Claim Missing Document
Check
Articles

PREDIKSI KESEHATAN MASYARAKAT INDONESIA MENGGUNAKAN RECURENT NEURAL NETWORK Amril Mutoi Siregar; Jajam Haerul Jaman; Abdul Mufti
INTERNAL (Information System Journal) Vol. 4 No. 1 (2021)
Publisher : Masoem University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32627/internal.v4i1.285

Abstract

Health is very important for all human beings, especially in Indonesia, because human health can do activities properly and have high performance for both work and other social life. The task of predicting the future values of a time series is a problem that applications have in areas such as sales, engineering, epidemiology, etc. Much research effort has been made in the development of predictive models and performance improvement. The level of public health in Indonesia from 1995 to 2018 varied with the percentage of the population who experienced health complaints. The purpose of this study is to predict the future health of the Indonesian public so that it can be used as a tool to determine government policies in the health sector. The method used in predicting is the Recurent Neural Network (RNN) with secondary data sourced from the Central Statistics Agency (BPS) in the form of data sets, and dividing the data sets into training data and test data. Before the data is used as training data, we clean and tidy up the data first so that when it is implemented there are no errors either during training or testing. The results showed that at the beginning of the method RNN, the prediction results were far from the data, after an interval of 7 and above the predicted results were actually the same. Based on Figures 5 and 6, it can be said that the RNN method is very good for the prediction method.
PENERAPAN ALGORITMA K-MEANS UNTUK PENGELOMPOKAN DAERAH RAWAN BENCANA DI INDONESIA Amril Mutoi Siregar
INTERNAL (Information System Journal) Vol. 1 No. 2 (2018)
Publisher : Masoem University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32627/internal.v1i2.322

Abstract

Indonesia is a country located in the equator, which has beautiful natural. It has a mountainous constellation, beaches and wider oceans than land, so that Indonesia has extraordinary natural beauty assets compared to other countries. Behind the beauty of natural it turns out that it has many potential natural disasters in almost all provinces in Indonesia, in the form of landslides, earthquakes, tsunamis, Mount Meletus and others. The problem is that the government must have accurate data to deal with disasters throughout the province, where disaster data can be in categories or groups of regions into very vulnerable, medium, and low disaster areas. It is often found when a disaster occurs, many found that the distribution of long-term assistance because the stock for disaster-prone areas is not well available. In the study, it will be proposed to group disaster-prone areas throughout the province in Indonesia using the k-means algorithm. The expected results can group all regions that are very prone to disasters. Thus, the results can be Province West java, central java very vulnerable categories, provinces Aceh, North Sumatera, West Sumatera, east Java and North Sulawesi in the medium category, provinces Bengkulu, Lampung, Riau Island, Babel, DIY, Bali, West Kalimantan, North Kalimantan, Central Sulawesi, West Sulawesi, Maluku, North Maluku, Papua, west Papua including of rare categories. With the results obtained in this study, the government can map disaster-prone areas as well as prepare emergency response assistance quickly. In order to reduce the death toll and it is important to improve the services of disaster victims. With accurate data can provide prompt and appropriate assistance for victims of natural disasters.
License Plate Localization for Low Computation Resources Systems Using Raw Image Input and Artificial Neural Network Wan Sen, Tjong; Suakanto, Sinung; Siregar, Amril Mutoi
Jurnal Telematika Vol. 15 No. 1 (2020)
Publisher : Yayasan Petra Harapan Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.61769/telematika.v15i1.349

