Article Per Year (5 Year)
p-Index From 2021 - 2026
1.756
P-Index
This Author published in this journals
All Journal IAES International Journal of Artificial Intelligence (IJ-AI) Journal of the Indonesian Mathematical Society JMPM: Jurnal Matematika dan Pendidikan Matematika BAREKENG: Jurnal Ilmu Matematika dan Terapan Sains, Aplikasi, Komputasi dan Teknologi Informasi MILANG Journal of Mathematics and Its Applications Majalah Ilmiah Bahasa dan Sastra
Fahren Bukhari
Bogor Agricultural University
Aerospace Engineering Arts Humanities Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Education Energy Engineering Languange, Linguistic, Communication & Media Mathematics Mechanical Engineering Physics Transportation Other

Published : 11 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 11 Documents
Search

 1   2 
Deteksi Penyakit Jantung Menggunakan Metode Klasifikasi Decision Tree dan Regresi Logistik Bukhari, Fahren; Nurdiati, Sri -; Najib, Mohamad Khoirun; Amalia, Rizki Nurul
Sains, Aplikasi, Komputasi dan Teknologi Informasi Vol 5, No 1 (2023): Sains, Aplikasi, Komputasi dan Teknologi Informasi
Publisher : Universitas Mulawarman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30872/jsakti.v5i1.10780

Abstract

Penyakit jantung merupakan salah satu penyakit paling umum dan kritis yang membahayakan kehidupan manusia. Selain diagnosis klinis, pembelajaran mesin dan pendekatan berbasis pembelajaran mendalam sangat penting dalam diagnosis penyakit jantung, seperti decision tree dan regresi logistik. Penelitian ini bertujuan membandingkan kedua metode klasifikasi tersebut untuk mendeteksi adanya penyakit jantung berdasarkan beberapa indikator. Data yang digunakan adalah data penyakit jantung yang dikeluarkan oleh University of California, Irvine (UCI) Machine Learning Repository.  Berdasarkan hasil yang diperoleh, model decision tree yang terbentuk menempatkan variabel thal (tipe detak jantung pasien) sebagai simpul akar, dikarenakan nilai entropy yang paling tinggi. Model decision tree memiliki akurasi terhadap data uji sebesar 75%. Sementara itu, model regresi logistik menempatkan variabel sex, cp_3, slope_1, ca, dan thal_2 sebagai variabel-variabel yang berpengaruh nyata. Model regresi logistik memiliki akurasi terhadap data uji sebesar 87%. Dari akurasi dari kedua model tersebut, regresi logistik lebih akurat untuk mendeteksi adanya penyakit jantung dibandingkan model decision tree.
Sensitivity and feature importance of climate factors for predicting fire hotspots using machine learning methods Hasafah Nugrahani, Endar; Nurdiati, Sri; Bukhari, Fahren; Khoirun Najib, Mohamad; Muliawan Sebastian, Denny; Nur Fallahi, Putri Afia
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 13, No 2: June 2024
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v13.i2.pp2212-2225

Abstract

Every year, Indonesia experiences a national crisis due to forest fires because the resulting impacts and losses are enormous. Hotspots as indicators of forest fires capable of quickly monitoring large areas are often predicted using various machine learning methods. However, there is still few research that analyzes the sensitivity and feature importance of each predictor that forms a machine learning prediction model. This study evaluates and compares machine learning methods to predict hotspots in Kalimantan based on local and global climate factors in 2001-2020. Using the most accurate machine learning model, each climate factor used as a predictor is analyzed for its sensitivity and feature importance. Four methods used include random forest, gradient boosting, Bayesian regression, and artificial neural networks. Meanwhile, measures of sensitivity and feature importance used are variance, density, and distributionbased sensitivity indices, as well as permutation and Shapley feature importance. Evaluation of the machine learning model concluded that the Bayesian linear regression model outperformed other models with an RMSE of 750 hotspots and an explained variance score of 68.96% on testing data. Meanwhile, tree-based models show signs of overfitting, including gradient boosting and random forest. Based on the results of sensitivity analysis and feature importance of the Bayesian linear regression model, the number of dry days is the most important feature in predicting fire hotspots in Kalimantan.
The Analisis Sensitivitas Model SEIRV Pada Penyebaran Penyakit Covid-19 Di Indonesia: Sensitivity Analysis of the SEIRV Model on the Spread of Covid-19 Disease in Indonesia Nabila, Nabila; Sianturi, Paian; Bukhari, Fahren
JMPM: Jurnal Matematika dan Pendidikan Matematika Vol 8 No 1 (2023): March - August 2023
Publisher : Prodi Pendidikan Matematika Universitas Pesantren Tinggi Darul Ulum Jombang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26594/jmpm.v8i1.3438

