STIKOM Tunas Bangsa

Abstract The aim of the research is to make predictions from the best architectural model of backpropagation neural networks. In determining the outcome in the form of a prediction model, the activation function in the artificial neural network is useful to transform an input into a certain output. In this study the activation function used is sigmoid. The study uses the case of population density in Indonesia considering that for developing countries population growth has many negative impacts such as increased poverty, unemployment and crime rates. This study uses data from Badan Pusat Statistic Indonesia for population categories in 2003-2015. The process of determining the architectural model is carried out 2 stages including: the training stage and the testing stage. The two architectural models used (5-2-1 and 5-10-1), the selection of architectural models is done by looking at several assessment parameters such as epoch, accuracy, MSE training and MSE testing. The process of training and testing of data is done by using the help of the Matlab application. The results of the study obtained that the architectural model 5-2-1 is the best model for predicting with an accuracy of 65%, MSE Training 0,0009997254, MSE Testing 0.0014897214 and Epoch 28548.

Indonesia is an agriculture-based country. Agriculture is a sector that becomes the backbone of Indonesia's economic development and improvement. Food security is one of the most important of farms. There are several types of food crops that become important commodities for the nation of Indonesia namely rice, corn, peanut, green beans, cassava and sweet potatoes. This research data is sourced from BPS-Statistic (https://www.bps.go.id/). This research raised the topic of rice crops clustering by province (1993-2015) using data mining with K-means method. The method used with the help of rapidminer software. The sample data used are 34 provinces in Indonesia with 3 parameters, namely: 1). Lack of Harvest Area (hectares), 2). Productivity (quintal / hectare) and 3). Production (ton). Cluster results using 3 clusters: (C1) high production cluster, (C2) normal production cluster and (C3) low production cluster. Based on the research results obtained (C1) high production cluster = 3 provinces, (C2) normal production cluster = 23 provinces and (C3) low production cluster = 8 provinces. This study also uses "% performance" to see the accuracy of the algorithm used with the research topic. From the result of accuracy using parameter average within centroid distance and Davies Bouldin obtained Davies-Bouldin index for rice plant is -0.392. Based on these performance results can be summed up as the best algorithm based on criteria. The lowest cluster clustering (C3): Aceh, North Sumatera, West Sumatera, South Sumatera, Lampung, West Nusa Tenggara, South Kalimantan, and South Sulawesi are input inputs to the government, to provide socialization to the province to increase rice production, is one of the commodities of Indonesian people, especially rice.

Artificial Neural Network (ANN) is often used to solve forecasting cases. As in this study. The artificial neural network used is with backpropagation algorithm. The study focused on cases concerning overcrowding forecasting based District in Simalungun in Indonesia in 2010-2015. The data source comes from the Central Bureau of Statistics of Simalungun Regency. The population density forecasting its future will be processed using backpropagation algorithm focused on binary sigmoid function (logsig) and a linear function of identity (purelin) with 5 network architecture model used the 3-5-1, 3-10-1, 3-5 -10-1, 3-5-15-1 and 3-10-15-1. Results from 5 to architectural models using Neural Networks Backpropagation with binary sigmoid function and identity functions vary greatly, but the best is 3-5-1 models with an accuracy of 94%, MSE, and the epoch 0.0025448 6843 iterations. Thus, the use of binary sigmoid activation function (logsig) and the identity function (purelin) on Backpropagation Neural Networks for forecasting the population density is very good, as evidenced by the high accuracy results achieved.

Backpropagation is a good artificial neural network algorithm used to predict, one of which is to predict the rate of Consumer Price Index (CPI) based on the foodstuff sector. While conjugate gradient fletcher reeves is a suitable optimization method when juxtaposed with backpropagation method, because this method can shorten iteration without reducing the quality of training and testing result. Consumer Price Index (CPI) data that will be predicted to come from the Central Statistics Agency (BPS) Pematangsiantar. The results of this study will be expected to contribute to the government in making policies to improve economic growth. In this study, the data obtained will be processed by conducting training and testing with artificial neural network backpropagation by using parameter learning rate 0,01 and target error minimum that is 0.001-0,09. The training network is built with binary and bipolar sigmoid activation functions. After the results with backpropagation are obtained, it will then be optimized using the conjugate gradient fletcher reeves method by conducting the same training and testing based on 5 predefined network architectures. The result, the method used can increase the speed and accuracy result.

