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

Document classification particularly in biomedical research plays a vital role in extracting knowledge from medical literature, journal, article and report. To extract meaningful information such as signs, symptoms, diagnoses and treatments of any disease by classification, the context needs to be considered. The need to automatically extract key information from medical text has been widely accepted and it has been proven that search based approaches are limited in their ability. This paper presents a novel method of information identification for a particular disease using Gaussian Naïve Bayes and feature weighting approach that is then classified by the context. It is useful to enhance the effectiveness of analytics by considering the importance of the term as well as the probability of every feature of the disease during classification. Experimental results show that our method upgrades performance of classification system and is an improvement from traditional classification system. © 2018 IEEE.

World University root node

School of Computer Engineering & Technology

Proceedings of the 8th International Advance Computing Conference, IACC 2018

Identifying Contextual Information in Document Classification using Term Weighting

Scissor lifts are used as an alternative to scaffolding and ladders to work in elevated areas, they are very commonly used in warehouses and working sites. But, the random distribution of load on and uneven surfaces on working sites, have accounted for a lot fatal accidents due to lift tip-over. The current understanding of scissor lift considers static load and working conditions. This paper proposes an embedded system, which can be added to the scissor lifts current control mechanism using an inertial measurement unit (IMU) to measure the tilt angles of the platform, and relays for signal conditioning. Complementary filter has been applied to decrease the drift error in angle measurement by the IMU. The electro-mechanical relays have high Mean Time between Failure hence increasing overall reliability of the system. The performance of the system along with the dynamic control mechanism have been mentioned in the paper. © 2018 IEEE.

School of Electronics & Communication Engineering

Proceedings - 2018 4th International Conference on Computing, Communication Control and Automation, ICCUBEA 2018

Embedded Control System for Self Adjusting Scissor Lift

This system is mainly based on two techniques, CNC machine and 3D printing. 2D plotter is used for drawing circuits on any surface like paper, cardboard as per the user requirement and conductive ink or marker is used as an object for drawing circuits. Conductive marker is placed in such a way that it can be moved in x and y direction using stepper motor and in up and down direction using servo motor. Arduino Uno or mega and CNC shield is used to drive motors. Benbox software is used to generate G-code and give input image of drawn circuit to the plotter. The research work is focused on a low cost and simple controlling system for 2D plotter machines to draw electronic circuit diagrams of PCBs on any surface. © 2018 IEEE.

Implementation of Paper PCB Using Conductive Ink 2D Plotter

Crop production problems are common in India which severely effect rural farmers, agriculture sector and the country's economy as a whole. In Crops leaf plays an important role as it gives information about the quantity and quality of agriculture yield in advance depending upon the condition of leaf. In this paper we proposed the system which works on preprocessing, feature extraction of leaf images from plant village dataset followed by convolution neural network for classification of disease and recommending Pesticides using Tensor flow technology. The main two processes that we use in our system is android application with Java Web Services and Deep Learning. We have use Convolution Neural Network with different layers five, four three to train our model and android application as a user interface with JWS for interaction between these systems. Our results show that the highest accuracy achieved for 5-layer model with 95.05% for 15 epochs and highest validation accuracy achieved is for Slayer model with 89.67% for 20 epochs using tensor flow. © 2018 IEEE.

Leaf Disease Detection and Recommendation of Pesticides Using Convolution Neural Network

For GIS database and environmental monitoring, detection of buildings and trees plays very important role. By integrating LiDAR data with aerial images, significant improvement in accuracy can be achieved. Primarily, after the pre-processing aerial images are fused with LiDAR images. Due to this, region of interest (ROI) has been extracted accurately. The relevant color (mean, standard deviation) and texture features (energy, contrast, entropy etc.) are extracted from the images. These extracted features are given to support vector machine (SVM) for classification which successfully classifies buildings and trees from images with accuracy 96.96% and 59.01 % respectively. Finally, the performance of classifier is evaluated by Kappa Statistic. © 2017 IEEE.

2017 9th International Conference on Advanced Computing, ICoAC 2017

Building and Tree Detection by Fusing LiDar and Aerial Images for Urban Development Planning

Abstract—In image processing feature extraction starts from an initial set of measured data and builds derived values as features which are intended as informative and non-redundant. This facilitates the learning and leading to interpretations. Image processing Algorithms are used to detect and differentiate among various desired portions or shapes features of an image. In particular texture, color and shape features of image are used to define similarity among images. Image is a representation of visual information. Objects and its shape are important aspect as image contains information about various useful structures during information analysis. Segmentation of image is one of the necessary task in image processing. It involves generation of various useful parts as set of selected pixels. Such division aims automation in image objects identification and relevant information analysis. For any image shape object is unique. Object detection algorithms typically use extracted features and learning algorithms to recognize instances of an object category. It is commonly used in applications such as image retrieval, security, surveillance and advanced driver assistance systems. During the process of object extraction there is a need to separate image background and foreground in efficient and accurate manner. This paper implements context shape boundary extraction along with color segmentation is done to identify objects and its region color. This combined methodology of image segmentation and context shape description algorithm increases accuracy of detecting useful feature of image. We describe a method for registering pairs of images based on thin-plate spline mappings. This method is scale, translation and rotation invariant.

IEEE International conference on Electrical Electronics, Computers

Improved Color Segmentation Based Context Shape Feature For Image Object Detection

School of Mechanical Engineering

International Engineering Research Journal, ISSN 2395

Design and Performance Analysis of Heat Exchanger for Thermoelectric Power Generation Using Exhaust Waste-Heat Energy

Humans are social animals, and interaction has been one of the major factors for the development of humans. Invention of computer was a benchmark in technological progress achieved by humans. Proper communication technique between humans and electronic appliances has eased out our lives. But due to improper designing of interfaces of systems, nuclear mishaps like Three Mile Island accident have also taken place. To avoid such huge man-made disasters and to facilitate and equip every common man with technology, proper interfacing of technology such that novice as well as experts can use it to reap the full benefits out of any electronic instrument is a must. © 2018, Springer Nature Singapore Pte Ltd.

Lecture Notes in Networks and Systems

Review on Interface Designing and Human–Computer Interaction

Human action recognition has become vital aspect of video analytics. This study explores methods for the classification of human actions by extracting silhouette of object and then applying feature extraction. The method proposes to integrate HOG feature and PCA feature effectively to form a feature descriptor which is used further to train KNN classifier. HOG gives local shape-oriented variations of the object while PCA gives global information about frequently moving parts of human body. Experiments conducted on Weizmann and KTH datasets show results comparable with existing methods. © 2018, Springer Nature Singapore Pte Ltd.