This page has only limited features, please log in for full access.
A micro-Doppler signature (m-DS) based on the rotation of drone blades is an effective way to detect and identify small drones. Deep-learning-based recognition algorithms can achieve higher recognition performance, but they needs a large amount of sample data to train models. In addition to the hovering state, the signal samples of small unmanned aerial vehicles (UAVs) should also include flight dynamics, such as vertical, pitch, forward and backward, roll, lateral, and yaw. However, it is difficult to collect all dynamic UAV signal samples under actual flight conditions, and these dynamic flight characteristics will lead to the deviation of the original features, thus affecting the performance of the recognizer. In this paper, we propose a small UAV m-DS recognition algorithm based on dynamic feature enhancement. We extract the combined principal component analysis and discrete wavelet transform (PCA-DWT) time–frequency characteristics and texture features of the UAV’s micro-Doppler signal and use a dynamic attribute-guided augmentation (DAGA) algorithm to expand the feature domain for model training to achieve an adaptive, accurate, and efficient multiclass recognition model in complex environments. After the training model is stable, the average recognition accuracy rate can reach 98% during dynamic flight.
Caidan Zhao; Gege Luo; Yilin Wang; Caiyun Chen; Zhiqiang Wu. UAV Recognition Based on Micro-Doppler Dynamic Attribute-Guided Augmentation Algorithm. Remote Sensing 2021, 13, 1205 .
AMA StyleCaidan Zhao, Gege Luo, Yilin Wang, Caiyun Chen, Zhiqiang Wu. UAV Recognition Based on Micro-Doppler Dynamic Attribute-Guided Augmentation Algorithm. Remote Sensing. 2021; 13 (6):1205.
Chicago/Turabian StyleCaidan Zhao; Gege Luo; Yilin Wang; Caiyun Chen; Zhiqiang Wu. 2021. "UAV Recognition Based on Micro-Doppler Dynamic Attribute-Guided Augmentation Algorithm." Remote Sensing 13, no. 6: 1205.
With the increasing demand for intelligent traffic management and road network intelligent information services, the vehicular ad hoc networks (VANETs) combined with information of air, space and ground have outstanding advantages in coverage, reliable transmission, and resource richness. Due to the characteristics of heterogeneous, numerous nodes, and frequent cross-network flow, the space–air–ground integrated network (SAGIN) puts forward higher requirements for security. This paper proposes a cross-regional node identity management architecture based on the hash chain, combined with radio frequency (RF) fingerprint theory, to guarantee node identity security with a non-duplicated physical information identity authentication mechanism. At the same time, the blockchain consensus mechanism is simplified to achieve block recording and verification. OMNet ++, SUMO, and Veins co-simulation platforms are used to generate transactions for cross-regional traffic flow. Based on the Hyperledger–Fabric architecture, Kafka and PBFT consensus algorithms are simulated. The simulation results show that the average delay of a single transaction generated block is about 0.9 ms, which achieves efficient and low-latency authentication.
Gege Luo; Mingxian Shi; Caidan Zhao; Zhiyuan Shi. Hash-Chain-Based Cross-Regional Safety Authentication for Space-Air-Ground Integrated VANETs. Applied Sciences 2020, 10, 4206 .
AMA StyleGege Luo, Mingxian Shi, Caidan Zhao, Zhiyuan Shi. Hash-Chain-Based Cross-Regional Safety Authentication for Space-Air-Ground Integrated VANETs. Applied Sciences. 2020; 10 (12):4206.
Chicago/Turabian StyleGege Luo; Mingxian Shi; Caidan Zhao; Zhiyuan Shi. 2020. "Hash-Chain-Based Cross-Regional Safety Authentication for Space-Air-Ground Integrated VANETs." Applied Sciences 10, no. 12: 4206.
