Mobile Industrial Internet of Things(IIoT)applications have achieved the explosive growth in recent years.The mobile IIoT has flourished and become the backbone of the industry,laying a solid foundation for the interc...Mobile Industrial Internet of Things(IIoT)applications have achieved the explosive growth in recent years.The mobile IIoT has flourished and become the backbone of the industry,laying a solid foundation for the interconnection of all things.The variety of application scenarios has brought serious challenges to mobile IIoT networks,which face complex and changeable communication environments.Ensuring data secure transmission is critical for mobile IIoT networks.This paper investigates the data secure transmission performance prediction of mobile IIoT networks.To cut down computational complexity,we propose a data secure transmission scheme employing Transmit Antenna Selection(TAS).The novel secrecy performance expressions are first derived.Then,to realize real-time secrecy analysis,we design an improved Convolutional Neural Network(CNN)model,and propose an intelligent data secure transmission performance prediction algorithm.For mobile signals,the important features may be removed by the pooling layers.This will lead to negative effects on the secrecy performance prediction.A novel nine-layer improved CNN model is designed.Out of the input and output layers,it removes the pooling layer and contains six convolution layers.Elman,Back-Propagation(BP)and LeNet methods are employed to compare with the proposed algorithm.Through simulation analysis,good prediction accuracy is achieved by the CNN algorithm.The prediction accuracy obtains a 59%increase.展开更多
Reweighting adversarial examples during training plays an essential role in improving the robustness of neural networks,which lies in the fact that examples closer to the decision boundaries are much more vulnerable t...Reweighting adversarial examples during training plays an essential role in improving the robustness of neural networks,which lies in the fact that examples closer to the decision boundaries are much more vulnerable to being attacked and should be given larger weights.The probability margin(PM)method is a promising approach to continuously and path-independently mea-suring such closeness between the example and decision boundary.However,the performance of PM is limited due to the fact that PM fails to effectively distinguish the examples having only one misclassified category and the ones with multiple misclassified categories,where the latter is closer to multi-classification decision boundaries and is supported to be more critical in our observation.To tackle this problem,this paper proposed an improved PM criterion,called confused-label-based PM(CL-PM),to measure the closeness mentioned above and reweight adversarial examples during training.Specifi-cally,a confused label(CL)is defined as the label whose prediction probability is greater than that of the ground truth label given a specific adversarial example.Instead of considering the discrepancy between the probability of the true label and the probability of the most misclassified label as the PM method does,we evaluate the closeness by accumulating the probability differences of all the CLs and ground truth label.CL-PM shares a negative correlation with data vulnerability:data with larger/smaller CL-PM is safer/riskier and should have a smaller/larger weight.Experiments demonstrated that CL-PM is more reliable in indicating the closeness regarding multiple misclassified categories,and reweighting adversarial training based on CL-PM outperformed state-of-the-art counterparts.展开更多
Recent state-of-the-art semi-supervised learning(SSL)methods usually use data augmentations as core components.Such methods,however,are limited to simple transformations such as the augmentations under the instance’s...Recent state-of-the-art semi-supervised learning(SSL)methods usually use data augmentations as core components.Such methods,however,are limited to simple transformations such as the augmentations under the instance’s naive representations or the augmentations under the instance’s semantic representations.To tackle this problem,we offer a unique insight into data augmentations and propose a novel data-augmentation-based semi-supervised learning method,called Attentive Neighborhood Feature Aug-mentation(ANFA).The motivation of our method lies in the observation that the relationship between the given feature and its neighborhood may contribute to constructing more reliable transformations for the data,and further facilitating the classifier to distinguish the ambiguous features from the low-dense regions.Specially,we first project the labeled and unlabeled data points into an embedding space and then construct a neighbor graph that serves as a similarity measure based on the similar representations in the embedding space.Then,we employ an attention mechanism to transform the target features into augmented ones based on the neighbor graph.Finally,we formulate a novel semi-supervised loss by encouraging the predictions of the interpolations of augmented features to be consistent with the corresponding interpolations of the predictions of the target features.We carried out exper-iments on SVHN and CIFAR-10 benchmark datasets and the experimental results demonstrate that our method outperforms the state-of-the-art methods when the number of labeled examples is limited.展开更多
