Garuda - Garba Rujukan Digital

KLASIFIKASI KUALITAS UDARA MENGGUNAKAN METODE EXTREME LEARNING MACHINE (ELM) Jannah, Rachma Raudhatul; Sholahuddin, Muhammad Zulfikar; Haq, Dina Zatusiva; Novitasari, Dian C Rini
METHODIKA: Jurnal Teknik Informatika dan Sistem Informasi Vol. 10 No. 2 (2024): Volume 10 Nomor 2
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/mtk.v10i2.3066

Air quality is a critical factor affecting both ecological and human well-being. Air pollution is a global epidemic that poses a threat to human health and the environment. High population density resulting from industrial expansion and the increased number of motor vehicles are two primary causes of declining air quality in metropolitan areas. Air pollutants include surface ozone (O3), dust particles (PM 10), sulfur dioxide (SO2), nitrogen dioxide (NO2), and carbon monoxide (CO). Researchers have begun exploring the use of Extreme Learning Machine (ELM) to classify air quality. The ELM method assesses air quality as either very good or poor. In this study, we compare datasets to evaluate the effectiveness of hidden node parameters using the split method. Our tests indicate that the split method impacts accuracy, sensitivity, and specificity. The ideal model with a 70:30 split ratio and 15 hidden nodes achieved a 90% success rate.

Enhancing Covid-19 Diagnosis: Glrlm Texture Analysis And Kelm For Lung X-Ray Classification Novitasari, Dian C Rini; Ramadanti , Alvin Nuralif; Haq, Dina Zatusiva
Fountain of Informatics Journal Vol. 9 No. 1 (2024): Mei 2024
Publisher : Universitas Darussalam Gontor

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstrak This study aims to diagnose COVID-19 using GLRLM feature extraction, known for its high accuracy, and optimize Kernel Extreme Learning Machine (KELM) with Genetic Algorithm (GA) for improved computational efficiency, along with Principal Component Analysis (PCA) for data reduction. The gamma values in KELM are optimized using GA, yielding the best solution function. Results reveal that at angles of 0°, 45°, and 135°, the optimal gamma value with KELM is 1, while at 90°, GA determines it to be 1.35. This adjustment demonstrates the critical role of gamma values in achieving optimal performance. Performance analysis of various classification methods demonstrates that GLRLM-PCA-Optimized KELM outperforms others, achieving an accuracy exceeding 97%, particularly notable at 90° angles. This study shows that the importance of hyperparameter optimization in enhancing classification accuracy, revealing a significant improvement of over 1% compared to non-optimized models. Kata kunci: COVID-19, GLRLM, KELM, Feature Reduction, PCA Abstract Penelitian ini bertujuan untuk mendiagnosis COVID-19 menggunakan ekstraksi fitur GLRLM yang dikenal dengan akurasi tinggi, dan mengoptimalkan Kernel Extreme Learning Machine (KELM) dengan Algoritma Genetika (GA) untuk meningkatkan efisiensi komputasi, bersama dengan Principal Component Analysis (PCA) untuk reduksi data. Nilai gamma dalam KELM dioptimalkan menggunakan GA, menghasilkan fungsi solusi terbaik. Hasil penelitian menunjukkan bahwa pada sudut 0°, 45°, dan 135°, nilai gamma optimal dengan KELM adalah 1, sedangkan pada 90°, GA menentukan nilainya menjadi 1,35. Penyesuaian ini menunjukkan peran penting nilai gamma dalam mencapai kinerja optimal. Analisis kinerja berbagai metode klasifikasi menunjukkan bahwa GLRLM-PCA-KELM yang Dioptimalkan mengungguli yang lain, mencapai akurasi lebih dari 97%, terutama mencolok pada sudut 90°. Studi ini menyoroti pentingnya optimasi hyperparameter dalam meningkatkan akurasi klasifikasi, mengungkapkan peningkatan signifikan lebih dari 1% dibandingkan dengan model KELM konvesional. Keywords: COVID-19, GLRLM, KELM, Feature Reduction, PCA

