• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.2
• /
• pp.1134-1147
• /
• 2017

With the rise in popularity of photographic and video cameras, an increasing number of fields are now using thermal imaging cameras. One such application is in the diagnosis of breast cancer, as thermal imaging provides a low-cost and noninvasive method. Thermal imaging is particularly safe for pregnant women, and those with large, dense, or sensitive breasts. In addition, excessive doses of radiation, which may be used in traditional methods of breast cancer detection, can increase the risk of cancer. This paper presents one method of breast cancer detection. Breast images were taken using a thermal camera, with preliminary experiments conducted on Cambodian women. Then the experimental results were analyzed and compared using Shannon entropy and logistic regression.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.10
• /
• pp.4080-4097
• /
• 2020

In recent years, convolutional neural network (CNN) has become the primary method for face detection. But its shortcomings are obvious, such as expensive calculation, heavy model, etc. This makes CNN difficult to use on the mobile devices which have limited computing and storage capabilities. Therefore, the design of lightweight CNN for face detection is becoming more and more important with the popularity of smartphones and mobile Internet. Based on the CPU real-time face detector FaceBoxes, we propose a multi-task lightweight face detector, which has low computing cost and higher detection precision. First, to improve the detection capability, the squeeze and excitation modules are used to extract attention between channels. Then, the textual and semantic information are extracted by shallow networks and deep networks respectively to get rich features. Finally, the landmark detection module is used to improve the detection performance for small faces and provide landmark data for face alignment. Experiments on AFW, FDDB, PASCAL, and WIDER FACE datasets show that our algorithm has achieved significant improvement in the mean average precision. Especially, on the WIDER FACE hard validation set, our algorithm outperforms the mean average precision of FaceBoxes by 7.2%. For VGA-resolution images, the running speed of our algorithm can reach 23FPS on a CPU device.

• Proceedings of the Korean Information Science Society Conference
• /
• 2011.06c
• /
• pp.105-108
• /
• 2011

범정부적인 차원에서 기록물은 종이 위주의 생산방식에서 전자문서방식으로 변하고 있다. 이미, 많은 국가에서 표준을 정의하여 기록물에 대한 연구가 진행되고 있다. 또한, 기록물을 효과적으로 저장하기 위한 기록물 보존소에 대한 연구도 활발하게 진행 되고 있다. 대부분의 기록물 보존소는 OAIS 참조모델을 기반으로 구성이 되고 있으며, SIP, AIP, DIP 패키지 형태로 수집, 보관, 배포되고 있다. 이러한 기록물 패키지들은 다양한 메타데이터 스키마를 포함 할 수 있어서, 여러 종류의 기록물들의 수집, 보관, 배포가 용이 하게 하지만, 기록물 보존소에 저장되어 있는 기록물 패키지를 검색하기 위해서는 다양한 스키마를 모두 검색 할 수 있어야 하는 문제점이 존재한다. 따라서 본 논문에서는 기록물 패키지를 위한 신경망 회로 기반 자동 스키마 매칭 기법을 제안 하고자 한다. 신경망 회로 기반 자동분류 알고리즘을 통하여 기록물 패키지 안에 존재하는 다양한 형태의 메타데이터 스키마들에 대한 검색을 가능하게 한다. 또한, 실험을 통하여 제안하는 방법의 정확성을 확인 하였다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.12
• /
• pp.6009-6027
• /
• 2019

Support vector machine (SVM) classifiers have been widely used for object detection. These methods usually locate the object by finding the region with maximal score in an image. With bag-of-features representation, the SVM score of an image region can be written as the sum of its inside feature-weights. As a result, the searching process can be executed efficiently by using strategies such as branch-and-bound. However, the feature-weight derived by optimizing region classification cannot really reveal the category knowledge of a feature-point, which could cause bad localization. In this paper, we represent a region in an image by a collection of local feature-points and determine the object by the region with the maximum posterior probability of belonging to the object class. Based on the Bayes' theorem and Naive-Bayes assumptions, the posterior probability is reformulated as the sum of feature-scores. The feature-score is manifested in the form of the logarithm of a probability ratio. Instead of estimating the numerator and denominator probabilities separately, we readily employ the density ratio estimation techniques directly, and overcome the above limitation. Experiments on a car dataset and PASCAL VOC 2007 dataset validated the effectiveness of our method compared to the baselines. In addition, the performance can be further improved by taking advantage of the recently developed deep convolutional neural network features.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.6
• /
• pp.2056-2069
• /
• 2014

In order to implement interactive and personalized Web services properly, it is necessary to understand the tangible and intangible responses of the users and to recognize their emotional states. Recently, some studies have attempted to build emotional state estimation models based on facial expressions. Most of these studies have applied multiple regression analysis (MRA), artificial neural network (ANN), and support vector regression (SVR) as the prediction algorithm, but the prediction accuracies have been relatively low. In order to improve the prediction performance of the emotion prediction model, we propose a novel SVR model that is optimized using a genetic algorithm (GA). Our proposed algorithm-GASVR-is designed to optimize the kernel parameters and the feature subsets of SVRs in order to predict the levels of two aspects-valence and arousal-of the emotions of the users. In order to validate the usefulness of GASVR, we collected a real-world data set of facial responses and emotional states via a survey. We applied GASVR and other algorithms including MRA, ANN, and conventional SVR to the data set. Finally, we found that GASVR outperformed all of the comparative algorithms in the prediction of the valence and arousal levels.

