Chest X-ray (CXR) imaging plays a pivotal role in diagnosing various pulmonary diseases, which account for a significant portion of the global mortality rate, as recognized by the World Health Organization (WHO). Medical practitioners routinely depend on CXR images to identify anomalies and make critical clinical decisions. Dramatic improvements in super-resolution (SR) have been achieved by applying deep learning techniques. However, some SR methods are very difficult to utilize due to their low-resolution inputs and features containing abundant low-frequency information, similar to the case of X-ray image super-resolution. In this paper, we introduce an advanced deep learning-based SR approach that incorporates the innovative residual-in-residual (RIR) structure to augment the diagnostic potential of CXR imaging. Specifically, we propose forming a light network consisting of residual groups built by residual blocks, with multiple skip connections to facilitate the efficient bypassing of abundant low-frequency information through multiple skip connections. This approach allows the main network to concentrate on learning high-frequency information. In addition, we adopted the dense feature fusion within residual groups and designed high parallel residual blocks for better feature extraction. Our proposed methods exhibit superior performance compared to existing state-of-the-art (SOTA) SR methods, delivering enhanced accuracy and notable visual improvements, as evidenced by our results.

Dense multi-view image reconstruction has been a focal point of research for an extended period, with recent surges in interest. The utilization of multi-view images offers solutions to numerous challenges and amplifies the effectiveness of various applications including 3D reconstruction, de-occlusion, depth sensing, saliency detection, and identifying salient objects. This paper introduces an approach to reconstructing high-density light field (LF) images, addressing the inherent challenge of balancing angular and spatial resolution caused by limited sensor resolution. We introduce an innovative approach to reconstructing LF images through a CNN-based network that combines spatial and epipolar features in both initial and deep feature extraction phases. Our network utilizes angular information during upsampling and employs dual feature extraction to effectively analyze horizontal and vertical epipolar data. Weight sharing within the CNN block between horizontal and vertically transposed stacks enhances quality while preserving model compactness. The outcomes of experiments carried out on real-world and synthetic datasets demonstrate the effectiveness of our method, showcasing its superior performance in both inference speed and reconstruction quality when compared to state-of-the-art (SOTA) techniques.

Depth estimation is an important task in autonomous driving, and usually needs special types of sensors or multiple cameras. In this paper, we propose a novel approach to monocular depth estimation based on two other cheaper annotation tasks: semantic segmentation and prediction of a single vanishing point without the need for ground truth depth data. In a Manhattan-world assumption with a single vanishing point, only one vanishing point exists and represents the end of the scene extension on the z-axis. Depending on semantic segmentation prediction, we set hand-crafted rules to determine the depth of each pixel in the scene depending on its label and its spatial position with regard to the vanishing point. We train two convolutional neural networks (CNNs): a semantic segmentation CNN and a vanishing point prediction CNN. We then fuse the results obtained from the two networks using the hand-crafted rules, which are defined based on single-view geometry rules by taking into consideration the label of the pixel and the nature of the object obtained by the segmentation model. Extensive experiments were done using the KITTI and Cityscapes benchmark datasets. The proposed model achieves impressive performance in semantic segmentation (mean intersection over union of 82.20%) and vanishing point estimation (mean absolute error of 1.87). Monocular depth estimation achieved a relative absolute error of 0.070 with the KITTI dataset and 0.289 with the Cityscapes dataset, outperforming many state-of-the-art methods in depth estimation and semantic segmentation at 10 frames per second.

