• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.1
• /
• pp.39-46
• /
• 2019

In this study, before system development for the elimination of foreign fish species, we propose an algorithm to classify fish species by training fish images with CNN. The raw data for CNN learning were directly captured images for each species, Dataset 1 increases the number of images to improve the classification of fish species and Dataset 2 realizes images close to natural environment are constructed and used as training and test data. The classification performance of four CNNs are over 99.97% for dataset 1 and 99.5% for dataset 2, in particular, we confirm that the learned CNN using Data Set 2 has satisfactory performance for fish images similar to the natural environment. And among four CNNs, AlexNet achieves satisfactory performance, and this has also the shortest execution time and training time, we confirm that it is the most suitable structure to develop the system for the elimination of foreign fish species.

• Korean Journal of Cognitive Science
• /
• v.1 no.1
• /
• pp.103-127
• /
• 1989

Learning systems by using examples have been developed which include ALEX, LP, and LEX.Specially Silver's LP systems suggerts the method to use a seyuence of operators, which was applied to the worked example, to sove a symbolic equation.This paper presents the new learning system, called LRD, in which generalization and discrimination steps are suggerted to solv all the problems similar to the worked example.The system LRD is illustrated by the problem of finding the ranges of transcendentral functions and compared to LP and LEX by the problems discussed in them.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.1
• /
• pp.53-59
• /
• 2017

Optical character recognition (OCR) automatically recognizes text in an image. OCR is still a challenging problem in computer vision. A successful solution to OCR has important device applications, such as text-to-speech conversion and automatic document classification. In this work, we analyze character recognition performance using the current state-of-the-art deep-learning structures. One is the AlexNet structure, another is the LeNet structure, and the other one is the SPNet structure. For this, we have built our own dataset that contains digits and upper- and lower-case characters. We experiment in the presence of salt-and-pepper noise or Gaussian noise, and report the performance comparison in terms of recognition error. Experimental results indicate by five-fold cross-validation that the SPNet structure (our approach) outperforms AlexNet and LeNet in recognition error.

• Journal of Biomedical Engineering Research
• /
• v.39 no.6
• /
• pp.229-236
• /
• 2018

Liver cancer is one of the highest incidents in the world, and the mortality rate is the second most common disease after lung cancer. The purpose of this study is to evaluate the diagnostic ability of deep learning in the classification of malignant and benign tumors in CT images of patients with liver tumors. We also tried to identify the best data processing methods and deep learning models for classifying malignant and benign tumors in the liver. In this study, CT data were collected from 92 patients (benign liver tumors: 44, malignant liver tumors: 48) at the Gil Medical Center. The CT data of each patient were used for cross-sectional images of 3,024 liver tumors. In AlexNet and VggNet, the average of the overall accuracy at each image size was calculated: the average of the overall accuracy of the $200{\times}200$ image size is 69.58% (AlexNet), 69.4% (VggNet), $150{\times}150$ image size is 71.54%, 67%, $100{\times}100$ image size is 68.79%, 66.2%. In conclusion, the overall accuracy of each does not exceed 80%, so it does not have a high level of accuracy. In addition, the average accuracy in benign was 90.3% and the accuracy in malignant was 46.2%, which is a significant difference between benign and malignant. Also, the time it takes for AlexNet to learn is about 1.6 times faster than VggNet but statistically no different (p > 0.05). Since both models are less than 90% of the overall accuracy, more research and development are needed, such as learning the liver tumor data using a new model, or the process of pre-processing the data images in other methods. In the future, it will be useful to use specialists for image reading using deep learning.

• Journal of Trauma and Injury
• /
• v.36 no.1
• /
• pp.60-64
• /
• 2023

Upper extremity vascular injuries occurring with acute compartment syndrome are very challenging to manage in an emergency context in resource-poor settings. The need to always recognize the likelihood of coexisting compartment syndrome guides surgeons to perform concomitant fasciotomy to ensure a better outcome. We managed three vascular injuries in the upper extremities in two patients with concomitant imminent compartment syndrome observed intraoperatively. The first injury was complete brachial artery disruption following blunt trauma, while the second and third injuries were radial and ulnar artery transection caused by sharp glass cuts. Both patients were treated with vascular repair and fasciotomy. Secondary wound coverage was applied with split-thickness skin grafting, and the outcomes were satisfactory. Concomitant fasciotomy potentially improves the outcomes of vascular repair in emergency vascular surgery and should be considered for all injuries with the potential for acute compartment syndrome.

