• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.2
• /
• pp.203-208
• /
• 2024

The convergence of deep learning and smart factory is drawing a lot of attentions from not only industrial but also academic circles. The objective of this article is to quantitatively review on deep learning and smart factory from 2010 to 2023. This research analyzed the 138 articles, extracted from the Core Collection of Web of Science, in terms of four dimensions such as the main trend in article publications, the main trend in article citations, the distribution of article publications by research area, and the keywords representing the main contents of published articles. The quantitative review results reveal the following four points: First, the article publications drastically grew from 2019 to 2022 in its annual trend. Second, the article citations have rapidly grown since 2018. Third, Engineering, Computer Science, and Telecommunications are the top 3 research areas composing the 138 articles. Fourth, it is the top 10 keywords such as 'deep', 'learning', 'smart', 'detection', factory', 'data', 'system', 'manufacturing', 'neural', and 'network' that represent the main contents of the 138 articles published from 2010 to 2023 in deep learning and smart factory. These findings revealed by this quantitative review will be significantly useful for deepening and widening relevant future research on deep learning and smart factory.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.5
• /
• pp.1369-1389
• /
• 2024

In the era of 6G, the rapid increase in communication data volume poses higher demands on traditional channel estimation techniques and those based on deep learning, especially when processing large-scale data as their computational load and real-time performance often fail to meet practical requirements. To overcome this bottleneck, this paper introduces quantum computing techniques, exploring for the first time the application of Quantum Generative Adversarial Networks (QGAN) to broadband channel estimation challenges. Although generative adversarial technology has been applied to channel estimation, obtaining instantaneous channel information remains a significant challenge. To address the issue of instantaneous channel estimation, this paper proposes an innovative QGAN with a dual-module design in the generator. The adversarial loss function and the Mean Squared Error (MSE) loss function are separately applied for the parameter updates of these two modules, facilitating the learning of statistical channel information and the generation of instantaneous channel details. Experimental results demonstrate the efficiency and accuracy of the proposed dual-module QGAN technique in channel estimation on the Pennylane quantum computing simulation platform. This research opens a new direction for physical layer techniques in wireless communication and offers expanded possibilities for the future development of wireless communication technologies.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.6
• /
• pp.1540-1561
• /
• 2024

This research proposes a novel approach for Tamil Handwritten Character Recognition (THCR) that combines feature selection and ensemble learning techniques. The Tamil script is complex and highly variable, requiring a robust and accurate recognition system. Feature selection is used to reduce dimensionality while preserving discriminative features, improving classification performance and reducing computational complexity. Several feature selection methods are compared, and individual classifiers (support vector machines, neural networks, and decision trees) are evaluated through extensive experiments. Ensemble learning techniques such as bagging, and boosting are employed to leverage the strengths of multiple classifiers and enhance recognition accuracy. The proposed approach is evaluated on the HP Labs Dataset, achieving an impressive 95.56% accuracy using an ensemble learning framework based on support vector machines. The dataset consists of 82,928 samples with 247 distinct classes, contributed by 500 participants from Tamil Nadu. It includes 40,000 characters with 500 user variations. The results surpass or rival existing methods, demonstrating the effectiveness of the approach. The research also offers insights for developing advanced recognition systems for other complex scripts. Future investigations could explore the integration of deep learning techniques and the extension of the proposed approach to other Indic scripts and languages, advancing the field of handwritten character recognition.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.4
• /
• pp.195-200
• /
• 2024

With the increase in urbanization and automobile demand, urban parking problems have emerged as a serious social issue. In response, research has been conducted to identify parking situations and provide efficient parking information to drivers by utilizing parking lot entry and exit data. This paper preprocesses entry and exit data based on public data to extract parking times and provides expected exit times using the mode value, allowing drivers to anticipate when a vehicle will leave the parking space at their desired parking time. Future research aims to improve the current system by using a real-time parking management system and enhance the accuracy and efficiency of parking space identification.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.24 no.4
• /
• pp.49-55
• /
• 2024

Code smells, used by Kent Beck, indicate potential quality issues and suggest the need for refactoring. This paper evaluates code smells in the LEA codebase, focusing on categorization and associated metrics. The research analyze LEA_core.c and LEA.cpp, highlighting differences in code quality and complexity. And metrics such as LOC, NOM, NOA, CYCLO, MAXNESTING, and FANOUT are used to assess size, complexity, coupling, encapsulation, inheritance, and cohesion. In the result of research, LEA_core.c is found to be more complex and challenging to maintain compared to LEA.cpp. In future work, we will develop automated tools for real-time code smell detection and refactoring suggestions

