Research and Development

Department of Electronics and Communication Engineering


KSCST Funding Sanctioned Projects for 2017-18

Sl No.

Project proposal Ref. No.








Implementation of Smart Gadget for Women Safety by using Raspberry Pi



Mrs. Swati Sarkar

Ms.GunaSree G




Design and Implementation of Asset Management Using Deep Learning



Mrs. Pratibha S N

Mr. Pradeep C


KSCST Project – 2017-18

Project Title: Implementation of Smart Gadget for Women Safety by using Raspberry Pi

Project Proposal Ref. No:  41S_BE_2180

Research topic by: Mrs. Swati Sarkar

Students: Ms.GunaSree G,Ms.Medamanuri Preethi,Mr.Dharmavarapu Bharath,Mrs.Jayashree G

Funding Agency: Karnataka State Council for Science and Technology (KSCST)

Fund Amount: Rs.5000/-

Project Duration: 6 Months (Jan 2018 to June 2018)


In today’s world, women safety has become a major issue as they can’t step out of their house at any given time due to some type of abuse and fear of violence. Even in the 21st century where the technology is rapidly growing and new gadgets were developed but still women and girls are facing problems. In such cases they feel handicap and need help to protect them. People are finding up in different techniques to defend. Hence there must be a system which can help them in such difficult situation.

This model consists of protective device that can be fitted to women’s wrist, belt. So that  it can use without making much effort in carrying and using it. This project involves the development of a Smart Gadget to overcome the problems faced by the women in the society. The project focuses on a security system that is designed using GSM, GPS and Raspberry Pi  board which can be managed to take with us at anywhere. This security system provides the applications like Location tracking of user, send location to emergency contacts and capturing images  and Screaming alarm is activated when the panic switch is pressed to serve the purpose of providing security and safety to women.

KSCST Project -2017-18

Project Title: Design and Implementation of Asset Management Using Deep Learning

Project Proposal Ref. No: 41S_BE_2162

 Research topic by: Mrs. Pratibha S N

 Students: Mr. Pradeep C, Mr. Rajitha G N, Mr. Vasuki B K, Mr. Venkatesh J

 Funding Agency: Karnataka State Council for Science and Technology (KSCST)

 Fund Amount: Rs.5000/-

 Project Duration: 6 Months (Jan 2018 to June 2018)


From the biological science point of view, computer vision aims to come up with computational models of the human visual system. From the engineering point of view, computer vision aims to build autonomous systems which could perform some of the tasks which the human visual system can perform (and even surpass it in many cases). The two goals are of course intimately related. Deep learning is growing rapidly and is surpassing traditional approaches for machine learning since 2012 by a factor of approximately 10%–20% in accuracy. This gives an introduction to Deep Learning and its application in Computer Vision.

For computer vision tasks, special architecture of Deep Learning is used and that is called a Convolutional Neural Network. Firstly we look into the basic components of a Convolutional network.

Deep learning (DL) is a subset of Machine learning (ML) in Artificial Intelligence (AI) that has networks which are capable of learning unsupervised from data that is unstructured or unlabeled which is also known as Deep Neural Learning or Deep Neural Network. Hence Deep Learning is more accurate compared to Machine Learning.

Major Research Areas:

KSCST Project -2015

Project Title: Design and Implementation of a Programmable Smart Glove for Gesture Recognition Application

Project Proposal Ref. No: 39S_BE_1831

Research topic by: Mr. Ravikiran B.A

Students: Ms. Rowena Maria Saldanha, Ms. Sangeetha U, Ms. Sneha R, Mr. Vasudev K Tonape

Funding Agency: Karnataka State Council for Science and Technology (KSCST)

Fund Amount: Rs.5000/-

Project Duration: 6 Months (Jan 2015 to June 2015)


Sign language is the most widely used mode of communication by the speech and hearing impaired. There are very few people in the world who understands sign language thoroughly. It is difficult for a common man to interpret this sign language. There is a demand for technology involving recognition of gestures. The existing technology for gesture recognition used image processing, which required proper illumination, making it less accurate. The existing Smart Glove had a separate accelerometer and gyroscope, which made the entire system bulky and costly. Also, previously the system was wired, making it difficult for it to be portable.

