• ETRI Journal
• /
• v.46 no.4
• /
• pp.697-707
• /
• 2024

Music identification is widely regarded as a solved problem for music searching in quiet environments, but its performance tends to degrade in TV broadcast audio owing to the presence of dialogue or sound effects. In addition, constructing an accurate dataset for measuring the performance of background music monitoring in TV broadcast audio is challenging. We propose a framework for monitoring background music by automatic identification and introduce a background music cue sheet. The framework comprises three main components: music identification, music-speech separation, and music detection. In addition, we introduce the Cue-K-Drama dataset, which includes reference songs, audio tracks from 60 episodes of five Korean TV drama series, and corresponding cue sheets that provide the start and end timestamps of background music. Experimental results on the constructed and existing datasets demonstrate that the proposed framework, which incorporates music identification with music-speech separation and music detection, effectively enhances TV broadcast audio monitoring.

• Journal of the Korean Society for information Management
• /
• v.37 no.2
• /
• pp.251-284
• /
• 2020

As the use of information has emerged as the core of national competitiveness, major developed countries and the Korean government have realized the importance of data. They have pursued technical research and standard establishment for long-term preservation and continuously strived for systematic management and preservation of data. However, although various types of data are specified for the purpose of record management in the law, there is no specific method on how to collect, manage and preserve them, except standard electronic documents. In particular, management and preservation of huge datasets from the administrative information system have been strongly demanded above all. Any guidelines for datasets do not have been properly provided. After the framework for selecting preservation format must be prepared, the system can be supplemented and built. The framework considering the characteristics of the dataset should be specified more concretely, and empirical verification of the conversion and restoration for the dataset preservation format derived according to the selection criteria is necessary. Therefore, this study intends to propose a method for long-term preservation through empirical verification of the preservation format after deriving an evaluation the framework for the preservation format selection criteria considering the characteristics of the dataset.

• Korean Journal of Remote Sensing
• /
• v.37 no.6_1
• /
• pp.1685-1695
• /
• 2021

To generate a deep learning model with high performance, a large training dataset should be required. However, it requires a lot of time and cost to generate a large training dataset in remote sensing. Therefore, the importance of transfer learning of deep learning model using a small dataset have been increased. In this paper, we performed transfer learning of trained model based on open datasets by using orthoimages and digital maps to detect changes of building objects in multitemporal orthoimages. For this, an initial training was performed on open dataset for change detection through the HRNet-v2 model, and transfer learning was performed on dataset by orthoimages and digital maps. To analyze the effect of transfer learning, change detection results of various deep learning models including deep learning model by transfer learning were evaluated at two test sites. In the experiments, results by transfer learning represented best accuracy, compared to those by other deep learning models. Therefore, it was confirmed that the problem of insufficient training dataset could be solved by using transfer learning, and the change detection algorithm could be effectively applied to various remote sensed imagery.

• Journal of Korean Society of Archives and Records Management
• /
• v.21 no.3
• /
• pp.227-246
• /
• 2021

The study seeks to analyze the procedures and methods of preparing the records management reference table of the electronic human resource management system dataset, the roles of participating organizations, and the contents of each management reference table area from the records manager's perspective to help the person in charge of establishing the management reference table. Improvement plans were suggested based on the problems that appeared during the process of preparing the reference table. As a major improvement plan, a separate selecting policy at the level of the national archives should be designed for the national important dataset records in the government information system, which should be operated such that it preserves the entire dataset rather than a part. It is necessary to set the unit function-data table-unstructured data mapping data as mandatory items, and the selection and management criteria for unstructured data that significantly influence system operation should be additionally prepared. Regarding the setting of the disposition delay period, because there is an aspect of increasing complexity, it is deemed desirable to operate it by integrating related unit functions or setting the retention period longer.

• Journal of Broadcast Engineering
• /
• v.23 no.6
• /
• pp.855-865
• /
• 2018

Sound event detection is one of the research areas to model human auditory cognitive characteristics by recognizing events in an environment with multiple acoustic events and determining the onset and offset time for each event. DCASE, a research group on acoustic scene classification and sound event detection, is proceeding challenges to encourage participation of researchers and to activate sound event detection research. However, the size of the dataset provided by the DCASE Challenge is relatively small compared to ImageNet, which is a representative dataset for visual object recognition, and there are not many open sources for the acoustic dataset. In this study, the sound events that can occur in indoor and outdoor are collected on a larger scale and annotated for dataset construction. Furthermore, to improve the performance of the sound event detection task, we developed a dual CNN structured sound event detection system by adding a supplementary neural network to a convolutional neural network to determine the presence of sound events. Finally, we conducted a comparative experiment with both baseline systems of the DCASE 2016 and 2017.

