WEKA Tool Research Articles

Performance Analysis of Soil Health Classifiers Using Data Analytics Tools and Techniques for Best Model and Tool Selection

One of the most crucial stages in the building of a Machine Learning (ML) model is the evaluation and analysis of classifier model performance. The agricultural sector is the economic backbone of India and needs extensions to provide solutions to the problems faced by the farmers. This paper presents agriculture soil health analysis using Machine Learning approaches for best model and tool selection and also bibliometric analysis to identify different sources and author’s keywords for finding the area of focus for proposed work. Models are built on SK-Learn, KNIME, WEKA and Rapid Miner tools using different ML algorithms. Nave Bayes, Random Forest (RF), Decision Tree (DT), Ensemble learning (EL), and k-Nearest Neighbor (KNN) are used to analyze soil data on these tools. Results show that Decision Tree model outperforms other algorithms, followed by RF algorithm which is a set of multiple Decision tree algorithms and SK-Learn tool gives better accuracy followed by WEKA tool then KNIME tool. Maximum accuracy obtained by Decision Tree algorithm is 98.40% using SK-Learn followed by KNIME tool with 73.07%, Maximum accuracy obtained by Naïve Bayes algorithm is 69.50% using SK-Learn followed by KNIME tool with 68.14%, maximum accuracy obtained by Random Forest algorithm is 85.00% using SK-Learn followed by 73.06% using WEKA tool, maximum accuracy obtained by Ensemble algorithm is 89.00% using SK-Learn followed by 73.06% using WEKA tool and for KNN it is 95.50% using SK-Learn followed by 71.85% using WEKA tool.

Penerapan Clustering K-Means untuk Pengelompokan Tingkat Kepuasan Pengguna Lulusan Perguruan Tinggi

One way to evaluate the quality of graduates is to provide questionnaires to graduate users, namely agencies / companies in the world of work in order to assess the quality of graduates of each university. Questionnaires for graduates are generally carried out by filling out the questionnaire form physically and then returning to the college. The K-Means method is one of several non-hierarchical clustering methods. Data clustering techniques are easy, simple and fast. Many approaches to creating clusters or groups, such as creating rules that dictate membership in the same group/group based on the level of similarity between the members of the group. Other approaches such as creating a set of functions to measure multiple criteria from grouping as a function of some parameters of clustering/grouping. From the results and discussions, K-Means clustering succeeded in grouping graduate user satisfaction data into three clusters where the results shown by manual calculations and applications showed the same results where clusterS C1 as many as 48 alternatives, C2 as many as 1 alternative, and C3 as many as 2 alternatives. In the sense that the application that is built successfully implements K-Means clustering is evidenced by the comparison of applications with weka tools has similar percentage results. In terms of the percentage of graduate users or alumni from STMIK PPKIA Tarakanita Rahmawati 94.12% Very satisfied, 1.96% Satisfied and 3.92% Quite Satisfied.

Implementasi Algoritma Data Mining J48 Untuk Klasifikasi Mahasiswa Yang Layak Mendapat Beasiswa PPA

The PPA Scholarship is a support for educational costs that is given to students who have taken at least semester 2 in Higher Education with consideration of limited economic capacity and have academic and non-academic achievements. In classifying students who are eligible for PPA scholarships, the management has difficulties because the limited PPA scholarships are not proportional to the number of students. One solution in classifying students who are eligible for PPA scholarships is to utilize the data of students who have received PPA scholarships in the previous year. However, in the classification process, data research is needed, one of the data research techniques is data mining. Where data mining is an interesting pattern extraction of large amounts of data [1]. One of the algorithms in data mining used in classification is the J48 algorithm. The J48 algorithm is the implementation of the C4.5 algorithm in the WEKA tools, besides the J48 algorithm is the decision tree implementation in the rapidminer tools. This algorithm is expected to help the management of the PPA scholarship at STMIK Budi Darma in classifying students who really deserve to receive the PPA scholarship. As a result, one of the criteria for a student to be classified as receiving a PPA scholarship is to have achievement

Usage of Machine Learning Algorithm Models to Predict Operational Efficiency Performance of Selected Banking Sectors of India

