The application of deep learning techniques in the medical field,specifically for Atrial Fibrillation(AFib)detection through Electrocardiogram(ECG)signals,has witnessed significant interest.Accurate and timely diagnos...The application of deep learning techniques in the medical field,specifically for Atrial Fibrillation(AFib)detection through Electrocardiogram(ECG)signals,has witnessed significant interest.Accurate and timely diagnosis increases the patient’s chances of recovery.However,issues like overfitting and inconsistent accuracy across datasets remain challenges.In a quest to address these challenges,a study presents two prominent deep learning architectures,ResNet-50 and DenseNet-121,to evaluate their effectiveness in AFib detection.The aim was to create a robust detection mechanism that consistently performs well.Metrics such as loss,accuracy,precision,sensitivity,and Area Under the Curve(AUC)were utilized for evaluation.The findings revealed that ResNet-50 surpassed DenseNet-121 in all evaluated categories.It demonstrated lower loss rate 0.0315 and 0.0305 superior accuracy of 98.77%and 98.88%,precision of 98.78%and 98.89%and sensitivity of 98.76%and 98.86%for training and validation,hinting at its advanced capability for AFib detection.These insights offer a substantial contribution to the existing literature on deep learning applications for AFib detection from ECG signals.The comparative performance data assists future researchers in selecting suitable deep-learning architectures for AFib detection.Moreover,the outcomes of this study are anticipated to stimulate the development of more advanced and efficient ECG-based AFib detection methodologies,for more accurate and early detection of AFib,thereby fostering improved patient care and outcomes.展开更多
With the increasing popularity of civilian unmanned aerial vehicles(UAVs),safety issues arising from unsafe operations and terrorist activities have received growing attention.To address this problem,an accurate class...With the increasing popularity of civilian unmanned aerial vehicles(UAVs),safety issues arising from unsafe operations and terrorist activities have received growing attention.To address this problem,an accurate classification and positioning system is needed.Considering that UAVs usually use radio frequency(RF)signals for video transmission,in this paper,we design a passive distributed monitoring system that can classify and locate UAVs according to their RF signals.Specifically,three passive receivers are arranged in different locations to receive RF signals.Due to the noncooperation between a UAV and receivers,it is necessary to detect whether there is a UAV signal from the received signals.Hence,convolutional neural network(CNN)is proposed to not only detect the presence of the UAV,but also classify its type.After the UAV signal is detected,the time difference of arrival(TDOA)of the UAV signal arriving at the receiver is estimated by the cross-correlation method to obtain the corresponding distance difference.Finally,the Chan algorithm is used to calculate the location of the UAV.We deploy a distributed system constructed by three software defined radio(SDR)receivers on the campus playground,and conduct extensive experiments in a real wireless environment.The experimental results have successfully validated the proposed system.展开更多
Given the advances in satellite altimetry and multibeam bathymetry,benthic terrain classification based on digital bathymetric models(DBMs)has been widely used for the mapping of benthic topographies.For instance,coba...Given the advances in satellite altimetry and multibeam bathymetry,benthic terrain classification based on digital bathymetric models(DBMs)has been widely used for the mapping of benthic topographies.For instance,cobaltrich crusts(CRCs)are important mineral resources found on seamounts and guyots in the western Pacific Ocean.Thick,plate-like CRCs are known to form on the summit and slopes of seamounts at the 1000–3000 m depth,while the relationship between seamount topography and spatial distribution of CRCs remains unclear.The benthic terrain classification of seamounts can solve this problem,thereby,facilitating the rapid exploration of seamount CRCs.Our study used an EM122 multibeam echosounder to retrieve high-resolution bathymetry data in the CRCs contract license area of China,i.e.,the Jiaxie Guyots in 2015 and 2016.Based on the DBM construted by bathymetirc data,broad-and fine-scale bathymetric position indices were utilized for quantitative classification of the terrain units of the Jiaxie Guyots on multiple scales.The classification revealed four first-order terrain units(e.g.,flat,crest,slope,and depression)and eleven second-order terrain units(e.g.,local crests,depressions on crests,gentle slopes,crests on slopes,and local depressions,etc.).Furthermore,the classification of the terrain and geological analysis indicated that the Weijia Guyot has a large flat summit,with local crests at the southern summit,whereas most of the guyot flanks were covered by gentle slopes.