Joint flexibility is an important factor to consider in the robot control design if high performance is expected for the robot manipulators. In this paper, we propose an adaptive tracking control method which can deal...
详细信息
This paper develops a method to learn very few discriminative part detectors from training videos directly, for action recognition. We hold the opinion that being discriminative to action classification is of primary ...
详细信息
Vehicle scheduling plays a crucial role in public transport bus companies. An efficient schedule can help bus companies reduce operating costs while being an essential guide to daily operations. However, the precompil...
详细信息
ISBN:
(纸本)9781538629185
Vehicle scheduling plays a crucial role in public transport bus companies. An efficient schedule can help bus companies reduce operating costs while being an essential guide to daily operations. However, the precompiled schedule is usually hard to be adhered to in practice due to the diversity of traffic and driving conditions. Therefore, dynamic vehicle scheduling becomes an important supplement to the daily operations. In this paper, a dynamic vehicle scheduling approach based on Hierarchical Task Network(HTN) is proposed. In the approach, two dynamic vehicle scheduling strategies are devised according to the practical scheduling philosophy. The first is to reschedule for individual vehicle independently, the objective is to maximize the execution of the precompiled schedule. The second is to reschedule for multiple vehicles simultaneously, which aims to maintain the scheduled headways. The two strategies are achieved in the HTN planning through different task decomposition processes, which are constrained by vehicle resources currently available. To verify the feasibility, this approach is implemented based on the Simple Hierarchical Ordered Planner 2(SHOP2), which is a domainindependent and state-based forward HTN planner. Experimental results show that the approach has good adaptability to solve dynamic vehicle schedule problem, meanwhile, it can be helpful to deal with the abnormal services agilely and hence to increase the service quality of public transit.
Labor division provides an adaptive and scalable technique for unmanned systems. However, its designing process usually relies heavily on the manually crafted paradigms, leading to inefficiencies and insufficient perf...
Labor division provides an adaptive and scalable technique for unmanned systems. However, its designing process usually relies heavily on the manually crafted paradigms, leading to inefficiencies and insufficient performance. To overcome these challenges, this paper introduce an evolutionary approach to labor division algorithm design. Drawing inspiration from the regulatory behaviors observed in natural lion populations, we propose a bipolar feedback-guided attraction–repulsion mechanism. A formal model is developed to encapsulate this mechanism, and we provide an in-depth analysis of the algorithm’s evolution through the framework of systems science. In addition, we leverage prompt engineering techniques to integrate a large language model (LLM) with our proposed mechanism, facilitating a bidirectional enhancement between the two. This integration culminates in the development of the ARE-LLM framework, a robust and adaptive solution for designing labor division algorithms. To demonstrate the practical applicability of our approach, we apply the ARE-LLM framework to the UAV-based task allocation problem for enemy air defense suppression. The experimental results indicate that our method outperforms several advanced approaches. In a scenario involving 50 UAVs tasked with completing 300 assignments, the total distance traveled is only 9 % of that required by the ALPDA algorithm, while the processing time is reduced to 8 % of that used by ALPDA.
Bus driver rostering is a world-wide problem, which is NP-hard. Two objectives exist in the problem: (1) minimizing the number of drivers;(2) minimizing excess workload of each driver and balancing excess workload amo...
详细信息
Bearing remaining useful life(RUL) prediction is critical for safe operation of rotating *** this paper,we propose a combined RUL prediction approach that leverages both trajectory similarity and relevance vector mach...
详细信息
ISBN:
(数字)9789887581536
ISBN:
(纸本)9781665482561
Bearing remaining useful life(RUL) prediction is critical for safe operation of rotating *** this paper,we propose a combined RUL prediction approach that leverages both trajectory similarity and relevance vector machine(RVM).The similarity based prediction relies on historical degradation trajectories that are highly similar to the online data,hence would perform poorly if all historical trajectories have low similarity with the online *** RVM based prediction relies solely on a regression model learned from the available online data,thus gives an inaccurate prediction when insufficient data are available in the early stage of degradation.A weighted sum of these above two predictions is proposed to address the limitation of each single prediction method,whose weights are determined by solving a non-negative least squares fitting *** further improve RUL prediction accuracy,we distinguish between fast and slow degradation modes,so that each mode uses a different set of historical degradation trajectories and kernel *** doing so,we predict RUL under the identified *** case study using the PHM2012 dataset demonstrates the effectiveness of the proposed RUL prediction approach.
In the past nearly two decades, DNA self-assembly technology as a promising technology, a body of laboratory work has been emerged in an endless stream. Single-stranded DNA tile (SST) assembly provides a simple, modul...
详细信息
With the development of medical image technology, multimodal medical image instance segmentation is a research hotspot. Existing instances segmentation model of multimodal medical image does not fully consider the com...
详细信息
With the development of medical image technology, multimodal medical image instance segmentation is a research hotspot. Existing instances segmentation model of multimodal medical image does not fully consider the complementary information of multimodal images lesions. To address the issues of low contrast and blurred boundary of lesion information in lung tumor medical images,the instance segmentation model is proposed for PET/CT lung tumor medical images in this paper. The main contributions of the model include the following 3 parts. Firstly,in order to adequately fully utilize the common features of lesions in different modal images for lesion morphological enhancement,a multimodal feature mixer is designed. The module adaptively learns the common features related to lesion area through the PET and CT 2 branches. Specifically,it first normalizes the input PET and CT feature maps to make the data distribution more stable. Then,it adopts the self-attention mechanism to extract the PET/CT branche features. This mechanism enables the model to focus on different parts of the features and capture more discriminative information. After that,it fuses the features of lesions areas learned from PET and CT branches into PET/CT branches pixel by pixel. By using a weighted fusion method,the important features are emphasized,thereby highlighting the features of lesions areas and making the lesion regions stand out more clearly in the images. Secondly,in order to increase the lesion area attention,the enhanced feature pyramid is designed,which includes an enhanced feature fusion module and a multi-scale feature fusion device. For the enhanced feature fusion module,in the top-down fusion process,the module focuses on the semantic information of the high-level feature map while suppressing the noise factor. It does this by leveraging self-attention mechanisms to selectively emphasize relevant features. For the multi-scale feature fusion device,which receives the coarse and fine
We consider the problem of looking for small universal spiking neural P systems with exhaustive use of rules, which was formulated as an open problem by Andrei PǍun and Gheorghe PǍun in a survey paper. Here, spiking...
详细信息
There have been increasing interests in studying multiplex dynamical networks *** paper focuses on topology identiflcation of two-layer multiplex networks with peer-to-peer interlayer *** a two-layer network model in ...
详细信息
There have been increasing interests in studying multiplex dynamical networks *** paper focuses on topology identiflcation of two-layer multiplex networks with peer-to-peer interlayer *** a two-layer network model in which different layers have different coupling patterns,we propose novel methods to recover unknown topological structure of one layer,using the information of the other layer known as a *** proposed methods make full use of the measured evolutional states of the multiplex network itself,and treat the layer with a known structure as an auxiliary layer which is designed to identify the unknown topological *** with the traditional synchronization-based identiflcation method,the proposed methods are in no need of constructing an additional auxiliary network to identify the unknown topological layer,and thus greatly reduce the cost of topology ***,numerical simulations validate the effectiveness of the proposed methods.
暂无评论