Few studies on competition in dual channel for durable goods take the product failures into consideration. However, the factors related to preventive maintenance (PM) and minimal maintenance (MM) have an important imp...
详细信息
Owing to an increasing number of functionally equivalent services on the cloud computing platform, quality-of-service (QoS) prediction and service recommendation have been developed using collaborative filtering (CF) ...
详细信息
Traditional navigation methods tend to design and train navigation skills based on the consideration of multi-scenario applicability and perform well in general scenarios. However, this results in sub-optimal navigati...
Traditional navigation methods tend to design and train navigation skills based on the consideration of multi-scenario applicability and perform well in general scenarios. However, this results in sub-optimal navigation performance in some context-specific scenarios, such as navigating through open or crowded scenarios. While some existing navigation skills can achieve satisfactory performance in context-specific scenarios, e.g., using PID in open scenarios and reinforcement learning-based training methods in crowded scenarios. Most methods currently do without consideration of the integration of navigation skills and contextual understanding. To address this gap, we propose an adaptive mapless navigation method to utilize the optimal capabilities of each skill corresponding to the context-specific scenario. Specifically, we package several existing navigation skills and train a scenario classifier to enable the agent to automatically select the most appropriate skill based on the current scenario. Furthermore, we incorporate evidential deep learning (EDL) to assess classification uncertainty and ensure the safe switching of navigation skills. Our method was tested in both simulated and real scenarios, and the results of the experiments confirmed the effectiveness and generalization of our method. Moreover, the proposed method exhibits notably enhanced, context-sensitive efficiency within a hybrid multi-scenario setting, in comparison to a single navigation skill.
3D information of surgical scene potentially enhances the accuracy of surgical navigation and facilitate the automation of robot-assisted surgery. However, current research seldom considers the relative 3D position be...
详细信息
ISBN:
(数字)9798331509644
ISBN:
(纸本)9798331509651
3D information of surgical scene potentially enhances the accuracy of surgical navigation and facilitate the automation of robot-assisted surgery. However, current research seldom considers the relative 3D position between instruments and tissue. In this paper, the instruments-tissue interaction estimation method is proposed to obtain the relative distance between instruments and tissue. The 3D Gaussian representation of instruments is established preoperatively, making the pose of instruments the only parameter to be learned and updated. Based on this, the instrument pose estimation method is proposed, which applies 3DGS (3D Gaussian Splatting) to the instrument Gaussian model to obtain rendered color images, projection masks, and depth maps. These are aligned with the input images, segmented masks and depth from stereo depth estimation to construct the target loss. By backpropagating through the target loss, the optimal instrument pose is obtained. The L1 loss and smooth loss based on TPS (the Thin Plate Spline) are used to complete the depth of tissue occluded by instruments. The instruments-tissue interaction is estimated by the nearest distance between instrument and tissue. The experimental results indicate an average error of 0.94 mm and an accuracy of 90.40% with an error less than 2mm in estimating relative 3D distance between instruments and tissue.
Online product reviews have been increasingly adopted by consumers to express their evaluation for products on e-commercial platforms. Consumers are encouraged to evaluate the review quality by helpful votes according...
详细信息
After natural disasters such as floods and earthquakes, Earth observation satellites (EOSs) often need to revisit affected areas multiple times to acquire multitemporal images. Such observation tasks are referred to a...
详细信息
Previous studies recognize pain expressions based on the entire face, for example, Prkachin and Solomon Pain intensity (PSPI). However, the patients face is often masked by instruments in an intensive care unit (ICU),...
详细信息
ISBN:
(纸本)9781665481106
Previous studies recognize pain expressions based on the entire face, for example, Prkachin and Solomon Pain intensity (PSPI). However, the patients face is often masked by instruments in an intensive care unit (ICU), such as respirator, and gauzes, just name a few, which causes the agent cannot measure the pain intensity using PSPI directly. To tackle this problem, we explore the pain intensity recognition from masked face. First, we conducted four levels of pain measurement experiments with four types of masked face using Swin-Transformer. Experiment results show that the accuracy of pain measurement is more than 90%, even masking a large part of facial Action Units (AU) related to the pain on the UNBC-McMaster dataset. Furthermore, we pre-train the pain recognition model with masked face dataset, such that the model can capture facial features contributed to the pain. Results on binary and four-level pain intensity measurement tasks show our model outperforms recent state-of-the-art performance, achieving 97.38% and 95.25% accuracy, respectively.
With the continuous emergence of new technologies, the manufacturing industry is facing unprecedented challenges. Manufacturing services typically involve various types of production equipment, diverse suppliers, and ...
详细信息
ISBN:
(数字)9798350387780
ISBN:
(纸本)9798350387797
With the continuous emergence of new technologies, the manufacturing industry is facing unprecedented challenges. Manufacturing services typically involve various types of production equipment, diverse suppliers, and varied customer demands. optimization in this context often encompasses multi pie objectives, necessitating timely adjustments in service comb ¡nations to meet customer needs. Traditional manufacturing models evidently fall short in resource allocation within manufacturing supply chains. Cloud manufacturing, proposed as a novel manufacturing model, aims to optimize resource allocation through the combination and configuration of resources, there by enhancing the efficiency of manufacturing supply chains. Logistics, as a crucial component within manufacturing supply chains, underscores the significance of coordinating the optimizad on of manufacturing and logistics services. This research focus es on the multi-objective optimization problem of cloud manufacturing service combinations. Building upon the execution process of manufacturing and logistics services for complex product manufacturing tasks, a novel mathematical model for the optimization of manufacturing resources and logistics resources i s constructed. The model utilizes the NSGA-H algorithm to coordinate the optimizationprocesses of manufacturing and legistics resources. Finally, a case study demonstrates the effectiveness of the proposed model.
Drawing on heuristic-systematic model (HSM), this study develops a research model to examine how content factors (i.e., persuasive and informative cues) and source factors (i.e., brand popularity and brand reputation)...
详细信息
Cross-efficiency evaluation in data envelopment analysis (DEA) assumes that decisionmaking units (DMUs) have full flexibility in choosing weights according to their individual preferences. However, this total autonom...
详细信息
暂无评论