• Journal of IKEEE
• /
• v.26 no.4
• /
• pp.647-652
• /
• 2022

In this paper, we propose a prediction system for skin pore labeling based on a CNN(Convolution Neural Network) model, where a data set is constructed by processing skin images taken by users, and a pore feature image is generated by the proposed image processing algorithm. The skin image data set was labeled for pore characteristics based on the visual classification criteria of skin beauty experts. The proposed image processing algorithm was applied to generate pore feature images from skin images and to train a CNN model that predicts pore feature ratings. The prediction results with pore features by the proposed CNN model is similar to experts visual classification results, where less learning time and higher prediction results were obtained than the results by the comparison model (Resnet-50). In this paper, we describe the proposed image processing algorithm and CNN model, the results of the prediction system and future research plans.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.06a
• /
• pp.301-301
• /
• 2022

본 연구는 운영 조건이 달라짐에 따라 회전수가 변하는 기기의 정상적 가동 여부와 고장 종류를 판별하기 위한 인공지능 알고리즘의 적용을 다루고 있다. 회전수가 변하는 장비로부터 계측된 상태 모니터링 센서의 신호는 비정상(non-stationary)적 특성이 있으므로, 상태 신호의 한계치가 고장 판별의 기준이 되기 어렵다는 점을 해결하고자 하였다. 정상 가동 여부는 이상 감지에 효율적인 오토인코더 및 기계학습 알고리즘을 적용하였으며, 고장 종류 판별에는 기계학습법과 합성곱 기반의 심층학습 방법을 적용하였다. 변하는 회전수와 연계된 주파수의 비정상적 시계열도 적절한 고장 특징 (Feature)로 대변될 수 있도록 시간 및 주파수 영역에서 특징 벡터를 구성할 수 있음을 예제로 설명하였다. 차원 축소 및 카이 제곱 기법을 적용하여 최적의 특징 벡터를 추출하여 기계학습의 분류 알고리즘이 비정상적 회전 신호를 가진 장비의 고장 예측에 활용될 수 있음을 보였다. 이 과정에서 k-NN(k-Nearest Neighbor), SVM(Support Vector Machine), Random Forest의 기계학습 알고리즘을 적용하였다. 또한 시계열 기반의 오토인코더 및 CNN (Convolution Neural Network) 적용하여 이상 감지와 고장진단을 수행한 결과를 비교하여 제시하였다.

• The Journal of Korean Society for Radiation Therapy
• /
• v.24 no.1
• /
• pp.11-14
• /
• 2012

Purpose: Anisotropic Analytical Algorithm (AAA) provides more accurate dose calculation regarding impact on scatter and tissue inhomogeneity in comparison to Pencil Beam Convolution (PBC) algorithm. This study tries to analyze the difference of dose distribution according to PBC algorithm and dose calculation algorithm of AAA on breast cancer tangential plan. Materials and Methods: Computerized medical care plan using Eclipse treatment planning system (version 8.9, VARIAN, USA) has been established for the 10 breast cancer patients using 6 MV energy of Linac (CL-6EX, VARIAN, USA). After treatment plan of Conventional Radiation Therapy plan (Conventional plan) and Field-in-Field Intensity Modulated Radiation Therapy plan (FiF plan) using PBC algorithm has been established, MU has been fixed, implemented dose calculation after changing it to AAA, and compared and analyzed treatment plan using Dose Volume Histogram (DVH). Results: Firstly, as a result of evaluating PBC algorithm of Conventional plan and the difference according to AAA, the average difference of CI value on target volume has been highly estimated by 0.295 on PBC algorithm and as a result of evaluating dose of lung, $V_{47Gy}$ and $V_{45Gy}$ has been highly evaluated by 5.83% and 4.04% each, Mean dose, $V_{20Gy}$, $V_{5Gy}$, $V_{3Gy}$ has been highly evaluated 0.6%, 0.29%, 6.35%, 10.23% each on AAA. Secondly, in case of FiF plan, the average difference of CI value on target volume has been highly evaluated on PBC algorithm by 0.165, and dose on ipsilateral lung, $V_{47Gy}$, $V_{45Gy}$, Mean dose has been highly evaluated 6.17%, 3.80%, 0.15% each on PBC algorithm, $V_{20Gy}$, $V_{5Gy}$, $V_{3Gy}$ has been highly evaluated 0.14%, 4.07%, 4.35% each on AAA. Conclusion: When calculating with AAA on breast cancer tangential plan, compared to PBC algorithm, Conformity on target volume of Conventional plan, FiF plan has been less evaluated by 0.295, 0.165 each. For the reason that dose of high dose region of ipsilateral lung has been showed little amount, and dose of low dose region has been showed much amount, features according to dose calculation algorithm need to be considered when we evaluate dose for the lungs.

