• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.6B
• /
• pp.597-603
• /
• 2006

The purpose of this study is to improve the short term rainfall forecast skill using neural network model that can deal with the non-linear behavior between satellite data and ground observation, and minimize the flood damage. To overcome the geographical limitation of Korean peninsula and get the long forecast lead time of 3 to 6 hour, the developed rainfall forecast model took satellite imageries and wide range AWS data. The architecture of neural network model is a multi-layer neural network which consists of one input layer, one hidden layer, and one output layer. Neural network is trained using a momentum back propagation algorithm. Flood was estimated using rainfall forecasts. We developed a dynamic flood inundation model which is associated with 1-dimensional flood routing model. Therefore the model can forecast flood aspect in a protected lowland by levee failure of river. In the case of multiple levee breaks at main stream and tributaries, the developed flood inundation model can estimate flood level in a river and inundation level and area in a protected lowland simultaneously.

• Journal of Intelligence and Information Systems
• /
• v.22 no.1
• /
• pp.139-157
• /
• 2016

Bankruptcy involves considerable costs, so it can have significant effects on a country's economy. Thus, bankruptcy prediction is an important issue. Over the past several decades, many researchers have addressed topics associated with bankruptcy prediction. Early research on bankruptcy prediction employed conventional statistical methods such as univariate analysis, discriminant analysis, multiple regression, and logistic regression. Later on, many studies began utilizing artificial intelligence techniques such as inductive learning, neural networks, and case-based reasoning. Currently, ensemble models are being utilized to enhance the accuracy of bankruptcy prediction. Ensemble classification involves combining multiple classifiers to obtain more accurate predictions than those obtained using individual models. Ensemble learning techniques are known to be very useful for improving the generalization ability of the classifier. Base classifiers in the ensemble must be as accurate and diverse as possible in order to enhance the generalization ability of an ensemble model. Commonly used methods for constructing ensemble classifiers include bagging, boosting, and random subspace. The random subspace method selects a random feature subset for each classifier from the original feature space to diversify the base classifiers of an ensemble. Each ensemble member is trained by a randomly chosen feature subspace from the original feature set, and predictions from each ensemble member are combined by an aggregation method. The k-nearest neighbors (KNN) classifier is robust with respect to variations in the dataset but is very sensitive to changes in the feature space. For this reason, KNN is a good classifier for the random subspace method. The KNN random subspace ensemble model has been shown to be very effective for improving an individual KNN model. The k parameter of KNN base classifiers and selected feature subsets for base classifiers play an important role in determining the performance of the KNN ensemble model. However, few studies have focused on optimizing the k parameter and feature subsets of base classifiers in the ensemble. This study proposed a new ensemble method that improves upon the performance KNN ensemble model by optimizing both k parameters and feature subsets of base classifiers. A genetic algorithm was used to optimize the KNN ensemble model and improve the prediction accuracy of the ensemble model. The proposed model was applied to a bankruptcy prediction problem by using a real dataset from Korean companies. The research data included 1800 externally non-audited firms that filed for bankruptcy (900 cases) or non-bankruptcy (900 cases). Initially, the dataset consisted of 134 financial ratios. Prior to the experiments, 75 financial ratios were selected based on an independent sample t-test of each financial ratio as an input variable and bankruptcy or non-bankruptcy as an output variable. Of these, 24 financial ratios were selected by using a logistic regression backward feature selection method. The complete dataset was separated into two parts: training and validation. The training dataset was further divided into two portions: one for the training model and the other to avoid overfitting. The prediction accuracy against this dataset was used to determine the fitness value in order to avoid overfitting. The validation dataset was used to evaluate the effectiveness of the final model. A 10-fold cross-validation was implemented to compare the performances of the proposed model and other models. To evaluate the effectiveness of the proposed model, the classification accuracy of the proposed model was compared with that of other models. The Q-statistic values and average classification accuracies of base classifiers were investigated. The experimental results showed that the proposed model outperformed other models, such as the single model and random subspace ensemble model.

