• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.45 no.1
• /
• pp.1-10
• /
• 2008

In this paper, we designed a facial feature(eyes, a moult and a nose) detection hardware based on the ICT transform which was developed for face detection earlier. Our design used a pipeline architecture for high throughput and it also tried to reduce memory size and memory access rate. The algerian and its hardware implementation were tested on the BioID database, which is a worldwide face detection test bed, and its facial feature detection rate was 100% both in software and hardware, assuming the face boundary was correctly detected. After synthesizing the hardware on Dongbu $0.18{\mu}m$ CMOS library, its die size was $376,821{\mu}m^2$ with the maximum operating clock 78MHz.

• Journal of the Korean Data and Information Science Society
• /
• v.19 no.4
• /
• pp.1297-1304
• /
• 2008

This paper proposes a machine learning approach for language-independent sentence boundary detection. The proposed method requires no heuristic rules and language-specific features, such as part-of-speech information, a list of abbreviations or proper names. With only the language-independent features, we perform experiments on not only an inflectional language but also an agglutinative language, having fairly different characteristics (in this paper, English and Korean, respectively). In addition, we obtain good performances in both languages. We have also experimented with the methods under a wide range of experimental conditions, especially for the selection of useful features.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2021.05a
• /
• pp.358-361
• /
• 2021

In order to improve the accuracy of small target detection more effectively, this paper proposes an improved single shot detector (SSD) target detection and recognition method based on cspdarknet53, which introduces lightweight ECA attention mechanism and Feature Pyramid Network (FPN). First, the original SSD backbone network is replaced with cspdarknet53 to enhance the learning ability of the network. Then, a lightweight ECA attention mechanism is added to the basic convolution block to optimize the network. Finally, FPN is used to gradually fuse the multi-scale feature maps used for detection in the SSD from the deep to the shallow layers of the network to improve the positioning accuracy and classification accuracy of the network. Experiments show that the proposed target detection algorithm has better detection accuracy, and it improves the detection accuracy especially for small targets.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.10
• /
• pp.5023-5038
• /
• 2017

Big data is an emerging technology which deals with wide range of data sets with sizes beyond the ability to work with software tools which is commonly used for processing of data. When we consider a huge network, we have to process a large amount of network information generated, which consists of both normal and abnormal activity logs in large volume of multi-dimensional data. Intrusion Detection System (IDS) is required to monitor the network and to detect the malicious nodes and activities in the network. Massive amount of data makes it difficult to detect threats and attacks. Sequential Pattern mining may be used to identify the patterns of malicious activities which have been an emerging popular trend due to the consideration of quantities, profits and time orders of item. Here we propose a sequential pattern mining algorithm with fuzzy logic feature selection and fuzzy weighted support for huge volumes of network logs to be implemented in Apache Hadoop YARN, which solves the problem of speed and time constraints. Fuzzy logic feature selection selects important features from the feature set. Fuzzy weighted supports provide weights to the inputs and avoid multiple scans. In our simulation we use the attack log from NS-2 MANET environment and compare the proposed algorithm with the state-of-the-art sequential Pattern Mining algorithm, SPADE and Support Vector Machine with Hadoop environment.

• The Korean Journal of Applied Statistics
• /
• v.21 no.6
• /
• pp.959-967
• /
• 2008

The purpose of this paper is to suggest a discrete feature vector, robust in various levels of noisy environment and inexpensive in computation, for detection of speech segments and is to show such properties of the feature with real speech data. The suggested feature is one dimensional vector which represents slope of short term energies and is discretized into three values to reduce computational burden of computations in HMM. In experiments with speech data, the method with the suggested feature vector showed good performance even in noisy environments.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.11
• /
• pp.181-186
• /
• 2014

The paper proposes a new method of segmentation-based feature extraction to improve performance in pedestrian upper-body detection. General pedestrian detectors that use local features are often plagued by false positives due to the locality. Color information of multi parts of the upper body is utilized in figure-ground segmentation scheme to extract an salient, "global" shape feature capable of reducing the false positives. The performance of the multi-part color segmentation-based feature is evaluated by changing color spaces and the parameters of color histogram. The experimental result from an upper-body dataset shows that the proposed feature is effective in reducing the false positives of local feature-based detectors.

• Journal of the Korea Society for Simulation
• /
• v.21 no.2
• /
• pp.79-90
• /
• 2012

In this paper, a feature signal extraction method is proposed in order to enhance the low performance of fault detection caused by unbalanced data which denotes the situations when severe disparity exists between the numbers of class instances. Most of the cyclic signals gathered during the process are recognized as normal, while only a few signals are regarded as fault; the majorities of cyclic signals data are unbalanced data. SOM(Self-Organizing Map)-based feature signal extraction method is considered to fix the adverse effects caused by unbalanced data. The weight neurons, mapped to the every node of SOM grid, are extracted as the feature signals of both class data which are used as a reference data set for fault detection. kNN(k-Nearest Neighbor) and SVM(Support Vector Machine) are considered to make fault detection models with comparisons to Hotelling's $T^2$ Control Chart, the most widely used method for fault detection. Experiments are conducted by using simulated process signals which resembles the frequent cyclic signals in semiconductor manufacturing.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.12 no.3
• /
• pp.186-191
• /
• 2019

In this paper, we propose a implementation approach of the high-speed feature extraction algorithm. The proposed method is based on the block type classification algorithm which reduces the computation time when target macro block is divided to smooth block type that has no image features. It is quantitatively identified that occurs at 29.5% of the total image using 200 standard test images with $64{\times}64$ macro block size. This means that within a standard test image containing various image information, 29.5% can reduce the complexity of the operation. When the proposed approach is applied to the Canny edge detection, the required latency of the edge detection can be completely eliminated, such as 2D derivative filter, gradient magnitude/direction computation, non-maximal suppression, adaptive threshold calculation, hysteresis thresholding. Also, it is expected that operation time of the feature detection can be reduced by applying block type classification algorithm to various feature extraction algorithms in this way.

• Journal of Korea Multimedia Society
• /
• v.9 no.8
• /
• pp.1030-1036
• /
• 2006

The rapid proliferation of wireless networks and mobile computing applications has changed the landscape of network security. Anomaly detection is a pattern recognition task whose goal is to report the occurrence of abnormal or unknown behavior in a given system being monitored. This paper presents an efficient rough set based anomaly detection method that can effectively identify a group of especially harmful internal masqueraders in cellular mobile networks. Our scheme uses the trace data of wireless application layer by a user as feature value. Based on the feature values, the use pattern of a mobile's user can be captured by rough sets, and the abnormal behavior of the mobile can be also detected effectively by applying a roughness membership function considering weighted feature values. The performance of our scheme is evaluated by a simulation. Simulation results demonstrate that the anomalies are well detected by the method that assigns different weighted values to feature attributes depending on importance.

• Journal of the Korea Society of Computer and Information
• /
• v.19 no.11
• /
• pp.43-52
• /
• 2014

In this paper, we propose the target detection method using image displacement, and classification method using SURF(Speeded Up Robust Features) feature points and BAS(Beam Angle Statistics) in infrared images. The SURF method that is a typical correspondence matching method in the area of image processing has been widely used, because it is significantly faster than the SIFT(Scale Invariant Feature Transform) method, and produces a similar performance. In addition, in most SURF based object recognition method, it consists of feature point extraction and matching process. In proposed method, it detects the target area using the displacement, and target classification is performed by using the geometry of SURF feature points. The proposed method was applied to the unmanned target detection/recognition system. The experimental results in virtual images and real images, we have approximately 73~85% of the classification performance.