Quadratic Discrimination Function （QDF） is commonly used in speech emotion recognition, which proceeds on the premise that the input data is normal distribution. In this paper, we propose a transformation to normali...Quadratic Discrimination Function （QDF） is commonly used in speech emotion recognition, which proceeds on the premise that the input data is normal distribution. In this paper, we propose a transformation to normalize the emotional features, emotion recognition. Features based on prosody then derivate a Modified QDF （MQDF） to speech and voice quality are extracted and Principal Component Analysis Neural Network （PCANN） is used to reduce dimension of the feature vectors. The results show that voice quality features are effective supplement for recognition, and the method in this paper could improve the recognition ratio effectively.展开更多
A new method based on principal component analysis (PCA) and support vector machines (SVMs) is proposed for fault diagnosis of mine hoists. PCA is used to extract the principal features associated with the gearbox. Th...A new method based on principal component analysis (PCA) and support vector machines (SVMs) is proposed for fault diagnosis of mine hoists. PCA is used to extract the principal features associated with the gearbox. Then, with the irrelevant gearbox variables removed, the remaining gearbox, the hydraulic system and the wire rope parameters were used as input to a multi-class SVM. The SVM is first trained by using the one class-based multi-class optimization algorithm and it is then applied to fault identification. Comparison of various methods showed the PCA-SVM method successfully removed redundancy to solve the dimensionality curse. These results show that the algorithm using the RBF kernel function for the SVM had the best classification properties.展开更多
Having researched for many years, seismologists in China presented about 80 earthquake prediction factors which reflected omen information of earthquake. How to concentrate the information that the 80 earthquake predi...Having researched for many years, seismologists in China presented about 80 earthquake prediction factors which reflected omen information of earthquake. How to concentrate the information that the 80 earthquake prediction factors have and how to choose the main factors to predict earthquakes precisely have become one of the topics in seismology. The model of principal component-discrimination consists of principal component analysis, correlation analysis, weighted method of principal factor coefficients and Mahalanobis distance discrimination analysis. This model combines the method of maximization earthquake prediction factor information with the weighted method of principal factor coefficients and correlation analysis to choose earthquake prediction variables, applying Mahalanobis distance discrimination to establishing earthquake prediction discrimination model. This model was applied to analyzing the earthquake data of Northern China area and obtained good prediction results.展开更多
A 58-year-old male patient, complaining of dysuresia, which increased over a period of 2 months, had a history of urine retention that did not respond to treatment administered in an outpatient clinic. Upon admission ...A 58-year-old male patient, complaining of dysuresia, which increased over a period of 2 months, had a history of urine retention that did not respond to treatment administered in an outpatient clinic. Upon admission to the hospital on August 2, 2005, examination showed that his prostate was midrange size by rectal palpation, and without pain or prostate nodus. An ultrasound examination indicated the prostate size was 6.1 cm×4.7 cm×3.6 cm, without an occupying lesion in the prostate.展开更多
The hard tissues of squid can provide important information for species identification. In this study, we used statolith and beak to identify three squid species including Uroteuthis duvaucelii, Loliolus beka, and U. ...The hard tissues of squid can provide important information for species identification. In this study, we used statolith and beak to identify three squid species including Uroteuthis duvaucelii, Loliolus beka, and U. edulis in the South China Sea. Because of the highly overlapping habitat and similar body morphology of the three squid species, we explored four different ways to identify them, by using statolith, upper beak, lower beak and a combination of statolith and beak. An outline geometric morphometric method and stepwise discriminant analysis were used to evaluate the most suitable method for the identification. We found that the combination of statolith and beak had the highest cross validation rate that was 75.0%, 87.5% and 88.7% for U. duvaucelii, L. beka and U. edulis, respectively. Using two beaks had similar results and the lowest cross validation rate was 60.0%, 50.0%, and 73.7% for the upper beak, 46.9%, 58.5% and 75.3% for the lower beak of U. duvaucelii, L. beka and U. edulis, respectively. Analyzing with the statolith had moderate cross validation which was 72.2%, 80.0%, and 87.7% for U. duvaucelii, L. beka and U. edulis, respectively. From the results it is suggested when the entire body of a squid is available, a combination of statolith and beak should be used for the identification. When only one hard tissue is available, species identification can be subjected to large errors.展开更多
As extrinsic rewards become very limited under organizational retrenchments, organizations should rely heavily on other types of rewards, such as intrinsic rewards, to improve the performance of those employees who ha...As extrinsic rewards become very limited under organizational retrenchments, organizations should rely heavily on other types of rewards, such as intrinsic rewards, to improve the performance of those employees who have been overwhelmed with a perception of job insecurity. This paper examines the impact of such perception, along with many other positive influencers such as enhancement in job features, recognition, and the personal values of those employees on the organizational involvement. The data analyzed were based on a sample of 34 employee respondents from a project based engineering and service company （identified as ABC Company in this paper） operating in the Middle East. The adopted research approach is basically a quantitative approach. The correlation and regression analysis tools have been used to explore this relationship. The results of this study suggest a generally unnoticed and disregarded resource that has the prime effect on improving and enhancing the organizational involvement, which is the recognition those employees receive from the management. This research suggests that recognition, as the top influencer, has a strong impact on organizational involvement/psychological attachment for the employees. The other factors that have proved to have the second degree influence on organizational involvement are enhancement in job features, increase in the job security level, and personal values.展开更多
基金the Ministry of Education Fund (No: 20050286001)Ministry of Education "New Century Tal-ents Support Plan" (No:NCET-04-0483)Doctoral Foundation of Ministry of Education (No:20050286001).
