cover
Contact Name
Heri Nurdiyanto
Contact Email
jurnal.ijasca@gmail.com
Phone
+6285766661199
Journal Mail Official
jurnal.ijasca@gmail.com
Editorial Address
Lucky Arya Residence 2 No. 18 Jalan HOS. Cokroaminoto Kab. Pringsewu 35373
Location
Kab. pringsewu,
Lampung
INDONESIA
International Journal of Advanced Science and Computer Applications
Published by UK Institute
ISSN : 28097599     EISSN : 28097467     DOI : https://doi.org/10.47679/ijasca
International Journal of Advanced Science and Computer Applications (IJASCA) is a peer-reviewed open-access journal. The journal invites scientists and engineers throughout the world to exchange and disseminate theoretical and practice-oriented the whole spectrum of Advanced Science and Computer Applications. Submitted papers must be written in English for an initial review stage by editors and further review process by a minimum of two international reviewers. Accepted papers will be freely accessed in this website
Articles 65 Documents
Integrating OCR and NLP Techniques for Accurate Text Extraction and Plagiarism Detection in Image-Based Content Palvadi Srinivas Kumar; Krishna Prasad
International Journal of Advanced Science and Computer Applications Vol. 4 No. 1 (2025): March 2025
Publisher : Utan Kayu Publishins

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47679/ijasca.v4i1.105

Abstract

In the digital age, images often contain valuable text-based information, including numbers, symbols, and other data. Efficient extraction and verification of this content is critical, particularly in academic and content-driven domains where originality is paramount. This paper presents a novel approach to detecting plagiarism in text embedded within images. The proposed method leverages Optical Character Recognition (OCR) to extract text from images and applies Natural Language Processing (NLP) techniques to evaluate the originality of the extracted content. By comparing the text against a comprehensive database of existing sources, the system is capable of identifying potential plagiarism while distinguishing between original and copied content. This approach ensures that not only text in conventional documents but also in images is scrutinized for authenticity, enhancing the reliability of plagiarism detection in diverse content formats. The proposed solution offers an efficient and automated pipeline for image-based text extraction and plagiarism detection, applicable in educational, legal, and content creation environments.
Developing Semantic Textual Similarity for Guragigna Language Using Deep Learning Approach Getnet Degemu
International Journal of Advanced Science and Computer Applications Vol. 5 No. 1 (2026): March 2026
Publisher : Utan Kayu Publishins

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47679/ijasca.v4i2.106

Abstract

Semantic Similarity is one of the highest levels of NLP. STS has significant advantages in NLP applications like information retrieval, information extraction, text summarization, data mining, machine translation, and other tasks. This research aims to present a deep learning approach for capturing semantic textual similarity (STS) in the Guragigna. The methodology involves collecting a Guragigna language corpus and preprocessing the text data and text representation is done using the Universal Sentence Encoder (USE), along with word embedding techniques including Word2Vec and GloVe and mean Square Error (MSE) is used to measure the performance. In the experimentation phase, models like LSTM, Bidirectional RNN, GRU, and Stacked RNN are trained and evaluated using different embedding techniques. The results demonstrate the efficacy of the developed models in capturing semantic textual similarity in the Guragigna language. Across different embedding techniques, including Word2Vec, GloVe, and USE, the Bidirectional RNN model with USE embedding achieves the lowest MSE of 0.0950 and the highest accuracy of 0.9244. GloVe and Word2Vec embedding also show competitive performance with slightly higher MSE and lower accuracy. The Universal Sentence Encoder consistently emerges as the top-performing embedding across all RNN architectures. The research results demonstrate the effectiveness of LSTM, GRU, Bi RNN, and Stacked RNN models in measuring semantic textual similarity in the Guragigna language.
Hand Gesture Recognition in Augmented Reality using Deep Learning Models Sneha Saini
International Journal of Advanced Science and Computer Applications Vol. 5 No. 1 (2026): March 2026
Publisher : Utan Kayu Publishins

