• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.43-45
• /
• 2021

The short-term quantitative precipitation prediction (QPF) system is important socially and economically to prevent damage from severe weather. Recently, many studies for short-term QPF model applying the Deep Neural Network (DNN) has been conducted. These studies require the sophisticated pre-processing because the mistreatment of various and vast meteorological data sets leads to lower performance of QPF. Especially, for more accurate prediction of the non-linear trends in precipitation, the dataset needs to be carefully handled based on the physical and dynamical understands the data. Thereby, this paper proposes the following approaches: i) refining and combining major factors (weather radar, terrain, air temperature, and so on) related to precipitation development in order to construct training data for pattern analysis of precipitation; ii) producing predicted precipitation fields based on Convolutional with ConvLSTM. The proposed algorithm was evaluated by rainfall events in 2020. It is outperformed in the magnitude and strength of precipitation, and clearly predicted non-linear pattern of precipitation. The algorithm can be useful as a forecasting tool for preventing severe weather.

• Journal of Korea Entertainment Industry Association
• /
• v.13 no.8
• /
• pp.117-130
• /
• 2019

After Marx, the issues regarding human labour have been the alienation towards production means and the distributive justice. Fourth industrial revolution and development of AI(Artificial Intelligence) opened the possibility of a independent production and economy system absolutely excluding against human nature and labour. Using robots and AI will deepen demarcation between living things and one not having life, separating the intelligence from the consciousness. At present, so called pre-stage of post human, seeking interests for life, new social relationship and new community will be increased as well. We can understand that interests for small community, self-sufficiency, dailiness, food and body in this context is increasing too. Representative trend towards this cultural phenomena is called as the 'Kinfolk culture.' Work-life balance, 'Aucalme', 'Hygge', 'So-Hwak-Haeng'(a small but reliable happiness) are the similar culture trends as. Vital capitalism, presented by O-Yong Lee, seeks focusing onto living things principles, e.g. 'topophilia', 'neophilia', and 'biophilia' as the dynamics looking for the history substructure, not class struggle and conflicts. He also argues the 'Vital Capitalism' be regarded as a new methodology to anticipate a social system after post human era. G. Deleuze said "arts is another expression method for existential philosophy. It gives a vitality onto philosophy and gives a role to letting abstract concept into definite image." We can find a lot cases arts' imagination overcomes critical point of scientific prediction power in the future prediction. This paper reviews ideas and issues of 'vital capitalism' in detail and explorers imaginating initial ideas of vital capitalism in the film 'Little Forest.'

• Korean Journal of Radiology
• /
• v.23 no.1
• /
• pp.77-88
• /
• 2022

Objective: Our study aimed to evaluate the quality of radiomics studies on brain metastases based on the radiomics quality score (RQS), Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (TRIPOD) checklist, and the Image Biomarker Standardization Initiative (IBSI) guidelines. Materials and Methods: PubMed MEDLINE, and EMBASE were searched for articles on radiomics for evaluating brain metastases, published until February 2021. Of the 572 articles, 29 relevant original research articles were included and evaluated according to the RQS, TRIPOD checklist, and IBSI guidelines. Results: External validation was performed in only three studies (10.3%). The median RQS was 3.0 (range, -6 to 12), with a low basic adherence rate of 50.0%. The adherence rate was low in comparison to the "gold standard" (10.3%), stating the potential clinical utility (10.3%), performing the cut-off analysis (3.4%), reporting calibration statistics (6.9%), and providing open science and data (3.4%). None of the studies involved test-retest or phantom studies, prospective studies, or cost-effectiveness analyses. The overall rate of adherence to the TRIPOD checklist was 60.3% and low for reporting title (3.4%), blind assessment of outcome (0%), description of the handling of missing data (0%), and presentation of the full prediction model (0%). The majority of studies lacked pre-processing steps, with bias-field correction, isovoxel resampling, skull stripping, and gray-level discretization performed in only six (20.7%), nine (31.0%), four (3.8%), and four (13.8%) studies, respectively. Conclusion: The overall scientific and reporting quality of radiomics studies on brain metastases published during the study period was insufficient. Radiomics studies should adhere to the RQS, TRIPOD, and IBSI guidelines to facilitate the translation of radiomics into the clinical field.

