Claim Missing Document
Check
Articles

Breast cancer identification using a hybrid machine learning system Arifin, Toni; Agung, Ignatius Wiseto Prasetyo; Junianto, Erfian; Agustin, Dari Dianata; Wibowo, Ilham Rachmat; Rachman, Rizal
International Journal of Electrical and Computer Engineering (IJECE) Vol 15, No 4: August 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijece.v15i4.pp3928-3937

Abstract

Breast cancer remains one of the most prevalent malignancies among women and is frequently diagnosed at an advanced stage. Early detection is critical to improving patient prognosis and survival rates. Messenger ribonucleic acid (mRNA) gene expression data, which captures the molecular alterations in cancer cells, offers a promising avenue for enhancing diagnostic accuracy. The objective of this study is to develop a machine learning-based model for breast cancer detection using mRNA gene expression profiles. To achieve this, we implemented a hybrid machine learning system (HMLS) that integrates classification algorithms with feature selection and extraction techniques. This approach enables the effective handling of heterogeneous and high-dimensional genomic data, such as mRNA expression datasets, while simultaneously reducing dimensionality without sacrificing critical information. The classification algorithms applied in this study include support vector machine (SVM), random forest (RF), naïve Bayes (NB), k-nearest neighbors (KNN), extra trees classifier (ETC), and logistic regression (LR). Feature selection was conducted using analysis of variance (ANOVA), mutual information (MI), ETC, LR, whereas principal component analysis (PCA) was employed for feature extraction. The performance of the proposed model was evaluated using standard metrics, including recall, F1-score, and accuracy. Experimental results demonstrate that the combination of the SVM classifier with MI feature selection outperformed other configurations and conventional machine learning approaches, achieving a classification accuracy of 99.4%.
Prediksi Kelangsungan Hidup Pasien Gagal Jantung Menggunakan Pendekatan Machine Learning dengan Optimasi GridSearchCV Mulyani, Sri; Arifin, Toni
Jurnal Informatika Polinema Vol. 11 No. 4 (2025): Vol. 11 No. 4 (2025)
Publisher : UPT P2M State Polytechnic of Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33795/jip.v11i4.7938

Abstract

Gagal jantung menjadi salah satu penyebab utama tingginya angka kematian secara global, termasuk di Indonesia. Deteksi dini sangat krusial untuk mencegah progresivitas penyakit, tetapi pendekatan konvensional kerap memiliki keterbatasan akurasi. Penelitian ini memiliki tujuan untuk meningkatkan akurasi prediksi terhadap kelangsungan hidup pasien dengan kondisi gagal jantung melalui proses optimasi algoritma Machine Learning menggunakan teknik penyesuaian hiperparameter Grid SearchCV. Dataset yang digunakan berasal dari Heart Failure Clinical Records Dataset yang tersedia di UCI Machine Learning Repository, mencakup 299 data rekam medis pasien dengan 13 atribut klinis. Penelitian ini menggunakan enam algoritma klasifikasi, yang terdiri dari Random Forest, Decision Tree, Neural Network, K-Nearest Neighbors (K-NN), Support Vector Machine (SVM), dan Naïve Bayes. Hasil evaluasi menunjukkan bahwa algoritma Random Forest menghasilkan akurasi tertinggi, yaitu sebesar 87%, sebelum dilakukan proses optimasi. Peningkatan performa dicapai dengan Grid SearchCV, menghasilkan akurasi akhir sebesar 95%. Temuan ini membuktikan bahwa optimasi Hyperparameter mampu meningkatkan kinerja model secara signifikan. Implementasi hasil penelitian dapat mendukung rumah sakit dan layanan kesehatan dalam meningkatkan ketepatan diagnosis dini serta pemantauan pasien. Selain itu, studi ini menjadi referensi pengembangan sistem prediksi medis berbasis Machine Learning yang lebih mutakhir di masa depan.
IMPLEMENTASI GREEDY FORWARD SELECTION UNTUK PREDIKSI METODE PENYAKIT KUTIL MENGGUNAKAN DECISION TREE Fitriyani, Fitriyani; Arifin, Toni
JST (Jurnal Sains dan Teknologi) Vol. 9 No. 1 (2020)
Publisher : Universitas Pendidikan Ganesha

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (291.575 KB) | DOI: 10.23887/jstundiksha.v9i1.24896

