• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.4
• /
• pp.116-128
• /
• 2011

In this paper, we propose the structure of a high-performance face-detection engine that responds well to facial rotating changes using rotation transformation which minimize the required memory usage compared to the previous face-detection engine. The validity of the proposed structure has been verified through the implementation of FPGA. For high performance face detection, the MCT (Modified Census Transform) method, which is robust against lighting change, was used. The Adaboost learning algorithm was used for creating optimized learning data. And the rotation transformation method was added to maintain effectiveness against face rotating changes. The proposed hardware structure was composed of Color Space Converter, Noise Filter, Memory Controller Interface, Image Rotator, Image Scaler, MCT(Modified Census Transform), Candidate Detector / Confidence Mapper, Position Resizer, Data Grouper, Overlay Processor / Color Overlay Processor. The face detection engine was tested using a Virtex5 LX330 FPGA board, a QVGA grade CMOS camera, and an LCD Display. It was verified that the engine demonstrated excellent performance in diverse real life environments and in a face detection standard database. As a result, a high performance real time face detection engine that can conduct real time processing at speeds of at least 60 frames per second, which is effective against lighting changes and face rotating changes and can detect 32 faces in diverse sizes simultaneously, was developed.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.10
• /
• pp.2809-2821
• /
• 2023

Effective recommendation of similar business groups is a critical factor in obtaining market information for companies. In this study, we propose a novel method for enhancing similar business group recommendation by incorporating derivative criteria and web crawling. We use employment announcements, employment incentives, and corporate vocational training information to derive additional criteria for similar business group selection. Web crawling is employed to collect data related to the derived criteria from 'credit jobs' and 'worknet' sites. We compare the efficiency of different datasets and machine learning methods, including XGBoost, LGBM, Adaboost, Linear Regression, K-NN, and SVM. The proposed model extracts derivatives that reflect the financial and scale characteristics of the company, which are then incorporated into a new set of recommendation criteria. Similar business groups are selected using a Euclidean distance-based model. Our experimental results show that the proposed method improves the accuracy of similar business group recommendation. Overall, this study demonstrates the potential of incorporating derivative criteria and web crawling to enhance similar business group recommendation and obtain market information more efficiently.

• Computers and Concrete
• /
• v.32 no.3
• /
• pp.233-246
• /
• 2023

Accurate prediction of concrete compressive strength can minimize the need for extensive, time-consuming, and costly mixture optimization testing and analysis. This study attempts to enhance the prediction accuracy of compressive strength using stacking ensemble machine learning (ML) with feature engineering techniques. Seven alternative ML models of increasing complexity were implemented and compared, including linear regression, SVM, decision tree, multiple layer perceptron, random forest, Xgboost and Adaboost. To further improve the prediction accuracy, a ML pipeline was proposed in which the feature engineering technique was implemented, and a two-layer stacked model was developed. The k-fold cross-validation approach was employed to optimize model parameters and train the stacked model. The stacked model showed superior performance in predicting concrete compressive strength with a correlation of determination (R²) of 0.985. Feature (i.e., variable) importance was determined to demonstrate how useful the synthetic features are in prediction and provide better interpretability of the data and the model. The methodology in this study promotes a more thorough assessment of alternative ML algorithms and rather than focusing on any single ML model type for concrete compressive strength prediction.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.12
• /
• pp.1109-1114
• /
• 2015

This paper presents an improved learning-based visual inspection method for auto parts inspection in severe lighting changes. Automobile sunroof frames are produced automatically by robots in most production lines. In the sunroof frame manufacturing process, there is a quality problem with some parts such as volts are missed. Instead of manual sampling inspection using some mechanical jig instruments, a learning-based machine vision system was proposed in the previous research[1]. But, in applying the actual sunroof frame production process, the inspection accuracy of the proposed vision system is much lowered because of severe illumination changes. In order to overcome this capricious environment, some selective feature vectors and cascade classifiers are used for each auto parts. And we are able to improve the inspection accuracy through the re-learning concept for the misclassified data. The effectiveness of the proposed visual inspection method is verified through sufficient experiments in a real sunroof production line.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2016.04a
• /
• pp.633-635
• /
• 2016

