• Journal of Information Processing Systems
• /
• v.19 no.1
• /
• pp.109-117
• /
• 2023

Defect detection is one of the key factors in fabric quality control. To improve the speed and accuracy of denim fabric defect detection, this paper proposes a defect detection algorithm based on cascading feature extraction architecture. Firstly, this paper extracts these weight parameters of the pre-trained VGG16 model on the large dataset ImageNet and uses its portability to train the defect detection classifier and the defect recognition classifier respectively. Secondly, retraining and adjusting partial weight parameters of the convolution layer were retrained and adjusted from of these two training models on the high-definition fabric defect dataset. The last step is merging these two models to get the defect detection algorithm based on cascading architecture. Then there are two comparative experiments between this improved defect detection algorithm and other feature extraction methods, such as VGG16, ResNet-50, and Xception. The results of experiments show that the defect detection accuracy of this defect detection algorithm can reach 94.3% and the speed is also increased by 1-3 percentage points.

• Journal of Life Science
• /
• v.20 no.11
• /
• pp.1691-1696
• /
• 2010

Neohesperidin is a natural new nutrition sweetener, widely existing in plants of dry citrus peel, which can be derived from extraction. Since the sweetness is 1,300-1,500 times greater than that of sugar, neohesperidin are widely used in fruit juices, wines, beverages, bakeries and pharmaceutical formulations, and are particularly suitable for consumption by diabetic patients. However, the yield of extraction from citrus peel waste is very low. In this study optimal yield conditions were determinedusing response surface methodology (RSM) in order to increase the neohesperidin extraction yield. The critical factors for maximum extraction yield were selected extraction pressure ($x_1$), extraction time ($x_2$), and concentration of ethanol ($x_3$). As a result, the extraction yield was improved when the extracting pressure increased. The extraction yield also increased in a time-dependent manner. When adding ethanol as an assistance solvent to the supercritical carbon dioxide, extraction yield was increased as more ethanol concentration was added. Finally, the extraction yield of neohesperidin was improved to about 162.22% compared to ethanol extraction as a conventional method.

• The Korean Journal of Food And Nutrition
• /
• v.16 no.4
• /
• pp.372-378
• /
• 2003

The volatile components of cinnamon bark were extracted by using different isolation methods, simultaneous distillation extraction (SDE) and solid phase microextraction (SPME). Then the volatile components were analyzed by gas chromatography(GC) and mass selective detector(MSD). 30 compounds were identified in cinnamon bark. In SPME technique, several factors influencing the equilibrium of the aroma compounds between sample and SPME fiber was taken into account, including the kind of SPME fiber, extraction temperature and extraction time. Four different SPME fibers were tested, namely polydimethylsiloxane (PDMS), poly acrylate(PA), divinyl- benzene-carboxen-polydimethylsiloxane (DVB/CAR/PDMS) and carbowax/divinylbenzene(CW/DVB). Among these SPME fiber, PDMS coating fiber showed the best results. The profile of volatile compounds of cinnamon bark at different extraction temperature and extraction time were investigated by 100$\mu\textrm{m}$ PDMS fiber.

• Applied Biological Chemistry
• /
• v.36 no.1
• /
• pp.17-22
• /
• 1993

Effects of temperature, time, solvent addition ratio and number of extraction on contents of effectual components and soluble materials of cinnamon extracts were studied. All of the chemical contents of proximate composition and cinnamic acid, cinnamic aldehyde and eugenol were significantly increased as the extraction temperature increased from $20^{\circ}C$ to $80^{\circ}C$, while little change measured at $100^{\circ}C$. During ten hours of extraction at $80^{\circ}C$, more than six hours extraction showed a little increase effects the contents of cinnamic aldehyde, eugenol and proximate components. The ratio of solvents added to dried cinnamon also showed improving effects of chemical properties as the ratio increased from 5 to 40 times. Two times of extractions for 1 hour was found to be effective to recover those components.

• Clean Technology
• /
• v.23 no.3
• /
• pp.279-285
• /
• 2017

In this study, a new organophosphorus acid-based solvent (KMC-P) from KMC Co., Ltd. was used for the recovery of the iron chloride etching waste solution. In order to increase the extraction efficiency for the new solvent in the solvent extraction process, we selected the process variables and conducted the optimization experiment according to the DOE to investigate the correlation between the variables. Solvent concentration, pH, and O/A ratio were found to be factors affecting extraction and stripping efficiency. The optimum stripping efficiency was 69.7% when the solvent concentration was 29.4 wt%, the HCl addition amount was 0 mL, and the O/A ratio was 7, and the reliability was more than 86%.

