Article Per Year (5 Year)
p-Index From 2021 - 2026
1.497
P-Index
This Author published in this journals
All Journal Reformasi : Jurnal Ilmiah Ilmu Sosial dan Ilmu Politik Buletin Ilmiah Sarjana Teknik Elektro Community Development Journal: Jurnal Pengabdian Masyarakat Indonesian Journal of Data and Science Journal of Community Service and Empowerment International Journal of Engineering, Science and Information Technology Jurnal Pembelajaran, Bimbingan, dan Pengelolaan Pendidikan Advance Sustainable Science, Engineering and Technology (ASSET)
Hariyono Hariyono
Universitas Negeri Malang
Humanities Astronomy Biochemistry, Genetics & Molecular Biology Chemical Engineering, Chemistry & Bioengineering Chemistry Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Earth & Planetary Sciences Economics, Econometrics & Finance Education Electrical & Electronics Engineering Energy Engineering Health Professions Industrial & Manufacturing Engineering Law, Crime, Criminology & Criminal Justice Library & Information Science Materials Science & Nanotechnology Mathematics Mechanical Engineering Physics Public Health Social Sciences Transportation Other

Published : 9 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 9 Documents
Search

 1 
Comparative Performance of Transformer Models for Cultural Heritage in NLP Tasks Tri Lathif Mardi Suryanto; Aji Prasetya Wibawa; Hariyono Hariyono; Andrew Nafalski
Advance Sustainable Science Engineering and Technology Vol. 7 No. 1 (2025): November-January
Publisher : Science and Technology Research Centre Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/asset.v7i1.1211

Abstract

AI and Machine Learning are crucial in advancing technology, especially for processing large, complex datasets. The transformer model, a primary approach in natural language processing (NLP), enables applications like translation, text summarization, and question-answer (QA) systems. This study compares two popular transformer models, FlanT5 and mT5, which are widely used yet often struggle to capture the specific context of the reference text. Using a unique Goddess Durga QA dataset with specialized cultural knowledge about Indonesia, this research tests how effectively each model can handle culturally specific QA tasks. The study involved data preparation, initial model training, ROUGE metric evaluation (ROUGE-1, ROUGE-2, ROUGE-L, and ROUGE-Lsum), and result analysis. Findings show that FlanT5 outperforms mT5 on multiple metrics, making it better at preserving cultural context. These results are impactful for NLP applications that rely on cultural insight, such as cultural preservation QA systems and context-based educational platforms.
The effect of teacher empowerment-based course program on teachers' knowledge of Pancasila character on the Indonesia-Malaysia literacy Daya Negri Wijaya; Evania Yafie; H. Hariyono; Andhika Yudha Pratama; Alfi Rohmatul Azizah; Suti Mega Nur Azizah
Journal of Community Service and Empowerment Vol. 5 No. 1 (2024): April
Publisher : Universitas Muhammadiyah Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22219/jcse.v5i1.29683

Abstract

The lack of teachers' ability to apply the Pancasila character can contribute to the fading of Pancasila culture abroad, especially for the families of Indonesian Immigrant Workers in Malaysia. This research aims to explore the understanding of the character of Pancasila among parents in the Indonesian-Malaysian literacy context. A quantitative research approach was used with a sample of 80 educators from the Kuala Lumpur Indonesian School and learning centers in Malaysia. The research instrument consists of a questionnaire with 15 items for the Teacher Empowerment Program variable and 14 items for Teacher Knowledge. Data analysis uses simple linear regression with validity, reliability, normality, heteroscedasticity, t test, and coefficient tests, which are processed using SPSS software. The research results found that the training program had a positive effect on teachers' knowledge about the character of Pancasila. The Teacher Empowerment Based Course Program has had a significant impact on teachers' understanding of the Indonesian-Malaysian Literacy Based Pancasila Character. After attending a course based on teacher empowerment, there was a significant increase in teachers' knowledge about the character of Pancasila based on Indonesian-Malaysian language literacy. This teacher empowerment-based course program provides educators with the opportunity to gain knowledge about Indonesian-Malaysian literacy. They can apply this knowledge through innovative and effective teaching methods. Future research could investigate further potential benefits beyond increasing teachers' knowledge after participating in this program.
Comparative Analysis of Speech-to-Text APIs for Supporting Communication of the Deaf Community Anik Nur Handayani; Hariyono Hariyono; Ahmad Munjin Nasih; Rochmawati Rochmawati; Imanuel Hitipeuw; Harits Ar Rosyid; Jevri Tri Ardiansah; Rafli Indar Praja; Ahmad Nurdiansyah; Desi Fatkhi Azizah
Indonesian Journal of Data and Science Vol. 6 No. 3 (2025): Indonesian Journal of Data and Science
Publisher : Yocto Brain

