• Journal of information and communication convergence engineering
• /
• v.5 no.3
• /
• pp.233-238
• /
• 2007

An approach to identify Chinese event types is proposed in this paper which combines a good feature selection policy and a Maximum Entropy (ME) model. The approach not only effectively alleviates the problem that classifier performs poorly on the small and difficult types, but improve overall performance. Experiments on the ACE2005 corpus show that performance is satisfying with the 83.5% macro - average F measure. The main characters and ideas of the approach are: (1) Optimal feature set is built for each type according to local feature selection, which fully ensures the performance of each type. (2) Positive and negative features are explicitly discriminated and combined by using one - sided metrics, which makes use of both features' advantages. (3) Wrapper methods are used to search new features and evaluate the various feature subsets to obtain the optimal feature subset.

• KIPS Transactions on Software and Data Engineering
• /
• v.2 no.1
• /
• pp.43-48
• /
• 2013

Adaboost is widely used for Haar-like feature boosting algorithm in Face Detection. It shows very effective performance on single distribution model. But when detecting front and side face images at same time, Adaboost shows it's limitation on multiple distribution data because it uses linear combination of basic classifier. This paper suggest the HDCT, modified decision tree algorithm for Haar-like features. We still tested the performance of HDCT compared with Adaboost on multiple distributed image recognition.

• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.1-13
• /
• 2015

As opinion mining in big data applications has been highlighted, a lot of research on unstructured data has made. Lots of social media on the Internet generate unstructured or semi-structured data every second and they are often made by natural or human languages we use in daily life. Many words in human languages have multiple meanings or senses. In this result, it is very difficult for computers to extract useful information from these datasets. Traditional web search engines are usually based on keyword search, resulting in incorrect search results which are far from users' intentions. Even though a lot of progress in enhancing the performance of search engines has made over the last years in order to provide users with appropriate results, there is still so much to improve it. Word sense disambiguation can play a very important role in dealing with natural language processing and is considered as one of the most difficult problems in this area. Major approaches to word sense disambiguation can be classified as knowledge-base, supervised corpus-based, and unsupervised corpus-based approaches. This paper presents a method which automatically generates a corpus for word sense disambiguation by taking advantage of examples in existing dictionaries and avoids expensive sense tagging processes. It experiments the effectiveness of the method based on Naïve Bayes Model, which is one of supervised learning algorithms, by using Korean standard unabridged dictionary and Sejong Corpus. Korean standard unabridged dictionary has approximately 57,000 sentences. Sejong Corpus has about 790,000 sentences tagged with part-of-speech and senses all together. For the experiment of this study, Korean standard unabridged dictionary and Sejong Corpus were experimented as a combination and separate entities using cross validation. Only nouns, target subjects in word sense disambiguation, were selected. 93,522 word senses among 265,655 nouns and 56,914 sentences from related proverbs and examples were additionally combined in the corpus. Sejong Corpus was easily merged with Korean standard unabridged dictionary because Sejong Corpus was tagged based on sense indices defined by Korean standard unabridged dictionary. Sense vectors were formed after the merged corpus was created. Terms used in creating sense vectors were added in the named entity dictionary of Korean morphological analyzer. By using the extended named entity dictionary, term vectors were extracted from the input sentences and then term vectors for the sentences were created. Given the extracted term vector and the sense vector model made during the pre-processing stage, the sense-tagged terms were determined by the vector space model based word sense disambiguation. In addition, this study shows the effectiveness of merged corpus from examples in Korean standard unabridged dictionary and Sejong Corpus. The experiment shows the better results in precision and recall are found with the merged corpus. This study suggests it can practically enhance the performance of internet search engines and help us to understand more accurate meaning of a sentence in natural language processing pertinent to search engines, opinion mining, and text mining. Naïve Bayes classifier used in this study represents a supervised learning algorithm and uses Bayes theorem. Naïve Bayes classifier has an assumption that all senses are independent. Even though the assumption of Naïve Bayes classifier is not realistic and ignores the correlation between attributes, Naïve Bayes classifier is widely used because of its simplicity and in practice it is known to be very effective in many applications such as text classification and medical diagnosis. However, further research need to be carried out to consider all possible combinations and/or partial combinations of all senses in a sentence. Also, the effectiveness of word sense disambiguation may be improved if rhetorical structures or morphological dependencies between words are analyzed through syntactic analysis.

