cover
Article Per Year (5 Year)
All
Home Page
OAI Link
Editorial Team
Contact
Reviewer
Google Scholar
Contact Name
Alde Alanda
Contact Email
alde@pnp.ac.id
Phone
+6281267775707
Journal Mail Official
editor@ijasce.org
Editorial Address
Kampus Limau Manis
Location
Kota padang,
Sumatera barat
INDONESIA
International Journal of Advanced Science Computing and Engineering
Published by Society of Visual Informatics
ISSN : 27147533     EISSN : 27147533     DOI : https://doi.org/10.30630/ijasce
Core Subject : Science, Engineering,
Computer Science & IT Control & Systems Engineering Electrical & Electronics Engineering
The journal scopes include (but not limited to) the followings: Computer Science : Artificial Intelligence, Data Mining, Database, Data Warehouse, Big Data, Machine Learning, Operating System, Algorithm Computer Engineering : Computer Architecture, Computer Network, Computer Security, Embedded system, Coud Computing, Internet of Thing, Robotics, Computer Hardware Information Technology : Information System, Internet & Mobile Computing, Geographical Information System Visualization : Virtual Reality, Augmented Reality, Multimedia, Computer Vision, Computer Graphics, Pattern & Speech Recognition, image processing Social Informatics: ICT interaction with society, ICT application in social science, ICT as a social research tool, ICT education
Arjuna Subject : Ilmu Komputer (semua kategori) - Ilmu Komputer (Lain-Lain)
Articles 149 Documents
 10   11   12   13   14 
Generating Accurate Human Face Sketches from Text Descriptions Sharma, Shorya
International Journal of Advanced Science Computing and Engineering Vol. 6 No. 1 (2024)
Publisher : SOTVI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/ijasce.6.1.195

Abstract

Drawing a face for a suspect just based on the descriptions of the eyewitnesses is a difficult task. There are some state-of-the-art methods in generating images from text, but there is only a little research in generating face images from text, and almost none in generating sketches from text. As a result, there is no dataset available to tackle this task.  We developed a text-to-sketch dataset derived from the CelebA dataset, which comprises 200,000 celebrity images, thereby facilitating the investigation of the novel task of generating police sketches from textual descriptions. Furthermore, we demonstrated that the application of AttnGAN for generating sketch images effectively captures the facial features described in the text. We identified the optimal configuration for AttnGAN and its variants through experiments involving various recurrent neural network types and embedding sizes. We provided commonly used metric values, such as the Inception score and Fréchet Inception Distance (FID), for the two-attention-based state-of-the-art model we achieved. However, we also identified areas for improvement in the model's application. Experiments conducted with a new dataset consisting of 200 sketch images from Beijing Normal University revealed that the model encounters challenges when handling longer sentences or unfamiliar terms within descriptions. This limitation in capturing features from such text contributes to a decrease in image diversity and realism, adversely impacting the overall performance of the model. For future improvements, consider exploring alternative models such as Stack-GAN, Conditional-GAN, DC-GAN, and Style-GAN, which are known for their capabilities in face image generation. Simplifying architecture while maintaining performance can also help deploy models on mobile devices for real-world use.
Identification of Ultraviolet (UV) Levels in the Caramelization Process of Sale Pisang Berlianti, Rahmi; Kurniadi, Dedi; Putri, Dian Permata; Alfitri, Nadia; Susanti, Roza; Mudia, Halim
International Journal of Advanced Science Computing and Engineering Vol. 6 No. 1 (2024)
Publisher : SOTVI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/ijasce.6.1.196

