• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.11a
• /
• pp.270-272
• /
• 2020

본 논문은 코로나 방역의 자동화를 위한 Deep learning 기술 적용에 대해 연구한다. 2020년에 가장 중요한 이슈 중 하나인 COVID-19와 그 방역에 대해 많은 사람들이 IT분야에서 떠오르고 있는 artificial intelligence(AI)에 주목하고 있다. COVID-19로 인해 마스크 착용이 선택이 아닌 필수가 되며, 이를 통제하기 위한 모델이 필요한 상황이다. AI, 그 중에서도 Deep learning의 Object detection 기술을 일상생활 곳곳에 존재하는 영상 장치들에 적용하여 합리적인 비용으로 방역의 실시간 자동화를 구현할 수 있다. 이번 논문에서는 인터넷에 공개되어 있는 사물인식 오픈소스를 활용하여 이를 구현하기 위한 연구를 진행하였다. 또 이를 위한 Dataset 확보에 대한 조사도 진행하였다.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.55-60
• /
• 2021

최근 한국어에 대한 자연어 처리 연구는 딥러닝 기반의 자연어 이해 모델을 중심으로 각 모델의 성능에 대한 비교 분석과 평가가 활발하게 이루어지고 있다. 그러나 한국어 생성 모델에 대해서도 자연어 이해 영역의 하위 과제(e.g. 감정 분류, 문장 유사도 측정 등)에 대한 수행 능력만을 정량적으로 평가하여, 생성 모델의 한국어 문장 구성 능력이나 상식 추론 과정을 충분히 평가하지 못하고 있다. 또한 대부분의 생성 모델은 여전히 간단하고 일반적인 상식에 부합하는 자연스러운 문장을 생성하는 것에도 큰 어려움을 겪고 있기에 이를 해결하기 위한 개선 연구가 필요한 상황이다. 따라서 본 논문은 이러한 문제를 해결하기 위해 한국어 생성 모델이 일반 상식 추론 능력을 바탕으로 문장을 생성하도록 KommonGen 데이터셋을 제안한다. 그리고 KommonGen을 통해 한국어 생성 모델의 성능을 정량적으로 비교 분석할 수 있도록 평가 기준을 구성하고, 한국어 기반 자연어 생성 모델의 개선 방향을 제시하고자 한다.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.11a
• /
• pp.461-464
• /
• 2023

최근 GPT-3 와 LLaMa 같은 생성형 거대 언어모델을 활용한 서비스가 공개되었고, 실제로 많은 사람들이 사용하고 있다. 해당 모델들은 사용자들의 다양한 질문에 대해 유창한 답변을 한다는 이유로 주목받고 있다. 하지만 LLMs 의 답변에는 종종 Inconsistent content 와 non-factual statement 가 존재하며, 이는 사용자들로 하여금 잘못된 정보의 전파 등의 문제를 야기할 수 있다. 이에 논문에서는 동일한 질문에 대한 LLM 의 답변 샘플과 외부 지식을 활용한 Hallucination Detection 방법을 제안한다. 제안한 방법은 동일한 질문에 대한 LLM 의 답변들을 이용해 일관성 점수(Consistency score)를 계산한다. 거기에 외부 지식을 이용한 사실검증을 통해 사실성 점수(Factuality score)를 계산한다. 계산된 일관성 점수와 사실성 점수를 활용하여 문장 수준의 Hallucination Detection 을 가능하게 했다. 실험에는 GPT-3 를 이용하여 WikiBio dataset 에 있는 인물에 대한 passage 를 생성한 데이터셋을 사용하였으며, 우리는 해당 방법을 통해 문장 수준에서의 Hallucination Detection 성능이 baseline 보다 AUC-PR scores 에서 향상됨을 보였다.

• Convergence Security Journal
• /
• v.24 no.3
• /
• pp.203-208
• /
• 2024

The identification and classification of victims in the county border area is one of the important issues. The personnel that can appear in the military border area are comprised of North Korean soldiers, U.S. soldiers, South Korean soldiers, and the general public, and are currently being confirmed through CCTV. They were classified into true categories and learned through transfer learning. The PyTorch machine learning library was used, and the dataset was utilized by crawling images corresponding to each item shared on Google. The experimental results show that each item is classified with an accuracy of 98.7500%. Future research will explore ways to distinguish more systematically and specifically by going beyond images and adding video or voice recognition.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.10
• /
• pp.8-15
• /
• 2020

A forecasting method using deep learning does not have consistent results due to the differences in the characteristics of the dataset, even though they have the same forecasting models and parameters. For example, the forecasting model X optimized with dataset A would not produce the optimized result with another dataset B. The forecasting model with the characteristics of the dataset needs to be optimized to increase the accuracy of the forecasting model. Therefore, this paper proposes novel optimization steps for outlier removal, dataset classification, and a CNN-LSTM-based hyperparameter tuning process to forecast the daily power usage of a university campus based on the hourly interval. The proposing model produces high forecasting accuracy with a 2% of MAPE with a single power input variable. The proposing model can be used in EMS to suggest improved strategies to users and consequently to improve the power efficiency.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.3
• /
• pp.166-172
• /
• 2022