Abstract

License Plate localization using Computer Vision needs a lot of computation resources. Thus, it is hard to deploy it on small systems. This paper presents an efficient license plate localization method using raw image input and artificial neural network. This is achieved by eliminating feature extraction stage and try to use as minimum as possible neural network architecture. Raw image input in dataset is cropped and labelled manually from random car images and video frames. The minimum architecture of the model has only three layers and 32,770 neurons. This is feasible to be deployed in today most single chip systems. The results, from various experiments, yield more than 90% of localization accuracy. Nomor plat kendaraan bermotor yang diperoleh dengan menggunakan Computer Vision membutuhkan banyak daya komputasi. Hal ini menyebabkan implementasinya ke dalam sistem minimum yang sederhana menjadi tidak mudah. Dalam penelitian ini, dikembangkan sebuah metoda untuk mendapatkan plat nomor kendaraan bermotor yang effisien menggunakan masukan langsung tanpa ektraksi ciri dan jaringan saraf tiruan. Penghematan daya komputasi dicapai dengan cara menghilangkan tahap ekstraksi ciri dan penggunaan arsitektur jaringan saraf tiruan yang seminimum mungkin. Citra masukan diperoleh dengan cara memotong dan memberi label gambar mobil dan frame video yang diperoleh secara acak. Arsitektur minimum yang dihasilkan berupa model yang hanya terdiri dari tiga lapisan dan 32,770 neuron. Model ini cukup fisibel untuk diterapkan pada kebanyakan system on a chip yang ada pada saat ini. Tingkat akurasi model dalam menemukan lokasi nomor kendaraan dari berbagai eksperimen berhasil mencapai lebih dari 90%. 
Analisis Sentimen Pindah Ibu Kota Negara (IKN) Baru pada Twitter Menggunakan Algoritma Naive Bayes dan Support Vector Machine (SVM) Siregar, Amril Mutoi
Faktor Exacta Vol 16, No 3 (2023)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v16i3.16703

Abstract

Pemindahan Ibu Kota Negara (IKN) Indonesia merupakan salah satu topik yang sedang menjadi sorotan bahkan trending topik di Twitter, sehingga menimbulkan pro kontra bagi masyarakat. Topik tersebut sudah menjadi sumber perdebatan bagi pengguna Twitter. Untuk mengetahui para pengguna twitter dalam mengemukakan pendapatnya dapat dilakukan dengan cara analisis sentimen, dimana cara tersebut memisahkan opini berdasarkan positif dan negatif. Pada analisis sentimen, metode yang digunakan biasanya menggunakan Naïve Bayes dan Support Vector Machine (SVM). Dengan dilakukannya analisa sentimen pada pemindahan IKN Indonesia dengan menggunakan dua metode algoritma yaitu Naïve Bayes dan SVM, maka permasalahan yang menjadi kontroversi dapat diketahui, sehingga dapat menjadi bahan evaluasi untuk kepentingan lainnya. Selain itu juga dengan penggunaan dua metode algoritma tersebut diharapkan dapat diketahui metode algoritma mana yang dapat menunjukkan tingkat akurasi yang tepat. Berlandaskan uraian tersebut, maka penelitian kali ini perlu memberikan kontribusi baru dalam mengalisis sentimen IKN Indonesia dengan menggunakan dua metode yang berbeda, sehingga penelitian berbeda dari penelitian-penelitian terdahulu. Penelitian ini bertujuan untuk menganalisis dan mengetahui sentimen masyarakat Indonesia terhadap pemindahan IKN melalui cuitan pada aplikasi Twitter. Untuk melakukan analisis sentimen tersebut, peneliti menggunakan dataset dari Twitter guna mengetahui perbandingan keakurasian diantara dua metode yang digunakan yaitu Naïve Bayes untuk mengkategorikan cuitan kedalam 2 kategori yaitu cuitan positif dan negatif, kemudian dibandingkan dengan metode SVM. Penelitian dilaksanakan sebagai pendukung informasi yang akurat kepada masyarakat terhadap Ibu Kota Negara. Metode penelitian yang digunakan yaitu klasifikasi Naïve Bayes dan klasifikasi SVM dengan dukungan tools Rapidminer. Hasil analisis sentimen dengan algoritma Naïve Bayes menghasilkan akurasi 86.94% memiliki nilai presisi rata-rata 96.24%, dan nilai recall 86.66%. Sedangkan hasil analisis dengan algoritma SVM menghasilkan nilai akurasi sejumlah 90.81%. Hasil analisis sentimen penelitian ini memiliki nilai presisi rata-rata sebesar 90.12%, dan nilai recall sebesar 99.12%.
COMPARISON OF DIABETES DISEASE CLASSIFICATION MODELS USING LOGISTIC REGRESSION AND RANDOM FOREST ALGORITHMS nabila, putri; Mutoi Siregar, Amril; Faisal, Sutan; Pratama, Adi Rizky
Faktor Exacta Vol 17, No 3 (2024)
Publisher : LPPM

