• Journal of the Institute of Electronics Engineers of Korea SC
• /
• 제49권1호
• /
• pp.88-93
• /
• 2012

Lane detection methods using camera, which are part of the driver assistance system, have been developed due to the growth of the vehicle technologies. However, lane detection methods are often failed by varying road conditions such as rainy weather and degraded lanes. This paper proposes a method for lane detection which is robust in varying road condition. Lane candidates are extracted by intensity comparison and lane detection filter. Hough transform is applied to compute the lane pair using lane candidates which is straight line in image. Then, a curved lane is calculated by using B-Snake algorithm. Also, weighting value is computed using previous lane detection result to detect the lanes even in varying road conditions such as degraded/missed lanes. Experimental results proved that the proposed method can detect the lane even in challenging road conditions because of weighting process.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• 제41권2호
• /
• pp.56-64
• /
• 2018

In recent years, imbalanced data is one of the most important and frequent issue for quality control in industrial field. As an example, defect rate has been drastically reduced thanks to highly developed technology and quality management, so that only few defective data can be obtained from production process. Therefore, quality classification should be performed under the condition that one class (defective dataset) is even smaller than the other class (good dataset). However, traditional multi-class classification methods are not appropriate to deal with such an imbalanced dataset, since they classify data from the difference between one class and the others that can hardly be found in imbalanced datasets. Thus, one-class classification that thoroughly learns patterns of target class is more suitable for imbalanced dataset since it only focuses on data in a target class. So far, several one-class classification methods such as one-class support vector machine, neural network and decision tree there have been suggested. One-class support vector machine and neural network can guarantee good classification rate, and decision tree can provide a set of rules that can be clearly interpreted. However, the classifiers obtained from the former two methods consist of complex mathematical functions and cannot be easily understood by users. In case of decision tree, the criterion for rule generation is ambiguous. Therefore, as an alternative, a new one-class classifier using hyper-rectangles was proposed, which performs precise classification compared to other methods and generates rules clearly understood by users as well. In this paper, we suggest an approach for improving the limitations of those previous one-class classification algorithms. Specifically, the suggested approach produces more improved one-class classifier using hyper-rectangles generated by using Gaussian function. The performance of the suggested algorithm is verified by a numerical experiment, which uses several datasets in UCI machine learning repository.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• 제26권3호
• /
• pp.587-601
• /
• 2016

In this paper we suggest method for scalar recoding which is both secure against SPA and DPA. Suggested method is countermeasure to power analysis attack through scalar recoding using negative expression. Suggested method ensures safety of SPA by recoding the operation to apply same pattern to each digit. Also, by generating the random recoding output according to random number, safety of DPA is ensured. We also implement precomputation table and modified scalar addition algorithm for addition to protect against SPA that targets digit's sign. Since suggested method itself can ensure safety to both SPA and DPA, it is more effective and efficient. Through suggested method, compared to previous scalar recoding that ensures safety to SPA and DPA, operation efficiency is increased by 11%.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• 제20권2호
• /
• pp.281-288
• /
• 2016

The natural moving objects are the most non-rigid shapes with randomly time-varying deformation, and its types also very diverse. Methods of non-rigid shape reconstruction have widely applied in field of movie or game industry in recent years. However, a realistic approach requires moving object to stick many beacon sets. To resolve this drawback, non-rigid shape reconstruction researches from input video without beacon sets are investigated in multimedia application fields. In this regard, our paper propose novel CPSRF(Chained Partial Stereo Rigid Factorization) algorithm that can reconstruct a non-rigid 3D shape. Our method is focused on the real-time reconstruction of non-rigid 3D shape and motion from stereo 2D video sequences per frame. And we do not constrain that the deformation of the time-varying non-rigid shape is limited by a Gaussian distribution. The experimental results show that the 3D reconstruction performance of the proposed CPSRF method is superior to that of the previous method which does not consider the random deformation of shape.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• 제60권1호
• /
• pp.184-192
• /
• 2011

In this study, we introduce a identification methodology for FCM-based fuzzy model. The two underlying design mechanisms of such networks involve Fuzzy C-Means (FCM) clustering method and Particle Swarm Optimization(PSO). The proposed algorithm is based on FCM clustering method for efficient processing of data and the optimization of model was carried out using PSO. The premise part of fuzzy rules does not construct as any fixed membership functions such as triangular, gaussian, ellipsoidal because we build up the premise part of fuzzy rules using FCM. As a result, the proposed model can lead to the compact architecture of network. In this study, as the consequence part of fuzzy rules, we are able to use four types of polynomials such as simplified, linear, quadratic, modified quadratic. In addition, a Weighted Least Square Estimation to estimate the coefficients of polynomials, which are the consequent parts of fuzzy model, can decouple each fuzzy rule from the other fuzzy rules. Therefore, a local learning capability and an interpretability of the proposed fuzzy model are improved. Also, the parameters of the proposed fuzzy model such as a fuzzification coefficient of FCM clustering, the number of clusters of FCM clustering, and the polynomial type of the consequent part of fuzzy rules are adjusted using PSO. The proposed model is illustrated with the use of Automobile Miles per Gallon(MPG) and Boston housing called Machine Learning dataset. A comparative analysis reveals that the proposed FCM-based fuzzy model exhibits higher accuracy and superb predictive capability in comparison to some previous models available in the literature.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• 제58권2호
• /
• pp.399-406
• /
• 2009