Artificial Neural Networks are a computational paradigm formed based on the neural structure of intelligent organisms to gain better knowledge. Artificial neural networks are often used for various computing purposes. One of them is for prediction (forecasting) data. The type of artificial neural network that is often used for prediction is the artificial neural network backpropagation because the backpropagation algorithm is able to learn from previous data and recognize the data pattern. So from this pattern backpropagation able to analyze and predict what will happen in the future. In this study, the data to be predicted is Human Development Index data from 2011 to 2015. Data sourced from the Central Bureau of Statistics of North Sumatra. This research uses 5 architectural models: 3-8-1, 3-18-1, 3-28-1, 3-16-1 and 3-48-1. From the 5 models of this architecture, the best accuracy is obtained from the architectural model 3-48-1 with 100% accuracy rate, with the epoch of 5480 iterations and MSE 0.0006386600 with error level 0.001 to 0.05. Thus, backpropagation algorithm using 3-48-1 model is good enough when used for data prediction.

Indonesia is a country where most of its people rely on the agricultural sector as a livelihood. Indonesia's rice production is so high that it can not meet the needs of its population, consequently Indonesia still has to import rice from other food producing countries. One of the main causes is the enormous population. Statistics show that in the range of 230-237 million people, the staple food of all residents is rice so it is clear that the need for rice becomes very large. This study discusses the application of datamining on rice import by main country of origin using K-Means Clustering Method. Sources of data of this study were collected based on import import declaration documents produced by the Directorate General of Customs and Excise. In addition since 2015, import data also comes from PT. Pos Indonesia, records of other agencies at the border, and the results of cross-border maritime trade surveys. The data used in this study is the data of rice imports by country of origin from 2000-2015 consisting of 10 countries namely Vietnam, Thailand, China, India, Pakistan, United States, Taiwan, Singapore, Myanmar and Others. Variable used (1) total import of rice (net) and (2) import purchase value (CIF). The data will be processed by clustering rice imports by main country of origin in 3 clusters ie high imported cluster, medium imported cluster and low import level cluster. The clustering method used in this research is K-Means method. Cetroid data for high import level clusters 7429180 and 2735452,25, Cetroid data for medium import level clusters 1046359.5 and 337703.05 and Cetroid data for low import level clusters 185559.425 and 53089.225. The result is an assessment based on rice import index with 2 high imported cluster countries namely Vietnam and Thailand, 4 medium-level clusters of moderate import countries namely China, India, Pakistan and Lainya and 4 low imported cluster countries namely USA, Taiwan, Singapore and Myanmar. The results of the research can be used to determine the amount of rice imported by the main country of origin

Disaster caused by both nature and human factors has resulted in the occurrence of human casualties, environmental damage, property loss, and psychological impact. The study aims to classify disaster prone areas in Indonesia using K-means clustering method implemented in rapid miner tools. The data are collected from the Central Bureau of Statistics about the number of villages that considered as natural disaster-prone by province in Indonesia in years [2008][2009][2010][2011][2012][2013][2014]. The sample data are 34 provinces in Indonesia with 3 natural disasters commonly happen i.e. namely: Flood, Earthquake and Landslide. The final outcomes of the study were: (1) 4 provinces classified as High with cluster center 1363.333 (flood), 528.25 (earthquake) and 949.583 (landslide); 14 provinces classified as Medium with cluster center 142.619 (flood), 96.071 (earthquake) and 72.048 (landslide); and 16 provinces classified as Low with cluster center 507.396 (flood), 57.604 (earthquake) and 177.479 (landslide). This work can further provide input to the Indonesia government through mapping of disaster prone areas especially 4 provinces with very high natural disasters such as Aceh, West Java, Central Java and East Java.