• Journal of Internet Computing and Services
• /
• v.19 no.3
• /
• pp.43-48
• /
• 2018

In this paper, we propose an indoor-space recognition using DNN and super-pixel. In order to recognize the indoor space from the image, segmentation process is required for dividing an image Super-pixel is performed algorithm which can be divided into appropriate sizes. In order to recognize each segment, features are extracted using a proposed method. Extracted features are learned using DNN, and each segment is recognized using the DNN model. Experimental results show the performance comparison between the proposed method and existing algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.9
• /
• pp.4412-4428
• /
• 2018

The purpose of this work is to solve the problem of representing an entire video using Convolutional Neural Network (CNN) features for human action recognition. Recently, due to insufficient GPU memory, it has been difficult to take the whole video as the input of the CNN for end-to-end learning. A typical method is to use sampled video frames as inputs and corresponding labels as supervision. One major issue of this popular approach is that the local samples may not contain the information indicated by the global labels and sufficient motion information. To address this issue, we propose a binary hashing method to enhance the local feature extractors. First, we extract the local features and aggregate them into global features using maximum/minimum pooling. Second, we use the binary hashing method to capture the motion features. Finally, we concatenate the hashing features with global features using different normalization methods to train the classifier. Experimental results on the JHMDB and MPII-Cooking datasets show that, for these new local features, binary hashing mapping on the sparsely sampled features led to significant performance improvements.

• Journal of the Institute of Convergence Signal Processing
• /
• v.3 no.2
• /
• pp.23-29
• /
• 2002

In this paper we proposed the user identification system using hybrid biometric information and non-contact IC card to improve the accuracy of the system. The hybrid biometric information consists of the face image, the iris image, and the 4-digit voice password of user. And the non-contact IC card provides the base information of user If the distance between the sample hybrid biometric Information corresponding to the base information of user and the measured biometric information is less than the given threshold value, the identification is accepted. Otherwise it is rejected. Through the result of experimentation, this paper shows that the proposed method has better identification rate than the conventional identification method.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2007.04a
• /
• pp.101-104
• /
• 2007

As the proportion of underground construction increases, the impact of inappropriate selection of a underground construction method for a construction size increases. The purpose of this study is to develop an objective way of selecting an excavation method. There have been several attempts to achieve the same goal using various data mining methods such as the artificial neural network, the support vector machine, and the case-based reasoning. However, they focused only on the selection of a retaining wall construction method out of six types of retaining walls. When we categorized an underground construction work into four groups and added more number of independent variables (i.e., more number of construction methods), the predictability decreased. As an alternative, we developed a decision tree by analyzing 25 earthwork cases with detailed information. We implemented the developed decision tree as a computer-supported program called Dr. underground and are still in the process of validating and revising the decision tree. This study is still in a preliminary stage and will be improved by collecting and analyzing more cases.

• Fibers and Polymers
• /
• v.7 no.2
• /
• pp.203-212
• /
• 2006

The purpose of this study was to examine the effects of the structural properties of plain knit fabrics on the subjective perception of textures, sensibilities, and preference among consumers. This study, then, aimed to provide useful information with respect to planning and designing knitted fabrics by predicting the subjective characteristics analyzed according to their structural properties. For this purpose, we employed statistical analysis tools, such as factor and regression analysis and an adaptive-network-based fuzzy inference system(ANFIS), thereby combining the merits of fuzzy and neural networks and presupposing a non-linear relationship. Through factor analysis, we also categorized the subjective textures into 'roughness', 'softness', 'bulkiness' and 'stretch-ability' with R2=70.32%: and categorized the sensibilities into 'Stable/Neat', 'Natural/Comfortable' and 'Feminine/Elegant' with R2=68.12%. We analyzed subjective textures, sensibilities, and preference with ANFIS, assuming non-linear relationships; consequently, we were able to generate three or four fuzzy rules using wool/rayon fiber content and loop length as input data. The textures of roughness and softness exhibited a linear relationship, but other subjective characteristics demonstrated a non-linear input-output relationship. Compared with linear regression analysis, the ANFIS exhibited had higher predictive power with respect to predicting subjective characteristics.