• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.105-122
• /
• 2019

Dimensionality reduction is one of the methods to handle big data in text mining. For dimensionality reduction, we should consider the density of data, which has a significant influence on the performance of sentence classification. It requires lots of computations for data of higher dimensions. Eventually, it can cause lots of computational cost and overfitting in the model. Thus, the dimension reduction process is necessary to improve the performance of the model. Diverse methods have been proposed from only lessening the noise of data like misspelling or informal text to including semantic and syntactic information. On top of it, the expression and selection of the text features have impacts on the performance of the classifier for sentence classification, which is one of the fields of Natural Language Processing. The common goal of dimension reduction is to find latent space that is representative of raw data from observation space. Existing methods utilize various algorithms for dimensionality reduction, such as feature extraction and feature selection. In addition to these algorithms, word embeddings, learning low-dimensional vector space representations of words, that can capture semantic and syntactic information from data are also utilized. For improving performance, recent studies have suggested methods that the word dictionary is modified according to the positive and negative score of pre-defined words. The basic idea of this study is that similar words have similar vector representations. Once the feature selection algorithm selects the words that are not important, we thought the words that are similar to the selected words also have no impacts on sentence classification. This study proposes two ways to achieve more accurate classification that conduct selective word elimination under specific regulations and construct word embedding based on Word2Vec embedding. To select words having low importance from the text, we use information gain algorithm to measure the importance and cosine similarity to search for similar words. First, we eliminate words that have comparatively low information gain values from the raw text and form word embedding. Second, we select words additionally that are similar to the words that have a low level of information gain values and make word embedding. In the end, these filtered text and word embedding apply to the deep learning models; Convolutional Neural Network and Attention-Based Bidirectional LSTM. This study uses customer reviews on Kindle in Amazon.com, IMDB, and Yelp as datasets, and classify each data using the deep learning models. The reviews got more than five helpful votes, and the ratio of helpful votes was over 70% classified as helpful reviews. Also, Yelp only shows the number of helpful votes. We extracted 100,000 reviews which got more than five helpful votes using a random sampling method among 750,000 reviews. The minimal preprocessing was executed to each dataset, such as removing numbers and special characters from text data. To evaluate the proposed methods, we compared the performances of Word2Vec and GloVe word embeddings, which used all the words. We showed that one of the proposed methods is better than the embeddings with all the words. By removing unimportant words, we can get better performance. However, if we removed too many words, it showed that the performance was lowered. For future research, it is required to consider diverse ways of preprocessing and the in-depth analysis for the co-occurrence of words to measure similarity values among words. Also, we only applied the proposed method with Word2Vec. Other embedding methods such as GloVe, fastText, ELMo can be applied with the proposed methods, and it is possible to identify the possible combinations between word embedding methods and elimination methods.

• Korean Journal of Environment and Ecology
• /
• v.35 no.5
• /
• pp.558-568
• /
• 2021

Poor supervision and tourism activities have resulted in forest degradation in islands in Korea. Since the southern coastal region of the Korean peninsula was originally dominated by warm-temperate evergreen broad-leaved forests, it is desirable to restore forests in this region to their original vegetation. In this study, we identified suitable areas to be restored as evergreen broad-leaved forests by analyzing the environmental factors of existing evergreen broad-leaved forests in the islands of Jeollanam-do. We classified forest lands in the study area into six vegetation types from Sentinel-2 satellite images using a deep learning algorithm and analyzed the tolerance ranges of existing evergreen broad-leaved forests by measuring the locational, topographic, and climatic attributes of the classified vegetation types. Results showed that evergreen broad-leaved forests were distributed more in areas with a high altitudes and steep slope, where human intervention was relatively low. The human intervention has led to a higher distribution of evergreen broad-leaved forests in areas with lower annual average temperature, which was an unexpected but understandable result because an area with higher altitude has a lower temperature. Of the environmental factors, latitude and average temperature in the coldest month (January) were relatively less contaminated by the effects of human intervention, thus enabling the identification of suitable restoration areas of the evergreen broad-leaved forests. The tolerance range analysis of evergreen broad-leaved forests showed that they mainly grew in areas south of the latitude of 34.7° and a monthly average temperature of 1.7℃ or higher in the coldest month. Therefore, we predicted the areas meeting these criteria to be suitable for restoring evergreen broad-leaved forests. The suitable areas cover 614.5 km², which occupies 59.0% of the total forest lands on the islands of Jeollanamdo, and 73% of actual forests that exclude agricultural and other non-restorable forest lands. The findings of this study can help forest managers prepare a restoration plan and budget for island forests.

