• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.316-326
• /
• 2022

The prompt development in the field of video is the outbreak of online services which replaces the television media within a shorter period in gaining popularity. The online videos are encouraged more in use due to the captions displayed along with the scenes for better understandability. Not only entertainment media but other marketing companies and organizations are utilizing videos along with captions for their product promotions. The need for captions is enabled for its usage in many ways for hearing impaired and non-native people. Research is continued in an automatic display of the appropriate messages for the videos uploaded in shows, movies, educational videos, online classes, websites, etc. This paper focuses on two concerns namely the first part dealing with the machine learning method for preprocessing the videos into frames and resizing, the resized frames are classified into multiple actions after feature extraction. For the feature extraction statistical method, GLCM and Hu moments are used. The second part deals with the deep learning method where the CNN architecture is used to acquire the results. Finally both the results are compared to find the best accuracy where CNN proves to give top accuracy of 96.10% in classification.

• International Journal of Computer Science & Network Security
• /
• v.23 no.4
• /
• pp.146-150
• /
• 2023

In areas where water is scarce, water management is critical. This has an impact on agriculture, as a significant amount of water is used for that purpose. Electronic measurement equipment are essential for regulating and storing soil data. As a result, research has been conducted to manage water usage in the irrigation process. Many equipment for managing soil fertility systems are extremely expensive, making this type of system unaffordable for small farmers. These soil fertility control systems are simple to implement because to recent improvements in IoT technology. The goal of this project is to develop a new methodology for smart irrigation systems. The parameters required to maintain water amount and quality, soil properties, and weather conditions are determined by this IoT-based Smart irrigation System. The system also assists in sending warning signals to the consumer when an error occurs in determining the percentage of moisture in the soil specified for the crop, as well as an alert message when the fertility of the soil changes, since many workers, particularly in big projects, find it extremely difficult to check the soil on a daily basis and operate agricultural devices such as sprinkler and soil fertilizing devices.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.3
• /
• pp.633-652
• /
• 2024

Software testing is an important phase as it ensures the software quality. The software testing process comprises of three steps: generation, execution, and evaluation of test cases. Literature claims the usage of single and multiple 'Unified Modeling Language' (UML) diagrams to generate test cases. Using multiple UML diagrams increases test case coverage. However, the existing approaches show limitations in test case generation from UML diagrams. Therefore, in this research study, we propose an approach to generate the test cases using UML State Chart Diagram (SCD), Activity Diagram (AD), and Sequence Diagram (SD). The proposed approach transforms UML diagrams into intermediate forms: SCD Graph, AD Graph, and SD Graph respectively. Furthermore, by integrating these three graphs, a System Testing Graph (STG) is formed. Finally, test cases are identified from STG by using a traversal algorithm such as Depth First Search (DFS) that is an optimization method. The results show that the proposed approach is better compared to existing approaches in terms of coverage and performance. Moreover, the generated test cases have the ability to detect faults at the unit level, integration, and system level testing.

• International Journal of Computer Science & Network Security
• /
• v.24 no.7
• /
• pp.59-62
• /
• 2024

Non-fungible tokens (NFTs) are interchangeable rights to digital assets such as art, in-game items, collectibles or music, etc. NFTs have the potential to be infinitely useful in many industries by increasing security and processing costs for transactions and providing a new platform for the gigeconomy to work through. Its markets have grown fast and significantly since early 2021. We investigate the uses of NFTs and research the facts and figures on the usage of NFTs supporting websites. Using daily data between 2019 to 2021. NFTs took the world by storm in 2021, bringing forth a digital art revolution while becoming one of the fastest-growing asset classes of the year. While the NFTs market has been growing at a rapid pace, many are still wary of entering it because of the theoretical insanity around its worth. NFTs have been out there for quite some time and this trend doesn't plan to go any further. NFTs services have many practical use cases and their potential will only grow over time. While celebrities dive into this marketplace to maintain their onlinepresence andincrease their Net worth.