• Journal of Korea Water Resources Association
• /
• v.51 no.6
• /
• pp.481-490
• /
• 2018

Recently, the spatiotemporal patterns of flood disasters have become more complex and unpredictable due to climate change. Flood hazard map including information on flood risk level has been widely used as an unstructured measure against flooding damages. In order to product a high-precision flood hazard map by combination of hydrologic and hydraulic modeling, huge digital information such as topography, geology, climate, landuse and various database related to social economic are required. However, in some areas, especially in developing countries, flood hazard mapping is difficult or impossible and its accuracy is insufficient because such data is lacking or inaccessible. Therefore, this study suggests a method to delineate large scale flood-prone area based on topographic factors produced by linear binary classifier and ROC (Receiver Operation Characteristics) using globally-available geographic data such as ASTER or SRTM. We applied the proposed methodology to five different countries: North Korea Bangladesh, Indonesia, Thailand and Myanmar. The results show that model performances on flood area detection ranges from 38% (Bangladesh) to 78% (Thailand). The flood-prone area detection based on the topographical factors has a great advantage in order to easily distinguish the large-scale inundation-potent area using only digital elevation model (DEM) for ungauged watersheds.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.11
• /
• pp.206-216
• /
• 2013

The emotion plays a critical role in human's daily life including learning, action, decision and communication. In this paper, emotion discrimination classifier is designed to reduce system complexity through reduced selection of dominant features from biosignals. The photoplethysmography(PPG), skin temperature, skin conductance, fontal and parietal electroencephalography(EEG) signals were measured during 4 types of movie watching associated with the induction of neutral, sad, fear joy emotions. The genetic algorithm with support vector machine(SVM) based fitness function was designed to determine dominant features among 24 parameters extracted from measured biosignals. It shows maximum classification accuracy of 96.4%, which is 17% higher than that of SVM alone. The minimum error features selected are the mean and NN50 of heart rate variability from PPG signal, the mean of PPG induced pulse transit time, the mean of skin resistance, and ${\delta}$ and ${\beta}$ frequency band powers of parietal EEG. The combination of parietal EEG, PPG, and skin resistance is recommendable in high accuracy instrumentation, while the combinational use of PPG and skin conductance(79% accuracy) is affordable in simplified instrumentation.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.107-119
• /
• 2023

The technology that recognizes a soldier's motion and movement status has recently attracted large attention as a combination of wearable technology and artificial intelligence, which is expected to upend the paradigm of troop management. The accuracy of state determination should be maintained at a high-end level to make sure of the expected vital functions both in a training situation; an evaluation and solution provision for each individual's motion, and in a combat situation; overall enhancement in managing troops. However, when input data is given as a timer series or sequence, existing feedforward networks would show overt limitations in maximizing classification performance. Since human behavior data (3-axis accelerations and 3-axis angular velocities) handled for military motion recognition requires the process of analyzing its time-dependent characteristics, this study proposes a high-performance data-driven classifier which utilizes the long-short term memory to identify the order dependence of acquired data, learning to classify eight representative military operations (Sitting, Standing, Walking, Running, Ascending, Descending, Low Crawl, and High Crawl). Since the accuracy is highly dependent on a network's learning conditions and variables, manual adjustment may neither be cost-effective nor guarantee optimal results during learning. Therefore, in this study, we optimized hyperparameters using Bayesian optimization for maximized generalization performance. As a result, the final architecture could reduce the error rate by 62.56% compared to the existing network with a similar number of learnable parameters, with the final accuracy of 98.39% for various military operations.

