Claim Missing Document
Check
Articles

Found 22 Documents
Search

Implementasi Fuzzy Logic Dalam Monitoring Infus Berbasis Internet of Things (IoT) Maulana, Moch Sigit Rizky; Rohana, Tatang; Mudzakir, Tohirin Al
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 7, No 2 (2023): EDISI SEPTEMBER
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v7i2.699

Abstract

The main function of the infusion is to provide fluids to the patient, the availability of the patient's infusion fluids must always be considered periodically. The increasing number of patients and the limited number of medical personnel is causing uncontrollable delays in changing IV fluids. Blockage in the infusion line can cause air embolism in the blood vessels, which can result in death. By using an automatic infusion monitoring system, the risk of delays in replacing patient infusion fluids can be reduced. To calculate the ambiguity of sensor values, the fuzzy mamdani method was used in this study. Load Cell, HX711 and IR HC-89 are the sensors used. The value generated by the sensor is in the form of NodeMCU ESP32 input which is used by the mamdani method to determine the value in the form of output. The command to turn on the buzzer is the value of the output. Maximizing the effectiveness of the infusion monitoring system is designed with the Mamdani calculation method. The difference in value with an average weight of 5.9% infusion and 5.54 Vo drops is obtained from the results of a comparison of sensor testing with manual tools. Infusion monitoring obtains an accuracy rate of 92% from the test results on system performance.
Classification of Dog Emotions Using Convolutional Neural Network Method Hermawan, Slamet; Siregar, Amril Mutoi; Faisal, Sutan; Mudzakir, Tohirin Al
Jurnal Nasional Pendidikan Teknik Informatika : JANAPATI Vol. 13 No. 2 (2024)
Publisher : Prodi Pendidikan Teknik Informatika Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23887/janapati.v13i2.74340

Abstract

The utilization of neural networks in dog emotion classification has great potential to improve the understanding of pet emotions. The goal is to develop a dog emotion classification system. This is important due to the lack of public ability to recognize and understand dog emotions. Neural networks able to create learning models can be used for decision-making, thus helping to reduce the risk of dangerous dog attacks. CNN itself is part of neural networks, where the CNN model has a higher accuracy rate of 74.75% compared to ResNet 65.10% and VGG 68.67%. Modeling using ROC-AUC shows the model's ability to distinguish emotion classes well. Angry has the highest AUC of 0.97, happy 0.93 and sad 0.96. While relaxed has the lowest AUC of 0.92. Classification report results show model has the highest precision and F1-Score values in angry class, while the highest recall value is in sad class.
PENGARUH SMOTE TERHADAP PERFORMA ALGORITMA RANDOM FOREST DAN ALGORITMA GRADIENT BOOSTING DALAM MEMPREDIKSI PENYAKIT STROKE Fadmadika, Fadilla; Handayani, Hanny Hikmayanti; Mudzakir, Tohirin Al; Indra, Jamaludin
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 7 No 2 (2024)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v7i2.1575

Abstract

Stroke is a disease that can occur suddenly, causing progressive brain damage due to non-traumatic blood flow disruption in the brain. Common symptoms of stroke include numbness in the limbs and impaired communication. Stroke is the second leading cause of death in the world and the third leading cause of mental retardation globally. Predictive machine learning-based technology can help identify early symptoms of stroke for prevention and early intervention. This study aims to compare the performance of the Random Forest and Gradient Boosting algorithms in predicting stroke. By applying the SMOTE method to address class accuracy in the dataset, this study shows that the Random Forest model is superior, with an accuracy of 95.5%, a precision of 78.8%, a recall of 93.1%, and an f1-score of 84.2%. In conclusion, the Random Forest algorithm performs better than Gradient Boosting in predicting stroke, showing significant potential in assisting early detection and medical decision making.
PENERAPAN ALGORITMA SUPPORT VECTOR MACHINES DAN RANDOM FOREST DALAM ANALISIS SENTIMEN ULASAN APLIKASI IDENTITAS KEPENDUDUKAN DIGITAL Ramadhan, Rizky Agung; Rohana, Tatang; Mudzakir, Tohirin Al; Wahiddin, Deden
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 7 No 2 (2024)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v7i2.1595

