• International Journal of Computer Science & Network Security
• /
• v.24 no.2
• /
• pp.158-168
• /
• 2024

There is hardly any person in modern times who has not taken soft drinks instead of drinking water. The rate of people taking soft drinks being surprisingly high, researchers around the world have cautioned from time to time that these drinks lead to weight gain, raise the risk of non-communicable diseases and so on. Therefore, in this work an image-based tool is developed to monitor the nutritional information of soft drinks by using deep convolutional neural network with transfer learning. At first, visual saliency, mean shift segmentation, thresholding and noise reduction technique, collectively known as 'pre-processing' are adopted to extract the location of drinks region. After removing backgrounds and segment out only the desired area from image, we impose Discrete Wavelength Transform (DWT) based resolution enhancement technique is applied to improve the quality of image. After that, transfer learning model is employed for the classification of drinks. Finally, nutrition value of each drink is estimated using Bag-of-Feature (BoF) based classification and Euclidean distance-based ratio calculation technique. To achieve this, a dataset is built with ten most consumed soft drinks in Bangladesh. These images were collected from imageNet dataset as well as internet and proposed method confirms that it has the ability to detect and recognize different types of drinks with an accuracy of 98.51%.

• International Journal of Computer Science & Network Security
• /
• v.24 no.3
• /
• pp.59-70
• /
• 2024

Background: The COVID-19 pandemic (the form of coronaviruses) developed at the end of 2019 and spread rapidly to almost every corner of the world. It has infected around 25,334,339 of the world population by the end of September 1, 2020 [1] . It has been spreading ever since, and the peak specific to every country has been rising and falling and does not seem to be over yet. Currently, the conventional RT-PCR testing is required to detect COVID-19, but the alternative method for data archiving purposes is certainly another choice for public departments to make. Researchers are trying to use medical images such as X-ray and Computed Tomography (CT) to easily diagnose the virus with the aid of Artificial Intelligence (AI)-based software. Method: This review paper provides an investigation of a newly emerging machine-learning method used to detect COVID-19 from X-ray images instead of using other methods of tests performed by medical experts. The facilities of computer vision enable us to develop an automated model that has clinical abilities of early detection of the disease. We have explored the researchers' focus on the modalities, images of datasets for use by the machine learning methods, and output metrics used to test the research in this field. Finally, the paper concludes by referring to the key problems posed by identifying COVID-19 using machine learning and future work studies. Result: This review's findings can be useful for public and private sectors to utilize the X-ray images and deployment of resources before the pandemic can reach its peaks, enabling the healthcare system with cushion time to bear the impact of the unfavorable circumstances of the pandemic is sure to cause

• International Journal of Computer Science & Network Security
• /
• v.24 no.1
• /
• pp.133-139
• /
• 2024

The educational situation, which resulted from the announced self-isolation regime, intensified the forced decisions on the organization of the distance educational process. The study is topical because of the provision of distance learning based on the experience of Kyiv National University of Culture and Arts. The study was conducted in three stages. Systemic, socio-communicative, competence approaches, sociological methods (questionnaires and interviews) were chosen as methodological tools of the research. The results of a survey of teachers and entrants to higher education institutions on the topic "Using social networks and digital platforms for online classes under the conditions of quarantine restrictions" allowed to scientifically substantiate the need for deeper knowledge of such tools as Google Meet (79%), Zoom (13.78%) and Google Classroom (11.62%), which are preferred by entrants. Almost a third of entrants (34.26%) noted the lack of scientific and methodological support for learning the subjects. The study showed high efficiency of messengers in distance education. The study found that in the process of organizing communication in the student-teacher system, it is necessary to take into account the priority of Telegram on the basis of which it is necessary to implement a chatbot for convenient and effective exchange of information about the educational process. Further research should focus on the effectiveness of the use of Telegram. The effectiveness of using chatbots should also be considered. Chatbots can be used to automate routine components of the learning process.

• Convergence Security Journal
• /
• v.23 no.4
• /
• pp.122-129
• /
• 2023

The paradigm of warfare is undergoing a revolutionary transformation due to the advancements in technology brought forth by the Fourth Industrial Revolution. Specifically, the U.S. military has introduced the concept of mosaic warfare as a means of military innovation, aiming to integrate diverse resources and capabilities, including various weapons, platforms, information systems, and artificial intelligence. This integration enhances the ability to conduct agile operations and respond effectively to dynamic situations. The incorporation of mosaic warfare could facilitate efficient and rapid command and control by integrating AI staff with human commanders. Ukrainian military operations have already employed mosaic warfare in response to Russian aggression. This paper focuses on the mosaic war fare concept, which is being proposed as a model for future warfare, and suggests the strategy for introducing the Korean mosaic warfare concept in light of the changing battlefield paradigm.

• Journal of Platform Technology
• /
• v.11 no.5
• /
• pp.37-48
• /
• 2023

Since the announcement of the Financial Services Commission's 'Token Securities Issuance and Distribution System Improvement Plan' in February 2023, financial institutions, securities firms, and blockchain companies have been actively considering implementing IT platforms, but they are facing difficulties in selecting IT platforms for token securities because related legal regulations have not yet been clearly established. As a result, the need for rational and systematic criteria for the selection of blockchain-based token securities IT platforms has emerged, and this study explores and evaluates the key factors of token securities IT platform selection. Four factors were identified as the top-level factors, including 'maturity of the platform', 'operation and management of the platform', 'cost of introducing and maintaining the platform', and 'regulatory compliance for token securities', and 17 factors were identified as sub-level factors, including 'diversity', 'user authentication management', 'Adoption Costs', and 'financial regulations'. Among the 17 sub-factors, 'government financial regulation' and 'personal information protection' are selected as important factors, and the results of this study can help related organizations and financial companies make strategic decisions by providing systematic decision-making criteria for selecting token securities IT platforms.