• Journal of the Korean Society of Radiology
• /
• v.84 no.5
• /
• pp.1123-1133
• /
• 2023

Purpose Our study aimed to evaluate the association between automated quantified body composition on CT and pulmonary function or quantitative lung features in patients with chronic obstructive pulmonary disease (COPD). Materials and Methods A total of 290 patients with COPD were enrolled in this study. The volume of muscle and subcutaneous fat, area of muscle and subcutaneous fat at T12, and bone attenuation at T12 were obtained from chest CT using a deep learning-based body segmentation algorithm. Parametric response mapping-derived emphysema (PRM^emph), PRM-derived functional small airway disease (PRM^fSAD), and airway wall thickness (AWT)-Pi10 were quantitatively assessed. The association between body composition and outcomes was evaluated using Pearson's correlation analysis. Results The volume and area of muscle and subcutaneous fat were negatively associated with PRM^emph and PRM^fSAD (p < 0.05). Bone density at T12 was negatively associated with PRM^emph (r = -0.1828, p = 0.002). The volume and area of subcutaneous fat and bone density at T12 were positively correlated with AWT-Pi10 (r = 0.1287, p = 0.030; r = 0.1668, p = 0.005; r = 0.1279, p = 0.031). However, muscle volume was negatively correlated with the AWT-Pi10 (r = -0.1966, p = 0.001). Muscle volume was significantly associated with pulmonary function (p < 0.001). Conclusion Body composition, automatically assessed using chest CT, is associated with the phenotype and severity of COPD.

• Korean Journal of Remote Sensing
• /
• v.40 no.4
• /
• pp.387-396
• /
• 2024

Most very high-resolution (VHR) satellite images provide rational polynomial coefficients (RPC) data to facilitate the transformation between ground coordinates and image coordinates. However, initial RPC often contains geometric errors, necessitating correction through matching with ground control points (GCPs). A GCP chip is a small image patch extracted from an orthorectified image together with height information of the center point, which can be directly used for geometric correction. Many studies have focused on area-based matching methods to accurately align GCP chips with VHR satellite images. In cases with seasonal differences or changed areas, edge-based algorithms are often used for matching due to the difficulty of relying solely on pixel values. However, traditional edge extraction algorithms,such as canny edge detectors, require appropriate threshold settings tailored to the spectral characteristics of satellite images. Therefore, this study utilizes deep learning-based edge information that is insensitive to the regional characteristics of satellite images for matching. Specifically,we use a pretrained pixel difference network (PiDiNet) to generate the edge maps for both satellite images and GCP chips. These edge maps are then used as input for normalized cross-correlation (NCC) and relative edge cross-correlation (RECC) to identify the peak points with the highest correlation between the two edge maps. To remove mismatched pairs and thus obtain the bias-compensated RPC, we iteratively apply the data snooping. Finally, we compare the results qualitatively and quantitatively with those obtained from traditional NCC and RECC methods. The PiDiNet network approach achieved high matching accuracy with root mean square error (RMSE) values ranging from 0.3 to 0.9 pixels. However, the PiDiNet-generated edges were thicker compared to those from the canny method, leading to slightly lower registration accuracy in some images. Nevertheless, PiDiNet consistently produced characteristic edge information, allowing for successful matching even in challenging regions. This study demonstrates that improving the robustness of edge-based registration methods can facilitate effective registration across diverse regions.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.7
• /
• pp.622-629
• /
• 2019

Recently, the government is taking new approaches to change the fact that the accident rate and accident death rate of the construction industry account for a high percentage of the whole industry. Especially, it is investing heavily in the development of construction technology that is fused with ICT technology in line with the current trend of the 4th Industrial Revolution. In order to cope with this situation, this paper proposed a concept to recognize and share the work situation information between the construction machine driver and the surrounding worker to enhance the safety in the place where construction machines are operated. In order to realize the part of the concept, we applied image processing technology using camera based on artificial intelligence to earth-moving work. Especially, we implemented an algorithm that can recognize the surrounding worker's circumstance and identify the risk situation through the experiment using the compaction equipment. and image processing algorithm based on YOLO-v3. This algorithm processes 15.06 frames per second in video and can recognize danger situation around construction machine with accuracy of 90.48%. We will contribute to the prevention of safety accidents at the construction site by utilizing this technology in the future.

• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.26 no.4
• /
• pp.17-34
• /
• 2023

Camera trapping has been used as a non-invasive survey method that minimizes anthropogenic disturbance to ecosystems. Nevertheless, it is labor-intensive and time-consuming, requiring researchers to quantify species and populations. In this study, we aimed to improve the preprocessing of camera trapping data by utilizing an object detection algorithm. Wildlife monitoring using unmanned sensor cameras was conducted in a forested urban forest and a green space on a university campus in Cheonan City, Chungcheongnam-do, Korea. The collected camera trapping data were classified by a researcher to identify the occurrence of species. The data was then used to test the performance of the YOLO-X object detection algorithm for wildlife detection. The camera trapping resulted in 10,500 images of the urban forest and 51,974 images of green spaces on campus. Out of the total 62,474 images, 52,993 images (84.82%) were found to be false positives, while 9,481 images (15.18%) were found to contain wildlife. As a result of wildlife monitoring, 19 species of birds, 5 species of mammals, and 1 species of reptile were observed within the study area. In addition, there were statistically significant differences in the frequency of occurrence of the following species according to the type of urban greenery: Parus varius(t = -3.035, p < 0.01), Parus major(t = 2.112, p < 0.05), Passer montanus(t = 2.112, p < 0.05), Paradoxornis webbianus(t = 2.112, p < 0.05), Turdus hortulorum(t = -4.026, p < 0.001), and Sitta europaea(t = -2.189, p < 0.05). The detection performance of the YOLO-X model for wildlife occurrence was analyzed, and it successfully classified 94.2% of the camera trapping data. In particular, the number of true positive predictions was 7,809 images and the number of false negative predictions was 51,044 images. In this study, the object detection algorithm YOLO-X model was used to detect the presence of wildlife in the camera trapping data. In this study, the YOLO-X model was used with a filter activated to detect 10 specific animal taxa out of the 80 classes trained on the COCO dataset, without any additional training. In future studies, it is necessary to create and apply training data for key occurrence species to make the model suitable for wildlife monitoring.

• Journal of Intelligence and Information Systems
• /
• v.23 no.4
• /
• pp.147-168
• /
• 2017

There have been many studies on accurate stock market forecasting in academia for a long time, and now there are also various forecasting models using various techniques. Recently, many attempts have been made to predict the stock index using various machine learning methods including Deep Learning. Although the fundamental analysis and the technical analysis method are used for the analysis of the traditional stock investment transaction, the technical analysis method is more useful for the application of the short-term transaction prediction or statistical and mathematical techniques. Most of the studies that have been conducted using these technical indicators have studied the model of predicting stock prices by binary classification - rising or falling - of stock market fluctuations in the future market (usually next trading day). However, it is also true that this binary classification has many unfavorable aspects in predicting trends, identifying trading signals, or signaling portfolio rebalancing. In this study, we try to predict the stock index by expanding the stock index trend (upward trend, boxed, downward trend) to the multiple classification system in the existing binary index method. In order to solve this multi-classification problem, a technique such as Multinomial Logistic Regression Analysis (MLOGIT), Multiple Discriminant Analysis (MDA) or Artificial Neural Networks (ANN) we propose an optimization model using Genetic Algorithm as a wrapper for improving the performance of this model using Multi-classification Support Vector Machines (MSVM), which has proved to be superior in prediction performance. In particular, the proposed model named GA-MSVM is designed to maximize model performance by optimizing not only the kernel function parameters of MSVM, but also the optimal selection of input variables (feature selection) as well as instance selection. In order to verify the performance of the proposed model, we applied the proposed method to the real data. The results show that the proposed method is more effective than the conventional multivariate SVM, which has been known to show the best prediction performance up to now, as well as existing artificial intelligence / data mining techniques such as MDA, MLOGIT, CBR, and it is confirmed that the prediction performance is better than this. Especially, it has been confirmed that the 'instance selection' plays a very important role in predicting the stock index trend, and it is confirmed that the improvement effect of the model is more important than other factors. To verify the usefulness of GA-MSVM, we applied it to Korea's real KOSPI200 stock index trend forecast. Our research is primarily aimed at predicting trend segments to capture signal acquisition or short-term trend transition points. The experimental data set includes technical indicators such as the price and volatility index (2004 ~ 2017) and macroeconomic data (interest rate, exchange rate, S&P 500, etc.) of KOSPI200 stock index in Korea. Using a variety of statistical methods including one-way ANOVA and stepwise MDA, 15 indicators were selected as candidate independent variables. The dependent variable, trend classification, was classified into three states: 1 (upward trend), 0 (boxed), and -1 (downward trend). 70% of the total data for each class was used for training and the remaining 30% was used for verifying. To verify the performance of the proposed model, several comparative model experiments such as MDA, MLOGIT, CBR, ANN and MSVM were conducted. MSVM has adopted the One-Against-One (OAO) approach, which is known as the most accurate approach among the various MSVM approaches. Although there are some limitations, the final experimental results demonstrate that the proposed model, GA-MSVM, performs at a significantly higher level than all comparative models.

