Search

Fake news is a type of essential problem on social media. The rapid circulate of fake news has an ability for disastrous influences on human beings and the society. Thus, it becomes more useful to detect fake news on social sites or internet. Recently, many models have been developed to detect the fake news from the publicly available datasets. In this paper discussed the various machine learning algorithms and their performance analysis on two different news data. The proposed framework contains two step process. In the first step, clean the data and extracted features by TF-IDF and Hashing Vectorizer. In the second step, machine learning algorithms (Logistic regression, Decision Tree, Random Forest, Multinomial Naive Bayes, and Passive Aggressive classifier) have been applied in an effective and efficient manner. Comparative analysis revealed that the optimal performance is achieved by the Logistic regression and Passive aggressive classifier, 95.45% and 97.35% respectively for two public datasets. [ABSTRACT FROM AUTHOR]

The Bayesian two-rule automatic adaptive quadrature (B2AAQ) of one-dimensional Riemann integrals is critically driven by the a priori input provided by the user. Conditions enabling straightforward elementary input of problem parameters are defined that result in either a single subrange decision tree or a forest of subrange decision trees. This secures a B2AAQ implementation characterized by robustness, reliability and efficiency, together with a significant extension of the flexibility of use as compared to the QUADPACK package, which is the core of the computational integration chapters of the major computer libraries worldwide. [ABSTRACT FROM AUTHOR]

In the maintenance and improvement of bridges performance in Padang City which is located in a disaster, it is necessary to evaluate the infrastructure. In this study, a visual evaluation was conducted to assess the condition of the bridges referring to the Bridges Management System. From the results, the visual observation study from 2019 to 2021 the condition of the bridges and the consideration of budget constraints, the treatment program is not following the BMS decision tree. Nevertheless, it can be concluded that in general the condition of the bridgess in Padang City is in good condition and requires routine maintenance every year in bridges inspections. Based on the results of the evaluation conducted, the bridges in Padang City is in good condition and ready for the disaster mitigation process and fulfills the need for land transportation. [ABSTRACT FROM AUTHOR]

This preliminary research article presents an alternative formulation of machine learning (ML) models for the prediction of the higher heating value (HHV) of biomass. The proposed method aims to improve the accuracy of the decision tree model (DT) while preserving its computational performance. It used 21 HHV prediction correlations augmented with the ML model formulation process rather than the sole use of raw experimental data as in a conventional approach. The method was also tested and compared with other two ML models, including support vector machine (SVM) and artificial neural network (ANN), with 148 experimental data sets. The test results showed that integration of the proposed method with DT had 2.72 times higher accuracy than the conventional model based on the R2 criterion with comparative computational performance. [ABSTRACT FROM AUTHOR]

Survival analysis is a branch of statistics deals to analyze and model the time to event data. To tackle this censoring problem, statistical strategies have been widely explored in the literature. To deal with survival data, traditionally many methods including Nonparametric, Semiparametric, Parametric and Bayesian Models were incorporated. But these methods require some assumptions, but many machine learning techniques (Survival Decision Tree, Survival Random Forest, Naive Bayes and Logistic Regression) are designed to handle survival data and other challenges that may emerge in real-time data. In this paper, the author elaborates significance of these methods for survival data and identified important variables for the specified event for three real time data. Important variables were prioritized using random forest's variable selection methods, and the results were compared to survival approaches. Supervised Machine Learning Methods were applied, and survival analysis was used to validate them. [ABSTRACT FROM AUTHOR]

This paper studies Health of individuals, an ever needed, relevant, fertile and in addition an interesting study for a human being. It is a study of the health status of individuals using machine learning models-logistic regression, Decision Tree and Neural Networks-by questionnaire-based data collection and found the factors which are major contributing aspects towards an individual's health and lifestyle. The questionnaire used is a simple one which is shared to friends, colleagues and professional acquaintances through social media. The collected data is analyzed using Machine Learning models – Logistic regression, Decision tree and Neural Network – and found factors which are contributing in a major way towards an individual's mental as well as physical health in the long run. The analysis is performed using R platform. [ABSTRACT FROM AUTHOR]

