Claim Missing Document
Check
Articles

Found 7 Documents
Search

Pelatihan Pembuatan Media Pembelajaran Interaktif Berbasis Web (MPI-BeWe) Bagi Guru-Guru SD Sekecamatan Pulau Beringin, Muara Dua, Sumatera Selatan Fathurohman, Apit; Yusup, Muhammad; Seira, Erazando Alfa; Kistiono; Pasaribu, Abidin; Samsuryadi
TRIMAS: Jurnal Inovasi dan Pengabdian Kepada Masyarakat Vol. 3 No. 1 (2023): Trimas: Jurnal Inovasi dan Pengabdian Kepada Masyarakat
Publisher : Indra Institute Research & Publication

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58707/trimas.v3i1.418

Abstract

The main objective of this research is to train and provide assistance to elementary school teachers in Pulau Beringin District, Ogan Komering Ulu Selatan District (OKUS) in making web-based interactive learning media (MPI BeWe). Using the Technical Assistance method in the form of Training and Workshops which is carried out by providing training and workshops with steps: socialization, practice, mentoring, and evaluation. One of the obstacles to the development of multimedia learning media is the lack of mastery of ICT-based multimedia learning media development technology by teachers so the development of ICT-based multimedia learning materials is not optimal. Especially elementary school teachers in the Beringin Island District, South Ogan Komering Ulu Regency (OKUS). After carrying out this activity, it can be concluded that elementary school teachers in Pulau Beringin District, Ogan Komering Ulu Selatan (OKUS) Regency who were participants in the training and mentoring for the creation of BeWe MPI-based learning media (Web-Based Learning Media) succeeded in making learning media in the form of blogs. The implementation of the training has been able to achieve the expected goals, this can be seen from the tasks given to participants which can be completed properly.
The Development of PISA-based Numerical Problem Using the Context of Religious Day during the Pandemic Sepriliani, Sisca Puspita; Zulkardi; Putri, Ratu Ilma Indra; Samsuryadi; Alwi, Zahra; Meryansumayeka; Jayanti; Nusantara, Duano Sapta; Sistyawati, Risda Intan; Tanjung, Ayu Luviyanti; Aprilisa, Shinta; Pratiwi, Riszky Pabela
Mathematics Education Journal Vol. 16 No. 2 (2022): Jurnal Pendidikan Matematika
Publisher : Universitas Sriwijaya in collaboration with Indonesian Mathematical Society (IndoMS)

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

Abstract

This study aims to produce valid and practical PISA-based numerical problems in the context of the pandemic period and to find out the role of the questions in the form of potential effects on the mathematical literacy skills of secondary school students. This research uses developmental research design, which has 2 stages, namely preliminary and formative evaluation (self-evaluation, expert review, one-to-one and small group validation, and field test). The participants in this study were students in Grade 8 who were under the age of 15 and different levels of skills. Data analysis was done descriptively by conducting observations, tests, interviews, and document analysis. The research was conducted face-to-face and via Zoom and WhatsApp Group (WAG) to produce valid and practical PISA-like arithmetic questions. Based on the students' responses, it can be stated that the questions presented are in the practical category because they can be completed quickly by students, they can be understood well by students, and they have the potential effect on students' mathematical literacy skills. In addition, there is a diversity of answers between one student and another according to the level of difficulty that is appropriate for Grade 8 students. This proves that a PISA-like numeration problem in the context of the religious day during a pandemic can help improve students' mathematical literacy.DOI : https://doi.org/10.22342/jpm.16.2.16010.157-170
Community Empowerment To Improve Clean And Healthy Living Behavior [Chlb]: An Action Research Hamzah Hasyim; Samsuryadi; Mulyadi Eko Purnomo; Bimo Brata Adhitya; Nur Alam Fajar; Hendro Cahyono
International Journal Of Community Service Vol. 1 No. 3 (2021): November 2021 (Indonesia - Malaysia)
Publisher : CV. Inara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51601/ijcs.v1i3.41

Abstract

Efforts to change people's behaviors to support the improvement of health status are carried out through the Clean and healthy living behavior (CHLB) development program. Although this program has been implemented by the Ministry of Health in Indonesia since 1996, CHLB implementation has not run optimally. Evaluation of CHLB development's success is carried out by looking at CHLB indicators, one of which is in the school setting. CHLB at school is an activity to empower students, teachers, and the school community to adopt a healthy lifestyle to create healthy schools. This study aims to increase the students' knowledge, attitudes, and actions regarding CHLB in Madrasah Diniyyah, Al Islam Educational Institution, Talang Aur Village, Ogan Ilir Regency, South Sumatra Province.The study uses action research. This activity is carried out by providing communication, information, and education (KIE) regarding CHLB. In addition, we offer knowledge tests about CHLB and demonstrations by practicing how to wash hands correctly and adequately using clean water and soap to increase students' understanding of CHLB activities. This study emphasizes the importance of socializing clean and healthy life early through integrating learning programs in schools. The results showed an increase in the target audience's knowledge, attitudes, and actions about CHLB. The benefits of CHLB in schools include creating a clean and healthy environment, improving the teaching, and learning process, and making students, teachers, and the school environment healthy.
Detection of Diabetic Retinopathy Using Convolutional Neural Network (CNN) Yazid, Rizq Khairi; Samsuryadi
Computer Engineering and Applications Journal (ComEngApp) Vol. 11 No. 3 (2022)
Publisher : Universitas Sriwijaya