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

We present a comprehensive exploration of hand gesture recognition models leveraging various deep learning architectures, including Convolutional Neural Networks (CNN), Long Short-Term Memory networks (LSTM), and pre-trained architectures such as VGG16 and ResNet. The primary objective of this research is to enhance the accuracy, robustness, and generalization capabilities of hand gesture recognition systems for applications in augmented reality (AR), human-computer interaction (HCI). We trained the models on a large-scale dataset consisting of 14,000 images representing various hand gestures, which ensured diverse and comprehensive training data. The models were designed to capture both the spatial and temporal patterns inherent in hand gestures. Additionally, pre-trained architectures like VGG16 and ResNet were employed using transfer learning techniques, which enabled these models to take advantage of their deep feature extraction capabilities. Both VGG16 and ResNet architectures were fine-tuned to adapt their learned features to the specific requirements of the hand gesture recognition task. Our experimental results demonstrate that while the CNN-LSTM models are capable of accurately recognizing gestures, the pre-trained architectures, especially ResNet, outshine them in terms of performance metrics and computational efficiency. The VGG16 model achieved the highest accuracy of 97.5% , compared to 96% for ResNet and 93% for the CNN-LSTM model. Our findings contribute to the ongoing development of more efficient and accurate hand gesture recognition systems. The insights gained from this research can be extended to future studies that explore hybrid models combining the strengths of CNN-LSTM, and pre-trained architectures to achieve even greater recognition accuracy in more challenging environments.
A Machine Learning-Based Recommendation System for Disease Prediction Sonali Dass; Khushi Jaiswal; Sandeep Kumar
International Journal of Advanced Science and Computer Applications Vol. 5 No. 1 (2026): March 2026
Publisher : Utan Kayu Publishins

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47679/ijasca.v5i1.121

Abstract

A key strategy for enhancing clinical judgment and tailored medicine is the incorporation of machine learning into healthcare systems. This study presents a Medicine Recommendation System (MRS) that uses a variety of machine learning models to recommend drugs based on disease prediction. Among these models are K-Means Clustering, Random Forest, Support Vector Classifier (SVC), Naive Bayes, Logistic Regression, and Gradient Boosting. In order to anticipate the likely condition and provide a suitable drug, the system makes use of patient data, including symptoms, demographics, and medical history. Accuracy, precision, recall, F1 score, and confusion matrix measures are used to assess each model's performance.
Revolutionizing Digital Advertising: The Role of Blockchain in Marketing Strategies Lusekelo Kibona
International Journal of Advanced Science and Computer Applications Vol. 5 No. 1 (2026): March 2026
Publisher : Utan Kayu Publishins

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

This study explored the role of blockchain technology in revolutionizing digital advertising, focusing on its awareness, adoption, and impact on marketing strategies. With a sample size of 98 participants, the research examined key indicators such as the level of awareness and understanding of blockchain concepts, the extent of adoption in digital advertising, and perceptions of its benefits and challenges. Findings revealed that while awareness and moderate understanding of blockchain were widespread, significant challenges hindered its full integration into advertising infrastructures. Despite these obstacles, the potential of blockchain to enhance transparency, prevent ad fraud, and improve targeting was recognized by many respondents. The study concludes that strategic efforts are needed to overcome adoption barriers and recommends targeted education, collaboration, and gradual implementation to unlock blockchain's full potential in digital advertising.
Shaping Modern Society: The Transformative Role of Information Technology Geofrey Nyabuto
International Journal of Advanced Science and Computer Applications Vol. 5 No. 1 (2026): March 2026
Publisher : Utan Kayu Publishins

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Information Technology (IT), a key field in computing, focuses on the creation, collection, processing, storage, and retrieval of information through digital systems. Over the past three decades, IT has profoundly transformed societal activities, reshaping how individuals and organizations operate. This paper examines the dual impact of IT, highlighting its positive contributions to societal growth and well-being while also addressing the challenges and negative consequences it has introduced. By exploring both perspectives, this review provides a comprehensive understanding of IT's role in shaping modern society
Bi-level Programming-Based Optimization of Vehicle Scheduling and Warehouse Operations in Power Logistics Parks yongjie ma; Ji-quan Zhang; Wen-xian Guo; Tian-chi Deng; Yong-xin Jing; Ji-yuan Chen; xian-guang jia
International Journal of Advanced Science and Computer Applications Vol. 5 No. 1 (2026): March 2026
Publisher : Utan Kayu Publishins

