• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.44 no.1
• /
• pp.100-107
• /
• 2007

AABR(automated auditory brainstem response) test is used for the screening purpose of hearing ability of neonates. In this paper, algorithm using Rolle's theorem is suggested for automatic detection of the ensemble averaged ABR waveform. The ABR waveforms were recorded from 55 normal-hearing ears of neonates at screening levels varying from 30 to 60 dBnHL. Recorded signals were analyzed by expert audiologist and by the proposed algorithm. The results showed that the proposed algorithm correctly identified latencies of the major ABR waves (III, V) with latent difference below 0.2 ms. No significant differences were found between the two methods. We also analyzed the ABR signals using derivative algorithm and compared the results with proposed algorithm. The number of detected candidate waves using the proposed algorithm was 47 % less than that of the existing one. The proposed method had lower relative errors (0.01 % error at 60dBnHL) compared to the existing one. By using proposed algorithm, clinicians can detect and label waves III and V more objectively and quantitatively than the manual detection method.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.119-137
• /
• 2022

Recent recommendation system studies apply various deep learning models to represent user and item interactions better. One of the noteworthy studies is ONCF(Outer product-based Neural Collaborative Filtering) which builds a two-dimensional interaction map via outer product and employs CNN (Convolutional Neural Networks) to learn high-order correlations from the map. However, ONCF has limitations in recommendation performance due to the problems with CNN and the absence of side information. ONCF using CNN has an inductive bias problem that causes poor performances for data with a distribution that does not appear in the training data. This paper proposes to employ a Vision Transformer (ViT) instead of the vanilla CNN used in ONCF. The reason is that ViT showed better results than state-of-the-art CNN in many image classification cases. In addition, we propose a new architecture to reflect side information that ONCF did not consider. Unlike previous studies that reflect side information in a neural network using simple input combination methods, this study uses an independent auxiliary classifier to reflect side information more effectively in the recommender system. ONCF used a single latent vector for user and item, but in this study, a channel is constructed using multiple vectors to enable the model to learn more diverse expressions and to obtain an ensemble effect. The experiments showed our deep learning model improved performance in recommendation compared to ONCF.

• Journal of Intelligence and Information Systems
• /
• v.17 no.4
• /
• pp.109-130
• /
• 2011

One of the major problems in the area of data mining is the size of the data, as most data set has huge volume these days. Streams of data are normally accumulated into data storages or databases. Transactions in internet, mobile devices and ubiquitous environment produce streams of data continuously. Some data set are just buried un-used inside huge data storage due to its huge size. Some data set is quickly lost as soon as it is created as it is not saved due to many reasons. How to use this large size data and to use data on stream efficiently are challenging questions in the study of data mining. Stream data is a data set that is accumulated to the data storage from a data source continuously. The size of this data set, in many cases, becomes increasingly large over time. To mine information from this massive data, it takes too many resources such as storage, money and time. These unique characteristics of the stream data make it difficult and expensive to store all the stream data sets accumulated over time. Otherwise, if one uses only recent or partial of data to mine information or pattern, there can be losses of valuable information, which can be useful. To avoid these problems, this study suggests a method efficiently accumulates information or patterns in the form of rule set over time. A rule set is mined from a data set in stream and this rule set is accumulated into a master rule set storage, which is also a model for real-time decision making. One of the main advantages of this method is that it takes much smaller storage space compared to the traditional method, which saves the whole data set. Another advantage of using this method is that the accumulated rule set is used as a prediction model. Prompt response to the request from users is possible anytime as the rule set is ready anytime to be used to make decisions. This makes real-time decision making possible, which is the greatest advantage of this method. Based on theories of ensemble approaches, combination of many different models can produce better prediction model in performance. The consolidated rule set actually covers all the data set while the traditional sampling approach only covers part of the whole data set. This study uses a stock market data that has a heterogeneous data set as the characteristic of data varies over time. The indexes in stock market data can fluctuate in different situations whenever there is an event influencing the stock market index. Therefore the variance of the values in each variable is large compared to that of the homogeneous data set. Prediction with heterogeneous data set is naturally much more difficult, compared to that of homogeneous data set as it is more difficult to predict in unpredictable situation. This study tests two general mining approaches and compare prediction performances of these two suggested methods with the method we suggest in this study. The first approach is inducing a rule set from the recent data set to predict new data set. The seocnd one is inducing a rule set from all the data which have been accumulated from the beginning every time one has to predict new data set. We found neither of these two is as good as the method of accumulated rule set in its performance. Furthermore, the study shows experiments with different prediction models. The first approach is building a prediction model only with more important rule sets and the second approach is the method using all the rule sets by assigning weights on the rules based on their performance. The second approach shows better performance compared to the first one. The experiments also show that the suggested method in this study can be an efficient approach for mining information and pattern with stream data. This method has a limitation of bounding its application to stock market data. More dynamic real-time steam data set is desirable for the application of this method. There is also another problem in this study. When the number of rules is increasing over time, it has to manage special rules such as redundant rules or conflicting rules efficiently.

• (The) Research of the performance art and culture
• /
• no.39
• /
• pp.701-748
• /
• 2019

Gwanak-yeongsanhoesang, called as Samhyeon-yeongsanhoesang or Pyojeongmanbangjigok, is played by the musical instrumental organization, Samhyeonyukgak or by a large scale wind ensemble added Sogeum and Ajaeng. This study aims to analyze the structure and form of Piri melody which plays major melody of Sangnyeongsan in Gwanak-yeongsanhoesang, and to examine the relationship between Piri melody and Daegeum yeoneum grasping the structure and function of yeoneum. In Sangnyeongsan of Gwanak-yeongsanhoesang, the criterion for grouping the phrases of Piri melody is yeoneum. Especially, Daegeum yeoneum carries out the function of finishing the phrase of Piri playing the major melody by ornamenting or extending it, and presenting the motives or motive elements of the next phrase while Piri rests. The types of a, b, g, and i in the various shapes of the minimum melodic fragment of Piri are important motive elements that constitute a phrase of Piri melody. Especially, main motive a-type (仲→無) contrasts with b type (林→潢) which forms a strong tension by transposing 2 degrees upward. In addition, a-type gradually descends towards the end of music by changing to g-type (仲→林) or to i-type (太→林) which is 3 degrees below, which is related to the gradual descent cadence of Korean traditional music. A phrase of Piri melody of Sangnyeongsan in Gwanak-yeongsanhoesang consists of a combination of the types a, b, g, i, and cadence (x-type), and each phrase is structured in the repeating tension-relaxation. Looking at the structure of Piri phrases by similar types, each phrase has a logical variation structure through the methods such as omission and addition of notes, and crossing of melodies. The shape of the minimum melodic fragment of Daegeum yeoneum can be divided into a back-yeoneum of a~b types and a front-yeoneum of x1~x3. The x-types ornament Jungnyeo (仲), the cadence tone of Piri melody or are simply used as the extending back-yeoneum, and types a and b have the function of a front-yeoneum that prepares the beginning of the next phrase of Piri melody. The combination types of the minimum melodic fragment of Daegeum yeoneum appear mostly as the shape of back-yeoneum + front-yeoneum. In addition, the front-yeoneum of the type a and b appears independently without back-yeoneum, and the x3 type has a shape of the back-yeoneum without the front-yeoneum. Looking at the structure of Daegeum yeoneum by similar types, it can be seen that Daegeum yeoneum is also composed of a variation structure of omission and addition of notes like Piri melody.