• Convergence Security Journal
• /
• v.21 no.4
• /
• pp.77-85
• /
• 2021

Cyber protection is an activity that protects the information systems we operate from cyber attacks and threats. To know the level of protection of the currently operating cyber protection system, it is necessary to update the current state of attack technology by reflecting the constantly evolving cyber threats and to analyze whether it is possible to respond with the protection function. Therefore, in this paper, we analyze the relationship between the attack procedures and defense types of the cyber kill chain with the defense technology(Mitigation ID) of MITRE and present the cyber protection level for each military unit type with a focus on defensive cyber activities. In the future, it is expected that the level of cyber protection will be improved through real-time analysis of the response capabilities of cyber protection systems operating in the defense sector to visualize the level of protection for each unit, investigate unknown cyber threats, and actively complement vulnerabilities.

• International Journal of Computer Science & Network Security
• /
• v.24 no.10
• /
• pp.1-16
• /
• 2024

Due to its complexity and high diagnosis and treatment costs, heart attack (HA) is the top cause of death globally. Heart failure's widespread effect and high morbidity and death rates make accurate and fast prognosis and diagnosis crucial. Due to the complexity of medical data, early and accurate prediction of HA is difficult. Healthcare providers must evaluate data quickly and accurately to intervene. This novel hybrid approach predicts HA using Long Short-Term Memory (LSTM) networks, Deep belief networks (DBNs) with attention mechanism, and robust data mining to fill this essential gap. HA is predicted using Kaggle, PhysioNet, and UCI datasets. Wearable sensor data, ECG signals, and demographic and clinical data provide a solid analytical base. To maintain consistency, ECG signals are normalized and segmented after thorough cleaning to remove missing values and noise. Feature extraction employs complex approaches like Principal Component Analysis (PCA) and Autoencoders to pick time-domain (MNN, SDNN, RMSSD, PNN50) and frequency-domain (PSD at VLF, LF, HF bands) characteristics. The hybrid model architecture uses LSTM networks for sequence learning and DBNs for feature representation and selection to create a robust and comprehensive prediction model. Accuracy, precision, recall, F1-score, and ROC-AUC are measured after cross-entropy loss and SGD optimization. The LSTM-DBN model outperforms predictive methods in accuracy, sensitivity, and specificity. The findings show that several data sources and powerful algorithms can improve heart attack predictions. The proposed architecture performed well on many datasets, with an accuracy rate of 96.00%, sensitivity of 98%, AUC of 0.98, and F1-score of 0.97. High performance proves this system's dependability. Moreover, the proposed approach is outperformed compared to state-of-the-art systems.

• Journal of the Korean Society for information Management
• /
• v.30 no.3
• /
• pp.207-228
• /
• 2013

The purpose of this study is to reveal the influence of the expectation and perceived performance of the online science & technology information service quality on user satisfaction and royalty. To achieve this goal, we use the NDSLQual model to measure the quality of NDSL service. The results were as follows: First, among seven expectation factors, four factors (reliability, convenience, system usability and information quality) had a positive effect on the user satisfaction. Second, while service recovery had a negative effect on the royalty, the other six factors (reliability, convenience, system usability, responsiveness, security and information quality) had a positive effect on the royalty. Third, among seven perceived performance factors, three factors (reliability, convenience and information quality) had a positive effect on the user satisfaction. Fourth, among seven perceived performance factors, three factors (reliability, convenience and information quality) had a positive effect on the royalty. As a result, information quality, reliability and convenience of the expectation and perceived performance are common factors influencing user satisfaction and royalty.

• Journal of Digital Convergence
• /
• v.16 no.1
• /
• pp.217-229
• /
• 2018

Electronic Health Record (EHR) systems are widely adopted worldwide in hospitals for generating and exchanging records of patient information. Recent developments are moving towards implementing interoperable EHR systems that enable information to be shared seamlessly across healthcare organizations. In this context, this paper explores the factors that cause medical information privacy concerns, identifies how people react to privacy invasion and what their perceptions are towards the acceptance of the EHR system. Interviews were conducted to draw a grounded theory on medical information privacy concerns in the use of EHRs. Medical information privacy concerns are caused by perceived sensitivity of medical information and the weaknesses in security technologies. Trust in medical professionals, medical institutions and technologies plays an important role in determining people's reaction to privacy invasion and their perceptions on the use of EHRs.

• Journal of KIISE:Information Networking
• /
• v.35 no.6
• /
• pp.474-481
• /
• 2008

Scanning worm increases network traffic load and result in severe network congestion because it is a self-replicating worm and send copies of itself to a number of hosts through the Internet. So an early detection system which can automatically detect scanning worms is needed to protect network from those attacks. Although many studies are conducted to detect scanning worms, most of them are focusing on the method using packet header information. The method using packet header information has long detection delay since it must examine the header information of all packets entering or leaving the network. Therefore we propose an algorithm to detect scanning worms using network traffic characteristics such as variance of traffic volume, differentiated traffic volume, mean of differentiated traffic volume, and product of mean traffic volume and mean of differentiated traffic volume. We verified the proposed algorithm by analyzing the normal traffic captured in the real network and the worm traffic generated by simulator. The proposed algorithm can detect CodeRed and Slammer which are not detected by existing algorithm. In addition, all worms were detected in early stage: Slammer was detected in 4 seconds and CodeRed and Witty were detected in 11 seconds.