Bayes Method Research Articles

Penerapan Metode Naïve Bayes dalam Peramalan Polusi Udara di Kota Jakarta

This research aims to analyze and predict the level of air pollution in Jakarta City using ISPU data of DKI Province, adopting the Naïve Bayes method. The test results show that the Naïve Bayes algorithm has excellent performance, with 93% accuracy, 98% precision, 100% recall, and 99% f1-score. The implication is that this model can be effectively used for air pollution forecasting in Jakarta City, assisting authorities in making decisions related to air quality and environmental improvement efforts.

Analysis of Student Satisfaction with the Quality of Education Services and Lecturer Performance Using the Survey and Naive Bayes Methods

This research aims to evaluate the level of student satisfaction with the quality of educational services and the assessment of faculty performance at STMIK Tegal through a survey method and the application of Naive Bayes. The research sample consists of 100 active students from different study programs. Survey results were processed using the Naive Bayes method to assess the impact of variables related to the quality of educational services and faculty performance on the level of student satisfaction. The findings of the analysis indicate that the quality of educational services has a positive effect on student satisfaction, while faculty performance also contributes positively. This research has practical implications for improving the quality of educational services and faculty performance at STMIK Tegal. Infrastructure and facilities supporting the teaching and learning process can be enhanced, and faculty members can receive training and guidance to improve their teaching quality. In the long term, this can enhance the institution's reputation and overall student satisfaction. This study has limitations related to the limited sample size and the use of non-random sampling techniques. Therefore, future research can expand the sample size and use more representative sampling techniques to enhance the accuracy of research results

Experience rating of risk premium for Esscher premium principle

In this article, a new method is introduced under the Bayesian framework to derive the credibility estimator of risk premiums based on the Esscher premium principle. This new estimator offers desirable statistical properties, making it more useful and practical compared to existing estimators. Additionally, Bayesian models for policy portfolios are established, and empirical Bayes methods are employed to estimate the structural parameters. The empirical Bayesian estimation of risk premiums is also discussed in detail. The convergence rate and goodness of the proposed estimators are verified through simulations. The results demonstrate the effectiveness and accuracy of the new estimator and its superior performance compared to other existing methods. Finally, an empirical analysis is conducted using real insurance data, which further confirms the applicability and reliability of the proposed credibility estimator and its superiority in practical insurance applications.

Perbandingan Kinerja K-Nearest Neighbors dan Naive Bayes Untuk Klasifikasi Perilaku Nasabah Pada Pembayaran Kredit Bank

:Credit customers are people who use banking services or other financial services. to use bank money in its business activities, so it expects that the bank's credit can meet business capital needs. To reach information to increase profits and reduce company losses, we need a method that can provide knowledge to support the company's data. Research data can be obtained from processing classification data from credit customer data that are categorized as potential or not potential in the next credit grant. Data processing can be done using machine learning, namely classification techniques. This technique will produce a predictive churn model to determine which customer categories belong to a group. potential smooth or jammed. The Naive Bayes method was chosen because it can produce maximum accuracy with little training data. Meanwhile, the K-Nearest Neighbor method was chosen because it is robust against noise data. The performance of the two methods will be compared, so that it can be seen which method is better in classifying documents. The results obtained show that the Naive Bayes method has better performance with an accuracy rate of 70%, while the K-Nearest Neighbor method has a fairly low accuracy rate of 40%. Thus, it can be seen the accuracy value displayed by applying the classification algorithm. K-Nears Neighbors and Naïve Bayes. Parameter category. which in this study are account numbers, names of debtors, collectibility in the categories: current, DPK (on special mention), substandard, doubtful, loss. Then clarified with a description of the type of loan, collectability of ADK (computer data archive), type of business.

