Book Cave: A Bookstore for Everyone

2022

Engineering Education in India is passing through turbulent times. It is seen that since 2018 the admissions for core branches such as Mechanical Engineering, Civil Engineering and Electrical Engineering is quite less compared to Computer Science and Engineering. Currently the supply of seats in engineering institutes exceeds the demand of seats. Institutions are unable to cope up with this sudden change and have reduced their intake in core branches or have altogether gone for closure of these branches over the last four years. Employability is one of the critical component for admissions. As the economy of nations boomed the demand for automation in manufacturing, use of Artificial Intelligence, machine learning has taken a quantum jump and the major IT companies over India had large hiring in these four years. In this work, the issues faced about employability of engineering graduates have been viewed from androgogical perspective and brainstorming was conducted with the stakeholders to arrive at the various issues ahead and the way to address the same. 26 measures were suggested by the various stakeholders be in alumni, parents, employers, training organizations, faculties. Google form was sent to the faculty members to solicit their opinion on the 26 points and Lickert scale of 1-5 rating was used to get the responses. Responses for 40 respondents (covering 6 Indian states) are analysed and the results are quite similar. 90% respondents agree that setting of new high tech labs and training for skill development, placement opportunities (Robotics, 3D Printing, Total Station QGIS, Revit, Sketch up), Functional MoUs with industries can help improve employability (with 70 % strongly agreeing). 90% respondents agree that finding out good sincere students (10-20%) i.e. segregation and grooming them in their field of interest, future plans can improve the knowledge, skill, attitude (KSA) for employment (with 50% strongly agreeing). 90% respondents agree that Self discipline /self management among students, attendance in college and responsibility in learning impact KSA of students (with 50% strongly agreeing). These responses are indicative that institutions need to align themselves in the changing times to make their students employable.

International Journal of Computer Applications

The quality higher education is required for growth and development of country. Professional education is one of the pillars of higher education. Data mining techniques aim to discover hidden knowledge in existing educational data, predict future trends and use it for betterment of higher educational institutes as well as students. The objective of this study is to use prediction technique using data mining for producing knowledge about students of Masters of Computer Application course before admitting them to the course.

Smart Innovation, Systems and Technologies, vol 281. Springer, Singapore, 2022

Immense career without a quality Education is just a DREAM. Degree, specialization, College/University and the knowledge are key factors in order to achieve great career. Career related decisions are discussed after 10th standard and mostly concluded after 12th. After successful completion of 12th, the next target of any student is to get into suitable College/University for appropriate course/program so that he can get a better education, guidance & placement for his future. In this research, exploratory data analysis (EDA), Feature selection, Label encoding, Feature scaling, normalization and standardization are rigorously implemented on the dataset using various python libraries to prepare the dataset ready to apply Machine Learning (ML) algorithms. We have built the ML models for prediction of the college by testing suit of ML classification algorithms using K-fold cross validation method and Ensemble Learning (EL) ML method. Suit of ML algorithms covers Logistic Regression, K Nearest Neighbors', Decision Tree Classifier, Random Forest Classifier, Naive Bayes & Support Vector Machine classifiers. Under EL we have tested Adaptive Boosting, Gradient Boosting and Grid Search CV methods. Nevertheless, EL methods are popular and gives best performance on a predictive modeling project, we have received opposite results. After comparison we found ML technique Decision tree has higher accuracy for college prediction project. At the end researchers have suggested "Free guide to engineering admission aspirant parent and student (FGEAAPS)" web module through which engineering aspirant parent and students can take the guidance for college selection.

Predictive models are quasi experimental structures used to determine the future patterns in data. These meaningful data patterns form the building block of any decision support system. Researchers all over the world have built many prediction models for major industries. Research works in the educational sector has increased steeply. This steep increase may be due to the high availability of data in the educational domain. This survey tries to comprehend a few literary works on academic performance prediction of engineering students with the focus on grade predictions. Meaningful interpretations have been made and inferences are presented at the end of this paper.

International Journal of Swarm Intelligence Research

Today, students are very confused while selecting colleges based on their ranking after XII standard exam. If students are willing to go for engineering, then they are interested to know the name of colleges on the basis of their merit. The particular college depends on several factors. More and more colleges are interested in mapping students' other features such as extra-curricular activities and financial background, so that they can provide better platforms to sharpen their skills. Thus, this paper proposes an intelligent technique to provide students a platform that will help them to match the colleges based on their academics and extra-curricular qualifications. A fuzzy inference and weighted fuzzy decision tree are used to calculate the score of each student based on the multiple factors of the student where results are shown to be promising.

