• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.6
• /
• pp.1058-1062
• /
• 2008

In clinical decision support system(CDSS), unlike rule-based expert method, appropriate data-driven machine learning method can easily provide the information of individual feature(clinical test) for disease classification. However, currently developed methods focus on the improvement of the classification accuracy for diagnosis. With the analysis of feature importance in classification, one may infer the novel clinical test sets which highly differentiate the specific diseases or disease states. In this background, we introduce a novel CDSS that integrate a classifier and feature selection module together. Random forest algorithm is applied for the classifier and the feature importance measure. The system selects the significant clinical tests discriminating the diseases by examining the classification error during backward elimination of the features. The superior performance of random forest algorithm in clinical classification was assessed against artificial neural network and decision tree algorithm by using breast cancer, diabetes and heart disease data in UCI Machine Learning Repository. The test with the same data sets shows that the proposed system can successfully select the significant clinical test set for each disease.

• Journal of information and communication convergence engineering
• /
• v.8 no.2
• /
• pp.173-179
• /
• 2010

Over recent years, much research attention has been devoted to a two-factor authentication mechanism which integrates both tokenized pseudorandom numbers with user specific biometric features for biometric verification, known as Biohash. The main advantage of Biohash over sole biometrics is that Biohash is able to achieve a zero equal error rate and provide a clean separation of the genuine and imposter populations, thereby allowing elimination of false accept rates without imperiling the false reject rates. Nonetheless, when the token of a user is compromised, the recognition performance of a biometric system drops drastically. As such, a few solutions have been proposed to improve the degraded performance but such improvements appear to be insignificant. In this paper, we investigate and pinpoint the basis of such deterioration. Subsequently, we propose a two-level approach by utilizing strong inner products and fuzzy logic weighting strategies accordingly to increase the original performance of Biohash under this scenario.

• Journal of Information Processing Systems
• /
• v.9 no.2
• /
• pp.333-348
• /
• 2013

Mobile authentication/identification has grown into a priority issue nowadays because of its existing outdated mechanisms, such as PINs or passwords. In this paper, we introduce gait recognition by using a mobile accelerometer as not only effective but also as an implicit identification model. Unlike previous works, the gait recognition only performs well with a particular mobile specification (e.g., a fixed sampling rate). Our work focuses on constructing a unique adaptive mechanism that could be independently deployed with the specification of mobile devices. To do this, the impact of the sampling rate on the preprocessing steps, such as noise elimination, data segmentation, and feature extraction, is examined in depth. Moreover, the degrees of agreement between the gait features that were extracted from two different mobiles, including both the Average Error Rate (AER) and Intra-class Correlation Coefficients (ICC), are assessed to evaluate the possibility of constructing a device-independent mechanism. We achieved the classification accuracy approximately $91.33{\pm}0.67%$ for both devices, which showed that it is feasible and reliable to construct adaptive cross-device gait recognition on a mobile phone.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.22 no.8
• /
• pp.1152-1163
• /
• 1998

In the present work, the image processing technique for measurement of drop sizes has been improved. Firstly, the local processing concept was adopted in addition to the global processing technique to take account of non-uniformity of the illumination intensity ; thereby, basically, the measurement error can be reduced. Also, the unfocussed image of drops can be eliminated more precisely since the elimination process is based on the local normalized contrast. Secondly the algorithms to process the partially detected or overlapped drop images and the non-spherical drop images were developed. Finally, the improved algorithm was tested by using an artificially prepared image-frame, where the partial or overlapped particles and the non-spherical particles are mixed with the normal spherical ones (with their true size-distributions known a priori). The results showed that both the recognition rate of the number of particles and the measurement accuracy were improved prominently.