“Radial”mountain ridges have developed on the eastern side,while large-scale gravitational landslides have developed on the western and southern flanks.Additionally,landslide masses can be observed at the bottom of these slopes.The coverage of local crests on the seamount is∼1000 km^(2),and the local crests on the peak and flanks of the guyots may be the areas where thick and continuous plate-like CRCs are likely to occur.展开更多
随着5G技术的不断发展,5G蜂窝网络已被广泛应用于城市地区。然而,基于5G的机会信号定位技术中存在着测距精度不高的问题。针对此问题,提出一种改进型5G机会信号定位算法,该算法将多信号分类(multiple signal classification,MUSIC)算法...随着5G技术的不断发展,5G蜂窝网络已被广泛应用于城市地区。然而,基于5G的机会信号定位技术中存在着测距精度不高的问题。针对此问题,提出一种改进型5G机会信号定位算法,该算法将多信号分类(multiple signal classification,MUSIC)算法与改进的早-晚功率锁相环(phase-locked loop,PLL)结合,不仅简化了锁相环结构,更保证了测距精度;同时搭建了基于5G机会信号定位的原理样机,并对改进算法方法的有效性和可行性进行了验证,试验结果表明伪距均方误差为3.03 m。本文所提出的算法不仅结构简单、系统稳定,而且在测距精度上也有一定的优势。展开更多
Support vector machines （SVMs） aim to find an optimal separating hyper-plane that maximizes separation between two classes of training examples （more precisely, maximizes the margin between the two classes of examp...Support vector machines （SVMs） aim to find an optimal separating hyper-plane that maximizes separation between two classes of training examples （more precisely, maximizes the margin between the two classes of examples）. The choice of the cost parameter for training the SVM model is always a critical issue. This analysis studies how the cost parameter determines the hyper-plane; especially for classifications using only positive data and unlabeled data. An algorithm is given for the entire solution path by choosing the ＇best＇ cost parameter while training the SVM model. The performance of the algorithm is compared with conventional implementations that use default values as the cost parameter on two synthetic data sets and two real-world data sets. The results show that the algorithm achieves better results when dealing with positive data and unlabeled classification.展开更多
文摘The application of deep learning techniques in the medical field,specifically for Atrial Fibrillation(AFib)detection through Electrocardiogram(ECG)signals,has witnessed significant interest.Accurate and timely diagnosis increases the patient’s chances of recovery.However,issues like overfitting and inconsistent accuracy across datasets remain challenges.In a quest to address these challenges,a study presents two prominent deep learning architectures,ResNet-50 and DenseNet-121,to evaluate their effectiveness in AFib detection.The aim was to create a robust detection mechanism that consistently performs well.Metrics such as loss,accuracy,precision,sensitivity,and Area Under the Curve(AUC)were utilized for evaluation.The findings revealed that ResNet-50 surpassed DenseNet-121 in all evaluated categories.It demonstrated lower loss rate 0.0315 and 0.0305 superior accuracy of 98.77%and 98.88%,precision of 98.78%and 98.89%and sensitivity of 98.76%and 98.86%for training and validation,hinting at its advanced capability for AFib detection.These insights offer a substantial contribution to the existing literature on deep learning applications for AFib detection from ECG signals.The comparative performance data assists future researchers in selecting suitable deep-learning architectures for AFib detection.Moreover,the outcomes of this study are anticipated to stimulate the development of more advanced and efficient ECG-based AFib detection methodologies,for more accurate and early detection of AFib,thereby fostering improved patient care and outcomes.
基金supported in part by the Shaanxi Provincial Key Research and Development Program(2023-ZDLGY-33,2022ZDLGY05-03,2022ZDLGY05-04)in part by the Guangzhou Basic and Applied Basic Research Foundation(2023A04J1740)+1 种基金in part by the Innovation Fund of Xidian University(YJSJ23012)in part by the Fundamental Research Funds for the Central Universities(XJS220116).
