cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
I Made Wicaksana Ekaputra
Contact Email
made@usd.ac.id
Phone
+62274883037
Journal Mail Official
editorial.ijasst@usd.ac.id
Editorial Address
Kampus III Universitas Sanata Dharma, Paingan, Maguwoharjo, Depok, Yogyakarta
Location
Kab. sleman,
Daerah istimewa yogyakarta
INDONESIA
International Journal of Applied Sciences and Smart Technologies
Published by Universitas Sanata Dharma
ISSN : 26558564     EISSN : 26859432     DOI : http://dx.doi.org/10.24071/ijasst
Core Subject : Science, Engineering,
Computer Science & IT Energy Engineering Industrial & Manufacturing Engineering
International Journal of Applied Sciences and Smart Technologies (IJASST) is published by Faculty of Science and Technology, Sanata Dharma University Yogyakarta-Central Java-Indonesia. IJASST is an open-access peer reviewed journal that mediates the dissemination of academicians, researchers, and practitioners in engineering, science, technology, and basic sciences which relate to technology including applied mathematics, physics, and chemistry. IJASST accepts submission from all over the world, especially from Indonesia.
Arjuna Subject : Umum - Umum
Articles 183 Documents
 15   16   17   18   19 
Enhancing the Cooling Effectiveness Utilizing a Tapered Fin Having Capsule-Shaped Cross-Sectional Area Numerically Simulated Using Finite Difference Method Pratama, Nico Ndaru; Setyahandana, Budi; Purwadianto, Doddy; Dyaksa, Gilang Argya; Winarbawa, Heryoga; Seen, Michael; Rines, Rines; Mardikus, Stefan; Kusbandono, Wibowo; Lukiyanto, Y.B
International Journal of Applied Sciences and Smart Technologies Volume 07, Issue 2, December 2025
Publisher : Universitas Sanata Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24071/ijasst.v7i2.12362

Abstract

This paper reports the results of our research on improving the cooling of an engine using fins. This problem is important to discuss because various parts of the world have utilized machining technology. When the engine operates, it produces heat. This heat reduces the efficiency of the engine's performance. In this problem, we developed a tapered fin method with a capsule cross-section to enhance cooling performance. The fin consists of two different materials that are perfectly joined. In this paper, the fin analysis is performed using the explicit finite difference numerical method. This method simulates the heat distribution on the fins. The results of our research include temperature distribution, heat flow rate, efficiency, and fin effectiveness in unsteady-state conditions with variations in material composition. The highest heat flow rate, fin efficiency, and fin effectiveness were achieved with a fin material composition of copper and aluminum, yielding an efficiency value of 0.89 and an effectiveness of 20.7. Our research results offer potential for the industry to design fins for innovative applications.
The Effect of Image Enhancement on Automatic Vehicle Detection Using Yolov8 Based on Jetson Nano Single Board Computer Putra, Rakhmad Gusta; Pribadi, Wahyu; Sudirman, Dirvi Eko Juliando
International Journal of Applied Sciences and Smart Technologies Volume 07, Issue 2, December 2025
Publisher : Universitas Sanata Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24071/ijasst.v7i2.11640

Abstract

Vehicle counting systems using image processing and deep learning have been widely studied. Using images captured by CCTV cameras makes vehicle counting effective and efficient. Although much research has been done, there are still challenges in direct application in the field. Object detection methods such as YOLO are widely chosen. In field applications, challenges are found such as rainy, nighttime, or foggy conditions and the use of appropriate hardware. In this study, the YOLOv8s and YOLOv8n object detection methods are proposed using contrast-limited Adaptive Histogram Equalization (CLAHE) image enhancement in preprocessing and datasets and run using SBC Jetson Nano. From this study, the results obtained an increase in detection values of around 10% to 20% in dark image conditions and there was no improvement for bright images. The average accuracy is 0.873312 for YOLOv8s and 0.866906 for YOLOv8n with image enhancement. And the processing time on Jetson Nano is 59.5 ms for YOLOv8n.
Braille Pattern Detection Modeling Using Inception V3 Architecture Using Median Filter Implementation and Segmentation Latif, Abdul; Yuliyanti, Siti; Al-Husaini, Muhammad
International Journal of Applied Sciences and Smart Technologies Volume 07, Issue 2, December 2025
Publisher : Universitas Sanata Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24071/ijasst.v7i2.12781

