Penerapan Algoritma Backpropagation dalam Memprediksi Hasil Panen Tanaman Sayuran

This study aims to see the development of the number of vegetable crop yields in the following year. With this prediction, it is hoped that it can help the government and the community to be more careful in increasing the supply of crop stocks in order to meet the food needs of the people of Simalungun Regency. The data source is obtained from the Central Bureau of Statistics. In this study, researchers used the Backpropagation Algorithm. The Backpropagation Algorithm is an algorithm that functions to reduce the error rate by adjusting the weight based on the desired output and target. The results of this study show that the best architectural model is the 2-1-1 model with an accuracy rate of 75.0% and an epoch of 1392 iterations in 00:07 seconds. This research is expected to be a reference material in other studies that have the same research object and as a consideration for the government in making an even more accurate evaluation system

Penerapan Algoritma K-Means dalam Mengelompokkan Balita yang Mengalami Gizi Buruk Menurut Provinsi

The purpose of this study was to screen toddlers who were experiencing severe malnutrition according to province. Sources of research data used were obtained from the Ministry of Health of the Republic of Indonesia. The variables used are toddlers who experience malnutrition according to the Province. In this study using Data Mining Techniques using the K-means algorithm. It is expected that the results of this study can provide input to the central government to pay more attention to nutritional intake in infants, so as to increase the growth and development of toddlers in Indonesia. . And the data obtained by high clusters are 15 Provinsi yaitu (Aceh, Sumatera Utara, Nusa Tenggara Barat, Nusa Tenggara Timur, Kalimantan Barat, kalimantan Tengah, Kalimantan Selatan, Sulawesi Tengah, Sulawesi Selatan, Sulawesi Tenggara, Sulawesi Tenggara, Gorontalo, Sulawesi Barat, Papua Barat, Papua), dan cluster rendah ada 19 yaitu (Sumatera Barat, Riau, Jambi, Sumatera Selatan, Bengkulu, Lampung, Kep. Bangka Belitung, Kep. Riau, Dki Jakarta, Jawa Barat, Jawa Tengah, DI Yogyakarta, Jawa Timur, Banten, Bali, Kalimantan Timur, Kalimantan Utara, Sulawesi utara, Maluku Utara).

Memanfaatkan Algoritma K-Means Dalam Memetakan Potensi Hasil Produksi Kelapa Sawit PTPN IV Marihat

Based on data on the results of oil palm production in PTPN IV Marihat displays several locations with fruit yields that vary in number. For this reason, grouping of potential fruit-producing locations is needed to know which locations produce large or small numbers of palm fruit. The production sharing is usually done based on the location or block of harvesting oil palm fruit. Therefore, a method is needed to facilitate the grouping of fruit producing locations. With the K-Means clustering approach, the division of location groups can be done based on harvested area (Ha), production realization (kg) and harvest year. In this research, clustering of potential fruit-producing areas was carried out using the K-Means algorithm. By using K-Means aims to facilitate the grouping of a block with a lot of fruit production, and low. The result of this research is that C1 (highest) is 14 Harvest Block data, and C2 (lowest) is 11 Harvest Block data.

Klasifikasi Data Antroprometri Individu Menggunakan Algoritma Naïve Bayes Classifier

With the development of advances in computer technology today, most companies and organizations need a decision support system based on information systems, where the information is generally stored in the form of documents / text that is not structured. In this regard, a system for text management that is integrated with the decision support system is needed. One of them is the use of text data classification for anthropometric case studies of several samples. Anthropometry is a measurement of a person's body dimensions. The object of research is gender, first name, and height of a person. The research aims to determine the ratio of the number and height probability level of the number of men and women based on the input into an application using the Naïve Bayes Classifier method. The implementation design uses the Python programming language. The results showed that the height classification data frequency of women was more than the height classification data for men. And the number of height probability of a woman's body is greater than the number of height probability of a man's body.

Analisis Penilaian Kualitas Jenis Pelayanan Tebaik dengan Metode Analytic Network Process (ANP) di Kantor Dinas Kependudukan dan Pencatatan Sipil Kota Pematangsiantar

This study aims to determine the best service quality at the Pematangsiantar City Population and Civil Registration Office, which includes services for making Identity Cards (KTP), Family Cards (KK), birth certificates, marriage certificates and receipt making. The method used in this research is the Analytic Network Process (ANP) method. The data collection technique used is a questionnaire technique that is distributed directly to the people who come to take care of the needs of personal and family data files. The parameters used consist of the facilities provided, employee behavior, services, and provisions. Determining community satisfaction with a service can be seen from the quality of the type of service. The results of this study were obtained in rank-1 with a normal value of 0.49126400, rank-2 family cards with a value of 0.18988000, rank-3 birth certificates with a value of 0.16073800, marriage certificates rank-4 with a value of 0.09707200 and Finally, rank-5 receipt services with a value of 0.06104600 With this research it is hoped that it can help the Pematangsiantar City Population and Civil Registration Service to evaluate the services provided to the community in order to meet community expectations in terms of managing the needs of personal and family data files and knowing the types of best services.

