• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.311-326
• /
• 2024

The rapid development of neural network technology promotes the neural network model driven by big data to overcome the texture effect of complex objects. Due to the limitations in complex scenes, it is necessary to establish custom template matching and apply it to the research of many fields of computational vision technology. The dependence on high-quality small label sample database data is not very strong, and the machine learning system of deep feature connection to complete the task of texture effect inference and speculation is relatively poor. The style transfer algorithm based on neural network collects and preserves the data of patterns, extracts and modernizes their features. Through the algorithm model, it is easier to present the texture color of patterns and display them digitally. In this paper, according to the texture effect reasoning of custom template matching, the 3D visualization of the target is transformed into a 3D model. The high similarity between the scene to be inferred and the user-defined template is calculated by the user-defined template of the multi-dimensional external feature label. The convolutional neural network is adopted to optimize the external area of the object to improve the sampling quality and computational performance of the sample pyramid structure. The results indicate that the proposed algorithm can accurately capture the significant target, achieve more ablation noise, and improve the visualization results. The proposed deep convolutional neural network optimization algorithm has good rapidity, data accuracy and robustness. The proposed algorithm can adapt to the calculation of more task scenes, display the redundant vision-related information of image conversion, enhance the powerful computing power, and further improve the computational efficiency and accuracy of convolutional networks, which has a high research significance for the study of image information conversion.

• Bulletin of the Korean Chemical Society
• /
• v.35 no.11
• /
• pp.3289-3293
• /
• 2014

Femtosecond laser ablation (fs LA) was used in this study to identify pollution by heavy metals and the distribution of elemental nutrients at different rice milling ratios. Polished rice (degrees of milling of 3, 5, 7, 9, and 11) was collected from major Korean supermarkets and one sample thereof was selected. An internal quality control experiment was conducted using a rice flour certified reference material from the Korea Research Institute of Standards and Science (KRISS CRM) for the evaluation of the efficacy. To assess the effectiveness of the analysis method, the reliability was validated using a food analysis performance assessment scheme (FAPAS), with chili powder serving as an external quality control. The results of the analysis of the inorganic elements Ti, Ca, Al, Fe and Mn in white and brown rice with degrees of milling of 3, 5, 7, 9 and 11 using ICP-MS, ICP-OES and AAS revealed contents of 0.40, 49.2, 2.43, 5.36 and 10.3 mg/kg in white rice and 0.59, 78.0, 7.52, 11.0 and 18.5 mg/kg in brown rice, respectively. Among the elements, there were remarkable differences in the measured contents. By comparing the contents of the elements at different degrees of milling, Ti, Co, As, Ca, Al, Cu, Fe, and Mn were determined to be distributed on the surface of the rice grains, whereas the contents of Cd and Pb increased toward the center of the rice grains, and Si was evenly distributed. After the quantitative analysis of rice samples polished to different degrees of milling, Ca and Al, which were contained in large amounts, and Si were analyzed with specificity by fs LA. The results show that Ca and Al were distributed in the rice husk (protective covering of rice) and Si was distributed in all parts of the rice.

• Analytical Science and Technology
• /
• v.23 no.1
• /
• pp.1-14
• /
• 2010

It is of importance that all countries in worldwide, including EU and China, have adopted the Restrictions on the use of certain Hazardous Substances (RoHS) for all electronics. IEC62321 document, which was published by the International Electronics Committee (IEC) can have conflicts with the standards in the market. On the contrary Publicly Accessible Specification (PAS) for sampling published by IEC TC111 can be adopted for complementary application. In this work, we tried to find a route to disassemble and disjoint cellular phone sample, based on PAS and compare the screening methods available in the market. For this work, the cellular phone produced in 2001, before the regulation was born, was chosen for better detection. Although X-ray Fluorescence (XRF) showed excellent performance for screening, fast and easy handling, it can give information on the surface, not the bulk, and have some limitations due to significant matrix interference and lack of variety of standards for quantification. It means that screening with XRF sometimes requires supplementary tool. There are several techniques available in the market of analytical instruments. Laser ablation (LA) ICP-MS, energy dispersive (ED) XRF and scanning electron microscope (SEM)-energy dispersive X-ray (EDX) were demonstrated for screening a cellular phone. For quantitative determination, graphite furnace atomic absorption spectrometry (GF-AAS) was employed. Experimental results for Pb in a battery showed large difference in analytical results in between XRF and GF-AAS, i.e., 0.92% and 5.67%, respectively. In addition, the standard deviation of XRF was extremely large in the range of 23-168%, compared with that in the range of 1.9-92.3% for LA-ICP-MS. In conclusion, GF-AAS was required for quantitative analysis although EDX was used for screening. In this work, it was proved that LA-ICP-MS can be used as a screening method for fast analysis to determine hazardous elements in electrical products.