To facilitate scene understanding and robot navigation in large scale urban environment, a two-layer enhanced geometric map(EGMap) is designed using videos from a monocular onboard camera. The 2D layer of EGMap consis...To facilitate scene understanding and robot navigation in large scale urban environment, a two-layer enhanced geometric map(EGMap) is designed using videos from a monocular onboard camera. The 2D layer of EGMap consists of a 2D building boundary map from top-down view and a 2D road map, which can support localization and advanced map-matching when compared with standard polyline-based maps. The 3D layer includes features such as 3D road model,and building facades with coplanar 3D vertical and horizontal line segments, which can provide the 3D metric features to localize the vehicles and flying-robots in 3D space. Starting from the 2D building boundary and road map, EGMap is initially constructed using feature fusion with geometric constraints under a line feature-based simultaneous localization and mapping(SLAM) framework iteratively and progressively. Then, a local bundle adjustment algorithm is proposed to jointly refine the camera localizations and EGMap features. Furthermore, the issues of uncertainty, memory use, time efficiency and obstacle effect in EGMap construction are discussed and analyzed. Physical experiments show that EGMap can be successfully constructed in large scale urban environment and the construction method is demonstrated to be very accurate and robust.展开更多
Currently,small payload and short endurance are the main problems of a single UAV in agricultural applications,especially in large-scale farmland.It is one of the important methods to solve the above problems of UAVs ...Currently,small payload and short endurance are the main problems of a single UAV in agricultural applications,especially in large-scale farmland.It is one of the important methods to solve the above problems of UAVs by improving operation efficiency through multi-UAV cooperative navigation.This study proposed a laser tracking leader-follower automatic cooperative navigation system for multi-UAVs.The leader in the cluster fires a laser beam to irradiate the follower,and the follower performs a visual tracking flight according to the light spot at the relative position of the laser tracking device.Based on the existing kernel correlation filter(KCF)tracking algorithm,an improved KCF real-time spot tracking method was proposed.Compared with the traditional KCF tracking algorithm,the recognition and tracking rate of the optimized algorithm was increased from 70%to 95%in indoor environment,and was increased from 20%to 90%in outdoor environment.The navigation control method was studied from two aspects:the distance coordinate transformation model based on micro-gyroscope and navigation control strategy.The error of spot position was reduced from the maximum(3.12,−3.66)cm to(0.14,0.12)cm by correcting the deviation distance of the spot at different angles through a coordinate correction algorithm.An image coordinate conversion model was established for a complementary metal-oxide-semiconductor(CMOS)camera and laser receiving device at different mounting distances.The laser receiving device was divided into four regions,S0-S3,and the speed of the four regions is calculated using an uncontrollable discrete Kalman filter.The outdoor flight experiments of two UAVs were carried out outdoors using this system.The experiment results show that the average flight error of the two UAVs on the X-axis is 5.2 cm,and the coefficient of variation is 0.0181.The average flight error on the Z-axis is 7.3 cm,and the coefficient of variation is 0.0414.This study demonstrated the possibility and adaptability of the developed system to achieve multi-UAVs cooperative navigation.展开更多
基金supported by the National Natural Science Foundation of China(No.62201313)the Opening Foundation of Fujian Key Laboratory of Sensing and Computing for Smart Cities(Xiamen University)(No.SCSCKF202101)the Open Project of Fujian Provincial Key Laboratory of Information Processing and Intelligent Control(Minjiang University)(No.MJUKF-IPIC202206).