Abstract

Model SEIRV dibentuk dengan melihat pada perlakuan terhadap orang yang terinfeksi di Indonesia dengan pembagian subpopulasi terinfeksi menjadi tiga: subpopulasi terinfeksi dirawat di rumah sakit, terinfeksi tidak teridentifikasi, dan terinfeksi isolasi mandiri. Model ini dianalisis sifat kestabilan titik tetapnya dan menganalisis parameter mana yang paling peka terhadap perubahan simulasi model. Model ini memiliki titik tetap tanpa penyakit yang stabil asimtotik lokal pada kondisi bilangan reproduksi dasar kurang dari satu dan titik tetap endemik stabil asimtotik lokal pada kondisi bilangan reproduksi dasar lebih dari satu. Hasil analisis sensitivitas menunjukkan ada tiga parameter yang memiliki pengaruh besar terhadap model: laju transmisi penyakit dari subpopulasi rentan menjadi terekspos, laju kesembuhan subpopulasi terinfeksi tidak teridentifikasi, dan laju vaksinasi. Hal yang dapat dilakukan ketika menginginkan kondisi dimana tidak ada lagi wabah Covid-19 adalah menekan laju penyebaran Covid-19, meningkatkan laju kesembuhan subpopulasi terinfeksi tidak teridentifikasi, dan meningkatkan laju pemberian vaksinasi terhadap populasi.
Mathematical Study for Proving Correctness of the Serial Graph-Validation Queue Scheme Salsabila, Fitra Nuvus; Bukhari, Fahren; Nurdiati, Sri
Journal of the Indonesian Mathematical Society Vol. 31 No. 2 (2025): JUNE
Publisher : IndoMS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22342/jims.v31i2.1592

Abstract

Numerous studies have been conducted to develop concurency control schemes that can be applied to client-server systems, such as the Validation Queue (VQ) scheme, which uses object caching on the client side. This scheme has been modified into the Serial Graph-Validation Queue (SG-VQ) scheme, which employs validation algorithms based on queues on the client side and graphs on the server side. This study focuses on verifying the correctness of the SG-VQ scheme by using serializability as a mathematical tool. The results of this study demonstrate that the SG-VQ scheme can execute its operations correctly, in accordance with Theorem 4.16, which states that every history (H) of SG-VQ is serializable. Implementing a cycle-free transaction graph is a necessary and sufficient condition to achieve serializability. To prove Theorem 4.16, mathematical statements involving ten definitions, two propositions, and three lemmas have been formulated.
PERFORMANCE COMPARISON OF GRADIENT-BASED CONVOLUTIONAL NEURAL NETWORK OPTIMIZERS FOR FACIAL EXPRESSION RECOGNITION Nurdiati, Sri; Najib, Mohamad Khoirun; Bukhari, Fahren; Revina, Refi; Salsabila, Fitra Nuvus
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 16 No 3 (2022): BAREKENG: Journal of Mathematics and Its Applications
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1086.562 KB) | DOI: 10.30598/barekengvol16iss3pp927-938

Abstract

A convolutional neural network (CNN) is one of the machine learning models that achieve excellent success in recognizing human facial expressions. Technological developments have given birth to many optimizers that can be used to train the CNN model. Therefore, this study focuses on implementing and comparing 14 gradient-based CNN optimizers to classify facial expressions in two datasets, namely the Advanced Computing Class 2022 (ACC22) and Extended Cohn-Kanade (CK+) datasets. The 14 optimizers are classical gradient descent, traditional momentum, Nesterov momentum, AdaGrad, AdaDelta, RMSProp, Adam, Radam, AdaMax, AMSGrad, Nadam, AdamW, OAdam, and AdaBelief. This study also provides a review of the mathematical formulas of each optimizer. Using the best default parameters of each optimizer, the CNN model is trained using the training data to minimize the cross-entropy value up to 100 epochs. The trained CNN model is measured for its accuracy performance using training and testing data. The results show that the Adam, Nadam, and AdamW optimizers provide the best performance in model training and testing in terms of minimizing cross-entropy and accuracy of the trained model. The three models produce a cross-entropy of around 0.1 at the 100th epoch with an accuracy of more than 90% on both training and testing data. Furthermore, the Adam optimizer provides the best accuracy on the testing data for the ACC22 and CK+ datasets, which are 100% and 98.64%, respectively. Therefore, the Adam optimizer is the most appropriate optimizer to be used to train the CNN model in the case of facial expression recognition.
PROVING THE CORRECTNESS OF THE EXTENDED SERIAL GRAPH-VALIDATION QUEUE SCHEME IN THE CLIENT-SERVER SYSTEM Salsabila, Fitra Nuvus; Bukhari, Fahren; Nurdiati, Sri
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 18 No 2 (2024): BAREKENG: Journal of Mathematics and Its Application
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol18iss2pp1359-1368