This project involves the development of a Smart Glove to overcome the difficulties in communication faced by the speech and hearing impaired in the society. The Smart Glove Controller senses hand movement and is programmed to recognize a set of predefined gestures, for use in sign language to speech translation applications. It involves the combined usage of smart glove and PC. The Smart Glove consists of flex sensors, accelerometer and a microcontroller. The transmission is wireless, which is achieved by the use of Bluetooth module. This project includes implementation of the Machine Learning algorithm for recognition of the gestures made by the Smart Glove and displaying it in the form of textual and voice output.

A system has been developed, using which the speech and hearing impaired can communicate in the society with ease. This Smart Glove is designed to recognize static gestures. It is portable, wireless and cost effective. The algorithm used here does not require human intervention, and the system has higher accuracy compared to the existing systems because it uses machine learning algorithm. The existing smart glove can be used in various fields, for instance, as an alternative for the mouse, to control musical processors, robot locomotion, tactile feedback systems, etc.

KSCST Project -2014

Project Title: Arduino Based Quad copter with Obstacle Avoidance Feature

Research topic by : Mr. Ravikiran B.A and Dr. Karthik P

Students: Mr. S. R. Aashik, Mr. Mahesh P, Mr.Thilak A.G and Mr. Venkatesh R

Funding Agency: Karnataka State Council for Science and Technology (KSCST)

Fund Amount: Rs.4500/-

Project Duration: 6 Months (Jan 2014 to June 2014)


An unmanned aerial vehicle also known as UAV is an unpiloted aircraft which can either be remotely operated or flown autonomously based on pre-programmed flight plans. Usually these types of vehicles are used in military applications for missions that are too dangerous for manned aircraft. They are also used in a growing number of civil applications such as aerial photography and the transport of various goods. Rotating wing (or helicopter) UAVs have the advantage above fixed wing UAVs in many ways; they are able to take off and land vertically, making it possible to hover at a fixed point. The design discussed in this report is based on the development of UAV quad rotor helicopter (Quad Copter), hardware, control system and flight dynamics. The copter is built of electric motor driven rotors, aluminum, an embedded on-board computer, power distribution system and various sensor units. The hardware platform utilized for the on board computer was a ATmega2560 microcontroller, with 54 Digital I/O pins, 256KB of Flash memory, 8KB of SRAM and 4KB of EEPROM with programming done predominately in C++ to express the control commands and overall system.

Research topic by Dr. Karthik P Project Title: “Design and Implementation of Novel Sensor for detection and direction finding of sound under water”Funding Agency: Naval Research Board (NRB)

Fund Amount: Rs.24, 89,200/-

Principal Investigator: Dr. Karthik P

Project Duration: 2 Years (Jan 2013 to Jan 2015)

An optical fiber that is exposed to pressure variations undergoes deformations and changes in refractive index. Such pressure variations impose phase modulation on a coherent light beam passing through the fiber. Fiber optic hydrophones have been proposed as a means to achieve high sensitivity and low noise.

Fiber optic sensor system, the sensor and reference fibers are shaped in loops circularly and uniformly (mandrel), heat treated or bonded together and embedded in a spiral pattern with a low bulk modulus and Young’s modulus in an appropriate elastomer (polyurethane). The acoustic sensitivity of the sensor has been found to be high in frequency (0.2-2.5 KHz) and static pressure independently.

Designing of mandrel has been done and we have tested the sensitivity performance with various parameters like Young’s modulus, Poisson’s ratio, ID (Inner Diameter), OD (Outer Diameter). The foaming layer is the main material, and if we introduce major changes in any behavioral property, we have done that in the foaming layer only. Then, we have changed some physical property of other materials like aluminum fiber, nylon etc, and by changing all these values depending on the sensitivity, we have obtained one appropriate model and with sensitivity around -62db, which is much better than the reference paper sensitivity value of -82dB.

This result we can achieve by varying the physical and behavioral properties of the below diagram.

Share This