Garuda - Garba Rujukan Digital

Peningkatan Kemampuan Editing Video untuk Promosi Produk UMKM Bagi Gks Kecamatan Tembalang Semarang Rastri Prathivi; Febrian Wahyu Christanto; Victor Gayuh Utomo
Jurnal Pengabdian Mitra Masyarakat (JPMM) Vol 2, No 2: Oktober (2020)
Publisher : Universitas Amikom Purwokerto

UMKM Kecamatan Tembalang Semarang ini merupakan salah satu organisasi para pelaku UMKM yang berada di Kecamatan Tembalang Kota Semarang. UMKM ini memproduksi dan memasarkan barang dalam bentuk yang beragam. Di dalam usahanya untuk mempromosikan barang-barang produk UMKM tersebut para pelaku UMKM memiliki kendala yaitu keterbatasan kemampuan mereka di dalam membuat media promosi yang kreatif, menarik dan tepat sasaran bagi konsumen. Mereka belum memiliki kemampuan yang cukup untuk memanfaatkan beragam media digital salah satunya video digital. Promosi melalui video merupakan cara yang paling strategis sehingga konsumen dapat melihat sekaligus menikmati produk ( secara virtual dalam imajinasi) atau jasa yang dijual oleh pelaku UMKM. Hal terpenting yang perlu ditingkatkan di dalam pembuatan video adalah bagaimana melakukan editing video promosi yang akan meninggalkan brand image atau persepsi bagi para konsumen yang melihat video promosi tersebut. Metode yang digunakan dalam PKM ini dalam bentuk seminar atau ceramah. Untuk tempat pengabdian masyarakat ini berada pada Laboratorium Komputer M2.1 FTIK USM yang berlangsung pada hari Kamis, 23 Juli 2020 dengan peserta sebanyak 10 orang. PkM ini berlangsung selama 3 jam dari pukul 10.00 – 13.00 Hasil yang dicapai dari kegiatan PKM ini adalah peningkatan kemampuan para pelaku UMKM GKS Kecamatan Tembalang Semarang untuk mengedit video promosi menggunakan software Filmora.

Pemanfaatan Data Mining untuk Media Pembelajaran di SMK Hidayah Semarang Astrid Novita Putri; Nur Wakhidah; Victor Gayuh Utomo
E-Dimas: Jurnal Pengabdian kepada Masyarakat Vol 13, No 3 (2022): E-DIMAS
Publisher : Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/e-dimas.v13i3.5572

Salah satu permasalahan dari wawancara yang kami laksanakan adalah dalam kegiatan pembelajaran pada pengolahan data yang dialami oleh pihak SMK Hidayah Semarang, hal ini disebabkan oleh belum adanya mata pelajaran data mining, sehingga siswa kesulitan dalam mengolah data yang miliki oleh sekolah. Dalam kegiatan pengabdian kepada masyarakat ini dapat mampu memberikan manfaat, tepat sasaran sehingga memberikan suatu wawasan baru pengetahuan baru di bidang teknologi informas pada sekolah tersebut. Konsep pengabdian akan menerapkan suatu teknologi data mining, dengan menggunakan software Rapidminer yang akan kita laksanakan adalah dalam berbentuk pelatihan pemanfaatan data mining yang menghasilkan informasi pengolahan pola data di SMK Hidayah Semarang. Kegiatan pelatihan ini dilaksanakan ditunjang dengan sesi tanya jawab, ceramah di Modul pelatihan ini juga akan diberikan pada setiap peserta murid. Tujuan dari pelaksanaan pengabdian kepada masyarakat ini adalah meningkatkan pembelajaran siswa dengan pengolahan database menggunakan teknik statistik, matematika, kecerdasan buatan, dan machine learning untuk menghasilkan suatu informasi yang bermanfaat dengan menggunakan aplikasi Rapidminer, sehingga nantinya ketika mereka terjun ke dalam masyarakat dapat memiliki skill yang didapatkan dari pelatihan tersebut.