Abstract

Numerous studies have been conducted to develop concurrency control schemes that can be applied to client-server systems, such as the Extended Serial Graph-Validation Queue (SG-VQ) scheme. Extended SG-VQ is a control concurrency scheme in client-server system which implements object caching on the client side and locking strategy on the server side. This scheme employs validation algorithms based on queues on the client side and graphs on the server side. This research focuses on the mathematical analysis of the correctness of the Extended SG-VQ scheme using serializability as the criterion that needs to be achieved. Implementing a cycle-free transaction graph is a necessary and sufficient condition to achieve serializability. In this research, the serializability of the Extended SG-VQ scheme has been proven through the exposition of ten definitions, two propositions, three lemmas, and one theorem.
EXTENDED SERIAL GRAPH-VALIDATION QUEUE SCHEME WITH LOCKING STRATEGY Jauhari, Muhammad Fakhri; Bukhari, Fahren; Nurdiati, Sri
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 18 No 3 (2024): BAREKENG: Journal of Mathematics and Its Application
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol18iss3pp1899-1908

Abstract

In today's digital landscape, collaborative work in real-time is on the rise, allowing individuals to connect across different locations through applications facilitated by client-server architecture, enabling users to access and work on the same project simultaneously. However, clients' simultaneous access and modifications to the database can result in data inconsistencies, underscoring the importance of concurrency control. Managing concurrent transactions can introduce complexities and potentially adversely impact server performance. Object caching emerges as a viable solution as an alternative approach to handling transaction traffic. Extended Serial Graph-Validation Queue (Extended SG-VQ) is a control concurrency scheme that operates within the client-server architecture framework and incorporates object caching. The cache component implements a queue-based validation algorithm as part of its validation process. At the same time, the server-side employs a graph-based validation algorithm with locking strategies. Through a series of hypothetical transaction scenarios across three cases, this study validates the effectiveness of the Extended SG-VQ, demonstrating its ability to utilize serial graphs, resolve conflicts, and identify cyclic patterns.
PREDIKSI MASA STUDI MAHASISWA MATEMATIKA IPB BERDASARKAN INDEKS PRESTASI KUMULATIF MENGGUNAKAN JARINGAN SYARAF TIRUAN Nurdiati, Sri; Bukhari, Fahren; Najib, Mohamad Khoirun; Hilmi, Kautsar
MILANG Journal of Mathematics and Its Applications Vol. 18 No. 1 (2022): MILANG Journal of Mathematics and Its Applications
Publisher : School of Data Science, Mathematics and Informatics, IPB University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/milang.18.1.1-13

