Claim Missing Document
Check
Articles

Found 5 Documents
Search

Performance Improvement of Deep Convolutional Networks for Aerial Imagery Segmentation of Natural Disaster-Affected Areas Nugraha, Deny Wiria; Ilham, Amil Ahmad; Achmad, Andani; Arief, Ardiaty
JOIV : International Journal on Informatics Visualization Vol 7, No 4 (2023)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.7.4.1383

Abstract

This study proposes a framework for improving performance and exploring the application of Deep Convolutional Networks (DCN) using the best parameters and criteria to accurately produce aerial imagery semantic segmentation of natural disaster-affected areas. This study utilizes two models: U-Net and Pyramid Scene Parsing Network (PSPNet). Extensive study results show that the Grid Search algorithm can improve the performance of the two models used, whereas previous research has not used the Grid Search algorithm to improve performance in aerial imagery segmentation of natural disaster-affected areas. The Grid Search algorithm performs parameter tuning on DCN, data augmentation criteria tuning, and dataset criteria tuning for pre-training. The most optimal DCN model is shown by PSPNet (152) (bpc), using the best parameters and criteria, with a mean Intersection over Union (mIoU) of 83.34%, a significant mIoU increase of 43.09% compared to using only the default parameters and criteria (baselines). The validation results using the k-fold cross-validation method on the most optimal DCN model produced an average accuracy of 99.04%. PSPNet(152) (bpc) can detect and identify various objects with irregular shapes and sizes, can detect and identify various important objects affected by natural disasters such as flooded buildings and roads, and can detect and identify objects with small shapes such as vehicles and pools, which are the most challenging task for semantic segmentation network models. This study also shows that increasing the network layers in the PSPNet-(18, 34, 50, 101, 152) model, which uses the best parameters and criteria, improves the model's performance. The results of this study indicate the need to utilize a special dataset from aerial imagery originating from the Unmanned Aerial Vehicle (UAV) during the pre-training stage for transfer learning to improve DCN performance for further research.
Perakitan Sistem WECG IoT dan Diseminasi Unjuk Kinerja untuk Memperkuat Sistem Layanan Kesehatan Puskesmas Kitta, Ikhlas; Palantei, Elyas; Suyuti, Ansar; Manjang, Salama; Samman, Faizal Arya; Nappu, Muhammad Bahtiar; Arief, Ardiaty; Said, Sri Mawar; ., Gassing; Gunadin, Indar Chaerah; ., Hasniaty; Adil, Andi Eri Andika; Palantei, Idris
JURNAL TEPAT : Teknologi Terapan untuk Pengabdian Masyarakat Vol 8 No 1 (2025): Community Empowerment through Higher Education Community Service Programs
Publisher : Faculty of Engineering UNHAS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25042/jurnal_tepat.v8i1.555

Abstract

This community service program is focused on a number of issues such as the implementation of the wireless ECG device design and the dissemination and demonstration of its technical operations in a such manner to all participants, e.g. the activists and supporters of the sub-village community healthcare center (PUSTU) located in Malimongeng Village, Salomekko District, Bone Regency. Several models of the latest WECG devices and the latest innovations have been developed and produced independently on the UNHAS campus, both hardware and software components. This Electrocardiogram (ECG) functions to monitor the condition of heart health and blood pressure in each patient who has been fitted with an ECG device. Each wireless ECG device is connected by an internet network and integrated at once in 1 Website that displays ECG signal graphics so that it can be monitored and controlled in real time from a distance. The application of ECG is very necessary for nurses or medical teams in a health institution to facilitate the control of the condition of patients in the room without having to walk back and forth to check the condition of patients being treated. The implementation of this community service is divided into 2 stages, namely the dissemination stage of basic knowledge of ECG technology and the technical training stage for operating ECG devices to support the patient condition control system at the health center. The results of recording the level of knowledge and understanding of the Malimongeng Village community who participated in community service activities carried out by a team of researchers and inventors from the Department of Electrical Engineering, Faculty of Engineering, Hasanuddin University were documented using the Googleform questionnaire application which had been designed earlier before the implementation of the activity in such a way as to measure the level of success of the implementation of the 2024 PKM program. The questionnaire survey was distributed and filled out by PKM participants online, both before and after the provision of material. After the implementation of the dissemination agenda and demonstration of the operation of the IoT WECG technology device, there was an increase in the knowledge and general understanding of the Malimongeng Village community who participated in the LBE Excellent Collaboration community service program in 2024 in both aspects of the category, namely general knowledge of health science and technical matters related to the development and production of IoT WECG devices along with their direct application in the midst of community life. The influence of participation in the series of PKM activities on both aspects of the target of counseling/socialization resulted in an increase in the capacity of knowledge in the community, namely around 30 percent and 25 percent respectively. Aspects of Technology Benefits and Activities, Based on the recommendations and input of all PKM activity participants, the following issues are highly expected by the Malimongeng Village community, including: aspects of the quality and diversity of cutting-edge science should be formulated to be more interesting and increase the insight of the village community, aspects of the availability of more sophisticated health devices should and should be equipped as soon as possible with more sophisticated and modern health infrastructure and facilities in the village and aspects of sustainability of research and development and production to overcome the problem of the availability of health facilities in the village and nationally.
Transformers for aerial images semantic segmentation of natural disaster-impacted areas in natural disaster assessment Wiria Nugraha, Deny; Ahmad Ilham, Amil; Achmad, Andani; Arief, Ardiaty
Bulletin of Electrical Engineering and Informatics Vol 14, No 2: April 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v14i2.8454