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.56705/ijodas.v6i3.327

Abstract

Hearing impairment can have a profound impact on the mental and emotional state of sufferers, as well as hinder communication and delay in accessing information directly that relies on interpreters. Advances in assistive technology, especially speech recognition systems that are able to convert spoken language into written text (speech-to-text). However, its implementation faces various challenges related to the level of accuracy of each speech-to-text Application Programming Interface (API), thus requiring an appropriate deep learning model. This study serves to analyze and compare the performance of speech-to-text API services (Deepgram API, Google API and Whisper AI) based on Word Error Rate (WER) and Words Per Minute (WPM), to determine the most optimal API in a web-based real-time transcription system using the JavaScript programming language and Glitch.com. The three API services were tested by calculating their error rates and transcription speeds, then evaluated to see how low the error accuracy rate was and how high the transcription speed was. On average, Whisper AI had a WER of 0% across all word categories, but its speed was lower than the other two APIs. Deepgram API displayed the best balance between accuracy and speed, with an average WER of 13.78% and 67 WPM. Google API performed stably, but its WER value was slightly higher than Deepgram API. In conclusion, based on the results, Deepgram API was deemed the most optimal for live transcription, as it is capable of producing fast and error-free transcriptions, significantly increasing the accessibility of information for the deaf community.
PELATIHAN ORGANIZATION MANAGEMENT BASED COMMUNITY (OMC) SENI UNTUK MENINGKATKAN ORGANIZATIONAL CAPABILITIES PADA PEMILIK UMKM Hariyono Hariyono; Evania Yafie; Daya Negri Wijaya; Primasa Minerva Nagari; Aimi Musa
Community Development Journal : Jurnal Pengabdian Masyarakat Vol. 6 No. 1 (2025): Volume 6 No. 1 Tahun 2025
Publisher : Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/cdj.v6i1.41192

Abstract

Penelitian ini bertujuan untuk meningkatkan organizational capabilities ada pemilik UMKM di Klampok Kasri melalui pelatihan Organization Management Based Community (OMC).   Metode penelitian Penelitian ini menggunakan pendekatan kuantitatif dengan eksperimen yaitu quasi eksperimen. Quasi eksperimen dipilih karena penelitian ini dilkukan tanpa pengacakan (random), namun melibatkan penembatan partisipan kedalam kelompok atau penelitian ini dilakukan dengan memberikan treatment pada kelompok yang diteliti dalam penelitian ini. Treatmen dilakukan dengan mengobservasi hasil pelatihan OMC terhadap masyarakat terutama UMKM di Klampok Kasri Jaman Biyen. Hasil penelitian bahwa kegiatan pelatihan Organization Management Based Community (OMC) terbukti efektif dalam meningkatkan kapabilitas organisasi UMKM. Melalui pelatihan OMC, UMKM di Klampok Kasri mendapatkan peningkatan keterampilan manajerial dan operasional, memperkuat kolaborasi antar anggota komunitas, dan mendorong inovasi. Dampak positif tersebut dirasakan baik pada tingkat individu maupun secara kolektif, meningkatkan efisiensi, produktivitas, dan daya saing, serta kontribusi pada pertumbuhan ekonomi lokal.
Transformer-Based Semantic Retrieval for Cultural Heritage Question Answering Tri Lathif Mardi Suryanto; Aji Prasetya Wibawa; Hariyono Hariyono; Andrew Nafalski
Buletin Ilmiah Sarjana Teknik Elektro Vol. 8 No. 3 (2026): June
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/biste.v8i3.15775

Abstract

Cultural heritage knowledge presents significant challenges for Question Answering (QA) systems due to their interpretive, context-dependent, and symbolically rich nature. While Transformer-based models have achieved strong performance in semantic representation, they remain prone to hallucination and contextual misalignment, particularly in culturally sensitive domains. This study proposes a Transformer-based cultural knowledge retrieval framework for domain-specific chatbots, combining a bi-encoder (MiniLM and MPNet) for efficient semantic retrieval and a cross-encoder (BERT-base) for fine-grained reranking. A curated dataset of 4,016 question–answer pairs in Indonesia is developed from cultural heritage sources and validated for contextual consistency. The proposed approach is evaluated using both quantitative and qualitative metrics, including accuracy, F1-score, Exact Match (EM), and semantic-based measures such as F1-BLEU, F1-EDIT, and F1-ANS. Experimental results show that while all models achieve high classification performance (accuracy up to 0.99), the BERT + MPNet configuration significantly outperforms others in answer quality metrics, indicating superior semantic fidelity. However, qualitative analysis reveals persistent issues of hallucination and contextual misalignment, highlighting the limitations of relying solely on statistical evaluation. These findings demonstrate that high numerical performance does not guarantee meaningful understanding in cultural domains. Therefore, this study emphasizes the need for hybrid evaluation frameworks and context-aware mechanisms to ensure epistemic fidelity. The proposed approach contributes to the development of more reliable and culturally grounded QA systems.
Contextual Relevance-Driven Question Answering Generation: Experimental Insights Using Transformer-Based Models Tri Lathif Mardi Suryanto; Aji Prasetya Wibawa; Hariyono Hariyono; Hechmi Shili
International Journal of Engineering, Science and Information Technology Vol 5, No 4 (2025)
Publisher : Malikussaleh University, Aceh, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52088/ijesty.v5i4.989