Leukaemia Identification based on Texture Analysis of Microscopic Peripheral Blood Images using Feed-Forward Neural Network Puspitasari, Wahyu Tri; Haq, Dina Zatusiva; Novitasari, Dian C Rini
Computer Engineering and Applications Journal Vol 11 No 3 (2022)
Publisher : Universitas Sriwijaya

Leukaemia is very dangerous because it includes liquid tumour that it cannot be seen physically and is difficult to detect. Alternative detection of Leukaemia using microscopy can be processed using a computing system. Leukemia disease can be detected by microscopic examination. Microscopic test results can be processed using machine learning for classification systems. The classification system can be obtained using Feed-Forward Neural Network. Extreme Learning Machine (ELM) is a neural network that has a feedforward structure with a single hidden layer. ELM chooses the input weight and hidden neuron bias at random to minimize training time based on the Moore Penrose Pseudoinverse theory. The classification of Leukaemia is based on microscopic peripheral blood images using ELM. The classification stages consist of pre-processing, feature extraction using GLRLM, and classification using ELM. This system is used to classify Leukaemia into three classes, that is acute lymphoblastic Leukaemia, chronic lymphoblastic Leukaemia, and not Leukaemia. The best results were obtained in ten hidden nodes with an accuracy of 100%, a precision of 100%, a withdrawal of 100%.

Water Quality Identification Using Ensemble Machine Learning and Hybrid Resampling SMOTE-ENN Algorithm Pratama, Moch Deny; Abdillah, Rifqi; Haq, Dina Zatusiva
Fountain of Informatics Journal Vol. 9 No. 2 (2024): November 2024
Publisher : Universitas Darussalam Gontor

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract Water is essential for all living organisms, yet only a small fraction is fresh and suitable for consumption. The limited availability of freshwater sources, worsened by pollution, overuse, and climate change, underscores the urgent need for sustainable water management. Traditional water quality identification methods are labour-intensive, slow, and costly. Water quality identification often struggles with data quality, imbalanced datasets, and model interpretability. These challenges lead to inaccuracies, especially in detecting minority classes, which is crucial for identifying pollution. This research explores machine learning (ML) techniques to address the limitations of water quality classification by integrating ensemble learning using LightGBM and hybrid Resampling using SMOTE-ENN. Ensemble learning techniques improve accuracy and robustness by aggregating the strengths of multiple models, effectively handling imbalanced data and reducing overfitting. Hybrid Resampling techniques enhance model sensitivity by generating synthetic minority-class samples and refining datasets through noise reduction. Together, these integrations provide a more reliable framework for water quality identification, enabling timely and accurate. This innovative method offers a robust solution for addressing data imbalance and overfitting, ensuring more effective detection of polluted conditions. This study highlights the importance of advanced ML techniques in improving water quality tasks and underscores LightGBM's effectiveness in handling imbalanced data post-SMOTE-ENN application. This method is known for its superior performance, achieving the highest performance evaluation metrics in water quality classification with accuracy, F1-Score, and increasing the recall value by 3% with values of 94.50%, 94.76% and 93.00%, respectively. Keywords: Water Quality, Machine Learning, Imbalanced Data, LightGBM, SMOTE-ENN, Ensemble Learning, Hybrid Resampling. Abstrak Air sangat penting bagi semua organisme hidup, namun hanya sebagian kecil yang segar dan layak untuk dikonsumsi. Terbatasnya ketersediaan sumber air bersih, yang diperburuk oleh polusi, penggunaan berlebihan, dan perubahan iklim, menggarisbawahi kebutuhan mendesak akan pengelolaan air berkelanjutan. Metode identifikasi kualitas air tradisional memerlukan banyak tenaga kerja, lambat, dan mahal. Identifikasi kualitas air sering kali bermasalah dengan kualitas data, kumpulan data yang tidak seimbang, dan kemampuan interpretasi model. Tantangan-tantangan ini menyebabkan ketidakakuratan, terutama dalam mendeteksi kelompok minoritas, yang sangat penting dalam mengidentifikasi polusi. Penelitian ini mengeksplorasi teknik pembelajaran mesin (ML) untuk mengatasi keterbatasan klasifikasi kualitas air dengan mengintegrasikan pembelajaran ensembel menggunakan LightGBM dan pengambilan sampel hybrid menggunakan SMOTE-ENN. Teknik pembelajaran ensemble meningkatkan akurasi dan ketahanan dengan menggabungkan kekuatan beberapa model, menangani data yang tidak seimbang secara efektif, dan mengurangi overfitting. Teknik pengambilan sampel hibrid meningkatkan sensitivitas model dengan menghasilkan sampel kelas minoritas sintetik dan menyempurnakan kumpulan data melalui pengurangan noise. Bersama-sama, integrasi ini memberikan kerangka kerja yang lebih andal untuk identifikasi kualitas air, sehingga memungkinkan dilakukannya identifikasi secara tepat waktu dan akurat. Metode inovatif ini menawarkan solusi yang kuat untuk mengatasi ketidakseimbangan dan overfitting data, sehingga memastikan deteksi kondisi tercemar dengan lebih efektif. Studi ini menyoroti pentingnya teknik ML tingkat lanjut dalam meningkatkan tugas kualitas air dan menggarisbawahi efektivitas LightGBM dalam menangani data yang tidak seimbang pasca penerapan SMOTE-ENN. Metode ini dikenal dengan kinerjanya yang unggul, mencapai metrik evaluasi kinerja tertinggi dalam klasifikasi kualitas air dengan akurasi, F1-Score, dan meningkatkan nilai recall sebesar 3% dengan nilai masing-masing 94,50%, 94,76% dan 93,00%. Kata kunci: Kualitas Air, Pembelajaran Mesin, Data Ketidakseimbangan, LightGBM, SMOTE-ENN, Pembelajaran Ensemble, Pengambilan Sampel Hibrid.