Abstract

This study aims to detect Braille letter patterns using the InceptionV3 architecture combined with the application of median filter and image segmentation. The dataset consists of 4,160 Braille images, with an average of 160 images for each letter from A to Z. The data is divided into 3,900 images for training, which are then split into 3,120 images for training and 780 images for validation, and 260 images are used for testing. Each image is resized to 299x299 pixels before being fed into the model. This study uses 100 epochs and applies early stopping to avoid overfitting. Two learning rate values are tested, namely 0.001 and 0.0001. The results show that the application of a median filter and segmentation significantly improves model performance, producing better accuracy, precision, recall, and F1 values compared to models without these techniques. At a learning rate of 0.001, the model achieves 99.65% accuracy, 99.62% precision, and 99.61% recall. On the other hand, without a median filter and segmentation at a learning rate of 0.0001, although accuracy and precision decreased, the values still reached 99.65% and 99.62%.
Numerical Solution of Two-Dimensional Advection Diffusion Equation for Multiphase Flows in Porous Media Using a Novel Meshfree Method of Lines. Kazeem, Jamiu Abiodun; Ogunfiditimi, Franklin Olusodayo
International Journal of Applied Sciences and Smart Technologies Volume 07, Issue 2, December 2025
Publisher : Universitas Sanata Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24071/ijasst.v7i2.12523

Abstract

This study proposes a novel Meshfree Method of Lines (MFMOL), in strong form formulation, to solve multiphase flows of solute transport modelled by two-dimensional (2D) Advection Diffusion Equations (ADE). The method uses a consistent and stable Augmented Radial Basis Point Interpolation Method (ARPIM) for spatial variables discretization of the models, while the time variable is left continuous, resulting in a system of Ordinary Differential Equations (ODEs) with initial conditions, which is solved numerically, via Matlab ode solver. The new method is proposed to overcome the challenges of numerical instabilities and large deformation due to complex domain, and distorted or low-quality meshes that attracts remeshing, all encountered by traditional Finite Element Method (FEM), Finite Difference Method (FDM) and Finite Volume Method (FVM). Also, the MFMOL is used in strong form formulation without any stabilization techniques for the convective terms in solute transport models, contrary to other methods like FEM, FDM, FVM and meshfree Finite Point Method (FPM) that require the stabilization techniques for fluid flow problems to guarantee acceptable results. The efficiency and accuracy of the new method were established and validated by using it to solve 2D diffusive and advective flow problems in the complex domain of porous structures. The results obtained agreed with the existing exact solutions, using less computational efforts, costs and time, compared with mesh-based methods and others that require stabilization for the convective terms. These features established the superior performance of the new method to the mesh-based methods and others that require special stabilization techniques for solving 2D multiphase flow of solute transport in porous media and other transient fluid flow problems.
Evaluating XGBoost Performance in Improving Community Security through Multi-Class Crime Prediction: Insights from the Denver Crime Dataset Pepple, Mc-Kelly Tamunotena
International Journal of Applied Sciences and Smart Technologies Volume 07, Issue 2, December 2025
Publisher : Universitas Sanata Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24071/ijasst.v7i2.11689

Abstract

Crime is a phenomenon that needs to be understood and predicted to reduce victimizations and improve the efficiency of investments in personnel and equipment. Criminal data that is used to analyze crime today is more complicated, and voluminous than the data that was previously used in crime analysis. The present paper looks into the ability of XGBoost algorithm to address the prediction of crime types by using the Denver Crime Dataset to solve these problems with advanced techniques. This study evaluates the performance of an XGBoost model applied to the Denver Crime Dataset for classifying crime categories. Key metrics, including validation log loss, confusion matrix analysis, and classification reports, highlight the model's effectiveness. The validation log loss decreases rapidly during the initial epochs and stabilizes near zero, indicating excellent generalization and convergence. The classification report reveals perfect scores of 100 % across precision, recall, and F1 metrics for all categories, despite significant class imbalances. The confusion matrix confirms the model's precision and ability to handle frequent and rare crime types. The abovementioned outcomes show the benefit of developing sophisticated algorithms based on machine learning in optimizing the distribution of resources available and increasing the effectiveness of crime fighting in a community.
Sign Language Detection Models using Resnet-34 and Augmentation Techniques Hilal, Rizki Ramdhan; Aradea, Aradea; Purwayoga, Vega
International Journal of Applied Sciences and Smart Technologies Volume 07, Issue 2, December 2025
Publisher : Universitas Sanata Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24071/ijasst.v7i2.12888