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.262-273
• /
• 2024

We provide a detailed analysis of the data processing and model training process for vulnerability classification using Transformer-based language models, especially sentence text-to-text transformers (ST5)-XXL and XLNet. The main purpose of this study is to compare the performance of the two models, identify the strengths and weaknesses of each, and determine the optimal learning rate to increase the efficiency and stability of model training. We performed data preprocessing, constructed and trained models, and evaluated performance based on data sets with various characteristics. We confirmed that the XLNet model showed excellent performance at learning rates of 1e-05 and 1e-04 and had a significantly lower loss value than the ST5-XXL model. This indicates that XLNet is more efficient for learning. Additionally, we confirmed in our study that learning rate has a significant impact on model performance. The results of the study highlight the usefulness of ST5-XXL and XLNet models in the task of classifying security vulnerabilities and highlight the importance of setting an appropriate learning rate. Future research should include more comprehensive analyzes using diverse data sets and additional models.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.7
• /
• pp.1929-1952
• /
• 2024

The development of drones is transforming society as a whole and playing a game-changing role in warfare. However, numerous problems pose threats to the lives and safety of people, and the counter-drone system lags behind the rapid development of drones. Most countries, including South Korea, have not established a reliable counter-drone system in response to the threat posed by numerous drones. Due to budget constraints in each country, an Analytic Hierarchy Process (AHP) analysis was conducted among a group of experts who have been involved in policymaking and research and development related to counter-drone systems. This analysis aimed to determine the priority of building a counter-drone system. Based on various research data, the counter-drone system was analyzed in three stages: detection/identification, governance, and response. The hierarchical design mapped out the existing researched counter-drone technology into a hierarchical model consisting of 31 evaluation criteria. The conclusion provided a roadmap for establishing a counter-drone system based on the prioritization of each element and considering factors such as technological advancement, outlining directions for development in each field.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.9
• /
• pp.2564-2588
• /
• 2024

Due to COVID19 pandemic, most of educational institutions and schools changed the traditional way of teaching to online teaching and learning using well-known Learning Management Systems (LMS) such as Moodle, Canvas, Blackboard, etc. Accordingly, LMS started to generate a large data related to students' characteristics and achievements and other course-related information. This makes it difficult to teachers to monitor students' behaviour and performance. Therefore, a need to support teachers with a tool alerting student who might be in risk based on their recorded activities and achievements in adopted LMS in the school. This paper focuses on the benefits of using recorded data in LMS platforms, specifically Moodle, to predict students' performance by analysing their behavioural data and engagement activities using data mining techniques. As part of the overall process, this study encountered the task of extracting and selecting relevant data features for predicting performance, along with designing the framework and choosing appropriate machine learning techniques. The collected data underwent pre-processing operations to remove random partitions, empty values, duplicates, and code the data. Different machine learning techniques, including k-NN, TREE, Ensembled Tree, SVM, and MLPNNs were applied to the processed data. The results showed that the MLPNNs technique outperformed other classification techniques, achieving a classification accuracy of 93%, while SVM and k-NN achieved 90% and 87% respectively. This indicates the possibility for future research to investigate incorporating other neural network methods for categorizing students using data from LMS.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.33-46
• /
• 2024

As YouTube is rapidly growing as an information platform, we investigated practical impacts of YouTube knowledge content and creator characteristics on viewer satisfaction and purchase intention. In so doing, an empirical survey was conducted among the viewers of <Chekgrim>, one of representative book YouTube channels in Korea. A total of 641 valid samples were analyzed. This study aims to understand the impact of knowledge contents on YouTube, and creator characteristics on viewer satisfaction and purchase intention. Specifically, for the study, content characteristics were divided into three sub-factors: entertainment, information, and interactivity, and the creator characteristics were divided into two sub-factors: intimacy and professionalism. Viewing satisfaction and purchase intention were set as dependent variables. The results of various analyses confirm that creator characteristics have direct and indirect effects on viewers' purchase intentions, and in particular, intimacy has the greatest influence on purchase intentions. This is expected to be a meaningful empirical analysis for future influencer marketing strategies and effective communications between content creators and consumers.

• Journal of the Korea Computer Graphics Society
• /
• v.17 no.1
• /
• pp.9-16
• /
• 2011

In this paper, we describe the development of a system for generating a 3-dimensional human face and predicting it's appearance as it ages over subsequent years using 3D scanned facial data and photo images. It is composed of 3-dimensional texture mapping functions, a facial definition parameter input tool, and 3-dimensional facial prediction algorithms. With the texture mapping functions, we can generate a new model of a given face at a specified age using a scanned facial model and photo images. The texture mapping is done using three photo images - a front and two side images of a face. The facial definition parameter input tool is a user interface necessary for texture mapping and used for matching facial feature points between photo images and a 3D scanned facial model in order to obtain material values in high resolution. We have calculated material values for future facial models and predicted future facial models in high resolution with a statistical analysis using 100 scanned facial models.