文摘Mobile Industrial Internet of Things(IIoT)applications have achieved the explosive growth in recent years.The mobile IIoT has flourished and become the backbone of the industry,laying a solid foundation for the interconnection of all things.The variety of application scenarios has brought serious challenges to mobile IIoT networks,which face complex and changeable communication environments.Ensuring data secure transmission is critical for mobile IIoT networks.This paper investigates the data secure transmission performance prediction of mobile IIoT networks.To cut down computational complexity,we propose a data secure transmission scheme employing Transmit Antenna Selection(TAS).The novel secrecy performance expressions are first derived.Then,to realize real-time secrecy analysis,we design an improved Convolutional Neural Network(CNN)model,and propose an intelligent data secure transmission performance prediction algorithm.For mobile signals,the important features may be removed by the pooling layers.This will lead to negative effects on the secrecy performance prediction.A novel nine-layer improved CNN model is designed.Out of the input and output layers,it removes the pooling layer and contains six convolution layers.Elman,Back-Propagation(BP)and LeNet methods are employed to compare with the proposed algorithm.Through simulation analysis,good prediction accuracy is achieved by the CNN algorithm.The prediction accuracy obtains a 59%increase.
基金supported by the National Natural Science Foundation of China (No.62072127,No.62002076,No.61906049)Natural Science Foundation of Guangdong Province (No.2023A1515011774,No.2020A1515010423)+3 种基金Project 6142111180404 supported by CNKLSTISS,Science and Technology Program of Guangzhou,China (No.202002030131)Guangdong basic and applied basic research fund joint fund Youth Fund (No.2019A1515110213)Open Fund Project of Fujian Provincial Key Laboratory of Information Processing and Intelligent Control (Minjiang University) (No.MJUKF-IPIC202101)Scientific research project for Guangzhou University (No.RP2022003).
文摘Reweighting adversarial examples during training plays an essential role in improving the robustness of neural networks,which lies in the fact that examples closer to the decision boundaries are much more vulnerable to being attacked and should be given larger weights.The probability margin(PM)method is a promising approach to continuously and path-independently mea-suring such closeness between the example and decision boundary.However,the performance of PM is limited due to the fact that PM fails to effectively distinguish the examples having only one misclassified category and the ones with multiple misclassified categories,where the latter is closer to multi-classification decision boundaries and is supported to be more critical in our observation.To tackle this problem,this paper proposed an improved PM criterion,called confused-label-based PM(CL-PM),to measure the closeness mentioned above and reweight adversarial examples during training.Specifi-cally,a confused label(CL)is defined as the label whose prediction probability is greater than that of the ground truth label given a specific adversarial example.Instead of considering the discrepancy between the probability of the true label and the probability of the most misclassified label as the PM method does,we evaluate the closeness by accumulating the probability differences of all the CLs and ground truth label.CL-PM shares a negative correlation with data vulnerability:data with larger/smaller CL-PM is safer/riskier and should have a smaller/larger weight.Experiments demonstrated that CL-PM is more reliable in indicating the closeness regarding multiple misclassified categories,and reweighting adversarial training based on CL-PM outperformed state-of-the-art counterparts.
基金supported by the National Natural Science Foundation of China (Nos.62072127,62002076,61906049)Natural Science Foundation of Guangdong Province (Nos.2023A1515011774,2020A1515010423)+4 种基金Project 6142111180404 supported by CNKLSTISS,Science and Technology Program of Guangzhou,China (No.202002030131)Guangdong basic and applied basic research fund joint fund Youth Fund (No.2019A1515110213)Open Fund Project of Fujian Provincial Key Laboratory of Information Processing and Intelligent Control (Minjiang University) (No.MJUKF-IPIC202101)Natural Science Foundation of Guangdong Province No.2020A1515010423)Scientific research project for Guangzhou University (No.RP2022003).
文摘Recent state-of-the-art semi-supervised learning(SSL)methods usually use data augmentations as core components.Such methods,however,are limited to simple transformations such as the augmentations under the instance’s naive representations or the augmentations under the instance’s semantic representations.To tackle this problem,we offer a unique insight into data augmentations and propose a novel data-augmentation-based semi-supervised learning method,called Attentive Neighborhood Feature Aug-mentation(ANFA).The motivation of our method lies in the observation that the relationship between the given feature and its neighborhood may contribute to constructing more reliable transformations for the data,and further facilitating the classifier to distinguish the ambiguous features from the low-dense regions.Specially,we first project the labeled and unlabeled data points into an embedding space and then construct a neighbor graph that serves as a similarity measure based on the similar representations in the embedding space.Then,we employ an attention mechanism to transform the target features into augmented ones based on the neighbor graph.Finally,we formulate a novel semi-supervised loss by encouraging the predictions of the interpolations of augmented features to be consistent with the corresponding interpolations of the predictions of the target features.We carried out exper-iments on SVHN and CIFAR-10 benchmark datasets and the experimental results demonstrate that our method outperforms the state-of-the-art methods when the number of labeled examples is limited.
