• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.1
• /
• pp.451-465
• /
• 2017

This paper presents a novel discriminative visual tracking algorithm with an adaptive incremental extreme learning machine. The parameters for an adaptive incremental extreme learning machine are initialized at the first frame with a target that is manually assigned. At each frame, the training samples are collected and random Haar-like features are extracted. The proposed tracker updates the overall output weights for each frame, and the updated tracker is used to estimate the new location of the target in the next frame. The adaptive learning rate for the update of the overall output weights is estimated by using the confidence of the predicted target location at the current frame. Our experimental results indicate that the proposed tracker can manage various difficulties and can achieve better performance than other state-of-the-art trackers.

• Transactions on Control, Automation and Systems Engineering
• /
• v.2 no.3
• /
• pp.189-195
• /
• 2000

The mathematical solutions of the stability convergence are important problems in system control. In this paper such problems are analyzed and resolved for system control using multilayer neural networks. We describe an algorithm to control an unknown nonlinear system with a disturbance, using a multilayer neural network. We include a disturbance among the modeling error, and the weight update rules of multilayer neural network are derived to satisfy Lyapunov stability. The overall control system is based upon the feedback linearization method. The weights of the neural network used to approximate a nonlinear function are updated by rules derived in this paper . The proposed control algorithm is verified through computer simulation. That is as the weights of neural network are updated at every sampling time, we show that the output error become finite within a relatively short time.

• Journal of Power Electronics
• /
• v.11 no.5
• /
• pp.719-725
• /
• 2011

This paper describes a novel Direct Torque Control (DTC) method for adjustable speed Doubly-Fed Induction Machine (DFIM) drives which is supplied by a two-level Space Vector Modulation (SVM) voltage source inverter (DTC-SVM) in the rotor circuit. The inverter reference voltage vector is obtained by using input-output feedback linearization control and a DFIM model in the stator a-b axes reference frame with stator currents and rotor fluxes as state variables. Moreover, to make this nonlinear controller stable and robust to most varying electrical parameter uncertainties, a two layer recurrent Artificial Neural Network (ANN) is used to estimate a certain function which shows the machine lumped uncertainty. The overall system stability is proved by the Lyapunov theorem. It is shown that the torque and flux tracking errors as well as the updated weights of the ANN are uniformly ultimately bounded. Finally, effectiveness of the proposed control approach is shown by computer simulation results.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.8
• /
• pp.39-47
• /
• 1999

This paper describes on-line retrainable RBF network in order to control the coiling temperature for a hot coil strip at Pohang Iron & Steel Company(POSCO). The proposed neural network can be used for improving conventional rule-based lookup table, which generates a heat transmission coefficient. To cope with time-varying characteristics of hot coil process, additional synaptic weights for on-line retraining purposes are introduced to hidden-to-output weights of conventional RBF network. Those weights are locally adjusted to newly incoming test data while preserving old information trained with off-line past data. Hence the effect of catastrophic interference can be greatly alleviated with the proposed network. In addition, rejection scheme is introduced for reliability concerns. From the experimental results applied to the actual process, it is noticed that overall control performance represents about 2.2% increase compared to the conventional one.

• Journal of Biosystems Engineering
• /
• v.6 no.2
• /
• pp.33-47
• /
• 1982

To modernize the conventional rice post production technology and reduce grain losses, a transition toward the wet-paddy threshing system has been strongly demanded. The head-feeding type thresher with pneumatic separation has been used dominantly for threshing dried-paddy, but some adverse effects in separation performance for threshing wet-paddy is encounterred. In order to solve the problems, the development of thresher with an additional oscillating sieve to the conventional pneumatic separation has been recommanded. This study was intended to evaluate the separating performance of thresher with oscillating sieve which was attached additionally to the conventional auto-thresher equipped with separation system of blower and suction fan. For different feed rates and rice varieties, wet-and dry-material were tested with threshers attached with and without oscillating sieve. Results of the study are summarized as follows: 1. When the feed rates were 480 and 640 kg/hr, there was no statistically significant difference in power reqirements between the threshers with and without an additional sieve device for both dry-and wet-threshing. However, when the feed rate was 960 kg/hr, power requirements of thresher without sieve were greater for wet-paddy threshing than the thresher with the additional sieve separator by about 20% points. 2. With additional oscillating sieve device, the ratios of total weights of whole grains including grains with branch let and damaged grains to the total output did not show statistical difference among the feed rates. However, with pneumatic separation the ratio was decreased as the level of feed rate increased. 3. The total amount of grains with branchlet (including broken panicle) increased with the moisture content. For both the wet-and dry-material threshing with the additional oscillating sieve, the percent of grains with branchlet to the total output decreased greatly as the feed rate increased. 4. The output of the damaged grains increased as moisture content decreased. Especially, for the dry-paddy threshing, the additional sieve separating device produced more damaged grains than the pneumatic separation at all feed rates. 5. Generally, for dry paddy threshing, the separating performance of the thresher with the additional sieve device was better at all feed rates, showing greater difference with increasing feed rates. 6. Separating losses were greater with the pneumatic than sieve separation for both the wet-and dry-threshing. 7. The overall comparison of separating performance of threshers tested with and without an additional sieve device showed that the former was more effective than the latter for the dry-material threshing. However, for the wet-paddy threshing, the separation performance with a sieve device was better than the pneumatic only when the feed rate was high.

