Search

Over the past decades, drones have become more attainable by the public due to their widespread availability at affordable prices. Nevertheless, this situation sparks serious concerns in both the cyber and physical security domains, as drones can be employed for malicious activities with public safety threats. However, detecting drones instantly and efficiently is a very difficult task due to their tiny size and swift flights. This paper presents a novel drone detection method using deep convolutional learning and deep transfer learning. The proposed algorithm employs a new feature extraction network, which is added to the modified YOU ONLY LOOK ONCE version2 (YOLOv2) network. The feature extraction model uses bypass connections to learn features from the training sets and solves the "vanishing gradient" problem caused by the increasing depth of the network. The structure of YOLOv2 is modified by replacing the rectified linear unit (relu) with a leaky-relu activation function and adding an extra convolutional layer with a stride of 2 to improve the small object detection accuracy. Using leaky-relu solves the "dying relu" problem. The additional convolution layer with a stride of 2 reduces the spatial dimensions of the feature maps and helps the network to focus on larger contextual information while still preserving the ability to detect small objects. The model is trained with a custom dataset that contains various types of drones, airplanes, birds, and helicopters under various weather conditions. The proposed model demonstrates a notable performance, achieving an accuracy of 77% on the test images with only 5 million learnable parameters in contrast to the Darknet53 + YOLOv3 model, which exhibits a 54% accuracy on the same test set despite employing 62 million learnable parameters. [ABSTRACT FROM AUTHOR]

In this paper, a new class of adjustable window function, based on combination of tangent hyperbolic function and a weighted cosine series, is proposed to design an FIR filter. The proposed window has only one adjustable parameter "r". By varying this parameter, it is possible to change the spectral characteristics of the filter. The performance of the proposed window is compared with Gaussian and Kaiser windows. The proposed window has slightly larger main-lobe width compare to the commonly used Gaussian and Kaiser windows, while featuring 19.71 dB and 8.29 dB smaller ripple ratios respectively. Moreover the side-lobe roll-off ratio of the proposed window is almost 115.03 dB and 14.95 dB better than the Gaussian and Kaiser windows respectively. Simulation results show that the filter designed by the proposed window, yields 4.45 dB and 30.69 dB smaller ripple ratios and 7.7 times and 5 times better side-lobe roll-off ratios than those of Gaussian and Kaiser windows respectively. This paper also highlights an application of the proposed method in the area of eliminating noise from corrupted ECG signals. [ABSTRACT FROM AUTHOR]