• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권11호
• /
• pp.3145-3162
• /
• 2023

As an important technology of the internetwork, wireless sensor network technique plays an important role in indoor localization. Non-line-of-sight (NLOS) problem has a large effect on indoor location accuracy. A location algorithm based on improved particle filter and directional probabilistic data association (IPF-DPDA) for WSN is proposed to solve NLOS issue in this paper. Firstly, the improved particle filter is proposed to reduce error of measuring distance. Then the hypothesis test is used to detect whether measurements are in LOS situations or NLOS situations for N different groups. When there are measurements in the validation gate, the corresponding association probabilities are applied to weight retained position estimate to gain final location estimation. We have improved the traditional data association and added directional information on the original basis. If the validation gate has no measured value, we make use of the Kalman prediction value to renew. Finally, simulation and experimental results show that compared with existing methods, the IPF-DPDA performance better.

• 대한의용생체공학회:의공학회지
• /
• 제40권2호
• /
• pp.48-54
• /
• 2019

This paper proposed a method of validation data augmentation for improving the grading accuracy of diabetic macular edema (DME) using deep learning. The data augmentation technique is basically applied in order to secure diversity of data by transforming one image to several images through random translation, rotation, scaling and reflection in preparation of input data of the deep neural network (DNN). In this paper, we apply this technique in the validation process of the trained DNN, and improve the grading accuracy by combining the classification results of the augmented images. To verify the effectiveness, 1,200 retinal images of Messidor dataset was divided into training and validation data at the ratio 7:3. By applying random augmentation to 359 validation data, $1.61{\pm}0.55%$ accuracy improvement was achieved in the case of six times augmentation (N=6). This simple method has shown that the accuracy can be improved in the N range from 2 to 6 with the correlation coefficient of 0.5667. Therefore, it is expected to help improve the diagnostic accuracy of DME with the grading information provided by the proposed DNN.

• Nuclear Engineering and Technology
• /
• 제54권4호
• /
• pp.1230-1244
• /
• 2022

This paper proposes an algorithm for signal validation using unsupervised methods in emergency situations at nuclear power plants (NPPs) when signals are rapidly changing. The algorithm aims to determine the stuck failures of signals in real time based on a variational auto-encoder (VAE), which employs unsupervised learning, and long short-term memory (LSTM). The application of unsupervised learning enables the algorithm to detect a wide range of stuck failures, even those that are not trained. First, this paper discusses the potential failure modes of signals in NPPs and reviews previous studies conducted on signal validation. Then, an algorithm for detecting signal failures is proposed by applying LSTM and VAE. To overcome the typical problems of unsupervised learning processes, such as trainability and performance issues, several optimizations are carried out to select the inputs, determine the hyper-parameters of the network, and establish the thresholds to identify signal failures. Finally, the proposed algorithm is validated and demonstrated using a compact nuclear simulator.

• Geomechanics and Engineering
• /
• 제16권1호
• /
• pp.21-34
• /
• 2018

Discontinuities considerably affect the mechanical and hydraulic properties of rock mass. These properties of the rock mass are influenced by the geometry of the discontinuities to a great extent. This paper aims to render an account of the geometrical parameters of several discontinuity sets related to the surrounding rock mass of Rudbar Lorestan Pumped Storage Power Plant powerhouse cavern making use of the linear and areal (circular and rectangular) sampling methods. Taking into consideration quite a large quantity of scanline and the window samplings used in this research, it was realized that the areal sampling methods are more time consuming and cost-effective than the linear methods. Having corrected the biases of the geometrical properties of the discontinuities, density (areal and volumetric) as well as the linear, areal and volumetric intensity accompanied by the other properties related to four sets of discontinuities were computed. There is an acceptable difference among the mean trace lengths measured using two linear and areal methods for the two joint sets. A 3D discrete fracture network generation code (3DFAM) has been developed to model the fracture network based on the mapped data. The code has been validated on the basis of numerous geometrical characteristics computed by use of the linear, areal sampling methods and volumetric method. Results of the linear sampling method have significant variations. So, the areal and volumetric methods are more efficient than the linear method and they are more appropriate for validation of 3D DFN (Discrete Fracture Network) codes.

