Limited by the sensitivity of laboratory techniques,conventional human DNA analysis of touch DNA on frequently used items and prints does not always provide satisfactory results.In this study,microbiome DNA on persona...Limited by the sensitivity of laboratory techniques,conventional human DNA analysis of touch DNA on frequently used items and prints does not always provide satisfactory results.In this study,microbiome DNA on personal computers,cell phones,and palm prints was analyzed and compared.After sample collection,DNA extraction,polymerase chain reaction amplification,library preparation,and sequencing,data were analyzed using the QIIME 1.8.0 software.Weighted unifrac distance between the right palm skin and the right side of a keyboard,the right palm skin and the mouse,and the left side of the keyboard and the left palm skin was 0.258850,0.265474,and 0.214098,respectively.Even after palm prints were left for 1 week,microbial community structures were still quite similar to those of samples collected from the palm skin on the day they were left(weighted unifrac distance was 0.270885).展开更多
In recent years,biometric sensors are applicable for identifying impor-tant individual information and accessing the control using various identifiers by including the characteristics like afingerprint,palm print,iris r...In recent years,biometric sensors are applicable for identifying impor-tant individual information and accessing the control using various identifiers by including the characteristics like afingerprint,palm print,iris recognition,and so on.However,the precise identification of human features is still physically chal-lenging in humans during their lifetime resulting in a variance in their appearance or features.In response to these challenges,a novel Multimodal Biometric Feature Extraction(MBFE)model is proposed to extract the features from the noisy sen-sor data using a modified Ranking-based Deep Convolution Neural Network(RDCNN).The proposed MBFE model enables the feature extraction from differ-ent biometric images that includes iris,palm print,and lip,where the images are preprocessed initially for further processing.The extracted features are validated after optimal extraction by the RDCNN by splitting the datasets to train the fea-ture extraction model and then testing the model with different sets of input images.The simulation is performed in matlab to test the efficacy of the modal over multi-modal datasets and the simulation result shows that the proposed meth-od achieves increased accuracy,precision,recall,and F1 score than the existing deep learning feature extraction methods.The performance improvement of the MBFE Algorithm technique in terms of accuracy,precision,recall,and F1 score is attained by 0.126%,0.152%,0.184%,and 0.38%with existing Back Propaga-tion Neural Network(BPNN),Human Identification Using Wavelet Transform(HIUWT),Segmentation Methodology for Non-cooperative Recognition(SMNR),Daugman Iris Localization Algorithm(DILA)feature extraction techni-ques respectively.展开更多
基金This work has received funding from the State Key Laboratory of Pathogen and Biosecurity(xxhz201510)Shanghai Research Institute of Criminal Science and Technology(2014XCWZK14).
文摘Limited by the sensitivity of laboratory techniques,conventional human DNA analysis of touch DNA on frequently used items and prints does not always provide satisfactory results.In this study,microbiome DNA on personal computers,cell phones,and palm prints was analyzed and compared.After sample collection,DNA extraction,polymerase chain reaction amplification,library preparation,and sequencing,data were analyzed using the QIIME 1.8.0 software.Weighted unifrac distance between the right palm skin and the right side of a keyboard,the right palm skin and the mouse,and the left side of the keyboard and the left palm skin was 0.258850,0.265474,and 0.214098,respectively.Even after palm prints were left for 1 week,microbial community structures were still quite similar to those of samples collected from the palm skin on the day they were left(weighted unifrac distance was 0.270885).
文摘In recent years,biometric sensors are applicable for identifying impor-tant individual information and accessing the control using various identifiers by including the characteristics like afingerprint,palm print,iris recognition,and so on.However,the precise identification of human features is still physically chal-lenging in humans during their lifetime resulting in a variance in their appearance or features.In response to these challenges,a novel Multimodal Biometric Feature Extraction(MBFE)model is proposed to extract the features from the noisy sen-sor data using a modified Ranking-based Deep Convolution Neural Network(RDCNN).The proposed MBFE model enables the feature extraction from differ-ent biometric images that includes iris,palm print,and lip,where the images are preprocessed initially for further processing.The extracted features are validated after optimal extraction by the RDCNN by splitting the datasets to train the fea-ture extraction model and then testing the model with different sets of input images.The simulation is performed in matlab to test the efficacy of the modal over multi-modal datasets and the simulation result shows that the proposed meth-od achieves increased accuracy,precision,recall,and F1 score than the existing deep learning feature extraction methods.The performance improvement of the MBFE Algorithm technique in terms of accuracy,precision,recall,and F1 score is attained by 0.126%,0.152%,0.184%,and 0.38%with existing Back Propaga-tion Neural Network(BPNN),Human Identification Using Wavelet Transform(HIUWT),Segmentation Methodology for Non-cooperative Recognition(SMNR),Daugman Iris Localization Algorithm(DILA)feature extraction techni-ques respectively.
