• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.05a
• /
• pp.627-630
• /
• 2022

Over the past few years, fake news has become one of the most significant problems. Since it is impossible to prevent people from spreading misinformation, people should analyze the news themselves. However, this process takes some time and effort, so the routine part of this analysis should be automated. There are many different approaches to this problem, but they only analyze the text and messages, ignoring the images. The fake news problem should be solved using a complex analysis tool to reach better performance. In this paper, we propose the approach of training an Artificial Intelligence using an unsupervised learning algorithm, combined with online data parsing tools, providing independence from subjective data set. Therefore it will be more difficult to spread fake news since people could quickly check if the news or article is trustworthy.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.59-68
• /
• 2022

This paper presents a method for 1:1 verification by comparing the similarity between the given real product image and the drawing image. The proposed method combines two existing CNN-based deep learning models to construct a Siamese Network. After extracting the feature vector of the image through the FC (Fully Connected) Layer of each network and comparing the similarity, if the real product image and the drawing image (front view, left and right side view, top view, etc) are the same product, the similarity is set to 1 for learning and, if it is a different product, the similarity is set to 0. The test (inference) model is a deep learning model that queries the real product image and the drawing image in pairs to determine whether the pair is the same product or not. In the proposed model, through a comparison of the similarity between the real product image and the drawing image, if the similarity is greater than or equal to a threshold value (Threshold: 0.5), it is determined that the product is the same, and if it is less than or equal to, it is determined that the product is a different product. The proposed model showed an accuracy of about 71.8% for a query to a product (positive: positive) with the same drawing as the real product, and an accuracy of about 83.1% for a query to a different product (positive: negative). In the future, we plan to conduct a study to improve the matching accuracy between the real product image and the drawing image by combining the parameter optimization study with the proposed model and adding processes such as data purification.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.10
• /
• pp.1300-1306
• /
• 2018

The purpose of this study is to see possibility of Char2Vec as alternative of Word2Vec that most famous word embedding model in Sentence Similarity Measure Problem by Deep-Learning. In experiment, we used the Siamese Ma-LSTM recurrent neural network architecture for measure similarity two random sentences. Siamese Ma-LSTM model was implemented with tensorflow. We train each model with 200 epoch on gpu environment and it took about 20 hours. Then we compared Word2Vec based model training result with Char2Vec based model training result. as a result, model of based with Char2Vec that initialized random weight record 75.1% validation dataset accuracy and model of based with Word2Vec that pretrained with 3 million words and phrase record 71.6% validation dataset accuracy. so Char2Vec is suitable alternate of Word2Vec to optimize high system memory requirements problem.

• Journal of KIISE
• /
• v.45 no.2
• /
• pp.134-140
• /
• 2018

A chat system is a computer program that understands user's miscellaneous utterances and generates appropriate responses. Sometimes a chat system needs to answer users' simple information-seeking questions. However, previous generative chat systems do not consider how to embed knowledge entities (i.e., subjects and objects in triple knowledge), essential elements for question-answering. The previous chat models have a disadvantage that they generate same responses although knowledge entities in users' utterances are changed. To alleviate this problem, we propose a knowledge entity embedding method for improving question-answering accuracies of a generative chat system. The proposed method uses a Siamese recurrent neural network for embedding knowledge entities and their synonyms. For experiments, we implemented a sequence-to-sequence model in which subjects and predicates are encoded and objects are decoded. The proposed embedding method showed 12.48% higher accuracies than the conventional embedding method based on a convolutional neural network.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.1
• /
• pp.1-8
• /
• 2023

In this paper, we propose a training method of a recommendation learning model that analyzes the battlefield situation and recommends a suitable hypothesis for the current situation. The proposed learning model uses the preference determined by comparing the two hypotheses as a label data to learn which hypothesis best analyzes the current battlefield situation. Our model is based on Siamese neural network architecture which uses the same weights on two different input vectors. The model takes two hypotheses as an input, and learns the priority between two hypotheses while sharing the same weights in the twin network. In addition, a score is given to each hypothesis through the proposed post-processing ranking algorithm, and hypotheses with a high score can be recommended to the commander in charge.