Examining Students' Opinions about NDUM e-Learning during COVID-19 is a study to improve the NDUM e-Learning system based on Sentiment Analysis approach. Firstly, surveys are distributed among the students to get feedback related to NDUM e-Learning. From the feedback, useful data can be collected for data analytic process. CRISP-DM framework and Opinion Mining architecture is used for this study. Next, Sentiment Analysis is implemented to classify the student's feedback into "positive" and "negative" sentiment. Further, two machine learning algorithms (i.e. Decision Tree and SVM) are used to construct the classifier model. Finally, results are displayed in graphical form to illustrate findings of the study. The result provides an overview of the level of satisfaction, suitability, system improvement, suggestions and the overall impact of the use of NDUM E-Learning during the pandemic. first, second, and third level headings (first level heading) [ABSTRACT FROM AUTHOR]

Mathematical programming techniques determine the optimal functional configuration of a Wireless Sensor Network (WSN). However, the high computational complexity of these techniques has been regarded as a Non-Polynomial problem. Hence, Machine Learning (ML) approaches are used for WSN parameter prediction with improved accuracy and less computing complexity. This study aims to predict the reliability of clustering algorithms in WSNs using supervised ML classification approaches. ML algorithms, namely, decision tree and K-nearest neighbor classifications are implemented on the obtained dataset to predict the reliability of clustering in WSNs on the basis of high packet delivery ratio, low delay, and high residual energy. The reliability parameter accepts binary values, where zero represents the absence of reliability and one represents the presence of reliability metrics. Then the predictions from each classifier are compared with one another. The results show that the accuracy rate of the decision tree is 97.98% and the error rate is 2.02% which shows that the decision tree performs better than the K-nearest neighbor in predicting the reliability of the proposed approach. [ABSTRACT FROM AUTHOR]

Classification of a person's cognitive state is important in many applications. The aim of this work is to develop a reliable classifier for predicting the cognitive state of the brain while performing various tasks. This dataset was recorded using a Muse headset with 10-20 EEG electrode placements and four different electrodes. The cognitive state of ten students was recorded while performing various tasks, such as mental arithmetic, reading technical articles, listening to technical podcasts, surfing the Internet, and resting with eyes open or closed. The EEG dataset is preprocessed and feature sets of five signals alpha, beta, gamma, delta and theta are selected for prediction. This dataset is trained by any machine learning algorithm such as decision trees, naive Bayes, and support vector machines. All machine learning algorithms are then embedded into a Stacking Ensemble Classifier with 10-fold cross-validation to predict the cognitive state of brain signals and classify them as high and low. Compared with existing algorithms, the method achieves an overall accuracy rate of 96%. [ABSTRACT FROM AUTHOR]

Aim-The aim of the study is to perform innovative detection of lung cancer using the Decision Tree classifier and also comparing it with the K-Nearest Neighbor classifier. Materials and methods-The lung cancer database includes records 32 samples (patients) and is therefore compiled with 32 ∗ 6 numerical data. The G power for samples is calculated from clincalc which contains two different groups where group 1 is taken as (n1=16) and for group 2 (n2=16), alpha (0.05), power (80 %) and enrollment ratio. Results-Implementation based on the MATLAB toolbox is done on CT lung images and the classification of these images is performed. In the proposed method, D-Tree numbers of samples are selected for each iteration and 90 % phase accuracy is obtained. There is a significant difference in Accuracy rate (P=0.072). Conclusion-The results of the study suggest that the accuracy of the decision tree algorithm is significantly higher than the nearest k-neighboring algorithm. [ABSTRACT FROM AUTHOR]

The study aims to evaluate the performance of the Music Genre Prediction System using a Novel Support Vector Machine and Decision Tree. The MARSYAS website provided the GTZAN dataset utilised in this investigation, which is comprised of one thousand.au-formatted music files and is intended for use in Music Information Retrieval. It is currently considered the gold standard dataset. Mel-frequency cepstralcoefficients (MFCC) are retrieved from music files and used to make predictions about the genre. All steps, from analysing data to training a model to testing it, take place within Jupyter. SPSS is used to analyse the mean accuracies of two algorithms side-by-side. Accuracy, precision, etc., numbers came out differently depending on the size of the input data set. SVM and Decision Tree are used for classification, with N equal to 20 for each of the two groups (proposed and comparative). The value of the pre-test achieved is 0.08. This research shows that compared to the Decision Tree method, Novel SVM is more effective. In the Research study, SVM with 81.10% accuracy is found more effective, efficient, and faster when compared to the Decision Tree with 59.88% accuracy. [ABSTRACT FROM AUTHOR]

