• Journal of Intelligence and Information Systems
• /
• v.16 no.2
• /
• pp.95-108
• /
• 2010

In this paper, we present a hybrid neural network model for dynamic hand gesture recognition. The model consists of two modules, feature extraction module and pattern classification module. We first propose a modified CNN(convolutional Neural Network) a pattern recognition model for the feature extraction module. Then we introduce a weighted fuzzy min-max(WFMM) neural network for the pattern classification module. The data representation proposed in this research is a spatiotemporal template which is based on the motion information of the target object. To minimize the influence caused by the spatial and temporal variation of the feature points, we extend the receptive field of the CNN model to a three-dimensional structure. We discuss the learning capability of the WFMM neural networks in which the weight concept is added to represent the frequency factor in training pattern set. The model can overcome the performance degradation which may be caused by the hyperbox contraction process of conventional FMM neural networks. From the experimental results of human action recognition and dynamic hand gesture recognition for remote-control electric home appliances, the validity of the proposed models is discussed.

• The Journal of Korean Institute of Electromagnetic Engineering and Science
• /
• v.28 no.8
• /
• pp.603-609
• /
• 2017

In the deployable solid surface antennas, the effects on the performances of antenna due to the structural errors that occur during the deployment are analyzed. The deployable solid surface antennas employed in a satellite are launched in folded configuration and those are deployed in the space environment, and the effects on the antenna performance are calculated depending on the type of surface errors. When the deviation error occurs in one panel, the degradation of performance appears in the side where the incomplete deployment of panel occurs. By assuming that the panel error distribution is in cosine function, the effect of errors are calculated and analyzed with regard to the types and the magnitude of the error. If the antena panel error is uniform, the gain is reduced and pattern is symmetric. For the panel error of cosine 1 or 3 cycle, the main lobe tilts while the pattern is symmetric and the gain reduces for 2 or 4 cycle error.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.16 no.6
• /
• pp.177-181
• /
• 2016

This paper analyzes the host cache effectiveness in full virtualization, particularly associated with journaling of guests. We observe that the journal access of guests degrades cache performance significantly due to the write-once access pattern and the frequent sync operations. To remedy this problem, we design and implement a novel caching policy, called PDC (Pollution Defensive Caching), that detects the journal accesses and prevents them from entering the host cache. The proposed PDC is implemented in QEMU-KVM 2.1 on Linux 4.14 and provides 3-32% performance improvement for various file and I/O benchmarks.

• Advances in concrete construction
• /
• v.9 no.5
• /
• pp.437-448
• /
• 2020

In high rise buildings that utilize precast large panel system for construction, the shear wall provides strength and stiffness during earthquakes. The performance of a wall panel system depends mainly on the type of connection used to transfer the forces from one wall element to another wall element. This paper presents an experimental investigation on different types of construction detailing of the precast wall to wall vertical connections under reverse cyclic loading. One of the commonly used connections in India to connect wall to wall panel is the loop bar connection. Hence for this study, three types of wet connections and one type of dry connection namely: Staggered loop bar connection, Equally spaced loop bar connection, U-Hook connection, and Channel connection respectively were used to connect the precast walls. One third scale model of the wall was used for this study. The main objective of the experimental work is to evaluate the performance of the wall to wall connections in terms of hysteretic behaviour, ultimate load carrying capacity, energy dissipation capacity, stiffness degradation, ductility, viscous damping ratio, and crack pattern. All the connections exhibited similar load carrying capacity. The U-Hook connection exhibited higher ductility and energy dissipation when compared to the other three connections.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.3
• /
• pp.319-327
• /
• 2012

In this paper, we present a sign language recognition model which does not use any wearable devices for object tracking. The system design issues and implementation issues such as data representation, feature extraction and pattern classification methods are discussed. The proposed data representation method for sign language patterns is robust for spatio-temporal variances of feature points. We present a feature extraction technique which can improve the computation speed by reducing the amount of feature data. A neural network model which is capable of incremental learning is described and the behaviors and learning algorithm of the model are introduced. We have defined a measure which reflects the relevance between the feature values and the pattern classes. The measure makes it possible to select more effective features without any degradation of performance. Through the experiments using six types of sign language patterns, the proposed model is evaluated empirically.

