Underwater direction of arrival(DOA)estimation has always been a very challenging theoretical and practical problem.Due to the serious non-stationary,non-linear,and non-Gaussian characteristics,machine learning based ...Underwater direction of arrival(DOA)estimation has always been a very challenging theoretical and practical problem.Due to the serious non-stationary,non-linear,and non-Gaussian characteristics,machine learning based DOA estimation methods trained on simulated Gaussian noised array data cannot be directly applied to actual underwater DOA estimation tasks.In order to deal with this problem,environmental data with no target echoes can be employed to analyze the non-Gaussian components.Then,the obtained information about non-Gaussian components can be used to whiten the array data.Based on these considerations,a novel practical sonar array whitening method was proposed.Specifically,based on a weak assumption that the non-Gaussian components in adjacent patches with and without target echoes are almost the same,canonical cor-relation analysis(CCA)and non-negative matrix factorization(NMF)techniques are employed for whitening the array data.With the whitened array data,machine learning based DOA estimation models trained on simulated Gaussian noised datasets can be used to perform underwater DOA estimation tasks.Experimental results illustrated that,using actual underwater datasets for testing with known machine learning based DOA estimation models,accurate and robust DOA estimation performance can be achieved by using the proposed whitening method in different underwater con-ditions.展开更多
Cross-Project Defect Prediction(CPDP)is a method that utilizes historical data from other source projects to train predictive models for defect prediction in the target project.However,existing CPDP methods only consi...Cross-Project Defect Prediction(CPDP)is a method that utilizes historical data from other source projects to train predictive models for defect prediction in the target project.However,existing CPDP methods only consider linear correlations between features(indicators)of the source and target projects.These models are not capable of evaluating non-linear correlations between features when they exist,for example,when there are differences in data distributions between the source and target projects.As a result,the performance of such CPDP models is compromised.In this paper,this paper proposes a novel CPDP method based on Synthetic Minority Oversampling Technique(SMOTE)and Deep Canonical Correlation Analysis(DCCA),referred to as S-DCCA.Canonical Correlation Analysis(CCA)is employed to address the issue of non-linear correlations between features of the source and target projects.S-DCCA extends CCA by incorporating the MlpNet model for feature extraction from the dataset.The redundant features are then eliminated by maximizing the correlated feature subset using the CCA loss function.Finally,cross-project defect prediction is achieved through the application of the SMOTE data sampling technique.Area Under Curve(AUC)and F1 scores(F1)are used as evaluation metrics.This paper conducted experiments on 27 projects from four public datasets to validate the proposed method.The results demonstrate that,on average,our method outperforms all baseline approaches by at least 1.2%in AUC and 5.5%in F1 score.This indicates that the proposed method exhibits favorable performance characteristics.展开更多
Biometric gait recognition is a lesser-known but emerging and effective biometric recognition method which enables subjects’walking patterns to be recognized.Existing research in this area has primarily focused on fe...Biometric gait recognition is a lesser-known but emerging and effective biometric recognition method which enables subjects’walking patterns to be recognized.Existing research in this area has primarily focused on feature analysis through the extraction of individual features,which captures most of the information but fails to capture subtle variations in gait dynamics.Therefore,a novel feature taxonomy and an approach for deriving a relationship between a function of one set of gait features with another set are introduced.The gait features extracted from body halves divided by anatomical planes on vertical,horizontal,and diagonal axes are grouped to form canonical gait covariates.Canonical Correlation Analysis is utilized to measure the strength of association between the canonical covariates of gait.Thus,gait assessment and identification are enhancedwhenmore semantic information is available through CCA-basedmulti-feature fusion.Hence,CarnegieMellon University’s 3D gait database,which contains 32 gait samples taken at different paces,is utilized in analyzing gait characteristics.The performance of Linear Discriminant Analysis,K-Nearest Neighbors,Naive Bayes,Artificial Neural Networks,and Support Vector Machines was improved by a 4%average when the CCA-utilized gait identification approachwas used.Asignificant maximumaccuracy rate of 97.8%was achieved throughCCA-based gait identification.Beyond that,the rate of false identifications and unrecognized gaits went down to half,demonstrating state-of-the-art for gait identification.展开更多
Decision implication is a form of decision knowledge represen-tation,which is able to avoid generating attribute implications that occur between condition attributes and between decision attributes.Compared with other...Decision implication is a form of decision knowledge represen-tation,which is able to avoid generating attribute implications that occur between condition attributes and between decision attributes.Compared with other forms of decision knowledge representation,decision implication has a stronger knowledge representation capability.Attribute granularization may facilitate the knowledge extraction of different attribute granularity layers and thus is of application significance.Decision implication canonical basis(DICB)is the most compact set of decision implications,which can efficiently represent all knowledge in the decision context.In order to mine all deci-sion information on decision context under attribute granulating,this paper proposes an updated method of DICB.To this end,the paper reduces the update of DICB to the updates of decision premises after deleting an attribute and after adding granulation attributes of some attributes.Based on this,the paper analyzes the changes of decision premises,examines the properties of decision premises,designs an algorithm for incrementally generating DICB,and verifies its effectiveness through experiments.In real life,by using the updated algorithm of DICB,users may obtain all decision knowledge on decision context after attribute granularization.展开更多