Abstract

Sale pisang is a typical Indonesian food made from dried bananas. Usually, this drying is done by drying directly in the sun. Drying bananas in the sun is not very effective because it takes a long time and is very dependent on weather conditions. After innovation was made by making a dryer, sale pisang was produced which had a hard texture and low moisture content that affected the caramelization process. Therefore, a dryer is needed that can replace the drying process under the sun. One of the contents of sunlight is ultraviolet light. Irradiation of ultraviolet light, especially UVC light, can help shrink the cell wall of bananas so that the evaporation of water during drying is small. This study aims to identify good UV levels for the caramelization process to produce the same sale pisang as drying under the sun using 5 different treatments, namely, without UV lighting, 15 minutes irradiation, 30 minutes irradiation, 1-hour irradiation, and 2 hours irradiation. Irradiation for 15 minutes produces a water content of 11%, irradiation for 30 minutes produces a water content of 12%, irradiation for 1 hour produces a water content of 18%, and Sale pisang with irradiation for 2 hours produces a water content of 20%. Based on the texture analysis produced by irradiation for 1 hour produces a texture that is almost the same as drying directly under the sun.
Design and Validation of Structural Causal Model: A Focus on SENSE-EGRA Datasets Ayem, Gabriel Terna; Nsang , Augustine Shey; Igoche, Bernard Igoche; Naankang, Garba
International Journal of Advanced Science Computing and Engineering Vol. 6 No. 1 (2024)
Publisher : SOTVI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/ijasce.6.1.200

Abstract

Designing and validating a causal model's correctness from a dataset whose background knowledge is obtained from a research process is not a common phenomenon. Studies have shown that in many critical areas, such as healthcare and education, researchers develop models from direct acyclic graphs without testing them. This phenomenon is worrisome and is bound to cast a dark shadow on the inference estimates that many arise from such models. In this study, we have designed a novel application-based SCM for the first time using the background knowledge gained from the American University of Nigeria (AUN), Yola, on the letter identification subtask of the Early Grade Reading Assessment (EGRA) program on the Strengthen Education in Northeast Nigeria (SENSE-EGRA) project dataset, which the USAID sponsored. We employed the conditional independence test (CIT) criteria for the model’s correctness validation testing, and the results show a near-perfect SCM.
Leveraging Social Media Networks' Impact on Technopreneurship Isa, Khairunesa; Palpanadan, Sarala Thulasi; Saparudin , Intan Farhana; Zainol, Nur Zainatul Nadra; Syahrudin
International Journal of Advanced Science Computing and Engineering Vol. 6 No. 1 (2024)
Publisher : SOTVI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/ijasce.6.1.201

Abstract

Technology has become an integral part of society, substantially contributing to its many facets. With the advent of technology, media entrepreneurship in Malaysia has expanded significantly. The younger generation, specifically Generation Z, relies heavily on social media for communication, information inquiry, and online purchasing and selling. This change has had a significant impact on the Malaysian field of technopreneurship. Therefore, the purpose of this study is to examine the relationship between the factors that influence Generation Z's use of social media for business and their propensity to engage in technopreneurship. This quantitative study utilizes a questionnaire to gather demographic information, explore factors influencing Generation Z's use of social media for business purposes, and examine their motivations and aspirations for engaging in technopreneurship activities. 280 respondents from Generation Z technopreneurs were selected through random sampling. The software Statistical Package for the Social Sciences (SPSS) was used to perform a descriptive analysis of the obtained data. According to the study's findings, each factor has a significant relationship with the motivation to engage in technopreneurship. By adopting these strategies, the government can help new and aspiring entrepreneurs make better-informed choices and utilize technology effectively to expand their businesses. This can boost the digital economy and generate new jobs in the tech industry. Consequently, policymakers and stakeholders should consider the study's findings and take proactive steps to promote technopreneurship development in Malaysia.
Disease Identification on Fig Leaf Images Using Deep Learning Method Bismi, Waeisul; Riana, Dwiza; Hewiz , Alya Shafira
International Journal of Advanced Science Computing and Engineering Vol. 6 No. 2 (2024)
Publisher : SOTVI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/ijasce.6.2.203

