Manuscripts

Recent Papers

Research Paper

Design guidelines for an effective workspace during the pandemic

The coronavirus (COVID‐19) pandemic has made employees nervous about returning to office spaces, as working situations in offices incorporates multiple shared surfaces, minimal scope for maintaining social distancing thereby increasing the risk of virus transmission. During the pandemic, both the government and the private sector witnessed significant modifications in their working methods. Although many adopted remote working, certain sectors such as banks, courts and health-care administrative offices have probably experienced more changes as most of them were open and operational throughout the pandemic. Considering the current pandemic situation and with all the Government and health mandates that has come into effect in an office workspace, new guidelines and design interventions needs to be identified to secure employee’s health and well-being within a shared workspace. This study is aimed at exploring the various organizational approaches in making an office space more welcoming during the pandemic and understanding the importance of designing a healthy interior environment. The nature of this research is intended in the direction to explore the potential ideas where remote working option is not feasible or where the nature of the work demands physical presence. Besides following the general measures, if certain changes or alterations can be done to an existing office space without having to completely change the interiors, could add an extra layer to the defensive measures.

Published by: Namrata Swargari, B. K. Chakravarthy, Abhijoy Banerjee, Ashima Banker

Author: Namrata Swargari

Paper ID: V7I3-2191

Paper Status: published

Published: June 29, 2021

Full Details
Research Paper

Applications of Artificial Intelligence in IoT and Sensor Networks: A Survey

The Internet of Things (IoT) is a digital universe in which tangible daily items are welcomed into a networked digital environment. Virtual assistants, smart thermostats, and fitness trackers are all examples of existing IoT gadgets. IoT innovation is accelerating, bringing more sophisticated gadgets to market with enormous potential to improve human well-being in sectors such as smart cities, efficient manufacturing, and customized healthcare. The factual motto of the IoT revolution is artificial intelligence (AI), which leverages computational power to learn from the massive amounts of data produced by IoT sensors to provide intelligent solutions and accurate predictions thereby providing value to IoT devices. To gain a bird's eye view of the future development of AI applications for IoT (referred to as AI-IoT in this Article), one critical consideration is whether such technology can be protected by intellectual property in the form of patents, and the impact of such patents on the AI-IoT innovation landscape. Enduringly this paper presents the ideas of artificial intelligence and machine learning together with defining its requirements, in the IoT.

Published by: Aryan Karn

Author: Aryan Karn

Paper ID: V7I3-2155

Paper Status: published

Published: June 29, 2021

Full Details
Research Paper

Improved tweet Sentiment Classification Using Convolution Neural Network and Random Forest

With over 319 million monthly active users, Twitter has developed into a goldmine for organizations and people with a strong political, social, or economic incentive to retain or enhance their clout and reputation. Sentiment analysis enables these firms to conduct real-time surveys on numerous social media platforms. Twitter sentiment analysis technology enables the measurement of public attitudes toward certain events or products. The majority of current research is devoted to extracting sentiment traits through the analysis of lexical and syntactic variables. These characteristics are openly stated using emotional words, emoticons, and exclamation points, among others. In this research, effective feature extraction is accomplished via the use of convolution mapping and an attention layer. These features are then learned by random forest.

Published by: Pallavi Sharma, Dr. Harpreet K. Bajaj

Author: Pallavi Sharma

Paper ID: V7I3-2142

Paper Status: published

Published: June 29, 2021

Full Details
Review Paper

A study on Web conferencing system and the deployment

In the current scenario due to the spread of COVID-19, there has been an increase in the use of web conferencing systems to communicate among people. Web conferencing systems have enabled organizations, universities, and individuals to communicate over the internet from their homes during the current pandemic. Web conferencing system not only allows people to communicate over the internet, but it also has other features which enable users spread across different regions to collaborate like a whiteboard, polls, chat, and others. As the number of users is increasing for such systems, scaling and load balancing becomes vital to handle all the users. This paper presents an exploration of the web conferencing systems and explores a case study of an open-source web conferencing system and scaling of the respective system to meet the demands of the system.

Published by: Sudarshan M., Harith L. K., K. Vadhi Raja, Pranava B., Dr. G. S. Mamatha

Author: Sudarshan M.

Paper ID: V7I3-2087

Paper Status: published

Published: June 29, 2021

Full Details
Research Paper

Reusable AI-based ensemble model for detecting SQL injection in service-oriented architectures

Cybersecurity has become one of the most sought-after domains in the field of computer science. Protection of computing resources and information against disruptive cyber threats has garnered utmost attention in recent times, owing to the conventional methods used in the field that often fall short of detecting or preventing the ever-evolving collection of malware. With the advent of new technologies such as Machine learning and Artificial intelligence, it is possible to streamline the approaches in the field of Cybersecurity. These technologies can be used to detect and prevent malicious content, thereby developing successful security solutions. The right AI tech could help us process huge volumes of threat data, discover anomalies and effectively eliminate potential threats. Currently, the most common approach involves using regular expressions to sequentially compare the incoming request or its vector with a predefined set of signatures. Though this approach is widely prevalent, it falls short in terms of accuracy. This is due to the fact that the signatures are not updated often, and several logical problems or loops come up when regular expressions are used within thousands of individual rules. In this project, we aim to identify various injections among neutral input vectors using ML models and will be predicting whether the vectors are injections or not. An ensemble of a number of ML models is used to build a voting mechanism to have an accurate prediction. For the sake of demonstration, the application consists of a frontend built using react and a python flask backend server

Published by: Sudarshan M., Pranava B., Dr. G. S. Mamatha

Author: Sudarshan M.

Paper ID: V7I3-2088

Paper Status: published

Published: June 28, 2021

Full Details
Review Paper

Number Script Recognition using Neural Networks

The ability for accurate digit recognizer modelling and prediction is critical for pattern recognition and security. A variety of classification machine learning algorithms are known to be effective for digit recognition. The purpose of this experiment is rapid assessment of multiple types of classification models on digit recognition problem. The work offers an environment for comparing four types of classification models in a unified experiment: Multi-class decision forest, Multi-class decision jungle, Multi-class Neural Network and Multi-class Logistic Regression. The work presents assessment results using 6 performance metrics: Overall accuracy, Average accuracy, Micro-averaged precision, Macro-averaged precision, Micro-averaged recall and Macro-averaged recall. The experimental results showed that the highest accuracy was obtained by a Multi-class Neural Network with a value of 97.14%. The purpose of this project was to introduce neural networks through a relatively easy-to-understand application to the general public. This paper describes several techniques used for preprocessing the handwritten digits, as well as a number of ways in which neural networks were used for the recognition task.

Published by: Y. Bhanu Prasad, A. Sai Kumar, Pruthvy Charan, Dr. G. Prasad Acharya

Author: Y. Bhanu Prasad

Paper ID: V7I3-2171

Paper Status: published

Published: June 28, 2021

Full Details