The purpose of this research is to compare the performance of logistic regression (LR) and decision tree boosting in landslide prediction (BODT). The Components and Procedures: Boosting of Decision Trees showed a higher recognition rate and enabled the precise detection of landslides, resulting in fewer false alarms than alternative machine learning methods. A landslide-monitoring system has been described and developed by comparing Decision Trees with Logistic Regression. The sample size was calculated to be 28 people in each group using the G power statistic. With two groups and 14 samples in each, the estimated pre-test power is 87%. Logistic Regression (LR) achieves 62% accuracy while Boosting of Decision Trees (BODT) achieves 87% accuracy in predicting landslides on the dataset. The results show that Decision Tree is superior to Logistic Regression. Results indicate that Boosting of Decision Trees outperforms Logistic Regression in terms of accuracy and precision, hence this method should be used instead. [ABSTRACT FROM AUTHOR]

The primary goal of this study is to predict fetal heart disease detection using Magnetic Resonance Imaging (MRI) scan images and comparing with decision tree (DT) classifiers to improve accuracy, specificity, and disease type. Materials and Methods: In this research 20 Magnetic Resonance Imaging (MRI) scan images in a view of samples of SVM (N=10) and DT (N=10). The sample size is calculated for each group with 80% of G power, 95% confidence interval, and 0.05 error rate (Alpha). Results: The proposed method SVM classifier achieves a high accuracy of 93%, specificity of 89% and DT classifier 82% accuracy, 79% specificity. The significance rate of accuracy is (p=0.001) and specificity is (p=0.018). Conclusion: The Novel Support Vector Machine classifiers have achieved significantly better accuracy, specificity when compared with the decision tree (DT) classifier to predict fetal heart disease. [ABSTRACT FROM AUTHOR]

The primary goal of this study is to compare the performance of the Novel Random Forest (RF) algorithm, Decision Tree (DT), and Logistic Regression in forecasting loan default (LR). The 346-record loan dataset that Novel Random Forest is associated with. It has been suggested and assessed how well the revolutionary methods of Random Forest, Decision Tree, and Logistic Regression can forecast loan defaults in the banking and finance industry. There were a total of 17 participants in each study group. The classifier's efficacy in terms of accuracy and precision is measured and documented. On this dataset, the Logistic Regression model predicts loan default with an accuracy of 81%, while the Decision Tree model achieves 93% and the Random Forest model achieves 95%. (p 0.031) is statistically significant. That's why it's clear that Novel Random Forest outperforms both Decision Tree and Logistic Regression. When compared to Decision Tree and Logistic Regression, Novel Random forest has superior accuracy and precision. [ABSTRACT FROM AUTHOR]

The fundamental objective of this study is to evaluate and contrast the performance of two innovative classification algorithms, namely Random Forest and Decision Tree. Each of the random forest and choice tree exercises had 20 participants. The academic success of a student in the past might serve as an indication of the possible future achievements the student will have. The purpose of this research is to come up with strategies that can accurately forecast how well a kid will do academically. The use of decision trees and random forests as methods for forecasting student success are now both considered to be well-established methodologies. Each of the research groups had a total of 72 participants. The accuracy of predictions made using this dataset ranges from 88.2 percent when utilising the time-tested Decision tree to 91.7 percent when utilising the innovative Random forest classifier. 0.03 is the most significant part of the fraction. The Random Forest algorithm is better to the decision tree approach for this reason. The innovative decision tree known as the random forest performs far better than its predecessor, the tried-and-true decision tree. [ABSTRACT FROM AUTHOR]

Predicting the onset of cardiovascular disease is the goal. Images are separated into labelled and unlabeled categories using two machine learning algorithms: Decision Tree and Logistic regression. In order to efficiently and accurately analyse labelled pictures with G power in 80% and threshold 0.05 percent, CI 95% mean and standard deviation, the sample size was iterated 10 times from n =5 in Decision Tree and n = 5 in Logistic Regression. Accurate predictions and classifications of values from cardiac patient data have been generated in this study by comparing the predictive and classifying abilities of Decision Tree and Logistic Regression. The accuracy of Decision Tree (72.40%) is statistically significant (p0.05) greater than that of Logistic Regression (67.59%). Decision Tree outperforms Logistic Regression in predicting cardiovascular disease. [ABSTRACT FROM AUTHOR]

