• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.4
• /
• pp.938-958
• /
• 2024

Unsupervised Video Object Segmentation (UVOS) is a highly challenging problem in computer vision as the annotation of the target object in the testing video is unknown at all. The main difficulty is to effectively handle the complicated and changeable motion state of the target object and the confusion of similar background objects in video sequence. In this paper, we propose a novel deep Dual-stream Co-enhanced Network (DC-Net) for UVOS via bidirectional motion cues refinement and multi-level feature aggregation, which can fully take advantage of motion cues and effectively integrate different level features to produce high-quality segmentation mask. DC-Net is a dual-stream architecture where the two streams are co-enhanced by each other. One is a motion stream with a Motion-cues Refine Module (MRM), which learns from bidirectional optical flow images and produces fine-grained and complete distinctive motion saliency map, and the other is an appearance stream with a Multi-level Feature Aggregation Module (MFAM) and a Context Attention Module (CAM) which are designed to integrate the different level features effectively. Specifically, the motion saliency map obtained by the motion stream is fused with each stage of the decoder in the appearance stream to improve the segmentation, and in turn the segmentation loss in the appearance stream feeds back into the motion stream to enhance the motion refinement. Experimental results on three datasets (Davis2016, VideoSD, SegTrack-v2) demonstrate that DC-Net has achieved comparable results with some state-of-the-art methods.

• Journal of KIISE
• /
• v.42 no.10
• /
• pp.1254-1267
• /
• 2015

Recently, excessive installations of APs have caused WLAN interference, and many techniques have been suggested to solve this problem. The AP aggregation technique serves to reduce active APs by moving station connections to a certain AP. Since this technique forcibly moves station connections, the transmission performance of some stations may deteriorate. The AP transmit power control technique may cause station disconnection or deterioration of transmission performance when power is reduced under a certain level. The combination of these two techniques can reduce interference through AP aggregation and narrow the range of interferences further through detailed power adjustment. However, simply combining these techniques may decrease the probability of power adjustment after aggregation and increase station disconnections upon power control. As a result, improvement in performance may be insignificant. Hence, this study suggests a scheme to combine the AP aggregation and the AP transmit power control techniques in OpenFlow-based WLAN to ameliorate the disadvantages of each technique and to reduce interferences efficiently by performing aggregation for the purpose of increasing the probability of adjusting transmission power. Simulations reveal that the average transmission delay of the suggested scheme is reduced by as much as 12.8% compared to the aggregation scheme and by as much as 18.1% compared to the power control scheme. The packet loss rate due to interference is reduced by as much as 24.9% compared to the aggregation scheme and by as much as 46.7% compared to the power control scheme. In addition, the aggregation scheme and the power control scheme decrease the throughput of several stations as a side effect, but our scheme increases the total data throughput without decreasing the throughput of each station.

• Journal of Nutrition and Health
• /
• v.34 no.2
• /
• pp.141-149
• /
• 2001

This study done to investigate the hypocholesterolemic effect of ow dietary fiber in a high cholesterol diet in aspect of cholesterol absorption and excretion using Sprague Dawley rats. After feeding diets containing 0.5% cholesterol and 5% tangerine pulp, sea tangle or prickly pear cactus for four weeks, we measured the levels of plasma and liver cholesterol and triglyceride, fecal neutral sterols and fecal radioactivity after ingestion 14(sup)C-cholesterol. We also examined platelet aggregation and histological change in liver tissues in association of hypercholesterolemia. The liver to body weight ratio was significantly(p<0.01) lower in rats fed prickly pear cactus than in other groups. The levels of plasma total cholesterol, LDL-cholesterol and triglyceride were decreased significantly(p<0.01) in the prickly pear cactus group compared with the control, while there was no difference in the liver levels of total cholesterol and triglyceride among groups. Fecal corprostanol and cholesterol were significantly(p<0.01) higher groups of control and prickly pear cactus compared to the other two groups. Radioisotope excretion after ingestion of 14(sup)C-cholesterol was higher in the control group than in tangerine pulp group or sea tangle group, with the highest in prickly pear group. Radioisotope excretion was the highest during the 2nd and 3rd days in all groups. Hematocrit and platelet aggregation were decreased in all fiber groups compared to the control, but not statistically different. Microscopic examination showed that cholesterol diet cause a fat accumulation in the liver and prickly pear cactus decreased the fat accumulation. Result indicates that prickly pear cactus has hypocholesterolemic effect by decreasing absorption and increasing excretion of cholesterol, thereby protective effect on fatty liver. Control group fed diet containing high cholesterol and low fiber seems to have a self control system in cholesterol absorption and excretion preventing hypercholesterolemia. (Korean J Nutrition 34(2) : 141-149, 2001)