Abstract The importance of efficiency in the space of search rules C4.5 decision tree algorithm has been the focus of a lot of researchers. Therefore, the development needs to be conducted to form a new, more efficient method but it can not be separated from the accuracy of the analysis as the results of the algorithm itself. For that purpose, by using a genetic algorithm (GA), it is expected to optimize and simplify the search rules of more complex combinations. The use of C4.5 with Hybrid genetic algorithm in search of a more effective rules requires a better understanding and a long time. But the use of the two algorithms will be mostly effective if the cases faced are very complex, having more branching condition and highly accurate.

Penyakit Demam Berdarah Dengue (DBD) adalah penyakit yang disebabkan oleh Dengue yang tergolong Arthropod-Borne Virus, genus Flavivirus, dan famili Flaviviridae. DBD ditularkan melalui gigitan nyamuk dari genus Aedes, terutama Aedes aegypti atau Aedes albopictus. Penyakit DBD dapat muncul sepanjang tahun dan dapat menyerang seluruh kelompok umur. Penyakit ini berkaitan dengan kondisi lingkungan dan perilaku masyarakat. Penelitian ini membahas tentang pengelompokkan jumlah daerah yang terjangkit demam berdarah dengue (DBD) berdasarkan provinsi. Metode yang digunakan adalah Data mining K-Means Clustering. Dengan menggunakan metode ini data-data yang telah diperoleh dapat dikelompokkan ke dalam beberapa cluster, dimana penerapan proses K-Means Clustering menggunakan tools RapidMiner. Penelitian ini menggunakan sumber data yang terekam di situs departemen kesehatan dengan alamat url https://www.depkes.go.id/. Data yang digunakan adalah (2014-2016) yang terdiri dari 34 provinsi. Kriteria yang digunakan, yakni: 1) jumlah kabupaten/kota dan 2) kabupaten/kota yang terjangkit. Data diolah dengan menggunakan K-means yang dibagi dalam 3 cluster yaitu: tingkat cluster tinggi (C1), tingkat cluster sedang (C2) dan tingkat cluster rendah (C3). Proses iterasi berlangsung 6 kali sehingga diperoleh penilaian dalam mengelompokkan daerah yang terjangkit demam berdarah dengue (DBD) berdasarkan provinsi. Hasil yang diperoleh bahwa terdapat 4 provinsi dengan cluster tingkatan tinggi (C1), 13 provinsi dengan cluster tingkatan sedang (C2), dan 17 provinsi dengan cluster tingkatan rendah (C3). Hal ini dapat menjadi masukan kepada masyarakat untuk menjaga kesehatan dengan meningkatkan kewaspadaan terhadap penularan demam berdarah, sehingga diperlukan kepedulian peran serta aktif masyarakat untuk bergotong-royong melakukan langkah-langkah pencegahan penularan penyakit DBD, melalui kegiatan pemberantasan nyamuk dan jentik secara berkala.

Abstract - At the beginning of March Indonesia was entering the corona outbreak virus (COVID) Every day the case of Covid-19 distribution in Indonesia continued to increase. the community is issued to conduct social distance to cut the distribution of COVID-19 distribution distributed in various regions. In Indonesia, therefore, the data that has been accommodated is certainly a lot, from the data it can be seen patterns - selection patterns of distribution of COVID-19 distribution are based on test scores, This study uses the K-Medoids method so that the distribution patterns of COVID-19 distribution can be used for the community. K-Medoids is a method of grouping Analytical sections that aim to get a set of k-clusters among the data that most require an object in the collection of data. The results of the new COVID-19 research grouping show the community produced from various regions in Indonesia. Characteristics with a body temperature above 36.9 ◦ c and with fever and cough resolution supported by one of the characteristics of COVID-19 symptoms.Kata Kunci - K-Medoids Algorithm, Clustering, Data Mining, COVID-19, Data GroupingAbstrak - Pada awal maret Indonesia sedang di landa masuknya wabah virus corona (covid) Setiap hari kasus penyebaran covid-19 di indonesia terus meningkat. masyarakat diminta untuk melakukan social distancing guna mamutus rantai penyebaran covid-19 yang tersebar diberbagai wilayah.di Indonesia. Oleh karena itu, data yang telah ditampung pastinya banyak sekali, dari data tersebut dapat dilihat pola – pola penentuan pengelompokan penyebaran covid-19 dilakukan berdasarkan nilai tes, Penelitian ini menggunakan metode K-Medoids agar dapat diketahui pola pemilihan penentuan pengelompokan penyebaran covid-19 bagi masyarakat. K-Medoids merupakan metode Analitis partisional clustering yang bertujuan untuk mendapatkan suatu set k-cluster di antara data yang paling mendekati suatu objek dalam pengelmpokan suatu data.. Hasil penelitian pengelompokan penyebaran covid-19 baru menunjukkan bahwa masyarakat yang berasal dari berbagai wilayah di Indonesia. Cirri-ciri dengan suhu badan di atas 36,9◦c dan dengan disertai demam dan batuk berkelanjutan menunjukkan salah satu ciri-ciri gejalah covid-19Kata Kunci - Algoritma K-Medoids, Clustering, Data Mining, Covid-19, Pengelompokan Data

