• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.1
• /
• pp.368-391
• /
• 2018

Face recognition (FR) with a single sample per person (SSPP) is common in real-world face recognition applications. In this scenario, it is hard to predict intra-class variations of query samples by gallery samples due to the lack of sufficient training samples. Inspired by the fact that similar faces have similar intra-class variations, we propose a virtual sample generating algorithm called k nearest neighbors based virtual sample generating (kNNVSG) to enrich intra-class variation information for training samples. Furthermore, in order to use the intra-class variation information of the virtual samples generated by kNNVSG algorithm, we propose image set based multimanifold discriminant learning (ISMMDL) algorithm. For ISMMDL algorithm, it learns a projection matrix for each manifold modeled by the local patches of the images of each class, which aims to minimize the margins of intra-manifold and maximize the margins of inter-manifold simultaneously in low-dimensional feature space. Finally, by comprehensively using kNNVSG and ISMMDL algorithms, we propose k nearest neighbor virtual image set based multimanifold discriminant learning (kNNMMDL) approach for single sample face recognition (SSFR) tasks. Experimental results on AR, Multi-PIE and LFW face datasets demonstrate that our approach has promising abilities for SSFR with expression, illumination and disguise variations.

• Communications for Statistical Applications and Methods
• /
• v.6 no.3
• /
• pp.843-848
• /
• 1999

Support vector machine(SVM) is a new and very promising classification and regression technique developed by Bapnik and his group at AT&T Bell laboratories. However it has failed to establish itself as common machine learning tool. This is partly due to the fact that SVM is not easy to implement and its standard implementation requires the optimization package for quadratic programming. In this paper we present simple iterative Kernl Adatron algorithm for nonparametric regression which is easy to implement and guaranteed to converge to the optimal solution and compare it with neural networks and projection pursuit regression.

• Transactions of the Society of Information Storage Systems
• /
• v.3 no.4
• /
• pp.167-172
• /
• 2007

The recently-developed off-line learning control approaches for the rejection of periodic disturbances utilize the specific property that the learning system tends to oscillate in steady state. Unfortunately, the prior works have not clarified how closely the learning system should approach the steady state to achieve the rejection of periodic disturbances to satisfactory level. In this paper, we address this issue extensively for the class of linear systems. We also attempt to remove the effect of other aperiodic disturbances on the rejection of the periodic disturbances effectively. In fact, the proposed learning control algorithm can provide very fast convergence performance in the presence of aperiodic disturbance. The effectiveness and practicality of our work is demonstrated through mathematical performance analysis as well as various simulation results.

• Proceedings of the KIEE Conference
• /
• 2007.04a
• /
• pp.107-109
• /
• 2007

The recently-developed off-line learning control approaches for the rejection of periodic disturbances utilize the specific property that the learning system tends to oscillate in steady state. Unfortunately, the prior works have not clarified how closely the learning system should approach the steady state to achieve the rejection of periodic disturbances to satisfactory level. In this paper, we address this issue extensively for the class of linear systems. We also attempt to remove the effect of other aperiodic disturbances on the rejection of the periodic disturbances effectively. In fact, the proposed learning control algorithm can provide very fast convergence performance in the presence of aperiodic disturbance. The effectiveness and practicality of our work is demonstrated through mathematical, performance analysis as well as various simulation results.

• Journal of KIISE:Computing Practices and Letters
• /
• v.8 no.3
• /
• pp.344-355
• /
• 2002

Having a variety of good characteristics against other pattern recognition techniques, Multilayer Perceptron (MLP) has been used in wide applications. But, it is known that Error Backpropagation (EBP) algorithm which MLP uses in learning has a defect that requires relatively long leaning time. Because learning data in pattern recognition contain abundant redundancies, in order to increase learning speed it is very effective to use online-based teaming methods, which update parameters of MLP pattern by pattern. Typical online EBP algorithm applies fixed learning rate for each update of parameters. Though a large amount of speedup with online EBP can be obtained by choosing an appropriate fixed rate, fixing the rate leads to the problem that the algorithm cannot respond effectively to different leaning phases as the phases change and the learning pattern areas vary. To solve this problem, this paper defines learning as three phases and proposes a Instant Learning by Varying Rate and Skipping (ILVRS) method to reflect only necessary patterns when learning phases change. The basic concept of ILVRS is as follows. To discriminate and use necessary patterns which change as learning proceeds, (1) ILVRS uses a variable learning rate which is an error calculated from each pattern and is suppressed within a proper range, and (2) ILVRS bypasses unnecessary patterns in loaming phases. In this paper, an experimentation is conducted for speaker verification as an application of pattern recognition, and the results are presented to verify the performance of ILVRS.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.5
• /
• pp.277-286
• /
• 2019