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.5
• /
• pp.1597-1610
• /
• 2022

At present, the main method of high-speed train chassis detection is using computer vision technology to extract keypoints from two related chassis images firstly, then matching these keypoints to find the pixel-level correspondence between these two images, finally, detection and other steps are performed. The quality and accuracy of image matching are very important for subsequent defect detection. Current traditional matching methods are difficult to meet the actual requirements for the generalization of complex scenes such as weather, illumination, and seasonal changes. Therefore, it is of great significance to study the high-speed train image matching method based on deep learning. This paper establishes a high-speed train chassis image matching dataset, including random perspective changes and optical distortion, to simulate the changes in the actual working environment of the high-speed rail system as much as possible. This work designs a convolutional neural network to intensively extract keypoints, so as to alleviate the problems of current methods. With multi-level features, on the one hand, the network restores low-level details, thereby improving the localization accuracy of keypoints, on the other hand, the network can generate robust keypoint descriptors. Detailed experiments show the huge improvement of the proposed network over traditional methods.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.1E
• /
• pp.64-74
• /
• 1997

In many decision making systems, rule-based approaches are used to solve complex problems in the areas of pattern analysis and computer vision. In this paper, we present methods for generating fuzzy IF-THEN rules automatically from training data for pattern classification and high-level computer vision. The rules are generated by construction minimal approximate fuzzy aggregation networks and then training the networks using gradient descent methods. The training data that represent features are treated as linguistic variables that appear in the antecedent clauses of the rules. Methods to generate the corresponding linguistic labels(values) and their membership functions are presented. In addition, an inference procedure is employed to deduce conclusions from information presented to our rule-base. Two experimental results involving synthetic and real are given.

• KSBB Journal
• /
• v.26 no.5
• /
• pp.393-399
• /
• 2011

Bacillus subtilis natto producing high level of a fibrinolytic enzyme was selected and Ultra Nattokinase$^{(R)}$ was manufactured by fermentation and purification. It was performed the evaluation of the antithrombotic effect of Ultra Nattokinase$^{(R)}$ (20,000 FU/g) with rat blood plasma. The maximum aggregation (inhibition ratio) was 71% (0%), 69% (2.8%), 62% (12.7%), 16% (77.5%) and 9% (87.3%), respectively, in the order of 0, 5, 10, 50 and 100 mg/mL of Ultra Nattokinase$^{(R)}$ solutions. Ultra Nattokinase$^{(R)}$ had antithrombotic effect, which was associated with the suppression of collagen-induced platelet aggregation. Ultra Nattokinase$^{(R)}$ in the topic of the FDP (fibrinogen degradation products) in blood coagulation tests showed a significant increasing trend. And based on the daily record of meal 39 people of ITT (what ?) group consisted with 19 people of NP (what ?) group and 20 people of PN (what ?) group except four people, two people who took vitamin K affecting the experiment and two people who took alcohol, finding to be taken Ultra Nattokinase$^{(R)}$ showed an increase in the FDP value after four weeks. In addition, FDP value of 41 people of ITT group except two people having metabolic syndrome was increased by Ultra Nattokinase$^{(R)}$.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.51 no.7
• /
• pp.18-25
• /
• 2014

