Manuscripts

Recent Papers

Thesis

Deep learning technique to reduce the volume of missing data

The challenges are learning from data with missing values and finding shared representations for multimodal data to improve inference and prediction. The proposed method uses deep learning technique to reduce the volume of missing data which occur due to low battery and transmission loss. In order to find missing data imputation and new modality prediction, the original incomplete raw data is trained and tested using the stacked autoencoder to predict the corresponding missing value. Deep Multimodal Encoding methods use intra and intermodal learning to compute a new modality prediction. Deep Multimodal Encoding (DME) can achieve a Root Mean Square Error (RMSE) of the missing data imputation which is only 20% of the traditional methods. The performance of Deep Multimodal Encoding is robust to the existence of missing data.

Published by: V. Arivu Pandeeswaran, Dr. P. Kumar, R. Sivakumar

Author: V. Arivu Pandeeswaran

Paper ID: V4I2-1878

Paper Status: published

Published: April 13, 2018

Full Details
Research Paper

Alcohol sensing based engine locking system

In today’s era where we are blessed with fast-moving automobiles which makes our movement easy as well as fast, it also poses a grave danger of accidents and one of the main causes of such fatal accidents is the case of drunken driving where the person loses his control over the automobile and can become a danger to himself and the surroundings. Controlling such cases manually is practically very difficult. And thus we came up with an idea of controlling such accidents, we in this project have used the idea of gaseous material sensing for sensing the fumes of alcohol in the breath of the person who is driving. As we know that stopping a person from drinking in today’s world is near to impossible so why not stop them from driving after drinking !!!. Our project here will be installed on the steering wheel of the car where the breath of the person driving comes, it will sense the amount of alcohol consumed by him in mg/liter and if the level exceeds then the engine will be stopped and thus decreasing the chance of an accident. This prototype of our can be further modified into a smaller size and with more efficient sensing.

Published by: I Rahul Rao, Saurabh Sinha

Author: I Rahul Rao

Paper ID: V4I2-1800

Paper Status: published

Published: April 13, 2018

Full Details
Research Paper

Predictive analysis of product search

The rapid increase in internet users along with growing power of online review sites and social media has given birth to Sentiment analysis or Opinion mining, which aims at determining what other people think and comment. Nowadays, several websites are available on which a variety of products are advertised and sold. Prior to making a purchase an online shopper typically browses through several similar products of different brands before reaching a final decision. This seemingly simple information retrieval task actually involves a lot of feature-wise comparisons and decision making, especially since all manufacturers advertise similar features and competitive prices for most products. The proposed system presents a semi-supervised approach for mining online user reviews to generate comparative feature-based statistical summaries that can guide a user in making an online purchase. In this system sentiment analysis of product reviews gives us not only positive and negative reviews but also gives neutral and constructive opinion where the system can suggest some improvement about the product also the result is represented in the graphical and tabular method. Our task is performed in three steps: (1) mining product features that have been commented on by customers; (2) identifying opinion sentences in each review and deciding whether each opinion sentence is positive or negative; (3) summarizing the results. This paper proposes several novel techniques to perform these tasks. Our experimental results using reviews of a number of products sold online to demonstrate the effectiveness of the techniques.

Published by: Rajendra Lasde, Gopika Tambare, Mayuri Tanpure, Pragati Naktode, Nilima Pardhake

Author: Rajendra Lasde

Paper ID: V4I2-1744

Paper Status: published

Published: April 12, 2018

Full Details
Research Paper

Determination and effective parameters for drying of Millets

One of the oldest methods used for preservation of fruits, vegetables, millets and other food products to increase their shelf life is drying. Cereals have a significant share in millet production both in the world and china. It acts a source of raw material for many food products. The important parameters of drying includes temperature, velocity and relative humidity. Drying and drying rate curves should be plotted to determine the drying kinetics of the products. Experiments are conducted in a tray dryer using different kinds of millets ( foxtail millet ,little millet, kodo millet )  for various drying temperatures ( 30- 60˚C)  and with different time intervals .The temperature and time are measured and recorded for every 15 minutes. The measured data is used to obtain drying and drying rate curves. The curves indicate that drying process takes place in the falling rate period   If drying is continued, the slope of the curve, the drying rate, becomes less steep (falling rate period) and gradually tends to nearly horizontal at very long times. The product moisture content will become constant at the "equilibrium moisture content", from the data collected during falling rate period and is calculated. Time and temperature are used as a parameters for the dried millet quality.  It is essential to follow up drying course and to decide whether it is obtained or not by drying processing method. Too long drying course may have bad effects for quality and food safety because of high fermentations and mould growth.  Also, drying to a too low moisture content can result in income losses.  

Published by: Venkata Naga Kaumudi Prabha Annavarapu

Author: Venkata Naga Kaumudi Prabha Annavarapu

Paper ID: V4I2-1782

Paper Status: published

Published: April 12, 2018

Full Details
Research Paper

Reducing headlight intensity to improve street visibility

Driving at night is dangerous. High headlight glares can make a driver temporarily blind thereby escalating the chances of fatal accidents. Many factors are considered when analyzing automobile transportation in order to increase safety. One of the most prominent factors for night-time travel is temporary blindness due to elevated headlight intensity. This is particularly prominent on single lane roads. Also, higher speed due to decreased traffic levels at night increases the severity of accidents. Proposed software module masks the high-intensity headlights, preventing temporary blindness that a driver may face and hence improves the view.

Published by: Amey Sathe, Prajakta Roshankhede, Priti Golar, Chetan Chitatwar

Author: Amey Sathe

Paper ID: V4I2-1789

Paper Status: published

Published: April 12, 2018

Full Details
Research Paper

An alternate method for generation and usage of P300 EEG signal using image processing

This paper presents a model for Developing a sustainable system for prolonged usage of Brain-computer interface for navigation and communication for the disabled, and the paralyzed with use of Electroencephalography (EEG) This model uses image recognition and classification of the video input from the camera for use in the P300 wave recognition.This model uses images instead of alphabets in oddball paradigm reducing the cognitive load on the brain and uses a different solution for the mental fatigue generated from the usage of the same visual stimulus over a long period of time

Published by: A. Vishnu Sai, N. Sathvik, A. Lakshmi Srinivas Jaidev, P. Ramani, N. Rupesh

Author: A. Vishnu Sai

Paper ID: V4I2-1808

Paper Status: published

Published: April 12, 2018

Full Details
Request a Call
If someone in your research area is available then we will connect you both or our counsellor will get in touch with you.

    [honeypot honeypot-378]

    X
    Journal's Support Form
    For any query, please fill up the short form below. Try to explain your query in detail so that our counsellor can guide you. All fields are mandatory.

      X
       Enquiry Form
      Contact Board Member

        Member Name

        [honeypot honeypot-527]

        X
        Contact Editorial Board

          X

            [honeypot honeypot-310]

            X