Claim Missing Document
Check
Articles

Found 17 Documents
Search

Pengembangan model akustik dengan deep neural network untuk sistem pengenalan wicara bahasa Indonesia Gunarso, Gunarso; Buono, Agus; Mushthofa, Mushthofa; Uliniansyah, Mohammad Teduh
AITI Vol 22 No 1 (2025)
Publisher : Fakultas Teknologi Informasi Universitas Kristen Satya Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24246/aiti.v22i1.84-100

Abstract

The Deep Neural Network (DNN)-based approach offers significantly higher accuracy compared to traditional methods such as Hidden Markov Model (HMM)-Gaussian Mixture Model (GMM) in acoustic model development. In this research, three popular DNN variants were evaluated: Time-Delay Neural Network (TDNN), Long Short-Term Memory (LSTM), and a hybrid combination of TDNN-LSTM for acoustic model development in Indonesian speech recognition. Using the KDW-BPPT-50K-ASR1 speech data for over 92 hours, acoustic models were trained, and experiments were conducted to analyze their performance. Research results show that the hybrid TDNN-LSTM model achieved the best performance with a Word Error Rate (WER) of 9.67%, outperforming TDNN with a WER of 12.16% and LSTM with a WER of 10.6%. This finding confirms that the hybrid model is able to improve the accuracy of Indonesian speech recognition compared to using TDNN or LSTM separately. These results provide a significant contribution to the development of more accurate and efficient speech recognition systems.
Modeling sentiment analysis of Indonesian biodiversity policy Tweets using IndoBERTweet Uliniansyah, Mohammad Teduh; Jarin, Asril; Santosa, Agung; Gunarso, Gunarso
IAES International Journal of Artificial Intelligence (IJ-AI) Vol 14, No 3: June 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijai.v14.i3.pp2389-2401

Abstract

This study develops and evaluates a sentiment analysis model using IndoBERTweet to analyze Twitter data on Indonesia’s biodiversity policy. Twitter data focusing on topics such as food security, health, and environmental management were collected, with a representative subset of 13,435 tweets annotated from a larger dataset of 500,000 to ensure reliable sentiment labels through majority voting. IndoBERTweet was compared to seven traditional machine-learning classifiers using TF-IDF and BERT embeddings for feature extraction. Model performance was assessed using mean accuracy, mean F1 score, and statistical significance (p-values). Additionally, sentiment analysis included word attribution techniques with BERT embeddings, enhancing relevance, interpretability, and consistent attribution to deliver accurate insights. IndoBERTweet models consistently outperformed traditional methods in both accuracy and F1 score. While BERT embeddings boosted performance for conventional models, IndoBERTweet delivered superior results, with p-values below 0.05 confirming statistical significance. This approach demonstrates that the model’s outputs are explainable and align with human understanding. Findings underscore IndoBERTweet’s substantial impact on advancing sentiment analysis technology, showcasing its potential to drive innovation and elevate practices in the field.
Design of Concrete Sheet Pile Revetment As A River Protector And Recreation Facilities Arbianto, Reki; Gunarso, Gunarso; Sungkono, Kukuh Kurniawan Dwi
International Journal of Sustainable Building, Infrastructure and Environment (IJOSBIE) Vol 1, No 2 (2020)
Publisher : Science and Technology Research Centre, Universitas PGRI Semarang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26877/ijosbie.v1i2.8218

