There is a widespread agreement that lung cancer is one of the deadliest types of cancer,affecting both women and men.As a result,detecting lung cancer at an early stage is crucial to create an accurate treatment plan...There is a widespread agreement that lung cancer is one of the deadliest types of cancer,affecting both women and men.As a result,detecting lung cancer at an early stage is crucial to create an accurate treatment plan and forecasting the reaction of the patient to the adopted treatment.For this reason,the development of convolutional neural networks(CNNs)for the task of lung cancer classification has recently seen a trend in attention.CNNs have great potential,but they need a lot of training data and struggle with input alterations.To address these limitations of CNNs,a novel machine-learning architecture of capsule networks has been presented,and it has the potential to completely transform the areas of deep learning.Capsule networks,which are the focus of this work,are interesting because they can withstand rotation and affine translation with relatively little training data.This research optimizes the performance of CapsNets by designing a new architecture that allows them to perform better on the challenge of lung cancer classification.The findings demonstrate that the proposed capsule network method outperforms CNNs on the lung cancer classification challenge.CapsNet with a single convolution layer and 32 features(CN-1-32),CapsNet with a single convolution layer and 64 features(CN-1-64),and CapsNet with a double convolution layer and 64 features(CN-2-64)are the three capsulel networks developed in this research for lung cancer classification.Lung nodules,both benign and malignant,are classified using these networks using CT images.The LIDC-IDRI database was utilized to assess the performance of those networks.Based on the testing results,CN-2-64 network performed better out of the three networks tested,with a specificity of 98.37%,sensitivity of 97.47%and an accuracy of 97.92%.展开更多
A global operational land imager(GOLI)Landsat-8 daytime active fire detection algorithm is presented.It utilizes established contextual active fire detection approaches but takes advantage of the significant increase ...A global operational land imager(GOLI)Landsat-8 daytime active fire detection algorithm is presented.It utilizes established contextual active fire detection approaches but takes advantage of the significant increase in fire reflectance in Landsat-8 band 7(2.20μm)relative to band 4(0.66μm).The detection thresholds are fixed and based on a statistical examination of 39 million non-burning Landsat-8 pixels.Multi-temporal tests based on band 7 reflectance and relative changes in normalized difference vegetation index in the previous six months are used to reduce commissions errors.The probabilities of active fire detection for the GOLI and two recent Landsat-8 active fire detection algorithms are simulated to provide insights into their performance with respect to the fire size and temperature.The algorithms are applied to 11 Landsat-8 images that encompass a range of burning conditions and environments.Commission and omission errors are assessed by visual interpretation of detected active fire locations and by examination of the Landsat-8 images and higher spatial resolution Google Earth imagery.The GOLI algorithm has lower omission and comparable commission errors than the recent Landsat-8 active fire detection algorithms.The GOLI algorithm has demonstrable potential for global application and is suitable for implementation with other Landsat-like reflective wavelength sensors.展开更多
The Brazilian Tropical Moist Forest Biome(BTMFB)spans almost 4 million km^(2) and is subject to extensive annual fires that have been categorized into deforestation,maintenance,and forest fire types.Information on fir...The Brazilian Tropical Moist Forest Biome(BTMFB)spans almost 4 million km^(2) and is subject to extensive annual fires that have been categorized into deforestation,maintenance,and forest fire types.Information on fire types is important as they have different atmospheric emissions and ecological impacts.A supervised classification methodology is presented to classify the fire type of MODerate resolution Imaging Spectroradiometer(MODIS)active fire detections using training data defined by consideration of Brazilian government forest monitoring program annual land cover maps,and using predictor variables concerned with fuel flammability,fuel load,fire behavior,fire seasonality,fire annual frequency,proximity to surface transportation,and local temperature.The fire seasonality,local temperature,and fuel flammability were the most influential on the classification.Classified fire type results for all 1.6 million MODIS Terra and Aqua BTMFB active fire detections over eight years(2003–2010)are presented with an overall fire type classification accuracy of 90.9%(kappa 0.824).The fire type user’s and producer’s classification accuracies were respectively 92.4%and 94.4%(maintenance fires),88.4%and 87.5%(forest fires),and,88.7%and 75.0%(deforestation fires).The spatial and temporal distribution of the classified fire types are presented and are similar to patterns reported in the available recent literature.展开更多
