• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.3
• /
• pp.91-98
• /
• 2018

Automatic detection of pig wasting diseases is an important issue in the management of group-housed pigs. In particular, porcine respiratory diseases are one of the main causes of mortality among pigs and loss of productivity in intensive pig farming. In this paper, we propose a noise-robust system for the early detection and recognition of pig wasting diseases using sound data. In this method, first we convert one-dimensional sound signals to two-dimensional gray-level images by normalization, and extract texture images by means of dominant neighborhood structure technique. Lastly, the texture features are then used as inputs of convolutional neural networks as an early anomaly detector and a respiratory disease classifier. Our experimental results show that this new method can be used to detect pig wasting diseases both economically (low-cost sound sensor) and accurately (over 96% accuracy) even under noise-environmental conditions, either as a standalone solution or to complement known methods to obtain a more accurate solution.

• The KIPS Transactions:PartD
• /
• v.10D no.4
• /
• pp.577-590
• /
• 2003

The shape-based retrieval is defined as the operation that searches for the (sub) sequences whose shapes are similar to that of a query sequence regardless of their actual element values. In this paper, we propose a similarity model suitable for shape-based retrieval and present an indexing method for supporting the similarity model. The proposed similarity model enables to retrieve similar shapes accurately by providing the combination of various shape-preserving transformations such as normalization, moving average, and time warping. Our indexing method stores every distinct subsequence concisely into the disk-based suffix tree for efficient and adaptive query processing. We allow the user to dynamically choose a similarity model suitable for a given application. More specifically, we allow the user to determine the parameter p of the distance function $L_p$ when submitting a query. The result of extensive experiments revealed that our approach not only successfully finds the subsequences whose shapes are similar to a query shape but also significantly outperforms the sequence search.

• The Journal of the Acoustical Society of Korea
• /
• v.22 no.7
• /
• pp.603-611
• /
• 2003

This paper proposes an effective feature compensation scheme based on speech model for achieving robust speech recognition. Conventional model-based method requires off-line training with noisy speech database and is not suitable for online adaptation. In the proposed scheme, we can relax the off-line training with noisy speech database by employing the parallel model combination technique for estimation of correction factors. Applying the model combination process over to the mixture model alone as opposed to entire HMM makes the online model combination possible. Exploiting the availability of noise model from off-line sources, we accomplish the online adaptation via MAP (Maximum A Posteriori) estimation. In addition, the online channel estimation procedure is induced within the proposed framework. For more efficient implementation, we propose a selective model combination which leads to reduction or the computational complexities. The representative experimental results indicate that the suggested algorithm is effective in realizing robust speech recognition under the combined adverse conditions of additive background noise and channel distortion.

• Journal of Korea Multimedia Society
• /
• v.23 no.4
• /
• pp.539-548
• /
• 2020

Deep learning technology is currently being used and applied in many different fields. Convolution neural network (CNN) is a method of artificial neural networks in deep learning, which is commonly used for analyzing different types of images through classification. In the conventional classification of histopathology images of prostate carcinomas, the rating of cancer is classified by human subjective observation. However, this approach has produced to some misdiagnosing of cancer grading. To solve this problem, CNN based classification method is proposed in this paper, to train the histological images and classify the prostate cancer grading into two classes of the benign and malignant. The CNN architecture used in this paper is based on the VGG models, which is specialized for image classification. However, color normalization was performed based on the contrast enhancement technique, and the normalized images were used for CNN training, to compare the classification results of both original and normalized images. In all cases, accuracy was over 90%, accuracy of the original was 96%, accuracy of other cases was higher, and loss was the lowest with 9%.

• The Journal of Korean Medicine
• /
• v.31 no.3
• /
• pp.1-7
• /
• 2010

Objectives: To introduce to TKM scientific dose conversion methods of human to animal or animal to human for new drug investigations. Methods: We searched guidelines of the FDA and KFDA, and compared them with references for drug-dose conversion from various databases such as PubMed and Google. Then, we analyzed the potential issues and problems related to dose conversion in safety documentation of new herbal drugs based on our experiences during Investigational New Drug (IND) applications of TKM. Results: Dose conversion from human to animal or animal to human must be appropriately translated during new drug development. From time to time, investigators have some difficulty in determining the appropriate dose, because of misunderstandings of dose conversion, especially when they estimate starting dose in clinical or animal studies to investigate efficacy, toxicology and mechanisms. Therefore, education of appropriate dose calculation is crucial for investigators. The animal dose should not be extrapolated to humans by a simple conversion method based only on body weight, because many studies suggest the normalization method is based mainly on body surface area (BSA). In general, the body surface area seems to have good correlation among species with several parameters including oxygen utilization, caloric expenditure, basal metabolism, blood volume and circulating plasma protein. Likewise, a safety factor should be taken into consideration when deciding high dose in animal toxicology study. Conclusion: Herein, we explain the significance of dose conversion based on body surface area and starting dose estimation for clinical trials with safety factor.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.22 no.1
• /
• pp.1-8
• /
• 2018

