• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.3798-3814
• /
• 2022

Social recommendation algorithm can alleviate data sparsity and cold start problems in recommendation system by integrated social information. Among them, matrix-based decomposition algorithms are the most widely used and studied. Such algorithms use dot product operations to calculate the similarity between users and items, which ignores user's potential preferences, reduces algorithms' recommendation accuracy. This deficiency can be avoided by a metric learning-based social recommendation algorithm, which learns the distance between user embedding vectors and item embedding vectors instead of vector dot-product operations. However, previous works provide no theoretical explanation for its plausibility. Moreover, most works focus on the indirect impact of social friends on user's preferences, ignoring the direct impact on user's rating preferences, which is the influence of user rating preferences. To solve these problems, this study proposes a user bias drift social recommendation algorithm based on metric learning (BDML). The main work of this paper is as follows: (1) the process of introducing metric learning in the social recommendation scenario is introduced in the form of equations, and explained the reason why metric learning can replace the click operation; (2) a new user bias is constructed to simultaneously model the impact of social relationships on user's ratings preferences and user's preferences; Experimental results on two datasets show that the BDML algorithm proposed in this study has better recommendation accuracy compared with other comparison algorithms, and will be able to guarantee the recommendation effect in a more sparse dataset.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2011년도 춘계학술발표대회
• /
• pp.346-349
• /
• 2011

In this paper, we design a perceptually invisible dot pattern layout and its recognition scheme, and we apply the recognition scheme into a smart self learning aid for interactive learning aid. To increase maximum information capacity and also increase robustness to the noises, we design a ECC (error correcting code) based dot pattern with directional vector indicator. To make a smart self-learning aid, we embed the micro dot pattern (20 information bit + 15 ECC bits + 9 layout information bit) using K ink (CMYK) and extract the dot pattern using IR (infrared) LED and IR filter based camera, which is embedded in the smart pen. The reason we use K ink is that K ink is a carbon based ink in nature, and carbon is easily recognized with IR even without light. After acquiring IR camera images for the dot patterns, we perform layout adjustment using the 9 layout information bit, and extract 20 information bits from 35 data bits which is composed of 20 information bits and 15 ECC bits. To embed and extract information bits, we use topology based dot pattern recognition scheme which is robust to geometric distortion which is very usual in camera based recognition scheme. Topology based pattern recognition traces next information bit symbols using topological distance measurement from the pivot information bit. We implemented and experimented with sample patterns, and it shows that we can achieve almost 99% recognition for our embedding patterns.

• 지능정보연구
• /
• 제27권4호
• /
• pp.73-95
• /
• 2021

본 연구는 Node2vec 그래프 임베딩 방법과 Light GBM 링크 예측을 활용해 우리나라 식음료 산업의 미개척 수출 후보국가를 탐색한다. Node2vec은 네트워크의 공통 이웃 개수 등을 기반으로 하는 기존의 링크 예측 방법에 비해 상대적으로 취약하다고 알려져 있던 네트워크의 구조적 등위성 표현의 한계를 개선한 방법이다. 따라서 해당 방법은 네트워크의 커뮤니티 탐지와 구조적 등위성 모두에서 우수한 성능을 나타내는 것으로 알려져 있다. 이에 본 연구는 이상의 방법을 우리나라 식음료 산업의 국제 무역거래 정보에 적용했다. 이를 통해 해당 산업의 글로벌 가치사슬 관계에서 우리나라의 광범위한 마진 다각화 효과를 창출하는데 기여하고자 한다. 본 연구의 결과를 통해 도출된 최적의 예측 모델은 0.95의 정밀도와 0.79의 재현율을 기록하며 0.86의 F1 score를 기록해 우수한 성능을 나타냈다. 이상의 모델을 통해 도출한 우리나라의 잠재적 수출 후보국가들의 결과는 추가 조사를 통해 대부분 적절하게 나타난 것을 알 수 있었다. 이상의 내용을 종합하여 본 연구는 Node2vec과 Light GBM을 응용한 링크 예측 방법의 실무적 활용성에 대해 시사할 수 있었다. 그리고 모델을 학습하며 링크 예측을 보다 잘 수행할 수 있는 가중치 업데이트 전략에 대해서도 유용한 시사점을 도출할 수 있었다. 한편, 본 연구는 그래프 임베딩 기반의 링크 예측 관련 연구에서 아직까지 많이 수행된 적 없는 무역거래에 이를 적용했기에 정책적 활용성도 갖고 있다. 본 연구의 결과는 최근 미중 무역갈등이나 일본 수출 규제 등과 같은 글로벌 가치사슬의 변화에 대한 빠른 대응을 지원하며 정책적 의사결정을 위한 도구로써 충분한 유용성이 있다고 생각한다.

