WiFi has been widely used for local area networking of devices and Internet access in the past two decades. Many researchers exploit WiFi signals for target sensing through analyzing the Channel State Information (CSI) of signals affected by the target movement. With the development of 6 G Integrated Sensing and Communication (ISAC), some researchers further consider using communication data packets for WiFi sensing. However, all the current works do not analyze the impact of ubiquitous interference on WiFi sensing performance. In this paper, we propose IRSensing, an interference-resistance design to improve the CSI quality under interference in the ISAC scenario, aiming to improve the WiFi sensing performance. IRSensing exploits the overall WiFi packet for CSI optimization. It first measures the interference level of each subcarrier based on variance analysis, then proposes a CSI optimization method based on maximal ratio combining to improve the CSI quality. It finally proposes a practical CSI enhancement process to adapt to complex interference situations in actual networks. We implement IRSensing on a hardware testbed and evaluate its performance under different settings. Experiment results show that it can significantly decrease the activity detection error rate by up to 80% and improve the classification accuracy by up to 15$\%$.

This work proposes a new retrospective motion correction method, termed DCGAN-MS, which employs disentangled CycleGAN based on multi-mask k-space subsampling (DCGAN-MS) to address the image domain translation challenge. The multi-mask k-space subsampling operator is utilized to decrease the complexity of motion artifacts by randomly discarding motion-affected k-space lines. The network then disentangles the subsampled, motion-corrupted images into content and artifact features using specialized encoders, and generates motion-corrected images by decoding the content features. By utilizing multi-mask k-space subsampling, motion artifact features become more sparse compared to the original image domain, enhancing the efficiency of the DCGAN-MS network. This method effectively corrects motion artifacts in clinical gadoxetic acid-enhanced human liver MRI, human brain MRI from fastMRI, and preclinical rodent brain MRI. Quantitative improvements are demonstrated with SSIM values increasing from 0.75 to 0.86 for human liver MRI with simulated motion artifacts, and from 0.72 to 0.82 for rodent brain MRI with simulated motion artifacts. Correspondingly, PSNR values increased from 26.09 to 31.09 and from 25.10 to 31.77. The method's performance was further validated on clinical and preclinical motion-corrupted MRI using the Kernel Inception Distance (KID) and Fréchet Inception Distance (FID) metrics. Additionally, ablation experiments were conducted to confirm the effectiveness of the multi-mask k-space subsampling approach.

Object detectors often struggle with accuracy and generalization when applied to aerial imagery, primarily due to the following challenges: 1) great scale variation of objects in aerial images: both extremely small and large objects are visible in the same image; and 2) an extreme imbalance of the training sample between positive and negative anchors: there are several positive ground truth (GT) anchors and an abundance of negative anchors. In this article, we propose a dynamic training sample selection network (DTSSNet) to solve the above-mentioned problems in two dimensions. An attention-enhanced feature module (AEFM) is proposed to enhance the basic features by focusing on both channel and semantic information related to targets. This module provides more valuable information for accurately classifying objects of different scales. To tackle the imbalance in training samples, this article implements a dynamic training sample selection (DTSS) module that divides the training samples based on GT information. This module dynamically selects samples, ensuring a more balanced representation of positive and negative anchors, leading to improved learning. Importantly, the combination of AEFM and DTSS does not introduce any additional computational costs. Experimental evaluations on the VisDrone2019-DET dataset demonstrate that DTSSNet outperforms base detectors and generic approaches. Furthermore, the effectiveness of DTSSNet is validated on the UAVDT benchmark dataset, where it achieves state-of-the-art performance.