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30998/faktorexacta.v17i3.24388

Abstract

Diabetes is a lifelong chronic disease that disrupts blood sugar regulation. Diabetes is a life-threatening condition that, if left untreated, can lead to death and other health problems. Several medical tests, including the glycated hemoglobin (A1C) test, blood sugar test, oral glucose tolerance test, and fasting blood sugar test, can be used to detect diabetes. According to statistics, high glucose levels are one of the problems associated with diabetes. This study aims to categorize patients into diabetic and non-diabetic groups using specific diagnostic metrics included in the dataset. 1500 patient records with 9 attributes and 2 classes were used by the researchers. The study used machine learning techniques, including Logistic Regression and Random Forest, along with Confusion Matrix and Receiver Operating Characteristics (ROC) assessment. The Random Forest method produced results of 97% accuracy, 97% precision, 100% recall, and 98% f1-score, indicating that the accuracy level seems good but can still be improved. Based on the accuracy findings, Random Forest is the most effective strategy of Logistic Regression.
Klasifikasi Penyakit Serangan Jantung Menggunakan Metode Machine Learning K-Nearest Neighbors (KNN) dan Support Vector Machine (SVM) Arif, Siti Novianti Nuraini; Siregar, Amril Mutoi; Faisal, Sutan; Juwita, Ayu Ratna
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7844

Abstract

Cardiovascular disease (CVD) is a general term for disorders related to the heart, coronary arteries, and blood vessels. These diseases are most commonly caused by blocked blood vessels, either due to fat buildup or internal bleeding. According to the WHO, each year, cardiovascular diseases account for 32% of all deaths, which translates to about 17.9 million people annually. The numerous factors causing CVD make it challenging for doctors to diagnose patients who are at low or higher risk of heart attacks. A machine learning model is needed for the early recognition of heart attack symptoms. Supervised learning models such as KNN and SVM were used in previous studies without feature selection, with datasets obtained from Kaggle. PCA was applied to reduce data dimensions to smaller variables. With the use of confusion matrix and ROC curve evaluations, the accuracy results of the previous KNN model improved from 83.6% to 90.16%. The SVM model also saw an accuracy increase from 85.7% to 86.88%. The use of PCA feature selection demonstrated an improvement in accuracy in the study. The KNN model, with a higher accuracy rate of 90.16%, is better for classifying individuals as normal or diagnosed with a heart attack.
OPTIMAL STUDY OF REAL-ESTATE PRICE PREDICTION MODELS USING MACHINE LEARNING Maulana, Ikhsan; Siregar, Amril Mutoi; Lestari, Santi Arum Puspita; Faisal, Sutan
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 4 (2024): JUTIF Volume 5, Number 4, August 2024
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.4.2565

