• Korean Journal of Remote Sensing
• /
• v.35 no.6_1
• /
• pp.959-971
• /
• 2019

CNN (Convolutional Neural Network) is one representative deep learning algorithm, which can extract high-level spatial and spectral features, and has been applied for hyperspectral image classification. However, one significant drawback behind the application of CNNs in hyperspectral images is the high dimensionality of the data, which increases the training time and processing complexity. To address this problem, several CNN based hyperspectral image classification studies have exploited PCA (Principal Component Analysis) for dimensionality reduction. One limitation to this is that the spectral information of the original image can be lost through PCA. Although it is clear that the use of PCA affects the accuracy and the CNN training time, the impact of PCA for CNN based hyperspectral image classification has been understudied. The purpose of this study is to analyze the quantitative effect of PCA in CNN for hyperspectral image classification. The hyperspectral images were first transformed through PCA and applied into the CNN model by varying the size of the reduced dimensionality. In addition, 2D-CNN and 3D-CNN frameworks were applied to analyze the sensitivity of the PCA with respect to the convolution kernel in the model. Experimental results were evaluated based on classification accuracy, learning time, variance ratio, and training process. The size of the reduced dimensionality was the most efficient when the explained variance ratio recorded 99.7%~99.8%. Since the 3D kernel had higher classification accuracy in the original-CNN than the PCA-CNN in comparison to the 2D-CNN, the results revealed that the dimensionality reduction was relatively less effective in 3D kernel.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.47 no.1
• /
• pp.35-43
• /
• 2010

1D PCA utilized in the face appearance-based face recognition methods such as eigenface-based face recognition method may lead to less face representative power and more computational cost due to the resulting 1D face appearance data vector of high dimensionality. To resolve such problems of 1D PCA, 2D PCA-based face recognition methods had been developed. However, the face representation model obtained by direct application of 2D PCA to a face image set includes both face common features and face distinctive identity features. Face common features not only prevent face recognizability but also cause more computational cost. In this paper, we first develope a model of a face distinctive identity feature subspace separated from the effects of face common features in the face feature space obtained by application of 2D PCA analysis. Then, a novel robust face recognition based on the face distinctive identity feature subspace model is proposed. The proposed face recognition method based on the face distinctive identity feature subspace shows better performance than the conventional PCA-based methods (1D PCA-based one and 2D PCA-based one) with respect to recognition rate and processing time since it depends only on the face distinctive identity features. This is verified through various experiments using Yale A and IMM face database consisting of face images with various face poses under various illumination conditions.

• The Korean Journal of Pain
• /
• v.8 no.2
• /
• pp.257-265
• /
• 1995

Patient-Controlled Analgesia (PCA) has been widely used for postoperative pain relief. Meperidine is useful for PCA and has efficient analgesia, rapid onset, and low incidence of adverse effect. To compare the analgesic effect, total dose and hourly dose, side effect and neonatal status of breast feeding with meperidine via intravenous or epidural PCA for 48 hours after Cesarean Section, 40 parturient women undergoing elective Cesarean Section were randomly divided into two groups. Each respective group of 20 parturient women received meperidine via one of the intravenous PCA after general anesthesia with enflurane (IVPCA group) and the epidural PCA after general anesthesia with enflurane (IVPCA group) and the epidural PCA after epidural block with 2% lidocaine 20ml combined with general anesthesia with only $N_2O$ and $O_2$ (EpiPCA group) when they first complained of pain in recovery room. Following the administration of analgesic initial dose, parturient women of IVPCA group were allowed intravenous meperidine 10 mg every 8 minutes when they felt pain. The EpiPCA group received additional bolus dose of meperidine 2 mg and bupivacaine 0.7 mg were administered every 8 minutes as requested the patients with hourly continuous infusion of meperidine 4 mg and bupivacaine 1.4 mg. Data was collected during the 48 hours observation period including visual analog scale (VAS) pain scores, total meperidine dose, hourly dose during 48 hours and each time interval, incidence of adverse effect, satisfaction, and neonatal status with breast feeding. VAS pain scores of analgesic effect in EpiPCA group was significantly lower than in IVPCA group at 2 hours after the initial pain after Cesarean Section. Total dose and hourly dose of meperidine significantly reduced in EpiPCA group. Hourly dose of meperidine at each time interval significantly reduced during first 6 hours and from 12 hours to 24 hours in EpiPCA group. The side effects in IVPCA group were mainly sedation, nausea, and local irritation of skin. And EpiPCA group experienced numbness and itching. The degree of satisfaction of parturient women was 88.2 % in IVPCA group and 85.7 % in EpiPCA group. We did not observe any sedation, abnormal behavior, or seizure like activity in any neonates of breast feeding. From the above results we conclude that epidural PCA was more efficiently analgesic, less sedative, and consumptional, and safer for neonate than intravenous PCA, and could be an alternative method to intravenous PCA.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.4
• /
• pp.45-50
• /
• 2004