Abstract

For deaf or hard of hearing people, sign language is a primary means of communication, but low public understanding makes social engagement difficult. Researchers now use computer vision technology and Convolutional Neural Network (CNN) to detect sign language movements. Problems such as overfitting and missing gradients still exist. Using CNN and ResNet-34 architecture, as well as image augmentation to overcome this problem, this research builds a deep learning-based sign language detection model. The Indonesian Sign Language System (SIBI) dataset was used to test the model. The test results show that the model with image augmentation trained for more than 50 epochs obtained an accuracy of 99.4%, precision of 99.5%, recall of 99.5%, and an F1 score of 99.5%. The model without image augmentation produced an accuracy of 99.4%, recall of 99.3%, F1 score of 99.3%, and precision of 99.4%. ResNet-34 architecture overcomes the problem of missing gradients, while image augmentation avoids overfitting and improves model accuracy.
Coconut Shell-Based Briquettes for Sustainable Energy: A Bibliometric Study on Biomass Mixtures and Binder Materials Darmawan, Ridho; Dewantoro, Awaly Ilham; Mardawati, Efri
International Journal of Applied Sciences and Smart Technologies Volume 07, Issue 2, December 2025
Publisher : Universitas Sanata Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24071/ijasst.v7i2.12668

Abstract

Coconut shell is one of the potential biomass resources that has been widely developed as a raw material for briquettes to support renewable energy initiatives and circular economy practices. This study aimed to explore the development, research focus, and future directions of cocomut shell briquette through a systematic literature review. The Methodi Ordinatio approach was employed for analysis, resulting in a final portfolio of 134 selected documents, which were the further examined to identify trends and research gaps. The findings showed that mixturing coconut shell with other biomass such as from wood-based and agricultural-based residues could enhance the briquette performance. Moreover, alternative binders such as lignocellulosic carbohydrate and its derivatives, plant sap, and waste cooking oil offered promising subsitutes for food-based materials. Oily biomass, such as eucalyptus wastes and pine resin, was also found to improve briquette performance due to its volatile content. In addition, the integration of automation technologies based on microcontrolers and the Internet of Things (IoT) began to applied to improve production efficiency and consistency. It is expected that the findings of this study can serve as a foundation for future development focused on material formulation and technological innovations for coconut shell-based briquette production that are more efficient, sustainable, and responsive to future energy needs.
Determination of Cyanide Content and Heavy Metals (Cu, Ni, Cd, & Pb) in Different Processed Cassava Meal in Abraka Metropolis, Delta State, Nigeria Udezi, Mercy Eloho
International Journal of Applied Sciences and Smart Technologies Volume 07, Issue 2, December 2025
Publisher : Universitas Sanata Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24071/ijasst.v7i2.11760

Abstract

Cassava is a tuberous plant in Nigeria that can be processed into different meal but its various forms contains a trace concentrations of cyanide, cadmium, nickel, lead and copper that are not only essential for man but toxic if their concentration levels are high. This study determined the cyanide content and some heavy metals in different processed cassava meal sold in markets at Abraka and its environs. Samples of fufu, garri, starch, and fresh cassava were collected from five selected markets in Abraka. Cyanide concentration was determined using AOAC (1990) method of alkaline titration steam distillation of the sample using silver nitrate. While copper, cadmium, nickel and lead were determined using the Atomic absorption spectrophotometer. Results for the cyanide levels were 7.56 mg/kg for fresh cassava, 5.4 mg/kg for starch, 3.24 mg/kg for garri, 2.16 mg/kg for fufu. The levels were in the order, fresh casava starch garri fufu. The heavy metals concentration of copper (Cu), were (mg/kg) 2.04 for fresh cassava, 1.62 for garri, 1.44 for fufu, and 1.02 for starch. The levels were in the order, fresh cassava garri fufu starch. The concentration of cadmium (Cd) were (mg/kg) 3.14 for fresh cassava, 1.03 for garri, 1.47 for fufu, 2.84 for starch. The levels were in the order, fresh cassava starch fufu garri. The concentrations of nickel (Ni) were (mg/kg) 2.46 for fresh cassava, 1.89 for garri. 1.94 for fufu and 1.73 for starch. The levels were in the order, fresh cassava fufu garri starch. Lead (Pb) was not detected in all the samples. From the results obtained in this study, fufu is the safest for consumption due to the low contents of cyanide and heavy metals. Garri is also considered to be safe as they fall within the WHO permissible limit for those metals. Hence, proper processing of cassava products should be encouraged to reduce bioaccumulation of cyanides levels in them.
SVM and Ensemble Majority Voting Algorithm on Sentiment Analysis of Using chatGPT in Education Yayukristi Weko, Hildegardis; Suparwito, Hari
International Journal of Applied Sciences and Smart Technologies Volume 07, Issue 2, December 2025
Publisher : Universitas Sanata Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24071/ijasst.v7i2.12680

