空调热交换器性能异常检测技术是快速判断民机空调系统运行状态并合理安排维修任务的关键,传统的异常检测方法难以有效处理高维时序数据,无法实现系统早期故障预警。为此,本文提出了一种基于长短期记忆网络(LSTM,long-short term memory...空调热交换器性能异常检测技术是快速判断民机空调系统运行状态并合理安排维修任务的关键,传统的异常检测方法难以有效处理高维时序数据,无法实现系统早期故障预警。为此,本文提出了一种基于长短期记忆网络(LSTM,long-short term memory)与自编码器(AE,autoencoder)模型的无监督异常检测方法,用以识别民机空调系统异常运行状态。首先,基于民机空调系统原始传感器参数构建表征空调热交换器性能的特征监测参数;其次,构建LSTM-AE模型进行数据特征重构并计算重构误差;最后,使用孤立森林(iForest, isolation forest)进行无监督异常监测。将本文构建的无监督异常检测方法与传统方法对比,并建立模型评估指标,验证结果表明,所构建的模型方法可以对民机空调热交换器性能异常状态进行有效检测。展开更多
Dear Editor,Dengue virus(DENV,family Flaviviridae,genus Flavivirus)serotypes 1 to 4(DENV-1,-2,-3,and-4)are responsible for more than 100 million infections per year worldwide.Symptoms of DENV infection can be diverse,...Dear Editor,Dengue virus(DENV,family Flaviviridae,genus Flavivirus)serotypes 1 to 4(DENV-1,-2,-3,and-4)are responsible for more than 100 million infections per year worldwide.Symptoms of DENV infection can be diverse,reaching from an acute febrile illness to the more severe,sometimes fatal dengue haemorrhagic fever/dengue shock syndrome.展开更多
Objective:To determine the suitable ecological habitats of Aedes(Ae.)aegypti and Ae.albopictus in Iran due to climate change by the 2070s.Methods:All data relating to the spatial distribution of Ae.aegypti and Ae.albo...Objective:To determine the suitable ecological habitats of Aedes(Ae.)aegypti and Ae.albopictus in Iran due to climate change by the 2070s.Methods:All data relating to the spatial distribution of Ae.aegypti and Ae.albopictus worldwide,which indicated the geographical coordinates of the collection sites of these mosquitoes,were extracted from online scientific websites and entered into an Excel file.The effect of climatic and environmental variables on these mosquitoes was evaluated using the MaxEnt model in the current and future climatic conditions in the 2030s,2050s,and 2070s.Results:The most suitable areas for the establishment of Ae.aegypti are located in the southern and northern coastal areas of Iran,based on the model outputs.The modelling result for suitable ecological niches of Ae.albopictus shows that in the current climatic conditions,the southern half of Iran from east to west,and parts of the northern coasts are prone to the presence of this species.In the future,some regions,such as Gilan and Golestan provinces,will have more potential to exist/establish Ae.albopictus.Also,according to the different climate change scenarios,suitable habitats for this species will gradually change to the northwest and west of the country.The temperature of the wettest season of the year(Bio8)and average annual temperature(Bio1)were the most effective factors in predicting the model for Ae.aegypti and Ae.albopictus,respectively.Conclusions:It is required to focus on entomological studies using different collection methods in the vulnerable areas of Iran.The future modelling results can also be used for long-term planning to prevent the entry and establishment of these invasive Aedes vectors in the country.展开更多
To address the issues of incomplete information,blurred details,loss of details,and insufficient contrast in infrared and visible image fusion,an image fusion algorithm based on a convolutional autoencoder is proposed...To address the issues of incomplete information,blurred details,loss of details,and insufficient contrast in infrared and visible image fusion,an image fusion algorithm based on a convolutional autoencoder is proposed.The region attention module is meant to extract the background feature map based on the distinct properties of the background feature map and the detail feature map.A multi-scale convolution attention module is suggested to enhance the communication of feature information.At the same time,the feature transformation module is introduced to learn more robust feature representations,aiming to preserve the integrity of image information.This study uses three available datasets from TNO,FLIR,and NIR to perform thorough quantitative and qualitative trials with five additional algorithms.The methods are assessed based on four indicators:information entropy(EN),standard deviation(SD),spatial frequency(SF),and average gradient(AG).Object detection experiments were done on the M3FD dataset to further verify the algorithm’s performance in comparison with five other algorithms.The algorithm’s accuracy was evaluated using the mean average precision at a threshold of 0.5(mAP@0.5)index.Comprehensive experimental findings show that CAEFusion performs well in subjective visual and objective evaluation criteria and has promising potential in downstream object detection tasks.展开更多
分布式显示控制系统(以下简称分布式)被广泛应用于指挥调度、视频会议、信息发布等领域,是高清视频信号传输和调度的核心,也担负着大量音频信号的传输和调度任务。分布式在与音频扩声系统之间相互传输音频信号时,通常需要通过非平衡模...分布式显示控制系统(以下简称分布式)被广泛应用于指挥调度、视频会议、信息发布等领域,是高清视频信号传输和调度的核心,也担负着大量音频信号的传输和调度任务。分布式在与音频扩声系统之间相互传输音频信号时,通常需要通过非平衡模拟信号线缆实现,存在多次数模(Digital to Analog,D/A)和模数(Analog to Digital,A/D)转换,造成音频信号质量显著下降和精度损失。针对该问题,提出将AES67音频网关作为分布式和音频扩声系统之间的桥梁,在2个系统之间通过AES67实现网际互连协议(Internet Protocol,IP)全数字方式转换与传输,保证高质量的音频传输和性能。展开更多
文摘空调热交换器性能异常检测技术是快速判断民机空调系统运行状态并合理安排维修任务的关键,传统的异常检测方法难以有效处理高维时序数据,无法实现系统早期故障预警。为此,本文提出了一种基于长短期记忆网络(LSTM,long-short term memory)与自编码器(AE,autoencoder)模型的无监督异常检测方法,用以识别民机空调系统异常运行状态。首先,基于民机空调系统原始传感器参数构建表征空调热交换器性能的特征监测参数;其次,构建LSTM-AE模型进行数据特征重构并计算重构误差;最后,使用孤立森林(iForest, isolation forest)进行无监督异常监测。将本文构建的无监督异常检测方法与传统方法对比,并建立模型评估指标,验证结果表明,所构建的模型方法可以对民机空调热交换器性能异常状态进行有效检测。
基金Supported by the German Research Foundation (JO 1276/5-1)the Federal Ministry of Education and Research of Germany (BMBF) under the project NEED (01Kl2022).