Abstract

The Digital Population Identity (IKD) application, developed by the Directorate General of Population and Civil Registration, aims to streamline access to digital documents and reduce reliance on printed KTPs. Despite its benefits, user reviews from the Play Store highlight significant issues. This research aims to analyze user sentiment towards the IKD application using Support Vector Machines (SVM) and Random Forest algorithms. The study employed these models to classify sentiment in user reviews and used word cloud analysis to further understand the feedback. Results indicate that both the Random Forest and SVM models struggled with accuracy, achieving only 19.25% and 18% respectively. The word cloud analysis revealed a high prevalence of negative reviews, reflecting the app's low rating. These findings suggest that the current sentiment analysis methods are insufficient for capturing the public's opinion on the IKD application, providing crucial insights for improving future digital population identity management strategies.
KLASTERING SPESIFIKASI DAN HARGA SMARTPHONE MENGGUNAKAN METODE FUZZY C-MEANS DAN PCA Butar Butar, Naomi Nova Meylica; Mudzakir, Tohirin Al; Novita, Hilda Yulia; Rohana, Tatang
Jurnal Informatika Teknologi dan Sains (Jinteks) Vol 7 No 2 (2025): EDISI 24
Publisher : Program Studi Informatika Universitas Teknologi Sumbawa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51401/jinteks.v7i2.5748

Abstract

Perkembangan pengguna smartphone yang pesat di Indonesia menuntut pendekatan segmentasi pasar yang lebih akurat, terutama terkait harga dan spesifikasi. Penelitian ini mengusulkan model klasterisasi menggunakan kombinasi Principal Component Analysis (PCA) dan Fuzzy C-Means (FCM) untuk memahami pola dalam data produk smartphone. Dataset diambil dari platform Kaggle dan mencakup berbagai atribut teknis seperti RAM, ROM, harga, baterai, serta fitur tambahan seperti dukungan 5G dan tipe perangkat (PRO/PLUS atau LITE). Melalui PCA, sembilan atribut direduksi menjadi empat komponen utama yang mampu mempertahankan 94% variasi data. FCM kemudian diterapkan untuk membentuk kelompok berdasarkan keanggotaan fuzzy, menghasilkan klasifikasi yang lebih fleksibel dan adaptif terhadap data yang tumpang tindih. Nilai Silhouette Score meningkat dari 0,57 menjadi 0,73 setelah reduksi dimensi, mengindikasikan kualitas pemisahan klaster yang lebih baik. Sebanyak sembilan klaster terbentuk, masing-masing mencerminkan segmen pasar mulai dari kelas entry-level hingga flagship. Hasil ini dapat menjadi acuan dalam perencanaan strategi pemasaran, pengembangan produk, dan pengambilan keputusan bisnis berbasis data.
Prediksi Pola Pergerakan Saham Adro.Jk Melalui Model LSTM Berbasis Data Historis Iskandar, Muhammad Irsyad; Mudzakir, Tohirin Al; Cahyana, Yana; Pratama, Adi Rizky
Bulletin of Computer Science Research Vol. 5 No. 4 (2025): June 2025
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/bulletincsr.v5i4.554