Analisis Indeks Pembangunan Manusia Di Jawa Timur Tahun 2022-2023 Berdasarkan Indikator Menggunakan Metode Fuzzy C-Means Hartanto, Salsabila; Adzan, M. Sailul; Haq, Dina Zatusiva; Novitasari, Dian C Rini
INTEK : Jurnal Informatika dan Teknologi Informasi Vol. 7 No. 2 (2024)
Publisher : Program Studi Teknologi Informasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37729/intek.v7i2.5358

Indeks Pembangunan Manusia (IPM) termasuk faktor perkembangan suatu negara. Khususnya di Jawa Timur yang dengan nilai IPM rendah dibandingkan dengan IPM provinsi lainnya karena IPM di Jawa Timur memiliki indikator yang berpengaruh pada nilai IPM rendah, yaitu Tingkat pengangguran Terbuka, Angka Harapan Hidup, Gini Rasio, dan Upah Minimum Regional. Penelitian ini bertujuan mengelompokkan Kabupaten/Kota di Jawa Timur dengan menerapkan algoritma Fuzzy C-Means. Dihasilkan cluster pada tahun 2023 dengan silhouette 0,7742 dengan 3 cluster. Berdasarkan kualitas IPM, bahwasannya mengungkapkan bahwa kota/kabupaten di Provinsi Jawa Timur terdiri dari 3 cluster : Cluster 0 (rendah) yang memiliki 23 kabupaten/kota, Cluster 1 (tinggi) yang memiliki 5 kabupaten/kota, dan Cluster 2 (sedang) dengan memiliki 10 kabupaten/kota. Terdapat perubahan pada Indeks Pembangunan Manusia di tahun 2022 dan 2023 yakni Jember, Kota Kediri, dan Kota Blitar.