• 한국산학기술학회논문지
• /
• 제19권4호
• /
• pp.161-166
• /
• 2018

본 논문에서는 컨볼루션 신경망 구조(Convolution Neural Network)에서 정규화 및 교차검증 횟수 감소를 위한 무작위로 풀링 연산을 선택하는 방법에 대해 설명한다. 컨볼루션 신경망 구조에서 풀링 연산은 피쳐맵(Feature Map) 크기 감소 및 이동 불변(Shift Invariant)을 위해 사용된다. 기존의 풀링 방법은 각 풀링 계층에서 하나의 풀링 연산이 적용된다. 이러한 방법은 학습 간 신경망 구조의 변화가 없기 때문에, 학습 자료에 과도하게 맞추는 과 적합(Overfitting) 문제를 가지고 있다. 또한 최적의 풀링 연산 조합을 찾기 위해서는, 각 풀링 연산 조합에 대해 교차검증을 하여 최고의 성능을 내는 조합을 찾아야 한다. 이러한 문제를 해결하기 위해, 풀링 계층에 확률적인 개념을 도입한 무작위 풀링 연산 선택 방법을 제안한다. 제안한 방법은 풀링 계층에 하나의 풀링 연산을 적용하지 않는다. 학습기간 동안 각 풀링 영역에서 여러 풀링 연산 중 하나를 무작위로 선택한다. 그리고 시험 시에는 각 풀링 영역에서 사용된 풀링 연산의 평균을 적용한다. 이러한 방법은 풀링 영역에서 서로 다른 풀링 조합을 사용한 구조의 평균을 한 것으로 볼 수 있다. 따라서, 컨볼루션 신경망 구조가 학습데이터에 과도하게 맞추어지는 과적합 문제를 피할 수 있으며, 또한 각 풀링 계층에서 특정 풀링 연산을 선택할 필요가 없기 때문에 교차 검증 횟수를 감소시킬 수 있다. 실험을 통해, 제안한 방법은 정규화 성능을 향상시킬 뿐만 아니라 및 교차 검증 횟수를 줄일 수 있다는 것을 검증하였다.

• KEPCO Journal on Electric Power and Energy
• /
• 제3권2호
• /
• pp.89-97
• /
• 2017

The substation is a critical node in the power network where power is transformed in the power generation, transmission and distribution system. The IEC 61850 is a global standard which proposes efficient substation automation by defining interoperable communication and data modelling techniques. In order to achieve this level of interoperability and automation, the IEC 61850 (Part 6) defines System Configuration description Language (SCL). The SCL is an XML based file format for defining the abstract model of primary and secondary substation equipment, communications systems and also the relationship between them. It enables the interoperable exchange of data during substation engineering by standardizing the description of applications at different stages of the engineering process. To achieve the seamless interoperability, multi-vendor devices are required to adhere completely to the IEC 61850. This paper proposes an efficient algorithm required for verifying the interoperability of multi-vendor devices by checking the adherence of the SCL file to specifications of the standard. Our proposed SCL validation algorithm consists of schema validation and other functionalities including information model validation using UML data model, the Vendor Defined Extension model validation, the User Defined Rule validation and the IED Engineering Table (IET) consistency validation. It also integrates the standard UCAIUG (Utility Communication Architecture International Users Group) Procedure validation for quality assurance testing. Our proposed algorithm is not only flexible and efficient in terms of ensuring interoperable functionality of tested devices, it is also convenient for use by system integrators and test engineers.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제30권7_8호
• /
• pp.744-751
• /
• 2003