Abstract

Penyakit kutil dapat ditangani dengan berbagai metode seperti cryotherapy dan  immunotherapy, akan tetapi dokter belum mengetahui metode pengobatan yang paling tepat untuk pasien, sehingga diperlukan pengujian agar dapat diketahui metode yang paling tepat untuk pasien. Penelitian ini menggunakan dataset cryotherapy dan immunotherapy dengan menggunakan algoritma klasifikasi Decision Tree. Pada dataset ini terdapat atribut atau fitur yang tidak relevan sehingga dilakukan seleksi fitur menggunakan Greedy Forward Selection. Hasil penelitian ini akan dilakukan perbandingan kinerja dari algoritma Decision Tree tanpa seleksi fitur Greedy Forward Selection dengan Decision Tree yang di integrasikan pada seleksi fitur Greedy Forward Selection dan pemilihan metode pengobatan penyakit kutil yang terbaik.
Use of Augmentation Data and Hyperparameter Tuning in Batik Type Classification using the CNN Model Auliaddina, Siti; Arifin, Toni
Sistemasi: Jurnal Sistem Informasi Vol 13, No 1 (2024): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v13i1.3395

Abstract

Batik is one of Indonesia's most recognized artistic cultures in the world and has different motifs and types of traditional batik and each has its own uniqueness. But unfortunately, there are still so many Indonesian people who cannot distinguish the types of batik based on their motifs. That's why we need a way to help people easily be able to distinguish the types of batik based on their motifs. This research was conducted to classify types of batik based on their motifs using the Convolutional Neural Network deep learning model using Data Augmentation and Hyperparameter Tuning. CNN is included in the type of Deep Neural Network because of its high network depth and is widely applied to image data. Besides that, Data Augmentation and Hyperparameter Tuning are also applied to reduce overfitting. The results of this study show that the CNN model that uses Data Augmentation optimization and Hyperparameter Tuning gets a much higher accuracy, precision and recall value of 66.67% compared to the CNN mode that does not use Data Augmentation and Hyperparameter Tuning which has validation accuracy, precision , and recall of 28.15%. Besides that, among Data Augmentation and Hyperparameter Tuning, Data Augmentation is the one that most influences the increase in validation accuracy, precision, and recall compared to Hyperparameter Tuning with an increase in validation accuracy to 64% from a validation accuracy of 28.15%.
SISTEM MONITORING DAN KONTROL PEMBERIAN PAKAN IKAN BERBASIS IOT MENGGUNAKAN BLYNK Risman, Risman; Rachman, Rizal; Arifin, Toni
Jurnal RESPONSIF: Riset Sains & Informatika Vol 6 No 2 (2024): Jurnal Responsif : Riset Sains dan Informatika
Publisher : LPPM Universitas Adhirajasa Reswara Sanjaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51977/jti.v6i2.1627

Abstract

Dalam era modern, permintaan akan sistem otomatis pemberian pakan ikan berbasis IoT semakin tinggi. Penelitian ini bertujuan mengembangkan sistem monitoring dan kontrol pemberian pakan ikan berbasis NodeMCU ESP8266 dan aplikasi Blynk. Sistem ini menggunakan servo untuk pemberian pakan otomatis dan manual melalui Blynk. Uji coba menunjukkan performa baik, sistem responsif merespons perintah pengguna dari jarak jauh. Akurasi gerakan servo mencapai 100%, mengindikasikan kualitas sistem yang kuat. Penelitian menyimpulkan bahwa sistem ini dapat dioperasikan secara efisien oleh pengguna dari jarak jauh melalui Blynk. Sistem ini berpotensi mengelola pemberian pakan ikan secara optimal, mendukung pertumbuhan dan kesehatan ikan. Dalam perkembangan teknologi, sistem ini membuka peluang baru dalam menjaga keberlangsungan akuakultur dengan pendekatan yang lebih pintar dan terhubung secara digital.
Emotion Detection in Indonesian Text Using the Logistic Regression Method Junianto, Erfian; Puspitasari, Mila; Zakaria, Salman Ilyas; Arifin, Toni; Agung, Ignatius Wiseto Prasetyo
Media Jurnal Informatika Vol 17, No 2 (2025): Media Jurnal Informatika
Publisher : Teknik Informatika Universitas Suryakancana Cianjur

