• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.7
• /
• pp.1794-1806
• /
• 2023

This study presents a method for capturing photographs of users as input and converting them into 2D character animation sprites using a generative adversarial network-based artificial intelligence network. Traditionally, 2D character animations have been created by manually creating an entire sequence of sprite images, which incurs high development costs. To address this issue, this study proposes a technique that combines motion videos and sample 2D images. In the 2D sprite generation process that uses the proposed technique, a sequence of images is extracted from real-life images captured by the user, and these are combined with character images from within the game. Our research aims to leverage cutting-edge deep learning-based image manipulation techniques, such as the GAN-based motion transfer network (impersonator) and background noise removal (U² -Net), to generate a sequence of animation sprites from a single image. The proposed technique enables the creation of diverse animations and motions just one image. By utilizing these advancements, we focus on enhancing productivity in the game and animation industry through improved efficiency and streamlined production processes. By employing state-of-the-art techniques, our research enables the generation of 2D sprite images with various motions, offering significant potential for boosting productivity and creativity in the industry.

• Smart Structures and Systems
• /
• v.32 no.1
• /
• pp.61-81
• /
• 2023

This study presents an ensemble learning based Bayesian model updating approach for structural damage diagnosis. In the developed framework, the structure is initially decomposed into a set of substructures. The autoregressive moving average (ARMAX) model is established first for structural damage localization based structural motion equation. The wavelet packet decomposition is utilized to extract the damage-sensitive node energy in different frequency bands for constructing structural surrogate models. Four methods, including Kriging predictor (KRG), radial basis function neural network (RBFNN), support vector regression (SVR), and multivariate adaptive regression splines (MARS), are selected as candidate structural surrogate models. These models are then resampled by bootstrapping and combined to obtain an ensemble model by probabilistic ensemble. Meanwhile, the maximum entropy principal is adopted to search for new design points for sample space updating, yielding a more robust ensemble model. Through the iterations, a framework of surrogate ensemble learning based model updating with high model construction efficiency and accuracy is proposed. The specificities of the method are discussed and investigated in a case study.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.9
• /
• pp.2334-2347
• /
• 2023

Metaverse services generate text data, data of ubiquitous computing, in real-time to analyze user emotions. Analysis of user emotions is an important task in metaverse services. This study aims to classify user sentiments using deep learning and pre-trained language models based on the transformer structure. Previous studies collected data from a single platform, whereas the current study incorporated the review data as "Metaverse" keyword from the YouTube and Google Play Store platforms for general utilization. As a result, the Bidirectional Encoder Representations from Transformers (BERT) and Robustly optimized BERT approach (RoBERTa) models using the soft voting mechanism achieved a highest accuracy of 88.57%. In addition, the area under the curve (AUC) score of the ensemble model comprising RoBERTa, BERT, and A Lite BERT (ALBERT) was 0.9458. The results demonstrate that the ensemble combined with the RoBERTa model exhibits good performance. Therefore, the RoBERTa model can be applied on platforms that provide metaverse services. The findings contribute to the advancement of natural language processing techniques in metaverse services, which are increasingly important in digital platforms and virtual environments. Overall, this study provides empirical evidence that sentiment analysis using deep learning and pre-trained language models is a promising approach to improving user experiences in metaverse services.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.63-73
• /
• 2023

This study explores modern portfolio theory by integrating the Black-Litterman portfolio with time-series clustering, specificially emphasizing K-shape clustering methodology. K-shape clustering enables grouping time-series data effectively, enhancing the ability to plan and manage investments in stock markets when combined with the Black-Litterman portfolio. Based on the patterns of stock markets, the objective is to understand the relationship between past market data and planning future investment strategies through backtesting. Additionally, by examining diverse learning and investment periods, it is identified optimal strategies to boost portfolio returns while efficiently managing associated risks. For comparative analysis, traditional Markowitz portfolio is also assessed in conjunction with clustering techniques utilizing K-Means and K-Means with Dynamic Time Warping. It is suggested that the combination of K-shape and the Black-Litterman model significantly enhances portfolio optimization in the stock market, providing valuable insights for making stable portfolio investment decisions. The achieved sharpe ratio of 0.722 indicates a significantly higher performance when compared to other benchmarks, underlining the effectiveness of the K-shape and Black-Litterman integration in portfolio optimization.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.4
• /
• pp.272-280
• /
• 2023

For the past 70 years, an intense rivalry has persisted on the Korean Peninsula, and North Korea's nuclear and missile threats are becoming increasingly imminent. Facing a shortage of military resources, South Korea has pursued a national defense reform, significantly reducing the number of units and troops while focusing on ground forces. However, North Korea's strategic objective of unifying South Korea through surprise attacks, prompt responses, and combined nuclear and missile assaults remains unchanged. The central issue in this context revolves around determining the appropriate size of the Korean military's standing forces. This study employs the concept of net assessment as a novel method to ascertain the optimal size of the Korean military. Threats, strategic objectives, doctrine, and unit rotations are simultaneously considered from the enemy's perspective. In anticipation of security risks on the Korean Peninsula, an acceptable troop size will be proposed using the net assessment approach to calculate the appropriate standing force size.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.10
• /
• pp.2844-2861
• /
• 2023

