• Journal of Korea Multimedia Society
• /
• v.16 no.5
• /
• pp.558-565
• /
• 2013

Mammography, the process of using X-ray to examine the woman breast, is the one of the effective tools for detecting breast cancer at an early state. In screening mammogram, Computer-Aided Detection(CAD) system helps radiologist to diagnose cases by detecting malignant masses. A mass is an important lesion in the breast that can indicate a cancer. Due to various shapes and unclear boundaries of the masses, detecting breast masses is considered a challenging task. To this end, CAD system detects a lot of regions of interest including normal tissues. Thus it is important to develop the well-organized classifier. In this paper, we propose an enhanced sparse representation (SR) based classifier using Fisher discrimination dictionary learning. Experimental results show that the proposed method outperforms the existing support vector machine (SVM) classifier.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.12
• /
• pp.2946-2952
• /
• 2014

Among the Example based Super Resolution(SR) techniques, Neighbor embedding(NE) has been inspired by manifold learning method, particularly locally linear embedding. However, the poor generalization of NE decreases the performance of such algorithm. The sizes of local training sets are always too small to improve the performance of NE. We propose the Learning Sparse-Neighbor Image Representation baesd on SVR having an excellent generalization ability to solve this problem. Given a low resolution image, we first use bicubic interpolation to synthesize its high resolution version. We extract the patches from this synthesized image and determine whether each patch corresponds to regions with high or low spatial frequencies. After the weight of each patch is obtained by our method, we used to learn separate SVR models. Finally, we update the pixel values using the previously learned SVRs. Through experimental results, we quantitatively and qualitatively confirm the improved results of the proposed algorithm when comparing with conventional interpolation methods and NE.

• Journal of the Korean earth science society
• /
• v.35 no.6
• /
• pp.484-497
• /
• 2014

This study aimed to investigate high school students' conceptions of plate tectonics. Seventy students (N=70) in their 2 year of high schools in the province of Chungcheong-do participated in this study, and they took a conception test of visual representation. We conducted a semi-structured interview with 10 volunteering participants out of seventy. After learning about the concept of plate tectonics, this study found that participants ended up having alternative conceptions relating to terminology, meaning of colors, plates' movement, plates' boundaries, position and cause of melting, mantle's physical conditions, and driving forces of plate motion. The conceptions that the participants held after class were organically related, which included the meaning of colors, mantle's physical characteristic, and driving forces of plate movement. In addition, the visual representation used for teaching plate tectonics influenced the students' understanding about terminologies, plates' boundaries, position of melting, and the physical characteristic of mantle. The study found that there were the factors of visual representation that caused the learners to create alternative conceptions in learning about plate tectonics.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.4
• /
• pp.1463-1480
• /
• 2014

It is well known that sparse code is effective for feature extraction of face recognition, especially sparse mode can be learned in the kernel space, and obtain better performance. Some recent algorithms made use of single kernel in the sparse mode, but this didn't make full use of the kernel information. The key issue is how to select the suitable kernel weights, and combine the selected kernels. In this paper, we propose a novel multiple kernel sparse representation based classification for face recognition (MKSRC), which performs sparse code and dictionary learning in the multiple kernel space. Initially, several possible kernels are combined and the sparse coefficient is computed, then the kernel weights can be obtained by the sparse coefficient. Finally convergence makes the kernel weights optimal. The experiments results show that our algorithm outperforms other state-of-the-art algorithms and demonstrate the promising performance of the proposed algorithms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.3
• /
• pp.1464-1480
• /
• 2019

Robust tracking of infrared (IR) pedestrian targets with various backgrounds, e.g. appearance changes, illumination variations, and background disturbances, is a great challenge in the infrared image processing field. In the paper, we address a new tracking method for IR pedestrian targets via multi-feature local sparse representation (SR), which consists of three important modules. In the first module, a multi-feature local SR model is constructed. Considering the characterization of infrared pedestrian targets, the gray and edge features are first extracted from all target templates, and then fused into the model learning process. In the second module, an effective tracker is proposed via the learned model. To improve the computational efficiency, a sliding window mechanism with multiple scales is first used to scan the current frame to sample the target candidates. Then, the candidates are recognized via sparse reconstruction residual analysis. In the third module, an adaptive dictionary update approach is designed to further improve the tracking performance. The results demonstrate that our method outperforms several classical methods for infrared pedestrian tracking.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.11a
• /
• pp.910-913
• /
• 2021