Abstract

Akreditasi sebuah program studi sangat dipengaruhi oleh masa studi dan Indeks Prestasi Kumulatif (IPK) lulusannya. Beberapa penelitian menunjukkan adanya keterkaitan antara kelulusan dengan IPK mahasiswa. Namun, model prediksi lama masa studi berdasarkan IPK masih sedikit. Oleh karena itu, penelitian ini bertujuan untuk memprediksi masa studi mahasiswa berdasarkan IPK menggunakan model jaringan syaraf tiruan (JST) berbasis backpropagation. Beberapa fungsi pelatihan diterapkan, meliputi gradient descent, Nesterov accelerated gradient descent, Adaptive moment estimation (Adam), dan Nesterov Adam (Nadam). Data yang digunakan dalam penelitian ini adalah data masa studi dan IPK semester 1-6 mahasiswa S1 Matematika IPB. Hasil penelitian menunjukkan bahwa model JST terbaik dihasilkan oleh jaringan dengan jumlah input node 6 yang dinormalisasi dengan batch normalization (BatchNorm), hidden node 10 dan output node 1. Parameter jaringan terbaik diperoleh dari percobaan menggunakan fungsi pelatihan gradient descent dan laju pembelajaran 0.5 dengan MAE sebesar 1.887 pada data testing. Fungsi pelatihan gradient descent memperlihatkan adanya penurunan nilai MAE ketika nilai laju pembelajaran meningkat. Sementara itu, pada fungsi pelatihan lainnya, terdapat tren bahwa semakin kecil nilai laju pembelajaran maka semakin kecil pula nilai MAE yang dihasilkan. Berdasarkan model JST terpilih, nilai IPK yang paling berpengaruh pada masa studi mahasiswa matematika IPB adalah nilai IPK pada semester 3, yaitu masa mahasiswa matematika IPB pertama kali menerima mata kuliah mayor dari Departemen Matematika secara keseluruhan. Kepentingan dari fitur ini sangat tinggi, mencapai 75.62%. Model JST terpilih menghasilkan MAPE sebesar 3.8% dan RMSPE sebesar 4.9% pada data testing.
IMPLEMENTASI PENYELESAIAN PERSAMAAN BURGERS DENGAN METODE BEDA HINGGA DALAM BAHASA PEMROGRAMAN JULIA Bukhari, Fahren; Nurdiati, Sri; Julianto, Mochamad Tito; Najib, Mohamad Khoirun; Valentdio, Ruben Harry
MILANG Journal of Mathematics and Its Applications Vol. 19 No. 1 (2023): MILANG Journal of Mathematics and Its Applications
Publisher : School of Data Science, Mathematics and Informatics, IPB University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/milang.19.1.1-9

Abstract

Burgers equation is a partial differential equation used to modelling several events related to fluids. Burgers equation was firstly introduced by Harry Bateman in 1915 and later studied by Johannes Martinus Burgers in 1948. This study discusses solving Burgers equations with finite difference method. In this study, several parameters have been known for the Burgers equation and several cases of partitions are used in finite difference method. The result shows that the more partitions used, the numerical result obtained will be closer to the exact values. In this study, calculations are numerically carried out with the help of Julia programming language.
PENERAPAN MODEL SEIRU PADA KASUS COVID-19 DI JAKARTA Dilla, Septia Rahma; Bukhari, Fahren; Julianto, Mochamad Tito; Ali Kusnanto
MILANG Journal of Mathematics and Its Applications Vol. 19 No. 2 (2023): MILANG Journal of Mathematics and Its Applications
Publisher : School of Data Science, Mathematics and Informatics, IPB University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29244/milang.19.2.81-95

Abstract

Sejak awal penyebaran COVID-19, telah diambil langkah-langkah pembatasan aktivitas publik untuk meredakan laju penularan, termasuk di Provinsi DKI Jakarta yang menerapkan Pembatasan Sosial Berskala Besar (PSBB). Dalam upaya menganalisis dampak kebijakan tersebut, digunakan model epidemiologi SEIRU, yang mempertimbangkan periode laten dan efek pembatasan aktivitas publik. Penelitian ini mengimplementasikan model SEIRU pada kasus COVID-19 di Jakarta, mengevaluasi parameter yang paling sesuai untuk merepresentasikan dinamika kasus, serta mengidentifikasi dampak dari penerapan PSBB terhadap kesesuaian model. Bahasa pemrograman Julia digunakan untuk mengimplementasikannya. Dari penelitian ini ditunjukkan bahwa model SEIRU cocok untuk menggambarkan perkembangan kasus COVID-19 hingga berakhirnya PSBB pertama, tetapi kurang sesuai untuk masa perpanjangan PSBB. Analisis juga mengindikasikan bahwa penerapan PSBB dapat mengurangi jumlah kasus terlapor hingga 41%, dengan rata-rata waktu individu yang terinfeksi namun tidak menunjukkan gejala adalah 7 hari, dan durasi rata-rata periode laten adalah 6 jam.
Co-Authors Ali Kusnanto Amalia, Rizki Nurul Amanah, Ayu Dilla, Septia Rahma Hasafah Nugrahani, Endar Hilmi, Kautsar Jauhari, Muhammad Fakhri Mochamad Tito Julianto Muliawan Sebastian, Denny Nabila, Nabila Najib, Mohamad Khoirun Nur Fallahi, Putri Afia Paian Sianturi REFI REVINA Salsabila, Fitra Nuvus Sri Nurdiati Valentdio, Ruben Harry