Journal of Informatics Electrical and Electronics Engineering (JIEEE)

Assessment of Water Quality using Machine Learning and Fuzzy Techniques

Shashi Kant — 2023-04-25

The water quality of river Ganga is an important concern due to its drinking, domestic uses, irrigation and also for aquatic life. But the extent of pollutants in river water has deteriorated the quality of river water. So, the assessment of river water becomes very important. But due to the involved subjectivity and uncertainty in the decision making parameter makes the task very complex. In this study, machine learning and fuzzy techniques are utilized to develop the river water quality assessment models. The quality of the water is grouped into three classes. Four machine learning algorithms namely decision tree, random forest tree, k-nearest neighbor and support vector machine are used and implemented on python and anaconda platform. Whereas, three fuzzy based models (fuzzy decision tree, wang-mendel and fast prototyping) are developed using Guaje open source software. All the seven models are analyzed in terms of accuracy, precision, recall and f1-score. The observed result shows that the fuzzy decision tree-based assessment model performs more accurately as compared with the machine learning based models.

PlantDoc-Plant Disease Detection using AI

Adiba Khan — 2023-04-25

Gardening is a hobby which requires dedication and consistency. It is something more than just watering a plant. Taking care of Garden plants is very important as most of the plants are prone to diseases frequently. Plant Diseases ruin the plant and ultimately may kill it with time so timely identification and treatment of the disease is required for a healthy plant. This also helps to preserve many threatened species of plants. PlantDoc uses Artificial Intelligence model created on Convolution Neural Network algorithm of Deep Learning to solve this problem. The model is trained with images of different plant leaves to identify defected plants. PlantDoc helps in disease detection. It uses computer vision concept of AI to find the disease of plant and provide solution for that automati-cally. PlantDoc uses MERN stack. PlantDoc web application successfully helps to identify plant diseases of various plants by analyzing plant leaf image and suggests cure to treat it. This helps in treatment of plants timely which helps to stop the further spread of dis-ease and provides cure.

Decentralized Crowdfunding Platform Using Blockchain

Arohi Rathore — 2023-04-25

Few years back, blockchain was particularly used to support cryptocurrencies, but after some decades, more and more sectors are adopting this brand-new technology. Blockchain will used by the majority of technologies in the future as an effective means of conducting online transactions. Crowdfunding platforms are one of the industries to which blockchain technology may be applied. Although crowdfunding is quite common online, there are still some problems with it. Projects that don't finish on schedule, don't finish at all, or don't provide what they promised cause trust concerns. Additionally, crowdfunding sites serve as intermediaries, so you must put your faith in them to transmit your cash properly. This project solves these problems by integrating Ethereum smart contracts with the crowdfunding platform, scams may be avoided, and it is ensured that projects can be fulfilled within the specified time frame. With the use of blockchain technology, decentralised crowdfunding offers more accessibility, transparency, and reduced fees. The ability to immediately create, watch, and donate to crowdfunding campaigns via the blockchain is the most crucial feature. The decentralised crowdfunding platform is linked to the blockchain and fea-tures authoring solidity code, pairing metamasks, interacting with smart contracts, and sending Ethereum across the network.

Enhancing the Fake News Classification Model Using Find-Tuning Approach

Mohammed Ali — 2023-04-25

Over the last few years, the rise of fake news on social media has emerged as a significant issue, posing a potential threat to individuals, organizations, and society as a whole. As a solution to this issue, researchers have been using various natural language processing (NLP) techniques to detect fake news. In this study, we introduce a new strategy for fake news detection and classification. Our approach involves enhancing the performance of accuracy through fine-tuning, by merging BEART model with the proposed model DCNN. We have collected the data from secondary sources and combined it into a unified dataset. To improve its quality, we performed various processes such as data cleaning, transformation, integration, and reduction, which involved techniques like stop word removal, tokenization, and stemming, resulting in binary classification. Therefore, DCNN" was trained to classify news articles as real or fake, and the experiments on the dataset show that this approach performs better than several recent studies for detecting fake news, achieving high accuracy

Using Machine Learning to Determine the Motorist Somnolence

Sakshi Pandey — 2023-04-25

Traffic accidents pose an increasing threat to society, and researchers are dedicated to preventing accidents and reducing fatalities, as highlighted by the World Health Organ-ization. One significant cause of accidents is drowsy driving, which often leads to severe injuries and loss of life. The objective of this research is to create a fatigue detection sys-tem that can effectively minimize accidents associated with exhaustion. The system uti-lizes facial recognition technology to identify drowsy drivers by analyzing eye patterns through video processing. When the level of fatigue surpasses a predetermined thresh-old, the system alerts the driver and adjusts the vehicle's acceleration accordingly. The implementation of OpenCv libraries, such as Haar-cascade, along with Raspberry Pi fa-cilitates seamless integration of the system. This dissertation evaluates advancements in computational engineering for the development of a fatigue detection system to miti-gate accidents caused by drowsiness. It offers valuable insights and recommendations to enhance comprehension and optimize the system's effectiveness, ultimately leading to safer road travel.