• Proceedings of the KIEE Conference
• /
• 1987.11a
• /
• pp.392-397
• /
• 1987

This paper concerns a method for micro-wave imaging. The image reconstruction of a perfect conducting cylinder by phase and amplitude measurement using the X-Band multifrequency is presented troll the simulated data. The high degree of range resolution is achieved using large signal band-width and cross-range resolution is obtained by doppler processing. The comparison of image reconstruction between range doppler processing and circular convolution algorithm is also shown.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.399-410
• /
• 2021

Aiming at the problem that complex external variables in natural scenes have a greater impact on facial expression recognition results, a facial expression recognition method based on two-stream convolutional neural network is proposed. The model introduces exponentially enhanced shared input weights before each level of convolution input, and uses soft attention mechanism modules on the space-time features of the combination of static and dynamic streams. This enables the network to autonomously find areas that are more relevant to the expression category and pay more attention to these areas. Through these means, the information of irrelevant interference areas is suppressed. In order to solve the problem of poor local robustness caused by lighting and expression changes, this paper also performs lighting preprocessing with the lighting preprocessing chain algorithm to eliminate most of the lighting effects. Experimental results on AFEW6.0 and Multi-PIE datasets show that the recognition rates of this method are 95.05% and 61.40%, respectively, which are better than other comparison methods.

• Journal of the Korean Society of Radiology
• /
• v.15 no.2
• /
• pp.153-158
• /
• 2021

X-ray image analysis is a very important field to improve the early diagnosis rate and prediction accuracy of periodontal disease. Research on the development and application of artificial intelligence-based algorithms to improve the quality of such dental X-ray images is being widely conducted worldwide. Thus, the aim of this study was to design a super-resolution algorithm for predicting periodontal disease and to evaluate its applicability in dental X-ray images. The super-resolution algorithm was constructed based on the convolution layer and ReLU, and an image obtained by up-sampling a low-resolution image by 2 times was used as an input data. Also, 1,500 dental X-ray data used for deep learning training were used. Quantitative evaluation of images used root mean square error and structural similarity, which are factors that can measure similarity through comparison of two images. In addition, the recently developed no-reference based natural image quality evaluator and blind/referenceless image spatial quality evaluator were additionally analyzed. According to the results, we confirmed that the average similarity and no-reference-based evaluation values were improved by 1.86 and 2.14 times, respectively, compared to the existing bicubic-based upsampling method when the proposed method was used. In conclusion, the super-resolution algorithm for predicting periodontal disease proved useful in dental X-ray images, and it is expected to be highly applicable in various fields in the future.

• Journal of Navigation and Port Research
• /
• v.46 no.3
• /
• pp.280-288
• /
• 2022

This study examined the diagnostics of abnormalities and faults of equipment, whose rotational speed changes even during regular operation. The purpose of this study was to suggest a procedure that can properly apply machine learning to the time series data, comprising non-stationary characteristics as the rotational speed changes. Anomaly and fault diagnosis was performed using machine learning: k-Nearest Neighbor (k-NN), Support Vector Machine (SVM), and Random Forest. To compare the diagnostic accuracy, an autoencoder was used for anomaly detection and a convolution based Conv1D was additionally used for fault diagnosis. Feature vectors comprising statistical and frequency attributes were extracted, and normalization & dimensional reduction were applied to the extracted feature vectors. Changes in the diagnostic accuracy of machine learning according to feature selection, normalization, and dimensional reduction are explained. The hyperparameter optimization process and the layered structure are also described for each algorithm. Finally, results show that machine learning can accurately diagnose the failure of a variable-rotation machine under the appropriate feature treatment, although the convolution algorithms have been widely applied to the considered problem.

