• 전기전자학회논문지
• /
• 제17권4호
• /
• pp.517-524
• /
• 2013

Stereo matching has been grabbing the attention of researchers because it plays an important role in computer vision, remote sensing and photogrammetry. Although most methods perform well with small size images, experiments applying them to large-scale data sets under uncontrolled conditions are still lacking. In this paper, we present an empirical study on stereo matching for large-scale high-resolution satellite images. A new method is studied to solve the problem of huge size and memory requirement when dealing with large-scale high resolution satellite images. Integrating the tiling technique with the well-known dynamic programming and coarse-to-fine pyramid scheme as well as using memory wisely, the suggested method can be utilized for huge stereo satellite images. Analyzing 350 points from an image of size of 8192 x 8192, disparity results attain an acceptable accuracy with RMS error of 0.5459. Taking the trade-off between computational aspect and accuracy, our method gives an efficient stereo matching for huge satellite image files.

• 인터넷정보학회논문지
• /
• 제21권5호
• /
• pp.67-73
• /
• 2020

In this paper, we present a CNN-based gesture recognition approach which reduces the memory burden of input data. Most of the neural network-based gesture recognition methods have used a sequence of frame images as input data, which cause a memory burden problem. We use a motion history image in order to define a meaningful gesture. The motion history image is a grayscale image into which the temporal motion information is collapsed by synthesizing silhouette images of a user during the period of one meaningful gesture. In this paper, we first summarize the previous traditional approaches and neural network-based approaches for gesture recognition. Then we explain the data preprocessing procedure for making the motion history image and the neural network architecture with three convolution layers for recognizing the meaningful gestures. In the experiments, we trained five types of gestures, namely those for charging power, shooting left, shooting right, kicking left, and kicking right. The accuracy of gesture recognition was measured by adjusting the number of filters in each layer in the proposed network. We use a grayscale image with 240 × 320 resolution which defines one meaningful gesture and achieved a gesture recognition accuracy of 98.24%.

• 한국해양공학회지
• /
• 제35권5호
• /
• pp.336-346
• /
• 2021

The prediction of wave conditions is crucial in the field of marine and ocean engineering. Hence, this study aims to predict the significant wave height through machine learning (ML), a soft computing method. The adopted metocean data, collected from 2012 to 2020, were obtained from the Korea Institute of Ocean Science and Technology. We adopted the feedforward neural network (FNN) and long-short term memory (LSTM) models to predict significant wave height. Input parameters for the input layer were selected by Pearson correlation coefficients. To obtain the optimized hyperparameter, we conducted a sensitivity study on the window size, node, layer, and activation function. Finally, the significant wave height was predicted using the FNN and LSTM models, by varying the three input parameters and three window sizes. Accordingly, FNN (W48) (i.e., FNN with window size 48) and LSTM (W48) (i.e., LSTM with window size 48) were superior outcomes. The most suitable model for predicting the significant wave height was FNN(W48) owing to its accuracy and calculation time. If the metocean data were further accumulated, the accuracy of the ML model would have improved, and it will be beneficial to predict added resistance by waves when conducting a sea trial test.

• 대한원격탐사학회지
• /
• 제37권4호
• /
• pp.719-731
• /
• 2021

This study proposes a two-stage hybrid classification model for crop classification using multi-temporal remote sensing images; the model combines feature embedding by using an autoencoder (AE) with a convolutional neural network (CNN) classifier to fully utilize features including informative temporal and spatial signatures. Long short-term memory (LSTM)-based AE (LAE) is fine-tuned using class label information to extract latent features that contain less noise and useful temporal signatures. The CNN classifier is then applied to effectively account for the spatial characteristics of the extracted latent features. A crop classification experiment with multi-temporal unmanned aerial vehicle images is conducted to illustrate the potential application of the proposed hybrid model. The classification performance of the proposed model is compared with various combinations of conventional deep learning models (CNN, LSTM, and convolutional LSTM) and different inputs (original multi-temporal images and features from stacked AE). From the crop classification experiment, the best classification accuracy was achieved by the proposed model that utilized the latent features by fine-tuned LAE as input for the CNN classifier. The latent features that contain useful temporal signatures and are less noisy could increase the class separability between crops with similar spectral signatures, thereby leading to superior classification accuracy. The experimental results demonstrate the importance of effective feature extraction and the potential of the proposed classification model for crop classification using multi-temporal remote sensing images.

• International Journal of Computer Science & Network Security
• /
• 제22권4호
• /
• pp.119-130
• /
• 2022

Crime is a common social problem that affects the quality of life. As the number of crimes increases, it is necessary to build a model to predict the number of crimes that may occur in a given period, identify the characteristics of a person who may commit a particular crime, and identify places where a particular crime may occur. Data privacy is the main challenge that organizations face when building this type of predictive models. Federated learning (FL) is a promising approach that overcomes data security and privacy challenges, as it enables organizations to build a machine learning model based on distributed datasets without sharing raw data or violating data privacy. In this paper, a federated long short- term memory (LSTM) model is proposed and compared with a traditional LSTM model. Proposed model is developed using TensorFlow Federated (TFF) and the Keras API to predict the number of crimes. The proposed model is applied on the Boston crime dataset. The proposed model's parameters are fine tuned to obtain minimum loss and maximum accuracy. The proposed federated LSTM model is compared with the traditional LSTM model and found that the federated LSTM model achieved lower loss, better accuracy, and higher training time than the traditional LSTM model.