In this paper, we propose an efficient hyperplane generation technique to classify human activity from combination of events and sequence information obtained from multiple-event sensors. By generating hyperplane efficiently, our machine learning algorithm classify with less memory and run time than the LSVM (Linear Support Vector Machine) for embedded system. Because the fact that light weight and high speed algorithm is one of the most critical issue in the IoT, the study can be applied to smart home to predict human activity and provide related services. Our approach is based on reducing numbers of hyperplanes and utilizing robust string comparing algorithm. The proposed method results in reduction of memory consumption compared to the conventional ML (Machine Learning) algorithms; 252 times to LSVM and 34,033 times to LSTM (Long Short-Term Memory), although accuracy is decreased slightly. Thus our method showed outstanding performance on accuracy per hyperplane; 240 times to LSVM and 30,520 times to LSTM. The binarized image is then divided into groups, where each groups are converted to binary number, in order to reduce the number of comparison done in runtime process. The binary numbers are then converted to string. The test data is evaluated by converting to string and measuring similarity between hyperplanes using Levenshtein algorithm, which is a robust dynamic string comparing algorithm. This technique reduces runtime and enables the proposed algorithm to become 27% faster than LSVM, and 90% faster than LSTM.

• Journal of IKEEE
• /
• v.12 no.1
• /
• pp.65-74
• /
• 2008

One of the popular methods used for pattern classification is the MBR (Memory-Based Reasoning) algorithm. Since it simply computes distances between a test pattern and training patterns or hyperplanes stored in memory, and then assigns the class of the nearest training pattern, it is notorious for memory usage and can't learn additional information from new data. In order to overcome this problem, we propose an incremental learning algorithm (iMPA). iMPA divides the entire pattern space into fixed number partitions, and generates representatives from each partition. Also, due to the fact that it can not learn additional information from new data, we present iMPA which can learn additional information from new data and not require access to the original data, used to train. Proposed methods have been successfully shown to exhibit comparable performance to k-NN with a lot less number of patterns and better result than EACH system which implements the NGE theory using benchmark data sets from UCI Machine Learning Repository.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.12
• /
• pp.4308-4325
• /
• 2021

The importance and necessity of artificial intelligence, particularly machine learning, has recently been emphasized. In fact, artificial intelligence, such as intelligent surveillance cameras and other security systems, is used to solve various problems or provide convenience, providing solutions to problems that humans traditionally had to manually deal with one at a time. Among them, information security is one of the domains where the use of artificial intelligence is especially needed because the frequency of occurrence and processing capacity of dangerous codes exceeds the capabilities of humans. Therefore, this study intends to examine the definition of artificial intelligence and machine learning, its execution method, process, learning algorithm, and cases of utilization in various domains, particularly the cases and contents of artificial intelligence technology used in the field of information security. Based on this, this study proposes a method to apply machine learning technology to the method of classifying and detecting malware that has rapidly increased in recent years. The proposed methodology converts software programs containing malicious codes into images and creates training data suitable for machine learning by preparing data and augmenting the dataset. The model trained using the images created in this manner is expected to be effective in classifying and detecting malware.

• Journal of the Semiconductor & Display Technology
• /
• v.17 no.1
• /
• pp.71-75
• /
• 2018

Image enhancement is a necessary end essential step after taking a picture with a digital camera. Many different photo software packages attempt to automate this process with various auto enhancement techniques. This paper provides and implements a system that can learn a user's preferences and apply the preferences into the process of image enhancement. Five major components are applied to the implemented system, which are computing a distance metric, finding a training set, finding an optimal parameter set, training and finally enhancing the input image. To estimate the validity of the method, we carried out user studies, and the fact that the implemented system was preferred over the method without learning user preferences.

• Journal of The Korean Association of Information Education
• /
• v.11 no.1
• /
• pp.29-38
• /
• 2007

Computer programming in computer education draws much attention recently. Encouraged by the increased tendency of acquiring logical ability and creativity through learning, various attempts have been made to develop them through learning computer programming in the area of computer education as well. The fact that a computer program is the representation of a computer algorithm expressed in a computer language makes us realize that the devise of a logical method for a solution - i.e., the design of an algorithm - is the key to the solution of a problem. Recognizing the importance of computer algorithm would lead us to such a point that systematic investigations for directional establishment for algorithm education are necessary. We observe that researches on teaching computer algorithm have concentrated mostly on specific problems such as sorting and searching, which can be characterized as problem-dependent and individual. In this paper, the idea of conceptual algorithm is stated from the standpoint of conceptual types of problem-solving methods which are considered as problem-independent and collective. A novice approach to algorithm education based on the characteristics of types of conceptual algorithms is proposed for the purpose of developing systematic, problem-independent, algorithmic problem-solving capabilities of learners, which is widely different from the current methods of individual and problem-dependent algorithm education.