文摘Quadratic Discrimination Function （QDF） is commonly used in speech emotion recognition, which proceeds on the premise that the input data is normal distribution. In this paper, we propose a transformation to normalize the emotional features, emotion recognition. Features based on prosody then derivate a Modified QDF （MQDF） to speech and voice quality are extracted and Principal Component Analysis Neural Network （PCANN） is used to reduce dimension of the feature vectors. The results show that voice quality features are effective supplement for recognition, and the method in this paper could improve the recognition ratio effectively.
基金Project 06KJD470182 supported by the Jiangsu Educational Natural Science Foundation of china
文摘A new method based on principal component analysis (PCA) and support vector machines (SVMs) is proposed for fault diagnosis of mine hoists. PCA is used to extract the principal features associated with the gearbox. Then, with the irrelevant gearbox variables removed, the remaining gearbox, the hydraulic system and the wire rope parameters were used as input to a multi-class SVM. The SVM is first trained by using the one class-based multi-class optimization algorithm and it is then applied to fault identification. Comparison of various methods showed the PCA-SVM method successfully removed redundancy to solve the dimensionality curse. These results show that the algorithm using the RBF kernel function for the SVM had the best classification properties.
文摘Having researched for many years, seismologists in China presented about 80 earthquake prediction factors which reflected omen information of earthquake. How to concentrate the information that the 80 earthquake prediction factors have and how to choose the main factors to predict earthquakes precisely have become one of the topics in seismology. The model of principal component-discrimination consists of principal component analysis, correlation analysis, weighted method of principal factor coefficients and Mahalanobis distance discrimination analysis. This model combines the method of maximization earthquake prediction factor information with the weighted method of principal factor coefficients and correlation analysis to choose earthquake prediction variables, applying Mahalanobis distance discrimination to establishing earthquake prediction discrimination model. This model was applied to analyzing the earthquake data of Northern China area and obtained good prediction results.
文摘A 58-year-old male patient, complaining of dysuresia, which increased over a period of 2 months, had a history of urine retention that did not respond to treatment administered in an outpatient clinic. Upon admission to the hospital on August 2, 2005, examination showed that his prostate was midrange size by rectal palpation, and without pain or prostate nodus. An ultrasound examination indicated the prostate size was 6.1 cm×4.7 cm×3.6 cm, without an occupying lesion in the prostate.
基金the National Natural Science Foundation of China (No. NSFC41476129)the Shanghai Leading Academic Discipline Project (Fisheries Discipline)supported by Shanghai Ocean University International Center for Marine Studies and Shanghai 1000 Talents Program
文摘The hard tissues of squid can provide important information for species identification. In this study, we used statolith and beak to identify three squid species including Uroteuthis duvaucelii, Loliolus beka, and U. edulis in the South China Sea. Because of the highly overlapping habitat and similar body morphology of the three squid species, we explored four different ways to identify them, by using statolith, upper beak, lower beak and a combination of statolith and beak. An outline geometric morphometric method and stepwise discriminant analysis were used to evaluate the most suitable method for the identification. We found that the combination of statolith and beak had the highest cross validation rate that was 75.0%, 87.5% and 88.7% for U. duvaucelii, L. beka and U. edulis, respectively. Using two beaks had similar results and the lowest cross validation rate was 60.0%, 50.0%, and 73.7% for the upper beak, 46.9%, 58.5% and 75.3% for the lower beak of U. duvaucelii, L. beka and U. edulis, respectively. Analyzing with the statolith had moderate cross validation which was 72.2%, 80.0%, and 87.7% for U. duvaucelii, L. beka and U. edulis, respectively. From the results it is suggested when the entire body of a squid is available, a combination of statolith and beak should be used for the identification. When only one hard tissue is available, species identification can be subjected to large errors.
文摘As extrinsic rewards become very limited under organizational retrenchments, organizations should rely heavily on other types of rewards, such as intrinsic rewards, to improve the performance of those employees who have been overwhelmed with a perception of job insecurity. This paper examines the impact of such perception, along with many other positive influencers such as enhancement in job features, recognition, and the personal values of those employees on the organizational involvement. The data analyzed were based on a sample of 34 employee respondents from a project based engineering and service company （identified as ABC Company in this paper） operating in the Middle East. The adopted research approach is basically a quantitative approach. The correlation and regression analysis tools have been used to explore this relationship. The results of this study suggest a generally unnoticed and disregarded resource that has the prime effect on improving and enhancing the organizational involvement, which is the recognition those employees receive from the management. This research suggests that recognition, as the top influencer, has a strong impact on organizational involvement/psychological attachment for the employees. The other factors that have proved to have the second degree influence on organizational involvement are enhancement in job features, increase in the job security level, and personal values.
