• Smart Media Journal
• /
• v.11 no.10
• /
• pp.65-75
• /
• 2022

Deep learning is used as a creative tool that could overcome the limitations of existing analysis models and generate various types of results such as text, image, and music. In this paper, we propose a method necessary to preprocess audio data using the Niko's MIDI Pack sound source file as a data set and to generate music using Bi-LSTM. Based on the generated root note, the hidden layers are composed of multi-layers to create a new note suitable for the musical composition, and an attention mechanism is applied to the output gate of the decoder to apply the weight of the factors that affect the data input from the encoder. Setting variables such as loss function and optimization method are applied as parameters for improving the LSTM model. The proposed model is a multi-channel Bi-LSTM with attention that applies notes pitch generated from separating treble clef and bass clef, length of notes, rests, length of rests, and chords to improve the efficiency and prediction of MIDI deep learning process. The results of the learning generate a sound that matches the development of music scale distinct from noise, and we are aiming to contribute to generating a harmonistic stable music.

• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.37-55
• /
• 2023

With the development of electronic journals and the emergence of various interdisciplinary studies, the selection of journals for publication has become a new challenge for researchers. Even if a paper is of high quality, it may face rejection due to a mismatch between the paper's topic and the scope of the journal. While research on assisting researchers in journal selection has been actively conducted in English, the same cannot be said for Korean journals. In this study, we propose a system that recommends Korean journals for submission. Firstly, we utilize SBERT (Sentence BERT) to embed abstracts of previously published papers at the document level, compare the similarity between new documents and published papers, and recommend journals accordingly. Next, the order of recommended journals is determined by considering the similarity of abstracts, keywords, and title. Subsequently, journals that are similar to the top recommended journal from previous stage are added by using a dictionary of words constructed for each journal, thereby enhancing recommendation diversity. The recommendation system, built using this approach, achieved a Top-10 accuracy level of 76.6%, and the validity of the recommendation results was confirmed through user feedback. Furthermore, it was found that each step of the proposed framework contributes to improving recommendation accuracy. This study provides a new approach to recommending academic journals in the Korean language, which has not been actively studied before, and it has also practical implications as the proposed framework can be easily applied to services.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.341-354
• /
• 2023

The title of a document is the brief summarization of the document. Readers can easily understand a document if we provide them with its title in their preferred styles and the languages. In this research, we propose a cross-lingual and style-based title generation model using multiple adapters. To train the model, we need a parallel corpus in several languages with different styles. It is quite difficult to construct this kind of parallel corpus; however, a monolingual title generation corpus of the same style can be built easily. Therefore, we apply a zero-shot strategy to generate a title in a different language and with a different style for an input document. A baseline model is Transformer consisting of an encoder and a decoder, pre-trained by several languages. The model is then equipped with multiple adapters for translation, languages, and styles. After the model learns a translation task from parallel corpus, it learns a title generation task from monolingual title generation corpus. When training the model with a task, we only activate an adapter that corresponds to the task. When generating a cross-lingual and style-based title, we only activate adapters that correspond to a target language and a target style. An experimental result shows that our proposed model is only as good as a pipeline model that first translates into a target language and then generates a title. There have been significant changes in natural language generation due to the emergence of large-scale language models. However, research to improve the performance of natural language generation using limited resources and limited data needs to continue. In this regard, this study seeks to explore the significance of such research.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.314-328
• /
• 2023

In this paper, we propose a texture map compression method based on the hierarchical coding method of SHVC to support the scalability function of dynamic mesh compression. The proposed method effectively eliminates the redundancy of multiple-resolution texture maps by downsampling a high-resolution texture map to generate multiple-resolution texture maps and encoding them with SHVC. The dynamic mesh decoder supports the scalability of mesh data by decoding a texture map having an appropriate resolution according to receiver performance and network environment. To evaluate the performance of the proposed method, the proposed method is applied to V-DMC (Video-based Dynamic Mesh Coding) reference software, TMMv1.0, and the performance of the scalable encoder/decoder proposed in this paper and TMMv1.0-based simulcast method is compared. As a result of experiments, the proposed method effectively improves in performance the average of -7.7% and -5.7% in terms of point cloud-based BD-rate (Luma PSNR) in AI and LD conditions compared to the simulcast method, confirming that it is possible to effectively support the texture map scalability of dynamic mesh data through the proposed method.

• Geophysics and Geophysical Exploration
• /
• v.25 no.4
• /
• pp.227-241
• /
• 2022

Full waveform inversion (FWI) in the field of seismic data processing is an inversion technique that is used to estimate the velocity model of the subsurface for oil and gas exploration. Recently, deep learning (DL) technology has been increasingly used for seismic data processing, and its combination with FWI has attracted remarkable research efforts. For example, DL-based data processing techniques have been utilized for preprocessing input data for FWI, enabling the direct implementation of FWI through DL technology. DL-based FWI can be divided into the following methods: pure data-based, physics-based neural network, encoder-decoder, reparameterized FWI, and physics-informed neural network. In this review, we describe the theory and characteristics of the methods by systematizing them in the order of advancements. In the early days of DL-based FWI, the DL model predicted the velocity model by preparing a large training data set to adopt faithfully the basic principles of data science and apply a pure data-based prediction model. The current research trend is to supplement the shortcomings of the pure data-based approach using the loss function consisting of seismic data or physical information from the wave equation itself in deep neural networks. Based on these developments, DL-based FWI has evolved to not require a large amount of learning data, alleviating the cycle-skipping problem, which is an intrinsic limitation of FWI, and reducing computation times dramatically. The value of DL-based FWI is expected to increase continually in the processing of seismic data.