Convolutional Networks (ConvNets) are powerful models that learn hierarchies of visual features, which could also be used to obtain image representations for transfer learning. The basic pipeline for transfer learning is to first train a ConvNet on a large dataset (source task) and then use feed-forward units activation of the trained ConvNet as image representation for smaller datasets (target task). Our key contribution is to demonstrate superior performance of multiple ConvNet layer features over single ConvNet layer features. Combining multiple ConvNet layer features will result in more complex feature space with some features being repetitive. This requires some form of feature selection. We use AdaBoost with single stumps to implicitly select only distinct features that are useful towards classification from concatenated ConvNet features. Experimental results show that using multiple ConvNet layer activation features instead of single ConvNet layer features consistently will produce superior performance. Improvements becomes significant as we increase the distance between source task and the target task.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2014.06a
• /
• pp.254-257
• /
• 2014

Recently, various applications using real-time face detection have been developed as face recognition technology and hardware grows. While network service is developing and video instruments costs lower, it is needed that smart surveillance camera and service using network camera based on IP and face detection technology. However, videos should be compressed for reducing network bandwidth and storage capacity in surveillance system. As it requires high-level improvement of system performance when all the compressed frames are processed in a face detection program, fast face detection method is needed. In this paper, not only a fast way of algorithm using Haar like features and adaboost learning and motion information but also an application on broadcast system is suggested.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.12
• /
• pp.1081-1088
• /
• 2013

Hyperspectral cameras acquire reflectance values at many different wavelength bands. Dimensions tend to increase because spectral information is stored in each pixel. Several attempts have been made to reduce dimensional problems such as the feature selection using Adaboost and dimension reduction using the Simulated Annealing technique. We propose a novel material detection method that consists of four steps: feature band selection, feature extraction, SVM (Support Vector Machine) learning, and target and specific region detection. It is a combination of the band ratio method and Simulated Annealing algorithm based on detection rate. The experimental results validate the effectiveness of the proposed feature selection and band ratio method.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.9-11
• /
• 2013

본 논문에서는 귀의 형태와 색을 통해서 질병을 자가진단 후 귀의 특정 부위를 자극하는 이침요법을 위한 시술 보조 시스템을 제안한다. 제안 시스템은 피시술자의 귀의 이미지 정보와 질병에 대한 정보를 처리하여 이침을 위한 혈자리를 귀 이미지에 표시해 주는 시스템을 구현하였다. 특히 귀를 인식하는 부분에 있어서, Haar-like feature와 Adaboost알고리즘을 사용하는 OpenCV내의 함수를 사용하였고 인식된 귀영역을 그리드 영역으로 나누고 질병에 대한 사전 정보에 따라서 그리드 영역내의 이침혈자리 시스템을 표시하는 시스템으로 구성하였다.

• The Korean Journal of Applied Statistics
• /
• v.37 no.3
• /
• pp.323-338
• /
• 2024

This study analyzes the Korean professional volleyball league and predict match outcomes using popular machine learning classification methods. Match data from the 2012/2013 to 2022/2023 seasons for both male and female leagues were collected, including match details. Two different data structures were applied to the models: Separating matches results into two teams and performance differentials between the home and away teams. These two data structures were applied to construct a total of four predictive models, encompassing both male and female leagues. As specific variable values used in the models are unavailable before the end of matches, the results of the most recent 3 to 4 matches, up until just before today's match, were preprocessed and utilized as variables. Logistc Regrssion, Decision Tree, Bagging, Random Forest, Xgboost, Adaboost, and Light GBM, were employed for classification, and the model employing Random Forest showed the highest predictive performance. The results indicated that while significant variables varied by gender and data structure, set success rate, blocking points scored, and the number of faults were consistently crucial. Notably, our win-loss prediction model's distinctiveness lies in its ability to provide pre-match forecasts rather than post-event predictions.

• Journal of Institute of Control, Robotics and Systems
• /
• v.15 no.5
• /
• pp.457-464
• /
• 2009

The weak classifier of AdaBoost algorithm is a central classification element that uses a single criterion separating positive and negative learning candidates. Finding the best criterion to separate two feature distributions influences learning capacity of the algorithm. A common way to classify the distributions is to use the mean value of the features. However, positive and negative distributions of Haar-like feature as an image descriptor are hard to classify by a single threshold. The poor classification ability of the single threshold also increases the number of boosting operations, and finally results in a poor classifier. This paper proposes a weak classifier that uses multiple criterions by adding a probabilistic criterion of the positive candidate distribution with the conventional mean classifier: the positive distribution has low variation and the values are closer to the mean while the negative distribution has large variation and values are widely spread. The difference in the variance for the positive and negative distributions is used as an additional criterion. In the learning procedure, we use a new classifier that provides a better classifier between them by selective switching between the mean and standard deviation. We call this new type of combined classifier the "Mixed Weak Classifier". The proposed weak classifier is more robust than the mean classifier alone and decreases the number of boosting operations to be converged.