Backpropagation is a good artificial neural network algorithm used to predict, one of which predict the rate Consumer Price Index (CPI) based on foodstuff sector. While conjugate gradient fletcher reeves suitable optimization method when juxtaposed with backpropagation method, because this can shorten iteration without reducing quality training and testing result. data that will be predicted come from Central Statistics Agency (BPS) Pematangsiantar. The results study expected contribute...

Artificial Neural Network (ANN) is often used to solve forecasting cases. As in this study. The artificial neural network with backpropagation algorithm. study focused on cases concerning overcrowding based District Simalungun Indonesia 2010-2015. data source comes from the Central Bureau of Statistics Regency. population density its future will be processed using algorithm binary sigmoid function (logsig) and a linear identity (purelin) 5 architecture model 3-5-1, 3-10-1, 3-5 -10-1,...

Abstract - At the beginning of March Indonesia was entering corona outbreak virus (COVID) Every day case Covid-19 distribution in continued to increase. community is issued conduct social distance cut COVID-19 distributed various regions. In Indonesia, therefore, data that has been accommodated certainly a lot, from it can be seen patterns selection are based on test scores, This study uses K-Medoids method so used for community. grouping Analytical sections aim get set k-clusters among most...

This research proposes a decision support system in determining thesis exam graduation using AHP and TOPSIS method. The method weighted the criteria to generate values for each criterion, which value of criterion was used obtain ranking some alternatives with TOPSIS. assessment are 5 chapters (C1), neatness (C2), manners (C3), material delivery (C4) mastery (C5). Merging methods can optimize weighting that affect more objective alternative results. resulting Hamming distance is 96.2%...

Abstract This study proposes an application of Data Mining in determining patterns Interest high school Graduates to attend AMIK Tunas Bangsa Pematangsiantar and the dominant factors which affect interest graduates. The data was picked up from forms completed by those enrolled . In this study, algorithm C 4.5 decision tree applied order obtain pattern classification, i.e. school, status, location, year graduation.. these graduates demonstrated that best variable predictor used is status...

Desktop mendeley application is actually an intended to facilitate the creation of citations and a list libraries commonly used by authors, so authors will be pressed error in making bibliography obtaining writings cited. In addition creating scientific papers, this can also manage files online journal articles that are output work. Furthermore, participants utilize for purpose or collection abstracts certain fields subscribed. Training activities undertaken Community Service show have...

Abstract This study aims to classify the level of understanding students at STIKOM Tunas Bangsa. Data obtained from results even semester student questionnaires, with data samples 165 students. The attributes used are 5, namely communication (C1), learning atmosphere (C2), media (C3), appearance (C4) and teaching methods (C5). method in this research is C4.5 Algorithm processed using RapidMiner software make decision trees. From eight rules determine understanding, 4 understand do not...

Abstract - COVID-19 is an infectious disease caused by acute coronavirus 2 (severe respiratory or SARS-CoV-2) syndrome. The even distribution of cases in all provinces Indonesia a fairly rapid spread and harms fields. vast territory allows the need for grouping sections region Indonesia. This will produce center points COVID 19. K-Means one Clustering algorithms that used to divide data into several groups with system partition. algorithm accepts input form without class labels. Due global...

Abstract This study aims to classify the quality of customer service at Bank BTN Pematangsiantar Branch. Data is obtained from results questionnaire Attributes used are 7, namely Age (C1), Job (C2), Old Customer (C3), Tangiable (C4), Reliability (C5), Assurance (C6), Responsivenenss (C7). Motede in this research C4.5 Algorithm and assisted by Rapidminer software make decision trees. From study, there were 5 rules for classification determining with 3 satisfaction status 2 dissatisfied...

Ayam bukanlah makanan yang asing bagi penduduk Indonesia. Makanan tersebut sangat mudah dijumpai dalam kehidupan masyarakat sehari-hari. Namun tingkat konsumsi daging ayam di Indonesia masih tergolong rendah dibandingkan dengan Negara tetangga. Penelitian ini membahas tentang Penerapan Datamining Pada Populasi Daging Ras Pedaging Berdasarkan Provinsi Menggunakan K-Means Clustering. Sumber data penelitian dikumpulkan berdasarkan dokumen-dokumen keterangan populasi dihasilkan oleh Badan Pusat...

Prediction required by decision makers to anticipate future planning. Artificial Neural Network (ANN) Backpropagation is one of method. This method however still has weakness, for long training time. a reason improve accelerate the training. One resilient Resilient changing weights and bias network with direct adaptation process weighting based on local gradient information from every learning iteration. Predicting data result Istanbul Stock Exchange getting better. Mean Square Error (MSE)...

Abstract Life expectancy is the average number of years life that still lived by someone who has reached a certain age. Expectancy tool to evaluate government performance in improving welfare population general and health status particular. The purpose this paper estimate world so benchmark determining policies further improve people their respective countries. estimation stated will use Cyclical Order Weight Neural Network method. data used expectations. Data sources come from United...