Abstract

Everyone wants a place to live, especially close to work, shopping centers, easy transportation, low crime rates and others. Pricing must also pay attention to external factors, not just the house. Determining this price is sometimes difficult for some people. Therefore, the aim of this research is to predict real-estate prices by taking these factors into account. Prediction results are very useful for sellers who have difficulty determining prices and also for prospective buyers who are confused when making financial plans to buy a house in the desired neighborhood. The dataset used in this research was obtained from Kaggle and consists of 506 samples with 14 attributes. Several machine learning algorithms, such as Extra Trees (ET), Support Vector Regression (SVR), Random Forest (RF), eXtreme Gradient Boosting (XGB), Gradient Boosting Machine (GBM), Light Gradient Boosting Machine (LGBM), and CatBoost, used to predict real-estate prices. This research uses Principal Component Analysis (PCA) for feature selection techniques in data sets after the preprocessing phase and before model building. The highest accuracy model obtained is CatBoost with GridSearchCV, this model has been cross validated so there is very little chance of overfitting when given new data. The SVR model with a poly kernel uses a Principal Component (PC) of 10 and GridSearchCV gets an R2 Score of 0.87, a very large number close to the score of CatBoost with GridSearchCV.
IMPLEMENTATION OF DIABETES PREDICTION MODEL USING RANDOM FOREST ALGORITHM, K-NEAREST NEIGHBOR, AND LOGISTIC REGRESSION Pratama, Rio; Siregar, Amril Mutoi; Lestari, Santi Arum Puspita; Faisal, Sutan
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 4 (2024): JUTIF Volume 5, Number 4, August 2024
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.4.2593

Abstract

Diabetes is a serious metabolic disease that can cause various health complications. With more than 537 million people worldwide living with diabetes in 2021, early detection is crucial to preventing further complications. This research aims to predict the risk of diabetes using machine learning algorithms, namely Random Forest (RF), K-Nearest Neighbor (KNN), and Logistic Regression (LR), with the diabetes dataset from UCI. Previous research has explored a variety of algorithms and techniques, with results varying in accuracy. This research uses a dataset from Kaggle which consists of 768 data with 8 parameters, which are processed through pre-processing and data normalization techniques. The model was evaluated using metrics such as accuracy, confusion matrix, and ROC-AUC. The results showed that Logistic Regression had the best performance with 77% accuracy and AUC 0.83, compared to KNN (75% accuracy, AUC 0.81) and Random Forest ( 74% accuracy, AUC 0.81). These findings emphasize the importance of appropriate algorithm selection and good data pre-processing in diabetes risk prediction. This study concludes that Logistic Regression is the most effective method for predicting diabetes risk in the dataset used.
Bank Customer Segmentation Model Using Machine Learning Bunga Tiara, Vira; Siregar, Amril Mutoi; Kusumaningrum, Dwi Sulistya Kusumaningrum; Rohana, Tatang
Jurnal Nasional Pendidikan Teknik Informatika : JANAPATI Vol. 13 No. 1 (2024)
Publisher : Prodi Pendidikan Teknik Informatika Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/janapati.v13i1.75233

Abstract

Banks generally carry out marketing strategies by offering deposit products directly to customers. However, this method is less effective because it requires individualized communication without considering the customer's interest in the product offered. Therefore, this research aims to categorize the classification of bank customers into Yes and No. This research uses a dataset of bank deposits taken from KTM. This research uses a bank deposit dataset taken from Kaggle, the data consists of 11162 rows with 17 attributes.  PCA technique was used for feature selection which was optimized by reducing the dimensionality of the dataset before modeling. It was found that the best model accuracy was SVM RBF kernel with C parameters achieving 80.51% accuracy and ANN 80.78%, but ANN showed a higher ROC graph than SVM because ANN performance results were faster than SVM. Thus, the overall performance measurement of ANN is much better.
Klasifikasi Penyakit Serangan Jantung Menggunakan Metode Machine Learning K-Nearest Neighbors (KNN) dan Support Vector Machine (SVM) Arif, Siti Novianti Nuraini; Siregar, Amril Mutoi; Faisal, Sutan; Juwita, Ayu Ratna
JURNAL MEDIA INFORMATIKA BUDIDARMA Vol 8, No 3 (2024): Juli 2024
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/mib.v8i3.7844

