In the realm of large-scale machine learning,it is crucial to explore methods for reducing computational complexity and memory demands while maintaining generalization performance.Additionally,since the collected data...In the realm of large-scale machine learning,it is crucial to explore methods for reducing computational complexity and memory demands while maintaining generalization performance.Additionally,since the collected data may contain some sensitive information,it is also of great significance to study privacy-preserving machine learning algorithms.This paper focuses on the performance of the differentially private stochastic gradient descent(SGD)algorithm based on random features.To begin,the algorithm maps the original data into a lowdimensional space,thereby avoiding the traditional kernel method for large-scale data storage requirement.Subsequently,the algorithm iteratively optimizes parameters using the stochastic gradient descent approach.Lastly,the output perturbation mechanism is employed to introduce random noise,ensuring algorithmic privacy.We prove that the proposed algorithm satisfies the differential privacy while achieving fast convergence rates under some mild conditions.展开更多
Sepsis poses a serious threat to health of children in pediatric intensive care unit.The mortality from pediatric sepsis can be effectively reduced through in-time diagnosis and therapeutic intervention.The bacillicul...Sepsis poses a serious threat to health of children in pediatric intensive care unit.The mortality from pediatric sepsis can be effectively reduced through in-time diagnosis and therapeutic intervention.The bacilliculture detection method is too time-consuming to receive timely treatment.In this research,we propose a new framework:a deep encoding network with cross features(CF-DEN)that enables accurate early detection of sepsis.Cross features are automatically constructed via the gradient boosting decision tree and distilled into the deep encoding network(DEN)we designed.The DEN is aimed at learning sufficiently effective representation from clinical test data.Each layer of the DEN fltrates the features involved in computation at current layer via attention mechanism and outputs the current prediction which is additive layer by layer to obtain the embedding feature at last layer.The framework takes the advantage of tree-based method and neural network method to extract effective representation from small clinical dataset and obtain accurate prediction in order to prompt patient to get timely treatment.We evaluate the performance of the framework on the dataset collected from Shanghai Children's Medical Center.Compared with common machine learning methods,our method achieves the increase on F1-score by 16.06%on the test set.展开更多
This paper presents a method for lane boundaries detection which is not affected by the shadows, illumination and un-even road conditions. This method is based upon processing grayscale images using local gradient fea...This paper presents a method for lane boundaries detection which is not affected by the shadows, illumination and un-even road conditions. This method is based upon processing grayscale images using local gradient features, characteris-tic spectrum of lanes, and linear prediction. Firstly, points on the adjacent right and left lane are recognized using the local gradient descriptors. A simple linear prediction model is deployed to predict the direction of lane markers. The contribution of this paper is the use of vertical gradient image without converting into binary image(using suitable thre-shold), and introduction of characteristic lane gradient spectrum within the local window to locate the preciselane marking points along the horizontal scan line over the image. Experimental results show that this method has greater tolerance to shadows and low illumination conditions. A comparison is drawn between this method and recent methods reported in the literature.展开更多
To automatically detecting whether a person is wearing mask properly,we propose a face mask detection algorithm based on hue-saturation-value(HSV)+histogram of oriented gradient(HOG)features and support vector machine...To automatically detecting whether a person is wearing mask properly,we propose a face mask detection algorithm based on hue-saturation-value(HSV)+histogram of oriented gradient(HOG)features and support vector machines(SVM).Firstly,human face and five feature points are detected with RetinaFace face detection algorithm.The feature points are used to locate to mouth and nose region,and HSV+HOG features of this region are extracted and input to SVM for training to realize detection of wearing masks or not.Secondly,RetinaFace is used to locate to nasal tip area of face,and YCrCb elliptical skin tone model is used to detect the exposure of skin in the nasal tip area,and the optimal classification threshold can be found to determine whether the wear is properly according to experimental results.Experiments show that the accuracy of detecting whether mask is worn can reach 97.9%,and the accuracy of detecting whether mask is worn correctly can reach 87.55%,which verifies the feasibility of the algorithm.展开更多
