Claim Missing Document
Check
Articles

Deep Learning Approach to Lung Cancer Detection Using the Hybrid VGG-GAN Architecture Pamungkas, Yuri; Kuswanto, Djoko; Syaifudin, Achmad; Triandini, Evi; Hapsari, Dian Puspita; Nakkliang, Kanittha; Uda, Muhammad Nur Afnan; Hashim, Uda
International Journal of Robotics and Control Systems Vol 5, No 3 (2025)
Publisher : Association for Scientific Computing Electronics and Engineering (ASCEE)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31763/ijrcs.v5i3.1923

Abstract

Lung cancer ranks among the primary contributors to cancer-related deaths globally, highlighting the need for accurate and efficient detection methods to enable early diagnosis. However, deep learning models such as VGG16 and VGG19, commonly used for CT scan image classification, often face challenges related to class imbalance, resulting in classification bias and reduced sensitivity to minority classes. This study contributes by proposing an integration of the VGG architecture and Generative Adversarial Networks (GANs) to improve lung cancer classification performance through balanced and realistic synthetic data augmentation. The proposed approach was evaluated using two datasets: the IQ-OTH/NCCD Dataset, which classifies patients into Benign, Malignant, and Normal categories based on clinical condition, and the Lung Cancer CT Scan Dataset, annotated with histopathological labels: Adenocarcinoma, Squamous Cell Carcinoma, Large Cell Carcinoma, and Normal. The method involves initial training of the VGG model without augmentation, followed by GAN-based data generation to balance class distribution. The experimental results show that, prior to augmentation, the models achieved relatively high overall accuracy, but with poor performance on minority classes (marked by low precision and F1-scores and FPR exceeding 8% in certain cases). After augmentation with GAN, all performance metrics improved dramatically and consistently across all classes, achieving near-perfect precision, TPR, F1-score, and overall accuracy of 99.99%, and FPR sharply reduced to around 0.001%. In conclusion, the integration of GAN and VGG proved effective in overcoming data imbalance and enhancing model generalization, making it a promising solution for AI-based lung cancer diagnostic systems.
Penerapan Rendam Kaki Air Hangat terhadap Tekanan Darah pada Lansia dengan Hipertensi: The Application of Warm Water Foot Soaking on Blood Pressure in Elderly with Hypertension Aldy Mandaty, Fhandy; Syaifudin, Achmad; Sumarno, Sumarno; komsiyah, komsiyah; Nur Kumlasari, Dian; Handayaningtyas, Dita
Jurnal Keperawatan Berbudaya Sehat Vol. 3 No. 2 (2025): Juli 2025
Publisher : Universitas Ngudi Waluyo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35473/jkbs.v3i2.4166

Abstract

The elderly undergo a degenerative process that affects various bodily organ functions, including the cardiovascular system. One common disorder that occurs in this system is hypertension. Hypertension is a cardiovascular disease that cannot be completely cured, but it can still be controlled through proper management. Uncontrolled hypertension can lead to more serious health problems. The research aims to determine the application of warm foot soaks on blood pressure in elderly hypertensive individuals. The type of research is a case study with 4 research subjects, namely elderly patients suffering from hypertension. This research was conducted at one of the public health centers in Semarang City. The warm foot soak was performed for 15 minutes. Blood pressure measurements were taken twice, before and after the intervention. Warm foot soak therapy has been proven effective in lowering blood pressure in elderly hypertensive individuals, with an average reduction of  9 mmHg in systolic and 4 mmHg in diastolic pressure. It is hoped that classical music therapy will begin to be integrated as part of non-pharmacological interventions in the management of hypertension, particularly in the elderly.
Rancang Bangun Mesin Pengaduk Multifungsi guna Meningkatkan Potensi dan Membantu UMKM dengan Kebutuhan Pencampuran Bahan yang Terdapat di Kota Blitar, Jawa Timur Alhadi, Kafi Hannan; Hendrowati, Wiwiek; Guntur, Harus Laksana; Solichin, Moch.; Yuniarto, Muhammad Nur; Sutantra, I Nyoman; Wikarta, Alief; Pramono, Agus Sigit; Sutikno, Sutikno; Syaifudin, Achmad; Harto, Budi
Sewagati Vol 9 No 4 (2025)
Publisher : Pusat Publikasi ITS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j26139960.v9i4.2495