In this study, we photograph driving obstacle objects such as crosswalks, side spheres, manholes, braille blocks, partial ramps, temporary safety barriers, stairs, and inclined curb that hinder or cause inconvenience to the movement of the vulnerable using electric mobility aids. We develop an optimal AI model that classifies photographed objects and automatically recognizes them, and implement an algorithm that can efficiently determine obstacles in front of electric mobility aids. In order to enable object detection to be AI learning with high probability, the labeling form is labeled as a polygon form when building a dataset. It was developed using a Mask R-CNN model in Detectron2 framework that can detect objects labeled in the form of polygons. Image acquisition was conducted by dividing it into two groups: the general public and the transportation weak, and image information obtained in two areas of the test bed was secured. As for the parameter setting of the Mask R-CNN learning result, it was confirmed that the model learned with IMAGES_PER_BATCH: 2, BASE_LEARNING_RATE 0.001, MAX_ITERATION: 10,000 showed the highest performance at 68.532, so that the user can quickly and accurately recognize driving risks and obstacles.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.3
• /
• pp.89-100
• /
• 2023

Recently, on-device artificial intelligence (AI) solutions using mobile devices and embedded edge devices have emerged in various fields, such as computer vision, to address network traffic burdens, low-energy operations, and security problems. Although vision transformer deep learning models have outperformed conventional convolutional neural network (CNN) models in computer vision, they require more computations and parameters than CNN models. Thus, they are not directly applicable to embedded edge devices with limited hardware resources. Many researchers have proposed various model compression methods or lightweight architectures for vision transformers; however, there are only a few studies evaluating the effects of model compression techniques of vision transformers on performance. Regarding this problem, this paper presents a performance evaluation of vision transformers on embedded platforms. We investigated the behaviors of three vision transformers: DeiT, LeViT, and MobileViT. Each model performance was evaluated by accuracy and inference time on edge devices using the ImageNet dataset. We assessed the effects of the quantization method applied to the models on latency enhancement and accuracy degradation by profiling the proportion of response time occupied by major operations. In addition, we evaluated the performance of each model on GPU and EdgeTPU-based edge devices. In our experimental results, LeViT showed the best performance in CPU-based edge devices, and DeiT-small showed the highest performance improvement in GPU-based edge devices. In addition, only MobileViT models showed performance improvement on EdgeTPU. Summarizing the analysis results through profiling, the degree of performance improvement of each vision transformer model was highly dependent on the proportion of parts that could be optimized in the target edge device. In summary, to apply vision transformers to on-device AI solutions, either proper operation composition and optimizations specific to target edge devices must be considered.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.174-176
• /
• 2022

In this paper, we present a mobile application for 'personalized customized learning' for children with articulation disorders using an artificial intelligence (AI) algorithm. A dataset (Data Set) to analyze, judge, and predict the learner's articulation situation and degree. In particular, we designed a prototype model by looking at how AI can be improved and advanced compared to existing applications from the UX/UI (GUI) aspect. So far, the focus has been on visual experience, but now it is an important time to process data and provide a UX/UI (GUI) experience to users. The UX/UI (GUI) of the proposed mobile application was to be provided according to the learner's articulation level and situation by using CRNN (Convolution Recurrent Neural Network) of DeepLearning and Auto Encoder GPT-3 (Generative Pretrained Transformer). The use of artificial intelligence algorithms will provide a learning environment with a high degree of perfection to children with articulation disorders, thereby enhancing the learning effect. I hope that you do not have any fear or discomfort in conversation by improving the perfection of articulation with 'personalized and customized learning'.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.5
• /
• pp.999-1008
• /
• 2023

Early prediction of chronic diseases such as diabetes is an important issue, and improving the accuracy of diabetes prediction is especially important. Various machine learning and deep learning-based methodologies are being introduced for diabetes prediction, but these technologies require large amounts of data for better performance than other methodologies, and the learning cost is high due to complex data models. In this study, we aim to verify the claim that DNN using the pima dataset and k-fold cross-validation reduces the efficiency of diabetes diagnosis models. Machine learning classification methods such as decision trees, SVM, random forests, logistic regression, KNN, and various ensemble techniques were used to determine which algorithm produces the best prediction results. After training and testing all classification models, the proposed system provided the best results on XGBoost classifier with ADASYN method, with accuracy of 81%, F1 coefficient of 0.81, and AUC of 0.84. Additionally, a domain adaptation method was implemented to demonstrate the versatility of the proposed system. An explainable AI approach using the LIME and SHAP frameworks was implemented to understand how the model predicts the final outcome.

• Journal of Platform Technology
• /
• v.12 no.3
• /
• pp.3-15
• /
• 2024

Knowledge mining is a research field that applies various techniques such as data modeling, information extraction, analysis, visualization, and result interpretation to find valuable knowledge from diverse large datasets. It plays a crucial role in transforming raw data into useful knowledge across various domains like business, healthcare, and scientific research etc. In this paper, we propose analytical techniques for performing knowledge discovery and data mining from various data by extending the Formal Concept Analysis method. It defines algorithms for representing diverse formats and structures of the data to be analyzed, including models such as many-valued data table data and triadic data table, as well as algorithms for data processing (dyadic scaling and flattening) and the construction of concept hierarchies and the extraction of association rules. The usefulness of the proposed technique is empirically demonstrated by conducting experiments applying the proposed method to public open data.