Claim Missing Document
Check
Articles

Found 15 Documents
Search

Penerapan Algoritma K-Means dan K-Medoids Clustering untuk Mengelompokkan Tindak Kriminalitas Berdasarkan Provinsi Hotma Dame Tampubolon; Suhada Suhada; M Safii; Solikhun Solikhun; Dedi Suhendro
Jurnal IT UHB Vol 2 No 2 (2021): Jurnal Ilmu Komputer dan Teknologi
Publisher : Universitas Harapan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (499.244 KB) | DOI: 10.35960/ikomti.v2i2.703

Abstract

Kriminalitas merupakan masalah yang sering terjadi di kehidupan sehari-hari dan dimana saja termasuk di berbagai provinsi yang ada di Indonesia. Dengan banyaknya tindak kriminalitas di Indonesia, diperlukan adanya pengelompokan daerah rawan tindak kriminalitas di Indonesia berdasarkan provinsi sebagai salah satu usaha untuk menentukan suatu daerah memerlukan pengawasan ekstra atau tidak. Pada penelitian ini akan dilakukan pengelompokkan tindak kriminalitas dengan menggunakan algoritma K-Means dan K-Medoids clustering. Data diolah menjadi dua cluster yaitu cluster tingkat tindak kriminalitas tinggi (C1) dan cluster tingkat tindak kriminalitas rendah (C2). Hasil algoritma K-Means diperoleh dengan C1 memiliki 6 anggota dan C2 memiliki 28 anggota. Sedangkan hasil algoritma K-Medoids diperoleh dengan C1 memiliki 7 anggota dan C2 memiliki 27 anggota. Perbedaan jumlah klaster pada kinerja tiap algoritma memiliki pola perhitungan yang berbeda sehingga keunggulan kinerja algoritma tergantung pada data yang akan diproses.
Machine Learning Algorithm for Determining the Best Performance in Predicting Turmeric Production in Indonesia Dendy Setiawan; Solikhun Solikhun
International Journal of Mechanical Computational and Manufacturing Research Vol. 11 No. 2 (2022): August: Mechanical Computational And Manufacturing Research
Publisher : Trigin Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (399.263 KB) | DOI: 10.35335/computational.v11i2.1

Abstract

The herb that has many uses in everyday life is turmeric. Not only in Indonesia but in other countries also use turmeric for consumption. Therefore, by making predictions on the level of turmeric production in the country, so that the government or other parties can use this as a reference and reference to solve problems. The method we use is Resilient Backpropagation where this method is one of the methods that is often used to forecast data. By using turmeric plant production data in Indonesia from 2016-2021 taken on the website of the Indonesian Central Statistics Agency. According to the data to be tested a network architecture model is formed, namely 2-15-1, 2-20-1, 2-25- 1 and 2-30-1. From this model, the Fletcher-Reeves method is used. From the 4 models that have been trained and tested, a 2-15-1 model is obtained to be the best architectural model for each method. The accuracy level of the Fletcher-Reeves method with the 2-15-1 model has an MSE value of 0.002481597.
Artificial Neural Network (ANN) Implementation with Conjugate Gradient Algorithm to Predict Sumatran Melinjo Plant Production Oktarihni Haloho; Solikhun Solikhun
International Journal of Mechanical Computational and Manufacturing Research Vol. 11 No. 2 (2022): August: Mechanical Computational And Manufacturing Research
Publisher : Trigin Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (535.34 KB) | DOI: 10.35335/computational.v11i2.3

Abstract

Melinjo is an annual plant with open seeds. Tree-shaped and has two houses called dioecious or there are males and females. Melinjo is often found in dry and tropical areas. Indonesia can be one that produces melinjo as a trade product in large quantities. Melinjo is collected and shipped natural products after 5-6 long time after sowing of seeds. In West Sumatra, it is detailed that each year produces 20,000 to 25,000 natural melinjo products and the seed generation reaches 80 to 100 kg per tree per year. Therefore, it is important to know every need for melinjo by anticipating the number of generations of Melinjo using a Manufacturing Artificial Neural System with Backpropagation strategy. With the neural structure made, it will be easier to carry out this investigation. Where the machine learning method can help to find the best performance value and value from the simple data studied. The Matlab2011b application has a feature that helps to calculate the best performance and value with the help of the Conjugate Gradient algorithm. After testing using 5 samples, namely: 4-10-1, 4-15-1, 4-20-1,4-25-1, 4-30-1. Of the five tests, the best results are on data 4-15-1 with the MSE/Performance value of 0.011154591. 4-15-1, 4-20-1,4-25-1, 4-30-1. Of the five tests, the best results are on data 4-15-1 with the MSE/Performance value of 0.011154591. 4-15-1, 4-20-1,4-25-1, 4-30-1. Of the five tests, the best results are on data 4- 15-1 with the MSE/Performance value of 0.011154591.
Development of Quantum Circuit Architecture on Quantum Perceptron Algorithm for Classification of Marketing Bank Data  Mochamad Wahyudi; Solikhun Solikhun
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 7 No 1 (2023): February 2023
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v7i1.4526

