The application of friction stir welding(FSW) is growing owing to the omission of difficulties in traditional welding processes. In the current investigation, artificial neural network(ANN) technique was employed to p...The application of friction stir welding(FSW) is growing owing to the omission of difficulties in traditional welding processes. In the current investigation, artificial neural network(ANN) technique was employed to predict the microhardness of AA6061 friction stir welded plates. Specimens were welded employing triangular and tapered cylindrical pins. The effects of thread and conical shoulder of each pin profile on the microhardness of welded zone were studied using tow ANNs through the different distances from weld centerline. It is observed that using conical shoulder tools enhances the quality of welded area. Besides, in both pin profiles threaded pins and conical shoulders increase yield strength and ultimate tensile strength. Mean absolute percentage error(MAPE) for train and test data sets did not exceed 5.4% and 7.48%, respectively. Considering the accurate results and acceptable errors in the models' responses, the ANN method can be used to economize material and time.展开更多
Aiming at the topic of electroencephalogram （EEG） pattern recognition in brain computer interface （BCI）, a classification method based on probabilistic neural network （PNN） with supervised learning is presented ...Aiming at the topic of electroencephalogram （EEG） pattern recognition in brain computer interface （BCI）, a classification method based on probabilistic neural network （PNN） with supervised learning is presented in this paper. It applies the recognition rate of training samples to the learning progress of network parameters. The learning vector quantization is employed to group training samples and the Genetic algorithm （GA） is used for training the network＇ s smoothing parameters and hidden central vector for detemlining hidden neurons. Utilizing the standard dataset I （a） of BCI Competition 2003 and comparing with other classification methods, the experiment results show that the best performance of pattern recognition Js got in this way, and the classification accuracy can reach to 93.8%, which improves over 5% compared with the best result （88.7 % ） of the competition. This technology provides an effective way to EEG classification in practical system of BCI.展开更多
Objective： To evaluate autogenous vein grafts and inside-out vein grafts as conduits for the defects repair in the rabbit facial nerves. Methods： The 10 nun segments of buccal division of facial nerve were transect...Objective： To evaluate autogenous vein grafts and inside-out vein grafts as conduits for the defects repair in the rabbit facial nerves. Methods： The 10 nun segments of buccal division of facial nerve were transected for 48 rabbits in this study. Then the gaps were immediately repaired by autogenous vein grafts or inside-out vein grafts in different groups. All the animals underwent the whisker movement test and electrophysiologic test during the following 16 weeks at different time points postoperatively. Subsequently, the histological examination was performed to observe the facial nerve regeneration morphologically. Results： At 8 weeks after operation, the facial nerve regeneration has significant difference between the experimental group and the control group in electrophysiologic test and histological observation. However, at the end of this study, 16 weeks after operation, there was no signifi- cant difference between inside-out vein grafts and standard vein grafts in enhancing peripheral nerve regeneration. Conclusion： This study suggest that both kinds of vein grafts play positive roles in facial nerve regeneration after being repaired immediately, but the autogenous inside-out vein grafts might accelerate and facilitate axonal regeneration as compared with control.展开更多
文摘The application of friction stir welding(FSW) is growing owing to the omission of difficulties in traditional welding processes. In the current investigation, artificial neural network(ANN) technique was employed to predict the microhardness of AA6061 friction stir welded plates. Specimens were welded employing triangular and tapered cylindrical pins. The effects of thread and conical shoulder of each pin profile on the microhardness of welded zone were studied using tow ANNs through the different distances from weld centerline. It is observed that using conical shoulder tools enhances the quality of welded area. Besides, in both pin profiles threaded pins and conical shoulders increase yield strength and ultimate tensile strength. Mean absolute percentage error(MAPE) for train and test data sets did not exceed 5.4% and 7.48%, respectively. Considering the accurate results and acceptable errors in the models' responses, the ANN method can be used to economize material and time.
基金Supported by the National Natural Science Foundation of China (No. 30570485)the Shanghai "Chen Guang" Project (No. 09CG69).
文摘Aiming at the topic of electroencephalogram （EEG） pattern recognition in brain computer interface （BCI）, a classification method based on probabilistic neural network （PNN） with supervised learning is presented in this paper. It applies the recognition rate of training samples to the learning progress of network parameters. The learning vector quantization is employed to group training samples and the Genetic algorithm （GA） is used for training the network＇ s smoothing parameters and hidden central vector for detemlining hidden neurons. Utilizing the standard dataset I （a） of BCI Competition 2003 and comparing with other classification methods, the experiment results show that the best performance of pattern recognition Js got in this way, and the classification accuracy can reach to 93.8%, which improves over 5% compared with the best result （88.7 % ） of the competition. This technology provides an effective way to EEG classification in practical system of BCI.
文摘Objective： To evaluate autogenous vein grafts and inside-out vein grafts as conduits for the defects repair in the rabbit facial nerves. Methods： The 10 nun segments of buccal division of facial nerve were transected for 48 rabbits in this study. Then the gaps were immediately repaired by autogenous vein grafts or inside-out vein grafts in different groups. All the animals underwent the whisker movement test and electrophysiologic test during the following 16 weeks at different time points postoperatively. Subsequently, the histological examination was performed to observe the facial nerve regeneration morphologically. Results： At 8 weeks after operation, the facial nerve regeneration has significant difference between the experimental group and the control group in electrophysiologic test and histological observation. However, at the end of this study, 16 weeks after operation, there was no signifi- cant difference between inside-out vein grafts and standard vein grafts in enhancing peripheral nerve regeneration. Conclusion： This study suggest that both kinds of vein grafts play positive roles in facial nerve regeneration after being repaired immediately, but the autogenous inside-out vein grafts might accelerate and facilitate axonal regeneration as compared with control.
