• Journal of Internet Computing and Services
• /
• v.22 no.1
• /
• pp.23-30
• /
• 2021

This paper proposes a noise-tolerant image classification system using multiple autoencoders. The development of deep learning technology has dramatically improved the performance of image classifiers. However, if the images are contaminated by noise, the performance degrades rapidly. Noise added to the image is inevitably generated in the process of obtaining and transmitting the image. Therefore, in order to use the classifier in a real environment, we have to deal with the noise. On the other hand, the autoencoder is an artificial neural network model that is trained to have similar input and output values. If the input data is similar to the training data, the error between the input data and output data of the autoencoder will be small. However, if the input data is not similar to the training data, the error will be large. The proposed system uses the relationship between the input data and the output data of the autoencoder, and it has two phases to classify the images. In the first phase, the classes with the highest likelihood of classification are selected and subject to the procedure again in the second phase. For the performance analysis of the proposed system, classification accuracy was tested on a Gaussian noise-contaminated MNIST dataset. As a result of the experiment, it was confirmed that the proposed system in the noisy environment has higher accuracy than the CNN-based classification technique.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.21 no.3
• /
• pp.183-191
• /
• 2021

Non-intrusive load monitoring is a technology that can be used for predicting and classifying the type of appliances through real-time monitoring of user power consumption, and it has recently got interested as a means of energy-saving. In this paper, we propose a system for classifying appliances from user consumption data by combining GAF(Gramian angular field) technique that can be used for converting one-dimensional data to the two-dimensional matrix with convolutional neural networks. We use REDD(residential energy disaggregation dataset) that is the public appliances power data and confirm the classification accuracy of the GASF(Gramian angular summation field) and GADF(Gramian angular difference field). Simulation results show that both models showed 94% accuracy on appliances with binary-state(on/off) and that GASF showed 93.5% accuracy that is 3% higher than GADF on appliances with multi-state. In later studies, we plan to increase the dataset and optimize the model to improve accuracy and speed.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.2
• /
• pp.83-88
• /
• 2022

The purpose of this study is to present an analysis and implications for the metaverse-based virtual real estate transaction service. Through blockchain-based technology and metaverse, the world we live in is expanding naturally. Therefore, changes in the environment and perceptions of market participants are also very important factors. The concept and thinking about the existing asset value change and investment are also changing. This means that you can generate profits through value and investment in intangible assets. The service user aspect is a case of investing in the future value of virtual real estate that if more users participate rather than the present value, the principle of supply and demand will be applied to increase the number of consumers and the price will naturally rise according to the principle of scarcity. The service provider provides a technical platform for the service to directly transact the portion of the virtual area considered of interest directly through the virtual real estate purchase business. As the number of participants increases as well as funds and transaction fees, various revenue models such as advertisements can be discovered and provided. It plays the role of providing jobs and information through new services. As a stakeholder, governments can exploit the emergence of new technologies and products to create people and services and secure economic benefits. Of course, various institutional supports should be provided so that new services can settle in the market while mitigating risk factors. This study is meaningful in that it contributes to the establishment of a domestic metaverse-based environment and related research and is utilized in the study of virtual space real estate services.

• Journal of Internet Computing and Services
• /
• v.23 no.5
• /
• pp.79-85
• /
• 2022

Anomaly detection is a method to detect and block abnormal data flows in general users' data sets. The previously known method is a method of detecting and defending an attack based on a signature using the signature of an already known attack. This has the advantage of a low false positive rate, but the problem is that it is very vulnerable to a zero-day vulnerability attack or a modified attack. However, in the case of anomaly detection, there is a disadvantage that the false positive rate is high, but it has the advantage of being able to identify, detect, and block zero-day vulnerability attacks or modified attacks, so related studies are being actively conducted. In this study, we want to deal with these anomaly detection mechanisms, and we propose a new mechanism that performs both anomaly detection and classification while supplementing the high false positive rate mentioned above. In this study, the experiment was conducted with five configurations considering the characteristics of various algorithms. As a result, the model showing the best accuracy was proposed as the result of this study. After detecting an attack by applying the Extra Tree and Three-layer ANN at the same time, the attack type is classified using the Extra Tree for the classified attack data. In this study, verification was performed on the NSL-KDD data set, and the accuracy was 99.8%, 99.1%, 98.9%, 98.7%, and 97.9% for Normal, Dos, Probe, U2R, and R2L, respectively. This configuration showed superior performance compared to other models.

