• Journal of the Korean Society for information Management
• /
• 제18권4호
• /
• pp.37-55
• /
• 2001

The purpose of this study is to present a text summarization system using a knowledge base containing information about verbs and their arguments that are statistically obtained from a subject domain. The system consists of two modules: the training module and the summarization module. The training module is to extract cue verbs and their basic sentence patterns by counting the frequency of verbs and case markers respectively, and the summarization module is substantiate basic sentence patterns and to generate summaries. Basic sentence patterns are substantiated by applying substantiation rules to the syntactics structure of sentences. A summary is then produced by connecting simple sentences that the are generated through the substantiation module of basic sentence patterns. ‘robbery’in the daily newspapers are selected for a test collection. The system generates natural summaries without losing any essential information by combining both cue verbs and essential arguments. In addition, the use of statistical techniques makes it possible to apply this system to other subject domains through its learning capability.

• The Journal of the Acoustical Society of Korea
• /
• 제39권5호
• /
• pp.447-453
• /
• 2020

In this paper, we propose a system to extract effective speaker representations from a speech signal using a deep learning method. Based on the fact that speech signal contains identity unrelated information such as text content, emotion, background noise, and so on, we perform a training such that the extracted features only represent speaker-related information but do not represent speaker-unrelated information. Specifically, we propose an auto-encoder based disentanglement method that outputs both speaker-related and speaker-unrelated embeddings using effective loss functions. To further improve the reconstruction performance in the decoding process, we also introduce a discriminator popularly used in Generative Adversarial Network (GAN) structure. Since improving the decoding capability is helpful for preserving speaker information and disentanglement, it results in the improvement of speaker verification performance. Experimental results demonstrate the effectiveness of our proposed method by improving Equal Error Rate (EER) on benchmark dataset, Voxceleb1.

• Journal of the Korean Institute of Intelligent Systems
• /
• 제11권3호
• /
• pp.223-230
• /
• 2001

Since self-organizing map (SOM) preserves the topology of ordering in input spaces and trains itself by unsupervised algorithm, it is Llsed in many areas. However, SOM has a shortcoming: structure cannot be easily detcrmined without many trials-and-errors. Structure-adaptive self-orgnizing map (SASOM) which can adapt its structure as well as its weights overcome the shortcoming of self-organizing map: SASOM makes use of structure adaptation capability to place the nodes of prototype vectors into the pattern space accurately so as to make the decision boundmies as close to the class boundaries as possible. In this scheme, the initialization of weights of newly adapted nodes is important. This paper proposes a method which optimizes SASOM with genetic algorithm (GA) to determines the weight vector of newly split node. The leanling algorithm is a hybrid of unsupervised learning method and supervised learning method using LVQ algorithm. This proposed method not only shows higher performance than SASOM in terms of recognition rate and variation, but also preserves the topological order of input patterns well. Experiments with 2D pattern space data and handwritten digit database show that the proposed method is promising.

• Education of Primary School Mathematics
• /
• 제6권2호
• /
• pp.75-84
• /
• 2002

After entering an elementary school, in fact, a number of children regard mathematics as one of very difficult subjects because of its abstractiveness. This is caused by the fact that their basic thinking power is not yet formed or they can not understand the special quality of mathematics. So this article emphasizes the need to build up the higher logical thought and a basic mathematical concept at the lower grade elementary school stage in which the loaming activity on mathematics begins in earnest, that is, at the stage before having an experience on the calculating activity using numbers. But at present the lower grade elementary school students in our country do not understand the special quality of mathematics composed of a various symbolic system and lay stress upon mathematics learning attached to the calculative activity. In order to make the right mathematical concept of the lower grade elementary school, the basic knowledge and ability as follows is sure to be formed. 1) the foundational logical manipulation activity and knowledge 2) the using ability of the sign and symbolic system At the stage on which mathematics learning activity begins, it is a very important task to make the right concept of the abstractive math and nurse the capability for finding mathematical relations covered under the sign system through the continuos loaming activity on . Through the basic logical manipulation activity and the game activity of sign for lower grade elementary school students mentioned in this article, they can not only foster the higher level logical thinking power and the foundational calculative ability but also bring up the interest on the activity of establishing a new problem solving strategy.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• 제60권2호
• /
• pp.398-406
• /
• 2011