• Korean Journal of Radiology
• /
• v.22 no.3
• /
• pp.334-343
• /
• 2021

Objective: We aimed to develop a prediction model for diagnosing severe aortic stenosis (AS) using computed tomography (CT) radiomics features of aortic valve calcium (AVC) and machine learning (ML) algorithms. Materials and Methods: We retrospectively enrolled 408 patients who underwent cardiac CT between March 2010 and August 2017 and had echocardiographic examinations (240 patients with severe AS on echocardiography [the severe AS group] and 168 patients without severe AS [the non-severe AS group]). Data were divided into a training set (312 patients) and a validation set (96 patients). Using non-contrast-enhanced cardiac CT scans, AVC was segmented, and 128 radiomics features for AVC were extracted. After feature selection was performed with three ML algorithms (least absolute shrinkage and selection operator [LASSO], random forests [RFs], and eXtreme Gradient Boosting [XGBoost]), model classifiers for diagnosing severe AS on echocardiography were developed in combination with three different model classifier methods (logistic regression, RF, and XGBoost). The performance (c-index) of each radiomics prediction model was compared with predictions based on AVC volume and score. Results: The radiomics scores derived from LASSO were significantly different between the severe AS and non-severe AS groups in the validation set (median, 1.563 vs. 0.197, respectively, p < 0.001). A radiomics prediction model based on feature selection by LASSO + model classifier by XGBoost showed the highest c-index of 0.921 (95% confidence interval [CI], 0.869-0.973) in the validation set. Compared to prediction models based on AVC volume and score (c-indexes of 0.894 [95% CI, 0.815-0.948] and 0.899 [95% CI, 0.820-0.951], respectively), eight and three of the nine radiomics prediction models showed higher discrimination abilities for severe AS. However, the differences were not statistically significant (p > 0.05 for all). Conclusion: Models based on the radiomics features of AVC and ML algorithms may perform well for diagnosing severe AS, but the added value compared to AVC volume and score should be investigated further.

• Journal of Intelligence and Information Systems
• /
• v.14 no.2
• /
• pp.193-206
• /
• 2008

Medical diagnosis can be considered a classification task which classifies disease types from patient's condition data represented by a set of pre-defined attributes. This study proposes a hybrid genetic algorithm based classification method to develop classifiers for multidimensional pattern classification problems related with medical decision making. The classification problem can be solved by identifying separation boundaries which distinguish the various classes in the data pattern. The proposed method fits a finite number of regional agents to the data pattern by combining genetic algorithms and local adaptive operations. The local adaptive operations of an agent include expansion, avoidance and relocation, one of which is performed according to the agent's fitness value. The classifier system has been tested with well-known medical data sets from the UCI machine learning database, showing superior performance to other methods such as the nearest neighbor, decision tree, and neural networks.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.10 no.1
• /
• pp.38-45
• /
• 2017

Attacking of computer and network is increasing as information processing technology heavily depends on computer and network. To prevent the attack of system and network, host and network based intrusion detection system has developed. But previous rule based system has a lot of difficulties. For this reason demand for developing a intrusion detection system which detects and cope with the attack of system and network resource in real time. In this paper we develop a real time intrusion detection system which is combination of APEX and LS-SVM classifier. Proposed system is for nonlinear data and guarantees convergence. While real time processing system has its advantages, such as memory efficiency and allowing a new training data, it also has its disadvantages of inaccuracy compared to batch way. Therefore proposed real time intrusion detection system shows similar performance in accuracy compared to batch way intrusion detection system, it can be deployed on a commercial scale.

• Journal of the Korea Convergence Society
• /
• v.7 no.4
• /
• pp.1-7
• /
• 2016

Structural MRI(sMRI) imaging is used to extract morphometric features after Grey Matter (GM), White Matter (WM) for several univariate and multivariate method, and Cerebro-spinal Fluid (CSF) segmentation. A new approach is applied for the diagnosis of very mild to mild AD. We propose the classification method of Alzheimer disease patients from normal controls by combining morphometric features and Gaussian Mixture Models parameters along with MMSE (Mini Mental State Examination) score. The combined features are fed into Multi-kernel SVM classifier after getting rid of curse of dimensionality using principal component analysis. The experimenral results of the proposed diagnosis method yield up to 96% stratification accuracy with Multi-kernel SVM along with high sensitivity and specificity above 90%.