It is easy for teenagers to view pornographic pictures on social networks. Many researchers have studied the detection of real pornographic pictures, but there are few studies on those that are artificial. In this wor...It is easy for teenagers to view pornographic pictures on social networks. Many researchers have studied the detection of real pornographic pictures, but there are few studies on those that are artificial. In this work, we studied how to detect artificial pornographic pictures, especially when they are on social networks. The whole detection process can be divided into two stages： feature selection and picture detection. In the feature selection stage, seven types of features that favour picture detection were selected. In the picture detection stage, three steps were included. 1） In order to alleviate the imbalance in the number of artificial pornographic pictures and normal ones, the training dataset of artificial pornographic pictures was expanded. Therefore, the features which were extracted from the training dataset can also be expanded too. 2） In order to reduce the time of feature extraction, a fast method which extracted features based on the proportionally scaled picture rather than the original one was proposed. 3） Three tree models were compared and a gradient boost decision tree （GBDT） was selected for the final picture detection. Three sets of experimental results show that the proposed method can achieve better recognition precision and drastically reduce the time cost of the method.展开更多
At present,underwater terrain images are all strip-shaped small fragment images preprocessed by the side-scan sonar imaging system.However,the processed underwater terrain images have inconspicuous and few feature poi...At present,underwater terrain images are all strip-shaped small fragment images preprocessed by the side-scan sonar imaging system.However,the processed underwater terrain images have inconspicuous and few feature points.In order to better realize the stitching of underwater terrain images and solve the problems of slow traditional image stitching speed,we proposed an improved algorithm for underwater terrain image stitching based on spatial gradient feature block.First,the spatial gradient fuzzy C-Means algorithm is used to divide the underwater terrain image into feature blocks with the fusion of spatial gradient information.The accelerated-KAZE(AKAZE)algorithm is used to combine the feature block information to match the reference image and the target image.Then,the random sample consensus(RANSAC)is applied to optimize the matching results.Finally,image fusion is performed with the global homography and the optimal seam-line method to improve the accuracy of image overlay fusion.The experimental results show that the proposed method in this paper effectively divides images into feature blocks by combining spatial information and gradient information,which not only solves the problem of stitching failure of underwater terrain images due to unobvious features,and further reduces the sensitivity to noise,but also effectively reduces the iterative calculation in the feature point matching process of the traditional method,and improves the stitching speed.Ghosting and shape warping are significantly eliminated by re-optimizing the overlap of the image.展开更多
Objective To investigate the correlation between the clinical features and endoscopic ultrasound-guided portal pressure gradient(EUS-PPG)in patients with cirrhosis.Methods A total of 148 patients with cirrhosis and po...Objective To investigate the correlation between the clinical features and endoscopic ultrasound-guided portal pressure gradient(EUS-PPG)in patients with cirrhosis.Methods A total of 148 patients with cirrhosis and portal hypertension who underwent EUS-PPG measurement at the Third Xiangya Hospital of Central South University from March 15,2022 to June 20,2023 were selected.The clinical data of patients collected before EUS-PPG measurement were analyzed.Variations in the EUS-PPG across different clinical data subgroups were analyzed.Multivariate