• 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.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.20 no.3
• /
• pp.562-569
• /
• 2019

Raman spectroscopy has been receiving increased attention as a standoff explosive detection technique. In addition, there is a growing need for a fast search method that can identify raman spectrum for measured chemical substances compared to known raman spectra in large database. By far the most simple and widely used method is to calculate and compare the Euclidean distance between the given spectrum and the spectra in a database. But it is non-trivial problem because of the inherent high dimensionality of the data. One of the most serious problems is the high computational complexity of searching for the closet spectra. To overcome this problem, we presented the MPS Sort with Sorted Variance+PDS method for the fast algorithm to search for the closet spectra in the last paper. the proposed algorithm uses two significant features of a vector, mean values and variance, to reject many unlikely spectra and save a great deal of computation time. In this paper, we present two new methods for the fast algorithm to search for the closet spectra. the PCA+PDS algorithm reduces the amount of computation by reducing the dimension of the data through PCA transformation with the same result as the distance calculation using the whole data. the Hierarchical Cluster Tree algorithm makes a binary hierarchical tree using PCA transformed spectra data. then it start searching from the clusters closest to the input spectrum and do not calculate many spectra that can not be candidates, which save a great deal of computation time. As the Experiment results, PCA+PDS shows about 60.06% performance improvement for the MPS Sort with Sorted Variance+PDS. also, Hierarchical Tree shows about 17.74% performance improvement for the PCA+PDS. The results obtained confirm the effectiveness of the proposed algorithm.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.6
• /
• pp.1092-1099
• /
• 2022

Research on exhaust aftertreatment devices to reduce air pollutants and greenhouse gas emissions is being actively conducted. However, in the case of the particulate matters/nitrogen oxides (PM/NOx) simultaneous reduction device for ships, the problem of back pressure on the diesel engine and replacement of the filter carrier is occurring. In this study, for the optimal design of the integrated device that can simultaneously reduce PM/NOx, an appropriate standard was presented by studying the flow inside the device and change in back pressure through the inlet/outlet pressure. Ansys Fluent was used to apply porous media conditions to a diesel particulate filter (DPF) and selective catalytic reduction (SCR) by setting porosity to 30%, 40%, 50%, 60%, and 70%. In addition, the ef ect on back pressure was analyzed by applying the inlet velocity according to the engine load to 7.4 m/s, 10.3 m/s, 13.1 m/s, and 26.2 m/s as boundary conditions. As a result of a computational fluid dynamics analysis, the rate of change for back pressure by changing the inlet velocity was greater than when inlet temperature was changed, and the maximum rate of change was 27.4 mbar. This was evaluated as a suitable device for ships of 1800kW because the back pressure in all boundary conditions did not exceed the classification standard of 68mbar.

• Korean Chemical Engineering Research
• /
• v.61 no.4
• /
• pp.523-541
• /
• 2023

As accessibility to 3D printers increases, there is a growing frequency of exposure to chemicals associated with 3D printing. However, research on the toxicity and harmfulness of chemicals generated by 3D printing is insufficient, and the performance of toxicity prediction using in silico techniques is limited due to missing molecular structure data. In this study, quantitative structure-activity relationship (QSAR) model based on data-centric AI approach was developed to predict the toxicity of new 3D printing materials by imputing missing values in molecular descriptors. First, MissForest algorithm was utilized to impute missing values in molecular descriptors of hazardous 3D printing materials. Then, based on four different machine learning models (decision tree, random forest, XGBoost, SVM), a machine learning (ML)-based QSAR model was developed to predict the bioconcentration factor (Log BCF), octanol-air partition coefficient (Log Koa), and partition coefficient (Log P). Furthermore, the reliability of the data-centric QSAR model was validated through the Tree-SHAP (SHapley Additive exPlanations) method, which is one of explainable artificial intelligence (XAI) techniques. The proposed imputation method based on the MissForest enlarged approximately 2.5 times more molecular structure data compared to the existing data. Based on the imputed dataset of molecular descriptor, the developed data-centric QSAR model achieved approximately 73%, 76% and 92% of prediction performance for Log BCF, Log Koa, and Log P, respectively. Lastly, Tree-SHAP analysis demonstrated that the data-centric-based QSAR model achieved high prediction performance for toxicity information by identifying key molecular descriptors highly correlated with toxicity indices. Therefore, the proposed QSAR model based on the data-centric XAI approach can be extended to predict the toxicity of potential pollutants in emerging printing chemicals, chemical process, semiconductor or display process.

