• Korean Journal of Remote Sensing
• /
• v.39 no.5_1
• /
• pp.599-608
• /
• 2023

The increasing interest in soil moisture data using satellite data for applications of hydrology, meteorology, and agriculture has led to the development of methods for generating soil moisture maps of variable resolution. This study demonstrated the capability of generating soil moisture maps using Sentinel-1 and Sentinel-2 data provided by Google Earth Engine (GEE). The soil moisture map was derived using synthetic aperture radar (SAR) image and optical image. SAR data provided by the Sentinel-1 analysis ready data in GEE was applied with normalized difference vegetation index (NDVI) based on Sentinel-2 and Environmental Systems Research Institute (ESRI)-based Land Cover map. This study produced a soil moisture map in the research area of Victoria, Australia and compared it with field measurements obtained from a previous study. As for the validation of the applied method's result accuracy, the comparative experimental results showed a meaningful range of consistency as 4-10%p between the values obtained using the algorithm applied in this study and the field-based ones, and they also showed very high consistency with satellite-based soil moisture data as 0.5-2%p. Therefore, public open data provided by GEE and the algorithm applied in this study can be used for high-resolution soil moisture mapping to represent regional land surface characteristics.

• Korean Journal of Remote Sensing
• /
• v.39 no.6_1
• /
• pp.1185-1193
• /
• 2023

The increasing interest in soil moisture data from satellite imagery for applications in hydrology, meteorology, and agriculture has led to the development of methods to produce variable-resolution soil moisture maps. Research on accurate soil moisture estimation using satellite imagery is essential for remote sensing applications. The purpose of this study is to generate a soil moisture estimation map for a test area using KOMPSAT-3/3A and KOMPSAT-5 SAR imagery and to quantitatively compare the results with soil moisture data from the Soil Moisture Active Passive (SMAP) mission provided by NASA, with a focus on accuracy validation. In addition, the Korean Environmental Geographic Information Service (EGIS) land cover map was used to determine soil moisture, especially in agricultural and forested regions. The selected test area for this study is the western part of Jeju, South Korea, where input data were available for the soil moisture estimation algorithm based on the Water Cloud Model (WCM). Synthetic Aperture Radar (SAR) imagery from KOMPSAT-5 HV and Sentinel-1 VV were used for soil moisture estimation, while vegetation indices were calculated from the surface reflectance of KOMPSAT-3 imagery. Comparison of the derived soil moisture results with SMAP (L-3) and SMAP (L-4) data by differencing showed a mean difference of 4.13±3.60 p% and 14.24±2.10 p%, respectively, indicating a level of agreement. This research suggests the potential for producing highly accurate and precise soil moisture maps using future South Korean satellite imagery and publicly available data sources, as demonstrated in this study.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.10
• /
• pp.445-454
• /
• 2023

Recently, various fault diagnosis studies are being conducted utilizing data from collaborative robots. Existing studies performing fault diagnosis on collaborative robots use static data collected based on the assumed operation of predefined devices. Therefore, the fault diagnosis model has a limitation of increasing dependency on the learned data patterns. Additionally, there is a limitation in that a diagnosis reflecting the characteristics of collaborative robots operating with multiple joints could not be conducted due to experiments using a single motor. This paper proposes an LSTM diagnostic model that can overcome these two limitations. The proposed method selects representative normal patterns using the correlation analysis of vibration and current data in single-axis and multi-axis work environments, and generates residual patterns through differences from the normal representative patterns. An LSTM model that can perform gear wear diagnosis for each axis is created using the generated residual patterns as inputs. This fault diagnosis model can not only reduce the dependence on the model's learning data patterns through representative patterns for each operation, but also diagnose faults occurring during multi-axis operation. Finally, reflecting both internal and external data characteristics, the fault diagnosis performance was improved, showing a high diagnostic performance of 98.57%.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.10
• /
• pp.455-460
• /
• 2023

Text augmentation is a methodology that creates new augmented texts by transforming or generating original texts for the purpose of improving the performance of NLP models. However existing text augmentation techniques have limitations such as lack of expressive diversity semantic distortion and limited number of augmented texts. Recently text augmentation using large language models and few-shot learning can overcome these limitations but there is also a risk of noise generation due to incorrect generation. In this paper, we propose a text augmentation method called TAGS that generates multiple candidate texts and selects the appropriate text as the augmented text. TAGS generates various expressions using few-shot learning while effectively selecting suitable data even with a small amount of original text by using contrastive learning and similarity comparison. We applied this method to task-oriented chatbot data and achieved more than sixty times quantitative improvement. We also analyzed the generated texts to confirm that they produced semantically and expressively diverse texts compared to the original texts. Moreover, we trained and evaluated a classification model using the augmented texts and showed that it improved the performance by more than 0.1915, confirming that it helps to improve the actual model performance.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.10
• /
• pp.461-470
• /
• 2023

