• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.52 no.1
• /
• pp.45-50
• /
• 2003

Texture analysis has been efficiently utilized in the area of terrain classification. In this application features have been obtained in the 2D image domain. This paper suggests 3D co-occurrence texture features by extending the concept of co-occurrence to 3D world. The suggested 3D features are described using co-occurrence histogram of digital elevations at two contiguous position as co-occurrence matrix. The practical construction of co-occurrence matrix limits the number of levels of digital elevation. If the digital elevation is quantized into the number of levels over the whole DEM(Digital Elevation Map), the distinctive features can not be obtained. To resolve the quantization problem, we employ local quantization technique which preserves the variation of elevations. Experiments has been carried out to verify the proposed 3D co-occurrence features, and the addition of the suggested features significantly improves the classification accuracy.

• International journal of advanced smart convergence
• /
• v.12 no.3
• /
• pp.13-18
• /
• 2023

This paper aims to investigate data features for neighbor path selection (NPS) in computer network with regional failures. It is necessary to find an available alternate communication path in advance when regional failures due to earthquakes or forest fires occur simultaneously. We describe previous general heuristics and simulation heuristic to solve the NPS problem in the regional fault network. The data features of general heuristics using proximity and sharing factor and the data features of simulation heuristic using machine learning are explained through examples. Simulation heuristic may be better than general heuristics in terms of communication success. However, additional data features are necessary in order to apply the simulation heuristic to the real environment. We propose novel data features for NPS in computer network with regional failures and Keras modeling for computing the communication success probability of candidate neighbor path.

• Journal of Engineering Education Research
• /
• v.18 no.2
• /
• pp.65-76
• /
• 2015

Despite its ineffectiveness, the dominant pedagogy for engineering education is still "chalk & talk". Meanwhile, student-centered learning models have been highlighted for strong communication, teamwork skills, deep understanding and analysis on social, environmental and economic issues as well as application of their engineering knowledge in practice. Among others, on problem- and project-based learning, this article examines theoretical background and detailed features and a comparison between both learning models including common and different features from the previous theoretical and empirical studies. It reviews some cases of where they have been practiced successfully in engineering, and further, applied strategies for engineering education are suggested.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.35 no.4
• /
• pp.142-148
• /
• 2012

Release planning for incremental software development is to select and assign features in sequence of releases along a specified planning horizon. It includes the technical precedence inherent in the features, the conflicting priorities as determined by the representative stakeholders, and the balance between required and available resources. The complexity of this consideration is getting more complicated when planning releases in software product lines. The problem is formulated as a precedence-constrained multiple 0-1 knapsack problem. In this research a genetic algorithm is developed for solving the release planning problems in software product lines as well as tests for the proposed solution methodology are conducted using data generated randomly.

• Journal of the Korean Society for Precision Engineering
• /
• v.10 no.1
• /
• pp.77-88
• /
• 1993

In this paper, we propose a stereo vision system to solve correspondence problem with large disparity and sudden change in environment which result from small distance between camera and working objects. First of all, a specific feature is divided by predfined elementary feature. And then these are combined to obtain coded data for solving correspondence problem. We use Neural Network to extract elementary features from specific feature and to have adaptability to noise and some change of the shape. Fourier transformation and Log-polar mapping are used for obtaining appropriate Neural Network input data which has a shift, scale, and rotation invariability. Finally, we use associative memory to obtain coded data of the specific feature from the combination of elementary features. In spite of specific feature with some variation in shapes, we could obtain satisfactory 3-dimensional data from corresponded codes.

• Journal of Korean Elementary Science Education
• /
• v.39 no.1
• /
• pp.40-53
• /
• 2020

This study analyzed the features of norms formed in mobile-based science problem-solving and interpreted them from the perspective of digital citizenship. For this, we implemented two mobile-based science problem-solving activities for nine elementary school preparatory teachers composed of two groups, and analyzed the norms observed in their activities. As a result, four norms were found as follows. First, the information presented as a basis should be scientifically reliable. Second, the information need to be searched widely, but the information should be selected and reconstructed in relation to the problem. Third, in a mobile environment, the ideas should be clearly expressed and understood. Fourth, courtesies in mobile interaction should be represented more politely than in face-to-face interaction. Based on the four norms found in this study, we discussed the characteristics and factors of digital citizenship for judging scientifically reliable and relevant information and expressing ideas clearer in mobile environment. Finally, we suggested the educational implications for fostering digital citizens who can judge and practice 'science issues' in a 'mobile environment'.

• Journal of Korea Multimedia Society
• /
• v.24 no.12
• /
• pp.1673-1681
• /
• 2021

Item cold start is a well studied problem in the research field of recommender systems. Still, many existing collaborative filters cannot recommend items accurately when only a few user-item interaction data are available for newly introduced items (Cold items). We propose a interaction feature prediction method to mitigate item cold start problem. The proposed method predicts the interaction features that collaborative filters can calculate for the cold items. For prediction, in addition to content features of the cold-items used by state-of-the-art methods, our method exploits the interaction features of k-nearest content neighbors of the cold-items. An attention network is adopted to extract appropriate information from the interaction features of the neighbors by examining the contents feature similarity between the cold-item and its neighbors. Our evaluation on a real dataset CiteULike shows that the proposed method outperforms state-of-the-art methods 0.027 in Recall@20 metric and 0.023 in NDCG@20 metric.

• ETRI Journal
• /
• v.18 no.1
• /
• pp.29-41
• /
• 1996

This paper describes a method to select a suitable feature for speech recognition using information theoretic measure. Conventional speech recognition systems heuristically choose a portion of frequency components, cepstrum, mel-cepstrum, energy, and their time differences of speech waveforms as their speech features. However, these systems never have good performance if the selected features are not suitable for speech recognition. Since the recognition rate is the only performance measure of speech recognition system, it is hard to judge how suitable the selected feature is. To solve this problem, it is essential to analyze the feature itself, and measure how good the feature itself is. Good speech features should contain all of the class-related information and as small amount of the class-irrelevant variation as possible. In this paper, we suggest a method to measure the class-related information and the amount of the class-irrelevant variation based on the Shannon's information theory. Using this method, we compare the mel-scaled FFT, cepstrum, mel-cepstrum, and wavelet features of the TIMIT speech data. The result shows that, among these features, the mel-scaled FFT is the best feature for speech recognition based on the proposed measure.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• pp.1833-1848
• /
• 2022

Named entity recognition (NER) is an important basic task in the field of Natural Language Processing (NLP). Recently deep learning approaches by extracting word segmentation or character features have been proved to be effective for Chinese Named Entity Recognition (CNER). However, since this method of extracting features only focuses on extracting some of the features, it lacks textual information mining from multiple perspectives and dimensions, resulting in the model not being able to fully capture semantic features. To tackle this problem, we propose a novel Multi-view Semantic Feature Fusion Model (MSFM). The proposed model mainly consists of two core components, that is, Multi-view Semantic Feature Fusion Embedding Module (MFEM) and Multi-head Self-Attention Mechanism Module (MSAM). Specifically, the MFEM extracts character features, word boundary features, radical features, and pinyin features of Chinese characters. The acquired font shape, font sound, and font meaning features are fused to enhance the semantic information of Chinese characters with different granularities. Moreover, the MSAM is used to capture the dependencies between characters in a multi-dimensional subspace to better understand the semantic features of the context. Extensive experimental results on four benchmark datasets show that our method improves the overall performance of the CNER model.

• 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.