文摘With the increasing popularity of civilian unmanned aerial vehicles(UAVs),safety issues arising from unsafe operations and terrorist activities have received growing attention.To address this problem,an accurate classification and positioning system is needed.Considering that UAVs usually use radio frequency(RF)signals for video transmission,in this paper,we design a passive distributed monitoring system that can classify and locate UAVs according to their RF signals.Specifically,three passive receivers are arranged in different locations to receive RF signals.Due to the noncooperation between a UAV and receivers,it is necessary to detect whether there is a UAV signal from the received signals.Hence,convolutional neural network(CNN)is proposed to not only detect the presence of the UAV,but also classify its type.After the UAV signal is detected,the time difference of arrival(TDOA)of the UAV signal arriving at the receiver is estimated by the cross-correlation method to obtain the corresponding distance difference.Finally,the Chan algorithm is used to calculate the location of the UAV.We deploy a distributed system constructed by three software defined radio(SDR)receivers on the campus playground,and conduct extensive experiments in a real wireless environment.The experimental results have successfully validated the proposed system.
基金The National Natural Science Foundation of China under contract Nos 42072324 and 91958202the Key Special Project for Introduced Talents Team of Southern Marine Science and Engineering Guangdong Laboratory(Guangzhou)under contract No.GML2019ZD0106+1 种基金the Resource&Environment Project of China Ocean Mineral Resources R&D Association under contract No.DY135-C1-1-03the Geological Survey Project of China Geological Survey under contract No.DD20190629.
文摘Given the advances in satellite altimetry and multibeam bathymetry,benthic terrain classification based on digital bathymetric models(DBMs)has been widely used for the mapping of benthic topographies.For instance,cobaltrich crusts(CRCs)are important mineral resources found on seamounts and guyots in the western Pacific Ocean.Thick,plate-like CRCs are known to form on the summit and slopes of seamounts at the 1000–3000 m depth,while the relationship between seamount topography and spatial distribution of CRCs remains unclear.The benthic terrain classification of seamounts can solve this problem,thereby,facilitating the rapid exploration of seamount CRCs.Our study used an EM122 multibeam echosounder to retrieve high-resolution bathymetry data in the CRCs contract license area of China,i.e.,the Jiaxie Guyots in 2015 and 2016.Based on the DBM construted by bathymetirc data,broad-and fine-scale bathymetric position indices were utilized for quantitative classification of the terrain units of the Jiaxie Guyots on multiple scales.The classification revealed four first-order terrain units(e.g.,flat,crest,slope,and depression)and eleven second-order terrain units(e.g.,local crests,depressions on crests,gentle slopes,crests on slopes,and local depressions,etc.).Furthermore,the classification of the terrain and geological analysis indicated that the Weijia Guyot has a large flat summit,with local crests at the southern summit,whereas most of the guyot flanks were covered by gentle slopes.“Radial”mountain ridges have developed on the eastern side,while large-scale gravitational landslides have developed on the western and southern flanks.Additionally,landslide masses can be observed at the bottom of these slopes.The coverage of local crests on the seamount is∼1000 km^(2),and the local crests on the peak and flanks of the guyots may be the areas where thick and continuous plate-like CRCs are likely to occur.
文摘随着5G技术的不断发展,5G蜂窝网络已被广泛应用于城市地区。然而,基于5G的机会信号定位技术中存在着测距精度不高的问题。针对此问题,提出一种改进型5G机会信号定位算法,该算法将多信号分类(multiple signal classification,MUSIC)算法与改进的早-晚功率锁相环(phase-locked loop,PLL)结合,不仅简化了锁相环结构,更保证了测距精度;同时搭建了基于5G机会信号定位的原理样机,并对改进算法方法的有效性和可行性进行了验证,试验结果表明伪距均方误差为3.03 m。本文所提出的算法不仅结构简单、系统稳定,而且在测距精度上也有一定的优势。
基金Supported by the National Natural Science Foundation of China(Nos.90604025 and 60703059)the Chinese Young Faculty Research Fund(No.20070003093)
文摘Support vector machines （SVMs） aim to find an optimal separating hyper-plane that maximizes separation between two classes of training examples （more precisely, maximizes the margin between the two classes of examples）. The choice of the cost parameter for training the SVM model is always a critical issue. This analysis studies how the cost parameter determines the hyper-plane; especially for classifications using only positive data and unlabeled data. An algorithm is given for the entire solution path by choosing the ＇best＇ cost parameter while training the SVM model. The performance of the algorithm is compared with conventional implementations that use default values as the cost parameter on two synthetic data sets and two real-world data sets. The results show that the algorithm achieves better results when dealing with positive data and unlabeled classification.