• The Journal of Korean Institute of Next Generation Computing
• /
• v.13 no.2
• /
• pp.18-25
• /
• 2017

In computer science, an encoding is a standardization of converting information to one format for audio, video or text. Therefore, the encoding information of the data should be known to open and read it and there are algorithms detecting encoder of the data. However, some informations of data could be disappeared by packet loss when transmitted on network, especially, if the data is snatched by packet sniffing or eavesdropping from wireless communications. In this paper, we improve the performance of encoding detection algorithm of 'uchardet' program for multi-byte encoded data with errors based on bit-shift algorithm. To simulate the performance, we generated Korean and Japanese text data with errors that is removed some random bits at random positions. Then the detection algorithm are tested using the data and 'uchardet-bitshift' showed better performance than 'uchardet'. When Korean texts are used, 'uchardet' could detect perfectly with ≤0.005% errors but it showed 0% detection rate with ≥1% errors while 'uchardet-bitshift' detected perfectly with ≤0.05% errors and it showed correct detection cases with ≥1% errors. Japanese texts with errors tend to report falsely as Chinese encoding because Japanese texts include lots of Chinese characters. As a results, we improved encoding detection algorithms by applying bit shift operation.

• The Korean Journal of Applied Statistics
• /
• v.36 no.6
• /
• pp.515-528
• /
• 2023

With the growth of the e-commerce market, consumers increasingly rely on user reviews to make purchasing decisions. Consequently, researchers are actively conducting studies to effectively analyze these reviews. Among the various methods of sentiment analysis, the aspect-based sentiment analysis approach, which examines user reviews from multiple angles rather than solely relying on simple positive or negative sentiments, is gaining widespread attention. Among the various methodologies for aspect-based sentiment analysis, there is an analysis method using a transformer-based model, which is the latest natural language processing technology. In this paper, we conduct an aspect-based sentiment analysis on multilingual user reviews using two real datasets from the latest natural language processing technology model. Specifically, we use restaurant data from the SemEval 2016 public dataset and multilingual user review data from the cosmetic domain. We compare the performance of transformer-based models for aspect-based sentiment analysis and apply various methodologies to improve their performance. Models using multilingual data are expected to be highly useful in that they can analyze multiple languages in one model without building separate models for each language.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.12
• /
• pp.505-518
• /
• 2023

3D point cloud semantic segmentation is a computer vision task that involves dividing the point cloud into different objects and regions by predicting the class label of each point. Existing 3D semantic segmentation models have some limitations in performing sufficient fusion of multi-modal features while ensuring both characteristics of 2D visual features extracted from RGB images and 3D geometric features extracted from point cloud. Therefore, in this paper, we propose MMCA-Net, a novel 3D semantic segmentation model using 2D-3D multi-modal features. The proposed model effectively fuses two heterogeneous 2D visual features and 3D geometric features by using an intermediate fusion strategy and a multi-modal cross attention-based fusion operation. Also, the proposed model extracts context-rich 3D geometric features from input point cloud consisting of irregularly distributed points by adopting PTv2 as 3D geometric encoder. In this paper, we conducted both quantitative and qualitative experiments with the benchmark dataset, ScanNetv2 in order to analyze the performance of the proposed model. In terms of the metric mIoU, the proposed model showed a 9.2% performance improvement over the PTv2 model using only 3D geometric features, and a 12.12% performance improvement over the MVPNet model using 2D-3D multi-modal features. As a result, we proved the effectiveness and usefulness of the proposed model.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.12
• /
• pp.519-524
• /
• 2023

In hashing-based image retrieval, the hash code of a manipulated image is different from the original image, making it difficult to search for the same image. This paper proposes and evaluates a self-supervised deephashing model that generates perceptual hash codes from feature information such as texture, shape, and color of images. The comparison models are autoencoder-based variational inference models, but the encoder is designed with a fully connected layer, convolutional neural network, and transformer modules. The proposed model is a variational inference model that includes a SimAM module of extracting geometric patterns and positional relationships within images. The SimAM module can learn latent vectors highlighting objects or local regions through an energy function using the activation values of neurons and surrounding neurons. The proposed method is a representation learning model that can generate low-dimensional latent vectors from high-dimensional input images, and the latent vectors are binarized into distinguishable hash code. From the experimental results on public datasets such as CIFAR-10, ImageNet, and NUS-WIDE, the proposed model is superior to the comparative model and analyzed to have equivalent performance to the supervised learning-based deephashing model. The proposed model can be used in application systems that require low-dimensional representation of images, such as image search or copyright image determination.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.6
• /
• pp.400-405
• /
• 2023

Currently, inverted pendulums are being studied in many fields, including posture control of missiles, rockets, etc, and bipedal robots. In this study, the vertical posture control of the pendulum was studied by constructing a rotary inverted pendulum using a 256-pulse rotary encoder and a DC motor. In the case of nonlinear systems, complex algorithms and controllers are required, but a control method using the classic and relatively simple PID(Proportional Integral Derivation) algorithm was applied to the rotating inverted pendulum system, and a simple but desired method was studied. The rotating inverted pendulum system used in this study is a nonlinear and unstable system, and a PID controller using Microchip's dsPIC30F4013 embedded processor was designed and implemented in linear modeling. Usually, PID controllers are designed by combining one or two or more types, and have the advantage of having a simple structure compared to excellent control performance and that control gain adjustment is relatively easy compared to other controllers. In this study, the physical structure of the system was analyzed using mathematical methods and control for vertical balance of a rotating inverted pendulum was realized through modeling. In addition, the feasibility of controlling with a PID controller using a rotating inverted pendulum was verified through simulation and experiment.