Anti-Corruption Disclosure Prediction Using Deep Learning Victor Gayuh Utomo; Tirta Yurista Kumkamdhani; Galih Setiarso
JOIN (Jurnal Online Informatika) Vol 7 No 2 (2022)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v7i2.840

Corruption gives major problem to many countries. It gives negative impact to a nation economy. People also realized that corruption comes from two sides, demand from the authority and supply from corporate. On that regard, corporates may have their part in fight against corruption in the form of anti- corruption disclosure (ACD). This study proposes new method of ACD prediction in corporate using deep learning. The data in this study are taken from every companies listed in Indonesia Stock Exchange (IDX) from the year 2017 to 2019. The companies can be categorized in 9 categories and the data set has 8 features. The overall data has 1826 items in which 1032 items are ACD and the other 794 items are non-ACD. In this study, the deep neural network or deep learning is composed from input layer, output layer and 3 hidden layers. The deep neural network uses Adam optimizer with learning rate 0.0010, batch size 16 and epochs 500. The drop out is set to 0.05. The accuracy result from deep learning in predicting ACD is considered good with the average training accuracy is 74.76% and average testing accuracy is 76.37%. However, the loss result isnâ€™t good with average training loss and testing loss are respectively 51.76% and 50.96%. Since the aim of the study to find the possibility of deep learning as alternative of logistic regression in ACD prediction, accuracy comparison from deep learning and logistic regression is held. Deep learning has average prediction accuracy of 76.37% is better than logistic regression with average accuracy of 67.15%. Deep learning also has higher minimum accuracy and maximum accuracy compared to logistic regression. This study concludes that deep learning may give alternatives in ACD prediction compared the more common method of logistic regression.

PENERAPAN RESPONSIVE WEB DESIGN DALAM PERANCANGAN SISTEM MODUL ONLINE ADAPTIF Arief Hidayat; Victor Gayuh Utomo; Henry Anggoro Djohan
Jurnal Sistem Informasi Vol. 12 No. 1 (2016): Jurnal Sistem Informasi (Journal of Information System)
Publisher : Faculty of Computer Science Universitas Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21609/jsi.v12i1.435

Dewasa ini akses sebuah aplikasi web dapat melalui smartphone maupun tablet, sehingga terdapat tuntutan aplikasi web yang biasanya diakses melalui komputer, tetap responsif terhadap ukuran layar smartphone maupun tablet. Teknik tersebut dinamakan responsive web design, sebuah teknik yang digunakan desainer website untuk memberikan pengalaman visual yang elegan tanpa mempedulikan ukuran browser yang digunakan dan batasan apapun tentang cara mengakses perangkat tersebut. Berbagai sistem berbasis web lambat laun mulai menerapkan responsive web design termasuk sistem pembelajaran. Sebuah sistem pembelajaran rata-rata didesain sama untuk semua siswa yang mengikutinya. Hal ini tentu saja oleh siswa dirasa tidak cukup untuk memahami materi yang tersedia di sistem pembelajaran, mengingat gaya belajar setiap siswa berlainan. Sistem modul online adaptif diharapkan mampu menyediakan sumber pembelajaran yang disesuaikan dengan gaya belajar siswa. Sistem tersebut juga mampu mengakomodir lingkungan pembelajaran sesuai dengan gaya belajar siswa. Hasil dari penelitian ini yaitu sebuah sistem modul online adaptif yang dapat mengakomodir pembelajaran sesuai dengan gaya belajar siswa dan dapat diakses dimanapun, kapanpun, dan menggunakan perangkat genggam apapun sehingga diharapkan dapat memberikan kontribusi pada bidang pendidikan sekaligus personalisasi gaya belajar siswa.

Fine-Grained Analysis of Coral Instance Segmentation using YOLOv8 Models Hassanudin, Wahyu Maulana; Utomo, Victor Gayuh; Apriyanto, Riski
Sinkron : jurnal dan penelitian teknik informatika Vol. 8 No. 2 (2024): Article Research Volume 8 Issue 2, April 2024
Publisher : Politeknik Ganesha Medan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33395/sinkron.v8i2.13583

Within the geographical boundaries of Indonesia, coral reefs flourish as intricate ecosystems bustling with a variety of marine creatures that play a crucial role, in preserving biodiversity. However this delicate harmony faces threats from climate change and human activities, leading to the risk of species loss. Despite growing awareness surrounding these challenges effectively and swiftly monitoring conditions remains a task. Existing methods for assessing corals often fall short due to requiring extensive specialist knowledge, lacking large-scale coverage, and being costly to implement. To tackle these obstacles this research suggests an approach for automated reef monitoring using instance segmentation with a YOLOv8 model. Leveraging YOLOv8 segmentation capabilities enables efficient analysis of corals. A systematic process is employed involving data collection, preparation (including techniques like Histogram Equalization), training the model on a reef dataset, model evaluation and enhancing the segmentation mask. The outcomes reveal the YOLOv8m Pp model with 96.7% precision 95.9% recall rate and a mean Average Precision (mAP50) score of 98.2%. This study demonstrates the potential of YOLOv8 to accurately segment instances for monitoring reefs in Indonesia, hence facilitating improved conservation strategies.

