• The Transactions of the Korea Information Processing Society
• /
• v.1 no.2
• /
• pp.215-224
• /
• 1994

In this paper, the rotation and size invariant fingerprint recognition using the neural network EART (Extended Adaptive Resonance Theory) is studied ($515{\times}512$) gray level fingerprint images are converted into the binary thinned images based on the adaptive threshold and a thinning algorithm. From these binary thinned images, we extract the ending points and the bifurcation points, which are the most useful critical feature points in the fingerprint images, using the $3{\times}3$ MASK. And we convert the number of these critical points and the interior angles of convex polygon composed of the bifurcation points into the 40*10 critical using the weighted code which is invariant of rotation and size as the input of EART. This system produces very good and efficient results for the rotation and size variations without the restoration of the binary thinned fingerprints.

• Journal of Korean Academy of Nursing
• /
• v.46 no.4
• /
• pp.475-489
• /
• 2016

Purpose: This study was a systematic review and meta-analysis designed to investigate the effects of stimulation-oriented interventions for behavioral problems among people with dementia. Methods: Based on the guidelines of the Preferred Reporting Items for Systematic Reviews and Meta-analyses (PRISMA), a literature search was conducted using seven electronic databases, gray literature, and other sources. Methodological quality was assessed using the Scottish Intercollegiate Guidelines Network (SIGN) for randomized controlled trials (RCTs). Data were analyzed using R with the 'meta' package and the Comprehensive Meta-Analysis (CMA 2.0) program. Results: Sixteen studies were included for meta-analysis to investigate the effect of stimulation-oriented interventions. The quality of individual studies was rated as '++' for eight studies and '+' for the rest. The effect sizes were analyzed according to three subgroups of interventions (light, music, and others); Hedges' g=0.04 (95% CI: -0.38~0.46), -0.23 (95% CI: -0.56~0.10), -0.34 (95% CI: -0.34~0.00), respectively. To explore the possible causes of heterogeneity ($I^2=62.8%$), meta-regression was conducted with covariates of sample size, number of sessions, and length of session (time). No moderating effects were found for sample size or number of sessions, but session time showed a significant effect (Z=1.96, 95% CI: 0.00~0.01). Finally, a funnel plot along with Egger's regression test was performed to check for publication bias, but no significant bias was detected. Conclusion: Based on these findings, stimulation-oriented interventions seem to have a small effect for behavioral problems among people with dementia. Further research is needed to identify optimum time of the interventions for behavioral problems among dementia pateints.

• Food Science of Animal Resources
• /
• v.38 no.2
• /
• pp.362-375
• /
• 2018

This study proposed a rapid microscopic examination method for pork freshness evaluation by using the self-assembled hyperspectral microscopic imaging (HMI) system with the help of feature extraction algorithm and pattern recognition methods. Pork samples were stored for different days ranging from 0 to 5 days and the freshness of samples was divided into three levels which were determined by total volatile basic nitrogen (TVB-N) content. Meanwhile, hyperspectral microscopic images of samples were acquired by HMI system and processed by the following steps for the further analysis. Firstly, characteristic hyperspectral microscopic images were extracted by using principal component analysis (PCA) and then texture features were selected based on the gray level co-occurrence matrix (GLCM). Next, features data were reduced dimensionality by fisher discriminant analysis (FDA) for further building classification model. Finally, compared with linear discriminant analysis (LDA) model and support vector machine (SVM) model, good back propagation artificial neural network (BP-ANN) model obtained the best freshness classification with a 100 % accuracy rating based on the extracted data. The results confirm that the fabricated HMI system combined with multivariate algorithms has ability to evaluate the fresh degree of pork accurately in the microscopic level, which plays an important role in animal food quality control.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.3
• /
• pp.91-98
• /
• 2018

Automatic detection of pig wasting diseases is an important issue in the management of group-housed pigs. In particular, porcine respiratory diseases are one of the main causes of mortality among pigs and loss of productivity in intensive pig farming. In this paper, we propose a noise-robust system for the early detection and recognition of pig wasting diseases using sound data. In this method, first we convert one-dimensional sound signals to two-dimensional gray-level images by normalization, and extract texture images by means of dominant neighborhood structure technique. Lastly, the texture features are then used as inputs of convolutional neural networks as an early anomaly detector and a respiratory disease classifier. Our experimental results show that this new method can be used to detect pig wasting diseases both economically (low-cost sound sensor) and accurately (over 96% accuracy) even under noise-environmental conditions, either as a standalone solution or to complement known methods to obtain a more accurate solution.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.16 no.3
• /
• pp.2141-2145
• /
• 2015