While speech animation generation employing deep learning has been actively researched for English, there has been no prior work for Korean. Given the fact, this paper for the very first time employs supervised deep learning to generate Korean speech animation. By doing so, we find out the significant effect of deep learning being able to make speech animation research come down to speech recognition research which is the predominating technique. Also, we study the way to make best use of the effect for Korean speech animation generation. The effect can contribute to efficiently and efficaciously revitalizing the recently inactive Korean speech animation research, by clarifying the top priority research target. This paper performs this process: (i) it chooses blendshape animation technique, (ii) implements the deep-learning model in the master-servant pipeline of the automatic speech recognition (ASR) module and the facial action coding (FAC) module, (iii) makes Korean speech facial motion capture dataset, (iv) prepares two comparison deep learning models (one model adopts the English ASR module, the other model adopts the Korean ASR module, however both models adopt the same basic structure for their FAC modules), and (v) train the FAC modules of both models dependently on their ASR modules. The user study demonstrates that the model which adopts the Korean ASR module and dependently trains its FAC module (getting 4.2/5.0 points) generates decisively much more natural Korean speech animations than the model which adopts the English ASR module and dependently trains its FAC module (getting 2.7/5.0 points). The result confirms the aforementioned effect showing that the quality of the Korean speech animation comes down to the accuracy of Korean ASR.

• Journal of the Institute of Convergence Signal Processing
• /
• v.24 no.1
• /
• pp.57-68
• /
• 2023

With the technological development in the era of the 4th Industrial Revolution, technologies using HMD are being applied in various fields. HMD is especially useful in virtual reality fields such as AR/VR, and is very effective in receiving vivid impressions from users located in remote locations. According to these characteristics, the frequency of using HMD is increasing in the field related to collaboration. However, when HMD is applied to collaboration, communication between experts located in remote locations and workers located in the field is not smooth, causing various problems in terms of usability. In this paper, remote experts and workers in the field use HMD to solve various problems arising from collaboration, design/propose new types of HMD structures and functions that enable more efficient collaboration, and verify their usability using SUS evaluation techniques. As a result of the SUS evaluation, the new type of HMD structure and function proposed in this paper was 86.75points, which is believed to have greatly resolved the restrictions on collaboration and inconvenience in use of the existing HMD structure. In the future, when the HMD structure and design proposed in this paper are actually applied, it is expected that the application technology using HMD will expand rapidly.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.6
• /
• pp.255-266
• /
• 2022

The quality control of coarse aggregate among aggregates, which are the main ingredients of concrete, is currently carried out by SPC(Statistical Process Control) method through sampling. We construct a smart factory for manufacturing innovation by changing the quality control of coarse aggregates to inspect the coarse aggregates based on this image by acquired images through the camera instead of the current sieve analysis. First, obtained images were preprocessed, and HED(Hollistically-nested Edge Detection) which is the filter learned by deep learning segment each object. After analyzing each aggregate by image processing the segmentation result, fineness modulus and the aggregate shape rate are determined by analyzing result. The quality of aggregate obtained through the video was examined by calculate fineness modulus and aggregate shape rate and the accuracy of the algorithm was more than 90% accurate compared to that of aggregates through the sieve analysis. Furthermore, the aggregate shape rate could not be examined by conventional methods, but the content of this paper also allowed the measurement of the aggregate shape rate. For the aggregate shape rate, it was verified with the length of models, which showed a difference of ±4.5%. In the case of measuring the length of the aggregate, the algorithm result and actual length of the aggregate showed a ±6% difference. Analyzing the actual three-dimensional data in a two-dimensional video made a difference from the actual data, which requires further research.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.6
• /
• pp.967-971
• /
• 2023

Recently, a variety of AI-based platform services are available, and one of them is ChatGPT that processes a large quantity of data in the natural language and generates an answer after self-learning. ChatGPT can perform various tasks including software programming in the IT sector. Particularly, it may help generate a simple program and correct errors using C Language, which is a major programming language. Accordingly, it is expected that ChatGPT is capable of effectively using Verilog HDL, which is a hardware language created in C Language. Verilog HDL synthesis, however, is to generate imperative sentences in a logical circuit form and thus it needs to be verified whether the products are executed properly. In this paper, we aim to select small-scale logical circuits for ease of experimentation and to verify the results of circuits generated by ChatGPT and human-designed circuits. As to experimental environments, Xilinx ISE 14.7 was used for module modeling, and the xc3s1000 FPGA chip was used for module embodiment. Comparative analysis was performed on the use area and processing time of FPGA to compare the performance of ChatGPT products and Verilog HDL products.

• 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.