• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.3875-3891
• /
• 2021

In this study, a Velostat pressure sensor was manufactured to develop a plantar pressure measurement system and a C#-based application was developed to monitor and collect plantar pressure data in real time. In order to evaluate the characteristics of the proposed plantar pressure measurement system, the accuracy of plantar pressure index and personal classification was verified by comparing with MatScan, a commercial plantar pressure measurement system. As a result, the output characteristics according to the weight of the Velostat pressure sensor were evaluated and a trend line with the reliability of r² = 0.98 was detected. The Root Mean Square Error(RMSE) of the weighted area was 11.315 cm², the RMSE of the x coordinate of Center of Pressure(CoP_x) was 1.036 cm and the RMSE of the y coordinate of Center of Pressure(CoP_y) was 0.936 cm. Finally, inaccuracy of personal classification, the proposed system was 99.47% and MatScan was 96.86%. Based on the advantage of being simple to implement and capable of manufacturing at low cost, it is considered that it can be applied to various fields of measuring vital signs such as sitting posture and breathing in addition to the plantar pressure measurement system.

• ETRI Journal
• /
• v.45 no.5
• /
• pp.847-861
• /
• 2023

Dynamic object detection is essential for ensuring safe and reliable autonomous driving. Recently, light detection and ranging (LiDAR)-based object detection has been introduced and shown excellent performance on various benchmarks. Although LiDAR sensors have excellent accuracy in estimating distance, they lack texture or color information and have a lower resolution than conventional cameras. In addition, performance degradation occurs when a LiDAR-based object detection model is applied to different driving environments or when sensors from different LiDAR manufacturers are utilized owing to the domain gap phenomenon. To address these issues, a sensor-fusion-based object detection and classification method is proposed. The proposed method operates in real time, making it suitable for integration into autonomous vehicles. It performs well on our custom dataset and on publicly available datasets, demonstrating its effectiveness in real-world road environments. In addition, we will make available a novel three-dimensional moving object detection dataset called ETRI 3D MOD.

• Proceedings of the KIEE Conference
• /
• 1988.07a
• /
• pp.662-665
• /
• 1988

This paper proposes the Minimum-Distance Classification(MDC) processor using the Residue Number System(RNS). The proposed MDC Processor in this paper is efficient for real-time pattern clustering application and illustrate satisfiable error rate in application experiments of image segmentation but error rate increase as cluster number do.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.493-494
• /
• 2023

본 논문은 벚꽃나무 영상 데이터를 활용하여 벚꽃의 상태(개화, 만개, 낙화)를 실시간으로 분류하는 연구를 소개한다. 이 연구의 목적은, 실시간으로 취득되는 벚꽃나무의 영상 데이터를 사전에 학습된 CNN 기반 이미지 분류 모델을 통해 벚꽃의 상태에 따라 분류하는 것이다. 약 1,000장의 벚꽃나무 이미지를 활용하여 CNN 모델을 학습시키고, 모델이 새로운 이미지에 대해 얼마나 정확하게 벚꽃의 상태를 분류하는지를 평가하였다. 학습데이터는 훈련 데이터와 검증 데이터로 나누었으며, 개화, 만개, 낙화 등의 상태별로 폴더를 구분하여 관리하였다. 또한, ImageNet 데이터셋에서 사전 학습된 ResNet50 가중치를 사용하는 전이학습 방법을 적용하여 학습 과정을 더 효율적으로 수행하고, 모델의 성능을 향상시켰다.

• Clinical Endoscopy
• /
• v.55 no.2
• /
• pp.197-207
• /
• 2022

Background/Aims: Endoscopic visualization of the microscopic anatomy can facilitate the real-time diagnosis of pancreatobiliary disorders and provide guidance for treatment. This study aimed to review the technique, image classification, and diagnostic performance of confocal laser endomicroscopy (CLE). Methods: We conducted a systematic review of CLE in pancreatic and biliary ducts of humans, and have provided a narrative of the technique, image classification, diagnostic performance, ongoing research, and limitations. Results: Probe-based CLE differentiates malignant from benign biliary strictures (sensitivity, ≥89%; specificity, ≥61%). Needle-based CLE differentiates mucinous from non-mucinous pancreatic cysts (sensitivity, 59%; specificity, ≥94%) and identifies dysplasia. Pancreatitis may develop in 2-7% of pancreatic cyst cases. Needle-based CLE has potential applications in adenocarcinoma, neuroendocrine tumors, and pancreatitis (chronic or autoimmune). Costs, catheter lifespan, endoscopist training, and interobserver variability are challenges for routine utilization. Conclusions: CLE reveals microscopic pancreatobiliary system anatomy with adequate specificity and sensitivity. Reducing costs and simplifying image interpretation will promote utilization by advanced endoscopists.

• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.67-72
• /
• 2023

In the past decade, Autonomous Vehicle Systems (AVS) have advanced at an exponential rate, particularly due to improvements in artificial intelligence, which have had a significant impact on social as well as road safety and the future of transportation systems. The fusion of light detection and ranging (LiDAR) and camera data in real-time is known to be a crucial process in many applications, such as in autonomous driving, industrial automation and robotics. Especially in the case of autonomous vehicles, the efficient fusion of data from these two types of sensors is important to enabling the depth of objects as well as the classification of objects at short and long distances. This paper presents classification of objects using CNN based vision and Light Detection and Ranging (LIDAR) fusion in autonomous vehicles in the environment. This method is based on convolutional neural network (CNN) and image up sampling theory. By creating a point cloud of LIDAR data up sampling and converting into pixel-level depth information, depth information is connected with Red Green Blue data and fed into a deep CNN. The proposed method can obtain informative feature representation for object classification in autonomous vehicle environment using the integrated vision and LIDAR data. This method is adopted to guarantee both object classification accuracy and minimal loss. Experimental results show the effectiveness and efficiency of presented approach for objects classification.

• Journal of The Korean Society of Integrative Medicine
• /
• v.5 no.1
• /
• pp.75-83
• /
• 2017

Purpose : The parameters used in architectural analysis are muscle thickness, fascicle length, pennation angle, etc. Pennation angle is an important muscle characteristic that plays a significant role in determining a fascicle's force contribution to movement. Ultrasonography has been widely used to obtain the image for measurement of a pennation angle since it is non-invasive and real-time. However, manual assessment in ultrasonographic images is time-consuming and subjective, making it difficult for using in muscle function analysis. Thus, in this study, I proposed an automatic method to extract the pennation angle from the ultrasonographic images of gastrocnemius muscle. Method : The ultrasonographic image obtained from 10 healthy participants's gastrocnemius muscle using for developed automatic measuring program. Automatic measuring program algorithm consists with preprocessing, line detection, line classification, and angle calculation. The resulting image was then used to detect the fascicles and aponeuroses for calculating the pennation angle with the consideration of their distribution in ultrasonographic image. Result : The proposed automatic measurement program showed the stable repeatability of pennation angle calculation. Conclusion : This study demonstrated that the proposed method was able to automatically measure the pennation angle of gastrocnemius, which made it possible to easily and reliably investigate pennation angle more.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.26 no.4
• /
• pp.404-413
• /
• 2015

The target classification for ballistic target(BT) is one of the most critical issues of ballistic defence mode(BDM) in multi-function radar(MFR). Radar responds to the target according to the result of classifying BT and air breathing target(ABT) on BDM. Since the efficiency and accuracy of the classification is closely related to the capacity of the response to the ballistic missile offense, effective and accurate classification scheme is necessary. Generally, JEM(Jet Engine Modulation), HRR(High Range Resolution) and ISAR(Inverse Synthetic Array Radar) image are used for a target classification, which require specific radar waveform, data base and algorithms. In this paper, the classification method that is applicable to a MFR system in a real environment without specific waveform is proposed. The proposed classifier adopts kinematic data as a feature vector to save radar resources at the radar time and hardware point of view and is implemented by fuzzy logic of which simple implementation makes it possible to apply to the real environment. The performance of the proposed method is verified through measured data of the aircraft and simulated data of the ballistic missile.

• Journal of Industrial Technology
• /
• v.28 no.B
• /
• pp.143-148
• /
• 2008

A real-time face detection is to find human faces robustly under the cluttered background free from the effect of occlusion by other objects or various lightening conditions. We propose a face detection system for real-time applications using wavelet decomposition method based on Gabor features. Firstly, skin candidate regions are extracted from the given image by skin color filtering and projection method. Then Gabor-feature based template matching is performed to choose face cadidate from the skin candidate regions. The chosen face candidate region is transformed into 2-level wavelet decomposition images, from which feature vectors are extracted for classification. Based on the extracted feature vectors, the face candidate region is finally classified into either face or nonface class by the Levenberg-Marguardt back-propagation neural network.

• Journal of the Korean Society of Radiology
• /
• v.10 no.8
• /
• pp.637-643
• /
• 2016

Due to the popularity of artificial intelligent, medical image processing using artificial neural network is increasingly attracting the attention of academic and industry researches. Deep learning with a convolutional neural network has been proved to very effective representation of images. However, the training process requires high performance H/W platform. Thus, the realtime learning of a large number of high dimensional samples within low-power devices is a challenging problem. In this paper, we attempt to establish this possibility by presenting a realtime neural network method on Raspberry pi using online sequential extreme learning machine. Our experiments on high-dimensional dataset show that the proposed method records an almost real-time execution.