Manuscripts

Recent Papers

Research Paper

Impact of social media on societal perception of youngsters: Empirical evidence from graduates in Bangalore City

Today, young people in India use internet and social network more than any middle-aged person. Now days, students are easily getting diverted from the studies because of social networking sites like Orkut, Twitter, Facebook, etc. more time is spending in these kinds of social sites by the youth. Though there is a risk of losing privacy and safety, the youngsters give more importance to such sites as they give chance for getting in contact with classmates, friends and people with common likes and dislikes. Social media has been an important factor in the lives of the people all over the world and providing people a much easy needed connect from shopping to electronic mails, education and business tool. The Social networking sites are giving a window of opportunity for people to connect with parents, relatives and friends who are at a distance or beyond geographical boundaries and reconnect with their old friends, colleagues and mates. It also helps people to make new friends, share content, pictures, audios, videos amongst them. The sample size of the study is 100. A questionnaire is designed to find out the various factors of social media that have impact on youngster’s perception of society. The current research also analyses the advantages and disadvantages of social media and the role of parents and teachers in prevention of misuse of social media.

Published by: Dr. Jaya Patil, Dr. Lakshmi P.

Author: Dr. Jaya Patil

Paper ID: V7I4-1162

Paper Status: published

Published: July 2, 2021

Full Details
Research Paper

Analysis of Dropout in ANN using MNIST Dataset

The concept of Neural Networks is propelled by the neurons within the human brain and researchers needed a machine to imitate the same process. A Neural Network (NN) is a circuit of connected neurons, or in a present-day sense, an artificial neural network, composed of artificial neurons constructed for solving artificial intelligence problems. In the deep neural network, Overfitting is a severe issue. This issue could be caused by unbalanced datasets and incorrect model parameter initialization, which causes the model to adhere too closely to the training data and reduces the model's generalization performance for unknown data. To overcome such problems, Regularization techniques are used. This technique modifies the learning algorithm in a way that increases the model's generalization and performance. Dropout is one such regularization technique for addressing the overfitting problem. During the training, it randomly drops the hidden units or neurons to prevent the units or neurons from co-adaption. This method significantly reduces the overfitting and improves the performance of the neural network model. Dropout is preferred for large neural networks in order to have more randomness.

Published by: Swathi N., Shreeraksha, Shruti A. P., Sparsha S. G., Farhana Kausar

Author: Swathi N.

Paper ID: V7I4-1145

Paper Status: published

Published: July 2, 2021

Full Details
Research Paper

Handwritten Digit Recognition using Deep Learning

Deep learning is powerful technique in current generation. This Paper presents the results of handwritten digit recognition on well-known image database using Convolution neural network. Deep learning increases accuracy and reduces computation time as was caused by simple artificial neural network. The applications of digit recognition includes in postal mail sorting, bank check processing, form data entry, etc. The heart of problem lies within the ability to develop an efficient algorithm that can recognize hand written digits and which is submitted by users by the way of a scanner, tablet, and other digital devices. The main objective of this paper is to ensure effective and reliable approaches for recognition of handwritten digits.

Published by: Sanjeeva Kumar, Seenakula Ravi Shankar, Shashank M. V., Vandana K. C., Farhana Kausar

Author: Sanjeeva Kumar

Paper ID: V7I4-1140

Paper Status: published

Published: July 2, 2021

Full Details
Research Paper

Reimagining the city’s identity by strengthening the inner core – A research enquiry for design intervention

A city is its’ past legacy and its present identity. While each city must strive to keep marching forward and upgrade to suit the latest demands of its’ residents, it is important to strike a balance between the past and the present. Flowing towards future ambitions as an urban setting doesn’t necessarily imply a disconnect from its past legacy. The legacy lends the city's identity and gives the citizens a sense of familiarity. Therefore, modern urban planning must not only work towards embracing transition and change of modernity but also strike a balanced relationship between the urban and natural environment. This all-inclusive approach is the soul and crux of cultural heritage management as well. As modernization, commercialization, and urbanization continue to threaten a multitude of historical precincts and buildings, recording and celebrating their existence, acknowledging their contribution to national identity, preserving their associations with the city’s identity today, and protecting them from extinction becomes chiefly important, the corresponding benefit of which is promoting tourism as well. The heritage precincts of Aurangabad city encompass areas surrounding the multitude of the city’s gates of historical significance.

Published by: Kapil Gujarathi, Kuldeep Bhatia, Tushar Paithankar

Author: Kapil Gujarathi

Paper ID: V7I4-1153

Paper Status: published

Published: July 2, 2021

Full Details
Research Paper

Driver Fatigue Detection using Deep Learning

Fatigued driving is becoming a dangerous and widespread occurrence for drivers, and it is a key contributor to deadly car accidents. To detect tiredness in drivers, machine learning researchers used a variety of sources of data. The morphological features of both the eye and mouth regions were combined in this work, which looked at the fatigue detection problem in terms of feature quantities, classifiers, and modelling parameters. This particular YOLO model is trained to detect two classes. They are “eyes_open” and “eyes_closed”. As soon as the model detects that a person is closing his/her eyes it rings an alarm to alert the driver and passengers.

Published by: Sujay S., Aditya Ashok Illur, Poornima Kulkarni, Rekha B. S.

Author: Sujay S.

Paper ID: V7I4-1151

Paper Status: published

Published: July 2, 2021

Full Details
Research Paper

Automatic number plate recognition using contours and Convolution Neural Networks

Image processing technology is used in Automatic Number Plate Recognition (ANPR). Automatic Number Plate Recognition (ANPR) is useful for identifying stolen vehicles, smart parking systems, and the use of automobiles in unlawful operations. Character recognition is the first step of ANPR, followed by character segmentation and localization. The technique uses contours and morphological processes to locate the number plate initially. We execute character segmentation after localization. Convolution neural networks (CNN) are used by a segmented character to recognize things because they are known to be good at it. The trained CNN model has an 85.31% accuracy rate.

Published by: Adithya M., Sumitha B. S., Rahul K., Nitish Kumar P., Pramod G. N.

Author: Adithya M.

Paper ID: V7I4-1139

Paper Status: published

Published: July 2, 2021

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