Customer Segmentation Analysis Using Random Forest & Naïve Bayes Method In The Case of Multi-Class Classification at PT. XYZ

Cases of the COVID-19 pandemic are gradually decreasing every day in Indonesia, but the impact of the COVID-19 pandemic has greatly affected various sectors, especially the economy and business. Sales transactions have not yet reached the company's target due to weak public purchasing power. The accuracy of customer segmentation analysis and attractive promo voucher offers are needed to increase the opportunity for people's purchasing power for a product. This study aimed to predict the level of customer purchasing power using the random forest and naïve Bayes methods in the case of multi-class data classification at PT. XYZ. The classification is carried out to determine the type of promo voucher suitable to be offered to customers according to the level of customer purchasing power. The data used is historical daily transaction data from January 1, 2022, to December 31, 2022, which is the transition period for the COVID-19 pandemic. Evaluation using the random forest method produces an accuracy of 99.99%, while the naïve Bayes method produces an accuracy of 92.99%. The random forest and naïve Bayes methods can work very well on large data volumes. However, from the comparison results, it can be concluded that the performance of the random forest method is better than the naïve Bayes method in the multi-class classification case in predicting the level of customer purchasing power at PT. XYZ.

PERBANDINGAN KLASIFIKASI ALGORITMA K-NN, NEURAL NETWORK, NAÏVE BAYES, C 4.5 UNTUK MENDETEKSI WEB PHISING

The increasing number of internet users in the world and the rise of web phishing. Based on the Wearesocial report, there are several facts which include the number of world internet users that have reached 4.021 billion people. explained that of the hundreds of millions of internet users in Indonesia, 60 percent have accessed the internet using smartphones. Internet usage is dominated by socializing activities in cyberspace. Evidenced by the large number of world social media users, reaching 3,196 billion users. But with the rise of internet users and social media accompanied by the proliferation of phishing webs. The purpose of this attack is to make users believe that they interact with the official virtual or online site in question. Generally the information sought is in the form of a password, account or victim's credit card number. by way of being directed to a fake web or sending an email, banner or pop-up where the victim is asked to give his personal information. In this study C.4.5, Neural Network and K-Nerest Neighbor algorithm comparison will be conducted to determine the performance of the algorithm in detecting webphising by using classification techniques. Based on the model testing based on the Naïve Bayes method, Decision Tree C.4.5, K-NN, Neural Network uses the Weka framework v.3.8.2. The results of the Decision Tree C.4.5 algorithm have a higher level of accuracy with 89.66 percent accuracy.

ANALISIS KEPUASAN MAHASISWA TERHADAP SISTEM PEMBELAJARAN ONLINE PADA MASA PANDEMIC COVID 19 DI STMIK AKAKOM DENGAN METODE NAIVE BAYES

In accordance with the circular of the Minister of Education and Culture of the Republic of Indonesia regarding Circular Letter Number 4 of 2020 concerning the Implementation of Educational Policies in the Emergency Period for the Spread of Corona Virus Disease (COVID-19), the learning system implemented is online. 
 STMIK AKAKOM is one of the universities that has also implemented online lectures since the government's policy for the home learning system was established. Various efforts have been made by STMIK AKAKOM to carry out the online learning process during this covid-19 pandemic. 
 Therefore, researchers conducted a study that aims to analyze the success of the online learning system for students conducted at STMIK AKAKOM with the Naive Bayes method approach, using 4 (four) criteria, namely Communication, Building a Learning Atmosphere, Assessment of Students, and Delivery of Lecture Materials. The level of satisfaction assessment using a Likert scale (likert scale) 5 points with the same interval. starting from point 1 (one) which states very less, to point 5 (five) which states very well. Based on the results of calculations that have been carried out, it can be seen that the classification of testing data from respondents numbered R89 to R93 for online learning systems during the Covid 19 pandemic is satisfied.

Intelligent decision support system using nested ensemble approach for customer churn in the hotel industry

ABSTRACT Since customer retention costs much less than attracting new customer, the problem of customer churn is a major challenge in various fields of work and particularly Hotel Industry. In this research, a solution based on an intelligent decision support system using text mining and nested ensemble techniques is presented, which combines the advantages of stacking and voting methods. In the proposed system, after the text mining of the data collected from the hotels of Kish Island, the effective feature selection is done using the gravity search algorithm. In the first level of nested ensemble technique method, stacking deep learning methods are used. Voting is used in the MetaClassifier section, which includes Random Forest, Xgboost and Naïve Bayes methods. The results of the implementation and comparison of the proposed system, show that the performance of the proposed system has increased the accuracy by 0.04 compared to the best existing method.

