Search

In order to achieve stable and reliable industrial manufacturing, wireless networks must meet the stringent communication requirements of industrial automation, particularly the need for deterministic low latency communication. The limited wireless resources and time-varying fading channel contribute to the random fluctuations of transmission delay, making it challenging to realize delay-deterministic wireless networks. An open challenge in this context is to model delay determinism, also known as jitter, and analyze delay performance. In this paper, we model jitter as the variance of delay and conduct a comprehensive analysis of delay performance. Specifically, we consider two transmission regimes: infinite blocklength (IBL) and finite blocklength (FBL). In the IBL regime, the distribution of the transmission delay is analyzed, and the closed-form expressions for the average delay, jitter, and delay violation probability are derived. In the FBL regime, an upper bound on the transmission delay is first approximated at a high signalto-noise ratio. Based on this upper bound, the delay distribution, delay violation probability, average delay, and jitter are derived. Finally, simulation results are provided to validate the accuracy of the analysis and derivations. Additionally, the impact of system parameters on jitter is analyzed to gain further insights.

Neural implicit representations have been explored to enhance visual SLAM algorithms, especially in providing high-fidelity dense map. Existing methods operate robustly in static scenes but struggle with the disruption caused by moving objects. In this paper we present NID-SLAM, which significantly improves the performance of neural SLAM in dynamic environments. We propose a new approach to enhance inaccurate regions in semantic masks, particularly in marginal areas. Utilizing the geometric information present in depth images, this method enables accurate removal of dynamic objects, thereby reducing the probability of camera drift. Additionally, we introduce a keyframe selection strategy for dynamic scenes, which enhances camera tracking robustness against large-scale objects and improves the efficiency of mapping. Experiments on publicly available RGB-D datasets demonstrate that our method outperforms competitive neural SLAM approaches in tracking accuracy and mapping quality in dynamic environments.

360{\deg} spherical images have advantages of wide view field, and are typically projected on a planar plane for processing, which is known as equirectangular image. The object shape in equirectangular images can be distorted and lack translation invariance. In addition, there are few publicly dataset of equirectangular images with labels, which presents a challenge for standard CNNs models to process equirectangular images effectively. To tackle this problem, we propose a methodology for converting a perspective image into equirectangular image. The inverse transformation of the spherical center projection and the equidistant cylindrical projection are employed. This enables the standard CNNs to learn the distortion features at different positions in the equirectangular image and thereby gain the ability to semantically the equirectangular image. The parameter, {\phi}, which determines the projection position of the perspective image, has been analyzed using various datasets and models, such as UNet, UNet++, SegNet, PSPNet, and DeepLab v3+. The experiments demonstrate that an optimal value of {\phi} for effective semantic segmentation of equirectangular images is 6{\pi}/16 for standard CNNs. Compared with the other three types of methods (supervised learning, unsupervised learning and data augmentation), the method proposed in this paper has the best average IoU value of 43.76%. This value is 23.85%, 10.7% and 17.23% higher than those of other three methods, respectively.

This paper establishes an existence and uniqueness result for the adapted solution of a general time interval multidimensional backward stochastic differential equation (BSDE), where the generator $g$ satisfies a weak stochastic-monotonicity condition and a general growth condition in the state variable $y$, and a stochastic-Lipschitz condition in the state variable $z$. This unifies and strengthens some known works. In order to prove this result, we develop some ideas and techniques employed in \citet{XiaoFan2017Stochastics} and \citet{LiuLiFan2019CAM}. In particular, we put forward and prove a stochastic Gronwall-type inequality and a stochastic Bihari-type inequality, which generalize the classical ones and may be useful in other places. The martingale representation theorem, It\^{o}'s formula and the BMO martingale tool are used to prove these two inequalities., Comment: 20 pages

As a type of prominent studies in deep learning, generative models have been widely investigated in research recently. Two research branches of the deep learning models, the Generative Networks (GANs, VAE) and the Semantic Segmentation, rely highly on the upsampling operations, especially the transposed convolution and the dilated convolution. However, these two types of convolutions are intrinsically different from standard convolution regarding the insertion of zeros in input feature maps or in kernels respectively. This distinct nature severely degrades the performance of the existing deep learning engine or frameworks, such as Darknet, Tensorflow, and PyTorch, which are mainly developed for the standard convolution. Another trend in deep learning realm is to deploy the model onto edge/ embedded devices, in which the memory resource is scarce. In this work, we propose a Highly Untangled Generative-model Engine for Edge-computing or HUGE2 for accelerating these two special convolutions on the edge-computing platform by decomposing the kernels and untangling these smaller convolutions by performing basic matrix multiplications. The methods we propose use much smaller memory footprint, hence much fewer memory accesses, and the data access patterns also dramatically increase the reusability of the data already fetched in caches, hence increasing the localities of caches. Our engine achieves a speedup of nearly 5x on embedded CPUs, and around 10x on embedded GPUs, and more than 50% reduction of memory access.