Manuscripts

Recent Papers

Research Paper

A Novel Approach of Preventing Cyber Attack on Industry 4.0

The Internet of things (IoT) describes the network of physical objects "things" that are embedded with sensors, software, and other technologies for the purpose of connecting and exchanging data with other devices and systems over the Internet.The IoT concerns a wide range of modules like the data acquisition, communication, sensors etc. Owing to the lack of consideration of cyber security threats, they have an inherent technical debt which results in compromised medical devices with unpredictable behaviour. With the increasing market share of the IoT devices in the healthcare field, it has offered a simple door for cyber criminals trying to misuse and profit from device vulnerabilities. In this paper we discussing about attack on smart bulb. We are providing cyber security on smart blub with different module such as attacking on smart bulb then detect the that particular attack last prevent the attack.

Published by: Gayatri Ravtole, Anushika Pandita, Rajshree Ghatkar, Rutuja Kamthe

Author: Gayatri Ravtole

Paper ID: V7I3-1935

Paper Status: published

Published: June 18, 2021

Full Details
Research Paper

An efficient data pre-processing model for machine learning

Currently, data pre-processing is one of the areas of nice interest as a result of it permits the discovery of hidden and infrequently attention-grabbing patterns in massive volumes of information. information scientists pay most of their time on information preparation tasks that have investigation regarding the info, loading information, and cleanup information, in line with an exploration conducted by Anaconda. The real-world massive information sets square measure obtained from several sources and contain data that tend to be incomplete, creaky, and inconsistent thence required correct investigation. during this context, it’s vital to arrange information to satisfy the necessities of information mining algorithms. this can be the role of the information pre-processing stage, within which information cleanup, transformation, and integration, or information spatiality reduction square measure performed. just about any sort of information analytics, information science or AI development needs some sort of information pre-processing to supply reliable, precise, and strong results for enterprise applications.

Published by: Piyush Lawatre, Mohammed Muzzammil, Rishabh Hingal, Fatir Khan, Rizwan Khan

Author: Piyush Lawatre

Paper ID: V7I3-1922

Paper Status: published

Published: June 18, 2021

Full Details
Research Paper

Image classification based plant disease detection

Agriculture is one of the important aspects in the world, also the contribution of agriculture to the GDP of India increased to 19.9 percent in 2020-21 from 17.8 percent in 2019-20. Globally crop disease becomes a major cause of concern, so to overcome this concern a plant disease detector should be there which gives good results and increases the yield for farmers. In this scenario, the best option for dealing with crop disease identification is an Image Classification based disease detection system. The key goal of this project is to identify the disease in real-time by uploading an image of the infected plant leaf to the system. Aside from that, the system suggests remedies for the particular disease that is identified by the system. Our proposed research paper includes various phases of implementation namely data set creation, image pre-processing, image post-processing, and finally disease classification and grading. Overall, we are using machine-learning techniques to train the dataset and finding the disease for that particular plant.

Published by: Jinesh Kansara, Kartik Atul Nerkar, Mihir Manish Brahmbhatt

Author: Jinesh Kansara

Paper ID: V7I3-1927

Paper Status: published

Published: June 18, 2021

Full Details
Review Paper

Mechanical response of PTFE-based nanocomposites

Polytetrafluoroethylene (PTFE), reinforced with Boron Carbide (B4C) and Molybdenum disulphide (MoS2) were prepared by Studying the various manufacturing processes and selecting the best suitable for Producing this Composite. Mechanical Properties such as the Tension test, Compression Test, and Hardness (Shore hardness) were done and their results were studies accordingly. The Composition of (MoS2), Boron, and PTFE compounds were varied with different Percentages so as to get the Optimized Result for Tension Test, Compression Test, and Hardness.

Published by: Aashish Sulebhavi, Bharat Aldar

Author: Aashish Sulebhavi

Paper ID: V7I3-1928

Paper Status: published

Published: June 18, 2021

Full Details
Survey Report

Automatic helmet detection & license plate recognition using CNN & GAN

Enforcing the use of helmets on every bike rider is mandatory nowadays because of the high accident rate and poor road conditions. There are laws regarding safety measures that ensure the use of a helmet. But for now, they involve manual intervention which is not so effective as of now because bike riders sometimes tend to escape without any penalty/fine after breaking the safety rules like wearing a helmet while riding. Automation is a better way to deal with this problem but automation in this area comes with its own challenges. To name a few, Low-quality image frames (low image resolution, pixel density, etc.), rain, dew and fog, and partly hidden faces. The robustness of detection methodology strongly depends on the strength of extracted features and also the ability to deal with the lower quality of extracted data. The first goal of this project is to boost the potency of helmet detection and then recognizing the license number plate recognition. This model consists of many essential steps developed using today’s most advanced amp; optimized CNN, GAN models amp; libraries. It is a classification-based model that uses a supervised learning approach to train CNN and Character Segmentation algorithm. The proposed helmet detection model can be used to detect helmets and recognizes license plates even in adverse conditions using character segmentation and CNN.

Published by: Pranav Sanjay Patil, Damini Kailas Pawar, Shruti Vilas Bairagi, Varun Dipak Bharambe, Nilesh Wankhede

Author: Pranav Sanjay Patil

Paper ID: V7I3-1921

Paper Status: published

Published: June 18, 2021

Full Details
Research Paper

Agriventure – Data analytics for farming and agro-businesses

Agricultural statistics and forecasts are a valuable resource that the government has not fully used despite their significance. Our project's goal is to automate this process by incorporating data mining and analytics concepts. More precisely, our project aims to address the social issue of drought by analyzing data for every crop in the state of Maharashtra, including crop statistics, rainfall, temperature and strain, production data, and other factors. Efficient countermeasures and recommendations would be provided based on the detailed studies conducted as part of this initiative, which, if applied quickly, will assist in addressing the drought issue in our state. It will also include forecasts for increases or decreases in consumer demand for specific agricultural goods, which will support agro-based sectors and enterprises. Data may be analyzed to uncover different patterns, such as recommendations to farmers for growing specific crops based on soil type and weather forecasts, district-level rainfall, and increases or decreases in market demand for specific agricultural goods. The project's final product will be research-driven publications that detail these patterns and will be based on data collected over the last three years. Drought mitigation measures would be proposed and also crop suggestions for the drought-prone regions, which will aid in the productive operation of AgriBusinesses.

Published by: Akshita Biyani, Bhoomi Bhanushali, Drishti Jain, Charmi Savla, Sangeeta Nagpure

Author: Akshita Biyani

Paper ID: V7I3-1882

Paper Status: published

Published: June 18, 2021

Full Details