Abstract

Salah satu kendala utama yang dihadapi oleh UMKM adalah keterbatasan teknologi dan peralatan yang memadai. Banyak pengusaha kecil masih menggunakan cara manual dalam proses produksi, yang tentunya akan memakan waktu lama dan tenaga lebih besar. Selain itu, kualitas produk yang dihasilkan sering kali tidak konsisten, karena bergantung pada keterampilan pekerja dan alat-alat sederhana. Hal ini mengakibatkan terhambatnya kemampuan UMKM untuk meningkatkan skala produksi dan bersaing dengan perusahaan yang lebih besar. UMKM yang menjadi sasaran dalam rancangan kegiatan abmas ini adalah UMKM yang melibatkan proses pencampuran bahan dalam menjalankan usahanya. Contoh UMKM yang menjadi sasaran utama dalam abmas ini adalah UMKM yang bergerak pada bidang konstruksi level menengah ke bawah yang memerlukan bantuan alat pengaduk cat, UMKM yang memproduksi sabun cair, UMKM yang memproduksi lem perekat, hingga UMKM yang memproduksi makanan seperti kerupuk puli bawang, roti, donat yang notabene memerlukan proses pencampuran bahan. Pada Abmas dan KKN ini tim telah berhasil merancang 3 alat mixer untuk pencampuran bahan dan mendistribusikan kepada UMKM yang membutuhkan melalui kerja sama dengan Dinas Koperasi, UKM, dan Tenaga Kerja Kota Blitar.
Crashworthy Structure Analysis of Indonesia's First High-speed Train Trailer Made from Aluminum Extrusion Syaifudin, Achmad; Muh Luqman, Khakim
Journal of Engineering and Technological Sciences Vol. 57 No. 6 (2025): Vol. 57 No. 6 (2025): December
Publisher : Directorate for Research and Community Services, Institut Teknologi Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/j.eng.technol.sci.2025.57.6.3

Abstract

In the development of high-speed trains, evaluating the crashworthiness of passenger car structures is essential, particularly in the vestibule area which designed to absorb impact energy. When constructed entirely from aluminum extrusion, the vestibule exhibits high stiffness and uncontrolled energy absorption, resulting in excessive deceleration during collisions. This study investigates the crashworthiness of the vestibule structure in Indonesian high-speed train trailers, referencing EN 15227/SNI 8826 and 49 CFR 238 standards. A numerical analysis was conducted using ANSYS LS-DYNA, examining four structural configurations: a full aluminum extrusion model referred to the rear end structure of the HST locomotive, and three alternatives incorporating structural beams in the roof, floor, and modified floor areas. Simulations involved train collisions with a rigid wall at regulated speeds, using aluminum 6005A-T6 modeled with the Johnson-Cook material model to account for high strain rates. Results showed that the full aluminum design produced excessive deceleration and failed to meet EN 15227/SNI 8826 criteria. In contrast, the modified floor frame design achieved the lowest crash force and deceleration, controlled energy absorption, no survival space reduction, and compliance with EN 15227/SNI 8826, though it did not meet 49 CFR 238 deceleration limits due to full vestibule deformation. These findings offer valuable insights for manufacturers seeking to enhance the crashworthiness of high-speed train passenger cars.
Media Informasi Latihan Isotonik Membantu Meningkatkan Rentang Gerak Sendi Lutut pada Lansia di Desa Leyangan Ungaran Syaifudin, Achmad; Nurhayati, Susi
Prosiding University Research Colloquium Proceeding of The 7th University Research Colloquium 2018: Bidang MIPA dan Kesehatan
Publisher : Konsorsium Lembaga Penelitian dan Pengabdian kepada Masyarakat Perguruan Tinggi Muhammadiyah 'Aisyiyah (PTMA) Koordinator Wilayah Jawa Tengah - DIY

