• ETRI Journal
• /
• v.45 no.3
• /
• pp.448-461
• /
• 2023

This article performs a detailed data scrutiny on a chronic kidney disease (CKD) dataset to select efficient instances and relevant features. Data relevancy is investigated using feature extraction, hybrid outlier detection, and handling of missing values. Data instances that do not influence the target are removed using data envelopment analysis to enable reduction of rows. Column reduction is achieved by ranking the attributes through feature selection methodologies, namely, extra-trees classifier, recursive feature elimination, chi-squared test, analysis of variance, and mutual information. These methodologies are ranked via Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) using weight optimization to identify the optimal features for model building from the CKD dataset to facilitate better prediction while diagnosing the severity of the disease. An efficient hybrid ensemble and novel similarity-based classifiers are built using the pruned dataset, and the results are thereafter compared with random forest, AdaBoost, naive Bayes, k-nearest neighbors, and support vector machines. The hybrid ensemble classifier yields a better prediction accuracy of 98.31% for the features selected by extra tree classifier (ETC), which is ranked as the best by TOPSIS.

• Geomechanics and Engineering
• /
• v.38 no.1
• /
• pp.69-77
• /
• 2024

The development of shield-driven cross-river tunnels in China is witnessing a notable shift towards larger diameters, longer distances, and higher water pressures due to the more complex excavation environment. Complex geological formations, such as fault and karst cavities, pose significant construction risks. Real-time adjustment of shield tunneling parameters based on parameter prediction is the key to ensuring the safety and efficiency of shield tunneling. In this study, prediction models for the torque and thrust of the cutter plate of ultra-large diameter slurry shield TBMs is established based on integrated learning algorithms, by analyzing the real data of Heyan Road cross-river tunnel. The influence of geological complexities at the excavation face, substantial burial depth, and high water level on the slurry shield tunneling parameters are considered in the models. The results reveal that the predictive models established by applying Random Forest and AdaBoost algorithms exhibit strong agreement with actual data, which indicates that the good adaptability and predictive accuracy of these two models. The models proposed in this study can be applied in the real-time prediction and adaptive adjustment of the tunneling parameters for shield tunneling under complex geological conditions.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.4
• /
• pp.377-385
• /
• 2015

This paper proposes a novel forward vehicle tracking algorithm based on the WMIL(Weighted Multiple Instance Learning) equipped with a particle filter. In the proposed algorithm Haar-like features are used to train a vehicle object detector to be tracked and the location of the object are obtained from the recognition result. In order to combine both the WMIL to construct the vehicle detector and the particle filter, the proposed algorithm updates the object location by executing the propagation, observation, estimation, and selection processes involved in particle filter instead of finding the credence map in the search area for every frame. The proposed algorithm inevitably increases the computation time because of the particle filter, but the tracking accuracy was highly improved compared to Ababoost, MIL(Multiple Instance Learning) and MIL-based ones so that the position error was 4.5 pixels in average for the videos of national high-way, express high-way, tunnel and urban paved road scene.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.7
• /
• pp.655-661
• /
• 2017

It is a very important task to extract character regions contained in various input color images, because characters can provide significant information representing the content of an image. In this paper, we propose a new method for extracting character regions from various input images using MCT features and an AdaBoost algorithm. Using geometric features, the method extracts actual character regions by filtering out non-character regions from among candidate regions. Experimental results show that the suggested algorithm accurately extracts character regions from input images. We expect the suggested algorithm will be useful in multimedia and image processing-related applications, such as store signboard detection and car license plate recognition.

• Journal of information and communication convergence engineering
• /
• v.8 no.5
• /
• pp.575-580
• /
• 2010

Eye gaze as a form of input was primarily developed for users who are unable to use usual interaction devices such as keyboard and the mouse; however, with the increasing accuracy in eye gaze detection with decreasing cost of development, it tends to be a practical interaction method for able-bodied users in soon future as well. This paper explores a low-cost, robust, rotation and illumination independent eye gaze system for gaze enhanced user interfaces. We introduce two brand-new algorithms for fast and sub-pixel precise pupil center detection and 2D Eye Gaze estimation by means of deformable template matching methodology. In this paper, we propose a new algorithm based on the deformable angular integral search algorithm based on minimum intensity value to localize eyeball (iris outer boundary) in gray scale eye region images. Basically, it finds the center of the pupil in order to use it in our second proposed algorithm which is about 2D eye gaze tracking. First, we detect the eye regions by means of Intel OpenCV AdaBoost Haar cascade classifiers and assign the approximate size of eyeball depending on the eye region size. Secondly, using DAISMI (Deformable Angular Integral Search by Minimum Intensity) algorithm, pupil center is detected. Then, by using the percentage of black pixels over eyeball circle area, we convert the image into binary (Black and white color) for being used in the next part: DTBGE (Deformable Template based 2D Gaze Estimation) algorithm. Finally, using DTBGE algorithm, initial pupil center coordinates are assigned and DTBGE creates new pupil center coordinates and estimates the final gaze directions and eyeball size. We have performed extensive experiments and achieved very encouraging results. Finally, we discuss the effectiveness of the proposed method through several experimental results.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.2A
• /
• pp.95-104
• /
• 2012