• Smart Structures and Systems
• /
• v.13 no.3
• /
• pp.389-406
• /
• 2014

Optimal sensor placement techniques play a significant role in enhancing the quality of modal data during the vibration based health monitoring of civil structures, where many degrees of freedom are available despite a limited number of sensors. The literature has shown a shift in the trends for solving such problems, from expansion or elimination approach to the employment of heuristic algorithms. Although these heuristic algorithms are capable of providing a global optimal solution, their greatest drawback is the requirement of high computational effort. Because a highly efficient optimisation method is crucial for better accuracy and wider use, this paper presents an improved simulated annealing (SA) algorithm to solve the sensor placement problem. The algorithm is developed based on the sensor locations' coordinate system to allow for the searching in additional dimensions and to increase SA's random search performance while minimising the computation efforts. The proposed method is tested on a numerical slab model that consists of two hundred sensor location candidates using three types of objective functions; the determinant of the Fisher information matrix (FIM), modal assurance criterion (MAC), and mean square error (MSE) of mode shapes. Detailed study on the effects of the sensor numbers and cooling factors on the performance of the algorithm are also investigated. The results indicate that the proposed method outperforms conventional SA and Genetic Algorithm (GA) in the search for optimal sensor placement.

• Journal of Korean Ophthalmic Optics Society
• /
• v.6 no.2
• /
• pp.121-127
• /
• 2001

While SVD and Gaussian elimination method were applied to the additive damped least squares(DLS), the convergence and the stability of the optimization process were examined in a triplet-type camera lens-system where the condition number is well conditioned. DLS with SVD method generated a suitable merit function but this merit function may be trapped in a local minimum by the nonlinearity of error function. Therefore, the least camera lens-system was further designed by the global optimization method is grid method, and this method is adopted to get merit function that convergent to global minimum without local minimum trapping.

• Journal of KIISE:Information Networking
• /
• v.37 no.2
• /
• pp.162-165
• /
• 2010

In the paper, we propose an algorithm that significantly reduces unnecessary computations, while keeping prediction quality almost similar to that of the full search. In the proposed algorithm, we can reduces only unnecessary computations efficiently by taking different search patterns and error criteria of block matching according to distribution probability of motion vectors. Our algorithm takes only 20~30% in computational amount and has decreased prediction quality about 0~0.02dB compared with the fast full search of the H.264 reference software. Our algorithm will be useful to real-time video coding applications using MPEG-2/4 AVC standards.

• Communications for Statistical Applications and Methods
• /
• v.16 no.3
• /
• pp.429-436
• /
• 2009

This paper considers the integrated process control procedure for detecting special causes in an IMA(1,1) process that is being adjusted automatically after each observation using a minimum mean squared error adjustment policy. When the control chart signals after the occurrence of a special cause, the special cause will be detected and eliminated from the process by the rectifying action. However, when the elimination of the special cause costs high or is not practically possible, an alternative action is to readjust the process with appropriately modified adjustment scheme. In this paper, we propose the readjustment procedure after having a true signal, and show that the use of the readjustment can reduce the deviation of a process from the target.

• Journal of the Korean Dietetic Association
• /
• v.3 no.1
• /
• pp.1-8
• /
• 1997

The purpose of the study is to evaluate the differential effects caused by the interviewers and the days of the week using the 24-hour dietary recall method on the dietary evaluation of nutrient intakes. Thirteen subjects were interviewed by three trained interviewers on a Monday, Wednesday, and Friday. The consumption of nutrients by the subjects during each day was assessed. The average intake of nutrients was found to be sufficient except in calcium, iron, and vitamin A. there was a significant difference between the food intake on the weekdays and that o the weekend. However, the were no significant differences between the interviewers assessments on the intake of nutrients consumed by the subjects. The standardization of the portion size, interview skill and experience may be a few of the reasons explaining the elimination of the potential error created by variations among the interviewers. This study suggests that repeated 24-hour recalls during weekdays and weekends may be a better method for estimating the nutrients consumed by the subjects.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.5
• /
• pp.1929-1950
• /
• 2020

Reliable and secure data transmission in the application environment assisted by the wireless sensor network is one of the major challenges. Problem like blind forwarding and data inaccessibility affect the efficiency of overall infrastructure performance. This paper proposes routing protocol for forwarding and error recovery during packet loss. The same is achieved by energy and hops distance-based formulation of the routing mechanism. The reachability of the intermediate node to the source node is the major factor that helps in improving the lifetime of the network. On the other hand, intelligent hop selection increases the reliability over continuous data transmission. The number of hop count is factor of hop weight and available energy of the node. The comparison over the previous state of the art using QualNet-7.4 network simulator shows the effectiveness of proposed work in terms of overall energy conservation of network and reliable data delivery. The simulation results also show the elimination of blind forwarding and data inaccessibility.