• Journal of Internet Computing and Services
• /
• v.23 no.4
• /
• pp.45-55
• /
• 2022

The size of the cryptocurrency market is growing. For example, market capitalization of bitcoin exceeded 500 trillion won. Accordingly, many studies have been conducted to predict the price of cryptocurrency, and most of them have similar methodology of predicting stock prices. However, unlike stock price predictions, machine learning become best model in cryptocurrency price predictions, conceptually cryptocurrency has no passive income from ownership, and statistically, cryptocurrency has at least three times higher liquidity than stocks. Thats why we argue that a methodology different from stock price prediction should be applied to cryptocurrency price prediction studies. We propose Reverse Walk-forward Validation (RWFV), which modifies Walk-forward Validation (WFV). Unlike WFV, RWFV measures accuracy for Validation by pinning the Validation dataset directly in front of the Test dataset in time series, and gradually increasing the size of the Training dataset in front of it in time series. Train data were cut according to the size of the Train dataset with the highest accuracy among all measured Validation accuracy, and then combined with Validation data to measure the accuracy of the Test data. Logistic regression analysis and Support Vector Machine (SVM) were used as the analysis model, and various algorithms and parameters such as L1, L2, rbf, and poly were applied for the reliability of our proposed RWFV. As a result, it was confirmed that all analysis models showed improved accuracy compared to existing studies, and on average, the accuracy increased by 1.23%p. This is a significant improvement in accuracy, given that most of the accuracy of cryptocurrency price prediction remains between 50% and 60% through previous studies.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.3
• /
• pp.1100-1118
• /
• 2021

In a wide range of ML applications, the training data contains privacy-sensitive information that should be kept secure. Training the ML systems by privacy-sensitive data makes the ML model inherent to the data. As the structure of the model has been fine-tuned by training data, the model can be abused for accessing the data by the estimation in a reverse process called model inversion attack (MIA). Although, MIA has been applied to shallow neural network models of recognizers in literature and its threat in privacy violation has been approved, in the case of a deep learning (DL) model, its efficiency was under question. It was due to the complexity of a DL model structure, big number of DL model parameters, the huge size of training data, big number of registered users to a DL model and thereof big number of class labels. This research work first analyses the possibility of MIA on a deep learning model of a recognition system, namely a face recognizer. Second, despite the conventional MIA under the white box scenario of having partial access to the users' non-sensitive information in addition to the model structure, the MIA is implemented on a deep face recognition system by just having the model structure and parameters but not any user information. In this aspect, it is under a semi-white box scenario or in other words a gray-box scenario. The experimental results in targeting five registered users of a CNN-based face recognition system approve the possibility of regeneration of users' face images even for a deep model by MIA under a gray box scenario. Although, for some images the evaluation recognition score is low and the generated images are not easily recognizable, but for some other images the score is high and facial features of the targeted identities are observable. The objective and subjective evaluations demonstrate that privacy cyber-attack by MIA on a deep recognition system not only is feasible but also is a serious threat with increasing alert state in the future as there is considerable potential for integration more advanced ML techniques to MIA.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.23 no.1
• /
• pp.171-176
• /
• 2023