—It was an attempt to predict the impact of NPAs in the selected public (SBI, BoI, BoB, BoM, CBoI, AB, CB, AlB,) and private (AxB, ICB, HDFCB and KB) banking sectors from 2008 to 2019. The data was also used to predict operational performance efficiency of these banking sectors after extracting through machine learning (ML) algorithm models and statistical interpretation of prediction accuracy by using WEKA tool. We used different models viz. NaiveBayes (NB), BayesNet (BN), logistic regression (LgR), Sequential minimal optimization of Support Vector Machine regression (SMOreg), Linear Logistic Regression (SL), Classification via Regression (CR), LogitBoost (LB); Logistic Model Tree (LMT), Random Forest & Random tree (RF & RT), Pruned & unpruned decision tree C4 (J48), and Class implementing minimal cost-complexity pruning (Cart) related to 15 attributes viz. GNPA, NNPA, GDP, CPI, PSL, TL, STA, GDP-1, RR, CPI-1, TE, TP and USTA as numeric as well as Banks, Year, GNPA>6, and GNPA>7, as nominal categories of dataset where overall performance accuracy was determined. The algorithm model classification predicted the highest values were for LB (78.47%) and Cart (74.30%) followed by J48 (73.61%), CR (72.91%) and LMT (69.44%) and lowest value in SMO (34.72%) as per 10-fold cross validation test. Additionally, these predicted results may have valuable implications for Indian banking sectors. We evaluated the operational efficiency as cumulative performance for 12 banking sectors as per assumed cut off values of GNPA. It may be varied with other independent variables like credit risk parameters, etc. It is suggested in future to study with parameters of deposit collection and investment to determine credit risk of these banking sectors. Keywords—Indian banking sectors, Machine learning models, Non-performing assets, Operational efficiency, WEKA tool

Fast and accurate classifying model for denial-of-service attacks by using machine learning

A denial of service (DoS) attack is one of the dangerous threats to networks that Internet resources and services will be less available, as they are easily operated and difficult to detect. As a result, identifying these intrusions is a hot issue in cybersecurity. Intrusion detection systems that use classic machine learning algorithms have a long testing period and high computational complexity. Therefore, it is critical to develop or improve techniques for detecting such an attack as quickly as possible to reduce the impact of the attack. As a result, we evaluate the effectiveness of rapid machine learning methods for model testing and generation in communication networks to identify denial of service attacks. In WEKA tools, the CICIDS2017 dataset is used to train and test multiple machine learning algorithms. The wide learning system and its expansions and the REP tree (REPT), random tree (RT), random forest (RF), decision stump (DS), and J48 were all evaluated. Experiments have shown that J48 takes less testing time and performs better, whereases it is performed by using 4-8 features. An accuracy result of 99.51% and 99.96% was achieved using 4 and 8 features, respectively.

Detection and Investigation of DDoS Attacks in Network Traffic using Machine Learning Algorithms

The Internet of Things (IoT) represents the start of a new age in information technology (IoT). Objects (things) such as smart TVs, telephones, and smartwatches may now connect to the Internet. New services and software improve many consumers' lives. Online lessons based on COVID-9 are also included in child education devices. Multiple device integration is becoming more widespread as the Internet of Things (IoT) grows in popularity. While IoT devices offer tremendous advantages, they may also create network disruptions. This article summarises current DDoS intrusion detection research utilizing machine learning methods. This study examines the detection performance of DDoS attacks utilizing WEKA tools using the most recent NSL KDD datasets. Logistic Regression (LR), Naive Bayes (NB), SVM, K-NN, Decision Tree (DT), and Random Forest (RF) are examples of Machine Learning algorithms. Using K-Nearest Neighbors in the presented assessment (K-NN), accuracy was attained. Finally, future research questions are addressed.