The core of this work presents an assembly method of EEG signals for the early detection of brain tumors using a novel support vector machine (SVM) algorithm compared with a decision tree algorithm Materials and methods: Collected from UCI repository 1472 samples contain 19 attributes. Early detection of brain tumors is performed using two groups, where group 1 is a SVM and group 2 is a decision tree. For the analysis of groups 1 and 2, 40 samples were used. Results: The accuracy of the SVM algorithm was 93%, while the accuracy of the decision tree was 82%. A significant value of 0.037 (P<0.05) was obtained and determined by independent samples test. Conclusion: The support vector machine algorithm has significantly higher accuracy than the decision tree algorithm. [ABSTRACT FROM AUTHOR]

The purpose of this research is to use the Decision Tree algorithm and the Logistic Regression model to the task of classifying mobile pricing ranges. The model's accuracy for mobile pricing range validation was tested via N=10 sample iterations using a combination of the Decision Tree algorithm and a Logistic Regression model with G power (value=0.8). Results: Decision Tree model accuracy results have the ability to reach (84.233 percent), whereas Logistic Regression model accuracy results have the capacity to reach (79.80 percent). Logistic Regression outperformed the Decision Tree by a significant margin (p=0.002).Conclusion: Decision Tree outperforms Logistic Regression in terms of performance and significance in this study's validation of mobile price range. [ABSTRACT FROM AUTHOR]

The study's primary objective is to compare the efficacy of the state-of-the-art SVM method for image prediction with that of KNN, Logistic Regression, Random Forest, and Decision Tree. The UCI Machine Learning Laboratory provides a total of 569 samples. Groups like SVM, KNN, Decision Tree, Random Forest, and Logistic Regression are used to the samples after they have been separated into benign and malignant cells so that their respective performances may be compared. G power calculation is used to determine how many samples are needed for this analysis. The maximum acceptable error is set at 0.5, and the minimum power of analysis is set at 0.8. Predictions made using Logistic Regression appear to have a higher accuracy(95%) than those made using SVM, KNN, Decision Tree, or Random Forest(92%,90%,85%, and 91%). This proposed system has a probability importance of 0.55. The Wisconsin dataset was used to compare Logistic Regression against SVM, KNN, Decision Tree, and Random Forest for the detection of breast cancer. [ABSTRACT FROM AUTHOR]

The purpose of this research is to evaluate the performance of four distinct approaches to prediction—namely, Logistic Regression (LR), Decision Tree (DT), K Means Algorithm (KMA), and Support Vector Machine (SVM) Classification—in order to determine which one yields the most accurate results. The Following are the Components and Methods: When testing the Classification technique, a dataset consisting of 778 items is employed. In the subject of education, the Logistic Regression (LR), K-Means, Decision Tree, and Support Vector Machine (SVM) are all viable frameworks that have been suggested and developed for the College Recommendation system. K-Means was the first of these frameworks to be built. Through the use of G power, we were able to establish that we need 55 people for each of the conditions. Both the precision and accuracy of the classifiers have been analysed and recognised. Through the use of G Power, we were able to establish that each of our groups required 55 individuals. The College dataset had a sample size of 303 students, 76 attributes, and a few blanks in addition to those numbers. A clinical study was conducted to establish the appropriate size of the sample, and the following were the findings: 80 percent predictive power on the pretest, 0.05 alpha, and a 1. When applied to the College Recommendation System data set, the results demonstrate that the K-Means classifier produces the same group that it predicts (50 percent). This is also the case for Logistic regression (86 percent), Decision Tree (88 percent), K-Means (50 percent), and Support Vector Machine (50 percent) (85 percent). The value assigned to significance is zero. Consequently, DT performs better than LR, SVM, and K-Means. The findings indicate that Decision Tree offers greater performance in terms of precision and accuracy when compared to SVM, LR, DT, and K-Means. This is shown by the fact that Decision Tree. [ABSTRACT FROM AUTHOR]

The goal is to anticipate cardiac arrest in heart disease patients. Machine learning methods like SVM and decision tree categorise photos (DT). To effectively and reliably analyse labelled pictures with G power of 80%, threshold 0.05 percent, CI 95 percent mean and standard deviation, SVM and Decision Tree sample sizes of n=5 were iterated 10 times. The Support Vector Machine (SVM) outperformed the Decision Tree (DT) in predicting and categorising cardiac patients' data with a p-value of 0.05. Support Vector Machine predicts cardiomyopathy risk better than Decision Tree. [ABSTRACT FROM AUTHOR]

