Logo

e-ISSN: 2455-6491 | Published by Global Advanced Research Publication House (GARPH)

Home Aim & Scope Abstracting and Indexing Call For Papers Instructions For Authors Editorial Board Archives Conferences Download Ethics and Policies Publication Ethics and Publication Malpractice Statement Article withdrawal Policy Plagiarism Policy Peer Review Policy Copyright, Grants and Ownership Declaration Open Access Policy Advertising Policy Join Us

Archives of International Journal of Advanced Innovative Technology in Engineering(IJAITE)

Volume 7 Issue 4 July 2022



1. Fake News Detection Based on Machine Learning Approach

AUTHOR NAME : Karishma K. Misal, Prof. Minakshi Ramteke

ABSTRACT : Fake news detection is an interesting topic for computer scientists and social science. Because of the recent growth of online social media fake news has a great impact on society. There is much information from disparate sources among various users around the world. Twitter is one of the most popular applications that are able to deliver appealing data in a timely manner. Developing a technique that can detect fake news from Twitter is becoming a necessary and challenging task. This paper proposes a machine learning method that can identify fake news from Kaggle data. The experiment is carried out with four widely used machine learning methods such as Logistic Regression, Naïve Bayes, Gradient Boost, and SVM using the data collected. The results show that all machine learning methods can detect fake news in this data set accurately. This investigated the four methods and compared their accuracies. The model that achieves the highest accuracy is gradient boost and the highest accuracy score is 99.61%.

Download



2. Personality Prediction System using Machine Learning Approach

AUTHOR NAME : Mayur Dnyaneshwar Nandeshwar, Ashish Ramdas Umredkar, Siddhesh Avinash Upadhye, Karan Wasudeo Ghormare, Prof. Milind Thote

ABSTRACT : Personality Prediction is a system which can be used by company to find right candidate with best personality for their organization. Admin can easily shortlist right candidate based on their personality scores. We are using Natural Language Processing which enables machine to become more like a human. The system built in this project predicts personality of peoples by using their gender, age, score openness, extraversion, Agreeableness, neuroticism and experience. We are fetching data from resumes. This system uses logistic regression for training the model and pyreparser module for parsing the information from resume which is built using nltk and spacy module in python. This paper helps to right the personality test and check the personality of the person. From the personality classification person can view the type of personality and can improve personality based upon the result.

Download



3. Underground Cable Fault Detection System Using GSM and Arduino Nano System

AUTHOR NAME : Mr. Akshay Sontakke, Mr. Rohit Nirapure, Mr. Hariom Tekade, Ms. Purnima Patil, Ms. Sapna Dupare, Ms. Chandani Bansod, Prof. Ashutosh V. Joshi

ABSTRACT : The objective of this paper is to determine the distance of faulty underground cable from the base station in kilometres using Arduino microcontroller. Using the concept of ohms law, controller measures resistance or capacitance of the circuit and finds distance in kilometres with the proposed system, finding the exact location of the fault is possible. In case there is a fault, the voltage across series resistors changes accordingly, which is then fed to inbuilt ADC of Arduino board to develop precise digital data for display in kilometres. The paper uses the standard concept of Ohms law i.e., when a low DC voltage is applied at the feeder end through a Cable line, then current would vary depending upon the location of fault in the cable. The project is assembled with a set of resistors representing cable length in KM’s and fault creation is made by a set of switches at every known KM to cross check the accuracy of the same. The fault occurring at a particular distance and the respective phase is displayed on an LCD interfaced to the Arduino board and sent SMS to registered mobile number.

Download



4. Solar, Wind, and Hydro Energy Hybrid Power Generation System

AUTHOR NAME : Suraj R. Bhuyar, Payal Rewatkar, Sankesh Deshmukh, Sarang Gathe

ABSTRACT : Today, the world is progressing at quite a fast rate with the use of conventional sources of energy. Now a day’s electricity is a most needed facility for human beings. All the conventional energy resources are depleting day by day and having disadvantages of using them are environmental pollution created by their use. So, we have to shift from conventional to non-conventional energy resources. Many types of clean and renewable energy sources can be used in the production of electrical energy. In this paper, the combination of two energy resources takes place i.e., wind, hydro, and solar energy. This process reviles the sustainable energy resources without damaging nature. We can give uninterrupted power by using a hybrid energy system. Basically, this system involves the integration of two energy systems that will give continuous power. Solar panels are used for converting solar energy into electricity and wind turbines are used for converting wind energy into electricity. This electrical power can utilize for various purposes. Generation of electricity will take place at an affordable cost. This project deals with the generation of electricity by using three sources combined which leads to generating electricity with affordable cost without damaging the natural balance.

Download



5. Comparative Analysis of Association Rule Mining Based on Genetic Algorithm

AUTHOR NAME : Nitin C. Sabne, Dr. Shubhangi D. Sapkal

ABSTRACT : Association rule mining plays an important role in the various data mining process. The diversity of association rule mining spread in various fields such as market bucket analysis, medical diagnosis, and share market prediction. Nowadays various authors and researchers focus on the validation of association rule mining. For the validation of association rule mining using various optimization algorithms are used such as genetic algorithm, Ant Colony Optimization, and particle of swarm optimization also used. For the mining of rule mining, a variety of algorithms is used such as the Apriori algorithm and the tree-based algorithm. Some algorithm is wonderful performance but generate negative association rules and also suffered from multi-scan problems. This paper proposed multi-level minimum supports (MLMS-GA) association rule mining based on the min-max algorithm and MLMS formula. In this method, we used multi-level minimum supports of data tables as 0 and 1. The divided process reduces the scanning time of the database. The proposed algorithm is a combination of MLMS and min-max algorithms. The support length key is a vector value given by the transaction data set. In the process of rule optimization, we used the min-max algorithm and to evaluate, the algorithm conducted the real-world dataset such as heart disease data and some standard data used from the UCI machine learning repository.

Download



6. Study of Intelligent Transportation System (ITS) and Internet of Things (IOT) in Transportation System

AUTHOR NAME : Rahul D. Jadhav, Dr. M. R. Vyawahare, Prof. A. R. Bijwe

ABSTRACT : Transport, tourists and various site visitors’ traffic jam is an internationally common hassle. Indian economy is growing very fast; the problem in transport is severely felt in almost all major cities. This is due to infrastructure growth, flood in variety of car segments, due to space and value constraints. However, traffic in India is being non-lane based and uncontrolled is basically different from the western visitors. Intelligent transportation systems (ITS), used for efficient traffic management at developed international locations, cannot be used as it is in India. A case study was done on urban area of Amravati from Raja Peth to Nandgaon Peth Toll Plaza of NH-6 and its detail analysis is presented in this study. The accident data was collected for last five years. Data collected on traffic volume and spot speed by adopting standard survey method. The collected data was analyzed to evaluate the effect of influencing parameters on accident rate, congestion of traffic and standardize the speed of the vehicles. It can be observed from above that project traffic has PCU index close to 2.0 which indicates good mix of commercial, goods traffic and passenger traffic. Increase speeding enforcement initiate traffic calming measures. Conduct public awareness efforts. Adjust the posted speed limit. The severity on highway study area is about 60% to 80%. Accident prediction model developed by Poisson distribution and Chi Square revealed that accident rate of analytical value is to be 0.09 and 0.71 respectively.

Download