Abstract

This study investigates the impact of contextual relevance and hyperparameter tuning on the performance of Transformer-based models in Question-Answer Generation (QAG). Utilising the FlanT5 model, experiments were conducted on a domain-specific dataset to assess how variations in learning rate and training epochs affect model accuracy and generalisation. Six QAG models were developed (QAG-A to QAG-F), each evaluated using ROUGE metrics to measure the quality of generated question-answer pairs. Results show that QAG-F and QAG-D achieved the highest performance, with QAG-F reaching a ROUGE-LSum of 0.4985. The findings highlight that careful tuning of learning rates and training duration significantly improves model performance, enabling more accurate and contextually appropriate question generation. Furthermore, the ability to generate both questions and answers from a single input enhances the interactivity and utility of NLP systems, particularly in knowledge-intensive domains. This study underscores the importance of contextual modelling and hyperparameter optimisation in generative NLP tasks, offering practical insights for improving chatbot development, educational tools, and digital heritage applications.
Signifikansi Peristiwa Malari 74: Mahasiswa dalam Lanskap Politik Indonesia Donny Maulana; Hariyono Hariyono; Indah Wahyu Puji Utami; Aditya Nugraha Widiadi; Arif Subekti
REFORMASI Vol 16, No 1 (2026)
Publisher : Universitas Tribhuwana Tunggadewi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33366/rfr.v16i1.7529

Abstract

The New Order's economic policy, which relied on foreign investment (PMA) and foreign debt (IGGI), paradoxically engendered dependency, sharp socio-economic inequality, and the marginalization of domestic enterprises, despite its success in curbing inflation. This research aims to analyze the historical significance of the 1974 Malari Incident as the culmination of public unrest spearheaded by students. Employing Kuntowijoyo's historical research method, this study examines primary sources, such as archives and contemporary news reports, as well as secondary literature. The findings reveal how discontent over the impacts of development was successfully consolidated by figures like Hariman Siregar, transforming sporadic actions into a solid mass movement. This movement raised the central issues of the dominance of foreign capital, particularly from Japan, and the controversial role of the presidential Personal Assistants (Aspri). In conclusion, the fundamental significance of the Malari Incident transcends that of a momentary political protest. The event reaffirms the historical thesis that national consciousness and responsibility are a calling for every intellectual, regardless of their academic discipline a principle reflected by medical and engineering students during the national movement era. They are called to "diagnose" and "treat" societal ills, such as injustice, thereby proving the essential role of students as a moral and intellectual force within Indonesia's political landscape.Kebijakan ekonomi Orde Baru yang bertumpu pada modal asing (PMA) dan utang luar negeri (IGGI), meski berhasil menekan inflasi, secara paradoksal justru melahirkan ketergantungan, ketimpangan sosial-ekonomi tajam, dan marginalisasi usaha domestik. Penelitian ini bertujuan menganalisis signifikansi historis Peristiwa Malari 1974 sebagai puncak artikulasi keresahan publik yang dimotori oleh mahasiswa. Dengan menggunakan metode penelitian sejarah Kuntowijoyo, kajian ini mengkaji sumber primer berupa arsip dan berita sezaman serta literatur sekunder. Hasil penelitian menunjukkan bagaimana kekecewaan atas dampak pembangunan berhasil dikonsolidasikan oleh figur seperti Hariman Siregar dari berbagai aksi sporadis menjadi gerakan massa yang solid. Gerakan ini mengangkat isu sentral tentang dominasi modal asing, khususnya Jepang, dan peran kontroversial Asisten Pribadi (Aspri) presiden. Simpulannya, signifikansi fundamental Malari melampaui gugatan politik sesaat. Peristiwa ini menegaskan kembali tesis historis bahwa kesadaran dan tanggung jawab kebangsaan adalah panggilan bagi setiap kaum terpelajar, tanpa tersekat disiplin ilmu—sebagaimana tercermin pada para mahasiswa kedokteran dan teknik di era pergerakan nasional. Mereka terpanggil untuk "mendiagnosis" dan "mengobati" penyakit masyarakat seperti ketidakadilan, membuktikan peran esensial mahasiswa sebagai kekuatan moral dan intelektual dalam lanskap politik Indonesia. 
Comparative Performance of Transformer Models for Cultural Heritage in NLP Tasks Tri Lathif Mardi Suryanto; Aji Prasetya Wibawa; Hariyono Hariyono; Andrew Nafalski
Advance Sustainable Science Engineering and Technology Vol. 7 No. 1 (2025): November-January
Publisher : Science and Technology Research Centre Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/asset.v7i1.1211