文摘Dear Editor,Dengue virus(DENV,family Flaviviridae,genus Flavivirus)serotypes 1 to 4(DENV-1,-2,-3,and-4)are responsible for more than 100 million infections per year worldwide.Symptoms of DENV infection can be diverse,reaching from an acute febrile illness to the more severe,sometimes fatal dengue haemorrhagic fever/dengue shock syndrome.
基金Research Deputy,Tehran University of Medical Sciences,grant No.46857。
文摘Objective:To determine the suitable ecological habitats of Aedes(Ae.)aegypti and Ae.albopictus in Iran due to climate change by the 2070s.Methods:All data relating to the spatial distribution of Ae.aegypti and Ae.albopictus worldwide,which indicated the geographical coordinates of the collection sites of these mosquitoes,were extracted from online scientific websites and entered into an Excel file.The effect of climatic and environmental variables on these mosquitoes was evaluated using the MaxEnt model in the current and future climatic conditions in the 2030s,2050s,and 2070s.Results:The most suitable areas for the establishment of Ae.aegypti are located in the southern and northern coastal areas of Iran,based on the model outputs.The modelling result for suitable ecological niches of Ae.albopictus shows that in the current climatic conditions,the southern half of Iran from east to west,and parts of the northern coasts are prone to the presence of this species.In the future,some regions,such as Gilan and Golestan provinces,will have more potential to exist/establish Ae.albopictus.Also,according to the different climate change scenarios,suitable habitats for this species will gradually change to the northwest and west of the country.The temperature of the wettest season of the year(Bio8)and average annual temperature(Bio1)were the most effective factors in predicting the model for Ae.aegypti and Ae.albopictus,respectively.Conclusions:It is required to focus on entomological studies using different collection methods in the vulnerable areas of Iran.The future modelling results can also be used for long-term planning to prevent the entry and establishment of these invasive Aedes vectors in the country.
文摘To address the issues of incomplete information,blurred details,loss of details,and insufficient contrast in infrared and visible image fusion,an image fusion algorithm based on a convolutional autoencoder is proposed.The region attention module is meant to extract the background feature map based on the distinct properties of the background feature map and the detail feature map.A multi-scale convolution attention module is suggested to enhance the communication of feature information.At the same time,the feature transformation module is introduced to learn more robust feature representations,aiming to preserve the integrity of image information.This study uses three available datasets from TNO,FLIR,and NIR to perform thorough quantitative and qualitative trials with five additional algorithms.The methods are assessed based on four indicators:information entropy(EN),standard deviation(SD),spatial frequency(SF),and average gradient(AG).Object detection experiments were done on the M3FD dataset to further verify the algorithm’s performance in comparison with five other algorithms.The algorithm’s accuracy was evaluated using the mean average precision at a threshold of 0.5(mAP@0.5)index.Comprehensive experimental findings show that CAEFusion performs well in subjective visual and objective evaluation criteria and has promising potential in downstream object detection tasks.
文摘分布式显示控制系统(以下简称分布式)被广泛应用于指挥调度、视频会议、信息发布等领域,是高清视频信号传输和调度的核心,也担负着大量音频信号的传输和调度任务。分布式在与音频扩声系统之间相互传输音频信号时,通常需要通过非平衡模拟信号线缆实现,存在多次数模(Digital to Analog,D/A)和模数(Analog to Digital,A/D)转换,造成音频信号质量显著下降和精度损失。针对该问题,提出将AES67音频网关作为分布式和音频扩声系统之间的桥梁,在2个系统之间通过AES67实现网际互连协议(Internet Protocol,IP)全数字方式转换与传输,保证高质量的音频传输和性能。