• The Journal of the Korea Contents Association
• /
• v.10 no.12
• /
• pp.84-90
• /
• 2010

In this paper, we propose a quadratic discriminant analysis based approach for improving the discriminating strength of weak classifiers based on simple Haar-like features that were used in the Viola-Jones object detection framework. Viola and Jones built a strong classifier using a boosted ensemble of weak classifiers. However, their single threshold (or decision boundary) based weak classifier is sub-optimal and too weak for efficient discrimination between object class and background. A quadratic discriminant analysis based approach is presented which leads to hyper-quadric boundary between the object class and background class, thus realizing multiple thresholds based weak classifiers. Experiments carried out for car detection using 1000 positive and 3000 negative images for training, and 500 positive and 500 negative images for testing show that our method yields higher classification performance with fewer classifiers than single threshold based weak classifiers.

• KIISE Transactions on Computing Practices
• /
• v.21 no.1
• /
• pp.64-69
• /
• 2015

Place awareness is an essential for location-based services that are widely provided to smartphone users. However, traditional GPS-based methods are only valid outdoors where the GPS signal is strong and also require symbolic place information of the physical location. In this paper, environmental sounds and images are used to recognize important aspects of each place. The proposed method extracts feature vectors from visual, auditory and location data recorded by a smartphone with built-in camera, microphone and GPS sensors modules. The heterogeneous feature vectors were then learned by an ensemble learning method that learns each group of feature vectors for each classifier respectively and votes to produce the highest weighted result. The proposed method is evaluated for place recognition using a data group of 3000 samples in six places and the experimental results show a remarkably improved recognition accuracy when using all kinds of sensory data comparing to results using data from a single sensor or audio-visual integrated data only.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.1
• /
• pp.552-569
• /
• 2017

The existing steganalysis method based on 2D Gabor filters can achieve a competitive detection performance for content-adaptive JPEG steganography. However, the feature dimensionality is still high and the time-consuming of feature extraction is relatively large because the optimal selection is not performed for 2D Gabor filters. To solve this problem, a new steganalysis method is proposed for content-adaptive JPEG steganography by selecting the optimal 2D Gabor filters. For the proposed method, the 2D Gabor filters with different parameter settings are generated first. Then, the feature is extracted by each 2D Gabor filter and the corresponding detection accuracy is used as the measure for filter selection. Next, some 2D Gabor filters are selected by a greedy strategy and the steganalysis feature is extracted by the selected filters. Last, the ensemble classifier is used to assemble the proposed steganalysis feature as well as the final steganalyzer. The experimental results show that the steganalysis feature extracted by the selected optimal 2D Gabor filters also can achieve a competitive detection performance while the feature dimensionality is reduced greatly.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.8
• /
• pp.4043-4060
• /
• 2017

Network Intrusion Detection (NID), an important topic in the field of information security, can be viewed as a pattern recognition problem. The existing pattern recognition methods can achieve a good performance when the number of training samples is large enough. However, modern network attacks are diverse and constantly updated, and the training samples have much smaller size. Furthermore, to improve the learning ability of SVM, the research of kernel functions mainly focus on the selection, construction and improvement of kernel functions. Nonetheless, in practice, there are no theories to solve the problem of the construction of kernel functions perfectly. In this paper, we effectively integrate the advantages of the radial basis function kernel and the polynomial kernel on the notion of the game theory and propose a novel kernel SVM algorithm with game theory for NID, called GTNID-SVM. The basic idea is to exploit the game theory in NID to get a SVM classifier with better learning ability and generalization performance. To the best of our knowledge, GTNID-SVM is the first algorithm that studies ensemble kernel function with game theory in NID. We conduct empirical studies on the DARPA dataset, and the results demonstrate that the proposed approach is feasible and more effective.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.6
• /
• pp.3144-3164
• /
• 2019

Face recognition systems have several potential applications, such as security and biometric access control. Ongoing research is focused to develop a robust face recognition algorithm that can mimic the human vision system. Face pose, non-uniform illuminations, and low-resolution are main factors that influence the performance of face recognition algorithms. This paper proposes a novel method to handle the aforementioned aspects. Proposed face recognition algorithm initially uses 68 points to locate a face in the input image and later partially uses the PCA to extract mean image. Meanwhile, the AdaBoost and the LDA are used to extract face features. In final stage, classic nearest centre classifier is used for face classification. Proposed method outperforms recent state-of-the-art face recognition algorithms by producing high recognition rate and yields much lower error rate for a very challenging situation, such as when only frontal ($0^{\circ}$) face sample is available in gallery and seven poses ($0^{\circ}$, ${\pm}30^{\circ}$, ${\pm}35^{\circ}$, and ${\pm}45^{\circ}$) as a probe on the LFW and the CMU Multi-PIE databases.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.614-616
• /
• 2021

