Claim Missing Document
Check
Articles

Implementasi Teknologi Cerdas Berbasis IoT dan Telegram untuk Monitoring Kesehatan Jantung Pangesti, Lintang Desy; Sandi A , Arif Setia; Ardianto, Rian
METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Vol. 9 No. 2 (2025): METHOMIKA: Jurnal Manajemen Informatika & Komputersisasi Akuntansi
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/jmika.Vol9No2.pp332-339

Abstract

The human heart acts as a vital organ that pumps blood throughout the body, and heart disease is the leading cause of death globally, including in Indonesia. To address this issue, this research proposes an Internet of Things (IoT)-based health monitoring system that can measure heart rate, oxygen saturation, and body temperature using MAX30100 and LM35 sensors. The system is equipped with real-time notification via Telegram and data display on an OLED screen. The method used is prototyping, with testing of sensor accuracy compared to conventional measuring instruments. The test results show good accuracy in BPM and SpO₂ measurements with an error of 5.78% and 3.6%, respectively, compared to the oximeter. However, body temperature measurement using the LM35 sensor showed an average error of 7.78%, due to the sensitivity of the sensor to ambient temperature.
Penerapan Algoritma DBSCAN dalam Mengidentifikasi Risiko Stroke Istiqomah, Hani; Khoirun Nisa; Arif Setia Sandi A.
METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Vol. 9 No. 2 (2025): METHOMIKA: Jurnal Manajemen Informatika & Komputersisasi Akuntansi
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/jmika.Vol9No2.pp340-349

Abstract

Stroke is a serious disease that can cause permanent disability and death. This study applies the DBSCAN algorithm to cluster Stroke risk using a public Kaggle dataset (n = 5,110), which contains demographic and clinical attributes such as age, gender, hypertension, heart disease, body mass index (BMI), glucose levels, and smoking status. Preprocessing steps included median imputation for BMI, categorical encoding, Z-score standardization, and PCA for visualization. Parameter selection was conducted using the k-distance plot and Silhouette evaluation, resulting in ε = 2.5 and min_samples = 3 with a Silhouette Score of 0.2158. The findings indicate that DBSCAN has potential to support Stroke prevention strategies, although further parameter tuning and feature optimization are required to improve clustering quality.
Pendampingan Ibu Balita Melalui Model Edukasi Gizi Berbasis Aplikasi Digital untuk Pencegahan Stunting di Kabupaten Brebes Sandi A., Arif Setia; Deny Nugroho Triwibowo; Azhar Bashir; Sony Kartika Wibisono; Fitri Ayuningtyas; Iis Setiawan Mangku Negara
Jurnal Pengabdian Pada Masyarakat METHABDI Vol 5 No 2 (2025): Jurnal Pengabdian Pada Masyarakat METHABDI
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/methabdi.Vol5No2.pp266-271

Abstract

Stunting is a chronic nutritional problem requiring sustainable intervention, particularly in priority areas such as Brebes Regency. Conventional nutritional interventions often lack sustainability in monitoring child growth and development. This program aims to evaluate the effectiveness of the Digital Application-Based Nutrition Education Model (Si Penting)—a collaboration between Universitas Harapan Bangsa and Universitas Muhammadiyah Brebes—in strengthening caregiver capacity. The activity was conducted in Bantarkawung Sub-district, involving 45 caregivers of toddlers aged 6–24 months. A one-group pre-test post-test design was employed. The intervention consisted of face-to-face nutrition education followed by training and mentoring on the Si Penting Digital Application for two weeks. This program emphasized intensive mentoring for caregivers to operate the application for independent monitoring. Results showed a significant increase in participants' knowledge and attitudes (p<0.05), followed by proactive behavioral changes in monitoring child growth. The intervention model was successful, as shown by a 95.6% adoption rate for the application. It is concluded that the Digital Application-Based Nutrition Education Model effectively helped caregivers improve their ability to monitor nutrition on their own and is suggested to be used alongside Posyandu services to create lasting benefits in lowering stunting risks.
Lightweight Hybrid Linformer-Mamba U-Net for Efficient Retinal Microaneurysm Segmentation Arif Setia Sandi Ariyanto; Deny Nugroho Triwibowo; Agriby Diandra Chaniago; Indah Trivilia; Annastasya Nabila Elsa Wulandari
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 11 No. 4 (2025): December
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v11i4.31598

Abstract

Diabetic retinopathy is a major microvascular complication of diabetes and a leading cause of vision loss among the working-age population. Microaneurysms (MAs), as the earliest clinical indicators of disease progression, remain challenging to segment due to their small size, low contrast, and extreme class imbalance. This study proposes a lightweight hybrid U-Net architecture for microaneurysm segmentation in retinal fundus images, designed to balance detection sensitivity and computational efficiency for deployment in resource-constrained environments. The proposed architecture integrates depthwise separable convolutions for efficient local feature extraction, a Transformer-Lite bottleneck based on Linformer self-attention for global contextual modeling, and a Mamba State Space Model (SSM)–based decoder to enhance feature propagation and spatial continuity.  The research contribution of this work is threefold: the introduction of an efficient hybrid U-Net combining Linformer and Mamba SSM for microaneurysm segmentation; a deployment-oriented evaluation protocol that explicitly distinguishes patch-level learning behavior from full-image reconstruction performance; and a transparent analysis of false positive behavior under extreme background dominance.  Experiments were conducted on the IDRiD dataset, consisting of 81 retinal images, using patient-level data splitting prior to patch extraction to prevent data leakage.  The results indicate that while patch-level evaluation demonstrates effective lesion-centric learning, deployment-realistic full-image evaluation reveals a notable performance degradation caused by false positive accumulation in extensive background regions. Nevertheless, the model maintains high recall, indicating preserved lesion sensitivity. These findings suggest that lightweight architectural design can deliver meaningful performance and is well suited for screening-oriented decision-support systems that prioritize efficiency and sensitivity.
Designing a stakeholder-informed digital learning model integrating virtual reality and e-learning for complementary therapy-based postpartum preeclampsia education Rini, Susilo; Sandi, Arif Setia; Ma’rifah, Atun Raudotul; Maya, Raden Ayu Aminah
MEDISAINS: Jurnal Ilmiah Ilmu-Ilmu Kesehatan Vol. 24 No. 1 (2026)
Publisher : Universitas Muhammadiyah Purwokerto