The goal of this work is to improve upon Logistic Regression's classification accuracy for student performance by 97 percent using a Decision Tree. The sample sizes of the decision tree (10 nodes) and the logarithmic regression (10 observations) are both determined using an online sample size calculator. A student's overall performance is determined by their combined scores in reading, writing, and arithmetic. The proposed method employs a decision tree to categorise student performance. Logistic regression is used to evaluate the results of the decision tree. Students' academic progress is evaluated and compared based on their test scores in mathematics, reading, and writing. Logistic Regression has a lesser accuracy than Decision Tree (81%). (95 percent). A highly substantial association was found. The p-value for tree and logistic regression in two-tailed t-tests is 0.001. (p0.05). Classifying student achievement looks to be an area where the Decision Tree excels above Logistic Regression. [ABSTRACT FROM AUTHOR]

Metrics such as accuracy, recall, and f-score will be used to compare the results of a decision tree approach to detecting lung cancer with those achieved by a novel polynomial support vector machine (SVM). The researchers have access to 1339 lung cancer patient samples because to the Kaggle collection. In order to determine the G power for samples, we need clinical data, which consists of two groups: group 1, with (n1=670) and group 2, with (n2=670), both with (alpha=0.05) and (power=80%) values. The f-score, recall, and precision were all computed. The collected data is split into two collections, one including 937 samples (representing 75% of the total) and the other containing 402 samples (representing the remaining 25%). (representing 25 percent). When comparing the decision tree with the polynomial support vector machine (SVM), the decision tree performed better, with values of 78.36%, 80.66%, and 79.54% for accuracy, recall, and f-score, respectively, while the innovative polynomial SVM performed worse, with values of 63.63%, 70%, and 66.66%. P0.001 is determined to be the threshold of significance. Based on the calculated f-score, we may conclude that the decision tree outperforms the novel polynomial SVM. [ABSTRACT FROM AUTHOR]

The purpose of this research is to compare and contrast how well the random forest algorithm and the decision tree method perform in classifying fire and smoke photographs. With a g power of 0.8 and an alpha of 0.05, we find that out of a total of 4000 photos, 2000 depict fire and the remaining 2000 depict smoke. In this case, we split the dataset into a training set (n=3200, or 80%) and a validation set (n=800, or 20%). Classification tasks are executed with the help of the Sklearn machine learning package in Python. Precision, recall, f score, and accuracy numbers are some of the metrics used to measure an algorithm's effectiveness. When compared to the Decision Tree algorithm's 90.54, 90.00, 90.9, and 89.70 percent accuracy, F-score, recall, and precision, Random Forest achieved 97.42, 97.28, 97.43, and 97.15 percent values, respectively (p0.001(2-tailed)). The results of this research show that the random forest method outperforms the decision tree algorithm by a wide margin. [ABSTRACT FROM AUTHOR]

The goal of this study is to assess the efficacy of two different intrusion detection systems, one based on the K-means cluster method (Group 1) and another based on the Decision Tree algorithm (Group 2). Substances and Techniques: In order to create a model for an intrusion detection system that can identify a grayhole assault, the NS2 tool was used to construct a data set containing 90 nodes and 12 network layer attributes. The IDSs were modelled using K-means clustering and Decision tree techniques, and then analysed using the SPSS software package with 19 samples in each group. Good performance of IDS is shown by the significance p0.05 (Accuracy - 0.047; Detection rate - 0.026). The results showed that the IDS using the K-means cluster classifier had an accuracy of 99.73 percent and a detection rate of 99.84 percent, while the IDS using the Decision tree had an accuracy of 99.49 percent and a detection rate of 99.57 percent. This concludes that the K-means cluster algorithm-based intrusion detection system outperforms the Decision tree algorithm-based IDS by a wide margin. [ABSTRACT FROM AUTHOR]

