Acute Lymphoblastic Leukemia(ALL)is a fatal malignancy that is featured by the abnormal increase of immature lymphocytes in blood or bone marrow.Early prognosis of ALL is indispensable for the effectual remediation of...Acute Lymphoblastic Leukemia(ALL)is a fatal malignancy that is featured by the abnormal increase of immature lymphocytes in blood or bone marrow.Early prognosis of ALL is indispensable for the effectual remediation of this disease.Initial screening of ALL is conducted through manual examination of stained blood smear microscopic images,a process which is time-consuming and prone to errors.Therefore,many deep learning-based computer-aided diagnosis(CAD)systems have been established to automatically diagnose ALL.This paper proposes a novel hybrid deep learning system for ALL diagnosis in blood smear images.The introduced system integrates the proficiency of autoencoder networks in feature representational learning in latent space with the superior feature extraction capability of standard pretrained convolutional neural networks(CNNs)to identify the existence of ALL in blood smears.An augmented set of deep image features are formed from the features extracted by GoogleNet and Inception-v3 CNNs from a hybrid dataset of microscopic blood smear images.A sparse autoencoder network is designed to create an abstract set of significant latent features from the enlarged image feature set.The latent features are used to perform image classification using Support Vector Machine(SVM)classifier.The obtained results show that the latent features improve the classification performance of the proposed ALL diagnosis system over the original image features.Moreover,the classification performance of the system with various sizes of the latent feature set is evaluated.The retrieved results reveal that the introduced ALL diagnosis system superiorly compete the state of the art.展开更多
In recent years, urban rail transit （URT） systems have rapidly developed in China, however, their existing strategies for vehicle maintenance are still based on experiential and qualitative methods which result in e...In recent years, urban rail transit （URT） systems have rapidly developed in China, however, their existing strategies for vehicle maintenance are still based on experiential and qualitative methods which result in either high cost or emergencies. In this paper, a tentative attempt at introducing the fuzzy set theory into quantitative analysis and assessment of URT trains＇ failures was presented. Based on the proposed FMEA-fuzzy model, a com- puter aided system for URT maintenance optimization was developed. The overall structure and procedure of the system were described in detail, and the important issues, including the development environment, improvement to FMEA table, acquisition of weight distribution matrix P, and setting of fuzzy vector R, were also discussed. Initial application into the vehicle maintenance of Shanghai Metro System shows, that the proposed model and computer aided system have a good performance and consequently are worth further development.展开更多
When a direct-current （DC） machine runs at extremely low speed or standstill, the reduction in the armature resistance and the armature flux linkage due to the short circuited coils by the brushes on the commutator ...When a direct-current （DC） machine runs at extremely low speed or standstill, the reduction in the armature resistance and the armature flux linkage due to the short circuited coils by the brushes on the commutator should not be neglected. Taking this reduction effect into account, the average values of the reduction coefficients relate to the machine parameters in complicated forms. In this paper, an effective algorithm for the precise computation of the average values of these reduction coefficients is proposed. Furthermore, in the algorithm, the effect of the insulation thickness between the commutator segments and the multiplicity of the wave winding are considered for the first time. The proposed algorithm can also be accommodated into the computer-aided design （CAD） of a DC machine, which normally runs at extremely low speed or standstill.展开更多
文摘Acute Lymphoblastic Leukemia(ALL)is a fatal malignancy that is featured by the abnormal increase of immature lymphocytes in blood or bone marrow.Early prognosis of ALL is indispensable for the effectual remediation of this disease.Initial screening of ALL is conducted through manual examination of stained blood smear microscopic images,a process which is time-consuming and prone to errors.Therefore,many deep learning-based computer-aided diagnosis(CAD)systems have been established to automatically diagnose ALL.This paper proposes a novel hybrid deep learning system for ALL diagnosis in blood smear images.The introduced system integrates the proficiency of autoencoder networks in feature representational learning in latent space with the superior feature extraction capability of standard pretrained convolutional neural networks(CNNs)to identify the existence of ALL in blood smears.An augmented set of deep image features are formed from the features extracted by GoogleNet and Inception-v3 CNNs from a hybrid dataset of microscopic blood smear images.A sparse autoencoder network is designed to create an abstract set of significant latent features from the enlarged image feature set.The latent features are used to perform image classification using Support Vector Machine(SVM)classifier.The obtained results show that the latent features improve the classification performance of the proposed ALL diagnosis system over the original image features.Moreover,the classification performance of the system with various sizes of the latent feature set is evaluated.The retrieved results reveal that the introduced ALL diagnosis system superiorly compete the state of the art.
基金supported by the Research Program of Science and Technology Commission in Shanghai under Grant No.10dz1122701
文摘In recent years, urban rail transit （URT） systems have rapidly developed in China, however, their existing strategies for vehicle maintenance are still based on experiential and qualitative methods which result in either high cost or emergencies. In this paper, a tentative attempt at introducing the fuzzy set theory into quantitative analysis and assessment of URT trains＇ failures was presented. Based on the proposed FMEA-fuzzy model, a com- puter aided system for URT maintenance optimization was developed. The overall structure and procedure of the system were described in detail, and the important issues, including the development environment, improvement to FMEA table, acquisition of weight distribution matrix P, and setting of fuzzy vector R, were also discussed. Initial application into the vehicle maintenance of Shanghai Metro System shows, that the proposed model and computer aided system have a good performance and consequently are worth further development.
文摘When a direct-current （DC） machine runs at extremely low speed or standstill, the reduction in the armature resistance and the armature flux linkage due to the short circuited coils by the brushes on the commutator should not be neglected. Taking this reduction effect into account, the average values of the reduction coefficients relate to the machine parameters in complicated forms. In this paper, an effective algorithm for the precise computation of the average values of these reduction coefficients is proposed. Furthermore, in the algorithm, the effect of the insulation thickness between the commutator segments and the multiplicity of the wave winding are considered for the first time. The proposed algorithm can also be accommodated into the computer-aided design （CAD） of a DC machine, which normally runs at extremely low speed or standstill.