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35194/mji.v17i2.5927

Abstract

Emotion detection in Indonesian text has become a crucial topic in the advancement of human–computer interaction and sentiment analysis on digital platforms. Despite its importance, challenges arise from the linguistic complexity and frequent use of slang in Indonesian text. This study aims to evaluate the performance of three classification models—Logistic Regression, K-Nearest Neighbors (KNN), and Naive Bayes—in detecting emotions from Indonesian text. The dataset comprises 1,000 texts categorized into four emotions: happy, sad, angry, and fear. Preprocessing steps included slang normalization, text cleaning, tokenization, stopword removal, and stemming, followed by TF-IDF weighting. Each model was trained and further optimized using ensemble bagging to improve classification performance. The optimized Logistic Regression model achieved the best performance, with an accuracy of 89%, precision of 0.90, recall of 0.89, F1-score of 0.89, and an average ROC-AUC score of 0.98. Both KNN and Naive Bayes models reached 81% accuracy after optimization, but their overall performance remained lower than Logistic Regression. The findings demonstrate that Logistic Regression is the most effective method for detecting emotions in Indonesian text, as it can effectively handle simple grammatical structures and slang variations. This study contributes to the development of emotion analysis models for Indonesian text, supporting applications in social computing and affective computing.
Stock Price Forecasting Using LSTM with Cross-Validation Rifki Ainul Yaqin; Anshori, Muhammad Iqbal; Angel, Reddis; Agung, Ignatius Wiseto Prasetyo; Arifin, Toni; Junianto, Erfian
Vokasi Unesa Bulletin of Engineering, Technology and Applied Science Vol. 3 No. 1 (2026)
Publisher : Universitas Negeri Surabaya or The State University of Surabaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26740/vubeta.v3i1.45130

Abstract

Stock price prediction remains challenging due to the market’s nonlinear, volatile nature, influenced by diverse economic and behavioral factors. Traditional models often suffer from overfitting and limited generalizability. This study addresses these limitations from prior research by other researchers for integrating Long Short-Term Memory (LSTM) with k-Fold Cross-Validation to improve prediction robustness. The proposed framework systematically evaluates model performance across varying market conditions. This methodological contribution enhances forecasting accuracy and stability, offering a more reliable approach to complex financial time series prediction. This study employs LSTM with one to two layers of 64–128 units, trained using Adam and dropout regularization, to capture long-term dependencies in stock price data. The workflow integrates feature selection, Min-Max scaling, and k-Fold Cross-Validation for robust evaluation. Model performance is assessed using RMSE, with reconfiguration applied to address underfitting or overfitting. The proposed model demonstrated substantial performance gains, achieving an average RMSE improvement of approximately 78.40% across all tested stocks compared to prior research. These enhancements are attributed to optimal hyperparameter tuning, consistent use of the Adam optimizer, and the implementation of k-Fold Cross-Validation, which reduced overfitting and provided more stable evaluations. Furthermore, findings revealed that simpler feature sets, such as using only closing prices, can outperform multiple technical indicators when normalization is inadequate, underscoring the importance of robust preprocessing and validation strategies. This study concludes that integrating LSTM with k-Fold Cross-Validation and optimized hyperparameters significantly improves stock price prediction accuracy.
Electric Vehicle Market Segmentation Based on Features and Specifications Using the K-Means Algorithm Rivanto, Farhan; Arifin, Toni
RIGGS: Journal of Artificial Intelligence and Digital Business Vol. 5 No. 1 (2026): Februari - April
Publisher : Prodi Bisnis Digital Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/riggs.v5i1.6879

Abstract

Kendaraan bermotor berbahan bakar fosil diketahui merupakan salah satu penyumbang utama emisi gas rumah kaca yang mempercepat perubahan iklim global. Sebagai alternatif yang lebih ramah lingkungan, mobil listrik hadir sebagai solusi karena tidak menghasilkan emisi gas buang secara langsung saat digunakan. Perkembangan teknologi kendaraan listrik mendorong meningkatnya minat konsumen terhadap berbagai tipe dan spesifikasi yang tersedia di pasar. Demikian, diperlukan segmentasi pasar untuk memahami karakteristik mobil listrik berdasarkan kebutuhan pengguna. Penelitian ini menerapkan algoritma K-Means Clustering untuk mengelompokkan mobil listrik berdasarkan fitur dan spesifikasi teknisnya. Dataset yang digunakan berasal dari platform Kaggle dengan judul Cheapest Electric Cars 2023 yang dipublikasikan oleh koustubhk. Dataset tersebut terdiri dari 307 data dengan beberapa variabel utama, yaitu Name, Acceleration, TopSpeed, Range, Efficiency, FastChargeSpeed, Drive, dan Number of Seats. Variabel-variabel ini merepresentasikan performa, efisiensi, dan kapasitas kendaraan yang relevan dalam pengambilan keputusan konsumen. Hasil analisis menunjukkan bahwa pasar mobil listrik dapat dikelompokkan menjadi tiga klaster utama, yaitu klaster C0 (mobil keluarga) sebanyak 137 item, klaster C1 (mobil perkotaan) sebanyak 109 item, dan klaster C2 (mobil sport) sebanyak 61 item. Evaluasi kualitas clustering menggunakan indeks Davies-Bouldin menghasilkan nilai sebesar 0,641. Nilai tersebut menunjukkan hasil segmentasi yang diperoleh tergolong cukup baik karena semakin kecil nilai Davies-Bouldin Index, maka semakin optimal pemisahan antar klaster yang terbentuk..