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30595/medisains.v24i1.30532

Abstract

Background: Postpartum preeclampsia remains a significant contributor to maternal morbidity and mortality in Indonesia. Midwives, as frontline maternal health providers, are expected to deliver holistic care; however, structured learning models integrating complementary therapies within digital education platforms remain limited. Although virtual reality (VR) and e-learning have been widely applied in healthcare education, their context-sensitive integration into postpartum preeclampsia management training has not been sufficiently explored. Objective: This study aimed to explore stakeholder perspectives and to design a stakeholder-informed conceptual digital learning model integrating complementary therapies into VR- and e-learning-based midwifery education. Methods: This qualitative exploratory study involved 31 participants, including practicing midwives, educational practitioners, policymakers, and clinical and technology experts in Banyumas Regency, Indonesia. Data were collected through focus group discussions and semi-structured in-depth interviews and analyzed using thematic analysis to identify stakeholder perspectives, contextual challenges, and design requirements informing the development of a conceptual digital learning model. Results: Four interconnected themes were identified: 1) fragmented integration of complementary care; 2) the need for experiential and clinically contextualized learning; 3) digital readiness and structural constraints; and 4) the importance of institutional support and policy alignment. These findings informed the development of a stakeholder-informed conceptual framework consisting of structured curriculum modules, a nine-scene VR storyboard simulating clinical decision-making, and a mobile-accessible Learning Management System integrating complementary therapies such as lavender aromatherapy, warm foot bath, and slow-stroke back massage. Conclusion: This study provides a contextually grounded digital learning framework for integrating VR, e-learning, and complementary therapies in postpartum preeclampsia education. The proposed model offers a foundation for future pilot implementation and effectiveness studies to evaluate its impact on midwifery competencies and clinical practice.
Co-Authors Agriby Diandra Chaniago Anggit Wirasto Annastasya Nabila Elsa Wulandari Apriliyanto, Erwin Ardianto, Rian Arkananta, Edgina Rangga Arrofie Darmawan Ashari, Imam Ashari, Imam Ahmad Ashari Asro Nasiri Asro Nasiri Aulia Zilmi Kafah, Aulia Zilmi Kafah Azhar Bashir Bagus Bambang Sumantri, Raden Bambang Soedijono Bambang Soedijono Bambang Sumantri, R Bagus Cipta Sigitta Haryono, Rito Deny Nugroho Triwibowo Deny Nugroho Triwibowo Diannike Putri, Diannike Putri Dung, Le Hoang E. Ida Hidayanti Edgina Rangga Arkananta, Edgina Rangga Arkananta Esa Aditya Kurniawan, Esa Aditya Kurniawan Faizal Rizky Yuttama Fenika Bunga Prawida Suwanto Feriyanto, Yanuar Fitri Ayuningtyas Grace Maria Fitricia Panggabean Husna, Aqmal Miftahul Iis Setiawan Mangku Negara Iis Setiawan Mangkunegara Imam Ahmad Ashari, Imam Ahmad Indah Trivilia Indriyanto, Jatmiko Irfan Arfianto Istiqomah, Hani Jayusman, Hadi Khairil Anwar Khoirun Nisa KHOIRUN NISA Kristanto, Barlian Mangku Negara, Iis Setiawan Mangku Negara, Iis Setiawan Mangkunegara, Iis Setiawan Maya, Raden Ayu Aminah Ma’rifah, Atun Raudotul Muryanto, Muhammad Negara, Iis Setiawan Mangku Nugroho Triwibowo, Deny Nugroho, Agus Susilo Nur Arifin, Nur Arifin Nurrizki, Kiki Alfaini Pangesti, Lintang Desy Pradestya Bima Arweina Prayoga, Estu Purwono Purwono, Purwono Purwono, Purwono Putri, Diannike Ramadya Wahyu Dwinanto Retno Agus Setiawan Rian Ardianto Ririn Damayanti Ririn Uke Saraswati Rito Cipta Sigitta Haryono riwibowo, Deny Nugroho Sandy Ferianda, Sandy Sarmin Sarmin Siti Shinta Yulistiyani, Siti Shinta Yulistiyani Slamet Slamet . Slamet Slamet Slamet Slamet Soedjatmoko Soedjatmoko Sony Kartika Wibisono Sony Sonjaya Sri Winda Hardiyanti Damanik susilo nugroho, agus Susilo Rini, Susilo Trivilia, Indah Triwibowo, Deny Nugroho Widadi, Budi Winda Neri Sari Yanuar Feriyanto Yayu Sri Rahayu, Yayu Sri Yusuf Fadlila Rahman