Specific Emitter Identification (SEI) detects the individual emitter according its varied signal characteristics. The method operates in the physical layer of the internet and can effectively improve the security of the Internet of Things (IoT). Generally, SEI identifies the uniqueness of the transmitting platform by using the unintentional modulation information of the emitter such as radar, which has ''fingerprint'' characteristics. Existing SEI methods are based on hand-crafted features to distinguish different emitters. In this paper, traditional feature extraction methods are studied and a new recognition method is proposed. To determine the effectiveness of the method, the output signals of eight amplifiers are collected as the research object. The power spectrum characteristics and adjacent channel power ratio (ACPR) of the signal are then extracted and eight amplifiers are distinguished. Finally, the quadrature-phase signals are converted into pictures, and convolutional neural networks are used to automatically extract features for classification and recognition. The results show that the recognition rate of converting signals into pictures can reach 95%, when SNR is 20dB. INDEX TERMS Specific emitter identification, IoT, power amplifier.
A hybrid numerical method was used to calculate the flow-induced noise and vibration of the centrifugal pump in the paper. The unsteady flows inside the centrifugal pumps with different blade outlet angles were simulated firstly. The unsteady pressure on the inner surface of the volute and the unsteady force applied on the impeller were analyzed. Then the vibration of the volute and sound field were calculated based on an acoustic-vibro-coupling method. The results show that the pump head has increased 7% while the hydraulic efficiency decreased 11.75% as blade outlet angles increased from 18 ∘ to 39 ∘ . The amplitude of pressure fluctuation at the first blade passing frequency has decreased but increased at the second-order blade passing frequency as the angle growing. The total fluctuation power near volute tongue goes up about 12% every 3 ∘ increment of blade outlet angle. The results also show that vibrating-velocity of the volute at second-order blade passing frequency is much higher than at other frequencies, and the velocity increases rapidly as blade outlet angle varies from 18 ∘ to 39 ∘ . At the same time, the sound pressure level outside the pump has increased about 8.6 dB when the angle increased from 18 ∘ to 39 ∘ .
The limitations in general methods to evaluate clustering will remain difficult to overcome if verifying the clustering validity continues to be based on clustering results and evaluation index values. This study focuses on a clustering process to analyze crisp clustering validity. First, we define the properties that must be satisfied by valid clustering processes and model clustering processes based on program graphs and transition systems. We then recast the analysis of clustering validity as the problem of verifying whether the model of clustering processes satisfies the specified properties with model checking. That is, we try to build a bridge between clustering and model checking. Experiments on several datasets indicate the effectiveness and suitability of our algorithms. Compared with traditional evaluation indices, our formal method can not only indicate whether the clustering results are valid but, in the case the results are invalid, can also detect the objects that have led to the invalidity.
Deep learning has been widely used in the field of image classification and image recognition and achieved positive practical results. However, in recent years, a number of studies have found that the accuracy of deep learning model based on classification greatly drops when making only subtle changes to the original examples, thus realizing the attack on the deep learning model. The main methods are as follows: adjust the pixels of attack examples invisible to human eyes and induce deep learning model to make the wrong classification; by adding an adversarial patch on the detection target, guide and deceive the classification model to make it misclassification. Therefore, these methods have strong randomness and are of very limited use in practical application. Different from the previous perturbation to traffic signs, our paper proposes a method that is able to successfully hide and misclassify vehicles in complex contexts. This method takes into account the complex real scenarios and can perturb with the pictures taken by a camera and mobile phone so that the detector based on deep learning model cannot detect the vehicle or misclassification. In order to improve the robustness, the position and size of the adversarial patch are adjusted according to different detection models by introducing the attachment mechanism. Through the test of different detectors, the patch generated in the single target detection algorithm can also attack other detectors and do well in transferability. Based on the experimental part of this paper, the proposed algorithm is able to significantly lower the accuracy of the detector. Affected by the real world, such as distance, light, angles, resolution, etc., the false classification of the target is realized by reducing the confidence level and background of the target, which greatly perturbs the detection results of the target detector. In COCO Dataset 2017, it reveals that the success rate of this algorithm reaches 88.7%.
Introduction: Model checking is always considered as a logical analysis of a programme which evolves various challenges in the stages of verification. The abstraction model checking reduces the complexity of the process by translating the programme into a scale down version. Main challenge of model checking is that the space explosion may lead to a verification failure because of limited memory, timeout or space out. This giving-up result was never reported back before, which wouldn't provide analysts much useful information about the system. Aim: The process of abstraction coding has great relevancy in designing biological systems at molecular level. Development of abstraction hierarchies in biological engineering will help us further in categorizing the biological networks. Materials and methods: This paper combines several state-of-art model checkers, and adjusts predicate abstraction blocks dynamically during the verification of biological sequences. In this way when it comes to a verification failure, our algorithm will record and report an abstract version of path from the starting state to the current one. The reported paths could be used as an evidence for designers to review the programs. Results and conclusion: Our experiments show that based on the advantages of implementing different model checkers serially, we use message-passing to execute our algorithm to obtain a better performance. At last the parallel version of our methods outperform some of the popular algorithms as the system scale grows, which has wide applications in computer, biomedical and other disciplines.
Small perturbations can make deep models fail. Since deep models are widely used in face recognition systems (FRS) such as surveillance and access control, adversarial examples may introduce more subtle threats to face recognition systems. In this paper, we propose a practical white-box adversarial attack method. The method can automatically form a local area with key semantics on the face. The shape of the local area generated by the algorithm varies according to the environment and light of the character. Since these regions contain major facial features, we generated patch-like adversarial examples based on this region, which can effectively deceive FRS. The algorithm introduced the momentum parameter to stabilize the optimization directions. We accelerated the generation process by increasing the learning rate in segments. Compared with the traditional adversarial algorithm, our algorithms are very inconspicuous, which is very suitable for application in real scenes. The attack was verified on the CASIA WebFace and LFW datasets which were also proved to have good transferability.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
334 Leonard St
Brooklyn, NY 11211
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.