Spatial distribution of suicides in Mato Grosso, Brazil, from 2008 to 2018

In the last few decades, it is believed that the state of Mato Grosso has been the stage of a substantial increase in suicide rates. However, the extension of this issue in the health regions of the state is still unknown. Therefore, the goal of this study was to analyze the spatial distribution of suicides in Mato Grosso, Brazil, from 2008 to 2018. This is an ecological study, with spatial-temporal distribution. Data collection took place in 2020 and was carried out in the Information System on Mortality for the period from January 2008 to December 2018. The suicide rates were calculated and smoothed using the empirical Bayes method, aided by the software GeoDa 1.12. To construct the maps, we used the software ArcGis 10.5. There were 1,977 recorded suicides in Mato Grosso, especially in males (79.3%), single (50.6%), from 20 to 29 years old (23.7%), brown (55.4%), with low educational levels (52.2%). Most suicides were carried out by intentional self-harm by hanging, strangulation and suffocation in the residence. The spatial-temporal distribution showed that the mesoregions North and Northeast had the highest rates, especially in cities in the health regions of Mid-Araguaia (for both sexes) and Garças Araguaia (for males). Suicides have followed a random, unequal pattern throughout Mato Grosso, but focused in areas of little development, showing the need to invest in health, and to strengthen and value policies to bring human resources to attend to these demands. The health care network must be structured to do so.

Analisis Sentimen Opini Publik Terhadap Chatgpt di Twitter Menggunakan Metode Naive Bayes

The presence of ChatGPT, which is based on Artificial Intelligence (AI), has attracted public attention and become a polemic. This application is very helpful for users in finding information, translating languages, and generating text similar to human speech. OpenAI's decision to launch the ChatGPT Plus service is related to its monetization strategy and maintaining user interest. In this regard, a study was conducted using the Naïve Bayes method to classify the sentiment of the Twitter community towards ChatGPT in the period 30/11/2022 to 31/12/2022. This study took 5001 tweet data from the available dataset, and used TF-IDF feature extraction and BOW feature extraction, with data division into 70% training data and 30% test data. This research gets the highest accuracy value of 59% using BOW feature extraction.

EXPERT SYSTEM FOR DIAGNOSIS OF DISEASES IN CAT USING THE NAIVE BAYES METHOD

Cats are animals that relieve stress. When a person spends time with a cat, the hormones serotonin, oxytocin and dopamine increase. One of the reasons why cats can relieve stress is purring, that has a frequency level of 25-50 hertz. But cats can also get sick. Researchers took the initiative to create an application to make it easier for users, to be able to diagnosed earlier. The purpose of this application was that it can be an option other than going to an expert, a good accuracy when compared to experts and providing the right solution. Making the application used the Naïve Bayes method as an analysis of cat data from expert sources that produced that symptoms produced appropriate disease with the solution. Implementation users starting from filling in biodata, symptoms, generating diseases and their solutions, and additional features such as disease info and messages. Meanwhile, admin requires a login to use the data management of symptoms, diseases, knowledge base, accounts and messages. The results of the application were explained from the results of the diagnosis which can detect the cats disease from the inputted symptoms, along with other disease options, with a disease comparison value of 91%.

Comparing Support Vector Machine and Naïve Bayes Methods with A Selection of Fast Correlation Based Filter Features in Detecting Parkinson's Disease

Dopamine levels fall due to brain nerve cell destruction, producing Parkinson's symptoms. Humans with this illness experience central nervous system damage, which lowers the quality of life. This disease is not deadly, but when people's quality of life decreases, they cannot perform daily activities as people do. Even in one case, this disease can cause death indirectly. Contrast support vector machines (SVM) and naive Bayesian approaches with and without fast correlation-based filter (FCBF) feature selection, this study attempts to determine the optimum model to detect Parkinson's disease categorization. In this study, datasets from the UCI Machine Learning Repository are used. The results showed that SVM with FCBF achieved the highest accuracy among all the models tested. SVM with FCBF provides an accuracy of 86.1538%, sensitivity of 93.8775%, and specificity of 62.5000%. Both methods, SVM and Naive Bayes, have improved in performance due to FCBF, with SVM showing a more significant increase in accuracy. This research contributed to helping paramedics determine if a patient has Parkinson's disease or not using characteristics obtained from data, such as movement, sound, or other pertinent factors.