linear regression analysis was used to explore the independent factors influencing EUS-PPG.Results The EUS-PPG was significantly elevated in patients exhibiting red signs(16.62±5.33 mmHg VS 13.44±5.34 mmHg,t=3.616,P<0.001),gastroesophageal varices(15.78±5.30 mmHg VS 9.70±4.77 mmHg,t=4.247,P<0.001),hepatic encephalopathy(20.83±7.52 mmHg VS 14.92±5.35 mmHg,t=2.606,P=0.010),thrombocytopenia(15.66±5.39 mmHg VS 13.29±5.83mmHg,t=2.136,P=0.034),hypoproteinemia(16.13±5.86 mmHg VS 14.12±5.03 mmHg,t=2.230,P=0.027),and an increased international normalized ratio(16.25±6.00 mmHg VS 14.40±5.11mmHg,t=2.022,P=0.045).Conversely,the EUS-PPG was significantly reduced in patients with a history of splenectomy and devascularization(13.17±5.88mmHgVS15.73±5.34mmHg,t=-2.379,P=0.019).The EUS-PPG in patients with varying degrees of ascites(no VS slight VS moderate or severe:13.40±5.48 mmHg VS 15.90±5.49 mmHg VS 16.69±5.17 mmHg,F=5.188,P=0.007)and different Child-Pugh classifications(A VS B VS C:14.07±5.05 mmHg VS 15.69±5.74 mmHg VS 17.64±5.99 mmHg,F=3.066,P=0.049)increased gradually.Multivariable linear regression analysis showed that red signs(β=2.44,t=2.732,P=0.007),gastroesophageal varices(β=4.45,t=2.990,P=0.003),ascites(β=1.75,t=2.368,P=0.019),and hepatic encephalopathy(β=5.82,t=2.644,P=0.009)were independentftactors fortheelevated1EUS-PPG.Conclusion There is a significant correlation between EUS-PPG and the clinical features related to the severity of cirrhotic portal hypertension,which indicates the feasibility of EUS-PPG in evaluating cirrhotic portal hypertension.展开更多
Two key challenges raised by a product images classification system are classification precision and classification time. In some categories, classification precision of the latest techniques, in the product images cl...Two key challenges raised by a product images classification system are classification precision and classification time. In some categories, classification precision of the latest techniques, in the product images classification system, is still low. In this paper, we propose a local texture descriptor termed fan refined local binary pattern, which captures more detailed information by integrating the spatial distribution into the local binary pattern feature. We compare our approach with different methods on a subset of product images on Amazon/e Bay and parts of PI100 and experimental results have demonstrated that our proposed approach is superior to the current existing methods. The highest classification precision is increased by 21% and the average classification time is reduced by 2/3.展开更多
Alzheimer’s disease is a non-reversible,non-curable,and progressive neurological disorder that induces the shrinkage and death of a specific neuronal population associated with memory formation and retention.It is a ...Alzheimer’s disease is a non-reversible,non-curable,and progressive neurological disorder that induces the shrinkage and death of a specific neuronal population associated with memory formation and retention.It is a frequently occurring mental illness that occurs in about 60%–80%of cases of dementia.It is usually observed between people in the age group of 60 years and above.Depending upon the severity of symptoms the patients can be categorized in Cognitive Normal(CN),Mild Cognitive Impairment(MCI)and Alzheimer’s Disease(AD).Alzheimer’s disease is the last phase of the disease where the brain is severely damaged,and the patients are not able to live on their own.Radiomics is an approach to extracting a huge number of features from medical images with the help of data characterization algorithms.Here,105 number of radiomic features are extracted and used to predict the alzhimer’s.This paper uses Support Vector Machine,K-Nearest Neighbour,Gaussian Naïve Bayes,eXtreme Gradient Boosting(XGBoost)and Random Forest to predict Alzheimer’s disease.The proposed random forest-based approach with the Radiomic features achieved an accuracy of 85%.This proposed approach also achieved 88%accuracy,88%recall,88%precision and 87%F1-score for AD vs.CN,it achieved 72%accuracy,73%recall,72%precisionand 71%F1-score for AD vs.MCI and it achieved 69%accuracy,69%recall,68%precision and 69%F1-score for MCI vs.CN.The comparative analysis shows that the proposed approach performs better than others approaches.展开更多
针对手势识别由于分割效果差,导致识别率较低等问题,提出基于改进支持向量机的动态多点手势动作识别方法。选用深度阈值法分割动态多点手势图像,提取出手掌中最大的圆细化手部区域,获取7维手部HOG(Histogram of Oriented Gradients)特...针对手势识别由于分割效果差,导致识别率较低等问题,提出基于改进支持向量机的动态多点手势动作识别方法。选用深度阈值法分割动态多点手势图像,提取出手掌中最大的圆细化手部区域,获取7维手部HOG(Histogram of Oriented Gradients)特征向量,完成手势动作图像预处理。引入支持向量机,并且通过误差项改进该算法。采用改进后的支持向量机最优线性分类特征向量,利用支持向量机输入分类后的手势特征向量,实现动态多点手势动作识别。实验结果表明,所提方法受光照影响波动小,在有光照情况下,识别率达到92.5%以上,而无光照情况下,识别率仍高于90.0%,并且图像分割信息完整、识别准确性高。展开更多
