A Review on Machine Learning Classification Technique for Bank Loan Approval

2019 ◽  
Author(s):  
R. Karthiban ◽  
M. Ambika ◽  
K.E. Kannammal
Keyword(s):  
Machine Learning ◽  
Bank Loan ◽  
Machine Learning Classification ◽  
Classification Technique ◽  
Loan Approval

Protein Classification using Machine Learning and Statistical Techniques

2019 ◽  
Vol 13 ◽  
Author(s):  
Chhote Lal Prasad Gupta ◽  
Anand Bihari ◽  
Sudhakar Tripathi
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Protein Classification ◽  
Classification Techniques ◽  
Random Forest Classification ◽  
Machine Learning Classification ◽  
Classification Technique ◽  
Human Enzyme ◽  
Clinical Verification ◽  
Enzyme Class

Background: In recent era prediction of enzyme class from an unknown protein is one of the challenging tasks in bioinformatics. Day to day the number of proteins increases that causes difficulties in clinical verification and classification; as a result, the prediction of enzyme class gives a new opportunity to bioinformatics scholars. The machine learning classification technique helps in protein classification and predictions. But it is imperative to know which classification technique is more suited for protein classification. This study used human proteins data that is extracted from UniProtKB databank. Total 4368 protein data with 45 identified features has been used for experimental analysis. Objective: The prime objective of this article is to find an appropriate classification technique to classify the reviewed as well as un-reviewed human enzyme class of protein data. Also find the significance of different features in protein classification and prediction. Method: In this article, the ten most significant classification techniques such as CRT, QUEST, CHAID, C5.0, ANN, SVM, Bayesian, Random Forest, XgBoost and CatBoost has been used to classify the data and know the importance of features. To validate the result of different classification technique, the accuracy, precision, recall, F-measures, sensitivity, specificity, MCC, ROC and AUROC has been used. All experiment has been done with the help of SPSS Clementine and Python. Result: Above discussed classification techniques give different results and found that the data are imbalanced for class C4, C5, and C6. As a result, all of the classification technique gives acceptable accuracy above of 60% for these classes of data, but their precision value is very less or negligible. The experimental results highlight that the Random forest gives highest accuracy as well as AUROC among all, i.e., 96.84% and 0.945 respectively. And also have high precision and recall value. Conclusion: The experiment conducted and analyzed in this article highlight that the Random Forest classification technique can be used for protein of human enzyme classification and predictions.

scholarly journals Student Intervention System using Machine Learning Techniques

2019 ◽  
Vol 8 (6S3) ◽  
pp. 2061-2065
Keyword(s):  
Machine Learning ◽  
Student Performance ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Student Records ◽  
Teaching Methodologies ◽  
Machine Learning Classification ◽  
Classification Technique ◽  
Learning Techniques ◽  
Vector Machines

Now a days, the educational institutes are adopting technologies for betterment of student’s quality, in respect to teaching methodologies etc. For which the huge information available with educational institutes can be used to predict student’s future in academics. The main objective of this paper is to predict the student performance in the examination and also to predict the student will graduate or not. Hence forth we are using statistical analytical method which is F1 score. F1 score or F measure is used to test the prediction accuracy by considering precision and recall to compute the score. To fulfill this requirement in machine learning, classification technique is used. The dataset used in this analysis contains 395 student records, having attributes, such as age, health, internet, school, father job, mother job etc. Using support vector machines (SVM), Decision Tree and Naïve Bayes (NB) classification algorithms F1 score is calculated for each algorithm. Based on the analysis done the F1 score of support vector machine is giving the better prediction compared to rest of the two algorithms.

scholarly journals Currency Recognition App

2021 ◽  
Vol 9 (VI) ◽  
pp. 435-437
Author(s):  
V. J. Chaudhari
Keyword(s):  
Machine Learning ◽  
Visually Impaired ◽  
Vision Loss ◽  
Vision Impairment ◽  
Daily Activities ◽  
Blind People ◽  
Android Application ◽  
Text To Speech ◽  
Machine Learning Classification ◽  
Classification Technique

Visually Impaired & foreign people are those people who have vision impairment or vision loss. Problems faced by visually impaired in performing daily activities are in great number. They also face a lot of difficulties in monetary transactions. They are unable to recognize the paper currencies due to similarity of paper texture and size between different categories. This money detector app helps visually impaired patients to recognize and detect money. Using this application blind people can speak and give command to open camera of a smartphone and camera will click picture of the note and tell the user by speech how much the money note is. This Android project uses speech to text conversion to convert the command given by the blind patient. Speech Recognition is a technology that allows users to provide spoken input into the systems. This android application uses text to speech concept to read the value of note to the user and then it converts the text value into speech. For currency detection, this application uses Azure custom vision API using Machine learning classification technique to detect currency based on images or paper using mobile camera.

scholarly journals Machine Learning Based Malware Detection: a Boosting Methodology

2020 ◽  
Vol 9 (4) ◽  
pp. 2241-2245
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Performance Enhancement ◽  
Support Vector ◽  
Training Set ◽  
Output Variable ◽  
Data Set ◽  
Machine Learning Classification ◽  
Classification Technique ◽  
Class Labels

Malware damages computers without user's consent; they cause various threats unknowingly, hence detection of these is very crucial. In this study, we proposed to detect the presence of malware by using the classification technique of Machine Learning. Classification type in Machine Learning requires the output variable to be of a categorical kind; it attempts to draw some conclusion from the ascertained values. In short, classification constructs a model based on the training set and values or predicts categorical class labels. In our work, we propose to classify the presence of malware by incorporating two chief classification algorithms, such as Support Vector Machine and Logistic Regression. The data set used for it was not satisfactory. Consequently, we tend to explore a data set that met our necessities and enforced Logistic Regression on the same moreover, we plotted a scatter-gram for the scope of visualization and incorporated XG-Boost for the performance enhancement. This study assists in analyzing the presence of malware by adopting a proper dataset and ascertaining pivotal attributes leading to this classification.

Sign in / Sign up

Export Citation Format

Share Document