As an emerging privacy-preservation machine learning framework,Federated Learning(FL)facilitates different clients to train a shared model collaboratively through exchanging and aggregating model parameters while raw ...
详细信息
As an emerging privacy-preservation machine learning framework,Federated Learning(FL)facilitates different clients to train a shared model collaboratively through exchanging and aggregating model parameters while raw data are kept local and *** this learning framework is applied to Deep Reinforcement Learning(DRL),the resultant Federated Reinforcement Learning(FRL)can circumvent the heavy data sampling required in conventional DRL and benefit from diversified training data,besides privacy preservation offered by *** FRL implementations presuppose that clients have compatible tasks which a single global model can *** practice,however,clients usually have incompatible(different but still similar)personalized tasks,which we called task *** may severely hinder the implementation of FRL for practical *** this paper,we propose a Federated Meta Reinforcement Learning(FMRL)framework by integrating Model-Agnostic Meta-Learning(MAML)and ***,we innovatively utilize Proximal Policy Optimization(PPO)to fulfil multi-step local training with a single round of ***,considering the sensitivity of learning rate selection in FRL,we reconstruct the aggregation optimizer with the Federated version of Adam(Fed-Adam)on the server *** experiments demonstrate that,in different environments,FMRL outperforms other FL methods with high training efficiency brought by Fed-Adam.
Customized keyword spotting needs to adapt quickly to small user *** methods primarily solve the problem under moderate noise *** work increases the level of difficulty in detecting keywords by introducing keyword ***...
详细信息
Customized keyword spotting needs to adapt quickly to small user *** methods primarily solve the problem under moderate noise *** work increases the level of difficulty in detecting keywords by introducing keyword ***,the current solution has been explored on large models with many parameters,making it unsuitable for deployment on small *** applying the current solution to lightweight models with minimal training data,the performance degrades compared to the baseline ***,we propose a light-weight multi-task architecture(<9.0×10^(4)parameters)created from integrating the triplet attention module in the ConvMixer networks and a new auxiliary mixed labeling encoding to address the *** results of our experiment show that the proposed model outperforms similar light-weight models for keyword spotting,with accuracy gains ranging from 0.73%to 2.95%for a clean set and from 2.01%to 3.37%for a mixed set under different scales of training ***,our model shows its robustness in different low-resource language datasets while converging faster.
This paper will improve the fundamental ant colony optimization algorithm in the context of mobile robot path planning in response to its flaws, which include easy descent into a local optimum, a large number of infle...
详细信息
To address the issues of unknown target size,blurred edges,background interference and low contrast in infrared small target detection,this paper proposes a method based on density peaks searching and weighted multi-f...
详细信息
To address the issues of unknown target size,blurred edges,background interference and low contrast in infrared small target detection,this paper proposes a method based on density peaks searching and weighted multi-feature local ***,an improved high-boost filter is used for preprocessing to eliminate background clutter and high-brightness interference,thereby increasing the probability of capturing real targets in the density peak ***,a triple-layer window is used to extract features from the area surrounding candidate targets,addressing the uncertainty of small target *** calculating multi-feature local differences between the triple-layer windows,the problems of blurred target edges and low contrast are *** balance the contribution of different features,intra-class distance is used to calculate weights,achieving weighted fusion of multi-feature local differences to obtain the weighted multi-feature local differences of candidate *** real targets are then extracted using the interquartile *** on datasets such as SIRST and IRSTD-IK show that the proposed method is suitable for various complex types and demonstrates good robustness and detection performance.
Language-guided fashion image editing is challenging,as fashion image editing is local and requires high precision,while natural language cannot provide precise visual information for *** this paper,we propose LucIE,a...
详细信息
Language-guided fashion image editing is challenging,as fashion image editing is local and requires high precision,while natural language cannot provide precise visual information for *** this paper,we propose LucIE,a novel unsupervised language-guided local image editing method for fashion *** adopts and modifies recent text-to-image synthesis network,DF-GAN,as its ***,the synthesis backbone often changes the global structure of the input image,making local image editing *** increase structural consistency between input and edited images,we propose Content-Preserving Fusion Module(CPFM).Different from existing fusion modules,CPFM prevents iterative refinement on visual feature maps and accumulates additive modifications on RGB *** achieves local image editing explicitly with language-guided image segmentation and maskguided image blending while only using image and text *** on the DeepFashion dataset shows that LucIE achieves state-of-the-art *** with previous methods,images generated by LucIE also exhibit fewer *** provide visualizations and perform ablation studies to validate LucIE and the *** also demonstrate and analyze limitations of LucIE,to provide a better understanding of LucIE.
Industrial cyber-physical systems closely integrate physical processes with cyberspace, enabling real-time exchange of various information about system dynamics, sensor outputs, and control decisions. The connection b...