Bayesian and Classical Semi-parametric Estimation of the Balanced Longitudinal Data Model

The primary objective of this study is to employ semi-parametric regression techniques in the balanced longitudinal data model. Where the parametric regression models are plagued by the problem of strict constraints, while non-parametric regression models, despite their flexibility, suffer from the problem of the curse of dimensionality. Consequently, semi-parametric regression presents a suitable solution to address the problems in parametric and non-parametric regression methods. The advantage of this model is that it contains all the positive properties included in the previous two models such as containing strict restrictions in its parametric component, complete flexibility in its non-parametric component, and clarity of the interaction between its parametric and non-parametric components. According to the above, two methods were used to estimate a semi-parametric balanced longitudinal data model. The first is the Bayesian estimating method; the second is the Speckman method, which estimated the unknown nonparametric smoothing function by employing the kernel smoothing Nadaraya & Watson method. The Aim was to make a comparison between the Bayesian estimation method and the classical estimation method. Based on simulation experiments conducted on three different sample sizes (50, 100, and 200), it was concluded that the Bayes method is best at the variance levels (1,5). In contrast, the Profile least square method is best at the variance level (10).

Using Auxiliary Item Information in the Item Parameter Estimation of a Graded Response Model for a Small to Medium Sample Size: Empirical Versus Hierarchical Bayes Estimation.

Marginal maximum likelihood estimation (MMLE) is commonly used for item response theory item parameter estimation. However, sufficiently large sample sizes are not always possible when studying rare populations. In this paper, empirical Bayes and hierarchical Bayes are presented as alternatives to MMLE in small sample sizes, using auxiliary item information to estimate the item parameters of a graded response model with higher accuracy. Empirical Bayes and hierarchical Bayes methods are compared with MMLE to determine under what conditions these Bayes methods can outperform MMLE, and to determine if hierarchical Bayes can act as an acceptable alternative to MMLE in conditions where MMLE is unable to converge. In addition, empirical Bayes and hierarchical Bayes methods are compared to show how hierarchical Bayes can result in estimates of posterior variance with greater accuracy than empirical Bayes by acknowledging the uncertainty of item parameter estimates. The proposed methods were evaluated via a simulation study. Simulation results showed that hierarchical Bayes methods can be acceptable alternatives to MMLE under various testing conditions, and we provide a guideline to indicate which methods would be recommended in different research situations. R functions are provided to implement these proposed methods.

Tomato Production Prediction Based on Deep Learning Algorithm-Cascade-PSPNET and Bayes

Accounting the problem of small sample size in tomato yield statistics, a dual-fusion prediction analysis model based on Bayes theory and deep learning algorithm Cascade-PSPNET is proposed. The tomato yield prediction is conducted based on remote sensing image time series analysis and multi-source information fusion theory with Bayesian theory and credibility weighting. First, the area of tomato planting is analyzed through semantic segmentation algorithms of remote sensing images during the tomato planting process. The yield is predicted by variables such as planting area fluctuation, disaster cycle fluctuation, etc. Through analyzing the reduced yield affected by disasters in different time periods of remote sensing images during planting process, the value chain of tomato industry is calculated by comprehensively analyzing price-value system, inflation coefficient, and unit area yield. At the same time, the annual patent application volume is used to predict the change of tomato yield year by year according to Bayesian theory, and the relationship between annual patent application volume and tomato yield year by year under different confidence levels is analyzed. The results show that it is feasible to use the Bayes method with semantic segmentation algorithms of remote sensing images to predict tomato yield. Next, the experiment of fusion prediction between two prediction models in the same target area will be carried out for verification.

Robust Kalman Filter for Systems With Colored Heavy-Tailed Process and Measurement Noises

In this paper, we consider the robust state estimation for a linear system with colored heavy-tailed process and measurement noises. We employ the state augmentation and measurement differencing methods to whiten the colored noise and use the Student’s t distribution to model the heavy-tailed property, which makes a new state space model with the augmented state vector. The posterior estimation of the system state, inaccurate scale matrices, and auxiliary parameters are jointly inferred with the variational Bayes method by constructing the hierarchical Gaussian forms of the prediction and likelihood probability density functions and selecting the proper prior distributions of the scale matrices and auxiliary parameters. A typical target tracking simulation is given to confirm the performance of the proposed robust Kalman filter.

