In this paper,we introduce a novel Multi-scale and Auto-tuned Semi-supervised Deep Subspace Clustering(MAS-DSC)algorithm,aimed at addressing the challenges of deep subspace clustering in high-dimensional real-world da...In this paper,we introduce a novel Multi-scale and Auto-tuned Semi-supervised Deep Subspace Clustering(MAS-DSC)algorithm,aimed at addressing the challenges of deep subspace clustering in high-dimensional real-world data,particularly in the field of medical imaging.Traditional deep subspace clustering algorithms,which are mostly unsupervised,are limited in their ability to effectively utilize the inherent prior knowledge in medical images.Our MAS-DSC algorithm incorporates a semi-supervised learning framework that uses a small amount of labeled data to guide the clustering process,thereby enhancing the discriminative power of the feature representations.Additionally,the multi-scale feature extraction mechanism is designed to adapt to the complexity of medical imaging data,resulting in more accurate clustering performance.To address the difficulty of hyperparameter selection in deep subspace clustering,this paper employs a Bayesian optimization algorithm for adaptive tuning of hyperparameters related to subspace clustering,prior knowledge constraints,and model loss weights.Extensive experiments on standard clustering datasets,including ORL,Coil20,and Coil100,validate the effectiveness of the MAS-DSC algorithm.The results show that with its multi-scale network structure and Bayesian hyperparameter optimization,MAS-DSC achieves excellent clustering results on these datasets.Furthermore,tests on a brain tumor dataset demonstrate the robustness of the algorithm and its ability to leverage prior knowledge for efficient feature extraction and enhanced clustering performance within a semi-supervised learning framework.展开更多
The skid resistance performance of pavement is closely related to the micro-texture of pavement aggregate, while there is very few research on the relationship between micro-texture and the skid resistance. In this pa...The skid resistance performance of pavement is closely related to the micro-texture of pavement aggregate, while there is very few research on the relationship between micro-texture and the skid resistance. In this paper, the optical microscope is used to acquire the surface morphology of three types of aggregates including basalt, limestone and red sandstone respectively, where a total of 12 indicators are developed based on the surface texture information. The polishing effect on aggregate is simulated by Wehner/Schulze (W/S) device, during the polishing procedure, the skid resistance are measured by British Pendulum Tester (BPT). Based on the results of independent T-test and the polishing resistance analysis, it shows that the surface texture of basalt is significantly different between limestone and red sandstone. Three indicators including the average roughness (Ra), the kurtosis of the surface (Sku) and the mean summit curvature (Ssc) are selected to describe the characteristics of aggregate micro-texture based on the correlation analysis. The contribution of micro-texture to the skid resistance can be described with the secondary polynomial regression model by these indicators.展开更多
Background:Alzheimer’s disease(AD)is one of the most popular tauopathies.Neurofibrillary tangles and senile plaques are-widely recognized as the pathological hallmarks of AD,which are mainly composed of tau andβ-amy...Background:Alzheimer’s disease(AD)is one of the most popular tauopathies.Neurofibrillary tangles and senile plaques are-widely recognized as the pathological hallmarks of AD,which are mainly composed of tau andβ-amyloid(Aβ)respectively.Recent failures of drugs targeting Aβhave led scientists to scrutinize the crucial impact of tau in neurodegenerative diseases.Mutated or abnormal phosphorylated tau protein loses affinity with microtubules and assembles into pathological accumulations.The aggregation process closely correlates to two amyloidogenic core of PHF6(^(306)VQIVYK^(311))and PHF6*(^(275)VQILNK^(280))fragments.Moreover,tau accumulations display diverse morphological characteristics in different diseases,which increases the difficulty of providing a unifying neuropathological criterion for early diagnosis.Results:This review mainly summarizes atomic-resolution structures of tau protein in the monomeric,oligomeric and fibrillar states,as well as the promising inhibitors designed to prevent tau aggregation or disaggregate tau accumulations,recently revealed by experimental and computational studies.We also systematically sort tau functions,their relationship with tau structures and the potential pathological processes of tau protein.Conclusion:The current progress on tau structures at atomic level of detail expands our understanding of tau aggregation and related pathology.We discuss the difficulties in determining the source of neurotoxicity and screening effective inhibitors.We hope this review will inspire new clues for designing medicines against tau aggregation and shed light on AD diagnosis and therapies.展开更多
基金supported in part by the National Natural Science Foundation of China under Grant 62171203in part by the Jiangsu Province“333 Project”High-Level Talent Cultivation Subsidized Project+2 种基金in part by the SuzhouKey Supporting Subjects for Health Informatics under Grant SZFCXK202147in part by the Changshu Science and Technology Program under Grants CS202015 and CS202246in part by Changshu Key Laboratory of Medical Artificial Intelligence and Big Data under Grants CYZ202301 and CS202314.