Drowsiness Detection System in Real Time Based on Behavioral Characteristics of Driver using Machine Learning Approach

Gauri Adarsh — 2023-04-25

The process of determining if a person, generally a driver, is becoming sleepy or drowsy while performing a task such as driving is known as drowsiness detection. It is a necessary system for detecting and alerting drivers to their tiredness, which might impair their driving ability and lead to accidents. The project aims to create a reliable and efficient system capable of real-time detection of drowsiness using OpenCV, Dlib, and facial landmark detection technologies. The project's results show that the sleepiness detection method can accurately and precisely identify tiredness in real time. The technology is less intrusive and more economical than conventional sleepiness detection techniques. The system is based on a 68 facial landmark detector, which is a highly trained and effective detector capable of recognizing human face points. The detector aids in assessing whether the driver's eyes are closed or open. The system analyses the data collected by the detector using machine learning methods to discover patterns associated with drowsiness. When drowsiness is detected, the system incorporates a warning mechanism, such as an alarm or a vibration in the steering wheel, to notify the driver. A variety of studies with different drivers and driving conditions were used to evaluate the performance of the real-time driver drowsiness detection system. The results show that the technology can detect tiredness properly and deliver timely warnings to the driver. This method can assist in preventing drowsy driving incidents, enhancing road safety, and saving lives. The results indicated that the algorithm had an average accuracy rate of 94% for identifying tiredness in drivers.

Evaluation of Data Sets and Algorithms for Brain Tumor Detection Using MRI Images: A Python-Based Approach

Mugda Singh — 2023-04-25

This study is to evaluate the work of the data sets and major algorithms that are in-volved in the brain tumor detection system using the MRI image with the help of the python concept. So basically, is an easy manner if we require to define the phenomena of the brain tumor it could be the abnormal condition that causes the problem of cancer, here the abnormal condition refer to the growth in cell body in not a very suitable way for the brain tissue. In the respective paper, we proposed an algorithm to segment brain tumor from 2D Magnetic Resonance Image of the brain by a CNN. When this algorithm is applied to MRI images, a brain tumor diagnosis can be made more quickly and accu-rately, which makes it easier to give patients treatment. These predictions enable the radiologist to make quick decisions as well. In the proposed work, the performance of a self-defined Convolution Neural Network (CNN) is evaluated. For the purpose of faster and efficient accuracy, we will implement the proposed method using the “TenserFlow” and “keras” in “Python.

Non-Deterministic and Polynomial Time Problem Simulator

Himanshu Mishra — 2023-04-25

The Non-Deterministic and Polynomial Time Problem is a problem in combinatorial op-timization. Finding the quickest route for an object to travel through a list of cities and return to the starting city is the goal of this problem. Cities are listed, along with the dis-tance between each pair. It belongs to the category of computer problems known as NP-complete problems, for which no effective algorithmic solution has yet been discov-ered; at this time, there is no polynomial solution. In order to discover a near-optimal solution as quickly as possible, we attempted to tackle this extremely challenging prob-lem in this study utilizing a variety of heuristics, including Simulated Annealing and Ge-netic Algorithm. Using these sophisticated heuristic techniques, we at-tempt to depart from the local optimum.

Applications of Fibonacci Sequences and Golden Ratio

Dr. Ambrish Kumar Pandey — 2023-04-25

The study mainly focuses on the use of the Golden Ratio and the Fibonacci sequence. The connection between them can be clearly visible in nature. With the help of the Fib-onacci sequence scientists have solved many mysteries related to nature. Everything that is around us somehow or other depends on Fibonacci numbers, the Golden Ratio, and the Fibonacci sequence. Some examples are –Flower petals- Lily, Rose, Daisy, Marigold, Sunflower, Iris, Buttercups, wild rose, larkspur Trillium, Bloodroot, Aster, and Susan; Seed heads-Sunflower; Snail; Fruit-Apple, Banana, Pineapple; Human Face; Tree Branches; Cyclone; Pinecones; Shells; Spiral Galaxies; Bees; Famous architecture design – Taj Ma-hal, in Hindu rituals, in decoding-coding the data, in providing security to the sensitive data and all over the world, in mother's womb (about her baby's position), etc. The cur-rent study reflects that there is no limitation to the Fibonacci pattern and Golden Ratio in our surroundings.