• Korean Journal of Heritage: History & Science
• /
• v.57 no.1
• /
• pp.82-108
• /
• 2024

With the transition of archaeological recording method's transition from analog to digital, the 3D scanning technology has been actively adopted within the field. Research on the digital archaeological digital data gathered from 3D scanning and photogrammetry is continuously being conducted. However, due to cost and manpower issues, most buried cultural heritage organizations are hesitating to adopt such digital technology. This paper aims to present a digital recording method of relics utilizing open-source software and photogrammetry technology, which is believed to be the most efficient method among 3D scanning methods. The digital recording process of relics consists of three stages: acquiring a 3D model, creating a joining map with the edited 3D model, and creating an digital drawing. In order to enhance the accessibility, this method only utilizes open-source software throughout the entire process. The results of this study confirms that in terms of quantitative evaluation, the deviation of numerical measurement between the actual artifact and the 3D model was minimal. In addition, the results of quantitative quality analysis from the open-source software and the commercial software showed high similarity. However, the data processing time was overwhelmingly fast for commercial software, which is believed to be a result of high computational speed from the improved algorithm. In qualitative evaluation, some differences in mesh and texture quality occurred. In the 3D model generated by opensource software, following problems occurred: noise on the mesh surface, harsh surface of the mesh, and difficulty in confirming the production marks of relics and the expression of patterns. However, some of the open source software did generate the quality comparable to that of commercial software in quantitative and qualitative evaluations. Open-source software for editing 3D models was able to not only post-process, match, and merge the 3D model, but also scale adjustment, join surface production, and render image necessary for the actual measurement of relics. The final completed drawing was tracked by the CAD program, which is also an open-source software. In archaeological research, photogrammetry is very applicable to various processes, including excavation, writing reports, and research on numerical data from 3D models. With the breakthrough development of computer vision, the types of open-source software have been diversified and the performance has significantly improved. With the high accessibility to such digital technology, the acquisition of 3D model data in archaeology will be used as basic data for preservation and active research of cultural heritage.

• Journal of Intelligence and Information Systems
• /
• v.24 no.1
• /
• pp.205-225
• /
• 2018

Convolutional Neural Network (ConvNet) is one class of the powerful Deep Neural Network that can analyze and learn hierarchies of visual features. Originally, first neural network (Neocognitron) was introduced in the 80s. At that time, the neural network was not broadly used in both industry and academic field by cause of large-scale dataset shortage and low computational power. However, after a few decades later in 2012, Krizhevsky made a breakthrough on ILSVRC-12 visual recognition competition using Convolutional Neural Network. That breakthrough revived people interest in the neural network. The success of Convolutional Neural Network is achieved with two main factors. First of them is the emergence of advanced hardware (GPUs) for sufficient parallel computation. Second is the availability of large-scale datasets such as ImageNet (ILSVRC) dataset for training. Unfortunately, many new domains are bottlenecked by these factors. For most domains, it is difficult and requires lots of effort to gather large-scale dataset to train a ConvNet. Moreover, even if we have a large-scale dataset, training ConvNet from scratch is required expensive resource and time-consuming. These two obstacles can be solved by using transfer learning. Transfer learning is a method for transferring the knowledge from a source domain to new domain. There are two major Transfer learning cases. First one is ConvNet as fixed feature extractor, and the second one is Fine-tune the ConvNet on a new dataset. In the first case, using pre-trained ConvNet (such as on ImageNet) to compute feed-forward activations of the image into the ConvNet and extract activation features from specific layers. In the second case, replacing and retraining the ConvNet classifier on the new dataset, then fine-tune the weights of the pre-trained network with the backpropagation. In this paper, we focus on using multiple ConvNet layers as a fixed feature extractor only. However, applying features with high dimensional complexity that is directly extracted from multiple ConvNet layers is still a challenging problem. We observe that features extracted from multiple ConvNet layers address the different characteristics of the image which means better representation could be obtained by finding the optimal combination of multiple ConvNet layers. Based on that observation, we propose to employ multiple ConvNet layer representations for transfer learning instead of a single ConvNet layer representation. Overall, our primary pipeline has three steps. Firstly, images from target task are given as input to ConvNet, then that image will be feed-forwarded into pre-trained AlexNet, and the activation features from three fully connected convolutional layers are extracted. Secondly, activation features of three ConvNet layers are concatenated to obtain multiple ConvNet layers representation because it will gain more information about an image. When three fully connected layer features concatenated, the occurring image representation would have 9192 (4096+4096+1000) dimension features. However, features extracted from multiple ConvNet layers are redundant and noisy since they are extracted from the same ConvNet. Thus, a third step, we will use Principal Component Analysis (PCA) to select salient features before the training phase. When salient features are obtained, the classifier can classify image more accurately, and the performance of transfer learning can be improved. To evaluate proposed method, experiments are conducted in three standard datasets (Caltech-256, VOC07, and SUN397) to compare multiple ConvNet layer representations against single ConvNet layer representation by using PCA for feature selection and dimension reduction. Our experiments demonstrated the importance of feature selection for multiple ConvNet layer representation. Moreover, our proposed approach achieved 75.6% accuracy compared to 73.9% accuracy achieved by FC7 layer on the Caltech-256 dataset, 73.1% accuracy compared to 69.2% accuracy achieved by FC8 layer on the VOC07 dataset, 52.2% accuracy compared to 48.7% accuracy achieved by FC7 layer on the SUN397 dataset. We also showed that our proposed approach achieved superior performance, 2.8%, 2.1% and 3.1% accuracy improvement on Caltech-256, VOC07, and SUN397 dataset respectively compare to existing work.