Highway safety researchers focus on crash injury severity,utilizing deep learning—specifically,deep neural networks(DNN),deep convolutional neural networks(D-CNN),and deep recurrent neural networks(D-RNN)—as the pre...
详细信息
Highway safety researchers focus on crash injury severity,utilizing deep learning—specifically,deep neural networks(DNN),deep convolutional neural networks(D-CNN),and deep recurrent neural networks(D-RNN)—as the preferred method for modeling accident *** learning’s strength lies in handling intricate relation-ships within extensive datasets,making it popular for accident severity level(ASL)prediction and *** prior success,there is a need for an efficient system recognizing ASL in diverse road *** address this,we present an innovative Accident Severity Level Prediction Deep Learning(ASLP-DL)framework,incorporating DNN,D-CNN,and D-RNN models fine-tuned through iterative hyperparameter selection with Stochastic Gradient *** framework optimizes hidden layers and integrates data augmentation,Gaussian noise,and dropout regularization for improved *** and factor contribution analyses identify influential *** on three diverse crash record databases—NCDB 2018–2019,UK 2015–2020,and US 2016–2021—the D-RNN model excels with an ACC score of 89.0281%,a Roc Area of 0.751,an F-estimate of 0.941,and a Kappa score of 0.0629 over the NCDB *** proposed framework consistently outperforms traditional methods,existing machine learning,and deep learning techniques.
To handle input and output time delays that commonly exist in many networked control systems(NCSs), a new robust continuous sliding mode control(CSMC) scheme is proposed for the output tracking in uncertain single inp...
详细信息
To handle input and output time delays that commonly exist in many networked control systems(NCSs), a new robust continuous sliding mode control(CSMC) scheme is proposed for the output tracking in uncertain single input-single-output(SISO) networked control systems. This scheme consists of three consecutive steps. First, although the network-induced delay in those systems can be effectively handled by using Pade approximation(PA), the unmatched disturbance cames out as another difficulty in the control design. Second, to actively estimate this unmatched disturbance, a generalized proportional integral observer(GPIO) technique is utilized based on only one measured state. Third, by constructing a new sliding manifold with the aid of the estimated unmatched disturbance and states, a GPIO-based CSMC is synthesized, which is employed to cope with not only matched and unmatched disturbances, but also networkinduced delays. The stability of the entire closed-loop system under the proposed GPIO-based CSMC is detailedly *** promising tracking efficiency and feasibility of the proposed control methodology are verified through simulations and experiments on Quanser's servo module for motion control under various test conditions.
Glaucoma is an ophthalmic disorder which results in permanent vision loss because high intraocular pressure damages the optic nerve in the eye. This paper proposes a two-stage network for automated glaucoma identifica...
详细信息
The integration of social networks with the Internet of Things (IoT) has been explored in recent research, giving rise to the Social Internet of Things (SIoT). One promising application of SIoT is viral marketing, whi...
详细信息
Reinforcement learning(RL) has been widely adopted for intelligent decision-making in embodied agents due to its effective trial-and-error learning capabilities. However, most RL methods overlook the causal relationsh...
详细信息
Reinforcement learning(RL) has been widely adopted for intelligent decision-making in embodied agents due to its effective trial-and-error learning capabilities. However, most RL methods overlook the causal relationships among states and actions during policy exploration and lack the human-like ability to distinguish signal from noise and reason with important abstractions, resulting in poor sample efficiency. To address this issue, we propose a novel method named causal action empowerment(CAE) for efficient RL, designed to improve sample efficiency in policy learning for embodied agents. CAE identifies and leverages causal relationships among states, actions, and rewards to extract controllable state variables and reweight actions for prioritizing high-impact behaviors. Moreover, by integrating a causality-aware empowerment term, CAE significantly enhances an embodied agent's execution of causally-aware behavior for more efficient exploration via boosting controllability in complex embodied environments. Benefiting from these two improvements, CAE bridges the gap between local causal discovery and global causal empowerment. To comprehensively evaluate the effectiveness of CAE, we conduct extensive experiments across 25 tasks in 5 diverse embodied environments, encompassing both locomotion and manipulation skill learning with dense and sparse reward settings. Experimental results demonstrate that CAE consistently outperforms existing methods across this wide range of scenarios, offering a promising avenue for improving sample efficiency in RL.
As optimization problems continue to grow in complexity,the need for effective metaheuristic algorithms becomes increasingly ***,the challenge lies in identifying the right parameters and strategies for these *** this...