Due to the wide range of intensive computational applications and ubiquitous connectivity of the Internet of Things (IoT) paradigms, it has become crucial to develop a new platform that can achieve low delay, high network throughput, and enhanced quality of service (QoS). This paper proposes a joint user association, service caching, and task offloading strategy to reduce delay and enhance users’ QoS in multi-tier communication and multi-tier edge computing heterogeneous networks (HetNets). The considered system model consists of multi-users with different tasks and service data sizes communicating in a heterogeneous network of one massive multiple-input multiple-output (M-MIMO) macro base station and some small base stations. The proposed work investigates user association, power allocation, optimum service data caching, and task offloading strategies at the computing network edges. Thereby, the …

Retained surgical items (RSIs) pose significant risks to patients and healthcare professionals, prompting extensive efforts to reduce their incidence. RSIs are objects inadvertently left within patients’ bodies after surgery, which can lead to severe consequences such as infections and death. The repercussions highlight the critical need to address this issue. Machine learning (ML) and deep learning (DL) have displayed considerable potential for enhancing the prevention of RSIs through heightened precision and decreased reliance on human involvement. ML techniques are finding an expanding number of applications in medicine, ranging from automated imaging analysis to diagnosis. DL has enabled substantial advances in the prediction capabilities of computers by combining the availability of massive volumes of data with extremely effective learning algorithms. This paper reviews and evaluates recently

Cancelable template protection techniques are indispensable to provide essential security and privacy privileges in biometric systems. This paper introduces an efficient cancelable palmprint recognition technique based on multi-level transformations. Gabor filtering with feature remapping is introduced for extracting highly discriminative features. Histogram remapping is applied to nonlinearly transform the downsampled Gabor features to be normally distributed. This feature-remapping step is proposed to enhance the discriminatory power and alleviate the effect of feature variability and image artifacts. Comb filtering is applied to the mapped features as a first protection layer. To provide security guarantees against linkability attacks, index-based locality-sensitive hashing (LSH) is introduced as a second protection layer to transform the comb-filtered mapped real-valued features into maximum-ranked indices …

The growing demand for high-quality video requires complex coding techniques that cost resource consumption and increase encoding time which represents a challenge for real-time processing on Embedded Systems. Kvazaar and x265 encoders are two efficient implementations of the High-Efficient Video Coding (HEVC) standard. In this paper, the performance of All Intra Kvazaar and x265 encoders on the Nvidia Jetson platform was evaluated using two coding configurations; highspeed preset and high-quality preset. In our work, we used two scenarios, first, the two encoders were run on the CPU, and based on the average encoding time Kvazaar proved to be 65.44% and 69.4% faster than x265 with 1.88% and 0.6% BD-rate improvement over x265 at high-speed and high-quality preset, respectively. In the second scenario, the two encoders were run on the GPU of the Nvidia Jetson, and the results show the …

Smart cities (SCs) were founded on the basis of the Internet of Vehicles paradigm, aiming to enhance the quality of life. Despite not having a unique composition, the intelligent transportation services (ITS) is a key component in most of the SCs. The ITS integrates the new communication systems along with the traditional transportation systems, forming a universal network of static and vehicular entities communicating over wireless broadcast channels. In addition to its vulnerability to co-channel interference (CCI), eavesdropping, and fading, the vehicle-to-vehicle communication channels could be subjected to shadowed fading. That is due to the probabilistic obstruction by big vehicles. Hence, degrading the signal-to-noise ratio at the receiving vehicle severely. This work evaluates the secrecy performance of a practical cooperative vehicular relaying network in terms of its secrecy outage probability (SOP). Due to …

Unmanned aerial vehicles (UAVs) are expected to be integrated into future wireless networks to offer services, especially in unreachable or congested areas. To improve the spectral efficiency, non-orthogonal multiple access (NOMA) scheme can be utilised within the UAV communication to allow more users to be covered and associated. The performance of the NOMA-UAVs network is governed by several factors including power allocation, user association and pairing methods. This paper presents an approach that uses multi-armed bandit (MAB) and two-sided matching frameworks to maximize the throughput of multi-UAV-assisted NOMA networks in a decentralized manner. The approach enables the UAVs to propose to the ground users (GUs) without explicit cooperation among the UAVs while the GUs can accept or reject the proposals. To this end, we propose a modified Thompson sampling algorithm that we named …