Article Per Year (5 Year)
p-Index From 2021 - 2026
2.572
P-Index
This Author published in this journals
All Journal JURNAL MEDIA INFORMATIKA BUDIDARMA Building of Informatics, Technology and Science JOURNAL OF INFORMATION SYSTEM RESEARCH (JOSH) Jurnal Sistem Komputer dan Informatika (JSON) Bulletin of Informatics and Data Science Bulletin of Artificial Intelligence
Mustakim Mustakim
Universitas Islam Negeri Sultan Syarif Kasim Riau, Pekanbaru
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Engineering

Published : 17 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 7 Documents
Search
Journal : jurnal sistem komputer dan informatika json

 1 
Prediksi Status Penanganan Pasien Covid-19 dengan Algoritma Naïve Bayes Classifier di Provinsi Riau Dedi Pramana; Mustakim Mustakim
Jurnal Sistem Komputer dan Informatika (JSON) Vol 3, No 2 (2021): Desember 2021
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v3i2.3570

Abstract

Covid-19 is a new virus that emerged at the end of 2019 in Wuhan city, China.  This virus continues to grow until it spreads to various countries in the world.  As a result, there has been a large accumulation of Covid-19 patients in every hospital in every country affected by Covid-19.  Covid-19 patients receiving treatment in hospitals have different conditions and severity, this of course affects the different mechanism for handling patients.  Therefore, technological support is needed to help classify the treatment of patients so that they can be concentrated on patients who can be treated with isoman treatment or must be referred to hospital.  This research was conducted to build a model based on a dataset of patients infected with Covid-19 using the Naive Bayes Classifier algorithm.  The model built can predict the treatment status of patients based on age and gender who have the highest probability of being treated in an isoman way or having to be referred to hosspital. Data used is applied using Rapidminer with validation used is spill validation with the ratio of training data is 70% and test data is 30%.  The results of this research indicate classification using the Naive Bayes Classifier algorithm has a high level of accuracy in classifying patient status data, rately 83.33%.
Implementasi Algoritma Naïve Bayes Classifier (NBC) untuk Klasifikasi Penyakit Ginjal Kronik Qurotul A'yuniyah; Ena Tasia; Nanda Nazira; Pangeran Fadillah Pratama; Muhammad Ridho Anugrah; Jeni Adhiva; Mustakim Mustakim
Jurnal Sistem Komputer dan Informatika (JSON) Vol 4, No 1 (2022): September 2022
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v4i1.4781

Abstract

Degenerative disease is a non-communicable disease that arises from an unhealthy lifestyle, so that it can reduce the physical and mental quality of the sufferer. Chronic Kidney Disease (CDK) is a degenerative disease that is included in the world's top 10 causes of death according to the World Health Organization (WHO). This study used CDK data with attributes of age, blood pressure, weight, albumin levels, sugar levels, red blood cells, pus cells, pus cell clots, bacteria, blood sugar levels, blood urea levels, creatinine serum, sodium, magnesium, hemoglobin, the volume occupied by red blood, indications of hypertension, indications of diabetes mellitus, indications of coronary heart disease, appetite, indications of swelling in the calves or feet, and indications of anemia. Therefore, the classification of kidney disease data is carried out with the implementation of the superior Naïve Bayes Classifier (NBC) algorithm and produces a high level of accuracy. The classification results using the RapidMiner tools carried out by the application of the NBC algorithm, the accuracy value is 96.43%, the average recall is 93.18%, the average precision is 93.02%, and the AUC is 93.2%. so it can be concluded that the performance of NBC in classifying chronic kidney disease data is excellent.
Seleksi Fitur untuk Prediksi Hasil Produksi Agrikultur pada Algoritma K-Nearest Neighbor (KNN) Delvi Nur Aini; Bella Oktavianti; Muhammad Jalal Husain; Dian Ayu Sabillah; Said Thaufik Rizaldi; Mustakim Mustakim
Jurnal Sistem Komputer dan Informatika (JSON) Vol 4, No 1 (2022): September 2022
Publisher : STMIK Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v4i1.4813

Abstract

Agriculture is one of the largest economic driving sectors in Indonesia. The Central Statistics Agency (BPS) in 2021 recorded that 37.02% of Indonesia's population worked in the agricultural sector. The problem faced by farmers today is the decline in yields, both in quantity and quality due to unpredictable weather, making it difficult for farmers to choose the types of plants that are suitable for planting. The application of data mining techniques has problems related to the complexity of weather parameters and natural conditions that support agricultural production, so it is very important to do feature selection, namely to form the most relevant features. This study conducted an experiment to determine the effect of implementing the Principal Component Analysis (PCA) selection feature on the performance of the K-Nearest Neighbor (KNN) algorithm which produces the highest accuracy of 99.64% in this study.
Proyeksi Data dan Analisis Sentimen Penggunaan Vaksin di Kabupaten Indragiri Hulu Berbasis Machine Learning Ahmad Rizky Andriawan; Mustakim Mustakim
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 3 No. 2 (2021): Desember 2021
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v3i2.3569