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

Abstract

Keberhasilan pembangunan adalah cita-cita suatu bangsa yangterlihat dari peningkatan taraf hidup dan Umur Harapan Hidup(UHH)/ Angka Harapan Hidup (AHH). Masalah kesehatan lansia diIndonesia berdasarkan data Kemenkes RI tahun 2016 dalam urutan 10besar adalah sebagai berikut: hipertensi, arthritis, stroke, PPOK, DM,kanker, Jantung koroner, batu ginjal, gagal jantung dan gagal ginjal.Data ini menunjukkan bahwa penyakit arthritis yang berkontribusipada keluhan kaku sendi, nyeri dan keterbatasan pergerakanmenempati urutan ke dua terbesar setelah hipertensi. Data diPerumnas Leyangan Ungaran terdapat 140 lansia yang menjadibinaan Posyandu Lansia Leyangan wilayah kerja PuskesmasLeyangan. Sekitar 30% dari jumlah tersebut mengalami masalahpenyakit degenerative diantaranya kaku-kaku pada persendian dannyeri persendian. Tujuan penelitian adalah untuk mengidentifikasikeluhan pada sendi khususnya lutut lansia, sehingga akandikembangkan media informasi dengan memberikan latihan isotonikdan dilakukan intervensi pada lansia dengan keluhan pada sendi.Design penelitian menggunakan Quasy Exsperiment without controlgroup. Teknik sampling tahap pertama dengan cluster randomsampling sebanyak 103 lansia, tahap kedua dengan teknik purposivesampling pada 15 lansia diberikan intervensi senam isotonicmenggunakan alat bantu media informasi lembar balik dan videosenam isotonik, peralatan senam isotonik (isotonik exercise kit). Datadikumpulkan menggunakan kuesioner, pengukuran rentang gerak predan post intervensi menggunakan Goniometer, diuji dengan paired ttest dengan hasil adanya perbedaan rentang gerak pada lutut kanan (pvalue 0,02) besar perbedaan 4,67. Ada perbedaan rentang gerak padalutut kiri (p value 0,02) besar perbedaan 8,00. Kesimpulan: Terdapatperbedaan yang bermakna antara rentang gerak sendi lutut sebelumdan sesudah perlakuan pada lutut sebelah kanan.dan lutut sebelah kiripada Lansia di Desa Leyangan.
Strength Assessment of Prosthetic Pylon Considering the Geometric of Raw Material Syaifudin, Achmad; Suryandari, Dika Andini; Agustin, Helena Carolina Kis
Journal of Medicine and Health Technology Vol. 1 No. 1 (2024)
Publisher : Direktorat Riset dan Pengabdian Kepada Masyarakat, Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j30466865.v1i1.1214

Abstract

Prosthetic limbs are crucial as assistive devices for individuals with lower limb amputations. This study focuses on designing and analysing prosthetic feet, specifically the telescopic tube component, to achieve optimal material strength and aesthetic appeal. Numerical simulations using ANSYS Workbench 19 are conducted to assess the total deformation and von Mises stress. Design iterations adjust the pylon tube thickness and material selection. Prototypes are developed using aluminium 6061 tube and rod materials for further testing. Various tests, including scanning electron microscopy, metallography, axial tensile testing, and tangential tensile testing (according to ASTM B 557M), are performed to evaluate the material properties. Results indicated that the axial and yield strengths of the aluminium 6061 rod are superior to the tube type. Conversely, the aluminium 6061 tube exhibits higher ultimate and yield stability in tangential testing. Ultimately, the study concludes that the aluminium 6061 tube material is more robust and suitable for prosthetic feet.
STRENGTH CONSIDERATION ON CAR BODY MODIFICATION FOR PANORAMIC TRAIN Harnany, Dinny; Adista, Reyhan K. A.; Syaifudin, Achmad; Putra, Ary Bachtiar Krishna; Priyambodo, Singgih
Jurnal Rekayasa Mesin Vol. 15 No. 1 (2024)
Publisher : Jurusan Teknik Mesin, Fakultas Teknik, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21776/jrm.v15i1.1510

Abstract

Modifying the car body structure from the existing train to another car body type requires an analysis of several factors. The strength of the design due to overload and the durability of the structures due to operational loads need to be re-evaluated. Furthermore, stiffness analysis also needs to determine the characteristics of the structure when it is not loaded. This study numerically analyzed the considerations in selecting the structural steel profile for modification of the existing car body into a panoramic type using the ANSYS Workbench R19. The underframe structure can still be used, and other structures are modified with the UNP profile. The side wall, and roof are changed in shape and size following the glass design of the panoramic train. The solid 3D model is rebuilt into a surface model to simplify the analysis. Static structural analysis is used to clarify the strength of the design under overload, a combination of static and transient structural analysis is applied to calculate the operating life, and modal analysis is chosen to figure out the stiffness. The simulation results showed that the modified design had met the needs and requirements based on the PM 175 standard of 2015 by the Indonesian Ministry of Transportation and the international standard EN-12663.
Numerical Analysis of the Failure of a 3D-Printed Knee Joint for a Transfemoral Amputee Amelia Arsyl , Majid; Syaifudin, Achmad
Journal of Medicine and Health Technology Vol. 2 No. 2 (2025)
Publisher : Direktorat Riset dan Pengabdian Kepada Masyarakat, Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12962/j30466865.v2i2.2625

