As a kind of physical signals that could be easily acquired in daily life,photoplethysmography(PPG)signal becomes a promising solution to biometric identification for daily access management system(AMS).State-of-the-a...As a kind of physical signals that could be easily acquired in daily life,photoplethysmography(PPG)signal becomes a promising solution to biometric identification for daily access management system(AMS).State-of-the-art PPG-based identification systems are susceptible to the form of motions and physical conditions of the subjects.In this work,to exploit the advantage of deep learning,we developed an improved deep convolutional neural network(CNN)architecture by using the Gram matrix(GM)technique to convert time-serial PPG signals to two-dimensional images with a temporal dependency to improve accuracy under different forms of motions.To ensure a fair evaluation,we have adopted cross-validation method and“training and testing”dataset splitting method on the TROIKA dataset collected in ambulatory conditions.As a result,the proposed GM-CNN method achieved accuracy improvement from 69.5%to 92.4%,which is the best result in terms of multi-class classification compared with state-of-the-art models.Based on average five-fold cross-validation,we achieved an accuracy of 99.2%,improved the accuracy by 3.3%compared with the best existing method for the binary-class.展开更多
Protein secretion plays an important role in bacterial lifestyles. In Gram-negative bacteria, a wide range of proteins are secreted to modulate the interactions of bacteria with their environments and other bacteria v...Protein secretion plays an important role in bacterial lifestyles. In Gram-negative bacteria, a wide range of proteins are secreted to modulate the interactions of bacteria with their environments and other bacteria via various secretion systems. These proteins are essential for the virulence of bacteria, so it is crucial to study them for the pathogenesis of diseases and the development of drugs. Using amino acid composition (AAC), position-specific scoring matrix (PSSM) and N-terminal signal peptides, two different substitution models are firstly constructed to transform protein sequences into numerical vectors. Then, based on support vector machine (SVM) and the “one to one”?algorithm, a hybrid multi-classifier named SecretP v.2.2 is proposed to rapidly and accurately?distinguish different types of Gram-negative?bacterial secreted proteins. When performed on the same test set for a comparison with other methods, SecretP v.2.2 gets the highest total sensitivity of 93.60%. A public independent dataset is used to further test the power of SecretP v.2.2 for predicting NCSPs, it also yields satisfactory results.展开更多
基金the National Key R&D Program of China(No.2019YFB2204500)the Translational Medicine Cross Research Fund of Shanghai Jiao Tong University(No.ZH2018QNB22)。
文摘As a kind of physical signals that could be easily acquired in daily life,photoplethysmography(PPG)signal becomes a promising solution to biometric identification for daily access management system(AMS).State-of-the-art PPG-based identification systems are susceptible to the form of motions and physical conditions of the subjects.In this work,to exploit the advantage of deep learning,we developed an improved deep convolutional neural network(CNN)architecture by using the Gram matrix(GM)technique to convert time-serial PPG signals to two-dimensional images with a temporal dependency to improve accuracy under different forms of motions.To ensure a fair evaluation,we have adopted cross-validation method and“training and testing”dataset splitting method on the TROIKA dataset collected in ambulatory conditions.As a result,the proposed GM-CNN method achieved accuracy improvement from 69.5%to 92.4%,which is the best result in terms of multi-class classification compared with state-of-the-art models.Based on average five-fold cross-validation,we achieved an accuracy of 99.2%,improved the accuracy by 3.3%compared with the best existing method for the binary-class.
文摘Protein secretion plays an important role in bacterial lifestyles. In Gram-negative bacteria, a wide range of proteins are secreted to modulate the interactions of bacteria with their environments and other bacteria via various secretion systems. These proteins are essential for the virulence of bacteria, so it is crucial to study them for the pathogenesis of diseases and the development of drugs. Using amino acid composition (AAC), position-specific scoring matrix (PSSM) and N-terminal signal peptides, two different substitution models are firstly constructed to transform protein sequences into numerical vectors. Then, based on support vector machine (SVM) and the “one to one”?algorithm, a hybrid multi-classifier named SecretP v.2.2 is proposed to rapidly and accurately?distinguish different types of Gram-negative?bacterial secreted proteins. When performed on the same test set for a comparison with other methods, SecretP v.2.2 gets the highest total sensitivity of 93.60%. A public independent dataset is used to further test the power of SecretP v.2.2 for predicting NCSPs, it also yields satisfactory results.