Abstract

AI and Machine Learning are crucial in advancing technology, especially for processing large, complex datasets. The transformer model, a primary approach in natural language processing (NLP), enables applications like translation, text summarization, and question-answer (QA) systems. This study compares two popular transformer models, FlanT5 and mT5, which are widely used yet often struggle to capture the specific context of the reference text. Using a unique Goddess Durga QA dataset with specialized cultural knowledge about Indonesia, this research tests how effectively each model can handle culturally specific QA tasks. The study involved data preparation, initial model training, ROUGE metric evaluation (ROUGE-1, ROUGE-2, ROUGE-L, and ROUGE-Lsum), and result analysis. Findings show that FlanT5 outperforms mT5 on multiple metrics, making it better at preserving cultural context. These results are impactful for NLP applications that rely on cultural insight, such as cultural preservation QA systems and context-based educational platforms.
Enhancing Academic Publication Performance at Higher Education Eko Pramudya Laksana; Betty Masruroh; Hariyono Hariyono; Aji Prasetya Wibawa; Lisa Ramadhani Harianti; Roni Herdianto; Bayu Koen Anggoro; Vira Setia Ningrum; Prananda Anugrah; Ghada Abd Elsattar Mohammed Oraby; Eko Pramudya Laksana; Betty Masruroh; Hariyono Hariyono; Aji Prasetya Wibawa; Lisa Ramadhani Harianti; Roni Herdianto; Bayu Koen Anggoro; Vira Setia Ningrum; Prananda Anugrah; Ghada Abd Elsattar Mohammed Oraby
Jurnal Pembelajaran, Bimbingan, dan Pengelolaan Pendidikan Vol. 6 No. 2 (2026)
Publisher : Universitas Negeri Malang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17977/um065.v6.i2.2026.1

Abstract

The academic publication serves as one of the central criteria in higher education ranking. Consequently, each university formulate a particular strategy for improving its academic publication, such as through the mapping and prediction of academic publication. This study aims to outline and foresee the growth of academic publications of Universitas Negeri Malang (UM), Indonesia. The retrospective analysis using the bibliometric method and time series analysis using Exponential Triple Smoothing was carried out in establishing the strategy for university ranking. The dataset was obtained from the Scopus database and Sinta database from the Ministry of Education and Culture from 2018-2022. The result of forecasting suggested a possible increase in publication from Universitas Negeri Malang on Scopus between 2023-2027. Meanwhile, the publication in Sinta database is predicted to be relatively stagnant. Consequently, six publication strategies have been formulated to enhance the academic publication of Universitas Negeri Malang.
Co-Authors Adi Gunawan Aditya Nugraha Widiadi Ahmad Munjin Nasih Ahmad Nurdiansyah Aimi Musa Aji Prasetya Wibawa Alfi Rohmatul Azizah Andhika Yudha Pratama Andrew Nafalski Anik Nur Handayani Ari Sapto Bayu Koen Anggoro Betty Masruroh Daya Negri Wijaya Desi Fatkhi Azizah Dian Fitri Nur Aini Dina Fitrohtur Rohmah Donny Maulana Eko Pramudya Laksana Eko Pramudya Laksana Emirta Z.A.S. Hanapi Ery Tri Djatmika RWW Evania Yafie Fathia Irani Ghada Abd Elsattar Mohammed Oraby Ghada Abd Elsattar Mohammed Oraby Hanurawan, Fattah Harits Ar Rosyid Hariyono Hariyono Hechmi SHILI Imanuel Hitipeuw Indah Wahyu Puji Utami, Indah Wahyu Jevri Tri Ardiansah Jihan Filisyamala Lisa Ramadhani Harianti Lisa Ramadhani Harianti M. Ramli Mega Lovrina Nur Laila Prananda Anugrah Prananda Anugrah Primasa Minerva Nagari Rafli Indar Praja Rina Diahwati Rochmawati Rochmawati Roni Herdianto Siti Malikah Towaf Subekti, Arif Sudarmiatin Sugeng Utaya Sumarmi Suti Mega Nur Azizah Tri Lathif Mardi Suryanto Vira Setia Ningrum Vira Setia Ningrum Wahyu Purwanto Wawan Suprianto Nadra Wina Nurfitriani Yasintus Tinja