• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1281-1281
• /
• 2001

Near-infrared (NIR) spectra have bean measured for high-density (HDPE), linear low-density (LLDPE), and low-density (LDPE) polyethylene in pellet or thin films. The obtained spectra have been analyzed by conventional spectroscopic analysis methods and chemometrics. By using the second derivative, principal component analysis (PCA), and two-dimensional (2D) correlation analysis, we could separate many overlapped bands in the NIR. It was found that the intensities of some bands are sensitive to density and crystallinity of PE. This may be the first time that such bands in the NIR region have ever been discussed. Correlations of such marker bands among the NIR spectra have also been investigated. This sort of investigation is very important not only for further understanding of vibration spectra of various of PE but also for quality control of PE by vibrational spectroscopy. Figure 1 (a) and (b) shows a NIR reflectance spectrum of one of the LLDPE samples and that of PE, respectively. Figure 2 shows a PC weight loadings plot of factor 1 for a score plot of PCA for the 16 kinds of LLDPE and PE based upon their 51 NIR spectra in the 1100-1900 nm region. The PC loadings plot separates the bands due to the $CH_3$ groups and those arising form the $CH_2$ groups, allowing one to make band assignments. The 2D correlation analysis is also powerful in band enhancement, and the band assignments based upon PCA are in good agreement with those by the 2D correlation analysis.(Figure omitted). We have made a calibration model, which predicts the density of LLDPE by use of partial least square (PLS) regression. From the loadings plot of regression coefficients for the model , we suggest that the band at 1542, 1728, and 1764 nm very sensitive to the changes in density and crystalinity.

• Journal of Institute of Control, Robotics and Systems
• /
• v.16 no.12
• /
• pp.1150-1158
• /
• 2010

In this study, the Polynomial-based Radial Basis Function Neural Networks is proposed as one of the recognition part of overall face recognition system that consists of two parts such as the preprocessing part and recognition part. The design methodology and procedure of the proposed pRBFNNs are presented to obtain the solution to high-dimensional pattern recognition problem. First, in preprocessing part, we use a CCD camera to obtain a picture frame in real-time. By using histogram equalization method, we can partially enhance the distorted image influenced by natural as well as artificial illumination. We use an AdaBoost algorithm proposed by Viola and Jones, which is exploited for the detection of facial image area between face and non-facial image area. As the feature extraction algorithm, PCA method is used. In this study, the PCA method, which is a feature extraction algorithm, is used to carry out the dimension reduction of facial image area formed by high-dimensional information. Secondly, we use pRBFNNs to identify the ID by recognizing unique pattern of each person. The proposed pRBFNNs architecture consists of three functional modules such as the condition part, the conclusion part, and the inference part as fuzzy rules formed in 'If-then' format. In the condition part of fuzzy rules, input space is partitioned with Fuzzy C-Means clustering. In the conclusion part of rules, the connection weight of pRBFNNs is represented as three kinds of polynomials such as constant, linear, and quadratic. Coefficients of connection weight identified with back-propagation using gradient descent method. The output of pRBFNNs model is obtained by fuzzy inference method in the inference part of fuzzy rules. The essential design parameters (including learning rate, momentum coefficient and fuzzification coefficient) of the networks are optimized by means of the Particle Swarm Optimization. The proposed pRBFNNs are applied to real-time face recognition system and then demonstrated from the viewpoint of output performance and recognition rate.

• Journal of Intelligence and Information Systems
• /
• v.29 no.4
• /
• pp.69-90
• /
• 2023

The purpose of this study is to evaluate the service attributes and consumer reactions of telemedicine apps in South Korea and visualize their differentiation by constructing positioning maps. We crawled 23,219 user reviews of 6 major telemedicine apps in Korea from the Google Play store. Topics were derived by BERTopic modeling, and sentiment scores for each topic were calculated through KoBERT sentiment analysis. As a result, five service characteristics in the application attribute category and three in the medical service category were derived. Based on this, a two-dimensional positioning map was constructed through principal component analysis. This study proposes an objective service evaluation method based on text mining, which has implications. In sum, this study combines empirical statistical methods and text mining techniques based on user review texts of telemedicine apps. It presents a system of service attribute elicitation, sentiment analysis, and product positioning. This can serve as an effective way to objectively diagnose the service quality and consumer responses of telemedicine applications.

• Asian Pacific Journal of Cancer Prevention
• /
• v.14 no.6
• /
• pp.3653-3661
• /
• 2013

Along with rapid economic growth and enhanced agricultural productivity, particulate matter emissions in the northern cities of Thailand have been increasing for the past two decades. This trend is expected to continue in the coming decade. Emissions of particulate matter have brought about a series of public health concerns, particularly chronic respiratory diseases. It is well known that lung cancer incidence among northern Thai women is one of the highest in Asia (an annual age-adjusted incidence rate of 37.4 per 100,000). This fact has aroused serious concern among the public and the government and has drawn much attention and interest from the scientific community. To investigate the potential causes of this relatively high lung cancer incidence, this study employed Fourier transform infrared spectroscopy (FTIR) transmission spectroscopy to identify the chemical composition of the $PM_{2.5}$ collected using Quartz Fibre Filters (QFFs) coupled with MiniVol$^{TM}$ portable air samplers (Airmetrics). $PM_{2.5}$ samples collected in nine administrative provinces in northern Thailand before and after the "Haze Episode" in 2013 were categorised based on three-dimensional plots of a principal component analysis (PCA) with Varimax rotation. In addition, the incremental lifetime exposure to $PM_{2.5}$ of both genders was calculated, and the first derivative of the FTIR spectrum of individual samples is here discussed.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.11
• /
• pp.527-536
• /
• 2017

With the recent development of smart grid industry, the necessity for efficient EMS(Energy Management System) has been increased. In particular, in order to reduce electric load and energy cost, sophisticated electric load forecasting and efficient smart grid operation strategy are required. In this paper, for more accurate electric load forecasting, we extend the data collected at demand time into high time resolution and construct an artificial neural network-based forecasting model appropriate for the high time resolution data. Furthermore, to improve the accuracy of electric load forecasting, time series data of sequence form are transformed into continuous data of two-dimensional space to solve that problem that machine learning methods cannot reflect the periodicity of time series data. In addition, to consider external factors such as temperature and humidity in accordance with the time resolution, we estimate their value at the time resolution using linear interpolation method. Finally, we apply the PCA(Principal Component Analysis) algorithm to the feature vector composed of external factors to remove data which have little correlation with the power data. Finally, we perform the evaluation of our model through 5-fold cross-validation. The results show that forecasting based on higher time resolution improve the accuracy and the best error rate of 3.71% was achieved at the 3-min resolution.

• 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.