基金supported by Zhejiang Provincial Natural Science Foundation of China(LR20A010001)National Natural Science Foundation of China(12271473 and U21A20426)。
文摘In the realm of large-scale machine learning,it is crucial to explore methods for reducing computational complexity and memory demands while maintaining generalization performance.Additionally,since the collected data may contain some sensitive information,it is also of great significance to study privacy-preserving machine learning algorithms.This paper focuses on the performance of the differentially private stochastic gradient descent(SGD)algorithm based on random features.To begin,the algorithm maps the original data into a lowdimensional space,thereby avoiding the traditional kernel method for large-scale data storage requirement.Subsequently,the algorithm iteratively optimizes parameters using the stochastic gradient descent approach.Lastly,the output perturbation mechanism is employed to introduce random noise,ensuring algorithmic privacy.We prove that the proposed algorithm satisfies the differential privacy while achieving fast convergence rates under some mild conditions.
文摘Sepsis poses a serious threat to health of children in pediatric intensive care unit.The mortality from pediatric sepsis can be effectively reduced through in-time diagnosis and therapeutic intervention.The bacilliculture detection method is too time-consuming to receive timely treatment.In this research,we propose a new framework:a deep encoding network with cross features(CF-DEN)that enables accurate early detection of sepsis.Cross features are automatically constructed via the gradient boosting decision tree and distilled into the deep encoding network(DEN)we designed.The DEN is aimed at learning sufficiently effective representation from clinical test data.Each layer of the DEN fltrates the features involved in computation at current layer via attention mechanism and outputs the current prediction which is additive layer by layer to obtain the embedding feature at last layer.The framework takes the advantage of tree-based method and neural network method to extract effective representation from small clinical dataset and obtain accurate prediction in order to prompt patient to get timely treatment.We evaluate the performance of the framework on the dataset collected from Shanghai Children's Medical Center.Compared with common machine learning methods,our method achieves the increase on F1-score by 16.06%on the test set.
文摘This paper presents a method for lane boundaries detection which is not affected by the shadows, illumination and un-even road conditions. This method is based upon processing grayscale images using local gradient features, characteris-tic spectrum of lanes, and linear prediction. Firstly, points on the adjacent right and left lane are recognized using the local gradient descriptors. A simple linear prediction model is deployed to predict the direction of lane markers. The contribution of this paper is the use of vertical gradient image without converting into binary image(using suitable thre-shold), and introduction of characteristic lane gradient spectrum within the local window to locate the preciselane marking points along the horizontal scan line over the image. Experimental results show that this method has greater tolerance to shadows and low illumination conditions. A comparison is drawn between this method and recent methods reported in the literature.
基金National Natural Science Foundation of China(No.519705449)。
文摘To automatically detecting whether a person is wearing mask properly,we propose a face mask detection algorithm based on hue-saturation-value(HSV)+histogram of oriented gradient(HOG)features and support vector machines(SVM).Firstly,human face and five feature points are detected with RetinaFace face detection algorithm.The feature points are used to locate to mouth and nose region,and HSV+HOG features of this region are extracted and input to SVM for training to realize detection of wearing masks or not.Secondly,RetinaFace is used to locate to nasal tip area of face,and YCrCb elliptical skin tone model is used to detect the exposure of skin in the nasal tip area,and the optimal classification threshold can be found to determine whether the wear is properly according to experimental results.Experiments show that the accuracy of detecting whether mask is worn can reach 97.9%,and the accuracy of detecting whether mask is worn correctly can reach 87.55%,which verifies the feasibility of the algorithm.