Recently, the convolutional neural network shows high performance in many computer vision tasks. However, convolutional neural networks require enormous amount of operation, so it is difficult to adopt them in the embedded environments. To solve this problem, many studies are performed on the ASIC or FPGA implementation, where an efficient representation method is required. The fixed-point representation is adequate for the ASIC or FPGA implementation but causes a performance degradation. This paper proposes a separate optimization of representations for the convolutional layers and the batch normalization layers. With the proposed method, the required bit width for the convolutional layers is reduced from 16 bits to 10 bits for the ResNet-50 neural network. Since the computation amount of the convolutional layers occupies the most of the entire computation, the bit width reduction in the convolutional layers enables the efficient implementation of the convolutional neural networks.

• Spatial Information Research
• /
• v.19 no.1
• /
• pp.29-40
• /
• 2011

GOCI the world first Ocean Color Imager in Geostationary Orbit, which could obtain total 8 images of the same region a day, however, its spatial resolution(500m) is not enough to use for the accurate land application, Super Resolution(SR), reconstructing the high resolution(HR) image from multiple low resolution(LR) images introduced by computer vision field. could be applied to the time-series remotely sensed images such as GOCI data, and the higher resolution image could be reconstructed from multiple images by the SR, and also the cloud masked area of images could be recovered. As the precedent study for developing the efficient SR method for GOCI images, on this research, it reproduced the simulated data under the acquisition process of the remote sensed data, and then the simulated images arc applied to the proposed algorithm. From the proposed algorithm result of the simulated data, it turned out that low resolution(LR) images could be registered in sub-pixel accuracy, and the reconstructed HR image including RMSE, PSNR, SSIM Index value compared with original HR image were 0.5763, 52.9183 db, 0.9486, could be obtained.

• Journal of Yeungnam Medical Science
• /
• v.2 no.1
• /
• pp.23-30
• /
• 1985

Keloids are abnormally healed skin wounds that develop in the subpapillary layer of the dermis. They are a lesion with wide, raised and deep scars. They exceed the original dimensions of the wound and grow mounds upon mounds of collagen in a pseudotumor fashion. Their treatment may take several forms such as surgery, intralesional injection of steroid, compression, superficial irradiation, and combination therapy. However, absolute method is nothing until now. Recently, the cryosurgery shows relatively good effect in treatment, so we tried the clinical experience with cryosurgery in the treatment of keloids. Material and methods: During the past 2 years, we treated 20 individuals of the keloids with severe itching and pain. The age ranged from 5 to 45 years old. Only 6 cases were biopsied before and after cryotherapy. The cryosurgery set we used was Toitu model CR 201 $N_2O$ gas (tip temperature is $-80^{\circ}C$) and was applied directly on the lesion about 4 to 5 minutes with slight compression. After cryosurgery in keloids, the following results were obtained: 1. It is both quick and easy method. 2. It causes little or no pain and no loss of blood. 3. Integumentary normalization is rapid. The new scar tissue is smaller, and more elastic and soft. 4. The pain, itching and paresthesia commonly associated with keloid is usually disappeared. 5. Other treatment can be used after cryosurgery. 6. Histologic picture after cryosurgery is similar with the result of steroid injection. 7. The mechanism of the cryosurgery in keloids is the result of the direct tissue destroying action and cryoimmunologic reaction.

• Journal of Korea Game Society
• /
• v.15 no.3
• /
• pp.135-150
• /
• 2015

After the release of SDK in 2011, Kinect developed for the motion recognition games has been applied not only in game but also in various fields such as science, education, and health care. It has some problems as belated responses to player's movements, a lot of noise in the recognized data, and an untraceable player when the body is partially occluded. Because of Kinect's such peculiarities of playing environment, most Kinect games require the inconvenience of Kinect's location or player's posture correction. In this paper, we propose an interface correction method that minimizes the requirements to be asked players, manages the exceptions such as noise, and enables to process consistently the player's movements in the game using Kinect. Also, we present the delay time to be considered to develop the game using Kinect through the experiment.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.14 no.2
• /
• pp.534-539
• /
• 2010

In genomic studies, thousands of features are collected on relatively few samples. One of the goals of these studies is to build classifiers to predict the outcome of future observations. There are three inherent steps to build classifiers: a significant gene selection, model selection and prediction assessment. In the paper, with a focus on prediction assessment, we normalize microarray data with quantile-normalization methods that adjust quartile of all slide equally and then design a system comparing several methods to estimate 'true' prediction error of a prediction model in the presence of feature selection and compare and analyze a prediction error of them. LOOCV generally performs very well with small MSE and bias, the split sample method and 2-fold CV perform with small sample size very pooly. For computationally burdensome analyses, 10-fold CV may be preferable to LOOCV.