基金National Natural Science Foundation of China(61305107,U1333109)the Fundamental Research Funds for the Central Universities(3122016B006)the Scientific Research Funds for Civil Aviation University of China(2012QD23X)
文摘To facilitate scene understanding and robot navigation in large scale urban environment, a two-layer enhanced geometric map(EGMap) is designed using videos from a monocular onboard camera. The 2D layer of EGMap consists of a 2D building boundary map from top-down view and a 2D road map, which can support localization and advanced map-matching when compared with standard polyline-based maps. The 3D layer includes features such as 3D road model,and building facades with coplanar 3D vertical and horizontal line segments, which can provide the 3D metric features to localize the vehicles and flying-robots in 3D space. Starting from the 2D building boundary and road map, EGMap is initially constructed using feature fusion with geometric constraints under a line feature-based simultaneous localization and mapping(SLAM) framework iteratively and progressively. Then, a local bundle adjustment algorithm is proposed to jointly refine the camera localizations and EGMap features. Furthermore, the issues of uncertainty, memory use, time efficiency and obstacle effect in EGMap construction are discussed and analyzed. Physical experiments show that EGMap can be successfully constructed in large scale urban environment and the construction method is demonstrated to be very accurate and robust.
基金This work was supported in part by the Laboratory of Lingnan Modern Agriculture Project(Grant No.NT2021009)in part by the Science and Technology Plan of Jian City of China(Grant No.20211-055316)+3 种基金in part by the National Natural Science Foundation of China(Grant No.31871520)in part by the Science and Technology Plan of Guangdong Province of China(Grant No.2021B1212040009,2017B090903007)in part by the Guangdong Basic and Applied Basic Research Foundation under(Grant No.2020A1515110214)in part by Innovative Research Team of Agricultural and Rural Big Data in Guangdong Province of China under(Grant No.2019KJ138).
文摘Currently,small payload and short endurance are the main problems of a single UAV in agricultural applications,especially in large-scale farmland.It is one of the important methods to solve the above problems of UAVs by improving operation efficiency through multi-UAV cooperative navigation.This study proposed a laser tracking leader-follower automatic cooperative navigation system for multi-UAVs.The leader in the cluster fires a laser beam to irradiate the follower,and the follower performs a visual tracking flight according to the light spot at the relative position of the laser tracking device.Based on the existing kernel correlation filter(KCF)tracking algorithm,an improved KCF real-time spot tracking method was proposed.Compared with the traditional KCF tracking algorithm,the recognition and tracking rate of the optimized algorithm was increased from 70%to 95%in indoor environment,and was increased from 20%to 90%in outdoor environment.The navigation control method was studied from two aspects:the distance coordinate transformation model based on micro-gyroscope and navigation control strategy.The error of spot position was reduced from the maximum(3.12,−3.66)cm to(0.14,0.12)cm by correcting the deviation distance of the spot at different angles through a coordinate correction algorithm.An image coordinate conversion model was established for a complementary metal-oxide-semiconductor(CMOS)camera and laser receiving device at different mounting distances.The laser receiving device was divided into four regions,S0-S3,and the speed of the four regions is calculated using an uncontrollable discrete Kalman filter.The outdoor flight experiments of two UAVs were carried out outdoors using this system.The experiment results show that the average flight error of the two UAVs on the X-axis is 5.2 cm,and the coefficient of variation is 0.0181.The average flight error on the Z-axis is 7.3 cm,and the coefficient of variation is 0.0414.This study demonstrated the possibility and adaptability of the developed system to achieve multi-UAVs cooperative navigation.