Abstract

Revetment is a strengthening structure on river slopes from erosion. Erosion of river slopes can widen the wet cross section of the river and increasing scouring can endanger the surrounding buildings. The construction of the Demangan Water Gate in Surakarta City (Phase I) is planned at the mouth of the Pepe river downstream. The construction work will result in changes in river morphology, therefore it is necessary to protect the river slopes so that landslides do not occur. Apart from being a river slope protector, the Revetment design can also be a recreation area and an inspection road. The construction to be used is a concrete sheet pile revetment with reinforcement of the piles behind it as an anchor. Between the concrete sheet pile and the concrete pile, it is connected by a beam-slab structure so that it becomes a portal system. River slope stability analysis using GeoStudio2018 R2 software. River slope conditions that may occur are applied in several modeling, including: River slope conditions without Revetment reinforcement, River slope conditions with Revetment reinforcement, Conditions when changes in river water level elevation occur and river slope conditions when erosion occurs. Based on the results of modeling analysis on the original slope when the river water level increase then recedes has the smallest safe number (SF = 1,822). This is because on the back side of the Revetment, the active soil pressure is in a saturated condition, while the front side of the Revetment loses hydrostatic pressure as a counterweight. The highest safety number is in slope modeling with Revetment strengthening when the river water level increase (SF = 3.114), because the hydrostatic pressure on the back and front of the Revetment is balanced. Revetment construction on river slopes increases the safety rate by 30.64% - 43.70%. With the strengthening of the river slopes, it is hoped that it can provide sufficient security from the main function of protecting the river slopes and obtaining additional functions as a recreation area.
Critical Review of Recent Papers in Learning Media: Advantages, Challenges, and Future Prospects Gunarso, Gunarso; Wahyudin, Wahyudin; Ranggana, Alfaza; Permatasari, Endah; Aprianto, Vani; Septiani, Hesti
Journal of Education Research Vol. 5 No. 1 (2024)
Publisher : Perkumpulan Pengelola Jurnal PAUD Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37985/jer.v5i1.736

Abstract

With the rapid development of technology at this time, the use of learning media is very necessary to support an interesting learning process and can motivate students to participate in learning. The aim of this research is to critically review the use of learning media, including the advantages of the media itself, the challenges faced and the prospects for using learning media in the future. The research method used is bibliometric analysis, utilizing machine learning to map data. This research consists of four stages of bibliometric analysis, namely: data collection using the Publish or Perish application, data processing, data mapping using machine learning, and mapping data analysis using the R programming language. Journal which is a reference published between two thousand nineteen and two thousand twenty three from the Google Scholar database. The search process uses the keyword learning media. The research results show that bibliometric analysis and mapping of 1000 publications using machine learning allows a deeper understanding of developments, trends and important aspects of research in the field of learning media. By using a bibliometric analysis approach and applying machine learning, this research contributes to the development of the use of technology in implementing learning media.
ANALISIS KINERJA STRUKTUR PADA GEDUNG BERTINGKAT DENGAN ANALISIS PUSHOVER BERDASARKAN ATC-40: ANALISIS KINERJA STRUKTUR PADA GEDUNG BERTINGKAT DENGAN ANALISIS PUSHOVER BERDASARKAN ATC-40 Kukuh Kurniawan Dwi Sungkono; Krisdianti, Ega Ayu; Gunarso, Gunarso
Jurnal Teknik Sipil dan Arsitektur Vol 29 No 2 (2024): JURNAL TEKNIK SIPIL DAN ARSITEKTUR
Publisher : Fakultas Teknik Universitas Tunas Pembangunan Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36728/jtsa.v29i2.3300