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

Abstract

One of the complications of Diabetes Mellitus, namely Diabetic Retinopathy (DR) damages the retina of the eye and has five levels of severity: Normal, Mild, Medium, Severe and Proliferate. If not detected and treated, this complication can lead to blindness. Detection and classification of this disease is still done manually by an ophthalmologist using an image of the patient's eye fundus. Manual detection has the disadvantage that it requires an expert in the field and the process is difficult. This research was conducted by detecting and classifying DR disease using Convolutional Neural Network (CNN). The CNN model was built based on the VGG-16 architecture to study the characteristics of the eye fundus images of DR patients. The model was trained using 4750 images which were rescaled to 256 X 256 size and converted to grayscale using the BT-709 (HDTV) method. The CNN-based software with VGG- 16 architecture developed resulted in an accuracy of 62% for the detection and classification of 100 test images based on five DR severity classes. This software produces the highest Sensitivity value in the Normal class at 90% and the largest Specificity value in the Mild class at 97.5%.
Brahmi Script Classification using VGG16 Architecture Convolutional Neural Network Vincen; Samsuryadi
Computer Engineering and Applications Journal (ComEngApp) Vol. 11 No. 2 (2022)
Publisher : Universitas Sriwijaya

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

Abstract

Many Indonesians have difficulty reading and learning the Brahmi script. Solving these problems can be done by developing software. Previous research has classified the Brahmi script but has not had an output that matches the letter. Therefore, letter classification is carried out as part of the process of recognizing Brahmi script. This study uses the Convolutional Neural Network (CNN) method with the VGG16 architecture for classifying Brahmi script writing. Training results from various amounts of image data. Smooth model. The requested image data is a 224x224 binary image. This study has the highest quality, accuracy is 96%, highest recall is 98% and highest precision is 98%.
Classification of Epilepsy Diagnostic Results through EEG Signals Using the Convolutional Neural Network Method Sari, Tri Kurnia; Rini, Dian Palupi; Samsuryadi
Computer Engineering and Applications Journal (ComEngApp) Vol. 12 No. 2 (2023)
Publisher : Universitas Sriwijaya

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

Abstract

The brain is one of the most important organs in the human body as a central nervous system which functions as a controlling center, intelligence, creativity, emotions, memories, and body movements. Epileptic seizure is one of the disorder of the brain central nervous system which has many symptoms, such as loss of awareness, unusual behavior and confusion. These symptoms lead in many cases to injuries due to falls, biting one’s tongue. Detecting a possible seizure beforehand is not an easy task. Most of the seizures occur unexpectedly, and finding ways to detect a possible seizure before it happens has been a challenging task for many researchers. Analyzing EEG signals can help us obtain information that can be used to diagnose normal brain activity or epilepsy. CNN has been demonstrated high performance on detection and classification epileptic seizure. This research uses CNN to classify the epilepsy EEG signal dataset. AlexNet and LeNet-5 are applied in CNN architecture. The result of this research is that the AlexNet architecture provides better precision, recall, and f1- score values on the epilepsy signal EEG data than the LeNet-5 architecture.
Optimization of Deep Neural Networks with Particle Swarm Optimization Algorithm for Liver Disease Classification Sidqi, Muhammad Nejatullah; Rini, Dian Palupi; Samsuryadi
Computer Engineering and Applications Journal (ComEngApp) Vol. 12 No. 1 (2023)
Publisher : Universitas Sriwijaya

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

Abstract

Liver disease has affected more than one million new patients in the world. which is where the liver organ has an important role function for the body's metabolism in channeling several vital functions. Liver disease has symptoms including jaundice, abdominal pain, fatigue, nausea, vomiting, back pain, abdominal swelling, weight loss, enlarged spleen and gallbladder and has abnormalities that are very difficult to detect because the liver works as usual even though some liver functions have been damaged. Diagnosis of liver disease through Deep Neural Network classification, optimizing the weight value of neural networks with the Particle Swarm Optimization algorithm. The results of optimizing the PSO weight value get the best accuracy of 92.97% of the Hepatitis dataset, 79.21%, Hepatitis 91.89%, and Hepatocellular 92.97% which is greater than just using a Deep Neural Network.