In this paper, we propose a new PCA-based LDA Mixture Algorithm(PLMA) for real-time face recognition system. This system greatly consists of the two parts: 1) face extraction part; 2) face recognition part. In the face extraction part we applied subtraction image, color filtering, eyes and mouth region detection, and normalization method, and in the face recognition part we used the method mixing PCA and LDA in extracted face candidate region images. The existing recognition system using only PCA showed low recognition rates, and it is hard in the recognition system using only LDA to apply LDA to the input images as it is when the number of image pixels ire small as compared with the training set. To overcome these shortcomings, we reduced dimension as we apply PCA to the normalized images, and apply LDA to the compressed images, therefore it is possible for us to do real-time recognition, and we are also capable of improving recognition rates. We have experimented using self-organized DAUface database to evaluate the performance of the proposed system. The experimental results show that the proposed method outperform PCA, LDA and ICA method within the framework of recognition accuracy.

• Journal of Korean Clinical Nursing Research
• /
• v.17 no.3
• /
• pp.455-466
• /
• 2011

Purpose: The purpose of this study was to investigate the effects of a structured preoperative PCA education on the knowledge and attitude regarding PCA usage, level of pain, and the consumption of analgesics after operation for colorectal surgery patients. Methods: This study was conducted from 18 Feb to 2 May, 2008. Participants were 80 colorectal cancer patients who would use the IV-PCA after colorectal surgery in a cancer hospital in Gyeonggi-do, Korea. Two groups, experimental and control were consisted of 40 patients each. The 20-minute structured education regarding PCA usage was applied to each patient individually in the experimental group but only the routine anesthetic consultation was given to each patient in the control group the day before the surgery. The SPSS/PC 10.0 program was introduced to analyze the collected data on frequency, percentage, mean, standard deviation, $x^2$-test, t-test and paired t-test. Results: The experimental group with the structured preoperative PCA education showed higher knowledge and more positive attitudes regarding the PCA usage than the control group. Also the experimental group showed better pain control and lower consumption of analgesics at 4, 8 and 24 hours after than the control group. Conclusion: The structured preoperative PCA education is an effective nursing intervention for improving the knowledge and attitude of the colorectal surgery patients on the PCA usage, and enabling the patient to take the analgesic more effectively with lower consumption, while reducing the patients' pain after operation.