• 한국전자거래학회지
• /
• 제24권2호
• /
• pp.1-14
• /
• 2019

게임은 소프트웨어 특성상 출시 후 사용자들의 반응을 빠르게 파악하여 개선하는 것이 중요하다. 하지만 구글 플레이 앱 스토어 등 사용자들이 게임을 다운로드하고 리뷰를 올릴 수 있는 대부분의 사이트들은 게임 리뷰에 대한 매우 제한적이고 모호한 분류 기능만을 제공한다. 따라서 본 논문에서는 사용자들이 사이트에 올린 게임 리뷰를 보다 명확하고 운영에 유용한 주제들로 자동 분류하는 시스템을 개발한다. 본 논문에서 개발한 시스템은 리뷰에 포함된 단어들을 대표적인 단어 임베딩 모델인 word2vec을 사용하여 벡터들로 변환하고, 이 벡터들과 각 주제 간 유사도를 측정하여 해당 리뷰를 관련된 주제로 분류한다. 특히 분류 성능에 직접적인 영향을 미치는 벡터 간 유사도 측정 방법을 선택하기 위해 본 연구에서는 대표적인 벡터 간 유사도 측정 방법인 유클리디안 유사도, 코사인 유사도, 확장된 자카드 유사도의 성능을 실제 데이터를 사용하여 비교하였다. 또한 어떤 리뷰가 둘 이상의 주제에 해당하는 경우를 위해 임계값에 기반한 다중 분류 방법을 사용하였다. 구글 플레이 앱스토어의 실제 데이터를 사용한 실험 결과 본 시스템은 95%까지의 정확도를 보임을 확인하였다.

• 융합신호처리학회논문지
• /
• 제16권4호
• /
• pp.122-128
• /
• 2015

멀티미디어 정보들이 인터넷 공간에 확산됨에 따라서 원래 정보 소유자의 권리 보호와 원본 증명 등의 문제가 대두되고 있다. DCT, DFT, DWT 등의 여러 영상 변환들을 이용하여 소유권의 징표로 워터마크를 원본 영상에 삽입하는 방법을 많이 사용하였으나, 보다 최근에는 수치해석 분야에 많이 쓰이는 SVD(Singular Value Decomposition) 방법을 부가적으로 사용하고 있다. 본 논문에서는 SVD의 특이 벡터와 동시에 Gabor 코사인과 사인 변환을 이용하여 디지털 표지 영상에 워터마크를 삽입하고 추출하는 방법을 제안한다. 워터마크가 삽입된 영상에 잡음, 공간 변형, 필터링, 압축 등의 공격을 가한 후, GCST-SVD의 워터마크 추출 알고리즘을 적용한다. 워터마킹 성능을 평가하기 위해서 삽입한 워터마크와 추출한 워터마크 사이의 유사성 척도로써 정규화한 상관계수값을 측정한다. 또한 추출한 워터마크 영상으로부터 시각적으로 직접 원본 워터마크인지를 판단한다. 가장 낮은 수직 교류 주파수 대역에 워터마크를 삽입한 실험으로부터 SVD의 특이 벡터를 이용한 워터마킹 방법은 대부분 공격에서 0.9이상의 큰 상관값과 삽입한 워터마크의 특징들을 시각적으로 파악할 수 있었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권7호
• /
• pp.2572-2589
• /
• 2014

Reversible data hiding is a technique for recovering original images without any distortion after secret data are extracted from the image. The technique continues to attract attention from many researchers. In this paper, we introduce a new reversible data hiding scheme based on the adjacent index differences of vector quantization (VQ) indices. The proposed scheme exploits the differences between two adjacent indices to embed secret data. Experimental results show that our scheme can achieve a lower compression rate than an earlier scheme by Yang and Lin. Our scheme's average compression rate, 0.44 bpp, outperforms that of Yang and Lin's scheme, which averages 0.53 bpp. Moreover, the embedding capacity of our scheme can rise to 1.45 bpi, which also is superior to that of Chang et al.'s scheme [35] (1.00 bpi)Yang and Lin's scheme [27] (0.91 bpi) as well as Chang et al.'s scheme [26] (0.74 bpi).

