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

In in-network data aggregation in Wireless Sensor Networks (WSN), selection of communication paths and aggregation points are critical network requirements. They enable efficient use of network resources in constrained environments. Base Station (BS) driven routing protocols are prime enablers to implement such network requirements. In Base Station (BS) driven routing protocols the BS proactively finds a path to communicate with each node in the network. However, if a node in the network fails or goes to sleep; the communication path between the BS and some nodes in the network is disabled and these nodes are disconnected from the BS. In this paper, an algorithm to reestablish a communication path between these disconnected nodes and the BS, is proposed. The reestablishment of paths add fault-tolerance; and facilitate retention of connectivity of the nodes in the network to enable communication with the BS. The results demonstrate the merit of the proposed algorithm.

Engineering and Technology

World University root node

Proceedings of the 2017 International Conference on Wireless Communications, Signal Processing and Networking, WiSPNET 2017

Path reestablishment in Wireless Sensor Networks

Human computer interaction is need of the time and has wide application range. Automatic emotion recognition is one of the important tasks which can be implemented through HCI systems. Facial expressions based non-verbal approach of emotion recognition is experimented for the work. Extracted features are fusion of features obtained through LDN and PCA. Extracted features are provided to feed forward neural network for emotion classification. The experimentation is carried out for CK+ and JAFFE database. The emotion recognition accuracy obtained for CK+ database is 82.07% and for JAFFE database is 84.22%. FAR - false acceptance rate and FRR - false rejection rate obtained for CK+ database is 4.18% and 17.92% respectively. FAR and FRR obtained for JAFFE database is 3.60% and 15.77% respectively.

Proceedings of 2018 the 8th International Workshop on Computer Science and Engineering, WCSE 2018

Facial expressions based emotion recognition through feature fusion approach

The main challenge of wireless sensor network is its lifetime. In this type of network, single static sink node is present and a sensor device node requires more energy for estimating information packet specifically those that are available in the area of the sink node. Such nodes separate the energy so fast due to the numerous tone traffic patterns and at the end they die. This uneven event is named as hotspot issue which gets more real as the numbers of sensor nodes increase. Generally, replacement of such energy sources is not a feasible and cost-effective solution. For this problem, there is one solution regarding to distance. If the distance among sensor and sink node is minimized, the energy consumption will be effectively reduced. This paper presents the solution for enhancing network lifetime with energy saving of sensor nodes. Here, we also discuss on the limitations and advantages of previous methods. The sensors nodes consume more battery power which is at minimum distance from sink node. Therefore, energy of sensor nodes in network will quickly consume their energy. So that, the lifetime of a sensor nodes will be produced. To overcome this drawback of this system, we propose alternate shortest path technique. To enhance the efficiency of energy along with network lifespan, this approach is used. Furthermore, we developed a novel technique known as Energy Aware Sink Relocation (EASR) for remote base station in WSN if the energy of alternate path is going to die. This system exploits information recognized with the remaining energy of sensor nodes battery for increasing the range of transmission of sensor node and relocation technique for the sink node in network. Some calculated numerical and theoretical calculations are given to demonstrate that the EASR strategy is used to increase the network energy of the remote system essentially. Our system proposes secure data sending using ECC algorithm and increases more network lifetime.

Advances in Intelligent Systems and Computing

Routing with secure alternate path selection for limiting the sink relocation and enhanced network lifetime

International Journal of Computer Science and Information Technologies

Sarcasm Detection in Amazon Product Reviews

2018 4th International Conference for Convergence in Technology (I2CT) SDMIT {\ldots}

Classification of Sheet Music using Optical Music Recognition

In this paper design and simulation of Ku band 105W highly efficient GaN HEMT power amplifier is presented. A single stage design using 20 mm bare die packaged GaN HEMT device is discussed. Inductor based equivalent bondwire array model is used for this design. Simulated performance of power amplifier (PA) shows 105W output power with drain efficiency of 70% and power added efficiency (PAE) of 59% at design frequency of 11.09 GHz. Less than 0.5 dB variation in large signal gain is observed between 10.02-11.17 GHz band of frequency. Proposed GaN HEMT power amplifier can be used to repalce conventional travelling wave tube amplifiers (TWTAs) used in Ku-band satellite communication. © 2018 Association for Computing Machinery.