The aim of this research is to use the Decision Tree classifier to identify lung cancer in scanned pictures and compare its performance to that of the Support Vector Machine classifier. Methods and materials The lung cancer database contains information on 60 samples (patients). Clincalc's sample G power has two groups, with alpha (0.05), power (80%), and enrollment ratio (n1 = 30) for group 1 and (n2 = 30) for group 2. Decision Tree outperforms standard SVM classifiers in terms of accuracy, with a 95.13 percent success rate. According to the results of this study, the decision tree method is more accurate than the Support Vector Machine classifier. [ABSTRACT FROM AUTHOR]

To enhance lung cancer CT scan picture categorization utilising algorithms. Materials and Methods: Training dataset (n=185 [70%]) and test dataset (n=80 [30%]) are created from 265 lung cancer CT scan pictures. Weka tool uses Decision tree algorithm and KNN classifier for classification. Results and Discussions: Decision tree method classified lung cancer CT scan pictures with 99 percent accuracy and KNN classifier with 92 percent. Statistically, decision tree algorithms and KNN classifiers meet independent sample T-Test value (p<0.005) with G-power estimate of 0.8. Conclusion: The Decision tree approach outperforms the KNN classifier in lung cancer CT scan image categorization. [ABSTRACT FROM AUTHOR]

To use tweets about finance to help decide on a financial choice. To forecast if financial tweets are positive or negative, we use a new Decision Tree that is better at getting the right results compared to Random Forest. The proposed way of doing things looks at 10 examples in each of two groups. We want to make sure we have enough power to detect any differences between the groups, so we aim for an 80% chance of finding a difference if one exists. We also set a significance level of 0. 05, which means we want to be fairly confident in our findings. The Novel Decision Tree is more accurate (96. 4%) than the Random Forest (92. 7%) in predicting the sentiments of financial tweets. The Novel Decision Tree Algorithm is much better than the Random Forest at guessing the feelings in financial tweets. [ABSTRACT FROM AUTHOR]

The purpose of this research is to enhance the reliability of Parkinson's disease forecasts by implementing and comparing various machine learning classifiers for this purpose. Predictions of Parkinson's illness are made using the Decision Tree method and the Naive Bayes algorithm in this study. The evaluation was carried out on a dataset consisting of 757 records. After ten iterations, the best prediction for each method was found for identifying Parkinson's disease symptoms in a programming experiment. About 80% of the available G-force is put to good use. An independent samples t-test compares two methods for making Parkinson's disease predictions and finds that the novel Decision Tree approach provides significantly better results than the Naive Bayes algorithm (0.034). The Decision Tree approach appeared to be more accurate (91) when comparing its Parkinson's disease prediction accuracy to that of the Naive Bayes algorithm (72 percent). The focus of this study is on employing cutting-edge machine learning classifiers to create a fresh approach to the prediction of Parkinson's disease and other relevant issues. The Decision Tree approach was found to be more efficient than the Naive Bayes algorithm in a head-to-head comparison. [ABSTRACT FROM AUTHOR]

The primary aim of the study was to assess the potential of two Algorithms (Novel K-Nearest Neighbor and Decision Tree) in classifying audio files according to genre, based on the features extracted from them. To this end, a dataset of 1000.wav files (GTZAN) was utilized for collecting and training the models with Mel-frequency cepstral coefficients(MFCCs), spectral centroid, zero-crossing, Chroma frequencies, and spectral roll-off via Python Librosa library. Sample sizes of 20 for both groups faced comparative analysis using SPSS software. Additionally, feature selection techniques identified characteristics that are effective for increasing accuracy. Results showed that KNN yielded 64.33%, outperforming the Decision Tree algorithm at 58.23%. Thus, it can be concluded that KNN is more proficient than a Decision tree for Music Genre Classification. [ABSTRACT FROM AUTHOR]

The neutron induced nuclear reaction cross sections of fission products are related with the neutron fiux and the reactor burnup, which are important for the accurate of nuclear engineering design. To predict the (n,2n) reaction cross section, especially those lack of experimental measurements, we analyzed the relevant features and establish the experimental data set on the basis of sorting out the experimental data recorded in EXFOR library. The back propagation artificial neural network (ANN) and decision tree (DT) models are built to learn the experimental data set, respectively, adopting PyTorch and XGBOOST toolboxes. we report that machine learning models are applied to analysis and predicate (n,2n) reaction cross section. [ABSTRACT FROM AUTHOR]