• Journal of Biomedical Engineering Research
• /
• v.43 no.1
• /
• pp.19-26
• /
• 2022

The Comprehensive in vitro Proarrhythmic Assay(CiPA) project was launched for solving the hERG assay problem of being classified as high-risk groups even though they are low-risk drugs due to their high sensitivity. CiPA presented a protocol to predict drug toxicity using physiological data calculated based on the in-silico model. in this study, features calculated through the in-silico model are analyzed for correlation of changing action potential in the near future, and features are verified through predictive performance according to drug datasets. Using the O'Hara Rudy model modified by Dutta et al., Pearson correlation analysis was performed between 13 features(dVm/dtmax, APpeak, APresting, APD90, APD50, APDtri, Ca_peak, Ca_resting, CaD90, CaD50, CaDtri, qNet, qInward) calculated at 100 pacing, and between dVm/d_{tmax_repol} calculated at 1,000 pacing, and linear regression analysis was performed on each of the 12 training drugs, 16 verification drugs, and 28 drugs. Indicators showing high coefficient of determination(R²) in the training drug dataset were qNet 0.93, AP resting 0.83, APDtri 0.78, Ca resting 0.76, dVm/dt_max 0.63, and APD90 0.61. The indicators showing high determinants in the validated drug dataset were APDtri 0.94, APD90 0.92, APD50 0.85, CaD50 0.84, qNet 0.76, and CaD90 0.64. Indicators with high coefficients of determination for all 28 drugs are qNet 0.78, APD90 0.74, and qInward 0.59. The indicators vary in predictive performance depending on the drug dataset, and qNet showed the same high performance of 0.7 or more on the training drug dataset, the verified drug dataset, and the entire drug dataset.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_4
• /
• pp.1111-1123
• /
• 2023

In recent times, semantic image segmentation methods using deep learning models have been widely used for monitoring changes in surface attributes using remote sensing imagery. To enhance the performance of various UNet-based deep learning models, including the prominent UNet model, it is imperative to have a sufficiently large training dataset. However, enlarging the training dataset not only escalates the hardware requirements for processing but also significantly increases the time required for training. To address these issues, transfer learning is used as an effective approach, enabling performance improvement of models even in the absence of massive training datasets. In this paper we present three transfer learning models, UNet-ResNet50, UNet-VGG19, and CBAM-DRUNet-VGG19, which are combined with the representative pretrained models of VGG19 model and ResNet50 model. We applied these models to building extraction tasks and analyzed the accuracy improvements resulting from the application of transfer learning. Considering the substantial impact of learning rate on the performance of deep learning models, we also analyzed performance variations of each model based on different learning rate settings. We employed three datasets, namely Kompsat-3A dataset, WHU dataset, and INRIA dataset for evaluating the performance of building extraction results. The average accuracy improvements for the three dataset types, in comparison to the UNet model, were 5.1% for the UNet-ResNet50 model, while both UNet-VGG19 and CBAM-DRUNet-VGG19 models achieved a 7.2% improvement.

• Proceedings of the IEEK Conference
• /
• 2002.06c
• /
• pp.135-138
• /
• 2002

This paper addresses incremental learning method for regression. SVM(support vector machine) is a recently proposed learning method. In general training a support vector machine requires solving a QP (quadratic programing) problem. For very large dataset or incremental dataset, solving QP problems may be inconvenient. So this paper presents an incremental support vector learning method for function approximation problems.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.05a
• /
• pp.431-432
• /
• 2018

MRC(기계독해)는 Passage, Question, Answel 로 이루어진 Dataset 으로 학습된 모델을 사용하여 요청한 Question 의 Answer 를 같이 주어진 Passage 내에서 찾아내는 것을 목적으로 한다. 최근 MRC 시스템의 성능 측정 지표로 활용되는 SQuAD Dataset 을 활용하여 RNN 의 한 분류인 match-LSTM과 R-NET 알고리즘의 성능을 비교 분석하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.606-609
• /
• 2021

최근 한국에서도 이루다의 윤리 이슈를 기점으로 딥러닝 모델의 윤리적 언어학습 필요성이 대두되었다. 그럼에도 불구하고 영어 데이터에 비해 한국어 데이터는 Korean Hate Speech Detection Dataset 이 유일하다. 이번 연구에서는 기존 데이터 세트의 유연성이 떨어지고 세부 라벨이 제한적이라는 문제를 개선한 새로운 데이터 세트를 제안하고, 해당 데이터 세트에 대하여 다양한 신경망 분류 모델을 적용한 벤치마크 결과를 공개한다.