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

A major problem in Wireless Mesh Network is capacity decrease due to wireless interference. A wireless mesh router with multiple routers and channels is capable of reducing network interference. Static channel allocation and dynamic channel allocation are types of channel allocation. Adaptive Dynamic Channel Allocation protocol (ADCA) is dynamic channel allocation protocol which decreases the packet delay without degrading the network throughput. The hybrid architecture shows much preferred adaptivity to changing traffic over absolutely static scheme without increasing in overhead and attains to lower delay than existing methodologies for hybrid networks. In addition, we have used an Interference and Congestion Aware Routing protocol (ICAR) in the hybrid network which achieves load balancing in the channel usage. Our simulation results show that compared to previous works, ADCA reduces the packet delay considerably without degrading the network throughput. Current hybrid implementation utilizes multiple static interfaces but only single dynamic interface. In this paper, we have implemented a novel scheme which utilized two dynamic interfaces along with two static interfaces so the performance of existing system has boosted. Our system have attain higher throughput and lessen the packet delay than existing system. We have compared our system performance with existing static and hybrid systems.

World University root node

Engineering and Technology

2015 Twelfth International Conference on Wireless and Optical Communications Networks (WOCN)

Evaluation of metrics in hybrid multichannel multiradio wireless mesh networks for multiple dynamic channel interfaces

Wireless Sensor Networks (WSN) plays vital role in research field. Due to its rapidly increasing application in monitoring various kinds of environment by sensing physical phenomenon. Clustering is an efficient and effective method to enhance performance of the WSNs system. In this project work, we study a secure transmission of data for cluster-based WSNs (CWSNs), where the clusters are formed dynamically and randomly. We propose two Secure and Efficient data Transmission (SET) protocols for CWSNs, called SET-IBS and SET-IBOOS, by using the Identity-Based digital Signature (IBS) scheme and the Identity-BasedOnline/Offline digital Signature (IBOOS) scheme, respectively. The cluster routing protocol LEACH (Low-Energy Adaptive Clustering Hierarchy) is considered and improved. In SET-IBS, security relies on the hardness of the Diffie-Hellman problem in the pairing area. SET-IBOOS additionally decreases the computational operating cost for protocol security, which is critical for WSNs, while its defense depends on the stability of the problem of discrete logarithm. We propose a clustering routing protocol named Enhanced LEACH, which extends LEACH protocol by balancing the energy consumption in the network.The simulation results show that Enhanced LEACH outperforms LEACH in terms of network system lifetime and reduce the energy consumption

International Journal of Innovative Research in Science,Engineering and Technology

Secure and Efficient Data Transmission forCluster Based Wireless Sensor Networks

Heart Attacks are the major cause of death in the world today, particularly in India. The need to predict this is a major necessity for improving the countries healthcare sector. Accurate and precise prediction of the heart disease mainly depends on Electrocardiogram (ECG) data. Heart disease is a major life threatening disease that cause to death and it has a serious long term disability. The time taken to recover from heart disease depends on patient’s severity. Heart disease diagnosis is complex task which requires much experience and knowledge. Nowadays, health care industry contain huge amount of health care data, which contain hidden information. Advanced data mining techniques along with computer generated information are used for appropriate results. Neural Network is widely used tool for predicting heart attack. A Heart Attack Prediction System we are going to develop using Neural Network and Genetic Algorithm. This system calculates the number of hidden nodes for neural network which train the network with proper selection of neural network architecture and uses the global optimization of genetic algorithm for initialization of neural network.

International Journal of Latest Trends in Engineering and Technology

A survey on ECG signal monitoring through sensor and prediction of heart attack with the help of optimized neural network using genetic algorithm

This paper describes a method to diagnose a subject with clinical depression. The approach taken utilizes EEG data from which specific channels are selected to obtain voltage fluctuations from Occipital and Parietal lobes of the brain. Studying these parts of the brain is highly informative about the subjects state of mind when he is awake and help us understand how he processes information, on these basis we can deduce if the subject is depressed or not. These channels are used to extract required alpha wave signals. Then Fast Fourier Transform is applied on the alpha wave and its fundamental frequency and corresponding amplitude of the alpha wave are obtained. The obtained information is used to determine if the test subject is depressed or not using a rule based classifier. The classifier classifies a subject as depressed if the fundamental frequency is below 8 Hz and normal if it is 8 Hz or above.

International Journal of Scientific Engineering and Research (IJSER)

An Advanced Design for Depression Analysisthrough EEG Signal

An evaluation and choice of learning algorithms is a current research area in data mining, artificial intelligence and pattern recognition, etc. Supervised learning is one of the tasks most frequently used in data mining. There are several learning algorithms available in machine learning field and new algorithms are being added in machine learning literature. There is a need for selecting the best suitable learning algorithm for a given data. With the information explosion of different learning algorithms and the changing data scenarios, there is a need of smart learning system. The paper shows one approach where past experiences learned are used to suggest the best suitable learner using 3 meta-features namely simple, statistical and information theoretic features. The system tests 38 UCI benchmark datasets from various domains using nine classifiers from various categories. It is observed that for 29 datasets, i.e., 76 % of datasets, both the predicted and actual accuracies directly match. The proposed approach is found to be correct for algorithm selection of these datasets. New proposed equation of finding classifier accuracy based on meta-features is determined and validated. The study compares various supervised learning algorithms by performing tenfold cross-validation paired t test. The work helps in a critical step in data mining for selecting the suitable data mining algorithm.