Classification Model for Hepatitis B Disease Using Supervised Machine Learning Technique

Hepatitis B is the most common serious liver infection in the world and caused by the Hepatitis disease. This results in many people injure and deaths, many human life lost due to this disease. The Most countries around the world, including Ethiopia, have increased the number of patients. This has led to an increase in the number of life lose. However, it is frequently challenging to determine which specific environments lead to such factor. Various studies have been conducted to classify hepatitis B disease, and others are focusing on whether the peoples will live or die because of this disease. Furthermore, most of the studies conducted so far focused on hepatitis B disease prediction with fewer number of features. The study aims to classify the factors relevant to hepatitis B disease such as chronic and acute hepatitis B disease factors based on the independent variables collected from Arba Minch. The data for this study was collected from Arba Minch General Hospital. It covers ten years hepatitis B patient data record from the year 2002-2012 E.C. the preprocessed dataset has 14 attribute and 50032 instance. This study has been conducted using an experimental approach to determine the best- performing model. This study used the WEKA tool and Asp.Net programming language for implementation and analysis purposes. For this study, the researchers trained four different models, including J48, REP Tree, Bayes Net, and PART algorithms. Those models are selected based on a comprehensive study showed to select the best First style performing model. In this study, evaluation of the model was done using percentage split (80/20), and classification performance metrics was used in order to compare the models. The finding of this study displays that the J48 classifier outclasses then the rest of the classifiers with an accuracy of 85.5% on training data and 82.7% on test data. Based on this result, a system prototype was developed and tested that is accomplished of classifying features of hepatitis B disease. Keywords: Machine Learning, Classification Algorithm, J48, Hepatitis B Diseases DOI: 10.7176/CEIS/13-3-01 Publication date: May 31 st 2022

Towards a classification of sustainable software development process using manifold machine learning techniques

With the evaluation of the software industry, a huge number of software applications are designing, developing, and uploading to multiple online repositories. To find out the same type of category and resource utilization of applications, researchers must adopt manual working. To reduce their efforts, a solution has been proposed that works in two phases. In first phase, a semantic analysis-based keywords and variables identification process has been proposed. Based on the semantics, designed a dataset having two classes: one represents application type and the other corresponds to application keywords. Afterward, in second phase, input preprocessed dataset to manifold machine learning techniques (Decision Table, Random Forest, OneR, Randomizable Filtered Classifier, Logistic model tree) and compute their performance based on TP Rate, FP Rate, Precision, Recall, F1-Score, MCC, ROC Area, PRC Area, and Accuracy (%). For evaluation purposes, We have used an R language library called latent semantic analysis for creating semantics, and the Weka tool is used for measuring the performance of algorithms. Results show that the random forest depicts the highest accuracy which is 99.3% due to its parametric function evaluation and less misclassification error.

Evaluating the Performance of Supervised Machine Learning Algorithms in Breast Cancer Datasets

Breast cancer is the leading cause of mortality globally. Several attempts have been made to use data mining methodology together with machine learning techniques to develop systems that can detect or prevent breast cancer. In line with the reviewed paper; large datasets for illness analysis have been developed. In this study, the results of selected Machine Learning algorithms are compared: Decision Table, J48, SGD, bagging, and Naïve Bayes Updateable on Wisconsin Breast Cancer Original dataset was conducted using weka tools. Exploratory data analysis, pre-processed with supervised attribute selection and class order, was used to identify potential features to aid the performance of the chosen algorithms in classification. The empirical result showed that Decision Table explores greater likelihood (74% correctly classified instances, True Positive Rate of 0.752, False Positive Rate of 0.478, Precision of 0.77, receiver operating characteristic Area of 0.682) in terms of accuracy and efficiency compared with others. This study's comparison technique is thought to aid breast cancer detection.

Diagnosis of Breast Cancer Pathology on the Wisconsin Dataset with the Help of Data Mining Classification and Clustering Techniques.

Breast cancer must be addressed by a multidisciplinary team aiming at the patient's comprehensive treatment. Recent advances in science make it possible to evaluate tumor staging and point out the specific treatment. However, these advances must be combined with the availability of resources and the easy operability of the technique. This study is aimed at distinguishing and classifying benign and malignant cells, which are tumor types, from the data on the Wisconsin Diagnostic Breast Cancer (WDBC) dataset by applying data mining classification and clustering techniques with the help of the Weka tool. In addition, various algorithms and techniques used in data mining were measured with success percentages, and the most successful ones on the dataset were determined and compared with each other.