Abstract

A leg prosthesis is a tool that can help people with disabilities due to amputation or birth defects. Prosthetic leg products created through the 3D printing process on the knee joint have been reported to have cracked after two months of use. The purpose of this study was to observe the causes of failure of knee joints in prosthetic legs printed using the 3D printing method. The numerical method based on the finite element method, ANSYS Workbench 2023, was chosen to complete the structural simulation. The model parameters observed in the simulation were the printing orientation, model position, and equivalent plastic strain of PETG, ABS, and PLA. Several print-direction positions were considered in this simulation, namely 0°, 45°, and 90°. Static simulation of the structure was performed because only the static forces acted on the knee joint. Static forces were obtained by applying the principle of static equilibrium to rigid objects. The results of the numerical simulation showed that damage to the knee joint made of PTEG was caused by the plane of 90°. The orientation position causes the force received in the perpendicular direction of the knee joint component; thus, it tends to break the printing layers. The ideal printing orientation for the knee joint is 0° orientation. This orientation is considered suitable because it has the highest safety factor compared to other orientations.
Behaviors to Prevent Needle Stick Injury Among Nursing Students : A Systematic Literature Review Saparwati, Mona; Trimawati; Achmad Syaifudin
Indonesian Journal of Nursing Research (IJNR) Vol. 8 No. 2 (2025)
Publisher : Program Studi S1 Keperawatan Universitas Ngudi Waluyo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35473/ijnr.v8i2.4582

Abstract

The highest incidence of accidents and safety issues among nursing students during clinical practice is needle stick injury (NSI). Various efforts have been made to develop behaviors that prevent such incidents. This study is a literature review adapted from the Arskey and O'Malley framework. The Prisma-Scr flowchart was used to display the literature search flow. Articles for this study were searched using  five search engines: PubMed, Sage, Wiley, Scopus, and ScienceDirect. The keywords used for literature search were occupational injury OR accidental AND needlestick injury AND nursing student AND program. The inclusion criteria used were publication between 2013 and 2023, articles in English, and a focus on preventing needle stick injuries among nursing students. The review results showed that there were 25 potentially relevant articles, and 10 articles met the selection criteria. The articles were from several different countries, and 10 articles that met the criteria used quantitative and qualitative designs. This review revealed three themes, namely the incidence of needle stick injuries among nursing students, nursing students' understanding of preventing NSI, and efforts to prevent NSI. NSI incidents still occur among nursing students who conduct clinical practice in hospitals. Nursing students' understanding of preventing NSI is obtained through education from academic institutions and hospitals. Efforts to improve knowledge, attitudes, and behaviors to prevent NSI are carried out through education, training, the use of safe needles, and communication.
Alzheimer's disease detection based on MR images using the quad convolutional layers CNN approach Pamungkas, Yuri; Syaifudin, Achmad; Yunanto, Wawan; Hashim, Uda
Bulletin of Electrical Engineering and Informatics Vol 14, No 6: December 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v14i6.10304

Abstract

Alzheimer’s disease is a progressive neurodegenerative disorder requiring early and accurate detection for effective intervention. Deep learning (DL) techniques, particularly convolutional neural networks (CNNs), have shown promise in medical image classification. However, conventional CNN models often suffer from high computational complexity and inefficiency in handling imbalanced datasets. This study proposes a quad convolutional layers-CNN (QCL-CNN) for Alzheimer’s disease detection using magnetic resonance images (MRI) scans from the open access series of imaging studies (OASIS) dataset, which includes four dementia stages, non-dementia, very mild dementia, mild dementia, and moderate dementia. The QCL-CNN model employs four sequential convolutional layers for enhanced multi-level feature extraction, ensuring efficient classification while minimizing computational overhead. The experimental results demonstrate that QCL-CNN outperforms traditional CNN architectures, achieving an accuracy of 99.90%, recall of 99.89%, specificity of 99.93%, and an F1-score of 99.52%. The model surpasses VGG19, Xception, ResNet50, and DenseNet201 while maintaining a significantly lower parameter count (4.2M), making it computationally efficient. These findings confirm that network optimization is more crucial than model depth, ensuring robust performance even with fewer layers. Future research should explore multi-modal imaging, class balancing techniques, and real-world clinical validation to further improve the model’s diagnostic capabilities. The QCL-CNN model offers a promising artificial intelligence (AI)-powered approach for early Alzheimer’s detection, enabling precise, and efficient medical diagnosis.