Article Per Year (5 Year)
p-Index From 2021 - 2026
0.778
P-Index
This Author published in this journals
All Journal Indonesian Journal of Global Health research Jurnal Teknologi dan Manajemen Industri Terapan Jurnal Manajemen Pelayanan Kesehatan (The Indonesian Journal of Health Service Management)
Lazuardi Fatahillah Hamdi
Universitas Muhammadiyah Gombong
Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Education Engineering Health Professions Industrial & Manufacturing Engineering Languange, Linguistic, Communication & Media Nursing Public Health

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

 1 
Kualitas Dataset dan Strategi YOLO untuk Deteksi Cacat Jahitan Berukuran Kecil: Tinjauan Literatur Sistematis menuju Inspeksi Bordir Real-Time Eko Ari Wibowo; Widyastuti; Lazuardi Fatahillah Hamdi; Eka Samsul Ma’arif
Jurnal Teknologi dan Manajemen Industri Terapan Vol. 5 No. 3 (2026): Jurnal Teknologi dan Manajemen Industri Terapan
Publisher : Yayasan Inovasi Kemajuan Intelektual

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55826/jtmit.v5i3.2002

Abstract

Inspeksi cacat bordir berbasis computer vision memerlukan dataset yang konsisten dan model yang mampu mendeteksi pola kecil, tipis, memanjang, serta berkontras rendah. Penelitian ini menyintesis praktik kualitas dataset dan strategi You Only Look Once (YOLO) untuk deteksi cacat tekstil sebagai dasar pengembangan inspeksi bordir real-time. Tinjauan dilakukan berdasarkan Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020. Pencarian Scopus menghasilkan 284 dokumen dan menyisakan 82 dokumen setelah penyaringan tahun, jenis dokumen, bahasa, dan akses terbuka. Sebanyak 61 artikel dinilai berdasarkan naskah lengkap, dan 34 studi primer disertakan dalam sintesis, sedangkan sumber lain yang relevan digunakan sebagai bukti pendukung. Data diekstraksi berdasarkan sumber dataset, akuisisi, anotasi, pembagian data, augmentasi, arsitektur YOLO, strategi small-object detection, dan kinerja komputasi. Hasil menunjukkan dominasi pendekatan model-centric berupa attention mechanism, multi-scale feature fusion, lightweight architecture, loss function optimization, operator konvolusi khusus, dan small-object detection head. Sebaliknya, definisi operasional kelas, pedoman anotasi bounding box, quality control label, metadata akuisisi, dan pencegahan data leakage masih terbatas. Kerangka terintegrasi diusulkan untuk menghubungkan definisi cacat, akuisisi, kurasi, anotasi, pengembangan YOLO, serta validasi akurasi, kecepatan, dan robustness sebagai landasan penelitian cacat bordir pada Usaha Mikro, Kecil, dan Menengah (UMKM).
Desain Sistem Pendeteksi Nominal dan Keaslian Uang untuk Tunanetra Berbasis Sensor Optik–UV dengan Pendekatan Value Engineering Eko Ari Wibowo; Widyastuti; Lazuardi Fatahillah Hamdi
Jurnal Teknologi dan Manajemen Industri Terapan Vol. 4 No. 4 (2025): Jurnal Teknologi dan Manajemen Industri Terapan
Publisher : Yayasan Inovasi Kemajuan Intelektual

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55826/jtmit.v4i4.1321

Abstract

Penyandang tunanetra menghadapi kendala signifikan dalam mengenali nominal dan keaslian uang kertas yang berdampak pada kemandirian dan keamanan transaksi. Penelitian ini bertujuan untuk merancang dan menguji sistem otomasi pendeteksi uang berbasis sensor optik (ESP32-CAM) dan ultraviolet (UV LED) dengan pendekatan Value Engineering (VE). Metode VE digunakan untuk memastikan rancangan sistem memiliki fungsi optimal, efisien dalam penggunaan komponen, dan sesuai kebutuhan pengguna. Lima tahap utama VE meliputi tahap informasi, kreatif, evaluasi, pengembangan, dan rekomendasi yang diterapkan dalam penelitian ini. Hasil evaluasi terhadap tiga alternatif desain menunjukkan bahwa konfigurasi ESP32-CAM + DFPlayer Mini + UV LED memiliki nilai fungsi tertinggi (rata-rata 4,55). Pengujian laboratorium terhadap 700 sampel citra uang menunjukkan tingkat akurasi pengenalan nominal 90–98% dan verifikasi keaslian 90–97%. Hasil ini menegaskan bahwa metode VE efektif dalam menghasilkan sistem deteksi uang yang akurat, efisien, dan inklusif bagi penyandang tunanetra.
Utilizing Artificial Intelligence to Analyze Gender Differences in Hypertension Risk Factors Husnul Khuluq; Tri Cahyani Widiastuti; Lazuardi Fatahillah Hamdi; Tunjung Winarno
Indonesian Journal of Global Health Research Vol 7 No 1 (2025): Indonesian Journal of Global Health Research
Publisher : GLOBAL HEALTH SCIENCE GROUP