• Investigative Magnetic Resonance Imaging
• /
• v.17 no.3
• /
• pp.192-199
• /
• 2013

Purpose : To retrospectively evaluate the diagnostic performance of dynamic contrast-enhanced MR imaging (DCE-MRI) in detecting recurrent prostate cancer after HIFU of clinically localized cancer, as compared with T2-weighted imaging (T2WI). Materials and Methods: Twenty-six patients with increased prostate-specific antigen levels after HIFU were included in this study. All MR examinations were performed using T2WI and DCE-MRI, followed by transrectal ultrasound-guided biopsy. MRI and biopsy results were correlated in six prostate sectors. Residual or recurrent cancer after HIFU was defined as local tumor progression if biopsy results showed any cancer foci. Two independent readers interpreted the MR images. Results: Of 156 prostate sectors, 51 (33%) were positive for cancer in 17 patients. For detecting local tumor progression, the sensitivity of DCE-MRI and T2WI was 80% and 57% for reader 1 (P < 0.001) versus 84% and 61% for reader 2 (P < 0.001), respectively. The specificity and overall accuracy between DCE-MRI and T2WI showed no statistical difference in both readers (P > 0.05). Interobserver agreement of DCE-MRI and T2WI was moderate and fair, respectively. Conclusion: For detecting local tumor progression of prostate cancer after HIFU, DCE-MRI was more sensitive than T2WI, with less interobserver variability.

• The Korean Journal of Physiology
• /
• v.1 no.2
• /
• pp.169-175
• /
• 1967

An experiment was designed to see if the hippocampus exerts any influence upon the aggressive behavior of male rats. Fighting between rats was observed for the estimation of aggressiveness. Seventeen rats in which the hippocampus was almost totally removed through a small hole with a diameter around 3 mm made in the neocortex at the boundary between the parietal and occipital lobes (hippocampal group), 8 rats with similar neocortical damage alone (operated control group), and 17 normal control rats (normal group) were prepared and subjected to the experiment 3 months after the operation. Applying electric shock of short duration to the feet in a box with grid floor, a fight was provoked between an animal belonging to the hippocampal group and one belonging to the nor-mal group, between a rat of the hippocampal group and one of the operated control group, and also between a rat of the operated control group and one of the normal group. Three observers judged the performance of each animal independently and described it as winning, defeated, tied, or non-fighting. Fifteen shocked trials were administered to each pair of animals with around 2 minutes' interval between each trial. An animal received a 'judging score' of 3 when it won more frequently than was defeated, a judging score of 2 when it won as frequently as was defeated, when all fights were tied, or when no fighting occurred, while it received a judging score of 1 when it won less frequently than was defeated. Group differences in performances were analyzed in terms of judging score using Kolmogorov-Smirnov test for one sample. The results obtained were as follows: 1. In the fights between the hippocampal and the normal groups, the hippocampal animals made significantly better judging scores than the normal animals did (Table 1). 2. There was no significant difference between the hippocampal and the operated control group as to the judging scores they made in the course of fights between the two groups. However, the hippocampal animals tended to dominate over the operated control group as judged by comparing the total 'winning' of the former (30) to that of the latter (14) (Table 2). 3. The total judging score made by the operated control group in the course of the fights against the normal group was not significantly superior to that made by the normal group (Table 3). It was inferred from the above results that, though inconspicuous, the hippocampus tended to exert an inhibitory influence upon the aggressive behavior of male rats.