• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 한국퍼지및지능시스템학회 1998년도 추계학술대회 학술발표 논문집
• /
• pp.173-179
• /
• 1998

This paper proposes a new call admission control scheme utilizing an inverse fuzzy vector quantizer(IFVQ) and neural net, which combines benefits of IFVQ and flexibilities of FCM(Fuzzy-C-Menas) arithmatics, to decide whether a requested call that is not trained in learning phase to be connected or not. The system generates the estimated traffic pattern of the cell stream of a new call, using feasible/infeasible patterns in codebook, fuzzy membership values that represent the degree to which each pattern of codebook matches input pattern, and FCM arithmatics. The input to the NN is the vector consisted of traffic parameters which is the means and variances of the number of cells arriving inthe interval. After training(using error back propagation algorithm), when the NN is used for decision making, the decision as to whether to accept or reject a new call depends on whether the output is greater or less then decision threshold(+0.5). This method is a new technique for call admi sion control using the membership values as traffic parameter which declared to CAC at the call set up stage, and is valid for a very general traffic model in which the calls of a stream can belong to an unlimited number of traffic classes. Through the simmulation. it is founded the performance of the suggested method outforms compared to the conventional NN method.

• Proceedings of the KIEE Conference
• /
• 대한전기학회 2009년도 춘계학술대회 논문집 에너지변화시스템부문
• /
• pp.225-227
• /
• 2009

The conventional fixed gain PI controller is very sensitive to step change of command speed, parameter variation and load disturbances. The precise speed control of interior permanent magnet synchronous motor(IPMSM) drive becomes a complex issue due to nonlinear coupling among its winding currents and the rotor speed as well as the nonlinear electromagnetic developed torque. Therefore, there exists a need to tune the PI controller parameters on-line to ensure optimum drive performance over a wide range of operating conditions. This paper is proposed artificial intelligent-PI(AIPI) controller of IPMSM drive using adaptive learning mechanism(ALM) and fuzzy neural network(FNN). The proposed controller is developed to ensure accurate speed control of IPMSM drive under system disturbances and estimation of speed using artificial neural network(ANN) controller. The PI controller parameters are optimized by ALM-FNN at all possible operating condition in a closed loop vector control scheme. The validity of the proposed controller is verified by results at different dynamic operating conditions.

• Proceedings of the Korean Institute of IIIuminating and Electrical Installation Engineers Conference
• /
• 한국조명전기설비학회 2009년도 춘계학술대회 논문집
• /
• pp.420-423
• /
• 2009

The conventional fixed gain PI controller is very sensitive to step change of command speed, parameter variation and load disturbances. The precise speed control of interior permanent magnet synchronous motor(IPMSM) drive becomes a complex issue due to nonlinear coupling among its winding currents and the rotor speed as well as the nonlinear electromagnetic developed torque. Therefore, there exists a need to tune the PI controller parameters on-line to ensure optimum drive performance over a wide range of operating conditions. This paper is proposed hybrid intelligent-PI(HIPI) controller of IPMSM drive using adaptive learning mechanism(ALM) and fuzzy neural network(FNN). The proposed controller is developed to ensure accurate speed control of IPMSM drive under system disturbances and estimation of speed using artificial neural network(ANN) controller. The PI controller parameters are optimized by ALM-FNN at all possible operating condition in a closed loop vector control scheme. The validity of the proposed controller is verified by results at different dynamic operating conditions.

• International Journal of Computer Science & Network Security
• /
• 제21권5호
• /
• pp.256-266
• /
• 2021

The Convolutional Neural Network (CNN) has recently made potential improvements in face verification applications. In fact, different models based on the CNN have attained commendable progress in the classification rate using a massive amount of data in an uncontrolled environment. However, the enormous computation costs and the considerable use of storage causes a noticeable problem during training. To address these challenges, we focus on relevant data trained within the CNN model by integrating a lifting method for a better tradeoff between the data size and the computational efficiency. Our approach is characterized by the advantage that it does not need any additional space to store the features. Indeed, it makes the model much faster during the training and classification steps. The experimental results on Labeled Faces in the Wild and YouTube Faces datasets confirm that the proposed CNN framework improves performance in terms of precision. Obviously, our model deliberately designs to achieve significant speedup and reduce computational complexity in deep CNNs without any accuracy loss. Compared to the existing architectures, the proposed model achieves competitive results in face recognition tasks

• IEMEK Journal of Embedded Systems and Applications
• /
• 제17권6호
• /
• pp.309-317
• /
• 2022

In this paper, we propose a machine learning-based copy-move forgery detection network with dual branches. Because the rotation or scaling operation is frequently involved in copy-move forger, the conventional convolutional neural network is not effectively applied in detecting copy-move tampering. Therefore, we divide the input into rotation-invariant and scaling-invariant features based on the wavelet coefficients. Each of the features is input to different branches having the same structure, and is fused in the combination module. Each branch comprises feature extraction, correlation, and mask decoder modules. In the proposed network, VGG16 is used for the feature extraction module. To check similarity of features generated by the feature extraction module, the conventional correlation module used. Finally, the mask decoder model is applied to develop a pixel-level localization map. We perform experiments on test dataset and compare the proposed method with state-of-the-art tampering localization methods. The results demonstrate that the proposed scheme outperforms the existing approaches.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.221-235
• /
• 2022