Abstract

The fluctuating nature of stock price movements presents a significant challenge in investment decision-making. To address this issue, a predictive model capable of capturing historical patterns and accurately forecasting stock prices is required. This study aims to develop a stock price prediction model for PT Alamtri Resources Indonesia Tbk (ADRO.JK) using the Long Short-Term Memory (LSTM) algorithm. The dataset comprises daily closing prices from January 1, 2020, to December 30, 2024, obtained from Yahoo Finance. The data was processed in a time series format using a sliding window approach, employing 30 historical data points to predict the next price point. The model was constructed using two LSTM layers, one Dense layer, and techniques such as Dropout and EarlyStopping to prevent overfitting.The training and testing results indicate that the model performs exceptionally well, achieving a Mean Absolute Percentage Error (MAPE) of 0.0341 or 3.41%, corresponding to a prediction accuracy of 96.59%. In a short-term prediction scenario over seven days, the model achieved an accuracy of 99.07% (MAPE = 0.0093), while in a medium-term scenario up to May 19, 2025, it achieved an accuracy of 98.76% (MAPE = 0.0124). The predicted stock price on May 19, 2025, is estimated at IDR 1,913.76. With its high accuracy and low error rate, the LSTM model has proven to be a reliable tool for forecasting stock prices based on historical data.
Pengembangan Model Klasifikasi Jenis Pisang Menggunakan Convolutional Neural Network Dengan Arsitektur VGG16 Habibah, Nur Habibah; Mudzakir, Tohirin Al; Novita, Hilda Yulia; Fauzi, Ahmad
Jurnal Sistem Komputer dan Informatika (JSON) Vol 6, No 4 (2025): Juni 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/json.v6i4.8616

Abstract

Indonesia memiliki kekayaan varietas pisang yang melimpah, namun permasalahan utama yang dihadapi adalah kesulitan dalam mengidentifikasi dan mengklasifikasikan jenis-jenis pisang secara akurat, terutama karena kemiripan visual antar varietas. Proses identifikasi secara manual dinilai kurang efisien dan rawan kesalahan, terutama dalam skala besar. Penelitian ini bertujuan untuk mengembangkan sistem klasifikasi untuk lima jenis pisang, yaitu pisang ambon, pisang kapas, pisang nangka, pisang siam, dan pisang tanduk, menggunakan metode CNN berbasis arsitektur VGG16. Dataset yang digunakan terdiri dari 634 gambar pisang yang diperoleh melalui kamera smartphone dan telah melalui proses augmentasi serta normalisasi untuk meningkatkan keragaman data. Model dilatih dengan parameter learning rate 0,0001 batch size 32, dan epoch sebanyak 50. Hasil pelatihan akurasi mencapai 99,60% dan akurasi validasi sebesar 98,48%. Hasil evaluasi performa menggunakan confusion matrix dan matrix klasifikasi presisi, recall, dan F1-score menunjukan model memiliki kemampuan yang baik dalam menglasifikasikan jenis pisang dengan tingkat akurasi yang tinggi.
Implementasi Algoritma Support Vector Machine (SVM) dan Random Forest Untuk Klasifikasi Penyakit Hipertensi Berdasarkan Data Kesehatan Azhaar, Siti Alia; Mudzakir, Tohirin Al; Novita, Hilda Yulia; Faisal, Sutan
JURIKOM (Jurnal Riset Komputer) Vol. 12 No. 4 (2025): Agustus 2025
Publisher : Universitas Budi Darma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30865/jurikom.v12i4.8744

Abstract

One of the most common non-communicable diseases causing death in Indonesia is hypertension. At one community health center, the prevalence of hypertension is quite high. Based on examination results, more than 1,000 patients are diagnosed with hypertension each year. The issue faced at this health center is the lack of structured data classification for hypertensive and normal patients. The objective of this study is to compare the performance of the Support Vector Machine (SVM) and Random Forest (RF) algorithms in creating a hypertension classification model based on health examination data from the Anggadita Health Center. Data from 2,500 patients was collected and preprocessed, including handling missing values, removing duplicate data, transforming data using label encoding, and dividing the data into training and testing sets. The SVM method applied a Radial Basis Function (RBF) kernel, while the RF consisted of 100 decision trees. Evaluation was conducted using a confusion matrix to calculate accuracy, precision, recall, and F1-score. The results showed that the SVM method achieved an accuracy of 93%, precision of 0.96 (Normal) and 0.90 (Hypertension), and F1-scores of 0.94 and 0.92. Meanwhile, the RF model showed superior performance with an accuracy of 96%, precision of 0.97 (Normal) and 0.95 (Hypertension), and F1-scores of 0.97 and 0.95, respectively. Thus, the Random Forest algorithm performs better in classifying hypertension data and can be implemented as a tool to assist healthcare institutions in managing patient data.
Deteksi Potensi Faktor Keberangkatan Jemaah Haji Menggunakan Algoritma Klasifikasi Machine Learning Farah Maulida, Oxana; Al Mudzakir, Tohirin; Yulia Novita, Hilda; Rohana, Tatang
Jurnal Pendidikan dan Teknologi Indonesia Vol 5 No 9 (2025): JPTI - September 2025
Publisher : CV Infinite Corporation