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

To address the coordination between vehicle scheduling and warehouse operations in power logistics parks, this paper develops a bi-level programming model: the upper level optimizes supply chain vehicle scheduling, and the lower level optimizes warehouse inspection and inbound–outbound operations. An improved Carnivorous Plant Algorithm (ISCMA-CPA), integrating self-learning, Cauchy mutation, and mayfly reproduction strategies, is proposed to solve the model. Real-world data from nine vehicles and 45 material types are used for validation. Compared with benchmark algorithms (WOA, IWOA, GA, MA, CPA, AFSC), ISCMA-CPA achieves superior performance: at the upper level, average working time, waiting time, and travel distance are reduced by 35.3%, 75.0%, and 9.3%, respectively, and the objective value decreases by 0.9%; at the lower level, inspection time and path distance decrease by 14.4%, achieving the lowest objective value of 7276.96. The results demonstrate that the proposed bi-level model and algorithm effectively shorten operation time, reduce waiting and travel distances, and realize coordinated optimization of vehicle scheduling and warehouse operations. Overall, this study provides a practical optimization framework that enhances operational efficiency, supports intelligent decision-making, and promotes the green transformation of power material logistics.
A New Approach to Improve Reliability in Software-Based Networks amir fakoor saghih; Majid Estiri
International Journal of Advanced Science and Computer Applications Vol. 5 No. 2 (2026): September
Publisher : Utan Kayu Publishins

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47679/ijasca.v5i2.116

Abstract

The increase of new computing technologies, including big data, Internet of Things and cloud computing, has caused significant changes in the method of storing, collecting and transferring information and data. Along with these computing trends, new challenges such as network management and improvement, optimal use of resources and fast data transfer have also emerged. In order to overcome these challenges, software-based networks (SDN) are used as a desirable model for next-generation networks. One of the big challenges facing this type of network is choosing a safe path for data transmission on the network path; In such a way that it can improve the reliability of the path by choosing a suitable path between controllers and network switches with the lowest cost and delay. The purpose of this research is to choose the best and safest path for data transfer in software-based networks. For this purpose, using ant colony genetic algorithms and running them on a network graph with 20 nodes in MATLAB software, the cost, delay, and reliability components of each node in the network path were evaluated and compared. The results showed that by running these algorithms several times and considering the type of classification of transmitted packets in the network, the safest, least expensive, and shortest path was calculated and compared accurately, taking into account the delay, cost, and reliability constraints, and the optimal path between the origin and destination to the associated switches and controllers with the highest level of reliability was announced by the genetic algorithm.
Artificial Intelligence in Ocean Clean-Up: Deep Learning Approaches to Marine Litter Detection K Poorna Pushkala,; P Subbulakshmi
International Journal of Advanced Science and Computer Applications Vol. 5 No. 2 (2026): September
Publisher : Utan Kayu Publishins

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47679/ijasca.v5i2.117

Abstract

Marine litter contamination causes a tremendous environmental issue with a high influence on the consequences for ocean ecosystems and human societies. This study offers a concise overview of the impacts, potential solutions, and causes to address this complex problem with Artificial Intelligence. The sources of marine pollution encompass a wide range of human activities, including oil spills, chemical discharges, plastic waste, nutrient runoff, sewage disposal, and atmospheric deposition. These pollutants pose significant threats to marine life, biodiversity, and ecosystem health. While deep learning technologies have shown promise in various environmental applications, including pollution monitoring and management, their direct application to solving marine pollution is limited. Deep learning algorithms can be used to analyze images and video footage from drones or underwater cameras to identify and track plastic pollution. This study additionally provides debris analysis utilizing publicly available datasets generated by a few studies. The several approaches that are being considered can be applied to the creation and efficient management of litter in the future, preserving our ecology. Collaborative efforts between environmental scientists, engineers, and data scientists are crucial to developing robust and effective deep-learning solutions for marine pollution management.
Spatial domain enhancement techniques of x-ray medical images: comparative study kawther seaad
International Journal of Advanced Science and Computer Applications Vol. 5 No. 2 (2026): September
Publisher : Utan Kayu Publishins

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47679/ijasca.v5i2.125

Abstract

Medical scenes and images often display degradations caused by poor light and inappropriate angles. These deteriorations impact diagnostic tasks as well as visual effects. X-ray is the more common imaging clinical for checking out and healing the human inner parts. The X-ray images have particular challenges with low contrast, noise, and intensity. Enhancing the quality of medical images thus becomes necessary. The improvement techniques for X-ray images based on the spatial domain are present in this research. It includes the following techniques: gamma modification, balance enhancement of contrast, image invert/compliment, super-resolution, contrasting-limited adaptive histogram equalization, and improvement with spatial filtering. These approaches can help patients and doctors by precisely determining specific illnesses. Shortly, these procedures yield more accurate diagnoses and higher image quality by concluding images' better contrast, less noise, etc. Lastly, a thorough comparison of the methods involved is provided, along with a description of their benefits, drawbacks, and restrictions.