In this paper, the Intensity of the Characteristic Q-learning (InCh Q-learning) algorithm is proposed. It allows for finding the shortest and at the same time the safest escape route. Data on the intensity and spread of a fire occurring in a virtual electrical substation are used. Matrices are entered with the intensity values of each considered fire characteristic. As the fire spreads in space, zones of intensity are formed. Rules are introduced that take into account intensity zones for finding an escape route. The learning algorithm finds the shortest path for which the intensity of each of the dangerous features is the least. A threshold of the intensity of each character is introduced at which a person can pass and evacuate successfully. The use of priorities for the dangerous features allows one to choose a path with a greater intensity of the safer features and at the same time with a lower intensity of the more dangerous ones. The optimal escape route found is used to build a decision tree to find the location of an injured user as quickly as possible. [ABSTRACT FROM AUTHOR]

Based on the literature review, many unemployed youths have undergraduate status in Indonesia. Colleges must evaluate and update curricula to reduce graduates who cannot find jobs in their domains. The curriculum must follow the era's demands as an essential aspect of producing quality graduates. As a basis for designing a new curriculum that serves the department's needs, it is necessary to build a web-based prediction system and alumni career analysis. End users can use the prediction and analysis system by employing dynamic data. Therefore, this study aims to build an alumni career analysis system. A variant of the machine learning algorithm that uses a decision tree, i.e., the J48 algorithm, was employed as an inference. The J48 algorithm can explain the relationship between features and has high accuracy. Then, nine features were employed for the career analysis of 622 data from the Informatics Engineering graduate. Based on experiments, the J48 algorithm has obtained an accuracy of 73.33%, precision of 86%, recall of 76%, and an F1 Score of 80%. Thus, this alumni career prediction and analysis system has the potential to be used. [ABSTRACT FROM AUTHOR]

The C4.5 algorithm still has weaknesses in predicting or classifying data if the amount is large. It is necessary to improve the performance of the C4.5 algorithm with the selected split attribute using application of the average gain value to perform the classification. The C4.5 algorithm is one of the Decision Tree methods in the classification process using entropy. The result of the classification obtained from the analysis can be a classification of 8 student data from 100 student data that is tested to produce information on Sanguine, Choleric, Melancholy, and Phlegmatic. From the result of the Decision Tree classification algorithm C4.5 has an accuracy rate of 86.36% with an application error rate or error of 13.64%. [ABSTRACT FROM AUTHOR]

Personality is significant in distinguishing the individual differences in the characteristic patterns of human thinking, feeling and behavior. By extension, there is a likelihood that personality can influence the development of self-stigma of getting psychological help among individuals. However, no research has investigated the effect of personality factors on the stigma related to obtaining psychological help. The study aims to fill the existing literature gap concerning the relationship between personality traits, mental well-being, and self-stigma of obtaining psychological help. The association between these factors among 86 students in a Malaysian university was investigated using logistic regression and decision tree learner. The experimental results recorded an accuracy of 0.778 and Cohen's Kappa score of 0.455 for Logistic Regression and an accuracy of 0.833 and a Cohen's Kappa score of 0.571 for the decision tree learner. The findings of this paper proved that the personality traits of a student can determine his/her self-stigma towards getting psychological help, and ironically mental health does not help in determining the self-stigma towards seeking help. [ABSTRACT FROM AUTHOR]

Students graduating on time are an essential indicator for a higher education institution in supporting campus accreditation. Several factors cause students to graduate on time, namely the origin of the previous student's school and student interest. This study aims to predict student graduation based on the head of the last student's school and student interest so that higher education institutions can get the basis for decisions that will be taken in the future. The method used in analyzing student data and supporting criteria for predicting student graduation is the C4.5 algorithm. Then for the decision tree classifier, this research uses data mining. [ABSTRACT FROM AUTHOR]

As one approach to improving reading literacy, visual novels can be an option. Visual novels are a type of game that focuses on the story aspect. The story of the visual novel game will run according to the choices made by the player. This game can make players feel happy while increasing interest in reading literacy. This research is a development research with a waterfall development model starting from data collection and processing, application design, application implementation and testing, analysis of test results, and application maintenance. This research aims to create a visual novel game by applying the Decision tree algorithm. The choices made by the player in the game are based on this algorithm. The game is then tested through black-box testing and white-box testing. Based on these tests, this visual novel game can perform all the functionalities well. [ABSTRACT FROM AUTHOR]