Automatic modulation classification (AMC) is one of the major challenges for cognitive radio (CR), which can enhance the spectrum utilization efficiency. In this study, a hybrid signal and image-based deep learning model is designed for AMC in CR. A convolutional neural network (CNN) is applied in both the deep learning models. The signal-based CNN (SBCNN) is designed with the optimal filter size for the prediction accuracy, which is used as a pre-training deep learning network to extract features with size $24\times 1$ . The features extracted by SBCNN are converted into heat map images, which showed RGB images in the scale range of −30 to +30. Finally, the images are utilized for training and testing the image-based CNN (IBCNN). The dataset used for the experiment is DeepSig: RADIOML2018.01A, which is the latest version. For the IBCNN, the prediction accuracy is 1.96%, 7.99%, and 4.63% higher at signal-to-noise ratio (SNR) 10 dB, and 3.26%, 6.4%, and 4.13% higher at SNR 0 dB as compared to conventional models: ECNN, SCGNet, and LCNN, respectively.
1 May 2014 in Journal of the Korean Mathematical Society
Given the availability of large source-code repositories, there has been a large number of applications for large-scale clone detection. Unfortunately, despite a decade of active research, there is a marked lack in clone detectors that scale to big software systems or large repositories, specifically for detecting near-miss (Type 3) clones where significant editing activities may take place in the cloned code. This paper demonstrates: (i) SourcererCC, a token-based clone detector that targets the first three clone types, and exploits an index to achieve scalability to large inter-project repositories using a standard workstation. It uses an optimized inverted-index to quickly query the potential clones of a given code block. Filtering heuristics based on token ordering are used to significantly reduce the size of the index, the number of code-block comparisons needed to detect the clones, as well as the number of required token-comparisons needed to judge a potential clone; and (ii) SourcererCC-I, an Eclipse plug-in, that uses SourcererCC's core engine to identify and navigate clones (both inter and intra project) in real-time during software development. In our experiments, comparing SourcererCC with the state-of-the-art tools 1, we found that it is the only clone detection tool to successfully scale to 250 MLOC on a standard workstation with 12 GB RAM and efficiently detect the first three types of clones (precision 86% and recall 86-100%). Link to the demo: https://youtu.be/17F_9Qp-ks4
Photoacoustic (PA) imaging has become invaluable in preclinical and clinical research. Endoscopic PA imaging in particular has been explored as a noninvasive imaging modality to view vasculature and diagnose cancers in the digestive system. However, these feasibility studies are still limited to rodents or rabbits. Here, we develop a fully synchronized simultaneous ultrasound and photoacoustic microscopy system using two spectral bands (i.e., the visible and near-infrared) in both optical- and acoustic-resolution modes. We investigate the feasibility of imaging gastric vasculature in an ex vivo porcine model. The entire gastric wall, including the mucosa, submucosa, muscularis propria, and serosa, was excised from fresh porcine stomachs immediately followed by ultrasound and PA imaging being performed within a few hours of sacrifice. PA images of the mucosal vasculature were obtained at depths of 1.90 mm, which is a clinically significant accomplishment considering that the average thickness of the human mucosa is 1.26 mm. The layer structure of the stomach wall could be clearly distinguished in the overlaid PA and US images. Because gastric cancer starts from the mucosal surface and infiltrates into the submucosa, PA imaging can cover a clinically relevant depth in early gastric cancer diagnosis. We were able to detect mucosal vasculature in the entire mucosal layer, suggesting the potential utility of combined PA/US imaging in gastroenterology.
The integration of radar and communication systems in 6G networks has led to a significant challenge of spectrum congestion. To address this issue, we propose a deep learning-based method for efficient waveform-based signal classification. Our method is designed to handle large and impaired radar and communication signals, and is crucial for the implementation of resource-limited cognitive radio-enabled Internet-of-Things (CR-IoT) devices. We introduce WaveNet, a cost-efficient deep convolutional neural network that can aptly learn underlying radio features from time-frequency images transformed by a smooth pseudo Wigner-Ville distribution. WaveNet incorporates several innovative modules, including cost-efficient feature awareness, which integrates two well-designed structural blocks: grouped-of-kernel-wise residual connections and dual asymmetric channel attention. These enhancements significantly reduce network size without compromising classification accuracy. Based on various simulations experimented on an impaired signal dataset containing eight radar and communication waveform types, the results demonstrate the effectiveness and robustness of WaveNet, achieving an overall classification accuracy of 92.02%. Compared to the current state-of-the-art deep models, WaveNet has the lowest architectural complexity, with a network size five times smaller, while still outperforming them by approximately 0.5 – 1.69%. Consequently, WaveNet emerges as a valuable solution for waveform classification in integrated radar-communication 6G systems.