• Journal of Soil and Groundwater Environment
• /
• v.18 no.4
• /
• pp.1-7
• /
• 2013

Subcritical water which acts as organic solvent with increasing temperature and pressure because dielectric constant and viscosity decrease can be used to remediate PAHs-contaminated soil. Factors influencing on extraction were studied with varying the water temperature $200{\sim}275^{\circ}C$, extraction time 0~90 min, flow rate 10~100 mL/min and pressure 3.9~10MPa. 300 g of soil sample which was contaminated with PAHs(naphthalene, phenanthrene, fluoranthene and pyrene; 423, 420, 539 and 428 mg/kg of initial concentration) was packed into the cell and placed to reactor and then the subcritical water was pumped through the cell for PAHs extraction. Naphthalene was removed almost 100% at relatively low temperature ($200^{\circ}C$). The removal rate of phenanthrene, fluoranthene, and pyrene increased by 8, 26, and 23% when the temperature increased from 200 to $275^{\circ}C$; and it was gradually increased as extraction time increased from 0 to 90 min. Decreasing removal rate when water flow rate increased from 10 to 30 mL/min, but there was no significant change after 30 mL/min. This is supposed due to channeling phenomenon. The pressure was not an effective factor for extraction of PAHs in this study. Based on the results, the importance of effective factor was in following sequence: temperature >> time > flow rate.

• Journal of the Korean Geotechnical Society
• /
• v.21 no.2
• /
• pp.121-126
• /
• 2005

It is not uncommon to observe tilt of buildings and towers as a result of unexpected differential foundation settlements. Over the years, a number of engineering methods including the soil extraction technique have been attempted to reduce inclination of buildings and towers. In this research, a series of novel geotechnical centrifuge model tests by using a state-of-the-art in-flit robotic manipulator have been conducted to study key factors which govern the restoration of building tilts. In the centrifuge model tests, the robotic manipulator was used to drill and extract soil in-flight near an initially tilted model building. The soil extraction was to induce stress release, thereby mitigating the inclination of the model building. Insights into the effects of different configurations, soil density and sequences of drilling observed during the centrifuge model tests on the restoration of the model building are to be investigated.

• KOREAN JOURNAL OF CROP SCIENCE
• /
• v.51 no.1
• /
• pp.89-94
• /
• 2006

Traditionally fatty acid composition used to be analysed by a GC and the sample preparation process includes lipid extraction from sample and subsequent methyl esters preparation, which are time-consuming and cumbersome. As an alternative, simultaneous extraction/methylation methods are being developed for rapid and simplified sample preparation. To optimize one-step extraction/methylation method for analysis of fatty acid composition in brown rice, various reaction factors such as sample to reaction solution ratio, reaction time and temperature, shaking intensity were changed and resultant fatty acid composition data were evaluated in comparison with previous reports. The ratio of sample weight to reaction solution volume was the most critical factor in that higher sample to reaction solution ratio caused overestimation of palmitic acid and linoleic acid composition, resulting in underestimation of oleic acid. Lower reaction temperature also induced overestimation of linoleic acid and underestimation of oleic acid. Reaction duration and the intensity of shaking prior to and during the reaction, however, caused no significant changes in analysis results. In conclusion, the optimum condition was mixing 5 grains (about 0.2 g) of brown rice with $680{\mu}L$ of extraction/methylation mixture and $400{\mu}L$ of heptane, followed by reaction at $80^{\circ}C$ for 2 hours.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2006.05a
• /
• pp.125-128
• /
• 2006

Since the diversification, complication of the construction industry, construction conflicts have been increased these days. Expansion of scale of construction has brought conflict treatment cost increase. Thus, needs of the study on construction conflict risk factors and its management is getting important. But the existing studies about construction conflicts and risk factors that need to be cared to decrease construction cost are almost focused on analysis of number of conflict proposed. It means those studies can be helpful when want to know how many conflict have been instituted, however, they do not contain a close examination between types of conflict and cost of conflict treatment. The purpose of this study, therefore, is an extraction of conflict causes based on the conflict treatment cost and the choice of significant risk factors to be managed to prevent conflict and its treatment cost, which enables reducing the conflict treatment colt on control the risk factors.

• Proceedings of the KSRS Conference
• /
• 2004.10a
• /
• pp.344-346
• /
• 2004

IKONOS 1m satellite imagery is particularly well suited for 3-D feature extraction and 1 :5,000 scale topographic mapping. Because the image line and sample calculated by given RPCs have the error of more than 11m, in order to be able to perform feature extraction and topographic mapping, rational polynomial coefficients(RPCs) camera model that are derived from the very complex IKONOS sensor model to describe the object-image geometry must be refined by several Ground Control Points(GCPs). This paper presents a quantitative evaluation of the geometric accuracy that can be achieved with IKONOS imagery by refining the offset and scaling factors of RPCs using several GCPs. If only two GCPs are available, the offsets and scale factors of image line and sample are updated. If we have more than three GCPs, four parameters of the offsets and scale factors of image line and sample are refined first, and then six parameters of the offsets and scale factors of latitude, longitude and height are updated. The stereo images acquired by IKONOS satellite are tested using six ground points. First, the RPCs model was refined using 2 GCPs and 4 check points acquired by GPS. The results from IKONOS stereo images are reported and these show that the RMSE of check point acquired from left images and right are 1.021m and 1.447m. And then we update the RPCs model using 4 GCPs and 2 check points. The RMSE of geometric accuracy is 0.621 m in left image and 0.816m in right image.