Evolving Systems

Evolving learners' behaviour in data mining

Currently in India college ranking is the issue that is discussed a lot. In this paper, a common forum where students can get information about various engineering colleges and their ranking. There are many websites that give information about various engineering colleges but when it comes to students, for them it is important to know certain insights to parameters like faculty, campus life, hostel facility, placement etc. Students from small cities and villages have less exposure to various Colleges which are funded by state and central government for studies, Research and Innovation. If these students will have sufficient exposure then the young talent will be properly channelized as per their interest. In this we have developed a recommender system that understands information seeker need and accordingly generates recommendations for him/her through simple interface, which provides information to the students and advisors to improve the choice of courses. In our methodology we have opted for hybrid approach which combines advantages of Collaborative filtering algorithm and Content based filtering algorithm to improve our recommendations. The system consists of an interactive User Profiling [9] process in order to construct profile of the User. As the sample datasets that are used for experiments are large and also contain more number of feature sets, it is essential to understand dataset beforehand. Recommending items based on the users interest requires processing of these large datasets, thus if this information is properly profiled then the task of recommending would get a lot easier. Also when results are shown to the user, big challenge is how well data can be ranked so that user satisfaction is guaranteed. © 2017 IEEE.

Proceeding - IEEE International Conference on Computing, Communication and Automation, ICCCA 2017

A user-friendly college recommending system using user-profiling and matrix factorization technique

Public Distribution System is a government-sponsored chain of shops entrusted with the work of distributing basic food and non-food commodities to the needy sections of the society at very cheap prices. It is also an important constituent of the strategy for poverty eradication and is intended to serve as a safety net for the poor people whose number is more than 33 Crores and are nutritionally at risk. The current Public Distribution System has several well documented problems such as lack of transparency, accountability, poor governance and poor service delivery mechanisms. A large number of poor and needy members of society are left out and a lot of bogus cards are also issued. This leads to increase in corruption. Our project proposes the improvised technique of implementing smart ration card system. It also depicts the automated version of the Public Distribution System. At the time of implementation, for identification purpose we are giving unique QR-code to each customer. This will help to keep track of their respective accounts. Customers will also receive SMS notification of their successful registration and stock allotted to them. Thus our system will help to create transparency in transactions and will also help to manage accountability. © 2017 IEEE.

A proposed architecture for automating public distribution system

Facial analysis in videos and images has been a relatively tough task for machine learning models. Recent use of deep learning approaches has demonstrated substantial improvement in results and reliability and can be used for problems such as face recognition, emotion recognition and emotion reaction prediction. In the case of emotion reaction, relevant information of emotions in individual frames often must be aggregated over a variable length sequence of frames and speech signal to produce an appreciable prediction. Emotion reaction prediction is a subset of sequence analysis task and heavily relies on dynamic temporal and spectral features. Convolution neural networks (CNNs) have been extensively used for emotion recognition problems and have produced reliable results. However, they lack the ability to extract time-series information from a sequence of inputs and cannot model an emotion transaction. Recurrent neural networks (RNNs) are being used profoundly due to their ability to yield impressive results on a variety of tasks in the field of sequence analysis. In this work, we propose a system for emotion recognition and reaction prediction in videos. The primary focus is experimental analysis of a hybrid CNN-RNN architecture for emotion transaction analysis that can recognize the emotion in a frame in a video and predict its appropriate reaction. © 2017 IEEE.

School of Mechanical Engineering

Proceedings - 2017 3rd IEEE International Conference on Research in Computational Intelligence and Communication Networks, ICRCICN 2017

Emotion recognition and reaction prediction in videos

Music directly connects to soul and induces emotions in mind and brain. Hindustani Art music (HAM) has nine different aesthetic delights and in turn various moods and emotions associated with it. It is also associated with seasons and time of day. HAM has many applications in music therapy and meditation. So, an exclusive Recommender system for HAM will help listeners to change their mood and rejuvenate their psychological and physiological health conditions. A framework for recommendation of HAM by extracting various attributes, features and properties of music and using a hybrid filtering approach for recommendation is presented. The traditional Nava-Rasa model is suitable for HAM with which we can track the emotions associated with this music.

Proceedings - 2nd International Conference on Computing, Communication, Control and Automation, ICCUBEA 2016

An efficient framework for recommendation of hindustani art music

We present staff notation recognition using deep learning technique. To satisfy the purpose, the application requires a user to provide input image of the staff notations. As the staff notations are predominantly black in color, algorithms like desaturation and decomposition can be used to convert colored images into gray scale equivalent (Image Processing). The converted images will undergo the processing of Convolutional Neural Network algorithms which will equip multilayer approach to perform convolution and pooling. The task achievement involves feature extraction to generate an output classification in the form of text. © 2016 IEEE.