• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2007.11a
• /
• pp.15-18
• /
• 2007

Identification of humans from multiple view points is an important task for surveillance and security purposes. For optimal performance the system should use the maximum information available from sensors. Multimodal biometric systems are capable of utilizing more than one physiological or behavioral characteristic for enrollment, verification, or identification. Since gait alone is not yet established as a very distinctive feature, this paper presents an approach to fuse face and gait for identification. In this paper we will use the single camera case i.e. both the face and gait recognition is done using the same set of images captured by a single camera. The aim of this paper is to improve the performance of the system by utilizing the maximum amount of information available in the images. Fusion is considered at decision level. The proposed algorithm is tested on the NLPR database.

• Journal of the Korean Society for Precision Engineering
• /
• v.28 no.9
• /
• pp.1040-1047
• /
• 2011

This paper proposes a novel method based on error back propagation neural networks to fuse laser sensor data and ultrasonic sensor data for enhancing the accuracy of mapping. For navigation of single robot, the robot has to know its initial position and accurate environment information around it. However, due to the inherent properties of sensors, each sensor has its own advantages and drawbacks. In our system, the robot equipped with seven ultrasonic sensors and a laser sensor navigates to map two different corridor environments. The experimental results show the effectiveness of the heterogeneous sensor fusion using an error backpropagation algorithm for mapping.

• Journal of the Korean Institute of Illuminating and Electrical Installation Engineers
• /
• v.23 no.7
• /
• pp.75-80
• /
• 2009

In this study, a Web server was constructed using LabVIEW's DataSocket, which makes possible acquisition, analysis, and saving in real time. The output value of the optical current sensor at the web server PC was measured and the output value was displayed using the Web browser of the client PC. DataSocket by LabVIEW makes the construction of a Web server easier than other languages and is compatible with other application programs. An optical current sensor was composed using a 1310 [nm] laser diode, and 9/125 [${\mu}m$] standard single mode optical fiber and was created to be a close type sensor. Data measurement using Web servers has the advantage of monitoring electric power systems at a great distance and can fuse IT technology and electric power systems. Also, this measurement uses inexpensive mounting and programming when compared to existing measurement equipment allowing the construction of a measurement system in any situation or surrounding.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.8 no.9
• /
• pp.3196-3210
• /
• 2014

This paper presents a novel video metrology approach based on robust tracking. From videos acquired by an uncalibrated stationary camera, the foreground likelihood map is obtained by using the Codebook background modeling algorithm, and the multiple moving objects are tracked by a combined tracking algorithm. Then, we compute vanishing line of the ground plane and the vertical vanishing point of the scene, and extract the head feature points and the feet feature points in each frame of video sequences. Finally, we apply a single view mensuration algorithm to each of the frames to obtain height measurements and fuse the multi-frame measurements using RANSAC algorithm. Compared with other popular methods, our proposed algorithm does not require calibrating the camera, and can track the multiple moving objects when occlusion occurs. Therefore, it reduces the complexity of calculation and improves the accuracy of measurement simultaneously. The experimental results demonstrate that our method is effective and robust to occlusion.

• Journal of Korea Multimedia Society
• /
• v.24 no.3
• /
• pp.423-430
• /
• 2021

Aiming Graph convolutional networks (GCNs) have achieved outstanding performances on skeleton-based action recognition. However, several problems remain in existing GCN-based methods, and the problem of low recognition rate caused by single input data information has not been effectively solved. In this article, we propose a Dual-stream fusion method that combines video data and skeleton data. The two networks respectively identify skeleton data and video data and fuse the probabilities of the two outputs to achieve the effect of information fusion. Experiments on two large dataset, Kinetics and NTU-RGBC+D Human Action Dataset, illustrate that our proposed method achieves state-of-the-art. Compared with the traditional method, the recognition accuracy is improved better.