Pengembangan E-Modul Berbantuan Flipbook Berbasis Literasi Untuk Mata Kuliah Statistika Kusumaningrum, Yulinda; Utomo, Victor Gayuh; Ellyawati, Hetty Catur; Maulana, Charis
Jurnal Transformatika Vol. 22 No. 1 (2024): July 2024
Publisher : Jurusan Teknologi Informasi Universitas Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26623/transformatika.v22i1.10233

Statistics is the basis for studying other subjects in the Informatics Engineering Study Program. However, some lecturers have not used teaching materials such as interactive modules to help students learn statistics. For this reason, research is needed which aims to (1) develop literacy-based Flipbook-assisted interactive e-modules in statistics courses that are valid, (2) determine the practicality of literacy-based Flipbook-assisted interactive e-modules in statistics courses for students. This type of research is Research and Development (R&D). The research subjects were 30 Informatics Engineering students taking Statistics courses. The development steps in this research are using ADDIE, namely Analysis, Design, Development, Implementation, and Evaluation. The research results obtained: 1) the literacy-based flipbook-assisted e-module that was developed was declared valid/feasible with an average percentage of material experts of 80% and media experts of 85.41%, 2) the flipbook-assisted interactive e-module that was developed met the criteria practically with a percentage reaching 75%.

Anti-Corruption Disclosure Prediction Using Deep Learning Utomo, Victor Gayuh; Kumkamdhani, Tirta Yurista; Setiarso, Galih
JOIN (Jurnal Online Informatika) Vol 7 No 2 (2022)
Publisher : Department of Informatics, UIN Sunan Gunung Djati Bandung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.15575/join.v7i2.840

Corruption gives major problem to many countries. It gives negative impact to a nation economy. People also realized that corruption comes from two sides, demand from the authority and supply from corporate. On that regard, corporates may have their part in fight against corruption in the form of anti- corruption disclosure (ACD). This study proposes new method of ACD prediction in corporate using deep learning. The data in this study are taken from every companies listed in Indonesia Stock Exchange (IDX) from the year 2017 to 2019. The companies can be categorized in 9 categories and the data set has 8 features. The overall data has 1826 items in which 1032 items are ACD and the other 794 items are non-ACD. In this study, the deep neural network or deep learning is composed from input layer, output layer and 3 hidden layers. The deep neural network uses Adam optimizer with learning rate 0.0010, batch size 16 and epochs 500. The drop out is set to 0.05. The accuracy result from deep learning in predicting ACD is considered good with the average training accuracy is 74.76% and average testing accuracy is 76.37%. However, the loss result isnâ€™t good with average training loss and testing loss are respectively 51.76% and 50.96%. Since the aim of the study to find the possibility of deep learning as alternative of logistic regression in ACD prediction, accuracy comparison from deep learning and logistic regression is held. Deep learning has average prediction accuracy of 76.37% is better than logistic regression with average accuracy of 67.15%. Deep learning also has higher minimum accuracy and maximum accuracy compared to logistic regression. This study concludes that deep learning may give alternatives in ACD prediction compared the more common method of logistic regression.

Upaya Peningkatan Kemampuan Siswa SMK Negeri 3 Kendal Melalui Pelatihan Artificial Intelligence Utomo, Victor Gayuh; Ardima, Muhammad Basyier; Pungkasanti, Prind Triajeng
Bahasa Indonesia Vol 21 No 02 (2024): Sarwahita : Jurnal Pengabdian Kepada Masyarakat
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21009/sarwahita.212.6