详细信息
As optimization problems continue to grow in complexity,the need for effective metaheuristic algorithms becomes increasingly ***,the challenge lies in identifying the right parameters and strategies for these *** this paper,we introduce the adaptive multi-strategy Rabbit Algorithm(RA).RA is inspired by the social interactions of rabbits,incorporating elements such as exploration,exploitation,and adaptation to address optimization *** employs three distinct subgroups,comprising male,female,and child rabbits,to execute a multi-strategy *** parameters,including distance factor,balance factor,and learning factor,strike a balance between precision and computational *** offer practical recommendations for fine-tuning five essential RA parameters,making them versatile and *** is capable of autonomously selecting adaptive parameter settings and mutation strategies,enabling it to successfully tackle a range of 17 CEC05 benchmark functions with dimensions scaling up to *** results underscore RA’s superior performance in large-scale optimization tasks,surpassing other state-of-the-art metaheuristics in convergence speed,computational precision,and ***,RA has demonstrated its proficiency in solving complicated optimization problems in real-world engineering by completing 10 problems in CEC2020.
The goal of infrared and visible image fusion(IVIF)is to integrate the unique advantages of both modalities to achieve a more comprehensive understanding of a scene. However, existing methods struggle to effectively h...
详细信息
The goal of infrared and visible image fusion(IVIF)is to integrate the unique advantages of both modalities to achieve a more comprehensive understanding of a scene. However, existing methods struggle to effectively handle modal disparities,resulting in visual degradation of the details and prominent targets of the fused images. To address these challenges, we introduce Prompt Fusion, a prompt-based approach that harmoniously combines multi-modality images under the guidance of semantic prompts. Firstly, to better characterize the features of different modalities, a contourlet autoencoder is designed to separate and extract the high-/low-frequency components of different modalities, thereby improving the extraction of fine details and textures. We also introduce a prompt learning mechanism using positive and negative prompts, leveraging Vision-Language Models to improve the fusion model's understanding and identification of targets in multi-modality images, leading to improved performance in downstream tasks. Furthermore, we employ bi-level asymptotic convergence optimization. This approach simplifies the intricate non-singleton non-convex bi-level problem into a series of convergent and differentiable single optimization problems that can be effectively resolved through gradient *** approach advances the state-of-the-art, delivering superior fusion quality and boosting the performance of related downstream tasks. Project page: https://***/hey-it-s-me/PromptFusion.
Sampling and communication are both crucial for coordination in multi-agent systems(MASs), with sampling capturing raw data from the environment for control decision making, and communication ensuring the data is shar...
详细信息
Sampling and communication are both crucial for coordination in multi-agent systems(MASs), with sampling capturing raw data from the environment for control decision making, and communication ensuring the data is shared effectively for synchronized and informed control decisions across agents. However, practical MASs often operate in environments where continuous and synchronous data samplings and exchanges are impractical, necessitating strategies that can handle intermittent sampling and communication constraints. This paper provides a comprehensive survey of recent advances in distributed coordination control of MASs under intermittent sampling and communication, focusing on both foundational principles and state-of-the-art techniques. After introducing fundamentals, such as communication topologies,agent dynamics, control laws, and typical coordination objectives, the distinctions between sampling and communication are elaborated, exploring deterministic versus random, synchronous versus asynchronous, and instantaneous versus sequential scenarios. A detailed review of emerging trends and techniques is then presented, covering time-triggered, event-triggered,communication-protocol-based, and denial-of-service-resilient coordination control. These techniques are analyzed across various attack models, including those based on data loss, sampled data, time constraints, and topology switching. By synthesizing these developments, this survey aims to equip researchers and practitioners with a clearer understanding of current challenges and methodologies, concluding with insights into promising future directions.
In the contemporary landscape, autonomous vehicles (AVs) have emerged as a prominent technological advancement globally. Despite their widespread adoption, significant hurdles remain, with security standing out as a c...
详细信息
Detecting surface defects on unused rails is crucial for evaluating rail quality and durability to ensure the safety of rail ***,existing detection methods often struggle with challenges such as complex defect morphol...
详细信息
Detecting surface defects on unused rails is crucial for evaluating rail quality and durability to ensure the safety of rail ***,existing detection methods often struggle with challenges such as complex defect morphology,texture similarity,and fuzzy edges,leading to poor accuracy and missed *** order to resolve these problems,we propose MSCM-Net(Multi-Scale Cross-Modal Network),a multiscale cross-modal framework focused on detecting rail surface ***-Net introduces an attention mechanism to dynamically weight the fusion of RGB and depth maps,effectively capturing and enhancing features at different scales for each *** further enrich feature representation and improve edge detection in blurred areas,we propose a multi-scale void fusion module that integrates multi-scale feature *** improve cross-modal feature fusion,we develop a cross-enhanced fusion module that transfers fused features between layers to incorporate interlayer *** also introduce a multimodal feature integration module,which merges modality-specific features from separate decoders into a shared decoder,enhancing detection by leveraging richer complementary ***,we validate MSCM-Net on the NEU RSDDS-AUG RGB-depth dataset,comparing it against 12 leading methods,and the results show that MSCM-Net achieves superior performance on all metrics.
暂无评论