Abstract

Aerial image segmentation of natural disaster-impacted areas and detailed and automatic natural disaster assessment are the main focus of this study. Detecting and recognizing objects on aerial images of areas impacted by natural disasters and assessing natural disaster-impacted areas are still difficult problems. To solve these problems, this study utilizes four of the latest transformer-based semantic segmentation network models, bidirectional encoder representation from image transformers (BEIT), dense prediction transformer (DPT), OneFormer, and SegFormer, and proposes a detailed and automatic natural disaster assessment of the segmented image. The SegFormer model achieved the first-best result, and the OneFormer model achieved the second-best result. The SegFormer model outperformed OneFormer by 1.58% higher for the mean accuracy value and 4.28% for the mean intersection over union (mIoU) value. All receiver operating characteristics (ROC) curves have mean area under curve (AUC) values above 0.9, which means that the SegFormer model performs well in generating semantic segmentation images. The fuzzy c-means (FCM) clustering algorithm performed well and could automatically cluster the natural disaster assessments into four categories. This study has produced semantic segmentation of aerial images of areas impacted by natural disasters and natural disaster assessments, which can be used in natural disaster management systems.
Implementation of Orientation, Mobility, Socialization, and Communication Training to Support the Independence and Social Participation of People with Visual Disabilities in South Sulawesi Arief, Ardiaty; Nurlela, Andi; Bachtiar Nappu, Muhammad Bachtiar Nappu; Musywirah Hamka, Icha Musywirah Hamka; Salim, Ishak; Arianti Said, Ida; May Sweetha, Nabila; Ilham, Muhammad; Indar Dewa, Yoga
JURNAL TEPAT : Teknologi Terapan untuk Pengabdian Masyarakat Vol 8 No 2 (2025): Collaboration for Accelerated Community Achievement
Publisher : Faculty of Engineering UNHAS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25042/jurnal_tepat.v8i2.618

Abstract

Hasanuddin University, through the Institute for Research and Community Service in collaboration with SLB Negeri 1 Parepare and the South Sulawesi Regional Leadership Council of the Indonesian Blind Association, held an Orientation, Mobility, Socialization, and Communication (OMSC) Training for people with visual impairments as part of their commitment to an inclusive campus and strengthening inclusive literacy. This activity involved cross-disciplinary collaboration between the Faculty of Engineering, the Faculty of Social and Political Sciences, the Disability Center of Hasanuddin University, and the South Sulawesi Regional Leadership Council of the Indonesian Blind Association. The main objective of this activity was to increase the capacity of participants to carry out independent activities in public spaces. The research assumption states that hands-on training will increase participants' independence and self-confidence. The theoretical basis of the activity refers to a community empowerment approach and inclusive education that emphasizes the active participation of vulnerable groups. The implementation method included initial observation, pre-test, technical training (use of a white cane, hand protection techniques, as well as socialization and communication simulations), and a post-test. Participants were divided into small groups to facilitate mentoring. The results showed significant improvements in mobility and communication skills, as well as psychosocial impacts such as increased self-confidence. This activity resulted in an OMSC training model that can be replicated in other inclusive educational institutions. In conclusion, OMSC training based on interdisciplinary collaboration is effective in supporting the independence of people with visual impairments and strengthening the inclusive education ecosystem.
Socialization of the Application of Internet of Things (IoT) Technology for Temperature and Humidity Control in Oyster Mushroom Cultivation for Women Farmers Groups at the Takalar Mushroom House Salam, Andi Ejah Umraeni; Subir, Ade Nur Fatimah; Suyuti, Ansar; Manjang, Salama; ., Yusran; Akil, Yusri Syam; Said, Sri Mawar; Kitta, Ikhlas; A, Hasniaty; Arief, Ardiaty; Dewi, Dianti Utami; B, Ian Adrian
JURNAL TEPAT : Teknologi Terapan untuk Pengabdian Masyarakat Vol 8 No 2 (2025): Collaboration for Accelerated Community Achievement
Publisher : Faculty of Engineering UNHAS

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25042/jurnal_tepat.v8i2.631

Abstract

This community service activity was conducted by the Department of Electrical Engineering, Hasanuddin University, in collaboration with the Women Farmers Group (Kelompok Wanita Tani/KWT) Rumah Jamur Takalar in Takalar Regency. The program was initiated to address low efficiency and unstable temperature and humidity conditions in oyster mushroom (Pleurotus ostreatus) cultivation houses, which were previously managed manually. The main objective was to improve the knowledge and technical skills of mushroom farmers in understanding and applying Internet of Things (IoT) technology for automatic environmental monitoring and control. The activity was grounded in the concept of IoT-based smart farming, integrating temperature and humidity sensors, a microcontroller, and the Blynk application for real-time environmental supervision. The implementation stages included device design, system socialization and demonstration, and evaluation through pre- and post-activity questionnaires. A total of 15 KWT participants and 4 vocational students were actively involved in the training sessions. The results showed a significant enhancement in participants’ understanding, with the average knowledge score increasing from 2.0 (low awareness) to 4.0 (good understanding), indicating a 100% improvement after training. Participants also demonstrated high enthusiasm during the activities, actively engaging in discussions, operating the Blynk application, and recognizing the advantages of automated systems in maintaining stable temperature and humidity levels in mushroom cultivation houses. The impact of this program was reflected not only in improved knowledge but also in greater awareness and interest among participants in adopting IoT technology for their farming practices. Overall, the activity effectively introduced simple yet relevant technological innovations for small-scale farmers.