Community perceptions classification towards the development of transportation access at Darmo Corridor Surabaya using SVM and naive bayes methods

This research conducts Classification of Public Perceptions of Transportation Access Development in Darmo Corridor Surabaya using SVM and Naive Bayes methods. The increasing mobility demands necessitate adequate public transportation facilities, such as the Surabaya bus, which has been operational since 2018. The Darmo corridor has witnessed significant development in public transportation facilities and infrastructure, serving as a transit point between two Surabaya bus routes. The purpose of this study is to evaluate public perception towards the implementation of Transit Oriented Development (TOD) concept in the corridor. In this study, a qualitative descriptive analysis was conducted on various aspects of TOD implementation, such as pedestrian paths, bicycle lanes, and green open spaces. Furthermore, public perception was analyzed using Naive Bayes Classifier and SVM methods by collecting data from Twitter accounts and giving weights based on the frequency of words in the tweets. From the analysis it could be concluded Naïve Bayes is not suitable for classification because it’s not stable enough, the SVM Methods matchs 95% proven when its repeated for 5 more time it. The results showed that the Darmo corridor successfully implemented the TOD concept well, with 90% of the community giving a positive response to the TOD implementation in the area. This finding indicates the success of TOD initiatives in improving transportation facilities and infrastructure in Darmo corridor.

Implementasi Sistem Pakar Diagnosis Autisme Pada Anak Menggunakan Metode Naïve Bayes

Autism is a developmental disorder that affects the normal functioning of the brain, thereby affecting a child's communication and social interaction abilities. This disorder poses a problem for children in communicating and forming relationships with their environment. As the number of individuals with autism increases, public awareness of autism remains very low. Additionally, most psychologists or psychiatrists are located in major cities, limiting access for rural communities. This leads to many parents struggling to obtain information about autism symptoms. The research method used is the naïve Bayes method, it can be drawn from the system is that it will generate the maximum score despite any disturbances in the provided data. The results of this research align with expert knowledge, suggesting that it can be relied upon to accurately diagnose autism based on the symptoms experienced by individuals. The aim of this study is to build an expert system that can provide information and solutions to parents regarding autism disorders based on their knowledge of the symptoms they experience, enabling users to diagnose autism in their children early on without incurring costs.

Naïve Bayes Classifier dengan Particle Optimize Weight Forward pada Dataset

Classification is the process of identifying and grouping objects into classes or categories based on their characteristics. In data mining, there are two processes, namely classification and clustering, which are used to group objects based on similarities. In the classification process, various methods such as K-NN, SVM, and Naïve Bayes are often used and developments are made in the method. The Naïve Bayes classifier is proven to have advantages, such as faster calculation and better accuracy. However, this method has limitations in the attribute selection process. To overcome this limitation, the Particle Optimize Weights Forward algorithm is used to improve accuracy by assigning weights to attributes in the Naïve Bayes method. This approach improves the efficiency and effectiveness of the Naïve Bayes classifier in data classification tasks.

Classification Of Maternal Health Risk Using Three Models Naive Bayes Method

Lack of information related to maternal health care during pregnancy and post-pregnancy, especially in rural areas, results in many cases of pregnancy complications. Risk analysis for pregnant women is really needed as a reference in handling pregnant women so that the risk to pregnant women can be minimized. To analyze the risk of pregnant women can use data mining techniques by classifying the risk of pregnant women. This study proposes to classify Maternal Health Risk using the Naive Bayes method with three models, namely Gaussian, Multinomial, and Bournolli. The data used is the health data of pregnant women based on risk intensity which is grouped into three classes, namely low, mid and high risk. while the attributes are Age, Systolic Blood Pressure as SystolicBP, Diastolic BP as DiastolicBP, Blood Sugar as BS, Body Temperature as BodyTemp, and HeartRate. The results show that among the three Naïve Bayes models that have the best performance are the Multinomial and Bournolli with an accuracy of 84.8% while the Gaussian produces an accuracy of 82.6%.