Recently, many studies have reported on image synthesis based on Generative Adversarial Networks (GAN). However, the use of GAN does not provide much attention on the signal classification problem. In the context of using wireless signals to classify illegal Unmanned Aerial Vehicles (UAVs), this paper explores the feasibility of using GAN to improve the training datasets and obtain a better classification model, thereby improving the accuracy of classification. First, we use the generative model of GAN to generate a large datasets, which does not need manual annotation. At the same time, the discriminative model of GAN is improved to classify the types of signals based on the loss function of the discriminative model. Finally, this model can be used to the outdoor environment and obtain a real-time illegal UAVs signal classification system. Our experiments confirmed that the improvements on the Auxiliary Classifier Generative Adversarial Networks (AC-GANs) by limited datasets achieve excellent results. The recognition rate can reach more than 95% in the indoor environment, and this method is also applicable in the outdoor environment. Moreover, based on the theory of Wasserstein GANs (WGAN) and AC-GANs, a more robust Auxiliary Classifier Wasserstein GANs (AC-WGANs) model is obtained, which is suitable for multi-class UAVs. Through the combination of AC-WGANs and Universal Software Radio Peripheral (USRP) B210 software defined radio (SDR) platform, a real-time UAVs signal classification system is also implemented.
Caidan Zhao; Caiyun Chen; Zeping He; Zhiqiang Wu. Application of Auxiliary Classifier Wasserstein Generative Adversarial Networks in Wireless Signal Classification of Illegal Unmanned Aerial Vehicles. Applied Sciences 2018, 8, 2664 .
AMA StyleCaidan Zhao, Caiyun Chen, Zeping He, Zhiqiang Wu. Application of Auxiliary Classifier Wasserstein Generative Adversarial Networks in Wireless Signal Classification of Illegal Unmanned Aerial Vehicles. Applied Sciences. 2018; 8 (12):2664.
Chicago/Turabian StyleCaidan Zhao; Caiyun Chen; Zeping He; Zhiqiang Wu. 2018. "Application of Auxiliary Classifier Wasserstein Generative Adversarial Networks in Wireless Signal Classification of Illegal Unmanned Aerial Vehicles." Applied Sciences 8, no. 12: 2664.
Nowadays, it is more and more important to deal with the potential security issues of internet-of-things (IoT). Indeed, using the physical layer features of IoT wireless signals to achieve individual identity authentication is an effective way to enhance the security of IoT. However, traditional classifiers need to know all the categories in advance to get the recognition models. Realistically, it is difficult to collect all types of samples, which will result in some mistakes that the unknown target class may be decided as a known one. Consequently, this paper constructs an improving open-categorical classification model based on the generative adversarial networks (OCC-GAN) to solve the above problems. Here, we have modified the loss function of the generative model G and the discriminative model D. Compared to the traditional GAN model which can generate the fake sample overlapping with the real samples, our proposed G model generates the fake samples as negative samples which are evenly surrounding with the real samples, while the D model learns to distinguish between real samples and fake samples. Besides, we add auxiliary training not only to gain a better recognition result but also to improve the efficiency of the model. Furthermore, Our proposed model is verified through experimental study. Compared to other common methods, such as one-class support vector machine (OC-SVM) and one-versus-rest support vector machine (OvR-SVM), the OCC-GAN model has a better performance. The recognition rate of the OCC-GAN model can reach more than 90% with a recall rate of 97% by the data of the IoT module.
Caidan Zhao; Mingxian Shi; Zhibiao Cai; Caiyun Chen. Research on the Open-Categorical Classification of the Internet-of-Things Based on Generative Adversarial Networks. Applied Sciences 2018, 8, 2351 .
AMA StyleCaidan Zhao, Mingxian Shi, Zhibiao Cai, Caiyun Chen. Research on the Open-Categorical Classification of the Internet-of-Things Based on Generative Adversarial Networks. Applied Sciences. 2018; 8 (12):2351.
Chicago/Turabian StyleCaidan Zhao; Mingxian Shi; Zhibiao Cai; Caiyun Chen. 2018. "Research on the Open-Categorical Classification of the Internet-of-Things Based on Generative Adversarial Networks." Applied Sciences 8, no. 12: 2351.
In the Internet of Things(IoT) equipment, the characteristic space of the physical layer has changed slightly due to prolongation of the use time and the change of the environment, which may result to the terrible identification of the new target. To solve the problem, this paper uses transfer learning to update the instance weights and combines the weight with rejection sampling to construct the training set. This method provides a black box for transfer learning and a possibility for building multi-classification transfer learning. Some experimental results show that the rate can increase 10% when the number of target samples is too small to train a new learning model.
