• Journal of Korean Society on Water Environment
• /
• v.37 no.4
• /
• pp.275-285
• /
• 2021

Algal bloom is an important issue in maintaining the safety of the drinking water supply system. Fast detection and classification of algae images are essential for the management of algal blooms. Conventional visual identification using a microscope is a labor-intensive and time-consuming method that often requires several hours to several days in order to obtain analysis results from field water samples. In recent decades, various deep learning algorithms have been developed and widely used in object detection studies. YOLO is a state-of-the-art deep learning algorithm. In this study the third version of the YOLO algorithm, namely, YOLOv3, was used to develop an algae image detection model. YOLOv3 is one of the most representative one-stage object detection algorithms with faster inference time, which is an important benefit of YOLO. A total of 1,114 algae images for 30 genera collected by microscope were used to develop the YOLOv3 algae image detection model. The algae images were divided into four groups with five, 10, 20, and 30 genera for training and testing the model. The mean average precision (mAP) was 81, 70, 52, and 41 for data sets with five, 10, 20, and 30 genera, respectively. The precision was higher than 0.8 for all four image groups. These results show the practical applicability of the deep learning algorithm, YOLOv3, for algae image detection.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.4
• /
• pp.1989-2011
• /
• 2019

Vehicle detection based on aerial images is an interesting and challenging research topic. Most of the traditional vehicle detection methods are based on the sliding window search algorithm, but these methods are not sufficient for the extraction of object features, and accompanied with heavy computational costs. Recent studies have shown that convolutional neural network algorithm has made a significant progress in computer vision, especially Faster R-CNN. However, this algorithm mainly detects objects in natural scenes, it is not suitable for detecting small object in aerial view. In this paper, an accurate and effective vehicle detection algorithm based on Faster R-CNN is proposed. Our method fuse a hyperactive feature map network with Eltwise model and Concat model, which is more conducive to the extraction of small object features. Moreover, setting suitable anchor boxes based on the size of the object is used in our model, which also effectively improves the performance of the detection. We evaluate the detection performance of our method on the Munich dataset and our collected dataset, with improvements in accuracy and effectivity compared with other methods. Our model achieves 82.2% in recall rate and 90.2% accuracy rate on Munich dataset, which has increased by 2.5 and 1.3 percentage points respectively over the state-of-the-art methods.

• Journal of the HCI Society of Korea
• /
• v.1 no.1
• /
• pp.45-52
• /
• 2006

This paper presents an image-space algorithm to real-time collision detection, which is run completely by GPU. For a single object or for multiple objects with no collision, the front and back faces appear alternately along the view direction. However, such alternation is violated when objects collide. Based on these observations, the algorithm propose the depth peeling method which renders the minimal surface of objects, not whole surface, to find colliding. The Depth peeling method utilizes the state-of-the-art functionalities of GPU such as framebuffer object, vertexbuffer object, and occlusion query. Combining these functions, multi-pass rendering and context switch can be done with low overhead. Therefore proposed approach has less rendering times and rendering overhead than previous image-space collision detection. The algorithm can handle deformable objects and complex objects, and its precision is governed by the resolution of the render-target-texture. The experimental results show the feasibility of GPU-based collision detection and its performance gain in real-time applications such as 3D games.

• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.8 no.6
• /
• pp.957-966
• /
• 2018

Recently, the demand for remote patient monitoring based on IoT has been increased due to aging population and an increase in single-person household. A non-contact biological signal measurement system using multiple IR-UWB radars for remote patient monitoring is proposed in this paper. To reduce error signals, a multilayer Subtraction algorithm is applied because when the background subtraction algorithm was applied to the biological signal processing, errors occurred such as voltage noise and staircase phenomenon. Therefore, a multilayer background subtraction algorithm is applied to reduce error occurrence. The multilayer background subtraction algorithm extracts the signal by calculating the amount of change between the previous clutter and the current clutter. In this study, the SVD algorithm is used. We applied the improved multilayer background subtraction algorithm to biological signal measurement and computed the respiration rate through Fast Fourier Transform (FFT). To verify the proposed system using IR-UWB radars and multilayer background subtraction algorithm, the respiration rate was measured. The validity of this study was verified by obtaining a precision of 97.36% as a result of a control experiment with Neulog's attachment type breathing apparatus. The implemented algorithm improves the inconvenience of the existing contact wearable method.

• Korean Journal of Mathematics
• /
• v.20 no.1
• /
• pp.137-159
• /
• 2012

In this paper, we deal with recent researches on Ying N$\ddot{u}$ and Ying Buzu(盈不足) which were addressed in the book Jiu Zhang Suan Shu(九章算術, The Nine Chapters on the Mathematical Art). Ying N$\ddot{u}$(Ying Buzu) is a concept on profit and loss problems. Ying Buzu Shu(盈不足術, the method of excess and deficit) represents an algorithm which has been used for solving many mathematical problems. It is known as a rule of double false position in the West. We show the importance of Ying Buzu Shu via an analysis of some problems in 'Ying Buzu' chapter. In 1202, Fibonacci(c.1170-c.1250) used Ying Buzu Shu in his book. This shows some of Asian mathematics were introduced to the West even before the year 1200. We present the origin of Ying Buzu Shu, and its relationship with Cramer's Rule. We have discovered how Asia's Ying Buzu Shu spread to Europe via Arab countries. In addition, we analyze some characters of Ying N$\ddot{u}$(Ying Buzu) in the book Suan Xue Bao Jian(算學寶鑑).

