With the rise of intelligent transportation (ITS), autonomous cars, and on-the-road entertainment and computation, vehicular edge computing (VEC) has become a primary research topic in 6G and beyond communications. On the other hand, reconfigurable intelligent surfaces (RIS) are a major enabling technology that can help in the task offloading domain. This study introduces a novel VEC architecture that incorporates non-orthogonal multiple access (NOMA) and reconfigurable intelligent surfaces (RIS), where vehicles perform binary or partial computation offloading to edge nodes (eNs) for task execution. We construct a vehicle-to-infrastructure (V2I) transmission model by considering vehicular interference and formulating a joint task offloading and resource allocation (JTORA) problem with the goal of reducing total service latency and energy usage. Next, we decompose this problem into task offloading (TO …

In the development history of high gradient magnetic separation (HGMS), the introduction of pulsating flow was extremely important, it successfully solved the problem of matrix clogging and allowed continuous and stable operation in the industry. However, the current pulsating HGMS (PHGMS) theory remains inadequately understood. In this paper, a 2D simulation model was established in COMSOL Multiphysics to reveal the magnetic field characteristics, flow field distribution, and particle capture dynamics in a PHGMS system. Quantitative comparisons were carried out between single-wire and multi-wire systems in the presence and absence of pulsation flow. The simulation results indicated that due to the coupled effect of neighboring magnetic wires in matrix, the magnetic field strength around an individual magnetic wire would slightly drop while the flow field velocity would increase. The introduction of pulsating flow could increase the peak value of fluid velocity and give particles a chance to move up and down. The analysis of particles travels length and capture probability indicated that the recovery for fine particles might be improved by increasing the strength of pulsating flow. This study provided a novel strategy for the highly efficient recovery of fine, weakly magnetic materials.

In southwest China, the Panzhihua area annually produces about 80 million tons of tailings with a TiO₂ grade of around 5.0%, which causes serious waste of titanium resources as well as environmental and safety issues. The ilmenite contained in these tailings is ultra-fine in size, so it is difficult to recover under the regular operating conditions of pulsating high gradient magnetic separation (PHGMS). In this study, an SLon-100 PHGMS separator was applied to concentrate an ultra-fine titanium tailing under a wide range of operating conditions. The experimental results indicated that a combination of high pulsating frequency, large pulsating stroke, and low feed velocity was favorable for the highly efficient recovery of ultra-fine ilmenite from the tailings. The TiO₂ grade in the optimal concentrate was enhanced from 4.33% to 13.64%, at a recovery of 66.55% and an enrichment ratio of 3.15 through a one-stage PHGMS process. The size analysis of the optimal concentrate showed that the TiO₂ recovery in -25+18 µm and -18+10 µm fractions exceeded 70%. To further understand this PHGMS performance, the optimal ultra-fine ilmenite and larger-size ilmenite concentration conditions were compared. This study provides a valuable reference in the PHGMS operation for recovering ultra-fine weakly magnetic minerals, including ilmenite.

Prostate cancer (PC) is a prevalent and potentially fatal form of cancer that affects men globally. However, the existing diagnostic methods, such as biopsies or digital rectal examination (DRE), have limitations in terms of invasiveness, cost, and accuracy. This study proposes a novel machine learning approach for the diagnosis of PC by leveraging clinical biomarkers and personalized questionnaires. In our research, we explore various machine learning methods, including traditional, tree-based, and advanced tabular deep learning methods, to analyze tabular data related to PC. Additionally, we introduce the novel utilization of convolutional neural networks (CNNs) and transfer learning, which have been predominantly applied in image-related tasks, for handling tabular data after being transformed to proper graphical representations via our proposed Tab2Visual modeling framework. Furthermore, we investigate leveraging the prediction accuracy further by constructing ensemble models. An experimental evaluation of our proposed approach demonstrates its effectiveness in achieving superior performance attaining an F1-score of 0.907 and an AUC of 0.911. This offers promising potential for the accurate detection of PC without the reliance on invasive and high-cost procedures.

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.