• Phonetics and Speech Sciences
• /
• v.16 no.1
• /
• pp.67-76
• /
• 2024

Recent advances in text-to-speech (TTS) technology have significantly improved the quality of synthesized speech, reaching a level where it can closely imitate natural human speech. Especially, TTS models offering various voice characteristics and personalized speech, are widely utilized in fields such as artificial intelligence (AI) tutors, advertising, and video dubbing. Accordingly, in this paper, we propose a one-shot multi-speaker TTS system that can ensure acoustic diversity and synthesize personalized voice by generating speech using unseen target speakers' utterances. The proposed model integrates a speaker encoder into a TTS model consisting of the FastSpeech2 acoustic model and the HiFi-GAN vocoder. The speaker encoder, based on the pre-trained RawNet3, extracts speaker-specific voice features. Furthermore, the proposed approach not only includes an English one-shot multi-speaker TTS but also introduces a Korean one-shot multi-speaker TTS. We evaluate naturalness and speaker similarity of the generated speech using objective and subjective metrics. In the subjective evaluation, the proposed Korean one-shot multi-speaker TTS obtained naturalness mean opinion score (NMOS) of 3.36 and similarity MOS (SMOS) of 3.16. The objective evaluation of the proposed English and Korean one-shot multi-speaker TTS showed a prediction MOS (P-MOS) of 2.54 and 3.74, respectively. These results indicate that the performance of our proposed model is improved over the baseline models in terms of both naturalness and speaker similarity.

• Journal of Korea Water Resources Association
• /
• v.57 no.1
• /
• pp.35-44
• /
• 2024

Research in dam inflow prediction has actively explored the utilization of data-driven machine learning and deep learning (ML&DL) tools across diverse domains. Enhancing not just the inherent model performance but also accounting for model characteristics and preprocessing data are crucial elements for precise dam inflow prediction. Particularly, existing rainfall data, derived from snowfall amounts through heating facilities, introduces distortions in the correlation between snow accumulation and rainfall, especially in dam basins influenced by snow accumulation, such as Soyang Dam. This study focuses on the preprocessing of rainfall data essential for the application of ML&DL models in predicting dam inflow in basins affected by snow accumulation. This is vital to address phenomena like reduced outflow during winter due to low snowfall and increased outflow during spring despite minimal or no rain, both of which are physical occurrences. Three machine learning models (SVM, RF, LGBM) and two deep learning models (LSTM, TCN) were built by combining rainfall and inflow series. With optimal hyperparameter tuning, the appropriate model was selected, resulting in a high level of predictive performance with NSE ranging from 0.842 to 0.894. Moreover, to generate rainfall correction data considering snow accumulation, a simulated snow accumulation algorithm was developed. Applying this correction to machine learning and deep learning models yielded NSE values ranging from 0.841 to 0.896, indicating a similarly high level of predictive performance compared to the pre-snow accumulation application. Notably, during the snow accumulation period, adjusting rainfall during the training phase was observed to lead to a more accurate simulation of observed inflow when predicted. This underscores the importance of thoughtful data preprocessing, taking into account physical factors such as snowfall and snowmelt, in constructing data models.

• Journal of Korea Water Resources Association
• /
• v.57 no.7
• /
• pp.437-449
• /
• 2024

Rainfall-runoff prediction studies using deep learning while considering catchment attributes have been gaining attention. In this study, we selected two models: the Transformer model, which is suitable for large-scale data training through the self-attention mechanism, and the LSTM-based multi-state-vector sequence-to-sequence (LSTM-MSV-S2S) model with an encoder-decoder structure. These models were constructed to incorporate catchment attributes and predict the inflow of 10 multi-purpose dam watersheds in South Korea. The experimental design consisted of three training methods: Single-basin Training (ST), Pretraining (PT), and Pretraining-Finetuning (PT-FT). The input data for the models included 10 selected watershed attributes along with meteorological data. The inflow prediction performance was compared based on the training methods. The results showed that the Transformer model outperformed the LSTM-MSV-S2S model when using the PT and PT-FT methods, with the PT-FT method yielding the highest performance. The LSTM-MSV-S2S model showed better performance than the Transformer when using the ST method; however, it showed lower performance when using the PT and PT-FT methods. Additionally, the embedding layer activation vectors and raw catchment attributes were used to cluster watersheds and analyze whether the models learned the similarities between them. The Transformer model demonstrated improved performance among watersheds with similar activation vectors, proving that utilizing information from other pre-trained watersheds enhances the prediction performance. This study compared the suitable models and training methods for each multi-purpose dam and highlighted the necessity of constructing deep learning models using PT and PT-FT methods for domestic watersheds. Furthermore, the results confirmed that the Transformer model outperforms the LSTM-MSV-S2S model when applying PT and PT-FT methods.