본 논문에서는 최근 뛰어난 예측력으로 각광받는 최소제곱 Support Vector Machine(Least Square Support Vector Machine: LS-SVM)과 First Principle(FP)을 결합한 하이브리드 최소제곱ㆍSupport Vector Machine 모델, HLS-SVM(Hybrid Least Square-Super Vector Machine)을 제안한다. 제안한 모델인 하이브리드 최소제곱 Support Vector Machine을 기존의 방법인 하이브리드 신경망(Hybrid Neural Network:HNN), 비선형 칼만필터와 하이브리드 신경망을 결합한 HNN-EKF (Hybrid Neural Network with Extended Kalman Filter) 모델과 비교해 보았다. HLS-SVM 모델은 학습 및 validation 과정에서는 HNN-EKF와 근사한 성능을 보였고, HNN 보다는 우수한 결과를 보였고, 일반화 성능에서는 HNN-EKF에 비해 3배, HNN보다 100배정도 우수한 결과를 보였다.

• International Journal of Computer Science & Network Security
• /
• 제21권4호
• /
• pp.65-74
• /
• 2021

The rapid change in gold price is an issue of concern in the global economy and financial markets. Gold has been used as a means for trading and transaction around the world for long period of time and it plays an integral role in monetary, business, commercial and financial activities. More importantly, it is used as economic measure for the global economy and will continue to play an important economic vital role - both locally and globally. There has been an explosive growth in demand for efficient and effective scheme to predict gold price due its volatility and fluctuation. Hence, there is need for the development of gold price prediction scheme to assist and support investors, marketers, and financial institutions in making effective economic and monetary decisions. This paper primarily proposed an intelligent based system for predicting and characterizing the gold market trend. The simulation result shows that the proposed intelligent gold price scheme has been able to predict the gold price with high accuracy and precision, and ultimately it has significantly reduced the prediction error when compared to baseline neural network (NN).

• Journal of Multimedia Information System
• /
• 제9권1호
• /
• pp.21-32
• /
• 2022

Early-stage diagnosis of Alzheimer's Disease (AD) from Cognitively Normal (CN) patients is crucial because treatment at an early stage of AD can prevent further progress in the AD's severity in the future. Recently, computer-aided diagnosis using magnetic resonance image (MRI) has shown better performance in the classification of AD. However, these methods use a traditional machine learning algorithm that requires supervision and uses a combination of many complicated processes. In recent research, the performance of deep neural networks has outperformed the traditional machine learning algorithms. The ability to learn from the data and extract features on its own makes the neural networks less prone to errors. In this paper, a dense neural network is designed for binary classification of Alzheimer's disease. To create a classifier with better results, we studied result of different activation functions in the prediction. We obtained results from 5-folds validations with combinations of different activation functions and compared with each other, and the one with the best validation score is used to classify the test data. In this experiment, features used to train the model are obtained from the ADNI database after processing them using FreeSurfer software. For 5-folds validation, two groups: AD and CN are classified. The proposed DNN obtained better accuracy than the traditional machine learning algorithms and the compared previous studies for AD vs. CN, AD vs. Mild Cognitive Impairment (MCI), and MCI vs. CN classifications, respectively. This neural network is robust and better.

• International Journal of Computer Science & Network Security
• /
• 제21권7호
• /
• pp.284-296
• /
• 2021

Quality Models are important element of the software industry to develop and implement the best quality product in the market. This type of model provides aid in describing quality measures, which directly enhance the user satisfaction and software quality. In software development, the inheritance technique is an important mechanism used in object-oriented programming that allows the developers to define new classes having all the properties of super class. This technique supports the hierarchy design for classes and makes an "is-a" association among the super and subclasses. This paper describes a standard procedure for validating the inheritance metric in Quality Model for Object-Oriented Design (QMOOD) by using a set of nine properties established by Weyuker. These properties commonly using for investigating the effectiveness of the metric. The integration of two measuring methods (i.e. QMOOD and Weyuker) will provide new way for evaluating the software quality based on the inheritance context. The output of this research shows the extent of satisfaction of the inheritance metric in QMOOD against Weyuker nine properties. Further results proved that Weyker's property number nine could not fulfilled by any inheritance metrics. This research introduces a way for measuring software that developed using object-oriented approach. The theoretical validation of the inheritance metric presented in this paper is a small step taken towards producing quality software and in providing assistance to the software industry.