Weather phenomenon recognition plays an important role in the field of meteorology.Nowadays,weather radars and weathers sensor have been widely used for weather recognition.However,given the high cost in deploying and...Weather phenomenon recognition plays an important role in the field of meteorology.Nowadays,weather radars and weathers sensor have been widely used for weather recognition.However,given the high cost in deploying and maintaining the devices,it is difficult to apply them to intensive weather phenomenon recognition.Moreover,advanced machine learning models such as Convolutional Neural Networks(CNNs)have shown a lot of promise in meteorology,but these models also require intensive computation and large memory,which make it difficult to use them in reality.In practice,lightweight models are often used to solve such problems.However,lightweight models often result in significant performance losses.To this end,after taking a deep dive into a large number of lightweight models and summarizing their shortcomings,we propose a novel lightweight CNNs model which is constructed based on new building blocks.The experimental results show that the model proposed in this paper has comparable performance with the mainstream non-lightweight model while also saving 25 times of memory consumption.Such memory reduction is even better than that of existing lightweight models.展开更多
This paper presents an effective machine learning-based depth selection algorithm for CTU(Coding Tree Unit)in HEVC(High Efficiency Video Coding).Existing machine learning methods are limited in their ability in handli...This paper presents an effective machine learning-based depth selection algorithm for CTU(Coding Tree Unit)in HEVC(High Efficiency Video Coding).Existing machine learning methods are limited in their ability in handling the initial depth decision of CU(Coding Unit)and selecting the proper set of input features for the depth selection model.In this paper,we first propose a new classification approach for the initial division depth prediction.In particular,we study the correlation of the texture complexity,QPs(quantization parameters)and the depth decision of the CUs to forecast the original partition depth of the current CUs.Secondly,we further aim to determine the input features of the classifier by analysing the correlation between depth decision of the CUs,picture distortion and the bit-rate.Using the found relationships,we also study a decision method for the end partition depth of the current CUs using bit-rate and picture distortion as input.Finally,we formulate the depth division of the CUs as a binary classification problem and use the nearest neighbor classifier to conduct classification.Our proposed method can significantly improve the efficiency of interframe coding by circumventing the traversing cost of the division depth.It shows that the mentioned method can reduce the time spent by 34.56%compared to HM-16.9 while keeping the partition depth of the CUs correct.展开更多
With the global climate change,the high-altitude detection is more and more important in the climate prediction,and the input-output characteristic curve of the air pressure sensor is offset due to the interference of...With the global climate change,the high-altitude detection is more and more important in the climate prediction,and the input-output characteristic curve of the air pressure sensor is offset due to the interference of the tested object and the environment under test,and the nonlinear error is generated.Aiming at the difficulty of nonlinear correction of pressure sensor and the low accuracy of correction results,depth neural network model was established based on wavelet function,and Levenberg-Marquardt algorithm is used to update network parameters to realize the nonlinear correction of pressure sensor.The experimental results show that compared with the traditional neural network model,the improved depth neural network not only accelerates the convergence rate,but also improves the correction accuracy,meets the error requirements of upper-air detection,and has a good generalization ability,which can be extended to the nonlinear correction of similar sensors.展开更多
In recent years,the problem of“Impolite Pedestrian”in front of the zebra crossing has aroused widespread concern from all walks of life.The traffic sector’s governance measures have become more serious.The traditio...In recent years,the problem of“Impolite Pedestrian”in front of the zebra crossing has aroused widespread concern from all walks of life.The traffic sector’s governance measures have become more serious.The traditional way of governance is on-site law enforcement,which requires a lot of manpower and material resources and is low efficiency.An enhanced YOLOv3-tiny model is proposed for pedestrians and vehicle detection in traffic monitoring.By modifying the backbone network structure of YOLOv3-tiny model,introducing deep detachable convolution operation,and designing the basic residual block unit of the network,the feature extraction ability of the backbone network is enhanced.The improved model is trained on the VOC2007+VOC2012 training set,and the trained model is tested for performance on the test data set.The experimental results show that:the mean Average Precision(mAP)increased from 0.672 to 0.732,increasing the measurement accuracy by 9%.The Intersection over Union(IoU)increased from 0.783 to 0.855,increasing the coverage accuracy by 7.2%.The enhanced YOLOv3-tiny model has higher measurement accuracy than the original model.Applying this model to the 1080P traffic video on the NVIDIA RTX 2080,the detection speed is 150 FPS,which can fully achieve real-time detection.Through the analysis of pedestrians and vehicle coordinates,it is judged whether or not illegal acts occur.For illegal vehicles,save three pictures as the basis for law enforcement,which forms an important supplement to off-site law enforcement.展开更多
