Claim Missing Document
Check
Articles

Found 28 Documents
Search

Pengelompokan Tindak Kejahatan Berdasarkan Tempat Kejadian Perkara di Kota Binjai Menggunakan Metode Clustering : Studi kasus: Polres Binjai Herdina Putri Ahmadi; Magdalena Simanjuntak; Muammar Khadapi
Saturnus : Jurnal Teknologi dan Sistem Informasi Vol. 3 No. 3 (2025): Juli : Saturnus : Jurnal Teknologi dan Sistem Informasi
Publisher : Asosiasi Riset Teknik Elektro dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61132/saturnus.v3i3.933

Abstract

Crime is a social issue that continues to evolve alongside increasing community activity and regional development. This study aims to Cluster crime data in Binjai City based on the location of incidents using the K-Means algorithm and the Cross Industry Standard Process for Data Mining (CRISP-DM) approach. The data were obtained from the Binjai Police Department, with attributes including the type of crime, time of occurrence, and location, categorized by district. A comprehensive data preprocessing stage was carried out, involving the extraction of information from raw data, normalization of crime type labels, and conversion of categorical data into numerical form using label encoding. The optimal number of Clusters was determined using the Silhouette score method, which yielded the best result at K = 10. The Clustering results were further evaluated using the Davies-Bouldin Index (DBI) to ensure Cluster quality. The analysis revealed that Binjai Utara District has the highest number of crimes, particularly aggravated theft (curat), which frequently occurs from early morning to late morning. This Clustering is expected to provide valuable insights for authorities in formulating more targeted and data-driven regional security strategies.
Penerapan Metode K-Means Clustering untuk Pengelompokan Minat Konsumen terhadap Pengguna Jasa Layanan pada Kantor Pos Binjai Andrean Samuel Siahaan; Rusmin Saragih; Magdalena Simanjuntak
Polygon : Jurnal Ilmu Komputer dan Ilmu Pengetahuan Alam Vol. 2 No. 5 (2024): September : Polygon : Jurnal Ilmu Komputer dan Ilmu Pengetahuan Alam
Publisher : Asosiasi Riset Ilmu Matematika dan Sains Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62383/polygon.v2i5.236

Abstract

This research aims to apply the K-Means Clustering method in grouping consumer interests regarding the use of services at the Binjai Post Office. The Post Office is part of a state-owned enterprise in North Sumatra Province with the main task of providing postal and logistics services. Postal services remain one of the most important means of communication, especially for sending packages, letters, and documents. However, with various services and diverse consumer needs, post offices can provide more effective and relevant services. The K-Means Clustering method is a classification technique based on machine learning algorithms used to identify patterns present in consumer interest data. The data used in this research includes various related variables, namely the type of delivery, total cost, and delivery time. The results of the clustering process conducted using 3 clusters indicate that there is a grouping of consumer data based on preferences for using delivery services. In group 1, there are (21 data points) with a centroid at coordinates (C1) 2; 4.3810; 3.5238. In group 2, there are (124 data points) with a centroid at coordinates (C2) 3; 2.0565; 3.1452. In group 3, there are (387 data points) with a centroid at coordinates (C3) 3.6925; 1.1370; 1.7209. This research shows that the application of K-Means Clustering can enhance the understanding of consumer interests and assist in the development of more targeted strategies to optimally meet needs.
Pengelompokan Data Kasus Keracunan Makanan Biologis Berdasarkan Faktor Penyebab Menggunakan Metode Clustering Dwi Astuti; Relita Buaton; Magdalena Simanjuntak
Bridge : Jurnal Publikasi Sistem Informasi dan Telekomunikasi Vol. 2 No. 4 (2024): Bridge: Jurnal Publikasi Sistem Informasi dan Telekomunikasi
Publisher : Asosiasi Riset Teknik Elektro dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/bridge.v2i4.199

Abstract

Cases of biological food poisoning can be caused by several causative factors, one of which is a food processing site that does not meet health requirements. According to the BPOM report (2016) cases of food poisoning in Indonesia in 2016 reached 1,068 cases. In 2016, 60 extraordinary events (KLB) of food poisoning were reported by 31 BB/BPOM throughout Indonesia. From the many cases of food poisoning that occur, it is necessary to take action in prevention by processing data on existing cases of poisoning to follow up on existing problems to reduce the number of cases of food poisoning by using a system on a computer so that the managed data can be processed quickly to obtain further information. Therefore the author wants to use a system with the clustering method to assist in processing data on biological poisoning cases grouping objects based on the characteristics of each object. Based on the research conducted, it can be seen that in cluster 2 in the dasta group of biological poisoning cases there are 11 data with centroid point age (x) 2, namely 12-16 years, centroid point on the type of poisoning (y) 6.36, namely sandwiches, and centroid point on the causative factor (z) 2.9, namely Gram-negative rod-shaped bacteria which are usually found in the intestines of humans and warm-blooded animals.
Penerapan Metode Association Rule untuk Mengetahui Faktor-Faktor yang Mempengaruhi Kelahiran Bayi Lala Arika; Yani Maulita; Magdalena Simanjuntak
Bridge : Jurnal Publikasi Sistem Informasi dan Telekomunikasi Vol. 2 No. 4 (2024): Bridge: Jurnal Publikasi Sistem Informasi dan Telekomunikasi
Publisher : Asosiasi Riset Teknik Elektro dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/bridge.v2i4.241