• Journal of Korea Multimedia Society
• /
• v.25 no.6
• /
• pp.819-832
• /
• 2022

Cross-domain recommender system transfers knowledge across different domains to improve the recommendation performance in a target domain that has a relatively sparse model. However, they suffer from the "negative transfer" in which transferred knowledge operates as noise. This paper proposes a novel Multiple Fusion-based Deep Cross-Domain Recommendation named MFDCR. We exploit Doc2Vec, one of the famous word embedding techniques, to fuse data user-wise and transfer knowledge across multi-domains. It alleviates the "negative transfer" problem. Additionally, we introduce a simple multi-layer perception to learn the user-item interactions and predict the possibility of preferring items by users. Extensive experiments with three domain datasets from one of the most famous services Amazon demonstrate that MFDCR outperforms recent single and cross-domain recommendation algorithms. Furthermore, experimental results show that MFDCR can address the problem of "negative transfer" and improve recommendation performance for multiple domains simultaneously. In addition, we show that our approach is efficient in extending toward more domains.

• Korean Journal of Crystallography
• /
• v.5 no.2
• /
• pp.100-107
• /
• 1994

A new Nl-pentenyl derivative of pyrimidines has been synthesized by an intramolecular (2+2) photocycloaddition and characterized by the single-crystal X-ray diffraction technique. The compound crystallizes in the rhombohedral system (R3, a=27.767(5)A c=6.390(2)A). In this structure, two 6-membered rings and a 4-membered ring are fused by the N-N or N-C bonds and the Tyidin Part adouts chair conformation. A pair of molecules related by an inversion center we held together through the hydrogen bonding interactions between N and O atoms of the uracil miety.

• Korean Journal of Ichthyology
• /
• v.19 no.4
• /
• pp.286-291
• /
• 2007

The bitterling, Acheilognathus koreensis spermatozoon has been examined by electron microscopy. The epididymal spermatozoa of A. koreensis are representing typical characteristic of cyprinid spermatozoa including the lateral insertion of flagellum, the organization of centriolar complex in shallow nuclear fossa and the asymmetrical arrangement of mitochondria. The sperm mid-piece contains a large mitochondrion characteristic enclosed by membranous vesicles. The mitochondria aspect is different from that of other cyprinid spermatozoa, which their mitochondria have a conventional aspect and never fuse to form a mitochondrial derivative. In term of sperm evolution, the fused mitochondria are regarded as the apomorphic character in comparison with the separate mitochondria. The single mitochondrion is not found in cyprinid spermatozoon except for Rodeus and Pungtungia.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.4
• /
• pp.302-306
• /
• 2001

Because face Images have many variations(expression, illumination, orientation of face, etc), there has been no popular method which has high recognition rate. To solve this difficulty, data fusion that fuses various information has been studied. But previous research for data fusion fused additional biological informationUingerplint, voice, del with face image. In this paper, cooperative results from several face image recognition modules are fused without using additional biological information. To fuse results from individual face image recognition modules, we use re-defined mass function based on Dempster-Shafer s fusion theory.Experimental results from fusing several face recognition modules are presented, to show that proposed fusion model has better performance than single face recognition module without using additional biological information.

• JSTS:Journal of Semiconductor Technology and Science
• /
• v.12 no.3
• /
• pp.331-340
• /
• 2012

In the deep sub-micron ICs, growing amounts of on-die memory and scaling effects make embedded memories increasingly vulnerable to reliability and yield problems. Spare columns are often included in memories to repair defective cells or bit lines during production test. In many cases, the repair process will not use all spare columns. Schemes have been proposed to exploit these unused spare columns to store additional check bits which can be used to reduce the miscorrection probability for triple errors in single error correction-double error detection (SEC-DED). These additional check bits increase the dimensions of the parity check matrix (H-matrix) requiring extra area overhead. A method is proposed in this paper to efficiently fill the extra rows of the H-matrix on the basis of similarity of logic between the other rows. Optimization of the whole H-matrix is accomplished through logic sharing within a feasible operating time resulting in reduced area overhead. A detailed implementation using fuse technology is also proposed in this paper.