• Journal of Internet Computing and Services
• /
• v.20 no.1
• /
• pp.25-37
• /
• 2019

Inspired by the rapid development of deep learning and online biometrics-based authentication, we propose a handwritten one-time password authentication system which employs deep learning-based handwriting recognition and writer verification techniques. We design a convolutional neural network to recognize handwritten digits and a Siamese network to compute the similarity between the input handwriting and the genuine user's handwriting. We propose the first application of the second edition of NIST Special Database 19 for a writer verification task. Our system achieves 98.58% accuracy in the handwriting recognition task, and about 93% accuracy in the writer verification task based on four input images. We believe the proposed handwriting-based biometric technique has potential for use in a variety of online authentication services under the FIDO framework.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.37-53
• /
• 2023

The AI based intelligent command and control system can automatically analyzes the properties of intricate battlefield information and tactical data. In addition, commanders can receive situation analysis results and battlefield awareness through the system to support decision-making. It is necessary to build a battlefield situation analysis dataset similar to the actual battlefield situation for learning AI in order to provide decision-making support to commanders. In this paper, we explain the next step of the dataset construction method of the existing previous research, 'A Virtual Battlefield Situation Dataset Generation for Battlefield Analysis based on Artificial Intelligence'. We proposed a method to build the dataset required for the final battlefield situation analysis results to support the commander's decision-making and recognize the future battlefield. We developed 'Dataset Generator SW', a software tool to build a learning dataset for battlefield situation analysis, and used the SW tool to perform data labeling. The constructed dataset was input into the Siamese Network model. Then, the output results were inferred to verify the dataset construction method using a post-processing ranking algorithm.

• The Journal of the Korea Contents Association
• /
• v.20 no.6
• /
• pp.556-578
• /
• 2020

There are many different researches about how to analyze issues based on real-time news streams. But, there are few researches which analyze issues hierarchically from news articles and even a previous research of hierarchical issue analysis make clustering speed slower as the increment of news articles. In this paper, we propose a hierarchical and incremental clustering for semi real-time issue analysis on news articles. We trained siamese neural network based weighted cosine similarity model, applied this model to k-means algorithm which is used to make word clusters and converted news articles to document vectors by using these word clusters. Finally, we initialized an issue cluster tree from document vectors, updated this tree whenever news articles happen, and analyzed issues in semi real-time. Through the experiment and evaluation, we showed that up to about 0.26 performance has been improved in terms of NMI. Also, in terms of speed of incremental clustering, we also showed about 10 times faster than before.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1505-1514
• /
• 2022

Image matching is a crucial preprocessing step for effective utilization of multi-temporal and multi-sensor very high resolution (VHR) satellite images. Deep learning (DL) method which is attracting widespread interest has proven to be an efficient approach to measure the similarity between image pairs in quick and accurate manner by extracting complex and detailed features from satellite images. However, Image matching of VHR satellite images remains challenging due to limitations of DL models in which the results are depending on the quantity and quality of training dataset, as well as the difficulty of creating training dataset with VHR satellite images. Therefore, this study examines the feasibility of DL-based method in matching pair extraction which is the most time-consuming process during image registration. This paper also aims to analyze factors that affect the accuracy based on the configuration of training dataset, when developing training dataset from existing multi-sensor VHR image database with bias for DL-based image matching. For this purpose, the generated training dataset were composed of correct matching pairs and incorrect matching pairs by assigning true and false labels to image pairs extracted using a grid-based Scale Invariant Feature Transform (SIFT) algorithm for a total of 12 multi-temporal and multi-sensor VHR images. The Siamese convolutional neural network (SCNN), proposed for matching pair extraction on constructed training dataset, proceeds with model learning and measures similarities by passing two images in parallel to the two identical convolutional neural network structures. The results from this study confirm that data acquired from VHR satellite image database can be used as DL training dataset and indicate the potential to improve efficiency of the matching process by appropriate configuration of multi-sensor images. DL-based image matching techniques using multi-sensor VHR satellite images are expected to replace existing manual-based feature extraction methods based on its stable performance, thus further develop into an integrated DL-based image registration framework.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2018.10a
• /
• pp.617-620
• /
• 2018

딥러닝 기술에 있어서 대량의 학습 데이터가 필요하다는 한계점을 극복하기 위한 시도로서, 적은 데이터 만으로도 좋은 성능을 낼 수 있는 few-shot 학습 모델이 꾸준히 발전하고 있다. 하지만 few-shot 학습 모델의 가장 큰 단점인 적은 데이터로 인한 과적합 문제는 여전히 어려운 숙제로 남아있다. 본 논문에서는 모델 압축에 사용되는 distillation 기법을 사용하여 few-shot 학습 모델의 학습 문제를 개선하고자 한다. 이를 위해 대표적인 few-shot 모델인 Siamese Networks, Prototypical Networks, Matching Networks에 각각 distillation을 적용하였다. 본 논문의 실험결과로써 단순히 결과값에 대한 참/거짓 뿐만 아니라, 참/거짓에 대한 신뢰도까지 같이 학습함으로써 few-shot 모델의 학습 문제 개선에 도움이 된다는 것을 실험적으로 증명하였다.