Current methods for the detection of differential gene expression focus on finding individual genes that may be responsible for certain diseases or external irritants. However, for common genetic diseases, multiple ge...Current methods for the detection of differential gene expression focus on finding individual genes that may be responsible for certain diseases or external irritants. However, for common genetic diseases, multiple genes and their interactions should be understood and treated together during the exploration of disease causes and possible drug design. The present study focuses on analyzing the dynamic patterns of co-regulated modules during biological progression and determining those having remarkably varying activities, using the yeast cell cycle as a case study. We first constructed dynamic active protein-protein interaction networks by modeling the activity of proteins and assembling the dynamic co-regulation protein network at each time point. The dynamic active modules were detected using a method based on the Bayesian graphical model and then the modules with the most varied dispersion of clustering coefficients, which could be responsible for the dynamic mechanism of the cell cycle, were identified. Comparison of results from our functional module detection with the state-of-art functional module detection methods and validation of the ranking of activities of functional modules using GO annotations demonstrate the efficacy of our method for narrowing the scope of possible essential responding modules that could provide multiple targets for biologists to further experimentally validate.展开更多
Personalized medicine is defined as "a model of healthcare that is predictive, personalized, preventive,and participator" and has very broad content. With the rapid development of high-throughput technologies, an ex...Personalized medicine is defined as "a model of healthcare that is predictive, personalized, preventive,and participator" and has very broad content. With the rapid development of high-throughput technologies, an explosive accumulation of biological information is collected from multiple layers of biological processes, including genomics, transcriptomics, proteomics, metabonomics, and interactomics(omics). Implementing integrative analysis of these multiple omics data is the best way of deriving systematical and comprehensive views of living organisms, achieving better understanding of disease mechanisms, and finding operable personalized health treatments. With the help of computational methods, research in the field of biology and biomedicine has gained tremendous benefits over the past few decades. In the new era of personalized medicine, we will rely more on the assistance of computational analysis. In this paper, we briefly review the generation of multiple omics and their basic characteristics. And then the challenges and opportunities for computational analysis are discussed and some state-of-art analysis methods that were recently proposed by peers for integrative analysis of multiple omics data are reviewed. We foresee that further integrated omics data platform and computational tools would help to translate the biological knowledge to clinical usage and accelerate development of personalized medicine.展开更多
基金This paper is supported by the following funds:National Key R&D Program of China(2018YFF01010100)National natural science foundation of China(61672064)+1 种基金Basic Research Program of Qinghai Province under Grants No.2020-ZJ-709Advanced information network Beijing laboratory(PXM2019_014204_500029).
文摘Weather phenomenon recognition plays an important role in the field of meteorology.Nowadays,weather radars and weathers sensor have been widely used for weather recognition.However,given the high cost in deploying and maintaining the devices,it is difficult to apply them to intensive weather phenomenon recognition.Moreover,advanced machine learning models such as Convolutional Neural Networks(CNNs)have shown a lot of promise in meteorology,but these models also require intensive computation and large memory,which make it difficult to use them in reality.In practice,lightweight models are often used to solve such problems.However,lightweight models often result in significant performance losses.To this end,after taking a deep dive into a large number of lightweight models and summarizing their shortcomings,we propose a novel lightweight CNNs model which is constructed based on new building blocks.The experimental results show that the model proposed in this paper has comparable performance with the mainstream non-lightweight model while also saving 25 times of memory consumption.Such memory reduction is even better than that of existing lightweight models.
基金This paper is supported by the National Natural Science Foundation of China(61672064)Basic Research Program of Qinghai Province(No.2020-ZJ-709)the project for advanced information network Beijing laboratory(PXM2019_014204_500029).
文摘This paper presents an effective machine learning-based depth selection algorithm for CTU(Coding Tree Unit)in HEVC(High Efficiency Video Coding).Existing machine learning methods are limited in their ability in handling the initial depth decision of CU(Coding Unit)and selecting the proper set of input features for the depth selection model.In this paper,we first propose a new classification approach for the initial division depth prediction.In particular,we study the correlation of the texture complexity,QPs(quantization parameters)and the depth decision of the CUs to forecast the original partition depth of the current CUs.Secondly,we further aim to determine the input features of the classifier by analysing the correlation between depth decision of the CUs,picture distortion and the bit-rate.Using the found relationships,we also study a decision method for the end partition depth of the current CUs using bit-rate and picture distortion as input.Finally,we formulate the depth division of the CUs as a binary classification problem and use the nearest neighbor classifier to conduct classification.Our proposed method can significantly improve the efficiency of interframe coding by circumventing the traversing cost of the division depth.It shows that the mentioned method can reduce the time spent by 34.56%compared to HM-16.9 while keeping the partition depth of the CUs correct.
基金This paper is supported by the following funds:National Key R&D Program of China(2018YFF01010100)National natural science foundation of China(61672064),Beijing natural science foundation project(4172001)Advanced information network Beijing laboratory(PXM2019_014204_500029).