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37287/ijghr.v7i1.4929

Abstract

Hypertension continues to pose a significant challenge to global health. Early identification of risk factors, particularly those influenced by gender differences, has the potential to markedly enhance treatment processes and outcomes. Artificial intelligence (AI), specifically machine learning (ML), offers a promising avenue for identifying and analysing these critical risk factors. Objective: This study aims to explore the influence of gender differences on risk factors affecting hypertensive patients by examining demographic, medication, clinical, and laboratory data.Method: The study utilized medical records of hospitalized hypertensive patients at PKU Muhammadiyah Hospital Yogyakarta, covering the years 2022 to 2023. Logistic regression analysis with Lasso penalty was applied to determine the most influential variables. Additionally, the Random Forest algorithm implemented in WEKA, combined with a 10-fold cross-validation approach, was employed to evaluate the model’s diagnostic performance using metrics such as precision, sensitivity, specificity, accuracy, and the area under the receiver operating characteristic curve (ROC-AUC). Results: A total of 1,006 patients were included in the sample, comprising 504 males and 502 females. Among the 33 clinical variables analysed, 13 demonstrated non-zero coefficients. For female hypertensive patients, the five most significant risk factors, along with their coefficients, were Haemoglobin (0.03), Diabetes Mellitus (0.04), Lymphocytes (0.06), Anaemia (0.13), and Creatinine (0.15). In male hypertensive patients, the top five risk factors and their coefficients were Acute Kidney Injury (-0.32), Erythrocytes (-0.15), Congestive Heart Failure (-0.03), Leukocytes (-0.02), and Length of Stay (LOS) (-0.01). The model’s overall performance, as reflected by a ROC-AUC score of 0.805, indicates a good level of predictive accuracy. Conclusions: The findings reveal a significant association between gender and hypertension risk factors. These results underscore the potential for gender-specific customization of hypertension treatments, paving the way for more individualized therapeutic strategies and improved patient outcomes.
MODEL PREDIKSI FAKTOR-FAKTOR RISIKO OBESITAS MENGGUNAKAN MACHINE LEARNING Husnul Khuluq; Lazuardi Fatahillah Hamdi; Ayu Nissa Ainni; Tri Cahyani Widiastuti
Journal of Health Service Management Vol 29 No 00 (2026): Vol 29/Edisi Khusus/Februari/2026
Publisher : Departemen of Health Policy and Management, Faculty of Medicine, Public Health, and Nursing, Universitas Gadjah Mada, Yogyakarta Jl. Farmako Sekip Utara Yogyakarta 55281 Telp 0274-547490

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/jmpk.v29i00.25716

Abstract

Background: Obesity is a major global health concern and a key risk factor for various non-communicable diseases, including diabetes, hypertension, and cardiovascular disorders. Despite extensive studies, accurately identifying the key contributing factors remains a challenge. Objective: This study aims to predict the likelihood of obesity using a machine learning algorithm, based on questionnaire-derived clinical and behavioral data. Several supervised machine learning algorithms—logistic regression, naïve Bayes, support vector machine (SVM), and random forest—will be employed to build predictive models. Model performance will be evaluated using accuracy, precision, sensitivity, specificity, and area under the receiver operating characteristic curve (AUC). Methods: We used an open-access dataset from Kaggle comprising 2,111 samples with anthropometric, demographic, and lifestyle data. Of these, 972 individuals were categorized as obese and 1,139 as non-obese. The target variable was categorized into binary labels: "Obesity" and "Non-Obesity." Preprocessing included one-hot encoding, label encoding, and train-test splitting. All four ML models were trained and evaluated using accuracy, area under the curve (AUC), precision, sensitivity, and specificity metrics. Results: The model achieved an accuracy of 98.58%, AUC of 99.96%, sensitivity of 98.99%, specificity of 98.21%, and precision of 98.01%. The most influential predictors were weight, frequent consumption of high-caloric food, family history of being overweight, physical activity frequency, and daily water intake. Conclusion: The model demonstrated high performance and identified key lifestyle-related features. These findings support machine learning's potential for obesity screening and public health strategy development.
Co-Authors Ayu Nissa Ainni Eka Samsul Ma’arif Eko Ari Wibowo Husnul Khuluq Tri Cahyani Widiastuti Tunjung Winarno Widyastuti