Claim Missing Document
Check
Articles

Found 20 Documents
Search

Pemodelan Klasifikasi Untuk Menentukan Penyakit Diabetes dengan Faktor Penyebab Menggunakan Decision Tree C4.5 Pada Wanita Nining Nur Habibah; Alwis Nazir; Iwan Iskandar; Fadhilah Syafria; Lola Oktavia; Ihda Syurfi
Jurnal Sistem Komputer dan Informatika (JSON) Vol 4, No 4 (2023): Juni 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v4i4.6202

Abstract

Diabetes is closely related to the pancreas, where the pancreas produces the natural hormone insulin, but its function is problematic which causes an increase in blood sugar levels in the body. Rising blood pressure can affect organ function in damaging the function of organs in a person's body such as the kidneys, heart and brain. Where makes a person have a history of diabetes. Diabetes that attacks adults can be prevented through exercise and a regular and healthy diet. According to the International Diabetes Federation (IDF) organization, it is estimated that at least 19.5 million Indonesian people between the ages of 20 and 79 will suffer from diabetes in 2021. China is in first place with diabetes with 140.9 million people. India is next in line with the number of people with diabetes of 74.2 million people. Therefore, early diagnosis is very important because it aims to reduce diabetes and diabetes complications in the future. It is necessary to collect data on patients with diabetes who are expected to be able to do prevention. Therefore applying classification techniques with data mining with the C4.5 algorithm. Where the classification can achieve better accuracy. Algorithm C4.5 is generally used in determining the nodes of a decision tree. Based on the test results, the accuracy is 76.67 percent, the precision is 72 percent, and the recall is 41.67 percent.
Penerapan Algoritma K-Medoids Pada Clustering Penerima Bantuan Pangan Non Tunai (BPNT) Tiara Ramayanti; Elin Haerani; Jasril Jasril; Lola Oktavia
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 7, No 3 (2023): Juli 2023
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v7i3.6475

Abstract

Bantuan Pangan Non Tunai (BPNT) is assistance distributed by the government to underprivileged communities to ease the financial burden that is increasingly burdening their lives. In a number of cases, it was found that the number of people who received BPNT was not properly targeted, so it was necessary to analyze the pattern of the characteristics of BPNT recipients so that the assistance was right on target. There are many criteria that must be considered to determine the people who are entitled to receive BPNT, so an appropriate algorithm is needed to determine the right cluster when analyzing characteristic patterns. This study applies the K-Medoids algorithm to classify BPNT data obtained from Firza Syahputra's research in 2020–2021, with a total of 732 attributes, so that the government can consider the factors that characterize beneficiaries. Perform tests using the Silhouette coefficient, which is useful for maximizing clustering results. The clustering result is three clusters, and the silhouette coefficient is 0.4439221599010089. The results of the analysis show that clustering performed using the K-Medoids algorithm can assume that clusters are grouped according to grouping: cluster 0 is eligible to receive BPNT, cluster 1 is considered, and cluster 2 is not eligible to receive BPNT.
Penerapan Fuzzy C-Means Pada Klasterisasi Penerima Bantuan Pangan Non Tunai Sola Huddin; Elin Haerani; Jasril Jasril; Lola Oktavia
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 4 No. 1 (2023): Agustus 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v4i1.988

Abstract

One of the social assistance programs routinely provided by the government to Beneficiary Families (KPM) to overcome poverty problems in Indonesia at this time is Non-Cash Food Assistance (BPNT). The Pekanbaru City Social Service itself in distributing BPNT still experiences obstacles, such as the provision of assistance that is less targeted due to the absence of a system that is able to determine the recipient of aid appropriately. This research applies the Fuzzy C-Means Clustering method to analyze KPM data using MATLAB tools. This algorithm allows overlap between data groups and classifies KPM based on their characteristic patterns. This algorithm takes into account the membership level of each data in each group, thus providing more flexible results and not categorizing data rigidly. The results of the application of the FCM Clustering method in this study form two clusters, where the first cluster contains 331 data while in the second cluster there are 351 data. Testing the results of FCM clustering conducted using the Silhouette Coefficient method produces an average coefficient value of 0.426653079. Based on the value of the test results that have been carried out, the FCM algorithm is considered capable of forming clusters on BPNT data
Application of K-Means Algorithm on Clustering Recipients of Non-Cash Food Assistance (NCFA) Said Nanda Saputra; Elin Haerani; Jasril Jasril; Lola Oktavia; Fadhilah Syafria
CESS (Journal of Computer Engineering, System and Science) Vol 8, No 2 (2023): July 2023
Publisher : Universitas Negeri Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24114/cess.v8i2.48026