The purpose of this study is to analyze the introduction and use cases of Metaverse in the financial sector to learn lessons and implications. Let's take a look. The era of the metaverse is coming. The financial sector is pioneering the blue ocean market in a new era and working with the MZ generation. In order to expand contact points, we are very interested in the new business model, Metaverse, and are actively engaged in research and development. appear to be participating. In the case of finance, information is efficiently transmitted through metaverse, and customers It is predicted that the convenience of customers will be greatly improved by making it possible to use convenient services without visiting a branch. Additionally, by utilizing technologies such as AR and VR, we are trying to provide services linked to the metaverse in earnest. In addition, new financial services such as non-face-to-face asset management consulting services and brokerage services for funds through Metaverse Business models are also expected to be created. It is still in its infancy, and it is currently in its infancy, Metaverse is being used for educational purposes.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.22 no.3
• /
• pp.193-200
• /
• 2022

In this study, the finite-failure NHPP software reliability model was applied to the software development model based on the Weibull lifetime distribution (Goel-Okumoto, Rayleigh, Type-2 Gumbe), which is widely used in the software reliability field, and then the cost attributes were compared and evaluated. For this study, failure time data detected during normal operation of the software system were collected and used, the most-likelihood estimation (MLE) method was applied to the parameter estimation of the proposed model, and the calculation of the nonlinear equation was solved using the binary method. As a result, first, in the software development model, when the cost of testing per unit time and the cost of removing a single defect increased, the cost increased but the release time did not change, and when the cost of repairing failures detected during normal system operation increased, the cost increased and the release time was also delayed. Second, as a result of comprehensive comparative analysis of the proposed models, it was found that the Type-2 Gumble model was the most efficient model because the development cost was lower and the release time point was relatively faster than the Rayleigh model and the Goel-Okumoto basic model. Third, through this study, the development cost properties of the Weibull distribution model were newly evaluated, and the analyzed data is expected to be utilized as design data that enables software developers to explore the attributes of development cost and release time.

• Journal of Internet Computing and Services
• /
• v.24 no.4
• /
• pp.127-135
• /
• 2023

This research paper explores the application of FinBERT, a variational BERT-based model pre-trained on financial domain, for sentiment analysis in the financial domain while focusing on the process of identifying suitable training data and hyperparameters. Our goal is to offer a comprehensive guide on effectively utilizing the FinBERT model for accurate sentiment analysis by employing various datasets and fine-tuning hyperparameters. We outline the architecture and workflow of the proposed approach for fine-tuning the FinBERT model in this study, emphasizing the performance of various datasets and hyperparameters for sentiment analysis tasks. Additionally, we verify the reliability of GPT-3 as a suitable annotator by using it for sentiment labeling tasks. Our results show that the fine-tuned FinBERT model excels across a range of datasets and that the optimal combination is a learning rate of 5e-5 and a batch size of 64, which perform consistently well across all datasets. Furthermore, based on the significant performance improvement of the FinBERT model with our Twitter data in general domain compared to our news data in general domain, we also express uncertainty about the model being further pre-trained only on financial news data. We simplify the complex process of determining the optimal approach to the FinBERT model and provide guidelines for selecting additional training datasets and hyperparameters within the fine-tuning process of financial sentiment analysis models.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.29 no.4D
• /
• pp.433-441
• /
• 2009

In the coming ubiquitous society, the importance of developing advanced public transportation systems (APTS) corresponding to individuals' needs and useful in their daily life is profound. In these regards, the study proposed new APTS services: Free internet access service and On-board real time traffic information service in public modes. A stated preference (SP) survey was performed to investigate individual's preference and willingness-to-pay (WTP) for the proposed APTS services. Multinomial logit models (MNL) incorporating the heterogeneity of respondents were developed to analyze individuals' preference and the difference of WTP. Some results of the study showed that the respondents' preferences were significantly different by in-vehicle travel times (30 min, 60 min) and their socioeconomic background. More respondents prefer new APTS services when invehicle travel time takes longer. For the housewife and self-employed group, the mean WTP for on-board realtime traffic information was higher than that of free internet access services, while for the company employees and students group, the mean WTP was similar in both services.