• Asian-Australasian Journal of Animal Sciences
• /
• v.13 no.6
• /
• pp.785-790
• /
• 2000

The effect of formaldehyde treatment of solvent and mechanical extracted cottonseed meal on the performance, digestibility and nitrogen balance was assessed in lambs. Four total mixed rations viz., A, B, C and D containing 40% untreated and treated solvent and mechanical extracted meal were prepared. Sixteen male lambs with average BW of 20-22 kg were randomly allocated to experimental rations and were fed individually during ninety days growth trial. The treatment of solvent extracted cottonseed meal resulted in a linear decrease in ruminal protein degradation. Maximum decrease (64%) in protein degradation was observed at 4 h incubation time with 0.3% formaldehyde treatment. Highest daily BW gain was observed in lambs fed on rations Band D compared to lambs fed on rations A and C. Daily BW gain was higher on rations having 0.3% for fromaldehyde treated cottonseed meals. Higher DM digestibility was observed on ration D compared to other rations. Higher (p<0.05) CP and CF digestibility was observed on rations Band D compared to rations A and C. Nitrogen retention as % age of nitrogen intake was (p<0.05) higher for lambs fed rations B and D compared to rations A and C. Similar pattern was observed for nitrogen retention as percent of nitrogen absorbed. The present study suggested that oil extraction methods of cottonseed did not alter their meal utilization in lambs, however, formaldehyde (0.3%) treatment of meals enhanced its efficiency for growth, digestibility and nitrogen balance in lambs.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.46 no.10
• /
• pp.856-867
• /
• 2018

This paper presents the applicability of MIMO joint decoding to dual-contact satellite systems in which two LEO satellites using X-band frequency band are transmitting each image data to two ground station antennas, simultaneously. When two satellites are closely positioned within the looking angle of the two antennas, each satellite interferes with each other by the relative antenna gain corresponding to an offset angle and this might cause the performance degradation without interference mitigation. To mitigate the performance degradation, SM MIMO techniques for joint decoding are applied. Especially, the relative antenna gain of ground station depending on the angle difference between two satellites in ground station antenna plays an important role in modelling the dual-contact satellite systems. The condition number of MIMO channel including the antenna gain calculated from the mathematical gain pattern model was primarily analyzed. Simulation results showed that the SM MIMO techniques using detection schemes such as ZF-SIC, MMSE-SIC, and ML can be applicable to dual-contact satellite systems.

• MALSORI
• /
• no.46
• /
• pp.51-64
• /
• 2003

In order to produce high quality synthesized speech, it is very important to get an accurate grapheme-to-phoneme conversion and prosody model from texts using natural language processing. Robust preprocessing for non-Korean characters should also be required. In this paper, we analyzed Korean texts using a morphological analyzer, part-of-speech tagger and syntactic chunker. We present a new grapheme-to-phoneme conversion method for Korean using a hybrid method with a phonetic pattern dictionary and CCV (consonant vowel) LTS (letter to sound) rules, for unlimited vocabulary Korean TTS. We constructed a prosody model using a probabilistic method and decision tree-based method. The probabilistic method atone usually suffers from performance degradation due to inherent data sparseness problems. So we adopted tree-based error correction to overcome these training data limitations.

• 한국정보디스플레이학회:학술대회논문집
• /
• 2008.10a
• /
• pp.1573-1576
• /
• 2008

A simulation system is developed to calculate the apparent motion-induced image from a sequence of temporal luminance transitions, while using the properties of the human visual system. Based on the simulation method, both edge (moving block) and detail degradation (line spreading, grating, sinusoidal pattern), and also color aberration are discussed.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2008.03a
• /
• pp.187-194
• /
• 2008

Because the types and severities of most engine faults are various and complex, it is not easy that the conventional model based fault detection approach like the GPA(Gas Path Analysis) method can monitor all engine fault conditions. Therefore this study proposed newly a diagnostic algorithm for isolating and diagnosing effectively the faulted components of the smart UAV propulsion system, which has been developed by KARI(Korea Aerospace Research Institute), using the fuzzy logic and the neural network algorithms. A precise performance model should be needed to perform the model-based diagnostics. The based engine performance model was developed using SIMULINK. For the work and mass flow matching between components of the steady-state simulation, the state-flow library was applied. The proposed steady-state performance model can simulate off-design point performance at various flight conditions and part loads, and in order to evaluate the steady-state performance model their simulation results were compared with manufacturer's performance deck data. According to comparison results, it was confirm that the steady-state model well agreed with the deck data within 3% in all flight envelop. The diagnosis procedure of the proposed diagnostic system has the following steps. Firstly after obtaining database of fault patterns through performance simulation, then secondly the diagnostic system was trained by the FFBP networks. Thirdly after analyzing the trend of the measuring parameters due to fault patterns, then fourthly faulted components were isolated using the fuzzy logic. Finally magnitudes of the detected faults were obtained by the trained neural networks. Because the detected faults have almost same as degradation values of the implanted fault pattern, it was confirmed that the proposed diagnostic system can detect well the engine faults.