Manuscripts

Recent Papers

Research Paper

Research and thinking of smart residential building technology

Smart Residential Building is emerging technology growing continuously now. It integrates of the many new technologies through building networking for rising human’s quality of living, therefore there have several comes researching in various technologies to use to the good home system . Accordingly, this paper reviews various topics on smart building/home technologies from surveying for smart residential building /home research project. This research paper also deals with the history and the concept of smart residential buildings. Smart buildings or at least discussion of the concept originated in the early 1980s.

Published by: Nishant Kumar Singh

Author: Nishant Kumar Singh

Paper ID: V6I3-1174

Paper Status: published

Published: May 10, 2020

Full Details
Research Paper

Evaluation of bucking characteristics of thin cylindrical shells with cutouts for aerospace applications

The aerospace industry finds a wide application of thin cylindrical shells. Cutouts in various structures are also an important application particularly in aircraft and aerospace industry which is a significant area of research today. The load-carrying capacity of these structures is determined by the buckling characteristics of that specimen mainly in aircraft since the primary cause of failure is elastic buckling. Even though cut-outs in these structures decrease the buckling strength due to the stress concentrations, it cannot be avoided in many engineering applications particularly in aircraft components. Cylindrical shells made of mild steel are considered for the study. In this paper the buckling behavior of the shells made without cutouts, with cutouts, and with semi cutouts of constant diameter are studied.

Published by: Raj Pranav, Ashok Kanna, Akshay Kumar, Ajith Raj R.

Author: Raj Pranav

Paper ID: V6I3-1168

Paper Status: published

Published: May 10, 2020

Full Details
Others

Android application based vehicle driver drowsiness detection system through Image Processing

Conduct the simulation experiment and analyze the data to search for an automatic detection system based on driver performance, human conduct, and emotions. A design of drowsiness detection systems is the goal of this venture. A driver with a Drowsy or sleepy mode can not tell when an uncontrolled sleep will take place. Injury crashes in fall asleep are very grave. Accompanying fatigue or drowsiness- related crashes[1] can result in 1.200 deaths and 77.000 injuries per year in recent statistics. Driver fatigue is responsible for more than 25 percent of road accidents[2]. Through alert the driver about his / her drowsiness, we will can the risk of an accident. The main concept of this system is the simulation of somnolence detection with image processing and the detection of somnolence. Furthermore, the person authorized to locate the vehicle can be notified by GPS. This system helps avoid most injuries, thereby protecting human lives and increasing personal suffering. With this system, the car driver's eyes are monitored by camera, and we detect driver drowsiness symptoms early enough to avoid accidents by developing an algorithm. Within a specified time interval the car driver's eyes are closed by more than80 percent. This project will help in advance in detecting driver fatigue and give alarming signals in the form of a sound and an LED blinking. The alarm is manually not immediately deactivated. A deactivation key is used to trigger the alert for this reason. The machine assumes that the operator sleeps and sends a warning message.

Published by: N. Suresh, Gayam Akil, M. Gnana Adithya, B. Vijaya Krishna

Author: N. Suresh

Paper ID: V6I3-1158

Paper Status: published

Published: May 10, 2020

Full Details
Review Paper

Speech recognition system using Deep Neural Network

Speech recognition is the property of a system to identify the words spoken by the user in a scripted language and convert the data to a readable and writable format. The work carried out was able to convert the speech to text. Using the speech as instructions to perform many web-based services, system bound tasks. Deep learning with deep neural networks coded in python is implemented in this paper which makes the system more reliable, robust against noise, and with an accuracy of 70%.

Published by: Dhanush N. D., Jagruth S., Rohini Hallikar

Author: Dhanush N. D.

Paper ID: V6I3-1151

Paper Status: published

Published: May 10, 2020

Full Details
Research Paper

Bi-clustering and classification-based detection for DDoS attacks

There are several Machine Learning (ML) techniques that have been adopted for detecting DDoS attacks, But the attacks still became a major threat. The various existing systems worked on supervised and unsupervised ML-based approaches. Various supervised ML approaches consider both labeled and unlabeled network traffic datasets to detect DDoS attacks. Whereas, unsupervised ML approaches depends on incoming network traffic data to the attacks. Both approaches analyses using large amount of network traffic data with very low accuracy and high false-positive rates. In this presented paper, we propose semi-supervised Machine Learning approach for DDoS detection based on various algorithms orderly, Entropy estimation, Bi-clustering approach, and Random Trees decision making algorithm. The unsupervised part allows removing the irrelevant traffic data for DDoS detection which allows decreasing false-positive rates and increases efficiency. Whereas, the supervised part allows us to reduce the false-positive rates from the unsupervised part and to accurately classify the DDoS traffic data. Various experiments were conducted to evaluate the proposed approach using public NSL-KDD dataset. An accuracy of 98.66% is achieved for respectively NSL-KDD dataset, with respect to the false-positive rate of 0.31%.

Published by: Santoshi Sahu, Mamidi Sushma Venkata Anisha, Rayudu Venusri Teja, Sai Smruti Rout

Author: Santoshi Sahu

Paper ID: V6I3-1170

Paper Status: published

Published: May 7, 2020

Full Details
Research Paper

Vision-based human activity recognition using CNN

Human Activity Recognition (HAR) is a commonly discussed topic in computer vision. HAR implementations include representations such as health care and contact between the human and computer systems. When the imaging technology progresses and the camera system improves, there is a relentless proliferation of innovative approaches for HAR. Human activity recognition is an important component of many creative and human-behavior driven programs. The ability to recognize various human activities enables the development of an intelligent control system. Usually, the task of the Identification of Human activities is mapped to the classification task of images representing a person’s actions. This Project used for human activities’ classification using machine learning methods such as CNN. This Project provides the results to Identification of Human activities task using the set of images representing five different categories of daily life activities. The usage of images also webcam to find out the live activities of the users that could improve the classification results of Identification of Human activities is beyond the scope of this research.

Published by: M. Sohan Raj Kumar, Dr. Syed Abudhagir Umar, M. Phillips Robert, J. Nagendra Vara Prasad, CH. Prasad, Talluri Sairam

Author: M. Sohan Raj Kumar

Paper ID: V6I3-1166

Paper Status: published

Published: May 7, 2020

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