With the development of unmanned vehicle technology, unmanned vehicles have played a huge role in logistics transportation, emergency rescue and disaster relief, etc., so the research on unmanned vehicles is becoming more and more important. Road detection is an important part of environmental perception and an important factor in the realization of assisted driving and unmanned driving technology. High-precision road detection technology can provide important environmental information for efficient planning and reasonable decision-making of unmanned vehicles. Firstly, the technical framework of road detection is given, and the road detection process is introduced in detail. Then, the vision-based road detection algorithm is introduced. Finally, some related data sets in the field of road detection are collected, which provides new ideas and methods for road detection researchers.

Learning-based algorithms are gradually emerging in the field of autonomous driving due to their powerful data processing capabilities. Researchers in the field of intelligent vehicle planning and decision-making are gradually using reinforcement learning algorithms to solve related problems. The safety research of reinforcement learning algorithms is significant and widely concerned. The main reason for the safety problem of the existing reinforcement learning algorithm is that there is still a bias in the safety judgment of the current environment, and it is impossible to make directional improvements by modifying the network and training method. In this paper, an action judgment network is designed as a standard to select the optimal action, which can assist the algorithm to judge environmental safety more deeply. Firstly, the action judgment network takes the state space and action as input, and the output is the safety state of the vehicle after the action. Secondly, this work establishes the required database to train the action judgment network through deep learning and achieves the highest accuracy of 98%. Finally, the proposed algorithm is tested in three scenarios: single-lane, intersection, and roundabout. This algorithm can judge the actions according to the reinforcement learning q value table order until the optimal and safe action is selected. The results show that the newly proposed algorithm can greatly improve the safety of the algorithm without affecting vehicle speed.

Big data applications have differentiated requirements for I/O resources in cloud environments. For instance, data analytic and AI/ML applications usually have periodical burst I/O traffic, and data stream processing and database applications often introduce fluctuating I/O loads based on a guaranteed I/O bandwidth. However, the existing resource isolation model (i.e., RLW) and methods (e.g., Token-bucket, mClock, and cgroup) cannot support the fluctuating I/O load and differentiated I/O demands well, and thus cannot achieve fairness, high resource utilization, and high performance for applications at the same time. In this paper, we propose a novel efficient and fair I/O resource isolation model and method called R2B, which can adapt to the differentiated I/O characteristics and requirements of different applications in a shared resource environment. R2B can simultaneously satisfy the fairness and achieve both high application efficiency and high bandwidth utilization.

Single-shot EPI(ssEPI) is one of the most important ultrafast MRI sequences commonly used for diffusion-weighted MRI and functional MRI. However, ssEPI suffers from susceptibility artifacts, especially in the high field or at the tissue boundaries. The widely used blip/down approaches, such as TOPUP, estimate the underlying distortion field from a pair of images with reversed-phase encoding direction. Typically, the iterative methods are used to find a solution to the ill-posed problem of finding the displacement map that maps up/down acquisitions onto each other. Then the geometric and intensity corrections are applied to obtain the undistorted images based on the estimated displacement map. This paper presents a new unsupervised cycle-consistent deep neural network that takes advantage of both the deep neural network and the gradient reversal method. The proposed method consists of three main components: (1) the Resnet50-Unet to map the pair of images with inverted phase encoding to the displacement maps; (2) the geometric and intensity correction module to obtain the undistorted images; (3) the forward model is applied to get the cycled blip up/down images, and the cycle-consistent loss is optimized. In addition, the CNN network will generate two field maps to overcome motion or field drift during the scan. This new network is trained unsupervised on the clinical datasets downloaded from the Human Connection Project website. And we test this method on both preclinical and clinical datasets. The preclinical dataset is collected from 20 mice based on the modified EPI pulse sequence in 7T scanner. Both simulated and experimental results demonstrate that our method outperforms state-of-the-art methods. In conclusion, we proposed an unsupervised cycle-consistent deep neural network for removing susceptibility artifacts. The results on both preclinical and clinical datasets show this new method’s acceleration and generalization capabilities.

This paper presents conditions such that multisided Bezier patches G/sup 1/-continuously fill any n-sided holes, formed by rectangular Bezier patches of any degrees.