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제10권12호
• /
• pp.5643-5656
• /
• 2016

The detection accuracy of steganalysis depends on many factors, including the embedding algorithm, the payload size, the steganalysis feature space and the properties of the cover source. In practice, the cover source mismatch (CSM) problem has been recognized as the single most important factor negatively affecting the performance. To address this problem, we propose a new framework for blind, universal steganalysis which uses traditional steganalyst features. Firstly, cover images with the same statistical properties are searched from a reference image database as aided samples. The test image and its aided samples form a whole test set. Then, by assuming that most of the aided samples are innocent, we conduct outlier detection on the test set to judge the test image as cover or stego. In this way, the framework has removed the need for training. Hence, it does not suffer from cover source mismatch. Because it performs anomaly detection rather than classification, this method is totally unsupervised. The results in our study show that this framework works superior than one-class support vector machine and the outlier detector without considering the image retrieval process.

• Journal of Electrical Engineering and Technology
• /
• 제13권4호
• /
• pp.1614-1622
• /
• 2018

The research related to fault diagnosis in permanent magnet synchronous motors (PMSMs) has attracted considerable attention in recent years because various faults such as permanent magnet demagnetization and short-circuited turns can occur and result in unexpected failure of motor related system. Several conventional current and back electromotive force (BEMF) analysis techniques were proposed to detect certain faults in PMSMs; however, they generally deal with a single fault only. On the contrary, cases of multiple faults are common in PMSMs. We propose a fault diagnosis method for PMSMs with single and multiple combined faults. Our method uses three phase BEMF voltages based on the fast Fourier transform (FFT), support vector machine(SVM), and visualization tools for identifying fault types and severities in PMSMs. Principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE) are used to visualize the high-dimensional data into two-dimensional space. Experimental results show good visualization performance and high classification accuracy to identify fault types and severities for single and multiple faults in PMSMs.

• Journal of Information Processing Systems
• /
• 제17권3호
• /
• pp.599-614
• /
• 2021

This paper proposes a digital signage system based on an intelligent recommendation model. The proposed system consists of a server and an edge. The server manages the data, learns the advertisement recommendation model, and uses the trained advertisement recommendation model to determine the advertisements to be promoted in real time. The advertisement recommendation model provides predictions for various products and probabilities. The purchase index between the product and weather data was extracted and reflected using correlation analysis to improve the accuracy of predicting the probability of purchasing a product. First, the user information and product information are input to a deep neural network as a vector through an embedding process. With this information, the product candidate group generation model reduces the product candidates that can be purchased by a certain user. The advertisement recommendation model uses a wide and deep recommendation model to derive the recommendation list by predicting the probability of purchase for the selected products. Finally, the most suitable advertisements are selected using the predicted probability of purchase for all the users within the advertisement range. The proposed system does not communicate with the server. Therefore, it determines the advertisements using a model trained at the edge. It can also be applied to digital signage that requires immediate response from several users.

• Geomechanics and Engineering
• /
• 제30권2호
• /
• pp.107-121
• /
• 2022

Coal pillar assessment is of broad importance to underground engineering structure, as the pillar failure can lead to enormous disasters. Because of the highly non-linear correlation between the pillar failure and its influential attributes, conventional forecasting techniques cannot generate accurate outcomes. To approximate the complex behavior of coal pillar, this paper elucidates a new idea to forecast the underground coal pillar stability using combined unsupervised-supervised learning. In order to build a database of the study, a total of 90 patterns of pillar cases were collected from authentic engineering structures. A state-of-the art feature depletion method, t-distribution symmetric neighbor embedding (t-SNE) has been employed to reduce significance of actual data features. Consequently, an unsupervised machine learning technique K-mean clustering was followed to reassign the t-SNE dimensionality reduced data in order to compute the relative class of coal pillar cases. Following that, the reassign dataset was divided into two parts: 70 percent for training dataset and 30 percent for testing dataset, respectively. The accuracy of the predicted data was then examined using support vector classifier (SVC) model performance measures such as precision, recall, and f₁-score. As a result, the proposed model can be employed for properly predicting the pillar failure class in a variety of underground rock engineering projects.