ACM International Conference Proceeding Series

105W highly efficient ku band GaN HEMT power amplifier

Gait analysis that is used to measure human activity level, is an important aspect for the health professionals. It helps in understanding the limitations caused in the locomotion due to some orthopedic conditions or some neurological disorders. Health analysis though of key importance is yet, limited to the routine pathological monitoring and dietitian consultation. A possible Extension of it could be pre-habilitation (Pre-hab) process for wellness. Pre-hab process helps to prepare your body for high level of activities, reduces the possible risk of injury and ensures quick recovery. The work proposed in the paper emphasize on aspect of Recognition of Gait Pattern for pre-hab through the body worn sensors comprising of accelerometer, gyroscope &amp; electromyography. Continuous remote monitoring is done using sensor connectivity to internet of things (IoT). The analysis of normal or abnormal gait is done using the Data Analytics Module. © 2018 Association for Computing Machinery.

Pre-habilitation and wellness through gait analysis using body worn sensors

There is a large number of credit card payments take place that is targeted by fraudulent activities. Companies which are responsible for the processing of electronic transactions need to efficiently detect the fraudulent activity to maintain customers’ trust and the continuity of their own business. In this paper, the developed algorithm detects credit card fraud. Prediction of any algorithm is based on certain attribute like customer’s buying behavior, a network of merchants that customer usually deals with, the location of the transaction, amount of transaction, etc. But these attribute changes over time. So, the algorithmic model needs to be updated periodically to reduce this kind of errors. Proposed System provides two solutions for handling concept drift. One is an Active solution and another one is Passive. Active solution refers to triggering mechanisms by explicitly detecting a change in statistics. Passive solution suggests updating the model continuously in order to consider newly added records. The proposed and developed system filters 80% fraudulent transactions and acts as a support system for the society at a large. © 2018, Springer Nature Singapore Pte Ltd.

Implementation of credit card fraud detection system with concept drifts adaptation

AVAYA Interaction Center is developed for communication between customer and the company. The Interaction Center provides business-class control of contact center communications across several channels like voice, email, web chat. Chat is a progressively popular communication channel due to growth in the era of Internet. Existing chat generator tool supports only IE browser. So, there is a need that the tool should be browser independent. The paper proposes the tool based on REST API. In the proposed system, the REST API of Chat media of CSPortal is captured through SOAPUI tool. The request–response of REST API is captured for different resources like/csportal/cometd/of CSPortal Chat Media. The result shows the proposed approach is more efficient than existing tool and chat is live for more than 2 min. © 2018, Springer Nature Singapore Pte Ltd.

Implementation of REST API automation for interaction center

Among the numerous factors that are responsible for increasing road accidents, the second most common cause is drowsiness. In an attempt to reduce the rate of accidents, we propose a system which would efficiently handle the timely detection of drowsiness and would accordingly curb the speed of the vehicle being driven. As a proof of concept of the proposed method, we have trained the SVM classifier on the EEG (electroencephalogram) waves derived from “Analysis of a sleep-dependent neuronal feedback loop: the slow-wave micro continuity of the EEG” by Kemp et al. [1, 2]. The data is obtained from a wireless EEG headset. The classification results will determine whether the EEG data corresponds to drowsiness or alertness. This level of drowsiness is then used to determine the maximum speed limit. As the work in [3] has stated, there is a strong correlation between the number of accidents and the speed limit. Hence altogether, the proposed system integrates EEG waves for sleep level detection, and speed lock as a preventive measure to reduce the number of plausible accidents. © 2019, Springer Nature Switzerland AG.