Perbandingan Algoritma Boyer-Moore dan Brute Force pada Pencarian Kamus Besar Bahasa Indonesia Berbasis Android

String matching is an algorithm for matching a text to another text or also known as a text search. There are several algorithms that can be used for string matching, including the Boyer-Moore algorithm and the Brute Force algorithm. The Boyer-Moore algorithm is a string matching algorithm published by Robert S. Boyer and J. Strother Moore in 1977. This algorithm is considered the most efficient algorithm in general applications. The Boyer-Moore algorithm starts matching characters from the pattern on the right. While the Brute Force algorithm is an algorithm that matches a pattern with all text between 0 and n-m to find the existence of a pattern in the text. These two algorithms have different patterns in the search process. In this article, a comparative analysis of the performance of the Boyer-Moore and Brute Force algorithms is carried out in a case study of the search for the Big Indonesian Dictionary (KBBI) based on Android. The search process is carried out by searching based on words and word descriptions. The results of this study indicate that the criteria for running time, the Brute Force algorithm is faster than the Boyer-Moore algorithm with the total running time of the Brute Force algorithm is 168.3 ms in words, 6994.16 ms in word descriptions, while the Boyer-Moore algorithm for running time reached 304.7 ms on the word, 8654.77 ms on the word description. In the testing criteria based on related keywords, the two algorithms can display the same list of related keywords.

Penerapan Wireless Distribution System (WDS) Mesh Untuk Optimasi Cakupan Area Wi-Fi di UM Jember

One very rapid change in computer networks is the use of Wireless Local Area Network (WLAN) to access systems both locally and the internet. One way to add an Access Point (AP) so as not to change the configuration of the running software is use the Wireless Distribution System Mesh (WDS) network. The use of WDS mesh at Universitas Muhammmadiyah Jember (UM Jember) enables a slightly different wireless configuration to reduce the connection loss in the user due to the wireless network area coverage. One step is use AP devices into one unit to handle the case of a connection break by utilizing a network service that is WDS Mesh. WDS Mesh can cover Wi-Fi areas at UM Jember, and the results of testing and analysis of client devices for APs that have been configured WDS Mesh with parameters Signal Strength, CCQ, Signal to Noise Ratio Ratio, Throughput is Excellent.

Penentuan Cluster Optimum pada Tingkat Pengangguran dan Tingkat Kemiskinan di Jawa Timur Menggunakan Algoritma Fuzzy C-Means

There are many methods used in resolving data clustering. One of them is the Fuzzy C-Means (FCM) method, which is a reliable method to solve clustering problems in the East Java region. This study aims to determine the optimum cluster in the East Java region which can help the government to identify problems and assist policymaking in regencies/cities in East Java province. The research process uses data from the central statistical agency, namely the unemployment rate and poverty rate from 2010 to 2015. In this study, the Davies Bouldin Index (DBI) is used as a cluster validation test for determining the optimum cluster. Unemployment rate and poverty rate data were analyzed using RStudio. From the calculation of the FCM method and also the determination of the optimum cluster results obtained in 2 clusters with a DBI value of 1.2759, 3 clusters with a DBI value of 0.9937, 4 clusters with a DBI value of 0.8737. The optimum cluster is in 4 clusters with a minimum DBI value.

Perbandingan Metode Double Exponential Smoothing dan Least Square untuk Sistem Prediksi Hasil Produksi Teh

Tea is one of the mainstay commodities of Indonesian plantation. In order to meet market demand, it is necessary to plan the right production needs, so that the amount of production capacity and market demand is balanced. To meet the needs of the right production requires good planning. The way that can be done is by making predictions. In this study, the prediction of tea production was carried out using the Double Exponential Smothing and Least Square methods. From the test results, it was found that the MAPE value of the Double Exponential Smoothing method, the most optimal α value is α 0.1 with a MAPE value of 18.084% and for the Least Square method the MAPE value is 17.008%.

Sistem Pakar Diagnosa Penyakit Tanaman Bawang Merah Menggunakan Metode Certainty Factor

The lack of knowledge of farmers and the unequal counseling about onion diseasefrom experts is a strong reason for the difficulty of overcoming or immediately treateddiseases of onions, for this requires early diagnosis of disease onion plants. Thisresearch uses the Certainty Factor method. This method uses the certainty of an experton the symptoms of each disease. By determining the value of MB (Measure ofBelieve) as the level of confidence in the hypothesis and MD (Measure of Disbelieve)the level of distrust of the hypothesis. After using the Certainty Factor formula, thevalue of each disease will be generated from the new symptoms owned by using thehighest value of each disease, so that is the result of disease diagnosis in shallots. Thisstudy uses as many as 35 data as testing and from these data obtained an accuracyvalue of 85.71%