Internet is the most prevailing word being used nowadays. Over the years, people are becoming more dependent on the internet as it makes their job easier. This became a part of everyone's life as a means of communication in almost every area like financial transactions, education, and personal-health operations. A lot of data is being converted to digital and made online. Many researchers have proposed different authentication factors - biometric and/or non-biometric authentication factors - as the first line of defense to secure online data. Among all those factors, passwords and passphrases are being used by many users around the world. However, the usability of these factors is low. Also, the passwords are easily susceptible to brute force and dictionary attacks. This paper proposes the generation of a novel passcode from the hybrid authentication factor - sound. The proposed passcode is evaluated for its strength to resist brute-force and dictionary attacks using the Shannon entropy and Passcode (or password) entropy formulae. Also, the passcode is evaluated for its usability. The entropy value of the proposed is 658.2. This is higher than that of other authentication factors. Like, for a 6-digit pin - the entropy value was 13.2, 101.4 for Password with Passphrase combined with Keystroke dynamics and 193 for fingerprint, and 30 for voice biometrics. The proposed novel passcode is far much better than other authentication factors when compared with their corresponding strength and usability values.

• Journal of Information Processing Systems
• /
• v.19 no.4
• /
• pp.417-426
• /
• 2023

To improve the effect of image restoration and solve the image detail loss, an image dehazing enhancement algorithm based on mean guided filtering is proposed. The superpixel calculation method is used to pre-segment the original foggy image to obtain different sub-regions. The Ncut algorithm is used to segment the original image, and it outputs the segmented image until there is no more region merging in the image. By means of the mean-guided filtering method, the minimum value is selected as the value of the current pixel point in the local small block of the dark image, and the dark primary color image is obtained, and its transmittance is calculated to obtain the image edge detection result. According to the prior law of dark channel, a classic image dehazing enhancement model is established, and the model is combined with a median filter with low computational complexity to denoise the image in real time and maintain the jump of the mutation area to achieve image dehazing enhancement. The experimental results show that the image dehazing and enhancement effect of the proposed algorithm has obvious advantages, can retain a large amount of image detail information, and the values of information entropy, peak signal-to-noise ratio, and structural similarity are high. The research innovatively combines a variety of methods to achieve image dehazing and improve the quality effect. Through segmentation, filtering, denoising and other operations, the image quality is effectively improved, which provides an important reference for the improvement of image processing technology.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.5
• /
• pp.217-223
• /
• 2023

In this paper, we propose a new model for the conditional generation of music, considering key and rhythm, fundamental elements of music. MIDI sheet music is converted into a WAV format, which is then transformed into a Mel Spectrogram using the Short-Time Fourier Transform (STFT). Using this information, key and rhythm details are classified by passing through two Convolutional Neural Networks (CNNs), and this information is again fed into the Music Transformer. The key and rhythm details are combined by differentially multiplying the weights and the embedding vectors of the MIDI events. Several experiments are conducted, including a process for determining the optimal weights. This research represents a new effort to integrate essential elements into music generation and explains the detailed structure and operating principles of the model, verifying its effects and potentials through experiments. In this study, the accuracy for rhythm classification reached 94.7%, the accuracy for key classification reached 92.1%, and the Negative Likelihood based on the weights of the embedding vector resulted in 3.01.

• Journal of Information Processing Systems
• /
• v.19 no.5
• /
• pp.590-601
• /
• 2023

University books are an important information resource. University book resources can be shared not only in the traditional paper form, but also electronic form under the background of the Internet. In order to better manage the sharing of electronic book resources in universities, this study put forward three resource sharing strategies: centralized sharing strategy, distributed sharing strategy, and centralized-distributed sharing strategy by analyzing the combined development of books and the Internet as well as the significance and development of book resource sharing. The centralized sharing strategy, however simple, was difficult to handle large traffic; while the resource nodes were independent and self-consistent, the distributed sharing strategy was not easy to find and had a high repetition rate. Combining the advantages of both strategies, the centralized-distributed sharing strategy was more suitable for the heterogeneous form of university book sharing. Finally, a teaching resources sharing platform for university libraries was designed based on the strategy of centralized and distributed sharing, and three interfaces including platform login, resource search, and resource release were displayed. The results of the simulated comparison experiment showed that centralized and distributed sharing strategies had limitations in resource searching and had low efficiencies; the efficiency of the centralized strategy reduced with an increase in search subjects; however, the centralized-distributed sharing strategy was able to search more resources efficiently and main stability.

• Journal of Information Processing Systems
• /
• v.19 no.6
• /
• pp.842-857
• /
• 2023

Currently, most sentiment classification models on microblogging platforms analyze sentence parts of speech and emoticons without comprehending users' emotional inclinations and grasping moral nuances. This study proposes a hybrid sentiment analysis model. Given the distinct nature of microblog comments, the model employs a combined stop-word list and word2vec for word vectorization. To mitigate local information loss, the TextCNN model, devoid of pooling layers, is employed for local feature extraction, while BiLSTM is utilized for contextual feature extraction in deep learning. Subsequently, microblog comment sentiments are categorized using a classification layer. Given the binary classification task at the output layer and the numerous hidden layers within BiLSTM, the Tanh activation function is adopted in this model. Experimental findings demonstrate that the enhanced TextCNN-BiLSTM model attains a precision of 94.75%. This represents a 1.21%, 1.25%, and 1.25% enhancement in precision, recall, and F1 values, respectively, in comparison to the individual deep learning models TextCNN. Furthermore, it outperforms BiLSTM by 0.78%, 0.9%, and 0.9% in precision, recall, and F1 values.