Abstract The Institute for Research and Community Service is a forum lecturers at every university/institution to develop their knowledge according respective disciplines through research fields. This study aims determine the recipient of best grant STIKOM Tunas Bangsa Pematangsiantar. data comes from relevant agencies. There are 9 names that used as alternatives 5 criteria assessment grantees, namely type problem formulation (C1), output opportunities (C2), method (C3), literature review...

This study aims to utilize Clushtering Algorithm in grouping the number of people who have health complaints with K-means algorithm Indonesia. The source this research data was collected based on documents provincial population which had produced by National Statistics Agency. used are from 2013-2017 consisting 34 provinces. method is Algorithm. Data will be processed clushtering 3 clushter, namely clusther high complaints, moderate and low complaints. Centroid for level clusters 37.48,...

Abstract This study aims to search for factors causing lazy students at STIKOM Tunas Bangsa. Data obtained from student questionnaire results with a sample of 20 students. The attributes used are 4, namely body condition (A1), lack learning motivation (A2), lecturer influence (A3) and environment (A4). method in the is ELECTRE II. From study, factor (A1) first alternative get rank pure concordance value 1.8571 discordance -2. Followed by on second 1.1905 -1.6935. With this analysis, it...

Abstract Indonesian people still consume a lot of corn as staple food. Corn productivity based on data from the Central Bureau Statistics 2005 to 2015 is not stable. Therefore this study was conducted determine right prediction model see level in Indonesia for coming year, with hope that government has reference continue work improve remain stable order meet needs and minimize imports. This uses 2005-2015 sourced Statistics. The algorithm used Backpropagation artificial neural network. able...

Mining age and technology have led to the emergence of an innovation that can help facilitate human activities, especially for parents in controlling looking after babies. By implementing a sound monitoring system baby room based on Arduino Atmega 328 microcontroller which functions detect noise. Data from voice sensor is processed by via pin. So will give instructions Buzzer send alarm notifications

The purpose of the study was to classify factors causing decline in student achievement during pandemic using C4.5 datamining method. Sources research data were obtained by conducting interviews and distributing questionnaires 7th semester students 2020-2021 school year information system program. Attributes that used classification include: Learning Method (C1), Study Time (C2), Material Understanding (C3), Giving Assignments (C4) Environment (C5). results calculation show (C3) attribute is...

Chronic Kidney Disease (CKD) is a progressive condition that impairs kidney function and cannot be cured. Early detection crucial for effective management therapy. However, diagnosing CKD challenging as patients often have comorbidities such diabetes, hypertension, or heart disease, which complicate diagnosis treatment. Accurate classification methods are essential early detection. K-Nearest Neighbor (KNN) algorithm groups data based on feature similarity. K-NN an resistant to outliers, easy...

Abstract: Clustering methods such as K-Means and K-Medoids are often used to analyze data, including student due their efficiency. However, this method has weaknesses, sensitivity selecting cluster centers (centroids) results that depend on medoid data. Clustering, an essential technique in data analysis, aims reveal the natural structure of even absence labeled information. The study, conducted with complete objectivity, compared performance two popular clustering methods, K-Means,...

Multilayer Perceptron (MLP) is a powerful machine learning algorithm capable of modeling complex, non-linear relationships, making it suitable for predicting car purchasing power. However, its performance depends on hyperparameter tuning and data quality. This study optimizes MLP using GridSearch Optuna while addressing imbalance with the Synthetic Minority Over-sampling Technique (SMOTE). The dataset comprises demographic financial attributes influencing Initially, exhibited class...

Hypertension is a major cause of cardiovascular disease, making early risk prediction essential. According to WHO, hypertension cases are estimated reach 1.28 billion by 2023. This study aims optimize the K-Nearest Neighbor (KNN) algorithm for predicting through hyperparameter tuning. Three methods Grid SearchCV, Bayes and Random SearchCV compared determine best parameter configuration. The dataset, obtained from Kaggle, consists 520 balanced samples (260 positive 260 negative) with 18...

The development of technology is very fast, especially in the field Internet that at any time experiencing significant changes, also supported by ability human resources, Keylogger a tool most developed because this application rarely recognized malicious program antivirus, keylogger will record all activities related to keystrokes, recording process accomplished using string matching method. method keyboard help admin knowing what user accessed on computer.

Early detection and proper management of Chronic Kidney Disease (CKD) are solicited for augmenting survivability due to fact that CKD is one the life-threatening diseases. The UCI's dataset which selected this study consisting attributes like age, blood pressure, specific grativity, albumin, sugar, red cells, plus cell, pus cell clumps, bacteria, glucose random, urea. main purpose work calculate performance various decision tree algorithm compare their performance. techniques used in...