Campus placements are a significant aspiration for college students, as they reflect both the quality of the educational institution and the performance of its students. Securing a placement during campus interviews can greatly impact a student's career trajectory, making it essential for institutions to effectively forecast students' potential for success in these interviews. In this context, machine learning, coupled with knowledge discovery processes, has emerged as a valuable tool for predicting student performance in placement scenarios. This paper proposes an ensemble model based on a voting classifier that integrates the BayesNet and J48 algorithms. This innovative approach aims to classify student academic data and predict their placement opportunities with high accuracy. The ensemble model leverages the strengths of both classifiers to enhance the overall predictive performance. This model produced 91% of accuracy in the placement prediction. J48 and BayesNet classifiers are combined by probability average-based combination rule in the ensemble voting model. Author(s) Details B. Kalaiselvi Department of Information Technology, Nallamuthu Gounder Mahalingam College, Pollachi, Tamil Nadu, India. S. Geetha Department of Computer Science, Government Arts and Science College for Women, Puliakulam, Coimbatore, Tamil Nadu, India. Please see the link:- https://doi.org/10.9734/bpi/strufp/v11/1804

 

Campus placements are a significant aspiration for college students, as they reflect both the quality of the educational institution and the performance of its students. Securing a placement during campus interviews can greatly impact a student's career trajectory, making it essential for institutions to effectively forecast students' potential for success in these interviews. In this context, machine learning, coupled with knowledge discovery processes, has emerged as a valuable tool for predicting student performance in placement scenarios. This paper proposes an ensemble model based on a voting classifier that integrates the BayesNet and J48 algorithms. This innovative approach aims to classify student academic data and predict their placement opportunities with high accuracy. The ensemble model leverages the strengths of both classifiers to enhance the overall predictive performance. This model produced 91% of accuracy in the placement prediction. J48 and BayesNet classifiers are combined by probability average-based combination rule in the ensemble voting model.

 

 

Author(s) Details

 

B. Kalaiselvi

Department of Information Technology, Nallamuthu Gounder Mahalingam College, Pollachi, Tamil Nadu, India.

S. Geetha

Department of Computer Science, Government Arts and Science College for Women, Puliakulam, Coimbatore, Tamil Nadu, India.

 

Please see the link:- https://doi.org/10.9734/bpi/strufp/v11/1804

A Comprehensive Examination, Execution, and Evaluation of Machine Learning Algorithms Applied to a Breast Cancer Dataset Utilizing the WEKA Software Tool | Chapter 7 | Mathematics and Computer Science: Contemporary Developments Vol. 8

In the contemporary world, cancer ranks as one of the most critical diseases. The factors contributing to cancer include modern lifestyle choices, environmental influences, and genetic predispositions. It has emerged as the leading cause of mortality in developed nations. Among various types of cancer, Breast Cancer is the most prevalent among women and is a significant contributor to female mortality. Cancer screening methods are typically experimental or natural in their approach. Machine Learning algorithms play a crucial role in identifying significant patterns within data, particularly in the context of disease prediction. In this research, a new Machine Learning approach is developed in predicting breast cancer at an early stage. The objective is to assess the effectiveness of the ML algorithm based on metrics such as precision, specificity, sensitivity, and accuracy. A real-time Breast Cancer dataset was collected from the UCI Machine Learning repository for performing research. The data was firstly preprocessed to identify the missing values of the features in the dataset and replaced with the mean of the relevant variable. Then the dataset was projected on popular Machine Learning algorithms, including Sequential Minimal Optimization (SMO), Naive Bayes (NB), J48 (C4.5 decision tree), K-Means, and K-Nearest Neighbours (k-NN). From the analysis, it is observed that the SMO Machine Learning algorithm provides 96.90% accuracy which is very high when compared to the accuracy of existing approaches. The results indicate that SMO outperforms the others in terms of accuracy and low error rate.

 

Author (s) Details

 

K. SrikanthA
Department of Computer Science & Engineering, G. Pulla Reddy Engineering College (A), Kurnool, Andhra Pradesh, India.

 

S. Zahoor Ul Huq
Department of Computer Science & Engineering, G. Pulla Reddy Engineering College (A), Kurnool, Andhra Pradesh, India.

 

A.P. Siva Kumar
Department of Computer Science & Engineering, JNTUA, Anantapuramu, India.

 

Please see the book here:- https://doi.org/10.9734/bpi/mcscd/v8/2986 

Decision Tree-based Machine Learning Algorithms to Classify Rice Plant Diseases: A Recent Study | Chapter 5 | Advanced Aspects of Engineering Research Vol. 16

 One of the most vital nutrients for humans on the planet is rice. India and China are two of the most rice-dependent nations on the planet. A variety of factors influence the production of this crop, including soil, water supply, pesticides employed, time period, and disease infection. One of the most important factors impacting rice yield and quality is rice plant disease (RPD). Farmers are always faced with the issue of recognising the type of rice plant disease and adopting appropriate corrective treatment. The most prevalent diseases that affect rice plants are Bacterial Leaf Blight (BLB), Brown Spot (BS), and Leaf Smut (LS). It is particularly difficult to diagnose this disease since the contaminated leaf must be processed by the human eye. In this chapter, we used machine learning techniques to describe and classify the RPD. To collect data on infected rice plants, we used the UCI Machine Learning repository. There are 120 photos of contaminated rice plants in the data set, containing 40 BLB images, 40 BS images, and 40 LS images. In the studies, decision tree-based machine learning algorithms RandomForest, REPTree, and J48 were used. To extract numerical characteristics from the infected photos, we used ColorLayoutFilter, which is provided by WEKA. 65 percent of the data is used for training and 35 percent is used for testing in the experimental analysis. According to the trials, the Random Forest algorithm works remarkably well in predicting RPD.

Author (S) Details

R. Sahith
CSE, CVR College of Engineering, Hyderabad, India.

P. Vijaya Pal Reddy
CSE, Matrusri Engineering College, Hyderabad, India.

Satyanarayana Nimmala
CSE, CVR College of Engineering, Hyderabad, India.

View Book :- https://stm.bookpi.org/AAER-V16/article/view/1990