基金Projects(61573380,61303185) supported by the National Natural Science Foundation of ChinaProjects(2016M592450,2017M612585) supported by the China Postdoctoral Science FoundationProjects(2016JJ4119,2017JJ3416) supported by the Hunan Provincial Natural Science Foundation of China
文摘It is easy for teenagers to view pornographic pictures on social networks. Many researchers have studied the detection of real pornographic pictures, but there are few studies on those that are artificial. In this work, we studied how to detect artificial pornographic pictures, especially when they are on social networks. The whole detection process can be divided into two stages： feature selection and picture detection. In the feature selection stage, seven types of features that favour picture detection were selected. In the picture detection stage, three steps were included. 1） In order to alleviate the imbalance in the number of artificial pornographic pictures and normal ones, the training dataset of artificial pornographic pictures was expanded. Therefore, the features which were extracted from the training dataset can also be expanded too. 2） In order to reduce the time of feature extraction, a fast method which extracted features based on the proportionally scaled picture rather than the original one was proposed. 3） Three tree models were compared and a gradient boost decision tree （GBDT） was selected for the final picture detection. Three sets of experimental results show that the proposed method can achieve better recognition precision and drastically reduce the time cost of the method.
基金This research was funded by College Student Innovation and Entrepreneurship Training Program,Grant Number 2021055Z and S202110082031the Special Project for Cultivating Scientific and Technological Innovation Ability of College and Middle School Students in Hebei Province,Grant Number 2021H011404.
文摘At present,underwater terrain images are all strip-shaped small fragment images preprocessed by the side-scan sonar imaging system.However,the processed underwater terrain images have inconspicuous and few feature points.In order to better realize the stitching of underwater terrain images and solve the problems of slow traditional image stitching speed,we proposed an improved algorithm for underwater terrain image stitching based on spatial gradient feature block.First,the spatial gradient fuzzy C-Means algorithm is used to divide the underwater terrain image into feature blocks with the fusion of spatial gradient information.The accelerated-KAZE(AKAZE)algorithm is used to combine the feature block information to match the reference image and the target image.Then,the random sample consensus(RANSAC)is applied to optimize the matching results.Finally,image fusion is performed with the global homography and the optimal seam-line method to improve the accuracy of image overlay fusion.The experimental results show that the proposed method in this paper effectively divides images into feature blocks by combining spatial information and gradient information,which not only solves the problem of stitching failure of underwater terrain images due to unobvious features,and further reduces the sensitivity to noise,but also effectively reduces the iterative calculation in the feature point matching process of the traditional method,and improves the stitching speed.Ghosting and shape warping are significantly eliminated by re-optimizing the overlap of the image.
文摘Objective To investigate the correlation between the clinical features and endoscopic ultrasound-guided portal pressure gradient(EUS-PPG)in patients with cirrhosis.Methods A total of 148 patients with cirrhosis and portal hypertension who underwent EUS-PPG measurement at the Third Xiangya Hospital of Central South University from March 15,2022 to June 20,2023 were selected.The clinical data of patients collected before EUS-PPG measurement were analyzed.Variations in the EUS-PPG across different clinical data subgroups were analyzed.Multivariate linear regression analysis was used to explore the independent factors influencing EUS-PPG.Results The EUS-PPG was significantly elevated in patients exhibiting red signs(16.62±5.33 mmHg VS 13.44±5.34 mmHg,t=3.616,P<0.001),gastroesophageal varices(15.78±5.30 mmHg VS 9.70±4.77 mmHg,t=4.247,P<0.001),hepatic encephalopathy(20.83±7.52 mmHg VS 14.92±5.35 mmHg,t=2.606,P=0.010),thrombocytopenia(15.66±5.39 mmHg VS 13.29±5.83mmHg,t=2.136,P=0.034),hypoproteinemia(16.13±5.86 mmHg VS 14.12±5.03 mmHg,t=2.230,P=0.027),and an increased international normalized ratio(16.25±6.00 mmHg VS 14.40±5.11mmHg,t=2.022,P=0.045).Conversely,the EUS-PPG was significantly reduced in patients with a history of splenectomy and devascularization(13.17±5.88mmHgVS15.73±5.34mmHg,t=-2.379,P=0.019).The EUS-PPG in patients with varying degrees of ascites(no VS slight VS moderate or severe:13.40±5.48 mmHg VS 15.90±5.49 mmHg VS 16.69±5.17 mmHg,F=5.188,P=0.007)and different Child-Pugh classifications(A VS B VS C:14.07±5.05 mmHg VS 15.69±5.74 mmHg VS 17.64±5.99 mmHg,F=3.066,P=0.049)increased gradually.Multivariable linear regression analysis showed that red signs(β=2.44,t=2.732,P=0.007),gastroesophageal varices(β=4.45,t=2.990,P=0.003),ascites(β=1.75,t=2.368,P=0.019),and hepatic encephalopathy(β=5.82,t=2.644,P=0.009)were independentftactors fortheelevated1EUS-PPG.Conclusion There is a significant correlation between EUS-PPG and the clinical features related to the severity of cirrhotic portal hypertension,which indicates the feasibility of EUS-PPG in evaluating cirrhotic portal hypertension.
