• Transactions of Materials Processing
• /
• v.27 no.2
• /
• pp.100-106
• /
• 2018

In the continuous casting process, the incidence of transverse surface cracks on the piece may occur by multiple and diverse variables. It is noted that mathematical models may predict only the occurance of the transverse surface cracks, but can require a lot of time (more than three days) to produce a result with this process. This study applied neural networks to predict whether the cracks on the piece surface occurs or does not occur. The computation time was shortened to three minutes, making it applicable to an on-line program, which predicts the non-cracks or cracks of the piece surface in the actual continuous casting process. In addition, the operating conditions to prevent the occurrence of the transverse surface cracks, using decision boundaries were also suggested.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.2
• /
• pp.209-215
• /
• 2003

A new GA-based methodology using information granules is suggested for the construction of fuzzy classifiers. The proposed scheme consists of three steps: selection of information granules, construction of the associated fuzzy sets, and tuning of the fuzzy rules. First, the genetic algorithm (GA) is applied to the development of the adequate information granules. The fuzzy sets are then constructed from the analysis of the developed information granules. An interpretable fuzzy classifier is designed by using the constructed fuzzy sets. Finally, the GA are utilized for tuning of the fuzzy rules, which can enhance the classification performance on the misclassified data (e.g., data with the strange pattern or on the boundaries of the classes). To show the effectiveness of the proposed method, an example, the classification of the Iris data, is provided.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.1
• /
• pp.107-113
• /
• 2003

A new GA-based methodology using information granules is suggested for the construction of fuzzy classifiers. The proposed scheme consists of three steps: selection of information granules, construction of the associated fuzzy sets, and tuning of the fuzzy rules. First, the genetic algorithm (GA) is applied to the development of the adequate information granules. The fuzzy sets are then constructed from the analysis of the developed information granules. An interpretable fuzzy classifier is designed by using the constructed fuzzy sets. Finally, the GA are utilized for tuning of the fuzzy rules, which can enhance the classification performance on the misclassified data (e.g., data with the strange pattern or on the boundaries of the classes). To show the effectiveness of the proposed method, an example, the classification of the Iris data, is provided.

• Journal of the Semiconductor & Display Technology
• /
• v.22 no.3
• /
• pp.161-165
• /
• 2023

One of the difficult works in an autonomous driving system is detecting road lanes or objects in the road boundaries. Detecting and tracking a vehicle is able to play an important role on providing important information in the framework of advanced driver assistance systems such as identifying road traffic conditions and crime situations. This paper proposes a vehicle detection scheme based on deep learning to classify and tracking vehicles in a complex and diverse environment. We use the modified YOLO as the object detector and polynomial regression as object tracker in the driving video. With the experimental results, using YOLO model as deep learning model, it is possible to quickly and accurately perform robust vehicle tracking in various environments, compared to the traditional method.

• Journal of Korean Medical classics
• /
• v.27 no.4
• /
• pp.181-198
• /
• 2014

Objectives : This study was to analyze definitions of herbal medicinal preparations, crude drug preparations, and new drugs from natural products in the relevant laws and regulations, understand the related problems, and propose directions for improvement. Methods : I analyzed the legal definitions in respect of herbal medicinal preparations, crude drug preparations, and new drugs from natural products in relevant laws and regulations since 1945, explained the problems, and suggested the solution-considering the academic stance of Traditional Korean Medicine and the dualistic medical and pharmaceutical system. Results : Regarding the current laws and regulations that are relevant to herbal medicinal preparations, we should 1) clarify the boundaries between the duty of physicians and that of pharmacists, 2) limit the principles of Korean Medicine as well as the contents of the related textbooks, 3) find a way to protect the intellectual property rights for herbal medicinal preparations, and 4) establish a separate standard for drug classification regarding herbal medicinal preparations. In case of crude drug preparations, we should 1) clarify the meaning and limitations of the phrase, "the point of view of Western medicine," and 2) establish a classification standard for drugs that are used in Korean Medicine and clarify the boundaries between herbal drug preparations and crude drug preparations. Furthermore, laws and regulations apropos of new drugs from natural products do not actually fit the concept of "new drug," and due to subordinate laws, a supplement to a new drug submission is contradictorily misclassified as a new drug from natural products. Conclusions : The problems of legal definitions of herbal medicinal preparations, crude drug preparations, and new drugs from natural products have emerged in the process of giving approval to drugs that are made of herbs and natural products under the dualistic medical and pharmaceutical System. Laws and regulations that differentiate the process of approving herbs that are used in Korean Medicine and the others should be established.

• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.386-389
• /
• 2008

It is important that the training stage of a supervised classification is designed to provide the spectral information. On the design of the training stage of a classification typically calls for the use of a large sample of randomly selected pure pixels in order to characterize the classes. Such guidance is generally made without regard to the specific nature of the application in-hand, including the classifier to be used. An approach to the training of a support vector machine (SVM) classifier that is the opposite of that generally promoted for training set design is suggested. This approach uses a small sample of mixed spectral responses drawn from purposefully selected locations (geographical boundaries) in training. A sample of such data should, however, be easier and cheaper to acquire than that suggested by traditional approaches. In this research, we evaluated them against traditional approaches with high-resolution satellite data. The results proved that it can be used small mixed pixels to derive a classification with similar accuracy using a large number of pure pixels. The approach can also reduce substantial costs in training data acquisition because the sampling locations used are commonly easy to observe.