This paper implements artificial neuralnetworkin predictingthe understanding level ofstudent'scourse.By implementing artificial neural network based on backpropagation algorithm, an institution can give a fair decision in prediction level of students' understanding of particular course / subject.This method was chosen because it is able to determine the level of students' understanding of the subject based on input from questionnaires given.The study was conducted into two ways, namely training and testing.Data will be divided into two parts, the first data for the training process and the second reading data of the testing process.The training process aims to identify or search for goals that are expected to use a lot of patterns.Thus, it will be able to produce the best pattern to train the data.After reaching the goal of training which is based on the best pattern, then it will be tested with new data to seeat the accuracy of the target data using Matlab 6.1 software.The results show that it can accelerate the process of prediction of students' understanding.By using architectural models 6-50-1 as the best model, some architectural models are tested and the result of prediction is reach to 87.75%.In other word, this model is good enough to make predictions on the level of students' understanding of the subject.

Coal is one of the most widely used energy sources in the world, and Indonesia is one of the coal exporting countries. Therefore, Indonesia's long-term availability of coal must be maintained, to support various industrial projects and the world economy. One way to maintain coal reserves is to predict the timing data of coal exports, to make it easier for the government to issue a coal export policy. In this study, the prediction method used is back propagation algorithm. The algorithm is able to solve many problems by building a well-trained model that shows good performance in some non-linear problems. The function used is bipolar, because this function is able to calculate data whose value is not stable. The data used in this study is the data of Coal Exports in Indonesia based on the main destination countries processed from customs documents of the Directorate General of Customs and Excise and Statistics Indonesia. This study uses 3 architectural models, namely: 4-5-1, 4-10-1 and 4-15-1. The best architectural model is 4-5-1, yielding 93% accuracy, Margin eror 7%, MSE 0,0117017098 with error rate 0.001 - 0.04. It is expected that these results can predict well.

The Internet today has become a primary need for its users. According to market research company e-Marketer, there are 25 countries with the largest internet users in the world. Indonesia is in the sixth position with a total of 112.6 million internet users. With the increasing number of internet users are expected to help improve the economy and also education in a country. To be able to increase the number of internet users, especially in Indonesia, it is necessary to predict for the coming years so that the government can provide adequate facilities and pre-facilities in order to balance the growth of internet users and as a precautionary step when there is a decrease in the number of internet users. The data used in this study focus on data on the number of internet users in 25 countries in 2013-2017. The algorithm used is Artificial Neural Network Backpropagation. Data analysis was processed by Artificial Neural Network using Matlab R2011b (7.13). This study uses 5 architectural models. The best network architecture generated is 3-50-1 with an accuracy of 92% and the Mean Squared Error (MSE) is 0.00151674.

