• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.47 no.3
• /
• pp.48-55
• /
• 2010

Hearing impairment is one of the most common birth defects among infants. Significant bilateral hearing impairment have profound effects on speech and language development. But it can be prevented, if a hearing impairment is identified and treated in its early stage. ABR (auditory brainstem response) is useful screening tool for new born hearing test. However, the interpretation of conventional ABR should be done by a experienced audiologist and testing takes some time. Therefore, A-ABR(automated ABR) which detect ABR peak automatically have been developed recently. In contrast to A-ABR researches became active in overseas, there has been little study in Korea. In this study, we have developed a portable A-ABR system based on the results of our previous study. For the evaluation of the developed system, the clinical trials were performed on adults and infants. As a results, it showed good sensitivity (94.4%) and specificity (92.2%), and accuracy (93.0%) between clinical diagnosis and the developed A-ABR test.

• Journal of IKEEE
• /
• v.22 no.4
• /
• pp.1140-1146
• /
• 2018

Recently, a methodology for analyzing complex bio-signals using a deep learning model has emerged among studies that recognize human emotions. At this time, the accuracy of emotion classification may be changed depending on the evaluation method and reliability depending on the kind of data to be learned. In the case of biological signals, the reliability of data is determined according to the noise ratio, so that the noise detection method is as important as that. Also, according to the methodology for defining emotions, appropriate emotional evaluation methods will be needed. In this paper, we propose a wavelet -based noise threshold setting algorithm for verifying the reliability of data for multimodal bio-signal data labeled Valence and Arousal and a method for improving the emotion recognition rate by weighting the evaluation data. After extracting the wavelet component of the signal using the wavelet transform, the distortion and kurtosis of the component are obtained, the noise is detected at the threshold calculated by the hampel identifier, and the training data is selected considering the noise ratio of the original signal. In addition, weighting is applied to the overall evaluation of the emotion recognition rate using the euclidean distance from the median value of the Valence-Arousal plane when classifying emotional data. To verify the proposed algorithm, we use ASCERTAIN data set to observe the degree of emotion recognition rate improvement.

• The Journal of Society for e-Business Studies
• /
• v.24 no.1
• /
• pp.1-16
• /
• 2019

Recently, since responding to meteorological changes depending on increasing greenhouse gas and electricity demand, the importance prediction of photovoltaic power (PV) is rapidly increasing. In particular, the prediction of PV power generation may help to determine a reasonable price of electricity, and solve the problem addressed such as a system stability and electricity production balance. However, since the dynamic changes of meteorological values such as solar radiation, cloudiness, and temperature, and seasonal changes, the accurate long-term PV power prediction is significantly challenging. Therefore, in this paper, we propose PV power prediction model based on deep learning that can be improved the PV power prediction performance by learning to use meteorological and seasonal information. We evaluate the performances using the proposed model compared to seasonal ARIMA (S-ARIMA) model, which is one of the typical time series methods, and ANN model, which is one hidden layer. As the experiment results using real-world dataset, the proposed model shows the best performance. It means that the proposed model shows positive impact on improving the PV power forecast performance.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.3
• /
• pp.525-532
• /
• 2021

In the ocean, it is difficult to separate the effects of one cause due to the multiple causes, but the self-organizing map can be analyzed by adding other factors to the cluster result. Therefore, in this study, the results of the clustering of sea level data were applied to sea surface temperature. Sea level data was clustered into a total of 6 nodes. The difference between sea surface temperature and sea level height has a one-month delay, which applied sea surface temperature data a month ago to the clustered results. As a result of comparing the mean of sea surface temperature of 140 to 150°E, where the sea surface temperature was variously distributed, in the case of nodes 1, 3, and 5, it was possible to find a meandering sea surface temperature distribution that is clearly distinguished from the sea level data. While nodes 2, 4 and 6, the sea surface temperature distribution was smooth. In this study, sea surface temperature data were applied to the clustered results of sea level data, but later it is necessary to apply wind or geostrophic velocity data to compare.

• Journal of Broadcast Engineering
• /
• v.25 no.6
• /
• pp.944-953
• /
• 2020

Object detection plays a crucial role in a self-driving system. With the advances of image recognition based on deep convolutional neural networks, researches on object detection have been actively explored. In this paper, we proposed a lightweight model of the mask R-CNN, which has been most widely used for object detection, to efficiently predict location and shape of various objects on the road environment. Furthermore, feature maps are adaptively re-calibrated to improve the detection performance by applying an attention module to the neural network layer that plays different roles within the mask R-CNN. Various experimental results for real driving scenes demonstrate that the proposed method is able to maintain the high detection performance with significantly reduced network parameters.

