The high-resolution devices for image capturing and the high professional requirement for users, are very complex to extract features of the fruit fly image for classification. Therefore, a bilinear CNN model based on the mid-level and high-level feature fusion (FB-CNN) is proposed for classifying the fruit fly image. At the first step, the images of fruit fly are blurred by the Gaussian algorithm, and then the features of the fruit fly images are extracted automatically by using CNN. Afterward, the mid-and high-level features are selected to represent the local and global features, respectively. Then, they are jointly represented. When finished, the FB-CNN model was constructed to complete the task of image classification of the fruit fly. Finally, experiments data show that the FB-CNN model can effectively classify four kinds of fruit fly images. The accuracy, precision, recall, and F1 score in testing dataset are 95.00%, respectively. INDEX TERMS Fruit fly images, feature fusion, convolution neural network, image classification.
In practical electrocardiogram (ECG) monitoring, there are some challenges in reducing the data burden and energy costs. Therefore, compressed sensing (CS) which can conduct under-sampling and reconstruction at the same time is adopted in the ECG monitoring application. Recently, deep learning used in CS methods improves the reconstruction performance significantly and can removes of some of the constraints in traditional CS. In this paper, we propose a deep compressive-sensing scheme for ECG signals, based on modified-Inception block and long short-term memory (LSTM). The framework is comprised of four modules: preprocessing; compression; initial; and final reconstruction. We adaptively compressed the normalized ECG signals, sequentially using three convolutional layers, and reconstructed the signals with a modified Inception block and LSTM. We conducted our experiments on the MIT-BIH Arrhythmia Database and Non-Invasive Fetal ECG Arrhythmia Database to validate the robustness of our model, adopting Signal-to-Noise Ratio (SNR) and percentage Root-mean-square Difference (PRD) as the evaluation metrics. The PRD of our scheme was the lowest and the SNR was the highest at all of the sensing rates in our experiments on both of the databases, and when the sensing rate was higher than 0.5, the PRD was lower than 2%, showing significant improvement in reconstruction performance compared to the comparative methods. Our method also showed good recovering quality in the noisy data.
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.