Abstract

Persoalan Kemiskinan pada berbagai daerah Indonesia menjadi fokus perhatian. Program BPNT (Bantuan Pangan Non Tunai) bermaksud memangkas biaya pangan dan membagikan gizi yang sepadan terhadap KPM (Keluarga Penerima Manfaat). Penelitian ini menerapkan algoritma K-Means untuk menganalisis pola karakteristik penerima BPNT di Pekanbaru. Data yang digunakan berasal dari penelitian sebelumnya oleh Firza Syahputra dan dari Dinas Sosial Kota Pekanbaru tahun 2020-2021 dengan 732 data dan 41 parameter. Penerapan K-Means dilakukan melalui Google Colab. Melalui data mining dan metode clustering, ditemukan dua klaster dengan 666 data dalam klaster 1 dan 16 data dalam klaster 2. Evaluasi menggunakan Silhouette Score menunjukkan hasil yang baik, dengan nilai 0.9169796594018274. Penelitian ini berpotensi membantu pemerintah dalam mengambil keputusan yang efektif selama penyebaran bantuan pangan non tunai kepada rakyat yang membutuhkan. Dengan demikian, algoritma K-Means Clustering dapat mengidentifikasi pola karakteristik penerima BPNT dan membedakan kelompok yang layak dan tidak layak menerima bantuan.Poverty issues in various parts of Indonesia are the focus of attention. The NCFA (Non-Cash Food Assistance) program's purpose are to lower food consumption and give Beneficiary Families (BF) a healthy diet. The k-means technique use in this study to assess the distinctive patterns of NCFA grantees in Pekanbaru. The data used comes from previous research by Firza Syahputra and from Social Affairs Office Pekanbaru in 2020-2021 with 732 data and 41 parameters. The application of k-means is done through Google Colab. Through data mining and clustering methods, two clusters were found with 666 data in cluster 1 and 16 data in cluster 2. Evaluation using Silhouette Score showed good results, with a value of 0.9169796594018274. This research has the potential to assist the government in making effective decisions in distributing non-cash food help people in need. For the result, the k-means Clustering technique is able to recognize the traits of NCFA recipients and identify groups that are and are not eligible for aid.
The Success Factors in Measuring the Millennial Generation’s Energy-Saving Behavior Toward the Smart Campus Lola Oktavia; Okfalisa Okfalisa; Pizaini Pizaini; Rahmad Abdillah; Saktioto Saktioto
Indonesian Journal of Electrical Engineering and Informatics (IJEEI) Vol 11, No 3: September 2023
Publisher : IAES Indonesian Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52549/ijeei.v11i3.4885

Abstract

The millennial generation has a pivotal role in leading the industrial digital revolution. Energy-saving behavior and millennials’ awareness of energy consumption for educational context become crucial in performing a smart campus. This study tries to identify the success factors in measuring the millennial generation’s energy-saving Behavior toward the smart campus. The measurement model considers two significant constructs, including energy-saving attitudes with energy-saving education (organizational saving climate); energy-saving education and environment knowledge (personal saving climate); and energy-saving information publicity as sub-indicators, and construct energy-saving Behavior viz sub-indicators Behavior regarding energy and behavior control. In order to determine the preference level of each indicator and sub-indicator, the Fuzzy Analytical Hierarchy Process (Fuzzy-AHP) approach was executed by disseminating the questionnaire to 100 respondents from energy practitioners, students, and academicians in Indonesia. The calculation reveals that the energy-saving behavior construct has a higher priority value (0.94) than the energy-saving attitude (0.06). Meanwhile, energy-saving education and environment knowledge (personal saving climate) have been analyzed at the cutting-edge sub-indicator, followed by energy-saving information publicity and education (organizational saving climate). In addition, the sub-indicator for behaviors regarding energy becomes more demanding compared to behavioral control. As a novelty, the priority analysis of this Model aids the management of the campus and government in developing smart campus policies and governance. This Model can be used as a guideline for the management level to execute the smart campus practices. Thus, the effectiveness and optimization of smart campus transformation can be cultivated and accelerated. Besides, the potential coming of risks can be avoidable.
Pengukuran Tingkat Layanan Helpdesk Menggunakan COBIT 5 Febby Kurniawan; Novriyanto; Elin Haerani; Lola Oktavia
KLIK: Kajian Ilmiah Informatika dan Komputer Vol. 4 No. 3 (2023): Desember 2023
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/klik.v4i3.1474