• Proceedings of the Korea Port Economic Association Conference
• /
• 2006.08a
• /
• pp.159-179
• /
• 2006

As the current trend to the main index of the port competitiveness evaluation, the competitiveness index of the port service comes to more important than the part of expense, location and facility. To reform the bottleneck of port has an effect on improving port service competitiveness. Therefore, this study shows the importance of analyzing bottlenecks on logistics to improve port competitiveness. It collected recent questionnaire data which are the subject as the Custom Service, the Chamber of Commerce and Industry, the Trade Association about bottlenecks of port logistics for working out bottlenecks of domestic port logistics and it produced the order of priorities of bottlenecks by multiplying each output priorities and weights of each process in user of Incheon inner-outer port which is focused on container freight by analysis of priority and Analytic Hierarchy Process(AHP). Unlike existing studies, this study has important values. It presents the priority evaluation only focused on the container freight was produced by port users who are categorized into shipping company, terminal operation company and forwarder, car-ferry in Incheon inner-outer port and making a application of logistics process. It means internal and external competitiveness improvement plan can be presented more concretely and detailed than past competitiveness attributes such as location, facility, service and expense. If the analysis of port logistics bottlenecks which was focused on container freight is extended to the part of general cargo and sundries such as haul grain, car, scrap iron, those studies will be able to provide Incheon port users with useful information and a model of analyzing overall bottleneck of logistics in Incheon port.

• Asian-Australasian Journal of Animal Sciences
• /
• v.26 no.1
• /
• pp.43-49
• /
• 2013

The aim of this study was to compare both the performance of litters derived from two sire genetic origins (SGO), Vienna Blue (VB) and Burgundy Fawn (BF), along successive seasons of birth (SB; winter, spring, summer and autumn), and doe reproductive performance in an organic production system. A total of fifty-eight does consisting of a mixture of crosses of several medium-large size breeds at different parity order (P, 1 = nulliparous; 2 = primiparous; ${\geq}3$ = multiparous) and twelve males (6 VB and 6 BF) were housed indoors at environmental conditions that followed seasonality. An extensive reproductive rhythm was used and kits were weaned at $46{\pm}6$ d of age. Doe reproductive performance and the data of 105 litters (55 from VB and 50 from BF SGO) were recorded throughout the SB. No statistically significant differences related to SGO effect were observed. As regards parity order, multiparous does showed higher live weights (LW) (p<0.05), total born (p<0.01), total born alive (p<0.05) per delivery, and litter weight of born alive (p<0.05), but lower milk output at 21st d than primiparous does (p<0.05). The extensive reproductive rhythm mainly increased litter performance at birth in multiparous does but was not sufficient to permit a complete recovery of body reserves lost during lactation. Autumn SB negatively affected doe LW variation between deliveries. The number of pups born and born alive per delivery (p<0.05) and litter size at 21 d of age and at weaning (p<0.01) were lower during hot SB. Due to the lower litter size of pups born in summer and autumn, their individual weight at 21st d of age and daily individual growth rate 0 to 21 d were higher than those of pups born in winter (p<0.001). Litter performance at 21st d of age and individual pup pre-weaning growth rate were poorer for those born in spring than in other seasons due to the harmful effects of increased environmental temperatures. SB affected most of the performance traits of does and young rabbits reared under the organic farming system. The rabbits seemed better suited to organic rearing conditions during winter than in other seasons. The worst results overall were obtained in the spring SB, whereas the hot SB negatively affected both doe energy balance and prolificacy. In conclusion, the pups of the 2 SGO showed good pre-weaning performance and seemed suited to the organic rabbit production system.