Peningkatan Performa Klasifikasi Machine Learning Melalui Perbandingan Metode Machine Learning dan Peningkatan Dataset

Classification using machine learning is an alternative that is widely used to classify data. There are various classification methods or also known as machine learning classification algorithms that can be used. However, to get the best classification results, we need a classifier that fits the dataset type to provide the best classification performance. In addition, the quality and quantity of data contained in a dataset also has an influence on the classification performance. In this study, several attempts were made to improve the classification performance of the dataset of Indonesian language exam questions at the elementary school level based on the category of difficulty level. The efforts made consist of improving the quality of the dataset and using the StringToWordVector filter algorithm to manage textual data, as well as the use of several classification algorithms such as the nave Bayes algorithm, Random Forest, and REPTree. Classification is done by using WEKA Tools. The results of the experiments carried out showed the highest performance increase of 15% after improving the quality of the dataset and using the right classification method.

The application of machine learning to predict genetic relatedness using human mtDNA hypervariable region I sequences.

Human identification of unknown samples following disaster and mass casualty events is essential, especially to bring closure to family and friends of the deceased. Unfortunately, victim identification is often challenging for forensic investigators as analysis becomes complicated when biological samples are degraded or of poor quality as a result of exposure to harsh environmental factors. Mitochondrial DNA becomes the ideal option for analysis, particularly for determining the origin of the samples. In such events, the estimation of genetic parameters plays an important role in modelling and predicting genetic relatedness and is useful in assigning unknown individuals to an ethnic group. Various techniques exist for the estimation of genetic relatedness, but the use of Machine learning (ML) algorithms are novel and presently the least used in forensic genetic studies. In this study, we investigated the ability of ML algorithms to predict genetic relatedness using hypervariable region I sequences; that were retrieved from the GenBank database for three race groups, namely African, Asian and Caucasian. Four ML classification algorithms; Support vector machines (SVM), Linear discriminant analysis (LDA), Quadratic discriminant analysis (QDA) and Random Forest (RF) were hybridised with one-hot encoding, Principal component analysis (PCA) and Bags of Words (BoW), and were compared for inferring genetic relatedness. The findings from this study on WEKA showed that genetic inferences based on PCA-SVM achieved an overall accuracy of 80–90% and consistently outperformed PCA-LDA, PCA-RF and PCA-QDA, while in Python BoW-PCA-RF achieved 94.4% accuracy which outperformed BoW-PCA-SVM, BoW-PCA-LDA and BoW-PCA-QDA respectively. ML results from the use of WEKA and Python software tools displayed higher accuracies as compared to the Analysis of molecular variance results. Given the results, SVM and RF algorithms are likely to also be useful in other sequence classification applications, making it a promising tool in genetics and forensic science. The study provides evidence that ML can be utilized as a supplementary tool for forensic genetics casework analysis.

IMPLEMENTASI DATA MINING MENGGUNAKAN METODE NAIVE BAYES DENGAN FEATURE SELECTION UNTUK PREDIKSI KELULUSAN MAHASISWA TEPAT WAKTU

The Education Efficiency Rate (AEE) is one of the parameters of the quality of the education program. The quality is measured based on 7 main standards, one of which is students and graduates. Meanwhile, to predict students' graduation rates accurately based on manually owned data set characteristics is very difficult. Data Mining by Naïve Bayes method was chosen to find patterns in analyzing and predicting timely graduation of students. As for the test will be done by comparing the initial dataset and dataset characteristics using the algorithm attribute selector Gain Ratio Attribute with the help of tools WEKA. The results showed that there was a difference to the accuracy of the results, and the larger ROC or AUC curves on the dataset characteristics using the selector attribute by using the Gain Ratio Attribute, although not very significant. And the result of this research yield 81% accuracy level with precision equal to 83.563% and recall 88.41%. The method used is included in Good Classification and will become the reference of the college management side, to address the problems that may arise in the decrease of the quality of education (e.g. decrease ratio of lecturers with students).