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jpti.1060

Abstract

Haji merupakan salah satu rukun islam yang memiliki makna spiritual dan sosial mendalam bagi umat muslim diseluruh dunia Dengan meningkatnya jamaah haji di Indonesia setiap tahunnya, pengelolaan dan pelayanan terhadap calon jamaah haji menjadi tantangan. Faktor yang mempengaruhi seperti faktor demografis dari usia, pendidikan dan pekerjaan yang mempengaruhi keberangkatan jamaah. Penelitian ini bertujuan untuk mendeteksi faktor keberangkatan jamaah haji menggunakan algoritma machine learning, khususnya metode Naïve Bayes, Random Forest dan Decision Tree. Dataset yang dikumpulkan dari Kantor Kementerian Agama Karawang dan diolah menggunakan bahasa pemrograman Phyton. Proses penelitian meliputi pengumpulan data, preprocessing, split data, implementasi algoritma, dan evaluasi. Random Forest mencapai akurasi tertinggi sebesar 99.23%, Decision Tree mencatat akurasi 98.75%, dan Naïve Bayes memiliki akurasi 76.69%. Hasil evaluasi menunjukkan model mampu memberikan akurasi signifikan dalam mengidentifikasi kategori jamaah haji. Diharapkan penelitian ini akan memeberikan wawasan mendalam tentang klasifikasi data jamaah haji dan membantu instansi dalam perencanaan sumber daya yang kebih baik sehingga instansi dapat mengoptimalkan penggunaan anggaran dan alokasi sumber daya yang lebih efisien.
Optimasi Metode Support Vector Machine Menggunakan Seleksi Fitur Recursive Feature Elimination dan Forward Selection untuk Klasifikasi Kanker Payudara Septiany, Eva Senia; Handayani, Hanny Hikmayanti; Mudzakir, Tohirin Al; Masruriyah, Anis Fitri Nur
TIN: Terapan Informatika Nusantara Vol 5 No 2 (2024): July 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/tin.v5i2.5324

Abstract

Cancer, the leading cause of global death, results from abnormal cell proliferation that spreads beyond the boundaries of normal tissue. Breast cancer is one of the most common types of cancer, with approximately 2.26 million cases reported in 2020. This research aims to develop a more effective Support Vector Machine (SVM) algorithm for breast cancer classification through efficient feature selection techniques. Previous research has used various algorithms such as K-Nearest Neighbor and Logistic Regression for breast cancer identification. This research focuses on improving accuracy by using alternative feature selection methods such as Recursive Feature Elimination (RFE) and Forward Selection. The dataset used consists of 569 instances with 32 features sourced from the UCI Machine Learning Repository, and classified into benign and malignant categories. Data pre-processing methods, including data cleaning, coding, and feature selection, were applied to the dataset. RFE and Forward Selection techniques were used to identify the most important features for model training. Evaluation of the improved SVM model shows a training accuracy of nearly 100% and a Cross Validation accuracy of 97%, demonstrating the effectiveness of the proposed approach in the context of breast cancer. In addition, the Learning Curve and testing showed the stability of the SVM model with no signs of overfitting or underfitting. Thus, this study developed an SVM algorithm with a feature selection method that produces better accuracy results in breast cancer classification.