文摘With the global climate change,the high-altitude detection is more and more important in the climate prediction,and the input-output characteristic curve of the air pressure sensor is offset due to the interference of the tested object and the environment under test,and the nonlinear error is generated.Aiming at the difficulty of nonlinear correction of pressure sensor and the low accuracy of correction results,depth neural network model was established based on wavelet function,and Levenberg-Marquardt algorithm is used to update network parameters to realize the nonlinear correction of pressure sensor.The experimental results show that compared with the traditional neural network model,the improved depth neural network not only accelerates the convergence rate,but also improves the correction accuracy,meets the error requirements of upper-air detection,and has a good generalization ability,which can be extended to the nonlinear correction of similar sensors.
基金supported by the following funds:National Key R&D Program of China(2018YFF01010100)National natural science foundation of China(61672064)+1 种基金Beijing natural science foundation project(4172001)Advanced information network Beijing laboratory(PXM2019_014204_500029).
文摘In recent years,the problem of“Impolite Pedestrian”in front of the zebra crossing has aroused widespread concern from all walks of life.The traffic sector’s governance measures have become more serious.The traditional way of governance is on-site law enforcement,which requires a lot of manpower and material resources and is low efficiency.An enhanced YOLOv3-tiny model is proposed for pedestrians and vehicle detection in traffic monitoring.By modifying the backbone network structure of YOLOv3-tiny model,introducing deep detachable convolution operation,and designing the basic residual block unit of the network,the feature extraction ability of the backbone network is enhanced.The improved model is trained on the VOC2007+VOC2012 training set,and the trained model is tested for performance on the test data set.The experimental results show that:the mean Average Precision(mAP)increased from 0.672 to 0.732,increasing the measurement accuracy by 9%.The Intersection over Union(IoU)increased from 0.783 to 0.855,increasing the coverage accuracy by 7.2%.The enhanced YOLOv3-tiny model has higher measurement accuracy than the original model.Applying this model to the 1080P traffic video on the NVIDIA RTX 2080,the detection speed is 150 FPS,which can fully achieve real-time detection.Through the analysis of pedestrians and vehicle coordinates,it is judged whether or not illegal acts occur.For illegal vehicles,save three pictures as the basis for law enforcement,which forms an important supplement to off-site law enforcement.
基金supported by the National Natural Science Foundation of China (No.30970780)Ph.D.Programs Foundation of Ministry of Education of China (No.20091103110005)
文摘Current methods for the detection of differential gene expression focus on finding individual genes that may be responsible for certain diseases or external irritants. However, for common genetic diseases, multiple genes and their interactions should be understood and treated together during the exploration of disease causes and possible drug design. The present study focuses on analyzing the dynamic patterns of co-regulated modules during biological progression and determining those having remarkably varying activities, using the yeast cell cycle as a case study. We first constructed dynamic active protein-protein interaction networks by modeling the activity of proteins and assembling the dynamic co-regulation protein network at each time point. The dynamic active modules were detected using a method based on the Bayesian graphical model and then the modules with the most varied dispersion of clustering coefficients, which could be responsible for the dynamic mechanism of the cell cycle, were identified. Comparison of results from our functional module detection with the state-of-art functional module detection methods and validation of the ranking of activities of functional modules using GO annotations demonstrate the efficacy of our method for narrowing the scope of possible essential responding modules that could provide multiple targets for biologists to further experimentally validate.
基金supported by the Project for the Innovation Team of Beijing, the National Natural Science Foundation of China (No. 81370038)the Beijing Natural Science Foundation (No. 7142012)+2 种基金the Science and Technology Project of Beijing Municipal Education Commission (No. km201410005003)the Rixin Fund of Beijing University of Technology (No. 2013-RX-L04)the Basic Research Fund of Beijing University of Technology
文摘Personalized medicine is defined as "a model of healthcare that is predictive, personalized, preventive,and participator" and has very broad content. With the rapid development of high-throughput technologies, an explosive accumulation of biological information is collected from multiple layers of biological processes, including genomics, transcriptomics, proteomics, metabonomics, and interactomics(omics). Implementing integrative analysis of these multiple omics data is the best way of deriving systematical and comprehensive views of living organisms, achieving better understanding of disease mechanisms, and finding operable personalized health treatments. With the help of computational methods, research in the field of biology and biomedicine has gained tremendous benefits over the past few decades. In the new era of personalized medicine, we will rely more on the assistance of computational analysis. In this paper, we briefly review the generation of multiple omics and their basic characteristics. And then the challenges and opportunities for computational analysis are discussed and some state-of-art analysis methods that were recently proposed by peers for integrative analysis of multiple omics data are reviewed. We foresee that further integrated omics data platform and computational tools would help to translate the biological knowledge to clinical usage and accelerate development of personalized medicine.