This paper focuses on a state sharing method for an artificial neural network (ANN) and hidden Markov model (HMM) hybrid on line handwriting recognition system. A modeling precision based distance measure is proposed ...This paper focuses on a state sharing method for an artificial neural network (ANN) and hidden Markov model (HMM) hybrid on line handwriting recognition system. A modeling precision based distance measure is proposed to describe similarity between two ANNs, which are used as HMM state models. Limiting maximum system performance loss, a minimum quantification error aimed hierarchical clustering algorithm is designed to choose the most representative models. The system performance is improved by about 1.5% while saving 40% of the system expense. About 92% of the performance may also be maintained while reducing 70% of system parameters. The suggested method is quite useful for designing pen based interface for various handheld devices.展开更多
Objective It has long been reported that prolactinomas treated with bromocriptine increase fibrosis and may affect surgical outcomes.We retrospectively studied 238 consecutive patients with histopathologically confirm...Objective It has long been reported that prolactinomas treated with bromocriptine increase fibrosis and may affect surgical outcomes.We retrospectively studied 238 consecutive patients with histopathologically confirmed prolactinomas undergoing microsurgery in a single neurosurgery department of Tongji Hospital(Wuhan,China) from 2012 to 2015 in order to evaluate tumor consistency changes after bromocriptine pretreatment and surgical outcomes.Methods We divided the patients into four groups;males in the dopamine agonist(DA) group,females in the DA group,males in the no DA group,and females in the no DA group,and we compared the surgery process,specimen Masson staining,and clinical outcomes of the four groups.According to a previously published classification,the operative notes from an experienced neurosurgeon were reviewed to classify the consistency of tumors as "fibrous" or "nonfibrous".Results No differences in tumor consistency were found in male patients with or without DA treatment.However,in female patients with DA treatment,tumors were likely to be harder in texture than the tumors of female patients without DA treatment.Despite tumor consistency differences between sexes,the tumor biological remission rate was similar between groups,as was the rate of tumor resection.Discussion Our study indicates that preoperative DA therapy impacts tumor consistency in female patients but not male patients.Although the surgical and histopathological outcomes are not influenced,these findings may provide useful information for the choice of operative approach and surgery process for pituitary adenoma.展开更多
A novel lossless information hiding algorithm based on wavelet neural network for digital vector maps is introduced. Wavelet coefficients being manipulated are embedded into a vector map, which could be restored by ad...A novel lossless information hiding algorithm based on wavelet neural network for digital vector maps is introduced. Wavelet coefficients being manipulated are embedded into a vector map, which could be restored by adjusting the weights of neurons in the designed neural network. When extracting the watermark extraction, those coefficients would be extracted by wavelet decomposition. With the trained multilayer feed forward neural network, the watermark would be obtained finally by measuring the weights of neurons. Experimental results show that the average error coding rate is only 6% for the proposed scheme and compared with other classical algorithms on the same tests, it is indicated that the proposed algorithm hashigher robustness, better invisibility and less loss on precision.展开更多
The availability of functional magnetic resonance imaging （fMRI） has revolutionized the study of language, especially figurative language such as metaphor comprehension. The last decade has witnessed considerable re...The availability of functional magnetic resonance imaging （fMRI） has revolutionized the study of language, especially figurative language such as metaphor comprehension. The last decade has witnessed considerable research on the neural mechanisms of metaphor comprehension at word, sentence, and discourse levels respectively. This paper offers a general review of fMRI investigations into the neural networks involved in metaphor processing to date. First we introduce how metaphor studies can be done by means of fMRI technique at word, sentence and discourse levels. Then we discuss several confounding factors such as familiarity, and task demand and difficulty, which may lead to inconsistent results in fMRI experiments. Finally, we try to propose some constructive suggestions for further research in this field.展开更多
文摘This paper focuses on a state sharing method for an artificial neural network (ANN) and hidden Markov model (HMM) hybrid on line handwriting recognition system. A modeling precision based distance measure is proposed to describe similarity between two ANNs, which are used as HMM state models. Limiting maximum system performance loss, a minimum quantification error aimed hierarchical clustering algorithm is designed to choose the most representative models. The system performance is improved by about 1.5% while saving 40% of the system expense. About 92% of the performance may also be maintained while reducing 70% of system parameters. The suggested method is quite useful for designing pen based interface for various handheld devices.
基金Supported by a grant from the National Natural Sciences Foundation of China(No.81270865)
文摘Objective It has long been reported that prolactinomas treated with bromocriptine increase fibrosis and may affect surgical outcomes.We retrospectively studied 238 consecutive patients with histopathologically confirmed prolactinomas undergoing microsurgery in a single neurosurgery department of Tongji Hospital(Wuhan,China) from 2012 to 2015 in order to evaluate tumor consistency changes after bromocriptine pretreatment and surgical outcomes.Methods We divided the patients into four groups;males in the dopamine agonist(DA) group,females in the DA group,males in the no DA group,and females in the no DA group,and we compared the surgery process,specimen Masson staining,and clinical outcomes of the four groups.According to a previously published classification,the operative notes from an experienced neurosurgeon were reviewed to classify the consistency of tumors as "fibrous" or "nonfibrous".Results No differences in tumor consistency were found in male patients with or without DA treatment.However,in female patients with DA treatment,tumors were likely to be harder in texture than the tumors of female patients without DA treatment.Despite tumor consistency differences between sexes,the tumor biological remission rate was similar between groups,as was the rate of tumor resection.Discussion Our study indicates that preoperative DA therapy impacts tumor consistency in female patients but not male patients.Although the surgical and histopathological outcomes are not influenced,these findings may provide useful information for the choice of operative approach and surgery process for pituitary adenoma.
文摘A novel lossless information hiding algorithm based on wavelet neural network for digital vector maps is introduced. Wavelet coefficients being manipulated are embedded into a vector map, which could be restored by adjusting the weights of neurons in the designed neural network. When extracting the watermark extraction, those coefficients would be extracted by wavelet decomposition. With the trained multilayer feed forward neural network, the watermark would be obtained finally by measuring the weights of neurons. Experimental results show that the average error coding rate is only 6% for the proposed scheme and compared with other classical algorithms on the same tests, it is indicated that the proposed algorithm hashigher robustness, better invisibility and less loss on precision.
文摘The availability of functional magnetic resonance imaging （fMRI） has revolutionized the study of language, especially figurative language such as metaphor comprehension. The last decade has witnessed considerable research on the neural mechanisms of metaphor comprehension at word, sentence, and discourse levels respectively. This paper offers a general review of fMRI investigations into the neural networks involved in metaphor processing to date. First we introduce how metaphor studies can be done by means of fMRI technique at word, sentence and discourse levels. Then we discuss several confounding factors such as familiarity, and task demand and difficulty, which may lead to inconsistent results in fMRI experiments. Finally, we try to propose some constructive suggestions for further research in this field.