Abstract

Cardiovascular disease (CVD) is a general term for disorders related to the heart, coronary arteries, and blood vessels. These diseases are most commonly caused by blocked blood vessels, either due to fat buildup or internal bleeding. According to the WHO, each year, cardiovascular diseases account for 32% of all deaths, which translates to about 17.9 million people annually. The numerous factors causing CVD make it challenging for doctors to diagnose patients who are at low or higher risk of heart attacks. A machine learning model is needed for the early recognition of heart attack symptoms. Supervised learning models such as KNN and SVM were used in previous studies without feature selection, with datasets obtained from Kaggle. PCA was applied to reduce data dimensions to smaller variables. With the use of confusion matrix and ROC curve evaluations, the accuracy results of the previous KNN model improved from 83.6% to 90.16%. The SVM model also saw an accuracy increase from 85.7% to 86.88%. The use of PCA feature selection demonstrated an improvement in accuracy in the study. The KNN model, with a higher accuracy rate of 90.16%, is better for classifying individuals as normal or diagnosed with a heart attack.
Co-Authors Abda Abda Abdul Mufti Ahmad Fauzi Ahmad Fauzi Alma Hidayanti Alya Nabilah Andri Juliyanto Anton Romadoni Junior Aprilia, Ely Ariesta, Eliza ARIF, SITI NOVIANTI NURAINI Aulia, Achmad Indra Baihaqi, Kiki Ahmad Basuni, Nursela Bunga Tiara, Vira Citra Nur Napiah Deden Wahiddin Dwi Sulistya Kusumaningrum Dwi Sulistya Kusumaningrum Dwi Vina Wijaya Faisal, Sutan Fariz Duta Nugraha Farkhina Dwi Utari Fauzi Ahmad Muda Favian Jarsi Taufiqqurakhman Fitri Nur Masruriyah, Anis Goeirmanto, Leonard Hanny Hikmayanti Handayani Hartono Wijaya, Sony Hexsel Aldoegasha Hilda Yulia Novita Indi Nurul Hassanah Indra Maulana` Indra Maulana Indra, Jamaludin Jaman, Jajam Haerul Jayidan, Zirji Juwita, Ayu Ratna Koirunnisa, Koirunnisa Kurniawan, Ade kurniawan, Rifky Kusumaningrum, Dwi Sulistya Kusumaningrum, Dwi Sulistya Kusumaningrum Lestari, Santi Arum Puspita Lilis Kartika Lutfiah Adeliana Maulana Abdur Rofik Maulana, Ikhsan Muhammad Fathir Fahlevi Mulya Cahya Ramadanty Murniasih nabila, putri Nahrowi Nahrowi Nahrowi Nilam Atsirina Krisnaputri Nofita Sari Nur Dava Kurniawan Nur Davi Kurniawan Nusaibah Nusaibah Permana, Tedi Pratama, Adi Rizky Priyatna, Bayu Rahmad Nahar Siregar Rahmat Rahmat Ramadhan, Naufal Cahya Rizqi Fahrozi Rohana, Tatang Romadoni, Nurul Salsa Desmalia Samsul Arifin Santi Arum Puspita Lestari Sekar Wuni Sinta Candra Dewi Sinung Suakanto SITI NURJANAH Siti Silvia Arifin Sony Hartono Wijaya Sony Hartono Wijaya Sukamto, Ika Sumiyarsi Surjandy Sutan Faisal Sutan Faisal Sutan Faisal Tatang Rohana Taufiqqurahman Hutri Tia Astiyah Hasan Tiawan Tjong Wan Sen Tjong Wan Sen Tohirin Al Mudzakir Tohirin Al Mudzakir Tria Pratiwi Sutriyani Tukino Tukino Tukino, Tukino Wilda Amalia Y Aris Purwanto Yana Cahyana Yana Cahyana Yana Cahyana Cahyana Yholanda Maldini Yogi Firman Alfiansyah Yusuf Khoiruddin