• The Journal of Society for e-Business Studies
• /
• v.26 no.2
• /
• pp.19-43
• /
• 2021

The prediction of box office performance in performing arts institutions is an important issue in the performing arts industry and institutions. For this, traditional prediction methodology and data mining methodology using standardized data such as cast members, performance venues, and ticket prices have been proposed. However, although it is evident that audiences tend to seek out their intentions by the performance guide poster, few attempts were made to predict box office performance by analyzing poster images. Hence, the purpose of this study is to propose a deep learning application method that can predict box office success through performance-related poster images. Prediction was performed using deep learning algorithms such as Pure CNN, VGG-16, Inception-v3, and ResNet50 using poster images published on the KOPIS as learning data set. In addition, an ensemble with traditional regression analysis methodology was also attempted. As a result, it showed high discrimination performance exceeding 85% of box office prediction accuracy. This study is the first attempt to predict box office success using image data in the performing arts field, and the method proposed in this study can be applied to the areas of poster-based advertisements such as institutional promotions and corporate product advertisements.

• Journal of Broadcast Engineering
• /
• v.27 no.2
• /
• pp.228-239
• /
• 2022

In this paper, we propose an unmanned vehicle scratch detection deep learning model for car sharing services. Conventional scratch detection models consist of two steps: 1) a deep learning module for scratch detection of images before and after rental, 2) a manual matching process for finding newly generated scratches. In order to build a fully automatic scratch detection model, we propose a one-step unmanned scratch detection deep learning model. The proposed model is implemented by applying transfer learning and fine-tuning to the deep learning model that detects changes in satellite images. In the proposed car sharing service, specular reflection greatly affects the scratch detection performance since the brightness of the gloss-treated automobile surface is anisotropic and a non-expert user takes a picture with a general camera. In order to reduce detection errors caused by specular reflected light, we propose a preprocessing process for removing specular reflection components. For data taken by mobile phone cameras, the proposed system can provide high matching performance subjectively and objectively. The scores for change detection metrics such as precision, recall, F1, and kappa are 67.90%, 74.56%, 71.08%, and 70.18%, respectively.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.2
• /
• pp.103-108
• /
• 2022

Various studies have been conducted on cloud observation using all-sky images acquired with a wide-angle camera system since the early 21st century, but it is judged that an automatic observation system that can completely replace the eye observation has not been obtained. In this study, to verify the quantification of cloud observation, which is the final step of the algorithm proposed to automate the observation, the cloud distribution of the all-sky image and the corrected image were compared and analyzed. The reason is that clouds are formed at a certain height depending on the type, but like the retina image, the center of the lens is enlarged and the edges are reduced, but the effect of human learning ability and spatial awareness on cloud observation is unknown. As a result of this study, the average cloud observation error of the all-sky image and the corrected image was 1.23%. Therefore, when compared with the eye observation in the decile, the error due to correction is 1.23% of the observed amount, which is very less than the allowable error of the eye observation, and it does not include human error, so it is possible to collect accurately quantified data. Since the change in cloudiness due to the correction is insignificant, it was confirmed that accurate observations can be obtained even by omitting the unnecessary correction step and observing the cloudiness in the pre-correction image.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.5
• /
• pp.328-334
• /
• 2022

The process that one may consciously focuses on necessary stimulation among tremendous amount of stimulation through human sensory systems is called attention in psychology. It is known that the attention can be affected by many factors such as room temperatures, humidity level, etc. In the field of sports science, ice packs are widely used for recovery from exercise fatigue providing fast heat transfer by conduction. However, the effect on attention by so-called iced-pack-cooling has not been tested. This research focuses on the attention levels when one is provided with a special cooling pad on their dorsal and lateral cervices. 40 subjects were divided into four groups and their attention level was evaluated based on the exposure conditions of combinations in reading and light walking with and without the cooling pad. The Frankfruter Aufmerksamkeits-Inventar, FAIR was used to evaluate the attention levels; the performance index, quality index, and continuity index consist of the FAIR test indicating the selectiveness of the attention, correctness of the attention, and maintaining term of the attention, respectively. Analysis of variance was carried out for those variables and post-hoc if applicable. When visual attention is constantly used for reading and studying, application of conductive heat transfer by the cooling pads is significantly helpful for improvement in selectiveness of the attention and maintaining terms of the attention levels. Also, light walking yielded improvement in selectiveness of the attention and maintaining terms of the attention levels; however one should presupposedly consider the loss of reading time.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.326-334
• /
• 2022

In this paper, we propose speech enhancement algorithm as a pre-processing for robust speech recognition in noisy environments. Auxiliary-function-based Independent Vector Analysis (AuxIVA) is performed with weighted covariance matrix using time-varying variances with scaling factor from target masks representing time-frequency contributions of target speech. The mask estimates can be obtained using Neural Network (NN) pre-trained for speech extraction or diffuseness using Coherence-to-Diffuse power Ratio (CDR) to find the direct sounds component of a target speech. In addition, outputs for omni-directional noise are closely chained by sharing the time-varying variances similarly to independent subspace analysis or IVA. The speech extraction method based on AuxIVA is also performed in Independent Low-Rank Matrix Analysis (ILRMA) framework by extending the Non-negative Matrix Factorization (NMF) for noise outputs to Non-negative Tensor Factorization (NTF) to maintain the inter-channel dependency in noise output channels. Experimental results on the CHiME-4 datasets demonstrate the effectiveness of the presented algorithms.