Successor representation (SR) 은 두뇌 내 해마의 공간 세포가 인지맵을 구성하여 환경을 학습하고, 이를 활용하여 변화하는 환경에서 유연하게 최적 전략을 수립하는 기전을 모사한 강화학습 방법이다. 특히, 학습한 환경 정보를 활용, 환경 구조 안에서 목표가 변화할 때 강인하게 대응하여 일반 model-free 강화학습에 비해 빠르게 보상 변화에 적응하고 최적 전략을 찾는 것으로 알려져 있다. 본 논문에서는 SR 기반 강화학습 알고리즘이 보상의 변화와 더불어 환경 구조, 특히 환경의 상태 천이 확률이 변화하여 보상의 변화를 유발하는 상황에서 어떠한 성능을 보이는 지 확인하였다. 벤치마크 알고리즘으로 SR 의 특성을 목적 기반 강화학습으로 통합한 SR-Dyna 를 사용하였고, 환경 상태 천이 불확실성과 보상 변화가 동시에 나타나는 2-stage 마르코프 의사결정 과제를 실험 환경으로 사용하였다. 시뮬레이션 결과, SR-Dyna 는 환경 내 상태 천이 확률 변화에 따른 보상 변화에는 적절히 대응하지 못하는 결과를 보였다. 본 결과를 통해 두뇌의 강화학습과 알고리즘 강화학습의 차이를 이해하여, 환경 변화에 강인한 강화학습 알고리즘 설계를 기대할 수 있다.

• The Journal of Korea Robotics Society
• /
• v.19 no.2
• /
• pp.196-202
• /
• 2024

The ability to understand given environments and plan a sequence of actions leading to goal state is crucial for personal service robots. With recent advancements in deep learning, numerous studies have proposed methods for state representation in planning. However, previous works lack explicit information about relationships between objects when the state observation is converted to a single visual embedding containing all state information. In this paper, we introduce graph-based state representation that incorporates both object and relationship features. To leverage these advantages in addressing the task planning problem, we propose a Graph Neural Network (GNN)-based subgoal prediction model. This model can extract rich information about object and their interconnected relationships from given state graph. Moreover, a search-based algorithm is integrated with pre-trained subgoal prediction model and state transition module to explore diverse states and find proper sequence of subgoals. The proposed method is trained with synthetic task dataset collected in simulation environment, demonstrating a higher success rate with fewer additional searches compared to baseline methods.

• International journal of advanced smart convergence
• /
• v.8 no.4
• /
• pp.75-81
• /
• 2019

Though recent advancement of deep learning methods have provided satisfactory results from large data domain, somehow yield poor performance on few-shot classification tasks. In order to train a model with strong performance, i.e. deep convolutional neural network, it depends heavily on huge dataset and the labeled classes of the dataset can be extremely humongous. The cost of human annotation and scarcity of the data among the classes have drastically limited the capability of current image classification model. On the contrary, humans are excellent in terms of learning or recognizing new unseen classes with merely small set of labeled examples. Few-shot learning aims to train a classification model with limited labeled samples to recognize new classes that have neverseen during training process. In this paper, we increase the backbone depth of the embedding network in orderto learn the variation between the intra-class. By increasing the network depth of the embedding module, we are able to achieve competitive performance due to the minimized intra-class variation.

• The Mathematical Education
• /
• v.56 no.2
• /
• pp.131-145
• /
• 2017

The representation of irrational numbers has a key role in the learning of irrational numbers. However, transparent and finite representation of irrational numbers does not exist in school mathematics context. Therefore, many students have difficulties in understanding irrational numbers as an 'Object'. For this reason, this research explored how mathematics textbooks affected to students' understanding of irrational numbers in the view of process and object. Specifically we analyzed eight textbooks based on current curriculum and used framework based on previous research. In order to supplement the result derived from textbook analysis, we conducted questionnaires on 42 middle school students. The questions in the questionnaires were related to the representation and calculation of irrational numbers. As a result of this study, we found that mathematics textbooks develop contents in order of process-object, and using 'non repeating decimal', 'numbers cannot be represented as a quotient', 'numbers with the radical sign', 'number line' representation for irrational numbers. Students usually used a representation of non-repeating decimal, although, they used a representation of numbers with the radical sign when they operate irrational numbers. Consequently, we found that mathematics textbooks affect students to understand irrational numbers as a non-repeating irrational numbers, but mathematics textbooks have a limitation to conduce understanding of irrational numbers as an object.

• International Journal of Computer Science & Network Security
• /
• v.21 no.9
• /
• pp.281-291
• /
• 2021

The Islamic jurisprudential legal system represents an essential component of the Islamic religion, that governs many aspects of Muslims' daily lives. This creates many questions that require interpretations by qualified specialists, or Muftis according to the main sources of legislation in Islam. The Islamic jurisprudence is usually classified into branches, according to which the questions can be categorized and classified. Such categorization has many applications in automated question-answering systems, and in manual systems in routing the questions to a specialized Mufti to answer specific topics. In this work we tackle the problem of automatic categorisation of Islamic jurisprudential legal questions using deep learning techniques. In this paper, we build a hierarchical deep learning model that first extracts the question text features at two levels: word and sentence representation, followed by a text classifier that acts upon the question representation. To evaluate our model, we build and release the largest publicly available dataset of Islamic questions and answers, along with their topics, for 52 topic categories. We evaluate different state-of-the art deep learning models, both for word and sentence embeddings, comparing recurrent and transformer-based techniques, and performing extensive ablation studies to show the effect of each model choice. Our hierarchical model is based on pre-trained models, taking advantage of the recent advancement of transfer learning techniques, focused on Arabic language.