Abstract

The fig plant, known as Ficus carica, has been cultivated worldwide, including in Indonesia. It has nutritional benefits and medicinal properties. However, there are still difficulties in growing it, making the plant scarce. The scarcity of fig plants in Indonesia is mainly due to the threat of diseases and viruses that affect them. Various diseases affect fig plants, including leaf rust (Cerotelium fici), mosaic disease, and Bemisia tabaci (whitefly) disease. Infected fig plants become unhealthy, experiencing stunted growth and deformed fruits; thus, it is necessary to identify the diseases accurately using technological assistance. This research aimed to identify diseases in fig leaves automatically. The method began by digitizing fig leaf images and consulting botanical experts specializing in fig plants to determine the types of diseases present. The research produced a dataset of fig leaf images consisting of four classes of fig leaves: Cerotelium fici, mosaic disease, whitefly, and healthy fig leaves. The dataset resulted in the confirmation of 300 fig leaf images. The augmentation techniques were applied to increase the number of images to 3,300 fig leaf images. This dataset was then divided into subsets for training, validation, and testing. For the classification and identification, a Deep Learning approach was used with three models: VGG16, VGG19, and MobileNet. Among these models, MobileNet achieved the highest accuracy of 98.79%. Subsequently, the identification system was implemented by converting the generated model into TensorFlow Lite and integrating it into the Android Studio software, enabling it to function as a mobile application on Android devices.
Impact the Classes’ Number on the Convolutional Neural Networks Performance for Image Classification Ali , Amna Kadhim; Abdullah , Abdulhussein Mohsin; Raheem , Sabreen Fawzi
International Journal of Advanced Science Computing and Engineering Vol. 6 No. 2 (2024)
Publisher : SOTVI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/ijasce.6.2.204

Abstract

Deep learning was developed as a realistic artificial intelligence technique that takes in numerous layers of information and produces the best results in various classes. Deep learning has demonstrated excellent performance in several areas, particularly picture grouping, division, and recognition. The convolutional neural network (CNN) is one of the algorithms that relies on deep learning in its work. It has proven its effectiveness in classifying images with high efficiency in medical images and their diagnoses, face recognition, and other different fields. In this paper, the focus was on images to alert new researchers to their effects on the performance of CNN in terms of the number of classes that existed within the database, in addition to the impact of incorrect classification of images by the source on the classification result and the necessity of adopting reliable and correct sources of data to avoid inaccurate results. A group of face images has been used, and three experiments on them were conducted using all existing classes with reduction. The results showed a significant improvement in the performance of the algorithm whenever the number of classes was reduced. The best result was when only two classes were chosen for classification, reaching a validation accuracy of 85%.
Online Platform of Mathematical Terms in Karakalpak Language Allabay, Arziev; Jumabek, Seypullayev; Purxan, Nasirov; Begench, Geldibayev
International Journal of Advanced Science Computing and Engineering Vol. 6 No. 2 (2024)
Publisher : SOTVI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/ijasce.6.2.205

Abstract

The paper is devoted to the creation of an online platform of mathematical terms in Karakalpak language and its importance for education, cultural heritage and development of scientific research in Karakalpakstan. The platform provides access to a rich base of mathematical terminology in the native language, which facilitates the learning and teaching of mathematics for Karakalpak students and teachers. It contributes to the preservation of cultural values, enriches linguistic resources and stimulates scientific cooperation in the field of mathematics. The creation of this platform emphasizes the importance of linguistic diversity and cultural identity in the context of scientific and educational progress.
Efficient Vehicle Registration Recognition System: Enhancing Accuracy and Power Efficiency through Digital Image Processing R. Madhumitha
International Journal of Advanced Science Computing and Engineering Vol. 6 No. 2 (2024)
Publisher : SOTVI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/ijasce.6.2.206