Triple Negative Breast Cancer (TNBC) is a malignant form of cancer with very high mortality and morbidity. Epithelial to Mesenchymal Transition (EMT) is the most common pathophysiological change observed in cancer cel...Triple Negative Breast Cancer (TNBC) is a malignant form of cancer with very high mortality and morbidity. Epithelial to Mesenchymal Transition (EMT) is the most common pathophysiological change observed in cancer cells of epithelial origin that promotes metastasis, drug resistance and cancer stem cell formation. Since the information regarding differential gene expression in TNBC cells and cell signaling events leading to EMT is limited, this investigation was done by comparing transcriptomic data generated by RNA isolation and sequencing of a EMT model TNBC cell line in comparison to regular TNBC cells. RNA sequencing and Ingenuity Pathway Software Analysis (IPA) of the transcriptomic data revealed several upregulated and downregulated gene expressions along with novel core canonical pathways including Sirtuin signaling, Oxidative Phosphorylation and Mitochondrial dysfunction events involved in EMT changes of the TNBC cells.展开更多
Grand canonical Monte Carlo simulation(GCMCs)is utilized for studying hydrogen storage gravimetric density by pha-graphene at different metal densities,temperatures and pressures.It is demonstrated that the optimum ad...Grand canonical Monte Carlo simulation(GCMCs)is utilized for studying hydrogen storage gravimetric density by pha-graphene at different metal densities,temperatures and pressures.It is demonstrated that the optimum adsorbent location for Li atoms is the center of the seven-membered ring of pha-graphene.The binding energy of Li-decorated phagraphene is larger than the cohesive energy of Li atoms,implying that Li can be distributed on the surface of pha-graphene without forming metal clusters.We fitted the force field parameters of Li and C atoms at different positions and performed GCMCs to study the absorption capacity of H_(2).The capacity of hydrogen storage was studied by the differing density of Li decoration.The maximum hydrogen storage capacity of 4Li-decorated pha-graphene was 15.88 wt%at 77 K and100 bar.The enthalpy values of adsorption at the three densities are in the ideal range of 15 kJ·mol^(-1)-25 kJ·mol^(-1).The GCMC results at different pressures and temperatures show that with the increase in Li decorative density,the hydrogen storage gravimetric ratio of pha-graphene decreases but can reach the 2025 US Department of Energy's standard(5.5 wt%).Therefore,pha-graphene is considered to be a potential hydrogen storage material.展开更多
基金supported by the National Natural Science Foundation of China(No.51279033).
文摘Underwater direction of arrival(DOA)estimation has always been a very challenging theoretical and practical problem.Due to the serious non-stationary,non-linear,and non-Gaussian characteristics,machine learning based DOA estimation methods trained on simulated Gaussian noised array data cannot be directly applied to actual underwater DOA estimation tasks.In order to deal with this problem,environmental data with no target echoes can be employed to analyze the non-Gaussian components.Then,the obtained information about non-Gaussian components can be used to whiten the array data.Based on these considerations,a novel practical sonar array whitening method was proposed.Specifically,based on a weak assumption that the non-Gaussian components in adjacent patches with and without target echoes are almost the same,canonical cor-relation analysis(CCA)and non-negative matrix factorization(NMF)techniques are employed for whitening the array data.With the whitened array data,machine learning based DOA estimation models trained on simulated Gaussian noised datasets can be used to perform underwater DOA estimation tasks.Experimental results illustrated that,using actual underwater datasets for testing with known machine learning based DOA estimation models,accurate and robust DOA estimation performance can be achieved by using the proposed whitening method in different underwater con-ditions.
基金NationalNatural Science Foundation of China,Grant/AwardNumber:61867004National Natural Science Foundation of China Youth Fund,Grant/Award Number:41801288.
文摘Cross-Project Defect Prediction(CPDP)is a method that utilizes historical data from other source projects to train predictive models for defect prediction in the target project.However,existing CPDP methods only consider linear correlations between features(indicators)of the source and target projects.These models are not capable of evaluating non-linear correlations between features when they exist,for example,when there are differences in data distributions between the source and target projects.As a result,the performance of such CPDP models is compromised.In this paper,this paper proposes a novel CPDP method based on Synthetic Minority Oversampling Technique(SMOTE)and Deep Canonical Correlation Analysis(DCCA),referred to as S-DCCA.Canonical Correlation Analysis(CCA)is employed to address the issue of non-linear correlations between features of the source and target projects.S-DCCA extends CCA by incorporating the MlpNet model for feature extraction from the dataset.The redundant features are then eliminated by maximizing the correlated feature subset using the CCA loss function.Finally,cross-project defect prediction is achieved through the application of the SMOTE data sampling technique.Area Under Curve(AUC)and F1 scores(F1)are used as evaluation metrics.This paper conducted experiments on 27 projects from four public datasets to validate the proposed method.The results demonstrate that,on average,our method outperforms all baseline approaches by at least 1.2%in AUC and 5.5%in F1 score.This indicates that the proposed method exhibits favorable performance characteristics.
