• 한국HCI학회:학술대회논문집
• /
• 2007.02a
• /
• pp.667-674
• /
• 2007

Facial expressions provide significant clues about one's emotional state; however, it always has been a great challenge for machine to recognize facial expressions effectively and reliably. In this paper, we report a method of feature-based adaptive motion energy analysis for recognizing facial expression. Our method optimizes the information gain heuristics of ID3 tree and introduces new approaches on (1) facial feature representation, (2) facial feature extraction, and (3) facial feature classification. We use minimal reasonable facial features, suggested by the information gain heuristics of ID3 tree, to represent the geometric face model. For the feature extraction, our method proceeds as follows. Features are first detected and then carefully "selected." Feature "selection" is finding the features with high variability for differentiating features with high variability from the ones with low variability, to effectively estimate the feature's motion pattern. For each facial feature, motion analysis is performed adaptively. That is, each facial feature's motion pattern (from the neutral face to the expressed face) is estimated based on its variability. After the feature extraction is done, the facial expression is classified using the ID3 tree (which is built from the 1728 possible facial expressions) and the test images from the JAFFE database. The proposed method excels and overcomes the problems aroused by previous methods. First of all, it is simple but effective. Our method effectively and reliably estimates the expressive facial features by differentiating features with high variability from the ones with low variability. Second, it is fast by avoiding complicated or time-consuming computations. Rather, it exploits few selected expressive features' motion energy values (acquired from intensity-based threshold). Lastly, our method gives reliable recognition rates with overall recognition rate of 77%. The effectiveness of the proposed method will be demonstrated from the experimental results.

• Journal of Information Technology Applications and Management
• /
• v.15 no.3
• /
• pp.79-90
• /
• 2008

With the corporate environment nowadays being surrounded by plenty of information, the sharing of information among businesses through mutual cooperation tops the list of hot issues. Predictions of demands from the customer, business, or consumer by sharing information can affect the inventory and order production system. However, notwithstanding the importance of sharing information, empirical studies on quantitative use of information still remain insufficient in spite of many a discussion now being made on the sharing of information. This paper proposes to examine the ways meteorological information may affect the rises in the achievements of supply chains in distributive businesses, the kind of information that noticeably affects the consumer behavioral patterns in the distributive businesses but rarely perceived as a form of information shared by businesses. This study is based on a model in which meteorological information has been added as the one used to predict demands, after the beer distribution game has been modified to fit the current status, and simulations under an assumptive situation, where decisions are made on a daily basis, were conducted 50 times for a period of 1000 days for the generalization of the results, while at the same time a Duncan Test was conducted to determine the threshold to use the meteorological information that will be most profitable to the retailer, wholesaler, supplier and the supply chain as a whole. Our findings indicate that corporations have thresholds that vary from business to business depending upon the ratio of backlog costs to inventory costs. At the same time, our findings also show that there existed effective thresholds depending upon the ratio of backlog costs to inventory costs for the performance of the overall supply chain.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.11 no.5
• /
• pp.379-387
• /
• 2001

We proposed an enhanced extraction method of vehicle plate, in which both the brightness variation of gray and the Hue value of HSI color model were used. For the extraction of the vehicle plate from a vehicle image, first of all, candidate regions for the vehicle plate were extracted from the image by using the property of brightness variation of the image. A real place region was determined among candidate regions by the density of pixels with the Hue value of green and white. For- extracting the feature area containing characters from the extracted vehicle plate, we used the histogram-based approach of individual characters. And we proposed and applied for the recognition of characters the enhanced ART2 algorithm which support the dynamical establishment of the vigilance threshold with the genera]iced union operator of Yager. In addition, we propose an enhanced SOSL algorithm which is integrated both enhanced ART2 and supervised learning methods. The performance evaluation was performed using 100's real vehicle images and the evaluation results demonstrated that the extraction rates of tole proposed extraction method were improved, compared with that of previous methods based un brightness variation, RGB and HSI individually . Furthermore, the recognition rates of the proposed algorithms were improved much more than that of the conventional ART2 and BP algorithms.

• Journal of the Korea Convergence Society
• /
• v.8 no.5
• /
• pp.13-17
• /
• 2017

Existing Speech feature extracting method in speech Signal, there are incorrect recognition rates due to incorrect speech which is not clear threshold value. In this article, the modeling method for improving speech recognition performance that combines the feature extraction for speech and silence characteristics normalized to the non-speech. The proposed method is minimized the noise affect, and speech recognition model are convergence of speech signal feature extraction to each speech frame and the silence feature normalization. Also, this method create the original speech signal with energy spectrum similar to entropy, therefore speech noise effects are to receive less of the noise. the performance values are improved in signal to noise ration by the silence feature normalization. We fixed speech and non speech classification standard value in cepstrum For th Performance analysis of the method presented in this paper is showed by comparing the results with CHMM HMM, the recognition rate was improved 2.7%p in the speech dependent and advanced 0.7%p in the speech independent.

• Korean journal of applied entomology
• /
• v.48 no.1
• /
• pp.45-51
• /
• 2009

This paper presents sequential sampling plans for evaluating the pest density based on complete counts from probe in a rice storage warehouse. Both maize weevil and Indian meal moth population showed negative binomial dispersion patterns in brown rice storage. For cost-effective monitoring and action decision making system, sequential sampling plans by using the sequential probability ratio test (SPRT) were developed for the maize weevil and Indian meal moth in warehouses with 0.8 M/T storage bags. The action threshold for the two insect pests was estimated to 5 insects per kg, which was projected by a matrix model. The results show that, using SPRT methods, managers can make decisions using only 20 probe with a minimum risk of incorrect assessment.