Application of Data Mining in Performance Management of Public Hospitals

With the rapid development of computer technology, information technology covers all aspects of daily life, and the medical industry is also paying more attention to information construction. Conventional management methods have been unable to further improve the hospital’s management capabilities. At the same time, countries that are better in terms of hospital management practices have set a benchmark for mainland hospitals and reformed hospitals in order to stand out in the future. In addition to evaluating the economic benefits and work efficiency of doctors, hospitals must also consider that hospitals, as a special service industry, cannot be measured by economic indicators. Therefore, there is a multiparty game in the performance appraisal of hospitals, and it is necessary to consider not only economic factors but also the characteristics of public services. This article is based on the case of a large domestic tertiary hospital, combined with the hospital’s performance management reform plan, through the design idea of performance management and incentive performance pay distribution, using data mining technology as an auxiliary means. It successfully helped the hospital complete the performance and incentive performance pay aspects reform. The main research work of this paper is divided into the following three aspects. (1) Using data mining technology, according to each nursing unit’s workload, risk level, the difficulty of internship, and other objective factors in the past year for patient outpatient visits, surgery implementation, critical first aid, etc., are classified in line with the actual situation and provide a reliable basis for the reasonable and efficient allocation of hospital human resources. (2) In the performance management system, we integrate the third-party data mining tool weka to assist in the evaluation of the performance distribution plan and the calculation of the follow-up incentive performance pay. (3) We use the mathematical model of data mining to measure and evaluate the reasonableness of historical workload and performance appraisal, determine a new incentive performance pay distribution model, and use the software as a calculation tool for the internal distribution of performance wages to provide monthly incentive performance wage statistics in the future.

Comparative analysis of HAR datasets using classification algorithms

In the current research and development era, Human Activity Recognition (HAR) plays a vital role in analyzing the movements and activities of a human being. The main objective of HAR is to infer the current behaviour by extracting previous information. Now-a-days, the continuous improvement of living condition of human beings changes human society dramatically. To detect the activities of human beings, various devices, such as smartphones and smart watches, use different types of sensors, such as multi modal sensors, non-video based and video-based sensors, and so on. Among the entire machine learning approaches, tasks in different applications adopt extensively classification techniques, in terms of smart homes by active and assisted living, healthcare, security and surveillance, making decisions, tele-immersion, forecasting weather, official tasks, and prediction of risk analysis in society. In this paper, we perform three classification algorithms, Sequential Minimal Optimization (SMO), Random Forest (RF), and Simple Logistic (SL) with the two HAR datasets, UCI HAR and WISDM, downloaded from the UCI repository. The experiment described in this paper uses the WEKA tool to evaluate performance with the matrices, Kappa statistics, relative absolute error, mean absolute error, ROC Area, and PRC Area by 10-fold cross validation technique. We also provide a comparative analysis of the classification algorithms with the two determined datasets by calculating the accuracy with precision, recall, and F-measure metrics. In the experimental results, all the three algorithms with the UCI HAR datasets achieve nearly the same accuracy of 98%.The RF algorithm with the WISDM dataset has the accuracy of 90.69%,better than the others.

Comparative Study for Prediction of Low and High Plasma Protein Binding Drugs by Various Machine Learning-Based Classification Algorithms

<p>In the drug discovery path, most drug candidates failed at the early stages due to their pharmacokinetic behavior in the system. Early prediction of pharmacokinetic properties and screening methods can reduce the time and investment for lead discoveries. Plasma protein binding is one of these properties which has a vital role in drug discovery and development. The focus of the current study is to develop a computational model for the classification of Low Plasma Protein Binding (LPPB) and High Plasma Protein Binding (HPPB) drugs using machine learning methods for early screening of molecules through WEKA. Plasma protein binding drugs data was collated from the Drug Bank database where 617 drug candidates were found to interact with plasma proteins, out of which an equal proportion of high and low plasma protein binding drugs were extracted to build a training set of ~300 drugs. The machine learning algorithms were trained with a training set and evaluated by a test set. We also compared various machine learning-based classification algorithms i.e., the Naïve Bayes algorithm, Instance-Based Learner (IBK), multilayer perceptron, and random forest to determine the best model based on accuracy. It was observed that the random forest algorithm-based model outperforms with an accuracy of 99.67% and 0.9933 kappa value on training set and on test set as compared to other classification methods and can predict drug plasma binding capacity in the given data set using the WEKA tool.</p>

Study and Application of Industrial Thermal Comfort Parameters by Using Bayesian Inference Techniques