A new broadcasting signal transmission, which can save its channel bandwidth using compressive sensing(CS), is proposed in this paper. A new compression technique, which uses two dimensional discrete wavelet transform technique, is proposed to get high sparsity of multimedia image. A L1 minimization technique based on orthogonal matching pursuit is also introduced in order to reconstruct the compressed multimedia image. The CS enables us to save the channel bandwidth of wired and wireless broadcasting signal because various transmitted data are compressed using it. A $256{\times}256$ gray-scale image with compression rato of 20 %, which is sampled by 10 Gs/s, was transmitted to an optical receiver through 20-km optical transmission and then was reconstructed successfully using L1 minimization (bit error rate of $10^{-12}$ at the received optical power of -12.2 dB).

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.38 no.3
• /
• pp.61-67
• /
• 2001

In this paper, a method that apply LP algorithm to image for speech recognition is suggested, using both speech and image information for recogniton of korean numeral speech. The input speech signal is pre-emphasized with parameter value 0.95, analyzed for B th LP coefficients using Hamming window, autocorrelation and Levinson-Durbin algorithm. Also, a gray image signal is analyzed for 2-dimensional LP coefficients using autocorrelation and Levinson-Durbin algorithm like speech. These parameters are used for input parameters of neural network using back-propagation algorithm. The recognition experiment was carried out at each noise level, three numeral speechs, '3','5', and '9' were enhanced. Thus, in case of recognizing speech with 2-dimensional LP parameters, it results in a high recognition rate, a low parameter size, and a simple algorithm with no additional feature extraction algorithm.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• v.9 no.2
• /
• pp.127-130
• /
• 2005

Internal cities such as gray level been enclosed to building forest are paying a lot of efforts and expenses to change to green city that park and street tree get put together. By the example, 'GREEN CITY of PUSAN 21' progress to decorate army facilities like the park, and to plant street trees in several places of city plan in Pusan. And urban environment that big cities of advanced nation are agreeable is making in the large park and road street trees at several places in downtown. Because price of tree for the park is very expensive, tree management system was all-important. In this paper, Motes deliver the sensor information in each tree through radio sensor network by server side. This information can use in state grasping of tree, harmful insects courtesy call etc and this system design was suggested to inform to mode of life administration scholars.

• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2005.10a
• /
• pp.217-220
• /
• 2005

Internal cities such as gray level been enclosed to building forest are paying a lot of efforts and expenses to change to green city toot park and street tree get put together. By the example, 'GREEN CITY of PUSAN 21' progress to decorate army facilities like the park, and to plant street trees in several places of city plan in Pusan. And urban environment that big citys of advanced nation are agreeable is making in the large park and road street trees at several places in downtown. Because price of tree for the park is very expensive, tree management system was all-important. In this paper, Motes deliver the sensor information in each tree through radio sensor network by server side. This information can use in state grasping of tree, harmful insects courtesy call etc and this system design was suggested to inform to mode of life administration scholars.

• The KIPS Transactions:PartC
• /
• v.19C no.1
• /
• pp.47-54
• /
• 2012

Sharing cross-site resources has been adopted by many recent websites in the forms of service-mashup and social network services. In this change, exploitation of the new vulnerabilities increases, which includes inserting malicious codes into the interaction points between clients and services instead of attacking the websites directly. In this paper, we present a system model to identify malicious script codes in the web contents by means of a remote verification while the web contents downloaded from multiple trusted origins are executed in a client's browser space. Our system classifies verification items according to the origin of request based on the information on the service code implementation and stores the verification results into three databases composed of white, gray, and black lists. Through the experimental evaluations, we have confirmed that our system provides clients with increased security by effectively detecting malicious scripts in the mashup web environment.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.10
• /
• pp.411-420
• /
• 2019

Camera model identification has been a subject of steady study in the field of digital forensics. Among the increasingly sophisticated crimes, crimes such as illegal filming are taking up a high number of crimes because they are hard to detect as cameras become smaller. Therefore, technology that can specify which camera a particular image was taken on could be used as evidence to prove a criminal's suspicion when a criminal denies his or her criminal behavior. This paper proposes a deep learning model to identify the camera model used to acquire the image. The proposed model consists of four convolution layers and two fully connection layers, and a high pass filter is used as a filter for data pre-processing. To verify the performance of the proposed model, Dresden Image Database was used and the dataset was generated by applying the sequential partition method. To show the performance of the proposed model, it is compared with existing studies using 3 layers model or model with GLCM. The proposed model achieves 98% accuracy which is similar to that of the latest technology.