Abstract

The Riau Provincial Information and Statistics Communication Service is a government agency tasked with formulating policies, conducting evaluations and reporting in the field of information and communication technology in various sectors of society. The Riau Provincial Information and Statistics Communication Agency has one of the services, namely a helpdesk to assist in handling problems related to the use of information technology. The helpdesk is one of the most important parts in the Riau Provincial Information and Statistics Communication Service because it is a liaison for each Regional Apparatus Organization (OPD), but the helpdesk at the Riau Provincial Information and Statistics Communication Service (Diskominfotik) does not yet have a benchmark that can be used to evaluate the performance of the helpdesk system. The purpose of this study is to determine the level or level of helpdesk services in optimizing information technology using the COBIT 5 framework and focusing on DSS03 Domain. This research was conducted by interviewing 8 respondents who were involved in the helpdesk and had 27 questions on the DSS03 domain. This research obtained the results of measuring the level of helpdesk service capability in Diskominfotik Riau Province  is at level 4, namely Predictable  Process where diskominfotik has run IT processes in accordance with established SOPs but needs to make continuous improvements in order to reach the target level to be achieved, which is at level 5 Optimizing Process
Penerapan Algoritma Naïve Bayes Classifier Dalam Klasifikasi Status Gizi Balita dengan Pengujian K-Fold Cross Validation Nurainun Nurainun; Elin Haerani; Fadhilah Syafria; Lola Oktavia
Journal of Computer System and Informatics (JoSYC) Vol 4 No 3 (2023): May 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v4i3.3414

Abstract

Nutritional status is a condition related to nutrition that can be measured and is the result of a balance between nutritional needs in the body and nutritional intake from food. In Indonesia, there are still many nutritional problems such as malnutrition and other nutritional problems. This research will use the Naïve Bayes Classifier algorithm with K-Fold Cross Validation testing. The data used is data on the nutritional status of toddlers in August 2022 at the Rambah Samo I Health Center. Attributes in this study include Gender, Birth Weight, Birth Height, Age at Measurement, Weight, Height, ZS BB/U, BB/U, ZS TB/U, and TB/U. Determination of the nutritional status of toddlers in this study was based on the BB/TB index which consisted of 6 classes, namely severely wasted, wasted, normal, possible risk of overweight, overweight, and obese. From the research conducted, it was found that the Naïve Bayes Classifier algorithm with K-Fold Cross Validation can correctly classify the nutritional status of toddlers. From data processing using 10-Fold Cross Validation on the Naïve Bayes Classifier algorithm, it is known that the highest accuracy value is 82.94% in the 5th iteration, while the lowest accuracy value is 65.88% in 6th iteration. With an average overall accuracy value of 75.47%. Meanwhile, the average precision value obtained is 81.36% and the average recall value is 75.47%.
Penerapan Algoritma Mean-Shift Pada Clustering Penerimaan Bantuan Pangan Non Tunai Rizuan Rizuan; Elin Haerani; Jasril Jasril; Lola Oktavia
Journal of Computer System and Informatics (JoSYC) Vol 4 No 4 (2023): August 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v4i4.3876