Pattern recognition using ensemble classifiers is composed of strong classifier which consists of many weak classifiers. In this paper, we used feature extraction to organize strong classifier using static camera sequence. The strong classifier is made of weak classifiers which considers environmental factors. So the strong classifier overcomes environmental effect. Proposed method uses binary foreground image by frame difference method and the boosting is used to train crowdedness model and recognize crowdedness using features. Combination of weak classifiers makes strong ensemble classifier. The classifier could make use of potential features from the environment such as shadow and reflection. We tested the proposed system with road sequence and subway platform sequence which are included in "AVSS 2007" sequence. The result shows good accuracy and efficiency on complex environment.

• The KIPS Transactions:PartB
• /
• v.13B no.3 s.106
• /
• pp.283-294
• /
• 2006

In this paper, we propose a real-time face detection/tracking methodology with Haar wavelets and skin color. The proposed method boosts face detection and face tracking performance by combining skin color and Haar wavelets in an efficient way. The proposed method resolves the problem such as rotation and occlusion due to the characteristic of the condensation algorithm based on sampling despite it uses same features in both detection and tracking. In particular, it can be applied to a variety of applications such as face recognition and facial expression recognition which need an exact position and size of face since it not only keeps track of the position of a face, but also covers the size variation. Our test results show that our method performs well even in a complex background, a scene with varying face orientation and so on.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.10 no.1
• /
• pp.87-92
• /
• 2016

In this paper, we improved classification performance of benign and malignant lung nodules by including the parenchyma features. For small pulmonary nodules (4-10mm) nodules, there are a limited number of CT data voxels within the solid tumor, making them difficult to process through traditional CAD(computer aided diagnosis) tools. Increasing feature extraction to include the surrounding parenchyma will increase the CT voxel set for analysis in these very small pulmonary nodule cases and likely improve diagnostic performance while keeping the CAD tool flexible to scanner model and parameters. In AdaBoost learning using naive Bayes and SVM weak classifier, a number of significant features were selected from 304 features. The results from the COPDGene test yielded an accuracy, sensitivity and specificity of 100%. Therefore proposed method can be used for the computer aided diagnosis effectively.

• Smart Media Journal
• /
• v.5 no.1
• /
• pp.15-23
• /
• 2016

This paper proposes an effective algorithm of Korean license plate recognition. By applying Haar-like feature and Canny edge detection on a captured vehicle image, it is possible to find a connected rectangular, which is a strong candidate for license plate. The color information of license plate separates plates into white and green. Then, OTSU binary image processing and foreground neighbor pixel propagation algorithm CLNF will be applied to each license plates to reduce noise except numbers and letters. Finally, through labeling, numbers and letters will be extracted from the license plate. Letter and number regions, separated from the plate, pass through mesh method and thinning process for extracting feature vectors by X-Y projection method. The extracted feature vectors are classified using neural networks trained by backpropagation algorithm to execute final recognition process. The experiment results show that the proposed license plate recognition algorithm works effectively.

• The Journal of Korea Robotics Society
• /
• v.5 no.2
• /
• pp.152-159
• /
• 2010

Finding a head of a person in a scene is very important for taking a well composed picture by a robot photographer because it depends on the position of the head. So in this paper, we propose a robust head tracking algorithm using a hybrid of an omega shape tracker and local binary pattern (LBP) AdaBoost face detector for the robot photographer to take a fine picture automatically. Face detection algorithms have good performance in terms of finding frontal faces, but it is not the same for rotated faces. In addition, when the face is occluded by a hat or hands, it has a hard time finding the face. In order to solve this problem, the omega shape tracker based on active shape model (ASM) is presented. The omega shape tracker is robust to occlusion and illuminationchange. However, whenthe environment is dynamic,such as when people move fast and when there is a complex background, its performance is unsatisfactory. Therefore, a method combining the face detection algorithm and the omega shape tracker by probabilistic method using histograms of oriented gradient (HOG) descriptor is proposed in this paper, in order to robustly find human head. A robot photographer was also implemented to abide by the 'rule of thirds' and to take photos when people smile.