基金Supported by the National Natural Science Foundation of China（60802061, 11426087） Supported by Key Project of Science and Technology of the Education Department Henan Province（14A120009）+1 种基金 Supported by the Program of Henan Province Young Scholar（2013GGJS-027） Supported by the Research Foundation of Henan University（2013YBZR016）
文摘Two key challenges raised by a product images classification system are classification precision and classification time. In some categories, classification precision of the latest techniques, in the product images classification system, is still low. In this paper, we propose a local texture descriptor termed fan refined local binary pattern, which captures more detailed information by integrating the spatial distribution into the local binary pattern feature. We compare our approach with different methods on a subset of product images on Amazon/e Bay and parts of PI100 and experimental results have demonstrated that our proposed approach is superior to the current existing methods. The highest classification precision is increased by 21% and the average classification time is reduced by 2/3.
文摘Alzheimer’s disease is a non-reversible,non-curable,and progressive neurological disorder that induces the shrinkage and death of a specific neuronal population associated with memory formation and retention.It is a frequently occurring mental illness that occurs in about 60%–80%of cases of dementia.It is usually observed between people in the age group of 60 years and above.Depending upon the severity of symptoms the patients can be categorized in Cognitive Normal(CN),Mild Cognitive Impairment(MCI)and Alzheimer’s Disease(AD).Alzheimer’s disease is the last phase of the disease where the brain is severely damaged,and the patients are not able to live on their own.Radiomics is an approach to extracting a huge number of features from medical images with the help of data characterization algorithms.Here,105 number of radiomic features are extracted and used to predict the alzhimer’s.This paper uses Support Vector Machine,K-Nearest Neighbour,Gaussian Naïve Bayes,eXtreme Gradient Boosting(XGBoost)and Random Forest to predict Alzheimer’s disease.The proposed random forest-based approach with the Radiomic features achieved an accuracy of 85%.This proposed approach also achieved 88%accuracy,88%recall,88%precision and 87%F1-score for AD vs.CN,it achieved 72%accuracy,73%recall,72%precisionand 71%F1-score for AD vs.MCI and it achieved 69%accuracy,69%recall,68%precision and 69%F1-score for MCI vs.CN.The comparative analysis shows that the proposed approach performs better than others approaches.
文摘针对手势识别由于分割效果差,导致识别率较低等问题,提出基于改进支持向量机的动态多点手势动作识别方法。选用深度阈值法分割动态多点手势图像,提取出手掌中最大的圆细化手部区域,获取7维手部HOG(Histogram of Oriented Gradients)特征向量,完成手势动作图像预处理。引入支持向量机,并且通过误差项改进该算法。采用改进后的支持向量机最优线性分类特征向量,利用支持向量机输入分类后的手势特征向量,实现动态多点手势动作识别。实验结果表明,所提方法受光照影响波动小,在有光照情况下,识别率达到92.5%以上,而无光照情况下,识别率仍高于90.0%,并且图像分割信息完整、识别准确性高。