• Journal of Intelligence and Information Systems
• /
• v.27 no.3
• /
• pp.175-197
• /
• 2021

Recently, with the development of deep learning technology, research on unstructured data analysis is being actively conducted, and it is showing remarkable results in various fields such as classification, summary, and generation. Among various text analysis fields, text classification is the most widely used technology in academia and industry. Text classification includes binary class classification with one label among two classes, multi-class classification with one label among several classes, and multi-label classification with multiple labels among several classes. In particular, multi-label classification requires a different training method from binary class classification and multi-class classification because of the characteristic of having multiple labels. In addition, since the number of labels to be predicted increases as the number of labels and classes increases, there is a limitation in that performance improvement is difficult due to an increase in prediction difficulty. To overcome these limitations, (i) compressing the initially given high-dimensional label space into a low-dimensional latent label space, (ii) after performing training to predict the compressed label, (iii) restoring the predicted label to the high-dimensional original label space, research on label embedding is being actively conducted. Typical label embedding techniques include Principal Label Space Transformation (PLST), Multi-Label Classification via Boolean Matrix Decomposition (MLC-BMaD), and Bayesian Multi-Label Compressed Sensing (BML-CS). However, since these techniques consider only the linear relationship between labels or compress the labels by random transformation, it is difficult to understand the non-linear relationship between labels, so there is a limitation in that it is not possible to create a latent label space sufficiently containing the information of the original label. Recently, there have been increasing attempts to improve performance by applying deep learning technology to label embedding. Label embedding using an autoencoder, a deep learning model that is effective for data compression and restoration, is representative. However, the traditional autoencoder-based label embedding has a limitation in that a large amount of information loss occurs when compressing a high-dimensional label space having a myriad of classes into a low-dimensional latent label space. This can be found in the gradient loss problem that occurs in the backpropagation process of learning. To solve this problem, skip connection was devised, and by adding the input of the layer to the output to prevent gradient loss during backpropagation, efficient learning is possible even when the layer is deep. Skip connection is mainly used for image feature extraction in convolutional neural networks, but studies using skip connection in autoencoder or label embedding process are still lacking. Therefore, in this study, we propose an autoencoder-based label embedding methodology in which skip connections are added to each of the encoder and decoder to form a low-dimensional latent label space that reflects the information of the high-dimensional label space well. In addition, the proposed methodology was applied to actual paper keywords to derive the high-dimensional keyword label space and the low-dimensional latent label space. Using this, we conducted an experiment to predict the compressed keyword vector existing in the latent label space from the paper abstract and to evaluate the multi-label classification by restoring the predicted keyword vector back to the original label space. As a result, the accuracy, precision, recall, and F1 score used as performance indicators showed far superior performance in multi-label classification based on the proposed methodology compared to traditional multi-label classification methods. This can be seen that the low-dimensional latent label space derived through the proposed methodology well reflected the information of the high-dimensional label space, which ultimately led to the improvement of the performance of the multi-label classification itself. In addition, the utility of the proposed methodology was identified by comparing the performance of the proposed methodology according to the domain characteristics and the number of dimensions of the latent label space.

• Journal of Korea Water Resources Association
• /
• v.57 no.3
• /
• pp.151-164
• /
• 2024

In water treatment plants supplying potable water, the management of chlorine concentration in water treatment processes involving pre-chlorination or intermediate chlorination requires process control. To address this, research has been conducted on water quality prediction techniques utilizing AI technology. This study developed an AI-based predictive model for automating the process control of chlorine disinfection, targeting the prediction of residual chlorine concentration downstream of sedimentation basins in water treatment processes. The AI-based model, which learns from past water quality observation data to predict future water quality, offers a simpler and more efficient approach compared to complex physicochemical and biological water quality models. The model was tested by predicting the residual chlorine concentration downstream of the sedimentation basins at Plant, using multiple regression models and AI-based models like Random Forest and LSTM, and the results were compared. For optimal prediction of residual chlorine concentration, the input-output structure of the AI model included the residual chlorine concentration upstream of the sedimentation basin, turbidity, pH, water temperature, electrical conductivity, inflow of raw water, alkalinity, NH₃, etc. as independent variables, and the desired residual chlorine concentration of the effluent from the sedimentation basin as the dependent variable. The independent variables were selected from observable data at the water treatment plant, which are influential on the residual chlorine concentration downstream of the sedimentation basin. The analysis showed that, for Plant, the model based on Random Forest had the lowest error compared to multiple regression models, neural network models, model trees, and other Random Forest models. The optimal predicted residual chlorine concentration downstream of the sedimentation basin presented in this study is expected to enable real-time control of chlorine dosing in previous treatment stages, thereby enhancing water treatment efficiency and reducing chemical costs.