• Transactions on Semiconductor Engineering
• /
• v.2 no.3
• /
• pp.13-18
• /
• 2024

This paper proposes a circuit utilizing auto zero technology to minimize offset and enhance accuracy in the reference generator and comparator. As evidence, a comparison between pre and post auto zero usage revealed a reduction of approximately 90% in standard deviation. The proposed circuit was implemented using a 55nm CMOS process, with an input frequency of 781.2 Hz. It achieves an Effective Number of Bits (ENOB) of 8.01 bits and a Signal-to-Noise Distortion Ratio (SNDR) of 49.98 dB.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.837-852
• /
• 2021

Recurrent neural network (RNN) architectures have been used for language modeling (LM) tasks that require learning long-range word or character sequences. However, the RNN architecture is still suffered from unstable gradients on long-range sequences. To address the issue of long-range sequences, an attention mechanism has been used, showing state-of-the-art (SOTA) performance in all LM tasks. A differentiable neural computer (DNC) is a deep learning architecture using an attention mechanism. The DNC architecture is a neural network augmented with a content-addressable external memory. However, in the write operation, some information unrelated to the input word remains in memory. Moreover, DNCs have been found to perform poorly with low numbers of weight parameters. Therefore, we propose a robust memory deallocation method using a limited retention vector. The limited retention vector determines whether the network increases or decreases its usage of information in external memory according to a threshold. We experimentally evaluate the robustness of a DNC implementing the proposed approach according to the size of the controller and external memory on the enwik8 LM task. When we decreased the number of weight parameters by 32.47%, the proposed DNC showed a low bits-per-character (BPC) degradation of 4.30%, demonstrating the effectiveness of our approach in language modeling tasks.

• Journal of Internet Computing and Services
• /
• v.13 no.6
• /
• pp.41-53
• /
• 2012

Open educational resources(OER) enable the spread of mutual information exchange and provide advantages to both their users and institutions, such as reducing costs, improving content quality, and establishing relationships. The recent research on OER was about their connection to formal education, copyright trends, and corporate e-learning. There have been very few studies, however, on the utilization of OER and on the problems related to their practical use. Thus, this study was conducted for the purposes of analyzing the status of OER usage in education-related institutions and of providing suggestions for institution operation based on the analysis results, to promote the use of OER. A survey was conducted among more than 200 institutions in Asia, and the survey results showed that 'images and visual materials' are the most commonly used materials in Asia, and that the factors barring OER usage in the said region are 'lack of awareness', 'lack of skills', 'the absence of a reward system', and poor cooperation in participation. To promote OER usage, each institution should provide training courses about awareness, utilization skills, and copyrights. There is also a need to provide support for the establishment of reward systems and environments for OER usage. Finally, more active participation is required for inter-agency cooperation in OER sharing.

• Journal of the Korea Computer Industry Society
• /
• v.8 no.1
• /
• pp.9-16
• /
• 2007

In this study, the change of neutron detection can be use the basic data of asphalt content detector under the influence of the jurisdiction and usage of radioisotopes are limited of $100[{\mu}Ci]$ or less. To obtain neutron detector's properties using design materials in first step phase, the change of neutron detection is to be calculated how can be increase or decrease due to the change of asphalt content, also it look over the change results which is installed absorber(cadmium plate) around moderator(polyethylene) using MCNP Code.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06b
• /
• pp.336-337
• /
• 2011

The popularity of general purpose GPU（GPGPU）makes the CPU-GPGPU heterogeneous architecture normal. Therefore, tradeoff the usage of CPU and GPGPU becomes a way to improve performance of programs. In this work, we exploit the properties of the CPU-GPGPU heterogeneous architecture and use them to accelerate the content based chunking operation of deduplication. We built a prototype system which is able to coordinate CPU and GPGPU to chunk file and has been proven to have a better performance compared to using either CPU or GPGPU alone.

• Proceedings of the Korea Society of Information Technology Applications Conference
• /
• 2005.11a
• /
• pp.77-80
• /
• 2005

Wireless sensor networks(WSN) technology has various applications such as surveillance and information gathering in the uncontrollable area of human. One of major issues in WSN is the research for reducing the energy consumption and reliability of data. A system with forward error correction(FEC) can provide an objective reliability while using less transmission power than a system without FEC. In this paper, we propose to use LDPC codes of various code rate(0.53, 0.81, 0.91) for FEC for WSN. Also, we considered node-to-node interference in addition to AWGN channel. The proposed system has not only high reliable data transmission at low SNR, but also reduced transmission power usage.