• Journal of The Geomorphological Association of Korea
• /
• v.25 no.3
• /
• pp.1-18
• /
• 2018

In Korea, 64% of the land is known as mountain area, but the definition and classification standard of mountain are not clear. Demand for utilization and development of mountain area is increasing. In this situation, the unclear definition and scope of the mountain area can lead to the destruction of the mountain and the increase of disasters due to indiscreet permission of forestland use conversion. Therefore, this study analyzed the variables and criteria that can extract the mountain boundaries through the questionnaire survey and the terrain analysis. We developed a mountain boundary extraction algorithm that can classify topographic mountain by using selected variables. As a result, 72.1% of the total land was analyzed as mountain area. For the three catchment areas with different mountain area ratio, we compared the results with the existing data such as forestland map and cadastral map. We confirmed the differences in boundary and distribution of mountain. In a catchment area with predominantly mountainous area, the algorithmbased mountain classification results were judged to be wider than the mountain or forest of the two maps. On the other hand, in the basin where the non-mountainous region predominated, algorithm-based results yielded a lower mountain area ratio than the other two maps. In the two maps, we was able to confirm the distribution of fragmented mountains. However, these areas were classified as non-mountain areas in algorithm-based results. We concluded that this result occurred because of the algorithm, so it is necessary to refine and elaborate the algorithm afterward. Nevertheless, this algorithm can analyze the topographic variables and the optimal value by watershed that can distinguish the mountain area. The results of this study are significant in that the mountain boundaries were extracted considering the characteristics of different mountain topography by region. This study will help establish policies for stable mountain management.

• The Journal of the Acoustical Society of Korea
• /
• v.6 no.3
• /
• pp.60-67
• /
• 1987

In this paper, a phoneme classification method for Korean speech recognition has been proposed and its performance has been studied. The phoneme classification has been done based on the phonemic features extracted by the prewindowed recursive least-square (PRLS) algorithm that is a kind of adaptive filter algorithms. Applying the PRLS algorithm to input speech signal, precise detection of phoneme boundaries has been made, Reference patterns of Korean phonemes have been generated by the ordinery vector quantization (VQ) of feature vectors obtained manualy from prototype regions of each phoneme. In order to obtain the performance of the proposed phoneme classification method, the method has been tested using spoken names of seven Korean cities which have eleven different consonants and eight different vowels. In the speaker-dependent phoneme classification, the accuracy is about $85\%$ considering simple phonemic rules of Korean language, while the accuracy of the speaker-independent case is far less than that of the speaker-dependent case.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.2
• /
• pp.155-163
• /
• 2009

In text-to-speech systems, the conversion of text into prosodic parameters is necessarily composed of three steps. These are the placement of prosodic boundaries. the determination of segmental durations, and the specification of fundamental frequency contours. Prosodic boundaries. as the most important and basic parameter. affect the estimation of durations and fundamental frequency. Break prediction is an important step in text-to-speech systems as break indices (BIs) have a great influence on how to correctly represent prosodic phrase boundaries, However. an accurate prediction is difficult since BIs are often chosen according to the meaning of a sentence or the reading style of the speaker. In Japanese, the prediction of an accentual phrase boundary (APB) and major phrase boundary (MPB) is particularly difficult. Thus, this paper presents a method to complement the prediction errors of an APB and MPB. First, we define a subtle BI in which it is difficult to decide between an APB and MPB clearly as a variable break (VB), and an explicit BI as a fixed break (FB). The VB is chosen using the classification and regression tree, and multiple prosodic targets in relation to the pith and duration are then generated. Finally. unit-selection is conducted using multiple prosodic targets. In the MOS test result. the original speech scored a 4,99. while proposed method scored a 4.25 and conventional method scored a 4.01. The experimental results show that the proposed method improves the naturalness of synthesized speech.

• Journal of Intelligence and Information Systems
• /
• v.14 no.2
• /
• pp.193-206
• /
• 2008

Medical diagnosis can be considered a classification task which classifies disease types from patient's condition data represented by a set of pre-defined attributes. This study proposes a hybrid genetic algorithm based classification method to develop classifiers for multidimensional pattern classification problems related with medical decision making. The classification problem can be solved by identifying separation boundaries which distinguish the various classes in the data pattern. The proposed method fits a finite number of regional agents to the data pattern by combining genetic algorithms and local adaptive operations. The local adaptive operations of an agent include expansion, avoidance and relocation, one of which is performed according to the agent's fitness value. The classifier system has been tested with well-known medical data sets from the UCI machine learning database, showing superior performance to other methods such as the nearest neighbor, decision tree, and neural networks.