• Proceedings of the Korea Contents Association Conference
• /
• 2003.05a
• /
• pp.344-350
• /
• 2003

In this paper, we propose a novel sharing method ordering the events occurring between users collaborated with the common telecomputing environment. We realize the sharing method with multimedia data to improve the coworking effect using teleprocessing network. This sharing method advances the efficiency of communicating projects such as remote education, tele-conference, and co-authoring of multimedia contents by offering conveniences of presentation, group authoring, common management, and transient event productions of the users. As for the conventional sharing white board system, all the multimedia contents segments should be authored by the exclusive program, and we cannot use any existing contents or program. Moreover we suffer from the problem that ordering error occurs in the teleprocessing operation because we do not have any line-up technology for the input ordering of commands. Therefore we develop a method of retrieving input and output events from the windows system and the message hooking technology which transmits between programs in the operating system In addition, we realize the allocation technology of the processing results for all sharing users of the distributed computing environment without any error. Our sharing technology should contribute to improve the face-to-face coworking efficiency for multimedia contents authoring, common blackboard system in the area of remote educations, and presentation display in visual conference.

• Asia pacific journal of information systems
• /
• v.19 no.2
• /
• pp.139-155
• /
• 2009

For the last few decades, many studies have tried to explore and unveil venture companies' success factors and unique features in order to identify the sources of such companies' competitive advantages over their rivals. Such venture companies have shown tendency to give high returns for investors generally making the best use of information technology. For this reason, many venture companies are keen on attracting avid investors' attention. Investors generally make their investment decisions by carefully examining the evaluation criteria of the alternatives. To them, credit rating information provided by international rating agencies, such as Standard and Poor's, Moody's and Fitch is crucial source as to such pivotal concerns as companies stability, growth, and risk status. But these types of information are generated only for the companies issuing corporate bonds, not venture companies. Therefore, this study proposes a method for evaluating venture businesses by presenting our recent empirical results using financial data of Korean venture companies listed on KOSDAQ in Korea exchange. In addition, this paper used multi-class SVM for the prediction of DEA-based efficiency rating for venture businesses, which was derived from our proposed method. Our approach sheds light on ways to locate efficient companies generating high level of profits. Above all, in determining effective ways to evaluate a venture firm's efficiency, it is important to understand the major contributing factors of such efficiency. Therefore, this paper is constructed on the basis of following two ideas to classify which companies are more efficient venture companies: i) making DEA based multi-class rating for sample companies and ii) developing multi-class SVM-based efficiency prediction model for classifying all companies. First, the Data Envelopment Analysis(DEA) is a non-parametric multiple input-output efficiency technique that measures the relative efficiency of decision making units(DMUs) using a linear programming based model. It is non-parametric because it requires no assumption on the shape or parameters of the underlying production function. DEA has been already widely applied for evaluating the relative efficiency of DMUs. Recently, a number of DEA based studies have evaluated the efficiency of various types of companies, such as internet companies and venture companies. It has been also applied to corporate credit ratings. In this study we utilized DEA for sorting venture companies by efficiency based ratings. The Support Vector Machine(SVM), on the other hand, is a popular technique for solving data classification problems. In this paper, we employed SVM to classify the efficiency ratings in IT venture companies according to the results of DEA. The SVM method was first developed by Vapnik (1995). As one of many machine learning techniques, SVM is based on a statistical theory. Thus far, the method has shown good performances especially in generalizing capacity in classification tasks, resulting in numerous applications in many areas of business, SVM is basically the algorithm that finds the maximum margin hyperplane, which is the maximum separation between classes. According to this method, support vectors are the closest to the maximum margin hyperplane. If it is impossible to classify, we can use the kernel function. In the case of nonlinear class boundaries, we can transform the inputs into a high-dimensional feature space, This is the original input space and is mapped into a high-dimensional dot-product space. Many studies applied SVM to the prediction of bankruptcy, the forecast a financial time series, and the problem of estimating credit rating, In this study we employed SVM for developing data mining-based efficiency prediction model. We used the Gaussian radial function as a kernel function of SVM. In multi-class SVM, we adopted one-against-one approach between binary classification method and two all-together methods, proposed by Weston and Watkins(1999) and Crammer and Singer(2000), respectively. In this research, we used corporate information of 154 companies listed on KOSDAQ market in Korea exchange. We obtained companies' financial information of 2005 from the KIS(Korea Information Service, Inc.). Using this data, we made multi-class rating with DEA efficiency and built multi-class prediction model based data mining. Among three manners of multi-classification, the hit ratio of the Weston and Watkins method is the best in the test data set. In multi classification problems as efficiency ratings of venture business, it is very useful for investors to know the class with errors, one class difference, when it is difficult to find out the accurate class in the actual market. So we presented accuracy results within 1-class errors, and the Weston and Watkins method showed 85.7% accuracy in our test samples. We conclude that the DEA based multi-class approach in venture business generates more information than the binary classification problem, notwithstanding its efficiency level. We believe this model can help investors in decision making as it provides a reliably tool to evaluate venture companies in the financial domain. For the future research, we perceive the need to enhance such areas as the variable selection process, the parameter selection of kernel function, the generalization, and the sample size of multi-class.