The students of SMK Negeri 3 Kendal, especially the Software and Game Development (PPLG) competency, has not received knowledge related to artificial intelligence which is starting to be widely used in the world of work. The school wanted the student to have knowledge in artificial intelligence. The reason is that artificial intelligence has begun to be widely used in the world of work. To satisfiy the need, this community service proposed to increase the ability of students at SMK Negeri 3. In this community service, the discussed artificial intelligence would be centered on the Large Language Model (LLM). The community service was carried out using the method of raising awareness/increasing understanding of artificial intelligence issues. The training/increasing understanding activity itself is carried out in 4 stages, namely pre-test, presentation, practice and post-test. From the results of the presentation of presentation and practice, several weaknesses emerged. This is related to understanding how artificial intelligence works, the application of artificial intelligence and how to recognize artificial intelligence results. This community service activity conveys correct information regarding these matters. By comparing pre-test and post-test results, which has 8 questions, there is an increase of their knowledge with an average of 25%. The greatest increase in understanding occurred in the question ‘Does AI really understand what it is doing?’ which relates to understanding how artificial intelligence works. The increase in understanding on this question occurred by 50%. Abstrak Dalam kegiatannya, SMK Negeri 3 Kendal, utamanya kompetensi Pengembangan Perangkat Lunak dan Gim (PPLG), belum mendapat pengetahuan terkait kecerdasan buatan yang mulai banyak digunakan dalam dunia kerja. Pihak sekolah memiliki keinginan agar par siswa dapat memiliki pengentahuan terkait kecerdasan buatan. Hal ini karena kecerdasan buatan sudah mulai banyak dimanfaatkan dalam dunia kerja. Pengabdian masyarakat ini mengusulkan peningkatan kemampuan para siswa SMK Negeri 3 Kendal untuk menjawab masalah yang telah dipaparkan. Secara khusus, pada pengabdian masyarakat ini, pengenalan kecerdasan buatan yang dimaksud akan berpusat pada bentuk Large Language Model (LLM). Kegiatan pengabdian kepada masyarakat kali ini dilakukan dengan metode penyadaran/peningkatan pemahaman terhadap masalah kecerdasan buatan. Kegiatan pelatihan/peningkatan pemahaman sendiri dilakukan dalam 4 tahap, yaitu pre-test, pemaparan/penyuluhan, praktek dan post-test. Dari hasil pemaparan materi dan praktek didapatkan bahwa terdapat beberapa kelemahan yang mengemuka. Hal ini terkait pemahaman cara kerja kecerdasan buatan, terapan kecerdasan buatan dan cara mengenali hasil kecerdasan buatan. Kegiatan pengabdian kepada masyarakat ini menyampaikan informasi yang benar terkait hal-hal tersebut. Hasil dari pre-test dan post-test yang mencakup 8 poin, menunjukkan terdapat peningkatan pemahaman dari peserta dengan rata-rata sebesar 25%. Peningkatan pemahaman terbesar terjadi pada pertanyaan tentang kebenaran bahwa AI memahami apa yang dilakukannya yang terkait pemahaman cara kerja kecerdasan buatan. Peningkatan pemahaman pada pertanyaan ini terjadi sebesar 50%.

Usability Test of Mental Health Application MoodPath with Software Usability Measurement Inventory Utomo, Victor Gayuh; Widhiastuti, Hardani; Heryanti, Rini; Susilo, Markus Nanang I. B.
Jurnal Transformatika Vol. 23 No. 1 (2025): July 2025
Publisher : Jurusan Teknologi Informasi Universitas Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26623/transformatika.v23i2.12041

MoodPath is a mobile application for mental health. The application uses Patient Health Questionnaire 9 (PHQ-9) and General Anxiety Disorder 7 (GAD-7) to assess mental health of its users. The study held usability test using Software Usability Measurement Inventory (SUMI) questionnaire with 27 respondents. MoodPath application got usability value of 46.26 that is Below Average in Global SUMI scales. The value is also related with every individual scale in SUMI. The Efficient, Affect, Helpfulness and Control scales have Below Average value. Only the Learnability scale has Above Average value. The usability result is reached with 95% Confidence Interval. Based on the IT skill, respondents with better IT skill gave lower usability score compared to respondent with lesser IT skill. The research also found that familiar UI and standard questionnaire (PHQ-9 and GAD-7) gave positive usability in Learnability and Efficiency scale. The research found that MoodPath application need to consider wider range of users by giving feature that not only satisfied people with lesser IT skill but also people with better IT skill. Based on the usability test, the MoodPath application may improve the usability by providing ‘Remember Me’ and result saving features.

Benchmarking IndoBERT and Transformer Models for Sentiment Classification on Indonesian E-Government Service Reviews Dhendra; Gayuh Utomo, Victor
Jurnal Transformatika Vol. 23 No. 1 (2025): July 2025
Publisher : Jurusan Teknologi Informasi Universitas Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26623/transformatika.v23i1.12095

The rapid adoption of e-government services in Indonesia has increased the importance of understanding public sentiment toward digital platforms. This study presents a comparative analysis of five models—IndoBERT, mBERT, XLM-R, CNN, and BiLSTM—for sentiment classification on user reviews of NEWSAKPOLE, a public service application for vehicle tax and licensing. A custom dataset of 11,000+ reviews was scraped from the Google Play Store and labeled using a hybrid rating-based and manual validation approach. Each model was evaluated using accuracy, precision, recall, and F1-score. IndoBERT achieved the highest performance with an F1-score of 0.882, outperforming multilingual and classical deep learning models. Confusion matrix analysis showed that transformer-based models were more effective in detecting neutral and mixed sentiments, while CNN and BiLSTM struggled with misclassification. The results highlight IndoBERT's robustness in low-resource sentiment analysis and its potential to enhance public service monitoring and policy feedback mechanisms in Indonesian digital governance.

Title

Found 30 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 30 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 30 Documents
Search