The world faces difficulties in terms of eye care, including treatment, quality of prevention, vision rehabilitation services, and scarcity of trained eye care experts. However, it is difficult to develop a method for classifying various ocular diseases because the existing dataset for retinal image disclosure does not consist of various diseases found in clinical practice. We propose a method for classifying ocular diseases using the Retinal Fundus Multi-disease Image Dataset (RFMiD), a dataset published in the ISBI-2021 challenge. Our goal is to develop a robust and generalizable model for screening retinal images into normal and abnormal categories. The performance of the proposed model shows a value of 0.9782 for the test dataset as an area under the curve (AUC) score.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.728-735
• /
• 2022

Roofers get exposed to increased risk of knee musculoskeletal disorders (MSDs) at different phases of a sloped shingle installation task. As different phases are associated with different risk levels, this study explored the application of machine learning for automated classification of seven phases in a shingle installation task using knee kinematics and roof slope information. An optical motion capture system was used to collect knee kinematics data from nine subjects who mimicked shingle installation on a slope-adjustable wooden platform. Four features were used in building a phase classification model. They were three knee joint rotation angles (i.e., flexion, abduction-adduction, and internal-external rotation) of the subjects, and the roof slope at which they operated. Three ensemble machine learning algorithms (i.e., random forests, decision trees, and k-nearest neighbors) were used for training and prediction. The simulations indicate that the k-nearest neighbor classifier provided the best performance, with an overall accuracy of 92.62%, demonstrating the considerable potential of machine learning methods in detecting shingle installation phases from workers knee joint rotation and roof slope information. This knowledge, with further investigation, may facilitate knee MSD risk identification among roofers and intervention development.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.119-137
• /
• 2022

Recent recommendation system studies apply various deep learning models to represent user and item interactions better. One of the noteworthy studies is ONCF(Outer product-based Neural Collaborative Filtering) which builds a two-dimensional interaction map via outer product and employs CNN (Convolutional Neural Networks) to learn high-order correlations from the map. However, ONCF has limitations in recommendation performance due to the problems with CNN and the absence of side information. ONCF using CNN has an inductive bias problem that causes poor performances for data with a distribution that does not appear in the training data. This paper proposes to employ a Vision Transformer (ViT) instead of the vanilla CNN used in ONCF. The reason is that ViT showed better results than state-of-the-art CNN in many image classification cases. In addition, we propose a new architecture to reflect side information that ONCF did not consider. Unlike previous studies that reflect side information in a neural network using simple input combination methods, this study uses an independent auxiliary classifier to reflect side information more effectively in the recommender system. ONCF used a single latent vector for user and item, but in this study, a channel is constructed using multiple vectors to enable the model to learn more diverse expressions and to obtain an ensemble effect. The experiments showed our deep learning model improved performance in recommendation compared to ONCF.

• The Journal of Society for e-Business Studies
• /
• v.21 no.1
• /
• pp.147-163
• /
• 2016

Gender information of a smart device user is essential to provide personalized services, and multi-modal data obtained from the device is useful for predicting the gender of the user. However, the method for utilizing each of the multi-modal data for gender prediction differs according to the characteristics of the data. Therefore, in this study, an ensemble method for predicting the gender of a smart device user by using three classifiers that have text, application, and acceleration data as inputs, respectively, is proposed. To alleviate privacy issues that occur when text data generated in a smart device are sent outside, a classification method which scans smart device text data only on the device and classifies the gender of the user by matching text data with predefined sets of word. An application based classifier assigns gender labels to executed applications and predicts gender of the user by comparing the label ratio. Acceleration data is used with Support Vector Machine to classify user gender. The proposed method was evaluated by using the actual smart device log data collected from an Android application. The experimental results showed that the proposed method outperformed the compared methods.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.2
• /
• pp.41-47
• /
• 2024

When there were disparities in performance between models trained in the time and frequency domains, even after conducting an ensemble, we observed that the performance of the ensemble was compromised due to imbalances in the individual model performances. Therefore, this paper proposes a leakage detection technique to enhance the accuracy of pipeline leakage detection through a step-wise learning approach that extracts features from both the time and frequency domains and integrates them. This method involves a two-step learning process. In the Stage 1, independent model training is conducted in the time and frequency domains to effectively extract crucial features from the provided data in each domain. In Stage 2, the pre-trained models were utilized by removing their respective classifiers. Subsequently, the features from both domains were fused, and a new classifier was added for retraining. The proposed transfer learning-based feature fusion technique in this paper performs model training by integrating features extracted from the time and frequency domains. This integration exploits the complementary nature of features from both domains, allowing the model to leverage diverse information. As a result, it achieved a high accuracy of 99.88%, demonstrating outstanding performance in pipeline leakage detection.