• Journal of Intelligence and Information Systems
• /
• v.22 no.2
• /
• pp.127-142
• /
• 2016

Deep learning model is a kind of neural networks that allows multiple hidden layers. There are various deep learning architectures such as convolutional neural networks, deep belief networks and recurrent neural networks. Those have been applied to fields like computer vision, automatic speech recognition, natural language processing, audio recognition and bioinformatics where they have been shown to produce state-of-the-art results on various tasks. Among those architectures, convolutional neural networks and recurrent neural networks are classified as the supervised learning model. And in recent years, those supervised learning models have gained more popularity than unsupervised learning models such as deep belief networks, because supervised learning models have shown fashionable applications in such fields mentioned above. Deep learning models can be trained with backpropagation algorithm. Backpropagation is an abbreviation for "backward propagation of errors" and a common method of training artificial neural networks used in conjunction with an optimization method such as gradient descent. The method calculates the gradient of an error function with respect to all the weights in the network. The gradient is fed to the optimization method which in turn uses it to update the weights, in an attempt to minimize the error function. Convolutional neural networks use a special architecture which is particularly well-adapted to classify images. Using this architecture makes convolutional networks fast to train. This, in turn, helps us train deep, muti-layer networks, which are very good at classifying images. These days, deep convolutional networks are used in most neural networks for image recognition. Convolutional neural networks use three basic ideas: local receptive fields, shared weights, and pooling. By local receptive fields, we mean that each neuron in the first(or any) hidden layer will be connected to a small region of the input(or previous layer's) neurons. Shared weights mean that we're going to use the same weights and bias for each of the local receptive field. This means that all the neurons in the hidden layer detect exactly the same feature, just at different locations in the input image. In addition to the convolutional layers just described, convolutional neural networks also contain pooling layers. Pooling layers are usually used immediately after convolutional layers. What the pooling layers do is to simplify the information in the output from the convolutional layer. Recent convolutional network architectures have 10 to 20 hidden layers and billions of connections between units. Training deep learning networks has taken weeks several years ago, but thanks to progress in GPU and algorithm enhancement, training time has reduced to several hours. Neural networks with time-varying behavior are known as recurrent neural networks or RNNs. A recurrent neural network is a class of artificial neural network where connections between units form a directed cycle. This creates an internal state of the network which allows it to exhibit dynamic temporal behavior. Unlike feedforward neural networks, RNNs can use their internal memory to process arbitrary sequences of inputs. Early RNN models turned out to be very difficult to train, harder even than deep feedforward networks. The reason is the unstable gradient problem such as vanishing gradient and exploding gradient. The gradient can get smaller and smaller as it is propagated back through layers. This makes learning in early layers extremely slow. The problem actually gets worse in RNNs, since gradients aren't just propagated backward through layers, they're propagated backward through time. If the network runs for a long time, that can make the gradient extremely unstable and hard to learn from. It has been possible to incorporate an idea known as long short-term memory units (LSTMs) into RNNs. LSTMs make it much easier to get good results when training RNNs, and many recent papers make use of LSTMs or related ideas.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.44 no.6 s.360
• /
• pp.40-47
• /
• 2007