Abstract

Indonesia is an area prone to earthquakes. Earthquakes can cause infrastructure damage and casualties. Efforts are needed to reduce the risk of earthquake hazards by strengthening earthquake-resistant infrastructure. The design procedures for earthquake-resistant buildings are carried out using a performance-based design approach. Building performance can be estimated through non-linear static pushover analysis. This research takes a case study in Jongke Market, Surakarta. This research aims to determine the capacity curve, performance level, and structure collapse mechanism. The method used is pushover analysis with the capacity spectrum. The result of this analysis is a capacity curve that processed to determine the level of structure performance referring to the drift ratio limitation table in the Applied Technology Council (ATC-40). Based on the results of this research, displacement that occurred in the x direction is 92 mm and in the y direction is 77 mm. Building displacement is good because the displacement that occurred is smaller than the displacement limit (control). The total maximum drift in the x direction is 0.007 and in the y direction is 0.006. The maximum inelastic total drift in the x direction is 0.005 and in the y direction is 0.004. Based on the drift ratio limitation table in the ATC-40 document, this building has an immediate occupancy performance level. Based on the plastic hinge mechanism formed, the existing structure also meets the ideal collapse concept (strong column-weak beam).
ANALISIS GEOTEKNIK DAN KESTABILAN LERENG TOWER SUTT PT. PLN (Studi kasus: TW. 203 Pembangunan T/L 150 KV GI KAMBANG – GI TAPAN): ANALISIS GEOTEKNIK DAN KESTABILAN LERENG TOWER SUTT PT. PLN (Studi kasus: TW. 203 Pembangunan T/L 150 KV GI KAMBANG – GI TAPAN) Kukuh Kurniawan Dwi Sungkono; Arbianto, Reki; Pande, Made Eka Prayuda; Gunarso, Gunarso
Jurnal Teknik Sipil dan Arsitektur Vol 29 No 2 (2024): JURNAL TEKNIK SIPIL DAN ARSITEKTUR
Publisher : Fakultas Teknik Universitas Tunas Pembangunan Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36728/jtsa.v29i2.3847

Abstract

Slope instability is caused by several lithological and structural factors, slope geometry, relative relief, ground water, as well as changes in use and land cover. Mountainous areas, development and expansion of infrastructure networks can inadvertently cause natural slope shifts, thereby negatively impacting the stability of the excavated slope. Analysis of the geotechnical properties of soil and rock is important for understanding and predicting the possibility of landslides at certain locations. Geotechnical analysis is needed to carry out slope stability analysis which is carried out using GEO5 software. Construction of T/L 150 KV GI Kambang – GI Tapan, Tower TW. 203 with a tower structure at the top of the slope. Based on these conditions, a comprehensive study is needed to analyze the stability of natural slopes due to tower loads. Soil Type, Parameters c' and ?' (Drained), Parameters Cu and ? (Undrained) and soil properties index are based on CPT test results. The Bishop, Spencer, Janbu and Morgenstern-Price methods on natural slopes, tower loads, Natural with Tower+Pile Loads, Natural Slopes with Tower+Pile Loads, Earthquake Loads produce a safe condition against failure in Short-Term (Construction) and Long-Term conditions. Term (Operational). Analysis of the Fellenius method on natural slopes and tower loads in Short-Term (Construction) and Long-Term (Operational) conditions shows unsafe conditions. The safety factors resulting from the Bishop, Spencer, Janbu and Morgenstern-Price methods do not show significant differences in values.
REKAYASA MESIN PENGKABUT AIR (HUMIDIFIER CONTROL) UNTUK PENINGKATAN PRODUKSI BIBIT KLENGKENG PINGPONG Widata, Sri; Gunarso, Gunarso; Nugroho, Fajar; Herahli, Among
INOTEKS: Jurnal Inovasi Ilmu Pengetahuan,Teknologi, dan Seni Vol 15, No 1 (2011)
Publisher : Universitas Negeri Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (388.314 KB) | DOI: 10.21831/ino.v15i1.2300

Abstract

This research is aimed to disclose fogging machine application effectiveness for improving klengkeng pingpong seed production. The effectiveness of fogging machine may be measured based on the degree of the fogging machine usage success in klengkeng pingpong nursery process, whose degree of achievement shall be higher than nursery process conducted in natural manner. The research result shows that the average degree of achievement in klengkeng  pingpong  nursery  in  way  of  seedling,  top  grafting,  bridging  or marcot, by using fogging machine is 79.26%. Meanwhile klengkeng pingpong nursery process in natural manner is approximately 40%. In return to this, it indicates that fogging machine usage on klengkeng pingpong nursery is deemed effective as it  has exceeded successful level of natural klengkeng pingpong nursery. Thus, it may eventually be applied in improving klengkeng pingpong seed production