In this paper, we introduce a new architecture of PSO-based Polynomial Neural Networks (PNN) and discuss its comprehensive design methodology. The conventional PNN is based on a extended Group Method of Data Handling (GMDH) method, and utilized the polynomial order (viz. linear, quadratic, and modified quadratic) as well as the number of node inputs fixed (selected in advance by designer) at Polynomial Neurons located in each layer through a growth process of the network. Moreover it does not guarantee that the conventional PNN generated through learning results in the optimal network architecture. The PSO-based PNN results in a structurally optimized structure and comes with a higher level of flexibility that the one encountered in the conventional PNN. The PSO-based design procedure being applied at each layer of PNN leads to the selection of preferred PNs with specific local characteristics (such as the number of input variables, input variables, and the order of the polynomial) available within the PNN. In the sequel, two general optimization mechanisms of the PSO-based PNN are explored: the structural optimization is realized via PSO whereas in case of the parametric optimization we proceed with a standard least square method-based learning. To evaluate the performance of the PSO-based PNN, the model is experimented with using Gas furnace process data, and pH neutralization process data. For the characteristic analysis of the given entire data with non-linearity and the construction of efficient model, the given entire system data is partitioned into two type such as Division I(Training dataset and Testing dataset) and Division II(Training dataset, Validation dataset, and Testing dataset). A comparative analysis shows that the proposed PSO-based PNN is model with higher accuracy as well as more superb predictive capability than other intelligent models presented previously.

• Journal of the Institute of Convergence Signal Processing
• /
• 제10권4호
• /
• pp.233-238
• /
• 2009

In this paper, we propose the methods to select the stable region for the detect region which is required in the system used the face to the ROI in the auto-focus digital camera. this method regards the face region as the ROI in the progressive input frame and focusing the region in the mobile camera embeded ISP module automatically. The learning algorithm to detect the face is the Adaboost algorithm. we proposed the method to detect the slanted face not participate in the train process and postprocessing method for the results of detection, and then we proposed the stabilization method to sustain the region not shake for the region. we estimated the capability for the stabilization algorithm using the RMS between the trajectory and regression curve.

• KIISE Transactions on Computing Practices
• /
• 제21권4호
• /
• pp.338-342
• /
• 2015

Recurrent Neural Network (RNN), a machine learning model which can handle time-series data, can possess more varied structures than a feed-forward neural network, since a RNN allows hidden-to-hidden connections. This research focuses on the network structure among hidden neurons, and discusses the information processing capability of RNN. Time-series learning potential and dynamics of RNNs are investigated upon several well-established network structure models. Hidden neuron network structure is found to have significant impact on the performance of a model, and the performance variations are generally correlated with the criticality of the network dynamics. Especially Preferential Attachment Network model showed an interesting behavior. These findings provide clues for performance improvement of the RNN.

• Journal of the Korea Convergence Society
• /
• 제12권12호
• /
• pp.31-37
• /
• 2021

In this paper proposed a feature fusion and spatial attention-based modified YOLOv4S for small and occluded detection. Conventional YOLOv4S is a lightweight network and lacks feature extraction capability compared to the method of the deep network. The proposed method first combines feature maps of different scales with feature fusion to enhance semantic and low-level information. In addition expanding the receptive field with dilated convolution, the detection accuracy for small and occluded objects was improved. Second by improving the conventional spatial information with spatial attention, the detection accuracy of objects classified and occluded between objects was improved. PASCAL VOC and COCO datasets were used for quantitative evaluation of the proposed method. The proposed method improved mAP by 2.7% in the PASCAL VOC dataset and 1.8% in the COCO dataset compared to the Conventional YOLOv4S.

• Journal of Convergence for Information Technology
• /
• 제11권12호
• /
• pp.168-175
• /
• 2021

In this study, a transdisciplinary convergence education program was developed to enhance the understanding for classification of reptiles and amphibians in biology education and also to increase AI (Artificial Intelligence) capability by using artificial intelligence education. The main content is to solve the classification of reptiles and amphibians that has been dealt with for a long time in biology education, using a decision tree and ML4K (Machine Learnig for Kids), it was designed for a total of 3 lessons. Experts review was conducted on the developed education program, as a result, the I-CVI(Item Content Validity Index) value was .88~1.00 so that can secure content validity. This education program has the advantage of being able to simultaneously learn about the learning contents of artificial intelligence in informatics and the classification of vertebrates in the biological education. In addition, since it is configured to minimize the cognitive load in the AI using part, it is characterized by the fact that all of any teachers can apply it their lesson easily.

• The Journal of the Korea Contents Association
• /
• 제21권9호
• /
• pp.34-41
• /
• 2021

The purpose of this study is to explore any effects of primary English language learners' affective factors and satisfaction through AI-based speaking activity. In order to answer these questions, a total number of 46 ELLs from a public elementary school participated in this research. Survey questionnaire on affective factors and learning satisfaction were distributed and the results were analyzed quantitatively. The findings are as follows. First, participants could expand their knowledge on AI-based activity towards its educational advantages and capability. Second, overall affective factors of the participants on AI-based activity changed positively, with the improvement of the mean score. The paired samples t-test showed that there was a significant difference among interest, value and attitude. Third, the satisfaction degree on AI-based learning escalated, particularly in the sense of efficacy, academic achievement and involvement. Lastly, it was revealed that the satisfaction degree was correlated with learners' self-confidence, interest and attitude.