• Progress in Medical Physics
• /
• v.30 no.4
• /
• pp.120-127
• /
• 2019

Purpose: This study was designed to evaluate the dosimetric performance of Mobius3D by comparison with an aSi-based electronic portal imaging device (EPID) and Octavius 4D, which are conventionally used for patient-specific prescription dose verification. Methods: The study was conducted using nine patients who were treated by volumetric modulated arc therapy. To evaluate the feasibility of Mobius3D for prescription dose verification, we compared the QA results of Mobius3D to an aSi-based EPID and the Octavius 4D dose verification methods. The first was the comparison of the Mobius3D verification phantom dose, and the second was to gamma index analysis. Results: The percentage differences between the calculated point dose and measurements from a PTW31010 ion chamber were 1.6%±1.3%, 2.0%±0.8%, and 1.2%±1.2%, using collapsed cone convolution, an analytical anisotropic algorithm, and the AcurosXB algorithm respectively. The average difference was found to be 1.6%±0.3%. Additionally, in the case of using the PTW31014 ion chamber, the corresponding results were 2.0%±1.4%, 2.4%±2.1%, and 1.6%±2.5%, showing an average agreement within 2.0%±0.3%. Considering all the criteria, the Mobius3D result showed that the percentage dose difference from the EPID was within 0.46%±0.34% on average, and the percentage dose difference from Octavius 4D was within 3.14%±2.85% on average. Conclusions: We conclude that Mobius3D can be used interchangeably with phantom-based dosimetry systems, which are commonly used as patient-specific prescription dose verification tools, especially under the conditions of 3%/3 mm and 95% pass rate.

• Journal of Positioning, Navigation, and Timing
• /
• v.11 no.3
• /
• pp.163-172
• /
• 2022

Typical anti-jamming technologies based on array antennas, Space Time Adaptive Process (STAP) & Space Frequency Adaptive Process (SFAP), are very effective algorithms to perform nulling and beamforming. However, it does not perform equally well for all types of jamming signals. If the anti-jamming algorithm is not optimized for each signal type, anti-jamming performance deteriorates and the operation stability of the system become worse by unnecessary computation. Therefore, jamming classification technique is required to obtain optimal anti-jamming performance. Machine learning, which has recently been in the spotlight, can be considered to classify jamming signal. In general, performing supervised learning for classification requires a huge amount of data and new learning for unfamiliar signal. In the case of jamming signal classification, it is difficult to obtain large amount of data because outdoor jamming signal reception environment is difficult to configure and the signal type of attacker is unknown. Therefore, this paper proposes few-shot jamming signal classification technique using meta-learning and transfer-learning to train the model using a small amount of data. A training dataset is constructed by anti-jamming algorithm input data within the GNSS receiver when jamming signals are applied. For meta-learning, Model-Agnostic Meta-Learning (MAML) algorithm with a general Convolution Neural Networks (CNN) model is used, and the same CNN model is used for transfer-learning. They are trained through episodic training using training datasets on developed our Python-based simulator. The results show both algorithms can be trained with less data and immediately respond to new signal types. Also, the performances of two algorithms are compared to determine which algorithm is more suitable for classifying jamming signals.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.19 no.3
• /
• pp.213-220
• /
• 2023

Face recognition is a very important process in video monitoring and is a type of biometric technology. It is mainly used for identification and security purposes, such as ID cards, licenses, and passports. The recognition process has many variables and is complex, so development has been slow. In this paper, we proposed a face recognition method using CNN, which has been re-examined due to the recent development of computers and algorithms, and compared with the feature comparison method, which is an existing face recognition algorithm, to verify performance. The proposed face search method is divided into a face region extraction step and a learning step. For learning, face images were standardized to 50×50 pixels, and learning was conducted while minimizing unnecessary nodes. In this paper, convolution and polling-based techniques, which are one of the deep learning technologies, were used for learning, and 1,000 face images were randomly selected from among 7,000 images of Caltech, and as a result of inspection, the final recognition rate was 98%.