• Annual Conference on Human and Language Technology
• /
• 2021.10a
• /
• pp.423-426
• /
• 2021

본 논문은 전역 스타일 토큰(Global Style Token)을 기준으로 하여 감정의 세기를 조절할 수 있는 방법을 소개한다. 기존의 전역 스타일 토큰 연구에서는 원하는 스타일이 포함된 참조 오디오(reference audio)을 사용하여 음성을 합성하였다. 그러나, 참조 오디오의 스타일대로만 음성합성이 가능하기 때문에 세밀한 감정 조절에 어려움이 있었다. 이 문제를 해결하기 위해 본 논문에서는 전역 스타일 토큰의 레퍼런스 인코더 부분을 잔여 블록(residual block)과 컴퓨터 비전 분야에서 사용되는 AlexNet으로 대체하였다. AlexNet은 5개의 함성곱 신경망(convolutional neural networks) 으로 구성되어 있지만, 본 논문에서는 1개의 신경망을 제외한 4개의 레이어만 사용했다. 청취 평가(Mean Opinion Score)를 통해 제시된 방법으로 감정 세기의 조절 가능성을 보여준다.

• KIISE Transactions on Computing Practices
• /
• v.23 no.7
• /
• pp.417-423
• /
• 2017

Recently, many embedded devices that have the computing capability required for deep learning have become available; hence, many new applications using these devices are emerging. However, these embedded devices have an architecture different from that of PCs and high-performance servers. In this paper, we propose a method that improves the performance of deep-learning framework by considering the architecture of an embedded device that shares memory between the CPU and the GPU. The proposed method is implemented in Caffe, an open-source deep-learning framework, and is evaluated on an NVIDIA Jetson TK1 embedded device. In the experiment, we investigate the image recognition performance of several state-of-the-art deep-learning networks, including AlexNet, VGGNet, and GoogLeNet. Our results show that the proposed method can achieve significant performance gain. For instance, in AlexNet, we could reduce image recognition latency by about 33% and energy consumption by about 50%.

• Journal of Genetic Medicine
• /
• v.1 no.1
• /
• pp.57-59
• /
• 1997

• KIISE Transactions on Computing Practices
• /
• v.24 no.1
• /
• pp.53-57
• /
• 2018

A poisoning accident is often caused by a situation in which people eat poisonous mushrooms because they cannot distinguish between edible mushrooms and poisonous mushrooms. In this paper, we propose an automatic mushroom recognition system by using the convolutional neural network. We collected 1478 mushroom images of 38 species using image crawling, and used the dataset for learning the convolutional neural network. A comparison experiment using AlexNet, VGGNet, and GoogLeNet was performed using the collected datasets, and a comparison experiment using a class number expansion and a fine-tuning technique for transfer learning were performed. As a result of our experiment, we achieve 82.63% top-1 accuracy and 96.84% top-5 accuracy on test set of our dataset.

• Asian-Australasian Journal of Animal Sciences
• /
• v.7 no.2
• /
• pp.191-196
• /
• 1994

Two experiments were conducted to study the effect of using Egyptian mallow leaf meal (EMLM) on growth performance and feed utilization of common carp (Cyprinus carpio L.) in experiment 1. Four diets containing 0, 5, 15 and 25% EMLM were included at the expense of berseem leaf meal and fed to fingerlings of common carp for 98 days. The results showed that the average daily gain, feed intake and feed coefficient ratio (FCR) were improved (p<0.05) with increasing the level of EMLM in the diet. Fish fed 25% EMLM were similar to control fish (30% berseem leaf meal) in the productive value (PPV%). In experiment 2, five diets were prepared to contain: 1) 30% berseem leaf meal, 2) 25% untreated EMLM, 3) 25% cooked EMLM 4) 25% treated EMLM with 0.5% NaOH and 5) 25% treated EMLM with 1% NaOH. The results showed that diet containing EMLM gave the best growth performance and feed utilization. However, diet containing 1% NaOH treated EMLM superior to the other diets in PPV% and energy utilization. Diets containing 0.5% NaOH-treated EMLM or cooked EMLM decreased the protein utilization compared to those containing EMLM.