Abstract

Birth problems are one of the problems that have not been resolved in various regions, where an average mother gives birth to three to four children. The increase in population due to births will also affect various aspects of development, and pose a big risk to ensuring community welfare. For example, opportunities to obtain educational facilities, job opportunities, health insurance, housing and can increase opportunities for increasing poverty and crime. To find out which factors influence the birth of a baby, an association rule is needed to find out which factors influence the birth of a baby which can be seen from several criteria such as a woman who has a low level of education or a bachelor's degree, a woman who marries at an old age. , or women who marry underage, give birth naturally or surgically. Association rules are a data mining technique for determining the relationship between items in a set of data that has been determined. By determining min support 0.01, confidence 0.1 and 7 itemsets, the results obtained are 25 data items with varying min support and confidence with a maximum support x confidence result of 100%. By using the a priori method, 14 of the best rules were produced by producing the most up-to-date information.
Pengelompokan Penyakit pada Pasien Berdasarkan Usia dengan Metode K-Means Clustering Maida Andriani; Akim Manaor Hara Pardede; Magdalena Simanjuntak
Bridge : Jurnal Publikasi Sistem Informasi dan Telekomunikasi Vol. 2 No. 4 (2024): Bridge: Jurnal Publikasi Sistem Informasi dan Telekomunikasi
Publisher : Asosiasi Riset Teknik Elektro dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/bridge.v2i4.246

Abstract

This research aims to cluster disease data based on patient age using the K-Means method at RSUD Dr. RM. Djoelham. In this case study, the clustering method with the K-Means algorithm is used to group patients based on patient age, address and type of disease. With this method, information can be obtained regarding patient grouping patterns based on age at Dr. RM. Djoelham, who helps identify the closest relationships between patient groups and provides insight into the distribution of disease across age groups, regions and types of disease suffered.This research was conducted at RSUD Dr. RM. Djoelham by loading data from patients treated at the hospital. The data used is 1,100 patient data from 2022-2024 which has been recorded by the hospital. This patient data will be analyzed using 3 variables in the research, namely Patient Age (C1), Address (C2), and Type of Disease (C3). With the results, cluster 1 contains 320 data, cluster 2 contains 326 data, and cluster 3 contains 454 data.
Signature Recognition Using Backpropagation Artificial Neural Network Method Layla Mutiara Hasibuan; Achmad Fauzi; Magdalena Simanjuntak
International Journal of Health Engineering and Technology Vol. 1 No. 2 (2022): IJHE-JULY 2022
Publisher : CV. AFDIFAL MAJU BERKAH

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (821.125 KB) | DOI: 10.55227/ijhet.v1i2.18

Abstract

A signature is a sign or symbol that is a miniature version of its owner. A signature is also a biometric feature that can be used to verify a person's identity. The signature used as a personal identification as well as the presence of a signature in a document states that the party who signed, knows and approves or as ratification of the entire contents of the document and becomes legal evidence. Signature recognition is done using an artificial neural network with backpropagation algorithm. In the backpropagation algorithm, signatures are trained to recognize a person's signature with some data such as target data, training data and test data. Then the network is tested for networking. The results of the application are used to recognize signature recognition using the backpropagation method obtained with different accuracy according to the original data obtained from feature extraction. Where the lowest accuracy is 30% and the highest accuracy is 100%
The Artificial Neural Network Predicts The Number Of Smart Indonesian Card Recipients Using The Backpropagation Algorithm Shella Nadya; Yani Maulita; Magdalena Simanjuntak
International Journal of Health Engineering and Technology Vol. 1 No. 3 (2022): IJHET-SEPTEMBER 2022
Publisher : CV. AFDIFAL MAJU BERKAH

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (804.057 KB) | DOI: 10.55227/ijhet.v1i3.43

Abstract

The Smart Indonesia Card is a form of implementing the Smart Indonesia Program which is the flagship program of President Joko Widodo. The Smart Indonesia Card program supports the realization of the 9-year compulsory education program for basic education and universal secondary education or 12-year compulsory education. However, in essence, in processing the Smart Indonesia Card, errors still occur in predicting the needs of students who really need the assistance. Unpredictable gifts include students per department. In dealing with the provision of Indonesia Smart Card assistance, predictions are needed in the distribution of funds so that the distribution can be carried out evenly according to students who need the Indonesia Smart Card funds.
Rancang Bangun Solar Tracker Otomatis pada Pengisian Energi Panel Surya Berbasis Internet of Things (IoT) Firmando Saragih; Realita Buaton; Magdalena Simanjuntak
Router : Jurnal Teknik Informatika dan Terapan Vol. 2 No. 3 (2024): September : Router : Jurnal Teknik Informatika dan Terapan
Publisher : Asosiasi Riset Teknik Elektro dan Informatika Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62951/router.v2i3.220

Abstract

This study aims to design and develop an automatic solar tracker system based on the Internet of Things (IoT) to enhance the efficiency of energy collection in solar panels. The system utilizes key components such as the ESP32 microcontroller, LDR sensors, servo motors, and the Blynk platform to monitor performance in real-time. The solar tracker is designed to follow the movement of the sun, ensuring that the solar panels are always positioned optimally to receive sunlight throughout the day. Testing indicates that this system improves solar energy absorption efficiency compared to static solar panel systems. Furthermore, the integration of IoT allows for more effective and efficient remote control and monitoring. Thus, this technology not only offers improvements in energy efficiency but also provides a practical solution for better and more sustainable solar energy management.