Manual inspection of steel box girders on long span bridges is time-consuming and labor-intensive. The quality of inspection relies on the subjective judgements of the inspectors. This study proposes an automated approach to detect and segment cracks in high-resolution images. An end-to-end cascaded framework is proposed to first detect the existence of cracks using a deep convolutional neural network (CNN) and then segment the crack using a modified U-Net encoder-decoder architecture. A Naïve Bayes data fusion scheme is proposed to reduce the false positives and false negatives effectively. To generate the binary crack mask, first, the original images are divided into 448 × 448 overlapping image patches where these image patches are classified as cracks versus non-cracks using a deep CNN. Next, a modified U-Net is trained from scratch using only the crack patches for segmentation. A customized loss function that consists of binary cross entropy loss and the Dice loss is introduced to enhance the segmentation performance. Additionally, a Naïve Bayes fusion strategy is employed to integrate the crack score maps from different overlapping crack patches and to decide whether a pixel is crack or not. Comprehensive experiments have demonstrated that the proposed approach achieves an 81.71% mean intersection over union (mIoU) score across 5 different training/test splits, which is 7.29% higher than the baseline reference implemented with the original U-Net.

• Proceedings of the Korea Information Processing Society Conference
• /
• 한국정보처리학회 2022년도 춘계학술발표대회
• /
• pp.161-164
• /
• 2022

Homomorphic Encryption (HE) schemes have been recently growing as a reliable solution to preserve users' information owe to maintaining and operating the user data in the encrypted state. In addition to that, several Neural Networks models merged with HE schemes have been developed as a prospective tool for privacy-preserving machine learning. Those mentioned works demonstrated that it is possible to match the accuracy of non-encrypted models but there is always a trade-off in the computation time. In this work, we evaluate the implementation of CKKS HE scheme operations over the layers of a LeNet5 convolutional inference model, however, owing to the limitations of the evaluation environment, the scope of this work is not to develop a complete LeNet5 encrypted model. The evaluation was performed using the MNIST dataset with Microsoft SEAL (MSEAL) open-source homomorphic encryption library ported version on Python (PyFhel). The behavior of the encrypted model, the limitations faced and a small description of related and future work is also provided.

• Journal of Internet Computing and Services
• /
• 제20권4호
• /
• pp.91-102
• /
• 2019

In autonomous driving systems, the ability to classify pedestrians in images captured by cameras is very important for pedestrian safety. In the past, after extracting features of pedestrians with HOG(Histogram of Oriented Gradients) or SIFT(Scale-Invariant Feature Transform), people classified them using SVM(Support Vector Machine). However, extracting pedestrian characteristics in such a handcrafted manner has many limitations. Therefore, this paper proposes a method to classify pedestrians reliably and effectively using CNN's(Convolutional Neural Network) deep features and transfer learning. We have experimented with both the fixed feature extractor and the fine-tuning methods, which are two representative transfer learning techniques. Particularly, in the fine-tuning method, we have added a new scheme, called M-Fine(Modified Fine-tuning), which divideslayers into transferred parts and non-transferred parts in three different sizes, and adjusts weights only for layers belonging to non-transferred parts. Experiments on INRIA Person data set with five CNN models(VGGNet, DenseNet, Inception V3, Xception, and MobileNet) showed that CNN's deep features perform better than handcrafted features such as HOG and SIFT, and that the accuracy of Xception (threshold = 0.5) isthe highest at 99.61%. MobileNet, which achieved similar performance to Xception and learned 80% fewer parameters, was the best in terms of efficiency. Among the three transfer learning schemes tested above, the performance of the fine-tuning method was the best. The performance of the M-Fine method was comparable to or slightly lower than that of the fine-tuningmethod, but higher than that of the fixed feature extractor method.

• Journal of the Korean Institute of Telematics and Electronics C
• /
• 제36C권4호
• /
• pp.87-94
• /
• 1999

This paper presents a study on the off-line handwritten Hangul (Korean) character recognition using the partially connected neural network (PCNN), which is based on partial connections between the input receptive fields and the hidden nodes. The hidden nodes of three PCNNs have ten receptive fields and different input feature sets. And we introduce modular partially connected neural network (MPCNN), The MPCNN combines three PCNNs with a merging network. The learning scheme of the proposed networks is composed of two steps: PCNN learning step and the merging step of combining three PCNN s. In the merging step, another merging PCNN network is introduced and trained by regarding the hidden output of each PCNN as a new input feature vector. The performance of the proposed classifier is verified on the recognition of 18 off-line handwritten Hangul characters widely used in business cards in Korea.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• 제11권4호
• /
• pp.91-97
• /
• 2011

In this paper we present an approach to the structure identification based on genetic algorithm and to the parameter identification by hybrid learning method in neuro-fuzzy-genetic hybrid system in order to predicate the Mackey-Glass Chaotic time series. In this scheme the basic idea consists of two steps. One is the construction of a fuzzy rule base for the partitioned input space via genetic algorithm, the other is the corresponding parameters of the fuzzy control rules adapted by the backpropagation algorithm. In an attempt to test the performance the proposed system, three patterns, x(t-3), x(t-6) and x(t-9), was prepared according to time interval. It was through lots of simulation proved that the initial small error of learning owed to the good structural identification via genetic algorithm. The performance was showed in Table 2.