Abstract

The creation of quantum circuit architecture based on the quantum perceptron algorithm to classify marketing bank data is proposed in this work. A quantum circuit is a quantum gate made up of two quantum gates. Quantum bits are used in this study's computation. The primary proposed learning method was not ideal, which is the context of this study. The percentage of qubits measurement value is still 90.7 percent. It is essential to raise the value of the qubit rate. Using the IBM Quantum Experience quantum computer, researchers measured, trained, and tested the quantum circuit architecture. Bank marketing data from the UCI Machine Learning Repository was used. A quantum circuit architecture model results from this research the quantum circuit measurement results.
Design and Build of Automatic Hand Sanitizer Using Arduino Budi Paul Sitompul; Solikhun Solikhun; Widodo Saputra; Indra Gunawan; Sumarno Sumarno
Eduvest - Journal of Universal Studies Vol. 1 No. 3 (2021): Journal Eduvest - Journal of Universal Studies
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (2632.892 KB) | DOI: 10.59188/eduvest.v1i3.27

Abstract

An automatic handwashing deviceis a handwashing devicethat works automatically by utilizing an infrared sensor as a hand detector and using the Arduino Uno as the main controller. In this study, the authors discussed the design of an Automatic Handwashing Devicethat is placed on the hand-sanitizer faucet using the InfraRed sensor (detecting hand movements) based on Arduino Uno. This system includes the design of hardware (Hardware) and software (Software). Researchers use descriptive analysis techniques that are presented in table form. In this study, the authors conducted an analysis and design of the devices used to build the input and output processes including System Algorithms, Research Design, and Research Flowcharts. The results showed that the Hands Sanitizer deviceautomatically runs well and can be assembled using Arduino Uno microcontroller components and IR (Infrared) sensors. In making this program, the Arduino Uno application software is needed.
The Implementation Of The Fletcher-Reeves Algorithm In Predicting The Growth Of Forest Plant Cultures Dwi Ramahdhani; Solikhun Solikhun
International Journal of Engineering and Computer Science Applications (IJECSA) Vol 2 No 1 (2023): March 2023
Publisher : Universitas Bumigora Mataram-Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/ijecsa.v2i1.2418

Abstract

Forest protection and development are essential because forests are the world's lungs. In addition, the HTI organization (modern manor backwoods) began to hide again. However, due to the great interest in wood to be used as raw material for material and property production lines, large organizations started to develop hamlet wood which was then marketed abroad, such as pressed wood, rattan, sawn timber, and done jobs for individuals in the area around the hamlet. By making a prediction, knowledge about the growth of forest plants can be known so that they can anticipate or minimize the risks that may arise. They can assist in determining policies and making decisions. This study aims to predict the growth of forest plants in the following year using an Artificial Neural Network Algorithm. The information used in this study is from the Central Bureau of Statistics from 2011 to 2022. The method of implementing this research uses the Fletcher-Reeves Algorithm, one of the Artificial Neural Network methods using 5 models, including 7-10-1, 7-15- 1, 7-20-1, 7-25-1, and 7-30-1. Of the five models, the structural model is 7-20-1 with an MSE value of 0.00037397. It can be said that this model can be used because it produces a fast combination and a short period of time.
The Performance Machine Learning Powel-Beale for Predicting Rubber Plant Production in Sumatera Siska Rama Dani; Solikhun Solikhun; Dadang Priyanto
International Journal of Engineering and Computer Science Applications (IJECSA) Vol 2 No 1 (2023): March 2023
Publisher : Universitas Bumigora Mataram-Lombok