In this paper, we propose and analyze the Adaptive Modulation System with optimal Turbo Coded V-BLAST(Vertical-Bell-lab Layered Space-Time) technique that adopts the extrinsic information from MAP (Maximum A Posteriori) Decoder with Iterative Decoding as a priori probability in two decoding procedures of V-BLAST; the ordering and the slicing. Also, we consider and compare the Adaptive Modulation System using conventional Turbo Coded V-BLAST technique that is simply combined V-BLAST with Turbo Coding scheme and the Adaptive Modulation System using conventional Turbo Coded V-BLAST technique that is decoded by the ML (Maximum Likelihood) decoding algorithm. We observe a throughput performance and a complexity. As a result of a performance comparison of each system, it has been proved that the complexity of the proposed decoding algorithm is lower than that of the ML decoding algorithm but is higher than that of the conventional V-BLAST decoding algorithm. however, we can see that the proposed system achieves a better throughput performance than the conventional system in the whole SNR (Signal to Noise Ratio) range. And the result shows that the proposed system achieves a throughput performance close to the ML decoded system. Specifically, a simulation shows that the maximum throughput improvement in each MIMO scheme is respectively about 350 kbps, 460 kbps, and 740 kbps compared to the conventional system. It is suggested that the effect of the proposed decoding algorithm accordingly gets higher as the number of system antenna increases.

• Journal of Intelligence and Information Systems
• /
• v.18 no.3
• /
• pp.185-202
• /
• 2012

.Since the value of information has been realized in the information society, the usage and collection of information has become important. A facial expression that contains thousands of information as an artistic painting can be described in thousands of words. Followed by the idea, there has recently been a number of attempts to provide customers and companies with an intelligent service, which enables the perception of human emotions through one's facial expressions. For example, MIT Media Lab, the leading organization in this research area, has developed the human emotion prediction model, and has applied their studies to the commercial business. In the academic area, a number of the conventional methods such as Multiple Regression Analysis (MRA) or Artificial Neural Networks (ANN) have been applied to predict human emotion in prior studies. However, MRA is generally criticized because of its low prediction accuracy. This is inevitable since MRA can only explain the linear relationship between the dependent variables and the independent variable. To mitigate the limitations of MRA, some studies like Jung and Kim (2012) have used ANN as the alternative, and they reported that ANN generated more accurate prediction than the statistical methods like MRA. However, it has also been criticized due to over fitting and the difficulty of the network design (e.g. setting the number of the layers and the number of the nodes in the hidden layers). Under this background, we propose a novel model using Support Vector Regression (SVR) in order to increase the prediction accuracy. SVR is an extensive version of Support Vector Machine (SVM) designated to solve the regression problems. The model produced by SVR only depends on a subset of the training data, because the cost function for building the model ignores any training data that is close (within a threshold ${\varepsilon}$) to the model prediction. Using SVR, we tried to build a model that can measure the level of arousal and valence from the facial features. To validate the usefulness of the proposed model, we collected the data of facial reactions when providing appropriate visual stimulating contents, and extracted the features from the data. Next, the steps of the preprocessing were taken to choose statistically significant variables. In total, 297 cases were used for the experiment. As the comparative models, we also applied MRA and ANN to the same data set. For SVR, we adopted '${\varepsilon}$-insensitive loss function', and 'grid search' technique to find the optimal values of the parameters like C, d, ${\sigma}^2$, and ${\varepsilon}$. In the case of ANN, we adopted a standard three-layer backpropagation network, which has a single hidden layer. The learning rate and momentum rate of ANN were set to 10%, and we used sigmoid function as the transfer function of hidden and output nodes. We performed the experiments repeatedly by varying the number of nodes in the hidden layer to n/2, n, 3n/2, and 2n, where n is the number of the input variables. The stopping condition for ANN was set to 50,000 learning events. And, we used MAE (Mean Absolute Error) as the measure for performance comparison. From the experiment, we found that SVR achieved the highest prediction accuracy for the hold-out data set compared to MRA and ANN. Regardless of the target variables (the level of arousal, or the level of positive / negative valence), SVR showed the best performance for the hold-out data set. ANN also outperformed MRA, however, it showed the considerably lower prediction accuracy than SVR for both target variables. The findings of our research are expected to be useful to the researchers or practitioners who are willing to build the models for recognizing human emotions.