Caidan Zhao; Zhibiao Cai; Minmin Huang; Mingxian Shi; Xiaojiang Du; Mohsen Guizani. The Identification of Secular Variation in IoT Based on Transfer Learning. 2018 International Conference on Computing, Networking and Communications (ICNC) 2018, 878 -882.
AMA StyleCaidan Zhao, Zhibiao Cai, Minmin Huang, Mingxian Shi, Xiaojiang Du, Mohsen Guizani. The Identification of Secular Variation in IoT Based on Transfer Learning. 2018 International Conference on Computing, Networking and Communications (ICNC). 2018; ():878-882.
Chicago/Turabian StyleCaidan Zhao; Zhibiao Cai; Minmin Huang; Mingxian Shi; Xiaojiang Du; Mohsen Guizani. 2018. "The Identification of Secular Variation in IoT Based on Transfer Learning." 2018 International Conference on Computing, Networking and Communications (ICNC) , no. : 878-882.
Though a lot of video quality assessment (VQA) models have been researched, most of them are lack of a recognized video quality assessment database, especially for High Efficiency Video Coding (HEVC) encoded video transmit on Long Term Evolution (LTE) system. On the one hand, HEVC video coding technology is rapidly growing in popularity, thus, it needs to build a new VQA model for HEVC; on the other hand, the LTE system is more popular than other communicate systems currently, as well as, different channels of mobile communication system has different effects on video, therefore, it is necessary to damage video over LTE channel. To achieve that, this paper combines the Gilbert model with LTE system to damage HEVC video, and assesses the quality of deterioration video by the method of Single Stimulus Continuous Quality Evaluation(SSCQE). Finally, building HEVC video quality assessment database over LTE systems.
Caidan Zhao; Zhibiao Cai; Yifeng Zhao; Mingjun Shi; Jun Geng. HEVC video quality assessment database toward LTE system. 2016 11th International Conference on Computer Science & Education (ICCSE) 2016, 357 -362.
AMA StyleCaidan Zhao, Zhibiao Cai, Yifeng Zhao, Mingjun Shi, Jun Geng. HEVC video quality assessment database toward LTE system. 2016 11th International Conference on Computer Science & Education (ICCSE). 2016; ():357-362.
Chicago/Turabian StyleCaidan Zhao; Zhibiao Cai; Yifeng Zhao; Mingjun Shi; Jun Geng. 2016. "HEVC video quality assessment database toward LTE system." 2016 11th International Conference on Computer Science & Education (ICCSE) , no. : 357-362.
The reduced-reference video quality evaluation method uses only partial reference video information to evaluate the quality of deteriorated videos. This method can evaluate the quality of a video in real-time because less transmission bandwidth is required. Because the video active area attracts significant human eye attention, any deterioration in the active area will directly affect video evaluation results. Given the advantage of reduced reference model in VQM (Video Qualify Metric), this paper proposes a reduced reference evaluation model named RR-PEVQ (Reduced Reference Perceptual Evaluation of Video Quality) for weighting the active video area. According to the experimental results, the RR-PEVQ evaluation score is similar to that of the full reference PEVQ and the proposed method’s practicability is greatly improved for big data purposes.
Wei-Jian Xu; Cai-Dan Zhao; Hua-Pei Chiang; Lianfen Huang; Yueh-Min Huang. The RR-PEVQ algorithm research based on active area detection for big data applications. Multimedia Tools and Applications 2014, 74, 3507 -3520.
AMA StyleWei-Jian Xu, Cai-Dan Zhao, Hua-Pei Chiang, Lianfen Huang, Yueh-Min Huang. The RR-PEVQ algorithm research based on active area detection for big data applications. Multimedia Tools and Applications. 2014; 74 (10):3507-3520.
Chicago/Turabian StyleWei-Jian Xu; Cai-Dan Zhao; Hua-Pei Chiang; Lianfen Huang; Yueh-Min Huang. 2014. "The RR-PEVQ algorithm research based on active area detection for big data applications." Multimedia Tools and Applications 74, no. 10: 3507-3520.