Abstract

Number-plate recognition technology uses optical character recognition on images to read vehicle registration plates using OpenCV, PyTesseract OCR Engine, and YOLOv4 model. Images of the license plates are provided to the YOLOv4 model using a web app. The model is trained with the help of images from the Kaggle dataset. Then the number plate is extracted from the vehicle using the model. The string from the image is extracted using PyTesseract OCR Engine. Tested on several datasets this method gave us a success rate of 94%. This method can also be used in real-time incidents.
Modification in Strength Parameter (CBR) of Sub-Grade Soil with Addition of Fly Ash Jadhav , Abhijit; Nalawade , R D; Gaikwad , D P
International Journal of Advanced Science Computing and Engineering Vol. 6 No. 2 (2024)
Publisher : SOTVI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/ijasce.6.2.207

Abstract

The determination of the California Bearing Ratio value of soil is tiresome, uneconomical, and time-consuming in the laboratory. Therefore, there is a required automation system to determine the California Bearing Ratio value of soil. Machine learning algorithms are being used for automation systems. In this paper, Artificial Neural Network has been proposed for the prediction of the California Bearing Ratio value of soil. Ash percentage, Liquid Limit, Plastic_Limit, Plasticity index, Shrinkage Limit, MDD and OMC parameters of soil affect the value of the California Bearing Ratio. In the laboratory, the training dataset has generated using these parameters of soil. The proposed classifier has been trained and tested using the training and testing dataset. Experimental results show that the proposed Artificial Neural Network is very accurate to predict California Bearing Ratio values of soil. It is also observed that the linear regression algorithm is very easy and useful to determine the value of the California Bearing ratio depending on seven attributes of soil. The rules generated by J48 and PART can be used to determine the California Bearing ratio. These models are very useful for civil engineers and civil constructors as a California Bearing ratio prediction automation system.
Development of Media Branding on Batik Products for MSME Actors in Kulon Progo Regency Istanti, Hanifah Nur; Kholifah, Nur; Putri, Gina Eka; Triyanto; Fitrihana, Noor
International Journal of Advanced Science Computing and Engineering Vol. 6 No. 2 (2024)
Publisher : SOTVI

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/ijasce.6.2.209

Abstract

Batik product marketing techniques are essential to the sustainability of an MSME in Kulon Progo. Various media can be used as a means of marketing. Based on previous research in 2021, the branding media used in the category is quite good, so there is a need to improve and develop the branding media used. This research aims to: (1) design the development of Sembung Batik branding media through an account on Shopee; and (2) Test the feasibility of developing Sembung Batik branding media through an account on Shopee. The research was carried out at Batik Sembung Kulon Progo. This type of research is development research using a 4D model and a quantitative descriptive approach. 4D Design comprises the definition, design, development, and dissemination stages. Three expert lecturers carried out the feasibility test. This research is to: (1). design the development of Sembung Batik branding media through an account on Shopee, which consists of four stages: the definition stage, the design stage, the development stage, and the disseminated stage, which is carried out 3 Shopee live times; and (2). the feasibility level of developing Sembung Batik branding media through an account on Shopee is very suitable for use based on the opinions of 3 experts. Based on this research, the development of branding media using live streaming can be implemented for other branding media so that it can have an impact on MSME branding.

Page 12 of 15 | Total Record : 149

 10   11   12   13   14 

Filter by Year

2019 2025


Reset
Filter By Issues
All Issue Vol. 7 No. 3 (2025) Vol. 7 No. 2 (2025) Vol. 7 No. 1 (2025) Vol. 6 No. 3 (2024) Vol. 6 No. 2 (2024) Vol. 6 No. 1 (2024) Vol. 5 No. 3 (2023) Vol. 5 No. 2 (2023) Vol. 5 No. 1 (2023) Vol. 4 No. 3 (2022) Vol. 4 No. 2 (2022) Vol. 4 No. 1 (2022) Vol. 3 No. 3 (2021) Vol. 3 No. 2 (2021) Vol. 3 No. 1 (2021) Vol. 2 No. 3 (2020) Vol. 2 No. 2 (2020) Vol. 2 No. 1 (2020) Vol. 1 No. 3 (2019) Vol. 1 No. 2 (2019) Vol. 1 No. 1 (2019) More Issue