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/ijecsa.v2i1.2420

Abstract

This study aims to predict rubber plants in Sumatra; rubber plants have a relatively high economic value; rubber sap must be cultivated because it is a product of the rubber plant, which is the raw material for the rubber industry, so in large quantities. Therefore, rubber sap, the selling value will increase so that it can increase farmers' income. Rubber production in Sumatra experiences ups and downs; therefore, this study aims to predict rubber plants using the Powell-Beale algorithm method, one of the Artificial Neural Network methods often used for data prediction, implemented using Matlab software. That supports it. This study does not discuss the prediction results. Still, it discusses the ability of the Powell-Beale algorithm to make predictions based on datasets of rubber plant production in recent years obtained from the Central Statistics Agency. Based on this data, a network architecture model will be formed and determined, including 6-10-1, 6-15-1, 6-30-1, 6-45-1 and 6-50-1. The best architecture is 6-15-1, with the lowest Performance/MSE test score of 0.00791984.
Q-Madaline: Madaline Based On Qubit Khodijah Hulliyah; Solikhun Solikhun
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 7 No 5 (2023): October 2023
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v7i5.5080

Abstract

This research focuses on developing the MADALINE algorithm using quantum computing. Quantum computing uses binary numbers 0 or 1 or a combination of 0 and 1. The main problem in this research is how to find other alternatives to the MADALINE algorithm to solve pattern recognition problems with a quantum computing approach. The data used in this study are heart failure data to predict whether a patient is at risk of death. The data source comes from KAGGLE, consisting of 299 data with 12 symptoms and one target, alive or dead. The result of this study is an alternative to the MADALINE algorithm that uses quantum computing. The precision of the test results with MADALINE with a learning rate of 0.1 = 100% with 2 epochs. The accuracy of the test results using a quantum approach with a learning rate of 0.1 is 85.71%. The results of this study can be an alternative to the MADALINE algorithm with a quantum computing approach, although it has not shown better accuracy than the classical MADALINE algorithm. More research is needed to produce better accuracy with larger data.
Application of Numerical Measure Variations in K-Means Clustering for Grouping Data Relita Buaton; Solikhun Solikhun
MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer Vol 23 No 1 (2023)
Publisher : LPPM Universitas Bumigora

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30812/matrik.v23i1.3269

Abstract

The K-Means Clustering algorithm is commonly used by researchers in grouping data. The main problem in this study was that it has yet to be discovered how optimal the grouping with variations in distance calculations is in K-Means Clustering. The purpose of this research was to compare distance calculation methods with K-Means such as Euclidean Distance, Canberra Distance, Chebychev Distance, Cosine Similarity, Dynamic TimeWarping Distance, Jaccard Similarity, and Manhattan Distance to find out how optimal the distance calculation is in the K-Means method. The best distancecalculation was determined from the smallest Davies Bouldin Index value. This research aimed to find optimal clusters using the K-Means Clustering algorithm with seven distance calculations based on types of numerical measures. This research method compared distance calculation methods in the K-Means algorithm, such as Euclidean Distance, Canberra Distance, Chebychev Distance, Cosine Smilirity, Dynamic Time Warping Distance, Jaccard Smilirity and Manhattan Distance to find out how optimal the distance calculation is in the K-Means method. Determining the best distance calculation can be seen from the smallest Davies Bouldin Index value. The data used in this study was on cosmetic sales at Devi Cosmetics, consisting of cosmetics sales from January to April 2022 with 56 product items. The result of this study was a comparison of numerical measures in the K-Means Clustering algorithm. The optimal cluster was calculating the Euclidean distance with a total of 9 clusters with a DBI value of 0.224. In comparison, the best average DBI value was the calculation of the Euclidean Distance with an average DBI value of 0.265.
COMPARISON OF ADALINE AND HEBBIAN ALGORITHMS ON PATTERN RECOGNITION WITH QUANTUM COMPUTING APPROACH Taufik Baidawi; Heri Kuswara; Muhammad Ridwan Effendi; Solikhun Solikhun
JITK (Jurnal Ilmu Pengetahuan dan Teknologi Komputer) Vol. 10 No. 1 (2024): JITK Issue August 2024
Publisher : LPPM Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/jitk.v10i1.4941

Abstract

In this research, a quantum computational approach was employed to enhance the Adaline and Hebbian algorithms. A comparative analysis of these algorithms was conducted, focusing on their performance, specifically the accuracy of test outcomes. The investigation was carried out utilizing a hepatitis prediction dataset comprising data related to individuals diagnosed with hepatitis, with observations on whether they were alive or deceased. The dataset encompassed 19 distinctive symptoms, with 18 symptoms utilized for hepatitis pattern recognition and ten symptoms employed as simulated test data for the Adaline and Hebbian algorithms integrated with quantum computation methodologies. The findings of the study revealed advancements in the Adaline and Hebbian algorithms, as influenced by the integration of a quantum computational framework. Notably, the simulation testing outcomes exhibited a remarkable accuracy rate of 100% for both the Adaline and Hebbian algorithms. Consequently, the results underscore the comparable performance of the two algorithms, highlighting their identical accuracy levels.