A brain tumor is a disorder caused by the growth of abnormal brain cells. The survival rate of a patient affected with a tumor is difficult to determine because they are infrequent and appear in various forms. These tumors can be identified through Magnetic Resonance (MRI) Images, which plays an essential role in determining the tumor site; however, manual detection is a time-consuming and challenging procedure that can cause some errors in results. The adoption of computer-assisted approaches is essential to help in overcoming these constraints. With the advancement of artificial intelligence, deep learning (DL) models are being used in medical imaging to diagnose brain tumors using MR images. In this study, a deep convolutional neural network (CNN) EfficientNet-B0 base model is fine-tuned with our proposed layers to efficiently classify and detect brain tumor images. The image enhancement techniques are used by applying various filters to enhance the quality of the images. Data augmentation methods are applied to increase the data samples for better training of our proposed model. The results show that the proposed fine-tuned state-of-the-art EfficientNet-B0 outperforms other CNN models by achieving the highest classification accuracy, precision, recall, and area under curve values surpassing other state-of-the-art models, with an overall accuracy of 98.87% in terms of classification and detection. Other DL algorithms such as VGG16, InceptionV3, Xception, ResNet50, and InceptionResNetV2 are used for comparative analysis.

Federated Learning (FL) has recently received a lot of attention for large-scale privacy-preserving machine learning. However, high communication overheads due to frequent gradient transmissions decelerate FL. To mitigate the communication overheads, two main techniques have been studied: (i) local update of weights characterizing the trade-off between communication and computation and (ii) gradient compression characterizing the trade-off between communication and precision. To the best of our knowledge, studying and balancing those two trade-offs jointly and dynamically while considering their impacts on convergence has remained unresolved even though it promises significantly faster FL. In this paper, we first formulate our problem to minimize learning error with respect to two variables: local update coefficients and sparsity budgets of gradient compression who characterize trade-offs between communication and computation/precision, respectively. We then derive an upper bound of the learning error in a given wall-clock time considering the interdependency between the two variables. Based on this theoretical analysis, we propose an enhanced FL scheme, namely Fast FL (FFL), that jointly and dynamically adjusts the two variables to minimize the learning error. We demonstrate that FFL consistently achieves higher accuracies faster than similar schemes existing in the literature.

Automatic road extraction from unmanned aerial vehicle (UAV) imagery has been one of the major research topics in the area of remote sensing analysis due to its importance in a wide range of applications such as urban planning, road monitoring, intelligent transportation systems, and automatic road navigation. Thanks to the recent advances in Deep Learning (DL), the tedious manual segmentation of roads can be automated. However, the majority of these models are computationally heavy and, thus, are not suitable for UAV remote-sensing tasks with limited resources. To alleviate this bottleneck, we propose two lightweight models based on depthwise separable convolutions and ConvMixer inception block. Both models take the advantage of computational efficiency of depthwise separable convolutions and multi-scale processing of inception module and combine them in an encoder–decoder architecture of U-Net. Specifically, we substitute standard convolution layers used in U-Net for ConvMixer layers. Furthermore, in order to learn images on different scales, we apply ConvMixer layer into Inception module. Finally, we incorporate pathway networks along the skip connections to minimize the semantic gap between encoder and decoder. In order to validate the performance and effectiveness of the models, we adopt Massachusetts roads dataset. One incarnation of our models is able to beat the U-Net’s performance with 10× fewer parameters, and DeepLabV3’s performance with 12× fewer parameters in terms of mean intersection over union (mIoU) metric. For further validation, we have compared our models against four baselines in total and used additional metrics such as precision (P), recall (R), and F1 score.

In this work, we consider a secure precoding optimization problem for the artificial noise (AN) scheme in multiple-input single-output (MISO) wiretap channels. In [4], it was proved that the generalized AN scheme which allows some portion of AN signal to be injected to the legitimate receiver's channel is the optimal precoding scheme for MISO wiretap channels. However, the optimality is valid only under some ideal assumptions such as perfect channel estimation and spatially uncorrelated channels. To break through this limitation, in this paper, we propose a novel deep neural network (DNN)-based secure precoding scheme, called the deep AN scheme. To the best of the authors’ knowledge, the deep AN scheme is the first secure precoding scheme which exploits a DNN to jointly design and optimize the precoders for the information signal and the AN signal. From the numerical experiments, it is demonstrated that the proposed deep AN scheme outperforms the generalized AN scheme under various practical wireless environments.

In this paper, we propose a novel two-stage transformer with GhostNet, which improves the performance of the small object detection task. Specifically, based on the original Deformable Transformers for End-to-End Object Detection (deformable DETR), we chose GhostNet as the backbone to extract features, since it is better suited for an efficient feature extraction. Furthermore, at the target detection stage, we selected the 300 best bounding box results as regional proposals, which were subsequently set as primary object queries of the decoder layer. Finally, in the decoder layer, we optimized and modified the queries to increase the target accuracy. In order to validate the performance of the proposed model, we adopted a widely used COCO 2017 dataset. Extensive experiments demonstrated that the proposed scheme yielded a higher average precision (AP) score in detecting small objects than the existing deformable DETR model.

This work considers the artificial noise (AN) scheme, proposed by Goel and Negi for securing wireless communications over multiple-input multiple-output multi-antenna eavesdropper (MIMOME) channels. In this work, we develop a lower bound on the ergodic secrecy rate of the artificial noise scheme and derive an analytic expression of the bound without assuming any asymptotes for system parameters. Thus, the derived bound explicitly elucidates how the system parameters exert influence on the secrecy rate in various cases to some of which the previous work cannot be applied. It will also be shown that the bound is tight over wide combinations of system parameters, and a normalized difference between the bound and secrecy rate vanishes with a growing number of antennas at the transmitter. The derived bound is analytically so amenable that it enables one to not only extend the results of the previous work but also explore untouched aspects of the AN scheme. The bound answers an intriguing question: when is the AN signal beneficial? Besides, it makes possible to study a new important system parameter called the minimum required transmit power for a certain target secrecy rate, which has never been touched before.