Accurate 3D object segmentation in point clouds is a basis for industrial robot applications, such as robot manipulation and digital twin, which require an understanding of the 3D environment. However, the unstructured and disordered nature of point clouds makes it challenging, especially for the incomplete 3D data under a single view in the real-world scenario. To this end, this paper proposes a novel 3D object segmentation framework (3DT-Seg) based on Cross-Window Point Transformer (CP-Former). CP-Former captures the long-range dependencies between local windows and latent semantic boundaries to enhance the point-wise features extracted from irregular point clouds via a bidirectional cross-attention mechanism. In addition, a contrastive learning loss and an adaptive dual aggregation strategy are introduced on semantic transition regions during the semantic supervising and instance clustering process, respectively. In this way, the latent boundary information is further utilized to improve the overall segmentation performance. Experiments on the popular benchmark (SI3DS) dataset show the state-of-the-art performance of the proposed approach in terms of semantic and instance segmentation. Furthermore, a real-world point cloud dataset (IP-Cloud) for the robotic grasping task is presented to fully validate the effectiveness of our method in practice, where it also achieves remarkable performance.
Deep learning plays an increasingly important role in industrial applications, such as the remaining useful life (RUL) prediction of machines. However, when dealing with multifeature data, most deep learning approaches do not have effective mechanisms to weigh the input features adaptively. In this article, a novel feature-attention-based end-to-end approach is proposed for RUL prediction. First, the proposed feature-attention mechanism is directly applied to the input data, which gives greater attention weights to more important features dynamically in the training process. This helps the model focus more on those critical inputs, and the prediction performance is therefore improved. Next, bidirectional gated recurrent units (BGRU) are used to extract long-term dependencies from the weighted input data, and convolutional neural networks are employed to capture local features from the output sequences of BGRU. Finally, fully connected networks are used to learn the above-mentioned abstract representations to predict the RUL. The proposed approach is validated in a case study of turbofan engines. The experimental results demonstrate that the proposed approach outperforms other latest existing approaches.
The wireless sensor network is one new hot spot for both research and industry. Currently several communication protocols have been developed for wireless sensor network, including Zigbee, wirelessHART, ISA100.11a, WIA-PA, and so on. Most of these protocols are developed based on IEEE 802.15.4. IEEE 802.15.4 was designed for low-cost and low-power wireless network which provides MAC layer and physical layer specification. In this paper, the performance of IEEE802.15.4 is analyzed based on NS-2 simulator. According to the simulation results, Performance is analyzed for different application requirements, for example, the packet reception ratio over different sending interval time, the packed routing load over different sending interval time. etc.
With the rapid development of various internet of things (IoT) applications, including industrial IoT (IIoT) and visual IoT (VIoT), the demand for direct device-to-device communication to support high data rates continues to grow. To address this demand, 5G-Advanced has introduced sidelink communication over the unlicensed spectrum (SL-U) as a method to increase data rates. However, the primary challenge of SL-U in the unlicensed spectrum is ensuring fair coexistence with other incumbent systems, such as Wi-Fi. In this paper, we address the challenge by designing channel access mechanisms and power control strategies to mitigate interference and ensure fair coexistence. First, we propose a novel collaborative channel access (CCHA) mechanism that integrates channel access with resource allocation through collaborative interactions between base stations (BS) and SL-U users. This mechanism ensures fair coexistence with incumbent systems while improving resource utilization. Second, we mathematically model the joint channel access and power control problems, analyzing the trade-off between fairness and transmission rate to minimize interference and optimize performance in the coexistence system. Finally, we develop a collaborative subgoal-based hierarchical deep reinforcement learning (C-GHDRL) framework. This framework enables SL-U users to make globally optimal decisions by leveraging collaborative operations between the BS and SL-U users, effectively overcoming the limitations of traditional optimization methods in solving joint optimization problems with nonlinear constraints. Simulation results demonstrate that the proposed scheme significantly enhances the coexistence system's performance while ensuring fair coexistence between SL-U and Wi-Fi users.
This paper presents a numerical analysis procedure, called spline semidiscretization procedure, for the unified analysis of orthotropic and/or isotropic thin plates and shallow shells of rectangular projection with the two opposite edges in the y direction simply supported. The sine and cosine functions may thus be employed as the displacement trial functions in the y direction. By semidiscretization through dividing plate and shell into N equal subintervals, the B3 spline function, consisting of the (N+3) local B3 spline functions (the first and last three local B3 spline functions have been modified for accommodating to any type of boundary conditions) with respect to the (N+1) points and two extended additional points in the x direction, can then be used as the displacement trial function in the x direction. Governing equations of an orthothopic shallow shell subjected to the distributed, linearly distributed, concentrated loads or their combinations are derived based on its potential energy functional. Unified formulas for the determination of displacements and internal forces of the orthotropic and/or isotropic thin plates and shallow shells are obtained. In comparison to the conventional finite element method, with the displacement trial functions having the good properties with piecewise polynomial as well as orthogonality and decoupling, the present procedure has remarkably fewer unknowns to be solved (more precisely, a term by term analysis involving only much smaller matrices can be conducted), and thus it is computatively more efficient. Likewise, the computational program, with minimal preparation of input data, can be very easily developed through the present formulation. Numerical results indicate that the present method can render a very high accuracy. The fast convergence shown in numerical examples demonstrates the reliability of the results.
With the introduction of cost-effective depth sensors, a tremendous amount of research has been devoted to studying human action recognition using 3D motion data. However, most existing methods work in an offline fashion, i.e., they operate on a segmented sequence. There are a few methods specifically designed for online action recognition, which continually predicts action labels as a stream sequence proceeds. In view of this fact, we propose a question: can we draw inspirations and borrow techniques or descriptors from existing offline methods, and then apply these to online action recognition? Note that extending offline techniques or descriptors to online applications is not straightforward, since at least two problems—including real-time performance and sequence segmentation—are usually not considered in offline action recognition. In this paper, we give a positive answer to the question. To develop applicable online action recognition methods, we carefully explore feature extraction, sequence segmentation, computational costs, and classifier selection. The effectiveness of the developed methods is validated on the MSR 3D Online Action dataset and the MSR Daily Activity 3D dataset.
How to measure reuse capability of a test case is critical in software test reuse research. A dynamic method based on Bayesian network is proposed for measure the reuse of test case. It collects the information of user's searching and reusing test cases, and then analysis the test case's reuse capability which give basis for consulting to users. The prominent characteristic of this method is that the reuse of test case is divided into three aspects in terms of different reuse preference that improve the accuracy of metric.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)