Identifikasi Penyakit Anemia menggunakan Metode Support Vector Machine (SVM) Berdasarkan Hemoglobin Darah Wulandari, A’isyah; Wahyuni, Sri; Haq, Dina Zatusiva; Novitasari, Dian C Rini
Jurnal Algoritme Vol 5 No 2 (2025): April 2025 || Algoritme Jurnal Mahasiswa Teknik Informatika
Publisher : Program Studi Teknik Informatika Universitas Multi Data Palembang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35957/algoritme.v5i2.8767

In the world, the number of people infected with anemia is still very high, especially in the Asian region, reaching 48.7 percent. Anemia or anemia occurs due to a lack of blood pressure below normal values. If many people experience blood shortages, there will be many people who suffer from anemia. So it can be seen that variable Then the variable Y shows that the anemia class can be grouped into two parts, namely class 1 which states that they are infected with anemia and class 0 which states that they are not infected with anemia. This research aims to identify anemia using the Support Vector Machine (SVM) method which can be used in the analysis process with approaches from various types of kernels including; Linear, Radial Basis Function (RBF), Polynomial, and Sigomid to determine the level of accuracy, sensitivity and specificity in anemia. This research can show that the best classification of anemia using a linear kernel produces an accuracy value of 99.3 percent. The results obtained from this study indicate that the SVM method with a linear kernel is highly effective in identifying and classifying cases of anemia.

FETAL HEALTH RISK STATUS IDENTIFICATION SYSTEM BASED ON CARDIOTOCOGRAPHY DATA USING EXTREME GRADIENT BOOSTING WITH ISOLATION FOREST AS OUTLIER DETECTION Sari, Firda Yunita; Rini Novitasari, Dian Candra; Hamid, Abdulloh; Haq, Dina Zatusiva
BAREKENG: Jurnal Ilmu Matematika dan Terapan Vol 19 No 3 (2025): BAREKENG: Journal of Mathematics and Its Application
Publisher : PATTIMURA UNIVERSITY

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30598/barekengvol19iss3pp1711-1724

Premature birth and birth defects contribute significantly to infant mortality, highlighting the need for early identification of fetal health risks. This study uses XGBoost for fetal health classification, integrating IForest for outlier detection to improve model performance. By varying the contamination percentage, learning rate (η), maximum depth, and n_estimator, the best results were achieved at CP = 8%, η = 0.01, max_depth = 7, and n_estimator = 100, which resulted in 100% accuracy, sensitivity, and specificity with a calculation time of 0.36 seconds. IForest effectively reduced the dataset from 2126 to 1956 samples by removing outliers, improving accuracy by 3.76%, and reducing computation time by 0.51 seconds. These findings suggest that IForest improves classification efficiency while maintaining high predictive performance, supporting early identification of fetal health risks to aid timely medical intervention.

Leukaemia Identification based on Texture Analysis of Microscopic Peripheral Blood Images using Feed-Forward Neural Network Puspitasari, Wahyu Tri; Haq, Dina Zatusiva; Novitasari, Dian Candra Rini
Computer Engineering and Applications Journal (ComEngApp) Vol. 11 No. 3 (2022)
Publisher : Universitas Sriwijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar

Leukaemia is very dangerous because it includes liquid tumour that it cannot be seen physically and is difficult to detect. Alternative detection of Leukaemia using microscopy can be processed using a computing system. Leukemia disease can be detected by microscopic examination. Microscopic test results can be processed using machine learning for classification systems. The classification system can be obtained using Feed-Forward Neural Network. Extreme Learning Machine (ELM) is a neural network that has a feedforward structure with a single hidden layer. ELM chooses the input weight and hidden neuron bias at random to minimize training time based on the Moore Penrose Pseudoinverse theory. The classification of Leukaemia is based on microscopic peripheral blood images using ELM. The classification stages consist of pre-processing, feature extraction using GLRLM, and classification using ELM. This system is used to classify Leukaemia into three classes, that is acute lymphoblastic Leukaemia, chronic lymphoblastic Leukaemia, and not Leukaemia. The best results were obtained in ten hidden nodes with an accuracy of 100%, a precision of 100%, a withdrawal of 100%.

Title

Found 8 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 8 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 8 Documents
Search