based approach for image retrieval using Image classes. Here formation of Feature vectors of the Images is based on Color based DFT Phase information of images those belongs to same class. DFT Image transform provides effective way to differentiate the image textures. Particularly Phase part of DFT carries the important information about the objects in image. In the proposed approach of image retrieval, DFT phase information is used for representing the images using feature vector effectively. To make image retrieval more accurate, class wise images are considered for creation of database feature vectors. As, images belonging same class are content wise similar, the generalized feature vector is produced for each class Generalized feature vectors represents all images of that class. Cosine correlation similarity measure is used in the proposed approach. 4 Different types of feature vectors are created and tested for each image class. The Images are retrieved based on the feature vector values of DFT Phase information of RGB's planes with similar to that of Feature vector of Image class. Image retrieval Performance of the proposed approach is compared for database of 1000 images of 10 different categories. Average Accuracy of Image retrieval is above 60% for all classes and more than 75% for some of the image classes. © 2017 IEEE.

Color Image Retrieval Using DFT Phase Information

A new method is proposed here for the automation of street lights. The goal of this project is to implement an energy efficient dynamic street lighting system that detects movements in the sensing area of the lamps, providing lighting only when required and is at its minimum intensity when not in use. This system continuously adapts to the presence and behavior of pedestrian or vehicle on the road. It can light the street only when it is needed. Energy efficiency is obtained by comparing the amount of energy consumed without using this system and with this system. Dynamic Street Lighting System (DSLS) can be represented by using a simulator which combines wireless sensor networks (WSN) and nodes to enable a precise simulation. It will be depicted in the project how the nodes which act like the street lamps will glow/increase its intensity when it senses movement in its sensing area using sensors. When the object is out of its sensing area the node will go back to its lowest intensity. Thus, the nodes switch on only when required. This will save energy consumed by a street light. Taking into consideration the sensing requirement of an area, an optimal sensor deployment scheme is proposed. © 2018 IEEE.

Proceedings of the 2nd International Conference on Electronics, Communication and Aerospace Technology, ICECA 2018

Energy Efficient Dynamic Street Lighting System

The advent of social media and the rapid development of mobile communication technologies have dramatically changed the way to express the feeling, attitude, mood, passion etc. People often express their reactions, fancies, preferences etc.Through social media in the form of short texts instead of long texts. In micro blogging services like twitter, people can share and discuss their views without any constraints. Thus, these are the sentiments of people which can characterize their behavior. Nowadays, politicians also refer facebook, twitter and blogs to collect reviews amongst the people about them. A model is developed which captures the comments of people and forwards it to the preprocessing module. It contains URL removal, stopword removal, tokenization, abbreviation expansion and stemming processes. Further the result obtained is passed on to neural network. Here, Recurrent Neural Network (RNN) model is used to predict the sentiments, whether audience have positive or negative responses. RNN uses its Long Short Term Memory (LSTM) module for processing of the data. The final result obtained is binary classification and representation of opinions. © 2018 IEEE.

Proceedings of the 2nd International Conference on Computing Methodologies and Communication, ICCMC 2018

Political Sentiment Analysis through Social Media

The contribution of this paper is to classify the images with transformation present in it. Transformations in the images are translation, rotation, scale and noise. The accuracy of classification decreases because of translations in the images. The proposed framework uses Convolutional Neural Network (CNN) for classification of transformed images. It consists of two convolutional neural networks, first CNN1, it is the standard CNN trained by images formed by data augmentation approach. Then its performance is tested for dataset of transformed images. The second one CNN2 is trained on only translated images. In the first stage, the images are classified using CNN1. And in the second stage, images misclassified by CNN1 are fed to CNN2 for further classification. The proposed framework is evaluated on hand written digits dataset-MNIST and alphabets dataset by NIST. The result shows that framework proposed outperforms single CNN. © 2018 IEEE.

School of Electronics & Communication Engineering

2018 3rd IEEE International Conference on Recent Trends in Electronics, Information and Communication Technology, RTEICT 2018 - Proceedings

A CNN based framework for translation invariant image classification

Movement is an important aspect of any human being's life therefore lack of it has adverse effect on their overall development. Physically disabled people unfortunately are devoid of this privilege. Mechanical wheelchairs provided some form of mobility but they relied on external help for moving around. Moreover, people with tetraplegia couldn't benefit from it due to loss of all four limbs. Brain Computer Interface (BCI) is construed as interacting with an electronic device solely with brain with the help of Electroencephalogram (EEG) Signals. This technology is applied to existing mechanical wheelchair to control it using brain to overcome the limitations of conventional wheelchair. This paper proposes cost effective application of BCI technology to aid in mobility of physically disabled people. The proposed system utilizes the voluntary eye blink as an event to trigger an action. An eye blink pattern is mapped to a context based physical action like moving the wheelchair in particular direction. © 2018 IEEE.

2018 3rd International Conference for Convergence in Technology, I2CT 2018

Innovative Approach to Control Wheelchair for Disabled People Using BCI

In dental root canal treatment, failure is due to incomplete Obturation. These are formation of voids, under-filling &amp; over-filling of Gutta Percha (GP) material (rubbery, biocompatible and inert material used in sealing canals against bacterial infection.) More studies are required to evolve with properties of GP material after loading. Compaction Force during obturation, Method and Techniques of Root filling are considered important factors. Root canal was modeled in ANSA 15.1.2 and FEA tool as LS DYNA R 7.11 was used to get stress distribution and energy consumed after loading the GP with time. Von Mises stress in the dentine (123.2 MPa) and in the GP present in the Coronal 1/3rd of root canal (13.04 MPa) was observed. © 2017 Elsevier Ltd.

School of Mechanical Engineering

Materials Today: Proceedings

Analysis of Gutta Percha a Dental Root Filling Material for Impact

International Journal for Research in Engineering Application \& Management 4 {\ldots}

Design and Transient Analysis of Earth-Air Heat Exchanger

In recent years the use of electronic learning in teaching institutions has increased extensively. In spite of this, no dedicated system specially developed to enhance the E-Learning experience currently exists. This paper is presented with the concept of building a bot which will be capable of providing a solution to all E-Learning needs of any user. The easiest way of controlling any device is through human voice and hence the bot will use speech recognition to perform actions as per the user. Existing speech recognition systems are expensive and available with usage of internet (online). The paper discusses an offline approach towards speech recognition. The bot will also be capable of performing sentiment analysis on speech so as to get users feedback of the bot and the learning experience. All of the above is planned to be implemented on a low cost Raspberry Pi. Thus a goal of building an E-Learning Bot has been designed at low cost using offline speech recognition.

International Journal of Computer Engineering and Applications (IJCEA)

ENHANCED E-LEARNING USING SPEECH RECOGNITION

Data aggregation algorithms play a primary role in WSN, as it collects and aggregates the data in an energy efficient manner so that the life expectancy of the network is extended. This paper intends to develop a query-based aggregation model for WSN using the advanced optimization algorithm called group search optimization (GSO). The proposed model is constructed in such a way that the querying order (QO) can be ranked based on latency and throughput. Accordingly, the main objective of the proposed GSO-based QO is to minimize the latency and maximize the throughput of WSN. The proposed data aggregation model facilitates the network administrator to understand the best queries so that the performance of the base station can be improved. After framing the model, it compares the performance of GSO-based QO with the traditional PSO-based QO, FF-based QO, GA-based QO, ABC-based QO and GSO-based QO in terms of idle time and throughput. Thus the data aggregation performance of proposed GSO-based QO is superior to the traditional algorithms by attaining high throughput and low latency.