This paper focuses on the use of Bayesian networks for the industrial thermal comfort issue, specifically in industries in Northern Argentina. Mined data sets that are analyzed and exploited with WEKA and ELVIRA tools are discussed. Thus, networks giving the predictive value of thermal comfort for different pairs of indoor temperature and humidity values according to activity, time, and season, verified in the workplace, were obtained. The results obtained were compared to other statistical models of linear regression used for thermal comfort, thus observing that comfort temperature values are within a same range, yet the network offered more information since a range of options for interior design parameters (temperature/relative humidity) was offered for different work, time, and season conditions. Additionally, if compared with static models of heat exchange, the contribution of Bayesian networks is noted when considering a context of actual operability and adaptability conditions to the environment, which is promising for developing thermal comfort intelligent systems, especially for the development of sustainable settings within the Industry 4.0 paradigm.

Using Decision Trees to Predict Critical Reading Performance.

In Colombia, all undergraduate students, regardless of the professional training program they take, must complete the general competencies sections of the Saber Pro exam that include Critical Reading, Quantitative Reasoning, Citizen Competencies, Written Communication, and English. This paper presents the application of the classification technique based on decision trees in the prediction of the performance in the Critical Reading section presented by the students of the Pontificia Universidad Javeriana Cali in the years 2017 and 2018. The CRISP methodology was used. From the socioeconomic, academic and institutional data stored in the ICFES databases, a data repository was built, cleaned and transformed. A mineable view composed of 2052 records and 17 attributes was obtained. The J48 algorithm of the Weka tool was used to build the decision tree. The score obtained in the Critical Reading section of the Saber Pro exam was taken as a class. According to the results obtained, the Philosophy, Applied Mathematics, and Medicine programs stood out for having the best performance in this test. Among the predictive variables associated with performance in the Critical Reading skill are the faculty, the age group and the student's transportation index, as three important variables related to the good or low academic performance of the students of the Universidad Javeriana Cali. The knowledge generated in this research is constituted in quality information to support the decision-making process of the university directives in order to improve the quality of the higher education offered in this institution.

Security Analysis of DDoS Attacks Using Machine Learning Algorithms in Networks Traffic

The recent advance in information technology has created a new era named the Internet of Things (IoT). This new technology allows objects (things) to be connected to the Internet, such as smart TVs, printers, cameras, smartphones, smartwatches, etc. This trend provides new services and applications for many users and enhances their lifestyle. The rapid growth of the IoT makes the incorporation and connection of several devices a predominant procedure. Although there are many advantages of IoT devices, there are different challenges that come as network anomalies. In this research, the current studies in the use of deep learning (DL) in DDoS intrusion detection have been presented. This research aims to implement different Machine Learning (ML) algorithms in WEKA tools to analyze the detection performance for DDoS attacks using the most recent CICDDoS2019 datasets. CICDDoS2019 was found to be the model with best results. This research has used six different types of ML algorithms which are K_Nearest_Neighbors (K-NN), super vector machine (SVM), naïve bayes (NB), decision tree (DT), random forest (RF) and logistic regression (LR). The best accuracy result in the presented evaluation was achieved when utilizing the Decision Tree (DT) and Random Forest (RF) algorithms, 99% and 99%, respectively. However, the DT is better than RF because it has a shorter computation time, 4.53 s and 84.2 s, respectively. Finally, open issues for further research in future work are presented.

IMPROVING STUDENTS PERFORMANCE PREDICTION USING MACHINE LEARNING AND SYNTHETIC MINORITY OVERSAMPLING TECHNIQUE

Classification under supervision is the most common job that performed by machine learning. However, most Educators were worried about the rising evidence of student academic failures in university education. So, this study presents a supervised classification strategy of machine learning algorithm using an actual dataset contains 44 students, fourteen attributes for three previous academic years. We have proposed features that show the relationship among three main subjects which are, calculus, mathematical analysis, and control system in the education course. The objective of this study is to identify the student’s failure in the control system subject and to enhance his performance by Multilayer Perceptron (MLP) algorithm. The dataset is unbalanced, which causes overfitting of the results. Synthetic Minority Oversampling Technique has applied to a dataset for obtaining balance dataset using Weka tool. Several standard metrics used to evaluate the classifier results. Therefore, the suitable results occurred after applying SMOTE with an accuracy of 76.9%.