Abstract

The pros and cons of using ChatGPT in education have caused academic debate as it has influenced current educational praxis. Discussions about the possibility of ChatGPT for writing manuscripts or doing assignments are rife on social media, one of which is Twitter. The purpose of this study is to understand the public perception of the use of ChatGPT in education. The proposed method is sentiment analysis with SVM and Majority Voting algorithms. SVM is one of the superior algorithms in pattern recognition and is suitable for use in classification. The Majority Voting ensemble algorithm combines independent algorithms' prediction results. In this research, majority voting uses three base classifiers, namely Naïve Bayes, Random Forest, and KNN. The results of the study showed that the accuracy of SVM is 83.6% and Majority Voting is 85.4%, with the accuracy of the NB, RF, and KNN base classifiers of 76.82%, 80.91%, and 74.5%, respectively. This proved that the Majority Voting Ensemble is superior to individual algorithms with higher accuracy values. This follows the results of previous research, where the ensemble performs better than the individual algorithm. The accuracy values of SVM and the Ensemble Majority Voting models showed that both models could successfully classify sentiment on tweet data for using ChatGPT in education.
Fine-Tuned IndoBERT-Based Sentiment Analysis for Old Indonesian Songs Using Contextual and Generating Augmentation Ramdhani, Gilang; Yuliyanti, Siti
International Journal of Applied Sciences and Smart Technologies Volume 07, Issue 2, December 2025
Publisher : Universitas Sanata Dharma

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24071/ijasst.v7i2.12586

Abstract

Studi ini meneliti analisis sentimen lagu-lagu tradisional Indonesia menggunakan model IndoBERT yang telah disempurnakan melalui penggabungan augmentasi data kontekstual dan tekstual. Kumpulan data tersebut terdiri dari komentar pengguna yang terkait dengan lagu-lagu klasik Indonesia, yang dipecah ke dalam sentimen positif, negatif, dan netral. Dua strategi augmentasi diterapkan: augmentasi tekstual menggunakan teknik pembuatan teks dan augmentasi kontekstual yang memanfaatkan kesamaan semantik. Evaluasi dilakukan dengan menggunakan metrik akurasi, presisi, recall, dan skor F1. Hasil penelitian menunjukkan bahwa model yang dibor pada kumpulan data asli mencapai kinerja yang seimbang dan stabil (akurasi: 0,86). Augmentasi tekstual, meskipun menghasilkan variasi data yang tinggi, mengurangi akurasi model (0,63) dan memperkenalkan bias terhadap sentimen negatif. Sebaliknya, augmentasi kontekstual mempertahankan stabilitas kinerja dan bahkan sedikit meningkatkan presisi (0,87). Temuan ini menunjukkan bahwa augmentasi kontekstual lebih efektif untuk memperkaya kumpulan sentimen data tanpa mengorbankan kinerja model. Temuan ini menyoroti efektivitas pengintegrasian model bahasa yang telah dikembangkan sebelumnya dan strategi augmentasi data untuk menganalisis sentimen dalam sumber daya rendah.

Page 18 of 19 | Total Record : 183

 15   16   17   18   19 

Filter by Year

2019 2025


Reset
Filter By Issues
All Issue Volume 07, Issue 2, December 2025 Volume 07, Issue 1, June 2025 Volume 06, Issue 2, December 2024 Volume 06, Issue 1, June 2024 Volume 05, Issue 02, December 2023 Volume 05, Issue 01, June 2023 Volume 04, Issue 02, December 2022 Volume 04, Issue 01, June 2022 Volume 03, Issue 02, December 2021 Volume 03, Issue 01, June 2021 Volume 02, Issue 02, December 2020 Volume 02, Issue 01, Juni 2020 Volume 02, Issue 01, June 2020 Volume 01, Issue 02, December 2019 Volume 01, Issue 01, June 2019 More Issue