Abstract

Kemiskinan merupakan kondisi individu atau sekumpulan individu yang tidak memiliki akses ke sumber daya yang memadai untuk memenuhi kebutuhan dasar serta menjalani kehidupan yang baik. Tujuan bantuan pangan non tunai adalah untuk memberikan bantuan pangan kepada yang membutuhkannya melalui metode non tunai, seperti kartu debit atau kartu elektronik. Penelitian ini bertujuan menemukan pola karakteristik calon penerima Bantuan Pangan Non Tunai (BPNT) berdasarkan kriteria dari Dinas Sosial Kota Pekanbaru. Berdasarkan hasil pengujian menggunakan Silhouette Score didapatkan kluster terbaik adalah 2 kluster dengan bandwidth 285 dan Silhouette Score 0.95 klaster 1 memiliki 680 data, dan klaster 2 memiliki 2 data. Hasil claster 1 memiliki pola status penguasaan tempat tinggal berstatus bebas sewa dan kontrak/sewa, untuk jenis lantai terluas adalah batu merah/ sementara, jenis adalah dinding plasteran dan jenis air konsumsi dari leding meteran. Sedangkan hasil cluster 2 memiliki pola penguasaan tempat tinggal berstatus milik sendiri, untuk jenis lantai adalah keramik, jenis dinding adalah tembok dan konsumsi air dari sumur bor pompa.
Penerapan Metode Clustering Dengan K-Means Untuk Memetakan Potensi Tanaman Padi di Sumatera Irma Sanela; Alwis Nazir; Fadhilah Syafria; Elin Haerani; Lola Oktavia
Journal of Computer System and Informatics (JoSYC) Vol 5 No 1 (2023): November 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i1.4523

Abstract

Rice plants are the primary source of rice, the staple food for the majority of the Indonesian population. Despite the presence of other food alternatives, rice remains irreplaceable for those accustomed to consuming rice. According to data from the Food and Agriculture Organization of the United Nations (FAO) in 2018, Indonesia is the third-largest rice producer in the world, with a total production of 59.2 million tons. However, urban and agricultural spatial planning is not yet fully integrated, resulting in often conflicting decisions in land use planning for agriculture and urban development. To meet the rice demand in Sumatra, efforts are needed to increase rice production in each province. Therefore, this research aims to map the potential for rice cultivation in Sumatra based on production and harvest results from 1993 to 2020. The method used in this study is K-Means, which allows the grouping of rice potential areas into three categories: high, medium, and low. The research results produced three clusters, evaluated using the Davies Bouldin Index (DBI) with a value of 0.3943. The clustering results indicate that Cluster 0 contains 92 areas with a high success rate, Cluster 2 comprises 84 areas with a medium success rate, and Cluster 1 consists of 48 areas with a low success rate. The category of low success rate is found in Cluster 1 with 48 areas. Cluster 0 includes Aceh, North Sumatra, West Sumatra, South Sumatra, and Lampung within certain time periods. Cluster 1 encompasses other areas with different characteristics. Cluster 2 includes the provinces of Riau, Jambi, and Bengkulu.
Prediksi Jumlah Perceraian Menggunakan Metode Support Vector Regression (SVR) Eka Suryani Indra Septiawati; Elvia Budianita; Fitri Insani; Lola Oktavia
Journal of Computer System and Informatics (JoSYC) Vol 5 No 1 (2023): November 2023
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josyc.v5i1.4613

Abstract

The increasing number of divorces poses an increasingly significant social challenge in Indonesia, including in the city of Pekanbaru. The impact of these divorces on the adolescent population can have negative effects on their emotional and psychological well-being, as well as their ability to interact socially and engage in the learning process. This study utilizes monthly divorce data from 2015 to April 2023 to conduct time series analysis and applies the Support Vector Regression (SVR) method to predict the number of divorces in the city of Pekanbaru. Three types of SVR kernels, namely linear, polynomial, and radial basis function (RBF), are evaluated and compared to find the kernel with the best Mean Squared Error (MSE) results. Through grid search analysis, optimal parameter values for each kernel are determined. The test results indicate that the SVR model with a polynomial kernel provides more accurate predictions with an MSE of 0.010228, compared to the linear kernel (MSE = 0.012767) and the RBF kernel (MSE = 0.010812).