• 한국해양공학회지
• /
• 제36권5호
• /
• pp.295-302
• /
• 2022

The initial response to a marine accident can play a key role to minimize the accident. Therefore, various decision support systems have been developed using sensors, simulations, and active response equipment. In this study, we developed an algorithm to predict damage locations using ship motion data with bidirectional long short-term memory (BiLSTM), a type of recurrent neural network. To reflect the low frequency ship motion characteristics, 200 time-series data collected for 100 s were considered as input values. Heave, roll, and pitch were used as features for the prediction model. The F1-score of the BiLSTM model was 0.92; this was an improvement over the F1-score of 0.90 of a prior model. Furthermore, 53 of 75 locations of damage had an F1-score above 0.90. The model predicted the damage location with high accuracy, allowing for a quick initial response even if the ship did not have flood sensors. The model can be used as input data with high accuracy for a real-time progressive flooding simulator on board.

• International Journal of Computer Science & Network Security
• /
• 제23권5호
• /
• pp.53-64
• /
• 2023

Early detection of endometrial carcinoma in uterus is essential for effective treatment. Endometrial carcinoma is the worst kind of endometrium cancer among the others since it is considerably more likely to affect the additional parts of the body if not detected and treated early. Non-invasive medical computer vision, also known as medical image processing, is becoming increasingly essential in the clinical diagnosis of various diseases. Such techniques provide a tool for automatic image processing, allowing for an accurate and timely assessment of the lesion. One of the most difficult aspects of developing an effective automatic categorization system is the absence of huge datasets. Using image processing and deep learning, this article presented an artificial endometrium cancer diagnosis system. The processes in this study include gathering a dermoscopy images from the database, preprocessing, segmentation using hybrid Fuzzy C-Means (FCM) and optimizing the weights using the Whale Optimization Algorithm (WOA). The characteristics of the damaged endometrium cells are retrieved using the feature extraction approach after the Magnetic Resonance pictures have been segmented. The collected characteristics are classified using a deep learning-based methodology called Long Short-Term Memory (LSTM) and Bi-directional LSTM classifiers. After using the publicly accessible data set, suggested classifiers obtain an accuracy of 97% and segmentation accuracy of 93%.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제36권7호
• /
• pp.590-606
• /
• 2009

C프로그램에서 발생할 수 있는 메모리 누수(memory leaks)를 실행 전에 찾아 주는 분석기를 제안한다. 이 분석기는 SPEC2000 벤치마크 프로그램과 여러 오픈 소스 프로그램들에 적용시킨 결과 다른 분석기에 비해 상대적으로 뛰어난 성능을 보여준다. 총 1,777 KLOC의 프로그램에서 332개의 메모리 누수 오류를 찾아냈으며 이 때 발생한 허위 경보(false positive)는 47개에 불과하다(12.4%의 허위 경보율). 이분석기는 초당720 LOC를 분석한다. 각각의 함수들이 하는 일을 요약하여 그 함수들이 불려지는 곳에서 사용함으로써 모든 함수에 대해 단 한번의 분석만을 실행한다. 각각의 함수 요약(procedural summary)은 잘 매개화 되어 함수가 불려질 때의 상황에 맞게 적용할 수 있다. 실제 프로그램들에 적용하고 피드백 받는 방법을 통해 함수가 하는 일중에 메모리 누수를 찾는데 효과적인 정보들만으로 추리는 과정을 거쳤다. 분석은 요약 해석(abstract interpretation)에 기반하였기 때문에 C의 여러 문법 구조와 순환 호출 (recursive call), 루프(loop)등은 고정점 연산(fixpoint iteration)을 통해 자연스럽게 해결한다.

• 한국축산식품학회지
• /
• 제29권2호
• /
• pp.278-282
• /
• 2009

Previous studies indicate that BF-7 enhances learning and memory in normal and elderly individuals. Here, we evaluated whether milk containing BF-7 (BF-7 milk) could improve the brain function, with thirty normal university students $(21{\pm}1.2 years)$. Two versions of the Paced Auditory Serial Addition Test were used under double-blinded conditions to measure the efficacy of BF-7 milk on learning and memory, especially working memory and attention, and on mathematical ability. As a result, BF-7 milk improved the accuracy of the task more than 3-fold. Furthermore, BF-7 milk protected cultured neuronal cells from 3-hydroxykynurenine, a normal endogenous brain stress agent. These results indicate that BF-7 milk enhances memory, attention and mathematical ability in normal persons.

• 인지과학
• /
• 제35권1호
• /
• pp.1-21
• /
• 2024

본 연구는 두 가지 이론적 모델인 통합된 객체 모형과 특장 병렬-독립 저장 모형을 검증함으로써 시각작업기억 표상의 특성을 조사하였다. 실험 I에서 참가자들은 색상 사각형, 방위 막대 또는 두 가지 모두로 구성된 배열을 기억한 뒤 이를 토대로 변화탐지과제를 수행했다. 단일 특징 조건에서 기억배열은 하나의 특징(방위 또는 색상)으로만 구성된 반면, 두 가지 특징 조건은 둘 모두를 포함했다. 두 조건간 변화탐지 수행의 차이는 없었으며 이는 병렬-독립 저장 모형보다는 통합된 객체 모형을 지지한다. 실험 II에서는 이등변삼각형의 방위, 색상 사각형 또는 두 특징 모두로 구성된 기억배열을 대상으로 회상과제가 실시되었으며, 단일 특징과 두 가지 특징 조건 간 회상 수행이 비교되었다. 두 조건 간 회상 정확도에는 차이가 없었으나 표상 선명도와 추측반응에 대한 분석 결과는 강한 객체 모형보다는 약한 객체 모형을 시사했다. 본 연구의 결과는 시각작업기억의 표상 특성을 둘러싼 현시점의 논쟁에 있어서 병렬-독립 저장 모형이 아닌 통합된 객체 모형의 우세를 지지한다.