International Journal of Electrical and Computer Engineering (IJECE), 2022

The knowledge discovery from student's data can be very useful in predicting the employment under different categories. The machine learning is helping in this regard up to the great extent. In this paper, a hybrid model of machine learning has proposed to predict the jobs categories, students may get in their campus placement. The considered groups of students are from undergraduate courses from engineering stream having the semester's scheme in their academic. The mapping of jobs has predicted based on their previous seven semesters marks as well as their personality index. The proposed hybrid model consists of three different model based on multilayer feed forward architecture, radial basis function neural network and K-means based clustering method. The proposed model provided the relative chances of available each job category with high accuracy and consistency.

Smart innovation, systems and technologies, 2022

Immense career without a quality Education is just a DREAM. Degree, specialization, College/University and the knowledge are key factors in order to achieve great career. Career related decisions are discussed after 10th standard and mostly concluded after 12th. After successful completion of 12th, the next target of any student is to get into suitable College/University for appropriate course/program so that he can get a better education, guidance & placement for his future. In this research, exploratory data analysis (EDA), Feature selection, Label encoding, Feature scaling, normalization and standardization are rigorously implemented on the dataset using various python libraries to prepare the dataset ready to apply Machine Learning (ML) algorithms. We have built the ML models for prediction of the college by testing suit of ML classification algorithms using K-fold cross validation method and Ensemble Learning (EL) ML method. Suit of ML algorithms covers Logistic Regression, K Nearest Neighbors’, Decision Tree Classifier, Random Forest Classifier, Naive Bayes & Support Vector Machine classifiers. Under EL we have tested Adaptive Boosting, Gradient Boosting and Grid Search CV methods. Nevertheless, EL methods are popular and gives best performance on a predictive modeling project, we have received opposite results. After comparison we found ML technique Decision tree has higher accuracy for college prediction project. At the end researchers have suggested “Free guide to engineering admission aspirant parent and student (FGEAAPS)” web module through which engineering aspirant parent and students can take the guidance for college selection.

In this study, the various employability skills that may likely influence performance of engineering students in campus placement were identified. An Artificial Neural Network (ANN) model was developed for predicting probability of placement based on employability skills. Identified 22 employability skills were validated by stakeholders and group into four major employability skills. Aptitude, Communication, Technical & Personality skill were used as input variable and success/failure in campus placement considered as output variable. The sample of 362 final year students from technical institutes affiliated to Rashtrasant Tukadoji Maharaj Nagpur University, Nagpur were used to analyze by using SPSS version 20 & develop the model. As per result of the research work, all employability skills have positive moderate correlation with probability of placement. It means institute needs to change their traditional focus & make special efforts to help their students for developing competencies that best foster Employability.

Imprint, 2020

Purpose: The growth and prosperity of a nation depends upon its ability to innovate technologically and engineering has erupted as a fundamental chauffer of this essence, since last couple of eras. But recent decline in engineering admissions triggers the downfall in skilled labour, which can cause recession in Industry or ultimately leads to economic crisis. This study tries to illustrate the present status of engineering education, particularly in India and tends to skim the various parameters that affect the enrolment of students among higher education institutes, directly or indirectly. Design/methodology/approach: A unique approach has been unleashed to tackle the nuisance of low admission among Indian engineering colleges or universities. Factors reviewed from literature were further prioritized quantitatively after floating suitable Questionnaire among relevant set of engineering aspirants. The ‘Survey Form’ used was tactically designed on the basis of Response Surface Methodology, which analysed the data captured in Minitab statistical software and deduct logical inferences to optimize the ‘Critical to Admission’ factors, applicably. Findings: A case study has successfully been executed in a North Indian state to prove the efficacy of proposed methodology, as far as downtrend in admission is concerned. This study is a rare blend of Questionnaire based work, where Design of Experiments Principles had been utilized exclusively. It provides significant findings on how to earmark different Admission-Decisive-Factors along with their required prioritization. Originality: Quantitative study in the service sector (like Higher Education) is quite rare to see. Present work is not only providing a roadmap for engineering institutions to boost their admissions in upcoming challenging times, but it also act as a light house for new students, as it provides necessary guidelines for shortlisting colleges or universities, while taking admission in higher studies. Practical implications: It can further help the universities and higher education institutes to draft their indispensable Professional Policies and Vision-Mission Statements, appropriately.

SinkrOn

University of Harapan Medan is one of the private universities in North Sumatra which has computer-based study programs such as Informatics Engineering and Information Systems. Every year this college receives many registrations from students who have completed their education at the school stage. The large number of incoming student data makes it difficult for the admin to select new students who will register. In this study using the C4.5 algorithm data mining method to map the pattern of student admissions selection in the field of Engineering and computers. The attributes used are the average value of report cards (high, enough, low), basic academic ability tests (very high, high, medium, low, very low), basic computer knowledge tests (very high, high, enough, low, very low) and interviews (good, bad). Data mining is a mathematical calculation process that uses algorithms and requires large data. While the C4.5 algorithm is an algorithm that processes data by calculating entroph...