Abstract

Sentiment analysis is research that processed used computer that comes from opinion and emotion wich realized in shape of text. The method that used to analyze sentiment is using Text Mining used for mining the text in order to get comprehension about the important aspect. Text Mining done at social media Twitter. This research analyze public sentiment related with vaccination. Step of Preprocessing contains Crawling Data, Cleaning, Filtering, Stemming, TF-IDF, and labeling. Result from labeling and percentage calculation get percentage that Positive Sentiment is 29.17%, Negative Sentiment is 55.09% percentage, and Neutral is 15.74% percentage. Could be seen that Indonesian public still given many Negative Comments related with vaccination. Result of K-NN calculation with K-9 generate the accuracy is 84.53%.
Prediksi Status Penanganan Pasien Covid-19 dengan Algoritma Naïve Bayes Classifier di Provinsi Riau Dedi Pramana; Mustakim Mustakim
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 3 No. 2 (2021): Desember 2021
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v3i2.3570

Abstract

Covid-19 is a new virus that emerged at the end of 2019 in Wuhan city, China.  This virus continues to grow until it spreads to various countries in the world.  As a result, there has been a large accumulation of Covid-19 patients in every hospital in every country affected by Covid-19.  Covid-19 patients receiving treatment in hospitals have different conditions and severity, this of course affects the different mechanism for handling patients.  Therefore, technological support is needed to help classify the treatment of patients so that they can be concentrated on patients who can be treated with isoman treatment or must be referred to hospital.  This research was conducted to build a model based on a dataset of patients infected with Covid-19 using the Naive Bayes Classifier algorithm.  The model built can predict the treatment status of patients based on age and gender who have the highest probability of being treated in an isoman way or having to be referred to hosspital. Data used is applied using Rapidminer with validation used is spill validation with the ratio of training data is 70% and test data is 30%.  The results of this research indicate classification using the Naive Bayes Classifier algorithm has a high level of accuracy in classifying patient status data, rately 83.33%.
Implementasi Algoritma Naïve Bayes Classifier (NBC) untuk Klasifikasi Penyakit Ginjal Kronik Qurotul A'yuniyah; Ena Tasia; Nanda Nazira; Pangeran Fadillah Pratama; Muhammad Ridho Anugrah; Jeni Adhiva; Mustakim Mustakim
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 4 No. 1 (2022): September 2022
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v4i1.4781

Abstract

Degenerative disease is a non-communicable disease that arises from an unhealthy lifestyle, so that it can reduce the physical and mental quality of the sufferer. Chronic Kidney Disease (CDK) is a degenerative disease that is included in the world's top 10 causes of death according to the World Health Organization (WHO). This study used CDK data with attributes of age, blood pressure, weight, albumin levels, sugar levels, red blood cells, pus cells, pus cell clots, bacteria, blood sugar levels, blood urea levels, creatinine serum, sodium, magnesium, hemoglobin, the volume occupied by red blood, indications of hypertension, indications of diabetes mellitus, indications of coronary heart disease, appetite, indications of swelling in the calves or feet, and indications of anemia. Therefore, the classification of kidney disease data is carried out with the implementation of the superior Naïve Bayes Classifier (NBC) algorithm and produces a high level of accuracy. The classification results using the RapidMiner tools carried out by the application of the NBC algorithm, the accuracy value is 96.43%, the average recall is 93.18%, the average precision is 93.02%, and the AUC is 93.2%. so it can be concluded that the performance of NBC in classifying chronic kidney disease data is excellent.
Seleksi Fitur untuk Prediksi Hasil Produksi Agrikultur pada Algoritma K-Nearest Neighbor (KNN) Delvi Nur Aini; Bella Oktavianti; Muhammad Jalal Husain; Dian Ayu Sabillah; Said Thaufik Rizaldi; Mustakim Mustakim
Jurnal Sistem Komputer dan Informatika (JSON) Vol. 4 No. 1 (2022): September 2022
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v4i1.4813

Abstract

Agriculture is one of the largest economic driving sectors in Indonesia. The Central Statistics Agency (BPS) in 2021 recorded that 37.02% of Indonesia's population worked in the agricultural sector. The problem faced by farmers today is the decline in yields, both in quantity and quality due to unpredictable weather, making it difficult for farmers to choose the types of plants that are suitable for planting. The application of data mining techniques has problems related to the complexity of weather parameters and natural conditions that support agricultural production, so it is very important to do feature selection, namely to form the most relevant features. This study conducted an experiment to determine the effect of implementing the Principal Component Analysis (PCA) selection feature on the performance of the K-Nearest Neighbor (KNN) algorithm which produces the highest accuracy of 99.64% in this study.
Co-Authors Adyah Widiarni Ahmad Harun Ahmad Rizky Andriawan Bella Oktavianti Dedi Pramana Delvi Nur Aini Dian Ayu Sabillah Dzul Asfi Warraihan Ena Tasia Inggih Permana Jeni Adhiva Kharisma, Oktaf Brillian M Afdal Muhammad Jalal Husain Muhammad Ridho Anugrah Muhammad Ridwan Nanda Nazira Nanda Try Luchia Pangeran Fadillah Pratama Qurotul A'yuniyah Qurotul A'yuniyah Rice Novita Said Thaufik Rizaldi Sania Fitri Octavia Siti Monalisa Suryani Suryani