基金supported by Istanbul University Scientific Research Project Department with IRP-51706 Project Number.
文摘Biometric gait recognition is a lesser-known but emerging and effective biometric recognition method which enables subjects’walking patterns to be recognized.Existing research in this area has primarily focused on feature analysis through the extraction of individual features,which captures most of the information but fails to capture subtle variations in gait dynamics.Therefore,a novel feature taxonomy and an approach for deriving a relationship between a function of one set of gait features with another set are introduced.The gait features extracted from body halves divided by anatomical planes on vertical,horizontal,and diagonal axes are grouped to form canonical gait covariates.Canonical Correlation Analysis is utilized to measure the strength of association between the canonical covariates of gait.Thus,gait assessment and identification are enhancedwhenmore semantic information is available through CCA-basedmulti-feature fusion.Hence,CarnegieMellon University’s 3D gait database,which contains 32 gait samples taken at different paces,is utilized in analyzing gait characteristics.The performance of Linear Discriminant Analysis,K-Nearest Neighbors,Naive Bayes,Artificial Neural Networks,and Support Vector Machines was improved by a 4%average when the CCA-utilized gait identification approachwas used.Asignificant maximumaccuracy rate of 97.8%was achieved throughCCA-based gait identification.Beyond that,the rate of false identifications and unrecognized gaits went down to half,demonstrating state-of-the-art for gait identification.
基金supported by the National Natural Science Foundation of China (Nos.61972238,62072294).
文摘Decision implication is a form of decision knowledge represen-tation,which is able to avoid generating attribute implications that occur between condition attributes and between decision attributes.Compared with other forms of decision knowledge representation,decision implication has a stronger knowledge representation capability.Attribute granularization may facilitate the knowledge extraction of different attribute granularity layers and thus is of application significance.Decision implication canonical basis(DICB)is the most compact set of decision implications,which can efficiently represent all knowledge in the decision context.In order to mine all deci-sion information on decision context under attribute granulating,this paper proposes an updated method of DICB.To this end,the paper reduces the update of DICB to the updates of decision premises after deleting an attribute and after adding granulation attributes of some attributes.Based on this,the paper analyzes the changes of decision premises,examines the properties of decision premises,designs an algorithm for incrementally generating DICB,and verifies its effectiveness through experiments.In real life,by using the updated algorithm of DICB,users may obtain all decision knowledge on decision context after attribute granularization.
文摘Triple Negative Breast Cancer (TNBC) is a malignant form of cancer with very high mortality and morbidity. Epithelial to Mesenchymal Transition (EMT) is the most common pathophysiological change observed in cancer cells of epithelial origin that promotes metastasis, drug resistance and cancer stem cell formation. Since the information regarding differential gene expression in TNBC cells and cell signaling events leading to EMT is limited, this investigation was done by comparing transcriptomic data generated by RNA isolation and sequencing of a EMT model TNBC cell line in comparison to regular TNBC cells. RNA sequencing and Ingenuity Pathway Software Analysis (IPA) of the transcriptomic data revealed several upregulated and downregulated gene expressions along with novel core canonical pathways including Sirtuin signaling, Oxidative Phosphorylation and Mitochondrial dysfunction events involved in EMT changes of the TNBC cells.
基金Project supported by the National Natural Science Foundation of China(Grant Nos.11904175,11804169,and 11804165)the Graduate Innovation Project of Jiangsu Province,China(Grant No.KYCX210700)。
文摘Grand canonical Monte Carlo simulation(GCMCs)is utilized for studying hydrogen storage gravimetric density by pha-graphene at different metal densities,temperatures and pressures.It is demonstrated that the optimum adsorbent location for Li atoms is the center of the seven-membered ring of pha-graphene.The binding energy of Li-decorated phagraphene is larger than the cohesive energy of Li atoms,implying that Li can be distributed on the surface of pha-graphene without forming metal clusters.We fitted the force field parameters of Li and C atoms at different positions and performed GCMCs to study the absorption capacity of H_(2).The capacity of hydrogen storage was studied by the differing density of Li decoration.The maximum hydrogen storage capacity of 4Li-decorated pha-graphene was 15.88 wt%at 77 K and100 bar.The enthalpy values of adsorption at the three densities are in the ideal range of 15 kJ·mol^(-1)-25 kJ·mol^(-1).The GCMC results at different pressures and temperatures show that with the increase in Li decorative density,the hydrogen storage gravimetric ratio of pha-graphene decreases but can reach the 2025 US Department of Energy's standard(5.5 wt%).Therefore,pha-graphene is considered to be a potential hydrogen storage material.
