Article Per Year (5 Year)
p-Index From 2021 - 2026
0.778
P-Index
This Author published in this journals
All Journal Journal of Computer Science and Engineering (JCSE)
Whig, Pawan
Unknown Affiliation
Computer Science & IT

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Analysis of Tomato Leaf Disease Identification Techniques Chopra, Gaurav; Whig, Pawan
Journal of Computer Science and Engineering (JCSE) Vol 2, No 2: August (2021)
Publisher : ICSE (Institute of Computer Sciences and Engineering)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36596/jcse.v2i2.171

Abstract

India loses thousands of metric tons of tomato crop every year due to pests and diseases. Tomato leaf disease is a major issue that causes significant losses to farmers and possess a threat to the agriculture sector. Understanding how does an algorithm learn to classify different types of tomato leaf disease will help scientist and engineers built accurate models for tomato leaf disease detection. Convolutional neural networks with backpropagation algorithms have achieved great success in diagnosing various plant diseases. However, human benchmarks in diagnosing plant disease have still not been displayed by any computer vision method. Under different conditions, the accuracy of the plant identification system is much lower than expected by algorithms. This study performs analysis on features learned by the backpropagation algorithm and studies the state-of-the-art results achieved by image-based classification methods. The analysis is shown through gradient-based visualization methods. In our analysis, the most descriptive approach to generated attention maps is Grad-CAM. Moreover, it is also shown that using a different learning algorithm than backpropagation is also possible to achieve comparable accuracy to that of deep learning models. Hence, state-of-the-art results might show that Convolutional Neural Network achieves human comparable accuracy in tomato leaf disease classification through supervised learning. But, both genetic algorithms and semi-supervised models hold the potential to built precise systems for tomato leaf detection.
IoT Based Novel Smart Blind Guidance System khera, Yashvi; Whig, Pawan
Journal of Computer Science and Engineering (JCSE) Vol 2, No 2: August (2021)
Publisher : ICSE (Institute of Computer Sciences and Engineering)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36596/jcse.v2i2.172

Abstract

In this research paper the system which is proposed that can be used for safe walking for blinds. This system consist of wireless sensor within the stick which provide the information of the obstacle between the way. The main advantage of this system is the safe for the blind people walking on the road, and make them independent while walking. When obstacle is detected an alert will be given to user with the help of buzzer an vibration . The unique feature of the system is to detect the temperature of a person who passes within the range of 6 feet of which helps in maintaining the social distancing in COVID situation. The system contains a wireless sensor that integrates temporary networks that can be made within the navigation stick, which can provide group communication between them, where roaming information and networks can be provided. With the help of IOT the location and alert message shared with family members in case of emergency. The system proposed in this research study is 60% more efficient then conventional system. The information is included in table1 to validate  the result.
Prediction of Loan Behaviour with Machine Learning Models for Secure Banking Anand, Mayank; Velu, Arun; Whig, Pawan
Journal of Computer Science and Engineering (JCSE) Vol 3, No 1: February (2022)
Publisher : ICSE (Institute of Computer Sciences and Engineering)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Given loan default prediction has such a large impact on earnings, it is one of the most influential factor on credit score that banks and other financial organisations face. There have been several traditional methods for mining information about a loan application and some new machine learning methods of which, most of these methods appear to be failing, as the number of defaults in loans has increased. For loan default prediction, a variety of techniques such as Multiple Logistic Regression, Decision Tree, Random Forests, Gaussian Naive Bayes, Support Vector Machines, and other ensemble methods are presented in this research work. The prediction is based on loan data from multiple internet sources such as Kaggle, as well as data sets from the applicant's loan application. Significant evaluation measures including Confusion Matrix, Accuracy, Recall, Precision, F1- Score, ROC analysis area and Feature Importance has been calculated and shown in the results section. It is found that Extra Trees Classifier and Random Forest has highest Accuracy of using predictive modelling, this research concludes effectual results for loan credit disapproval on vulnerable consumers from a large number of loan applications
Novel approach of Predicting Human Sentiment using Deep Learning Shadadi, Ebtesam; Kouser, Shama; Alamer, Latifah; Whig, Pawan
Journal of Computer Science and Engineering (JCSE) Vol 3, No 2: August (2022)
Publisher : ICSE (Institute of Computer Sciences and Engineering)

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Due to its interactive and real-time character, gathering public opinion through the analysis of massive social data has garnered considerable attention. Recent research have used sentiment analysis and social media to do this in order to follow major events by monitoring people's behavior. In this article, we provide a flexible approach to sentiment analysis that instantly pulls user opinions from social media postings and evaluates them. As time passed, an increasing number of people shared their opinions on social media. More individuals can now communicate with one another as a result. Along with these advantages, it also has certain drawbacks that cause resentment in some people. Hate speech is another possibility. Hate speech impacts the community when it contains insulting or threatening language. Before it spreads, this kind of speech has to be identified and deleted from social media platforms. The process of determining whether a text's feelings reflect hatred or not involves sentiment analysis. Python language was used to analyze the Twitter dataset. There were 5000 Tweets in total in this dataset, and we used deep learning to improve the machine learning model's accuracy. The experimental outcome in both cases of the Twitter dataset uses the Random Forest approach, which has a 99 percent accuracy rate.
Co-Authors Alamer, Latifah Anand, Mayank Chopra, Gaurav khera, Yashvi Kouser, Shama Shadadi, Ebtesam Velu, Arun