• Parasites, Hosts and Diseases
• /
• v.59 no.6
• /
• pp.547-556
• /
• 2021

Our objective was to investigate whether inflammatory microenvironment induced by Trichomonas vaginalis infection can stimulate proliferation of prostate cancer (PCa) cells in vitro and in vivo mouse experiments. The production of CXCL1 and CCL2 increased when cells of the mouse PCa cells (TRAMP-C2 cell line) were infected with live T. vaginalis. T. vaginalis-conditioned medium (TCM) prepared from co-culture of PCa cells and T. vaginalis increased PCa cells migration, proliferation and invasion. The cytokine receptors (CXCR2, CCR2, gp130) were expressed higher on the PCa cells treated with TCM. Pretreatment of PCa cells with antibodies to these cytokine receptors significantly reduced the proliferation, mobility and invasiveness of PCa cells, indicating that TCM has its effect through cytokine-cytokine receptor signaling. In C57BL/6 mice, the prostates injected with T. vaginalis mixed PCa cells were larger than those injected with PCa cells alone after 4 weeks. Expression of epithelial-mesenchymal transition markers and cyclin D1 in the prostate tissue injected with T. vaginalis mixed PCa cells increased than those of PCa cells alone. Collectively, it was suggested that inflammatory reactions by T. vaginalis-stimulated PCa cells increase the proliferation and invasion of PCa cells through cytokine-cytokine receptor signaling pathways.

• Journal of Advanced Navigation Technology
• /
• v.18 no.2
• /
• pp.178-184
• /
• 2014

CMOS technology based on PCA is very efficient at an implementation of memory or ALU. However, there has been a growing interest in quantum-dot cellular automata (QCA) because of the limitation of CMOS scaling. In this paper, we propose a design of PCA architecture based on QCA. In the proposed PCA design, we utilize D flip-flop and XOR logic gate without wire crossing technique, and design a input and rule control switches. In experiment, we perform the simulation of the proposed PCA architecture by QCADesigner. As the result, we confirm the efficiency the proposed architecture.

• Women's Health Nursing
• /
• v.20 no.3
• /
• pp.204-214
• /
• 2014

Purpose: This study was to investigate the effects of the provision of concrete information about patient-controlled analgesia (PCA) in hysterectomy patients. Methods: Study design was a nonequivalent control group non-synchronized pre- and post-test design. Sixty subjects participated were assigned to experimental group (30 patients) or control group (30 patients) at one university hospital. Concrete information about PCA was composed of three sections: explanation with a leaflet, practice of using PCA, and question and answer session. Results: The experimental group who received concrete information about PCA before surgery had statistically higher knowledge level about PCA, more positive attitude toward pain control analgesia, a lower pain score, and a higher satisfaction level of the use of PCA post-surgery compared to the control group who received general information before surgery. Conclusion: Provision of concrete information about PCA was an effective nursing intervention that reduced post-operative pain for patients and increased their satisfaction with using PCA. It is recommended that concrete information about PCA be provided by nurses to promote the use of PCA and consequently reduce patient's pain post-surgery.

• Journal of Korean Academy of Fundamentals of Nursing
• /
• v.14 no.1
• /
• pp.18-28
• /
• 2007

Purpose: This study was to identify knowledge, attitude, use and state of the Patient Controlled Analgesics (PCA) in postoperative patients. Method: The research design was a descriptive research. From December 7, 2005 to January 6, 2006, 102 postoperative patients in a university hospital at Daegu were participated in the study Results: Analgesics with PCA were mainly morphine complex 73.5% and Demerol complex 26.5%. Previous experience of using PCA was only 28.4%, and the main sources of information were other post-op patients and families(43.1%). The most common reason of choice was a recommendation from other post-op patients and families(46.1%). The most common side effects of PCA were nausea and vomiting(20.6%). About 57% of the patients were satisfied with PCA, and pain scores decreased with PCA. Mean score for knowledge about PCA was 2.55 out of a possible 6, and for attitude related to pain medication. 2.31 out of possible 5. Conclusion: To increase the score on knowledge of PCA, a structured preoperative PCA education program should be developed by nursing staff.

• MALSORI
• /
• no.54
• /
• pp.73-83
• /
• 2005

The goal of our research is to build a text-independent speaker identification system that can be used in any condition without any additional adaptation process. The performance of speaker recognition systems can be severely degraded in some unknown mismatched microphone and noise conditions. In this paper, we show that PCA(principal component analysis) can improve the performance in the situation. We also propose an augmented PCA process, which augments class discriminative information to the original feature vectors before PCA transformation and selects the best direction for each pair of highly confusable speakers. The proposed method reduced the relative recognition error by 21%.