文摘There is a widespread agreement that lung cancer is one of the deadliest types of cancer,affecting both women and men.As a result,detecting lung cancer at an early stage is crucial to create an accurate treatment plan and forecasting the reaction of the patient to the adopted treatment.For this reason,the development of convolutional neural networks(CNNs)for the task of lung cancer classification has recently seen a trend in attention.CNNs have great potential,but they need a lot of training data and struggle with input alterations.To address these limitations of CNNs,a novel machine-learning architecture of capsule networks has been presented,and it has the potential to completely transform the areas of deep learning.Capsule networks,which are the focus of this work,are interesting because they can withstand rotation and affine translation with relatively little training data.This research optimizes the performance of CapsNets by designing a new architecture that allows them to perform better on the challenge of lung cancer classification.The findings demonstrate that the proposed capsule network method outperforms CNNs on the lung cancer classification challenge.CapsNet with a single convolution layer and 32 features(CN-1-32),CapsNet with a single convolution layer and 64 features(CN-1-64),and CapsNet with a double convolution layer and 64 features(CN-2-64)are the three capsulel networks developed in this research for lung cancer classification.Lung nodules,both benign and malignant,are classified using these networks using CT images.The LIDC-IDRI database was utilized to assess the performance of those networks.Based on the testing results,CN-2-64 network performed better out of the three networks tested,with a specificity of 98.37%,sensitivity of 97.47%and an accuracy of 97.92%.
基金funded by the NASA Land Cover/Land Use Change(LCLUC14-2):Multi-Source Land Imaging Science Program,Grant[NNX15AK94G]by the U.S.Department of Interior,U.S.Geological Survey(USGS)under grant[G12PC00069].
文摘A global operational land imager(GOLI)Landsat-8 daytime active fire detection algorithm is presented.It utilizes established contextual active fire detection approaches but takes advantage of the significant increase in fire reflectance in Landsat-8 band 7(2.20μm)relative to band 4(0.66μm).The detection thresholds are fixed and based on a statistical examination of 39 million non-burning Landsat-8 pixels.Multi-temporal tests based on band 7 reflectance and relative changes in normalized difference vegetation index in the previous six months are used to reduce commissions errors.The probabilities of active fire detection for the GOLI and two recent Landsat-8 active fire detection algorithms are simulated to provide insights into their performance with respect to the fire size and temperature.The algorithms are applied to 11 Landsat-8 images that encompass a range of burning conditions and environments.Commission and omission errors are assessed by visual interpretation of detected active fire locations and by examination of the Landsat-8 images and higher spatial resolution Google Earth imagery.The GOLI algorithm has lower omission and comparable commission errors than the recent Landsat-8 active fire detection algorithms.The GOLI algorithm has demonstrable potential for global application and is suitable for implementation with other Landsat-like reflective wavelength sensors.
文摘The Brazilian Tropical Moist Forest Biome(BTMFB)spans almost 4 million km^(2) and is subject to extensive annual fires that have been categorized into deforestation,maintenance,and forest fire types.Information on fire types is important as they have different atmospheric emissions and ecological impacts.A supervised classification methodology is presented to classify the fire type of MODerate resolution Imaging Spectroradiometer(MODIS)active fire detections using training data defined by consideration of Brazilian government forest monitoring program annual land cover maps,and using predictor variables concerned with fuel flammability,fuel load,fire behavior,fire seasonality,fire annual frequency,proximity to surface transportation,and local temperature.The fire seasonality,local temperature,and fuel flammability were the most influential on the classification.Classified fire type results for all 1.6 million MODIS Terra and Aqua BTMFB active fire detections over eight years(2003–2010)are presented with an overall fire type classification accuracy of 90.9%(kappa 0.824).The fire type user’s and producer’s classification accuracies were respectively 92.4%and 94.4%(maintenance fires),88.4%and 87.5%(forest fires),and,88.7%and 75.0%(deforestation fires).The spatial and temporal distribution of the classified fire types are presented and are similar to patterns reported in the available recent literature.