• Journal of Broadcast Engineering
• /
• v.18 no.4
• /
• pp.543-549
• /
• 2013

Motion artifacts of central and autonomic nervous system signals degrades the performance of the bio-signal based human factor analysis. Firstly, we propose a defining method of motion artifact section by analyzing successive image frames. Motion artifact section is defined when the amount of motion is greater than the pre-defined threshold. In here, the amount of motion is estimated by first derivation of image frames at temporal domain. Secondly, we propose another defining method of motion artifact section through designing 2D Gaussian probability density function model by analyzing feature vectors of one cycle of signal such as length and amplitude. The defined motion artifact sections are interpolated on the basis of 1D Gaussian function. At result of applying the method into photoplethysmography signal, we confirmed that the calculated heartbeat rate from the restored photoplethysmography came up to the one from electrocardiography. Also, we found that the video based method generated relatively more false acceptance of motion artifact section and the probability density function based method generated relatively more false rejection of motion artifact section.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.43 no.4 s.346
• /
• pp.23-30
• /
• 2006

This paper describes the short-channel effect(SCE), corner effect of nano-scale MuGFETs(Multiple-Gate FETs) by three-dimensional simulation. We can extract the equivalent gate number of MuGFETs(Double-gate=2, Tri-gate=3, Pi-gate=3.14, Omega-gate=3.4, GAA=4) by threshold voltage model. Using the extracted gate number(n) we can calculate the natural length for each gate devices. We established a scaling theory for MuGFETs, which gives a optimization to avoid short channel effects for the device structure(silicon thickness, gate oxide thickness). It is observed that the comer effects decrease with the reduction of doping concentration and gate oxide thickness when the radius of curvature is larger than 17 % of the channel width.

• Journal of the Semiconductor & Display Technology
• /
• v.8 no.4
• /
• pp.31-36
• /
• 2009

In this paper, the laser cutting characteristics of the flexible PCB using high power Nd:YAG UV laser were investigated. A specific FPCB model was selected for the experiment. Test sheets were made, which had equal materials and layer structure to those of the outline (OL) region and the contact pad (CP) region in the FPCB. The experiment is made up of two stages. In the first stage of the experiment, the laser cutting fluence was found, which is the threshold fluence to cut the test sheets completely. The laser cutting fluence of the OL sheet is $1781.26{\sim}1970.16\;J/cm^2$ and that of the CP sheet is $2109.34{\sim}2134.34\;J/cm^2$. In the second stage, cutting performance and its qualities were analyzed by the experiment. The laser cutting performance remained almost unchanged for all laser and process parameter sets. The average cutting width (top side/bottom side) of the OL sheet was $40.45\;{\mu}m/11.52\;{\mu}m$ and that of the CP sheet was $22.14\;{\mu}m/10.93\;{\mu}m$. However, the laser cutting qualities were different according to the parameters. The adjacent region of the cutting line on the OL sheet was carbonized as the beam speed was low and the overlap coefficient was high. The surface quality around the cutting line of the CP sheet was about the same. Carbonization and debris occurred on the surface of the cutting line. As a result of the experiment, the cutting qualities were better as the overlap coefficient was made low and beam speed high. Therefore, the overlap coefficient 2 or 3 is proper for the FPCB laser cutting.

• Korean journal of applied entomology
• /
• v.38 no.1
• /
• pp.29-33
• /
• 1999

Orius strgicollis Poppius is an endemic natural enemy of thrips recently found. To estimatethe optimum temperature for rearing in laboratory, development and oviposition of 0. strigicollis wasstudied at 15, 20, 25 and 30$^{\circ}$C with a 16L : 8D photoperiod and 60-80% RH. Cotton aphid, Aphisgossipyii, was supplied as prey. Total number of eggs laid per female ranged from 39.1 to 68.5 with thehighest at 25$^{\circ}$C. Adult longevity decreased as temperature increased, and the reverse was true for eggsurvivorship. Survivorship of larvae was 26.7,43.3, 76.7 and 46.7% at 15, 20, 25 and 30$^{\circ}$C, respectively.Duration of eggs and larvae at tested temperatures ranged from 3.4 days to 18.9 days and from 9.4 days to45.6 days, respectively. A linear regression model could describe development of the predator as afunction of temperature (R2=0.949-0.997). The lower developmental threshold temperatures for egg,larvae, and total immature stage were estimated to be 12.4, 11.4, and 11.6"C, respectively.6"C, respectively.vely.

• Journal of Internet Computing and Services
• /
• v.14 no.4
• /
• pp.13-24
• /
• 2013

IEEE 802.15.4 network and WiFi network are installed to overlap each other and configured to use adjacent frequency bands in which case the communication service required by applications can not be guaranteed because of randomly increased frame transmission delay and frequent frame transmission failures at nodes in IEEE 802.15.4 network. In this paper, transmission delay model at IEEE 802.15.4 nodes and an experimental system to evaluate the interference from WiFi traffic are described, then elements for the evaluation of interference are measured with the analysis of their characteristics. A sequential method of using medium access layer and physical layer elements of IEEE 802.15.4 protocols is proposed to decide interference from WiFi network. With the proposed method, if an evaluation function having frame transmission failures and transmission delay as variables returns a value greater than a threshold, intensive measurements of wireless channel power are carried out subsequently and the final decision of interference is made by the calculated average channel power. Experimental results of the method show that the decision time is reduced with increased frequency of decision in comparison to an other similar method.