Natural disasters are natural events that have a large impact on the human population. Located on the Pacific Ring of Fire (an area with many tectonic activities), Indonesia must continue to face the risk of volcanic eruptions, earthquakes, floods, tsunamis. Application of Clustering Algorithm in Grouping the Number of Villages / Villages According to Anticipatory / Natural Disaster Mitigation Efforts by Province With K-Means. The source of this research data is collected based on documents that contain the number of villages / kelurahan according to natural disaster mitigation / mitigation efforts produced by the National Statistics Agency. The data used in this study is provincial data consisting of 34 provinces. There are 4 variables used, namely the Natural Disaster Early Warning System, Tsunami Early Warning System, Safety Equipment, Evacuation Line. The data will be processed by clustering in 3 clushter, namely clusther high level of anticipation / mitigation, clusters of moderate anticipation / mitigation levels and low anticipation / mitigation levels. The results obtained from the assessment process are based on the Village / Kelurahan index according to the Natural Disaster Anticipation / Mitigation Efforts with 3 provinces of high anticipation / mitigation levels, namely West Java, Central Java, East Java, 9 provinces of moderate anticipation / mitigation, and 22 other provinces including low anticipation / mitigation. This can be an input to the government, the provinces that are of greater concern to the Village / Village According to the Natural Health Disaster Mitigation / Mitigation Efforts based on the cluster that has been carried out.Keywords: Data Mining, Natural Disaster, Clustering, K-Means

Artificial Intelligent

The purpose of this study is to determine and predict coffee exports in Indonesia based on the main destination countries for years to come. The results of this study are expected to be widely used for both government and private sector as an evaluation material in coffee, economic and business development. The data used in this study is Coffee Exports In Indonesia based on the main destination countries in 2006-2015. Data processed from customs documents of the Directorate General of Customs and Excise cited from Indonesia Statistics Publication. This research uses artificial neural network Polak-Ribiere updates which will be combined with bipolar activation function and linear function. The architectural model used there are 4, among others: 8-10-15-1, 8-15-10-1, 8-15-30-1 and 8-30-15-1. The best architectural model of the 4 models used is 8-10-15-1 with error rate of 0.001-0.06, alpha = 0.001, beta = 0.1, delta = 0.01 and gama = 0.1. The resulting accuracy is 86%.

Abstract Covid-19 is an infectious illness caused by a newly identified form of coronavirus. This is a new virus and illness that was previously unknown before the December 2019 outbreak in Wuhan, China. The number of confirmed cases of Covid-19 and the number of deaths due to this virus in Southeast Asia are increasing and quite alarming. Therefore this study will discuss the grouping of Cases and Deaths of COVID-19 in Southeast Asia. The method used is the K-Means Clustering Data Mining. By using this method the data that has been obtained can be grouped into several clusters, where K-Means Clustering Process is applied using RapidMiner tools. Data used are Country statistics, Area of recorded laboratory-confirmed cases of COVID-19, and April 2020 deaths from WHO (World Health Organization). Data is divided into 3 clusters: high (C1), medium (C2) and low (C3). The results obtained are that there are four countries with a high level cluster (C1), one country with a moderate level cluster (C2), and 6 countries with a low level cluster (C3). This can be an input for each country to increase awareness of the transmission of Covid-19.

Artificial Intelligent

Measles is one of the causes of death in children around the world which always increases every year. Although measles immunization programs have been implemented, the incidence of measles in children is still quite high. This study discusses the Implementation of Rapidminer with the K-Means Method (Case Study: Measles Immunization in Toddlers by Province). The increase in cases of measles in toddlers in Indonesia is a case that has never been separated from the government's attention. Data sources and research were obtained from the Central Statistics Agency (BPS). The data used in this study are data from 2004-2017 which consists of 34 provinces. The cluster process is divided into 3 (three) clusters, namely high cluster level (C1), medium cluster level (C2) and low cluster level (C3). So that the assessment for cases of immunization against measles based on high cluster province (C1) is 21 provinces for medium cluster (C2) of 12 provinces and for low cluster (C3) of 1 province. The results of the cluster can be used as input for the government, especially the provinces, so that provinces that enter the high cluster receive more attention and increase the socialization of measles immunization against children under five. Keywords: Data Mining, Measles, Clustering, K-means

This research proposes a decision support system in determining thesis exam graduation using AHP and TOPSIS method. The AHP method weighted the criteria to generate values for each criterion, in which the value of each criterion was used to obtain a ranking of some alternatives with TOPSIS. The criteria used for the assessment are 5 chapters (C1), neatness (C2), manners (C3), material delivery (C4) and material mastery (C5). Merging the AHP and TOPSIS methods can optimize the weighting of criteria values that affect the more objective alternative ranking results. The resulting Hamming distance is 96.2% and the Euclidean distance is 0.8096 for 95 students.