To increase wireless capacity, the concurrent use of multiple wireless interfaces on different frequency bands, called aggregation, can be considered. In this paper, we focus on aggregation of multiple Wi-Fi interfaces with packet-level traffic spreading between the interfaces. Two aggregation schemes, link bonding and multipath TCP (MPTCP), are tested and compared in a dualband Wi-Fi radio system with their Linux implementation. Various test conditions such as traffic types, network delay, locations, interface failures and configuration parameters are considered. Experimental results show that aggregation increases throughput performance significantly over the use of a single interface. Link bonding achieves lower throughput than MPTCP due to duplicate TCP acknowledgements (ACKs) resulting from packet reordering and filtering such duplicate ACKs out is considered as a possible solution. However, link bonding is fast responsive to links' status changes such as a link failure. It is shown that different combinations of interface weights for packet spread in link bonding result in different throughput performance, envisioning a spatio-temporal adaptation of the weights. We also develop a mathematical model of power consumption and compare the power efficiency of the schemes applying different power consumption profiles.

• The Transactions of the Korean Institute of Electrical Engineers A
• /
• v.50 no.9
• /
• pp.424-430
• /
• 2001

A multi-level optimal power flow(OPF) algorithm has been evolved from a simple two stage optimal Power flow algorithm for constrained power economic dispatch control. In the proposed algorithm, we consider various constraints such as ower balance, generation capacity, transmission line capacity, transmission losses, security equality, and security inequality constraints. The proposed algorithm consists of four stages. At the first stage, we solve the aggregated problem that is the crude classical economic dispatch problem without considering transmission losses. An initial solution is obtained by the aggregation concept in which the solution satisfies the power balance equations and generation capacity constraints. Then, after load flow analysis, the transmission losses of an initial generation setting are matched by the slack bus generator that produces power with the cheapest cost. At the second stage we consider transmission losses. Formulation of the second stage becomes classical economic dispatch problem involving the transmission losses, which are distributed to all generators. Once a feasible solution is obtained from the second stage, transmission capacity and other violations are checked and corrected locally and quickly at the third stage. The fourth stage fine tunes the solution of the third stage to reach a real minimum. The proposed approach speeds up the two stage optimization method to an average gain of 2.99 for IEEE 30, 57, and 118 bus systems and EPRI Scenario systems A through D testings.

• Journal of electromagnetic engineering and science
• /
• v.16 no.1
• /
• pp.19-23
• /
• 2016

This paper presents a novel design for dual-band bandpass filters. The proposed filters are applicable to the carrier aggregation of the TV white space (TVWS) band and long-term evolution (LTE) band for cognitive radio applications. The lower passband is the TVWS band (470-698 MHz) whose fractional bandwidth is 40 %, while the higher passband is the LTE band (824-894 MHz) with 8 % fractional bandwidth. Since the two passbands are located very close to each other, a transmission zero is inserted to enhance the rejection level between the two passbands. The TVWS band filter is designed using magnetic coupling to obtain a wide bandwidth, and the LTE band filter is designed using dielectric resonators to achieve good insertion loss characteristics. In addition, in the proposed design, a transmission zero is placed with cross-coupling. The proposed dual-band bandpass filter is designed as a two-port filter (one input/one output) as well as a three-port filter (one common input/two outputs). The measured performances show good agreement with the simulated performances.

• Korean Journal of Environmental Agriculture
• /
• v.26 no.4
• /
• pp.279-285
• /
• 2007

Soil physical properties in organic farming apple orchard were evaluated in relation to conventional farming to better understand the effects of organic farming system on soil quality. Two adjacent apple orchards, matched by soil type, were chosen to ensure the same pedological conditions except management system. Soil samples were collected from middle of two adjacent trees along the tree line at two depths of 5-20 and 20-35 cm in September 2006. Contents of organic matter in organic farming soil were twice as much as those found in soil of conventional farming. The higher level of organic matter in organic farming soil was reflected through a consequent trend in improved soil physical properties. Organic farming produced greater aggregation in >2 mm size and increased aggregate stability. Bulk density was lower by 13% and hence porosity was higher in soils of organic farming as compared with conventional farming. Water holding capacity was significantly greater with organic farming by >17% over conventional farming. The capacity of organic farming to improve soil physical properties can be contributed to the regular application of relatively large amount of organic materials and the sustainable ground-cover managements, mulching with compost and cover crop cultivation.