• The Journal of the Korea Contents Association
• /
• v.9 no.7
• /
• pp.1-8
• /
• 2009

In this paper, we propose a home medical system that integrates a self-diagnosing disease classification system and a tele-consulting system by communication technology. The proposed disease classification system supports to self-diagnose the health condition based on oriental medical science using fuzzy neural network algorithm. The prepared database includes 72 different diseases and their associated symptoms based on a famous medical science book "Dong-eui-bo-gam". The proposed system extracts three most prospective diseases from user's symptoms by analyzing disease database with fuzzy neural network technology. Technically, user's symptoms are used as an input vector and the clustering algorithm based upon a fuzzy neural network is performed. The degree of fuzzy membership is computed for each probable cluster and the system infers the three most prospective diseases with their degree of membership. Such information should be sent to medical doctors via our tele-consulting system module. Finally a user can take an appropriate consultation via video images by a medical doctor. Oriental medical doctors verified the accuracy of disease diagnosing ability and the efficacy of overall system's plausibility in the real world.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.1
• /
• pp.27-36
• /
• 2000

As a potential approach for non-destructive testing of concrete structures, we evaluate the time-of-flight (TOF) ultrasound tomography technique In conventional X ray tomography, the reconstructed Image corresponds to the internal attenuation coefficient However, in TOF ultrasound tomography, the reconstructed Image is proportional to the retractive index of the medium Because refractive effects are minimal for X-rays, conventional reconstruction techniques are applied to reconstruct the Image in X-ray tomography However, since ultrasound travels in curved path, due to the spatial variations in the refractive index of the medium, the path must be known to correctly reconstruct the Image. Algorithm for determining the ultrasound path is developed from a Geometrical Optics point view and the image reconstruction algorithm, since the paths are curved It requires the algebraic approach, namely the ART or the SIRT Here, the difference between the computed and the measured TOP data is used as a basis, for the iteration process First the initial image is reconstructed assuming straight paths. It then updates the path based on the recently reconstructed image This process of reconstruction and path determination repeats until convergence The proposed algorithm is evaluated by computer simulations, and in addition is applied to a real concrete structure.

• Journal of Information Processing Systems
• /
• v.14 no.2
• /
• pp.418-434
• /
• 2018

With the increasing use of the Internet and electronic documents, automatic text categorization becomes imperative. Several machine learning algorithms have been proposed for text categorization. The k-nearest neighbor algorithm (kNN) is known to be one of the best state of the art classifiers when used for text categorization. However, kNN suffers from limitations such as high computation when classifying new instances. Instance selection techniques have emerged as highly competitive methods to improve kNN through data reduction. However previous works have evaluated those approaches only on structured datasets. In addition, their performance has not been examined over the text categorization domain where the dimensionality and size of the dataset is very high. Motivated by these observations, this paper investigates and analyzes the impact of instance selection on kNN-based text categorization in terms of various aspects such as classification accuracy, classification efficiency, and data reduction.

• Proceedings of the Korea Multimedia Society Conference
• /
• 2002.11b
• /
• pp.149-154
• /
• 2002

운송 컨테이너의 식별자를 추출하고 인식하는 것은 컨테이너 식별자들의 크기나 위치가 정형화되어 있지 않고 외부의 잡음으로 인하여 식별자의 형태가 훼손되어 있기 때문에 어렵다. 본 논문에서는 이러한 특성을 고려하여 컨테이너 영상에 대해 Canny 에지 추출 기법을 이용하여 컨테이너의 식별자 영역을 추출하고 추출된 컨테이너 식별자 영역에서 히스토그램 방법과 윤곽선 추적 알고리즘을 결합하여 개별 식별자를 추출한다. 추출된 컨테이너 개별 식별자 인식은 ART1을 수정하여 지도 학습 방법과 결합한 개선된 자가생성 지도학습 알고리즘을 제안하여 적용한다. 실험결과에서는 제안된 컨테이너 식별자 추출 및 인식 방법이 다양한 컨테이너 영상에 대해 효율적인 것을 보인다.

• 제어로봇시스템학회:학술대회논문집
• /
• 1987.10b
• /
• pp.264-268
• /
• 1987

This paper is concerned on kinematic analysis and simulation of an automatic feeding mechanism subjected by the motion of a curvilinear inverse can. The curvilinear cam is rotated by positioning a translating roller and the automatic feeding mechanism is moved to the sliding position by the motion of a campin fixed on the curvilinear cam. The curvilinear cam consists of two arcs of circles and two straight lines. The modular approach is used for the kinematic analysis of the feeding mechanism. As the first part of the paper for the motion simulation of the cam-feeding system, this paper discusses the algorithm to simulate the motion of the cam-feeding mechanism. The second part of the paper presents the state-of-art for the graphics-oriented CAD technique,