In this study, Polynomial Radial Basis Function Neural Network(pRBFNN) based on Fuzzy Inference System is designed and its parameters such as learning rate, momentum coefficient, and distributed weight (width of RBF) are optimized by means of Particle Swarm Optimization. The proposed model can be expressed as three functional module that consists of condition part, conclusion part, and inference part in the viewpoint of fuzzy rule formed in 'If-then'. In the condition part of pRBFNN as a fuzzy rule, input space is partitioned by defining kernel functions (RBFs). Here, the structure of kernel functions, namely, RBF is generated from HCM clustering algorithm. We use Gaussian type and Inverse multiquadratic type as a RBF. Besides these types of RBF, Conic RBF is also proposed and used as a kernel function. Also, in order to reflect the characteristic of dataset when partitioning input space, we consider the width of RBF defined by standard deviation of dataset. In the conclusion part, the connection weights of pRBFNN are represented as a polynomial which is the extended structure of the general RBF neural network with constant as a connection weights. Finally, the output of model is decided by the fuzzy inference of the inference part of pRBFNN. In order to evaluate the proposed model, nonlinear function with 2 inputs, waster water dataset and gas furnace time series dataset are used and the results of pRBFNN are compared with some previous models. Approximation as well as generalization abilities are discussed with these results.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 한국정보통신학회 2016년도 춘계학술대회
• /
• pp.661-663
• /
• 2016

Corruption occurs in the process of processing image signal and the corruption changes the pixel value within the image to damage the original information. AWGN(additive white Gaussian noise) is a representative example. For filters to remove AWGN, there are filters such as MF(mean filter), WF(wiener filter), and AWMF(adaptive weighted mean filter). However images processed through standard previous filters lock preservation characteristics in edge areas. Therefore, threshold value is applied for processing on the standard deviation of the local mask in this study and if the standard deviation is smaller than the threshold value, it is not filtered and if the value is bigger than the threshold value, the study suggested an algorithm that processes using weighted value utilizing standard deviation.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 한국정보통신학회 2018년도 추계학술대회
• /
• pp.620-622
• /
• 2018

The need for particulate matter prediction algorithms has increased as social interest in the effects of human on particulate matter increased. Many studies have proposed statistical modelling and machine learning techniques based prediction models using weather data, but it is difficult to accurately set the environment and detailed conditions of the models. In addition, there is a need to design a new prediction model for missing data in domestic weather monitoring station. In this paper, fine dust prediction is performed using multi-layer perceptron network as a previous study for particulate matter prediction. For this purpose, a prediction model is designed based on weather data of three monitoring station and the suitability of the algorithm for particulate matter prediction is evaluated through comparison with actual data.

• The KIPS Transactions:PartC
• /
• 제10C권7호
• /
• pp.857-866
• /
• 2003

For detecting an intrusion based on the anomaly of a user's activities, previous works are concentrated on statistical techniques in order to analyze an audit data set. However. since they mainly analyze the average behavior of a user's activities, some anomalies can be detected inaccurately. In this paper, a new clustering algorithm for modeling the normal pattern of a user's activities is proposed. Since clustering can identify an arbitrary number of dense ranges in an analysis domain, it can eliminate the inaccuracy caused by statistical analysis. Also, clustering can be used to model common knowledge occurring frequently in a set of transactions. Consequently, the common activities of a user can be found more accurately. The common knowledge is represented by the occurrence frequency of similar data objects by the unit of a transaction as veil as the common repetitive ratio of similar data objects in each transaction. Furthermore, the proposed method also addresses how to maintain identified common knowledge as a concise profile. As a result, the profile can be used to detect any anomalous behavior In an online transaction.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• 제29권4C호
• /
• pp.494-504
• /
• 2004

The researches about gaze detection have been much developed with many applications. Most previous researches only rely on image processing algorithm, so they take much processing time and have many constraints. In our work, we implement it with a computer vision system setting a IR-LED based single camera. To detect the gaze position, we locate facial features, which is effectively performed with IR-LED based camera and SVM(Support Vector Machine). When a user gazes at a position of monitor, we can compute the 3D positions of those features based on 3D rotation and translation estimation and affine transform. Finally, the gaze position by the facial movements is computed from the normal vector of the plane determined by those computed 3D positions of features. In addition, we use a trained neural network to detect the gaze position by eye's movement. As experimental results, we can obtain the facial and eye gaze position on a monitor and the gaze position accuracy between the computed positions and the real ones is about 4.2 cm of RMS error.