• Bulletin of the Korean Chemical Society
• /
• v.31 no.5
• /
• pp.1361-1367
• /
• 2010

A series of O,O-dialkyl-1-phenoxyacetoxy-1-methylphosphonate analogues (1~22) as a new class of potent inhibitors of pyruvate dehydrogenase were synthesized and 3D-QSARs (three dimensional qantitative structure-activity relationships) models on the pre-emergency herbicidal activity against the seed of cucumber (Cucumus Sativa L.) were derived and discussed quantitatively using comparative molecular field analysis (CoMFA) and comparative molecular similarity indeces analysis (CoMSIA) methods. The statistical values of CoMSIA models were better predictability and fitness than those of CoMFA models. The inhibitory activities according to the optimized CoMSIA model I were dependent on the electrostatic field (41.4%), the H-bond acceptor field (26.0%), the hydrophobic field (20.8%) and the steric field (11.7%). And also, it was found that the optimized CoMSIA model I with the sensitivity to the perturbation ($d_q{^{2'}}/dr^2{_{yy'}}$ = 0.830) and the prediction ($q^2$ = 0.503) produced by a progressive scrambling analyses were not dependent on chance correlation. From the results of graphical analyses on the contour maps with the optimized CoMSIA model I, it is expected that the structural distinctions and descriptors that subscribe to herbicidal activities will be able to apply new an herbicide design.

• Industrial Engineering and Management Systems
• /
• v.13 no.3
• /
• pp.289-296
• /
• 2014

With society becoming more advanced and complex, the required management engineering makes essential the development of human resources that can propose solutions for problems of new phenomena from a different perspective. As an example of such phenomena, we note a consumer electronics 'Eco-point' system campaign in this study. To mitigate global warming, revitalize the economy, and encourage the adoption of terrestrial digital compatible TVs, the consumer electronics Eco-point system campaign was implemented in May 2009 in Japan. In this study, we note a model which is constant term with exponential curve with notion of the growth phenomenon (Nakagiri and Kurita, Journal of the Operations Research Society of Japan, 2002). In our study, we call this model the 'differential equation model of the growth phenomenon.' This model represents a phenomenon with a hierarchical structure for capturing the properties of n species. In this study, we propose a new model which can represent not only the impact of largescale campaigns but also seasonal factors. Accordingly, we understand the phenomenon of fluctuation of sales of some products caused by large-scale campaigns and predict the fluctuation of sales. The final goal of this study is to develop human resources that can propose provision and solution for pre-consumption and reactionary decline in demand by understanding the impact of large-scale campaigns. As the first step of this goal, our objective is to propose a new regression method with different conventional perspective that can describe the fluctuation of sales caused by large-scale campaigns and show the possibility of new management engineering education.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.4
• /
• pp.2477-2481
• /
• 2013

Aims and Background: The purpose of the research was to study the prognostic value of tumor 18F-FDG PET-based parameters in neoadjuvant chemoradiation for patients with squamous esophageal carcinoma. Methods: Sixty patients received chemoradiation therapy followed by esophagectomy and two 18FDG-PET examinations at pre- and post-radiation therapy. PET-based metabolic-response parameters were calculated based on histopathologic response. Linear regression correlation and Cox proportional hazards models were used to determine prognostic value of all PET-based parameters with reference to overall survival. Results: Sensitivity (88.2%) and specificity (86.5%) of a percentage decrease of SUVmax were better than other PET-based parameters for prediction of histopathologic response. Only percentage decrease of SUVmax and tumor length correlated with overall survival time (linear regression coefficient ${\beta}$: 0.704 and 0.684, P<0.05). The Cox proportional hazards model indicated higher hazard ratio (HR=0.897, P=0.002) with decrease of SUVmax compared with decrease of tumor size (HR=0.813, P=0.009). Conclusion: Decrease of SUVmax and tumor size are significant prognostic factors in chemoradiation of esophageal carcinoma.

• Journal of the Korean earth science society
• /
• v.32 no.7
• /
• pp.871-880
• /
• 2011

The purpose of this research is to explore preservice earth science teachers' understanding of volcanic systems using a modified version of InVEST Volcanic Concept Survey (InVEST VCS, Parham et al., 2010). Results showed that participants' understanding of volcanic concepts was rather limited. Questions requiring only basic content knowledge (e.g., terminology associated with volcano) received high scoring responses, while questions requiring higher order thinking and deeper conceptual connections as the mechanics of volcanic eruption received low scoring responses. Specifically, the prediction of hazards and impacts on the environment appeared to be poorly understood. VCS results can be applied to improve the subject content knowledge as well as the pedagogical knowledge that instructors may use when they assess students' understanding of volcanism within a solid conceptual framework.