文摘In this paper,we introduce a novel Multi-scale and Auto-tuned Semi-supervised Deep Subspace Clustering(MAS-DSC)algorithm,aimed at addressing the challenges of deep subspace clustering in high-dimensional real-world data,particularly in the field of medical imaging.Traditional deep subspace clustering algorithms,which are mostly unsupervised,are limited in their ability to effectively utilize the inherent prior knowledge in medical images.Our MAS-DSC algorithm incorporates a semi-supervised learning framework that uses a small amount of labeled data to guide the clustering process,thereby enhancing the discriminative power of the feature representations.Additionally,the multi-scale feature extraction mechanism is designed to adapt to the complexity of medical imaging data,resulting in more accurate clustering performance.To address the difficulty of hyperparameter selection in deep subspace clustering,this paper employs a Bayesian optimization algorithm for adaptive tuning of hyperparameters related to subspace clustering,prior knowledge constraints,and model loss weights.Extensive experiments on standard clustering datasets,including ORL,Coil20,and Coil100,validate the effectiveness of the MAS-DSC algorithm.The results show that with its multi-scale network structure and Bayesian hyperparameter optimization,MAS-DSC achieves excellent clustering results on these datasets.Furthermore,tests on a brain tumor dataset demonstrate the robustness of the algorithm and its ability to leverage prior knowledge for efficient feature extraction and enhanced clustering performance within a semi-supervised learning framework.
基金Acknowledgements This paper is supported by the National Natural Science Foundation of China (Grant Nos. 51308042 and 41372320).
文摘The skid resistance performance of pavement is closely related to the micro-texture of pavement aggregate, while there is very few research on the relationship between micro-texture and the skid resistance. In this paper, the optical microscope is used to acquire the surface morphology of three types of aggregates including basalt, limestone and red sandstone respectively, where a total of 12 indicators are developed based on the surface texture information. The polishing effect on aggregate is simulated by Wehner/Schulze (W/S) device, during the polishing procedure, the skid resistance are measured by British Pendulum Tester (BPT). Based on the results of independent T-test and the polishing resistance analysis, it shows that the surface texture of basalt is significantly different between limestone and red sandstone. Three indicators including the average roughness (Ra), the kurtosis of the surface (Sku) and the mean summit curvature (Ssc) are selected to describe the characteristics of aggregate micro-texture based on the correlation analysis. The contribution of micro-texture to the skid resistance can be described with the secondary polynomial regression model by these indicators.
基金supported by the National Natural Science Foundation of China(Nos.11704256 and 11932013).
文摘Background:Alzheimer’s disease(AD)is one of the most popular tauopathies.Neurofibrillary tangles and senile plaques are-widely recognized as the pathological hallmarks of AD,which are mainly composed of tau andβ-amyloid(Aβ)respectively.Recent failures of drugs targeting Aβhave led scientists to scrutinize the crucial impact of tau in neurodegenerative diseases.Mutated or abnormal phosphorylated tau protein loses affinity with microtubules and assembles into pathological accumulations.The aggregation process closely correlates to two amyloidogenic core of PHF6(^(306)VQIVYK^(311))and PHF6*(^(275)VQILNK^(280))fragments.Moreover,tau accumulations display diverse morphological characteristics in different diseases,which increases the difficulty of providing a unifying neuropathological criterion for early diagnosis.Results:This review mainly summarizes atomic-resolution structures of tau protein in the monomeric,oligomeric and fibrillar states,as well as the promising inhibitors designed to prevent tau aggregation or disaggregate tau accumulations,recently revealed by experimental and computational studies.We also systematically sort tau functions,their relationship with tau structures and the potential pathological processes of tau protein.Conclusion:The current progress on tau structures at atomic level of detail expands our understanding of tau aggregation and related pathology.We discuss the difficulties in determining the source of neurotoxicity and screening effective inhibitors.We hope this review will inspire new clues for designing medicines against tau aggregation and shed light on AD diagnosis and therapies.