• Journal of Internet Computing and Services
• /
• v.23 no.3
• /
• pp.35-45
• /
• 2022

Even in recent years, treatment of first-aid patients is still often delayed due to a shortage of medical resources in marginalized areas. Research on automating the analysis of medical data to solve the problems of inaccessibility for medical services and shortage of medical personnel is ongoing. Computer vision-based medical inspection automation requires a lot of cost in data collection and labeling for training purposes. These problems stand out in the works of classifying lesion that are rare, or pathological features and pathogenesis that are difficult to clearly define visually. Anomaly detection is attracting as a method that can significantly reduce the cost of data collection by adopting an unsupervised learning strategy. In this paper, we propose methods for detecting abnormal images on chest X-RAY images as follows based on existing anomaly detection techniques. (1) Normalize the brightness range of medical images resampled as optimal resolution. (2) Some feature vectors with high representative power are selected in set of patch features extracted as intermediate-level from lesion-free images. (3) Measure the difference from the feature vectors of lesion-free data selected based on the nearest neighbor search algorithm. The proposed system can simultaneously perform anomaly classification and localization for each image. In this paper, the anomaly detection performance of the proposed system for chest X-RAY images of PA projection is measured and presented by detailed conditions. We demonstrate effect of anomaly detection for medical images by showing 0.705 classification AUROC for random subset extracted from the PadChest dataset. The proposed system can be usefully used to improve the clinical diagnosis workflow of medical institutions, and can effectively support early diagnosis in medically poor area.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.12
• /
• pp.29-40
• /
• 2022

In this paper, we studied a system that detects and analyzes the pathological features of diabetic retinopathy using Mask R-CNN and a Random Forest classifier. Those are one of the deep learning techniques and automatically diagnoses diabetic retinopathy. Diabetic retinopathy can be diagnosed through fundus images taken with special equipment. Brightness, color tone, and contrast may vary depending on the device. Research and development of an automatic diagnosis system using artificial intelligence to help ophthalmologists make medical judgments possible. This system detects pathological features such as microvascular perfusion and retinal hemorrhage using the Mask R-CNN technique. It also diagnoses normal and abnormal conditions of the eye by using a Random Forest classifier after pre-processing. In order to improve the detection performance of the Mask R-CNN algorithm, image augmentation was performed and learning procedure was conducted. Dice similarity coefficients and mean accuracy were used as evaluation indicators to measure detection accuracy. The Faster R-CNN method was used as a control group, and the detection performance of the Mask R-CNN method through this study showed an average of 90% accuracy through Dice coefficients. In the case of mean accuracy it showed 91% accuracy. When diabetic retinopathy was diagnosed by learning a Random Forest classifier based on the detected pathological symptoms, the accuracy was 99%.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.