详细信息
Industrial cyber-physical systems closely integrate physical processes with cyberspace, enabling real-time exchange of various information about system dynamics, sensor outputs, and control decisions. The connection between cyberspace and physical processes results in the exposure of industrial production information to unprecedented security risks. It is imperative to develop suitable strategies to ensure cyber security while meeting basic performance *** the perspective of control engineering, this review presents the most up-to-date results for privacy-preserving filtering,control, and optimization in industrial cyber-physical systems. Fashionable privacy-preserving strategies and mainstream evaluation metrics are first presented in a systematic manner for performance evaluation and engineering *** discussion discloses the impact of typical filtering algorithms on filtering performance, specifically for privacy-preserving Kalman filtering. Then, the latest development of industrial control is systematically investigated from consensus control of multi-agent systems, platoon control of autonomous vehicles as well as hierarchical control of power systems. The focus thereafter is on the latest privacy-preserving optimization algorithms in the framework of consensus and their applications in distributed economic dispatch issues and energy management of networked power systems. In the end, several topics for potential future research are highlighted.
Temporal knowledge graph(TKG) reasoning, has seen widespread use for modeling real-world events, particularly in extrapolation settings. Nevertheless, most previous studies are embedded models, which require both enti...
详细信息
Temporal knowledge graph(TKG) reasoning, has seen widespread use for modeling real-world events, particularly in extrapolation settings. Nevertheless, most previous studies are embedded models, which require both entity and relation embedding to make predictions, ignoring the semantic correlations among different entities and relations within the same timestamp. This can lead to random and nonsensical predictions when unseen entities or relations occur. Furthermore, many existing models exhibit limitations in handling highly correlated historical facts with extensive temporal depth. They often either overlook such facts or overly accentuate the relationships between recurring past occurrences and their current counterparts. Due to the dynamic nature of TKG, effectively capturing the evolving semantics between different timestamps can be *** address these shortcomings, we propose the recurrent semantic evidenceaware graph neural network(RE-SEGNN), a novel graph neural network that can learn the semantics of entities and relations simultaneously. For the former challenge, our model can predict a possible answer to missing quadruples based on semantics when facing unseen entities or relations. For the latter problem, based on an obvious established force, both the recency and frequency of semantic history tend to confer a higher reference value for the current. We use the Hawkes process to compute the semantic trend, which allows the semantics of recent facts to gain more attention than those of distant facts. Experimental results show that RE-SEGNN outperforms all SOTA models in entity prediction on 6 widely used datasets, and 5 datasets in relation prediction. Furthermore, the case study shows how our model can deal with unseen entities and relations.
Accurate 3D hand pose estimation is a challenging computer vision problem primarily because of self-occlusion and viewpoint variations. Existing methods address viewpoint variations by applying data-centric transforma...
详细信息
Accurate 3D hand pose estimation is a challenging computer vision problem primarily because of self-occlusion and viewpoint variations. Existing methods address viewpoint variations by applying data-centric transformations, such as data alignments or generating multiple views, which are prone to data sensitivity, error propagation, and prohibitive computational requirements. We improve the estimation accuracy by mitigating the impact of self-occlusion and viewpoint variations from the network side and propose MH-Net, a novel multiheaded network for accurate 3D hand pose estimation from a depth image. MH-Net comprises three key components. First, a multiscale feature extraction backbone based on an improved multiscale vision transformer (MViTv2) is proposed to extract shift-invariant global features. Second, a 3D anchorset generator is proposed to generate three disjoint sets of 3D anchors that serve two purposes: formulating hand pose estimation as an anchor-to-joint offset estimation and defining three unique viewpoints from a single depth image. Third, three identical regression heads are proposed to regress 3D joint positions based on unique viewpoints defined by their respective anchorsets. Extensive ablation studies have been conducted to investigate the impact of anchorsets, regression heads, and feature extraction backbones. Experiments on three public datasets, ICVL, MSRA, and NYU, show significant improvements over the state-of-the-art. IEEE
Real-time systems are widely implemented in the Internet of Things(IoT) and safety-critical systems, both of which have generated enormous social value. Aiming at the classic schedulability analysis problem in real-ti...
详细信息
Real-time systems are widely implemented in the Internet of Things(IoT) and safety-critical systems, both of which have generated enormous social value. Aiming at the classic schedulability analysis problem in real-time systems, we proposed an exact Boolean analysis based on interference(EBAI) for schedulability analysis in real-time systems. EBAI is based on worst-case interference time(WCIT), which considers both the release jitter and blocking time of the task. We improved the efficiency of the three existing tests and provided a comprehensive summary of related research results in the field. Abundant experiments were conducted to compare EBAI with other related results. Our evaluation showed that in certain cases, the runtime gain achieved using our analysis method may exceed 73% compared to the stateof-the-art schedulability test. Furthermore, the benefits obtained from our tests grew with the number of tasks, reaching a level suitable for practical application. EBAI is oriented to the five-tuple real-time task model with stronger expression ability and possesses a low runtime overhead. These characteristics make it applicable in various real-time systems such as spacecraft, autonomous vehicles, industrial robots, and traffic command systems.
Purpose-Path planning is an important part of UAV mission *** main purpose of this paper is to overcome the shortcomings of the standard particle swarm optimization(PSO)such as easy to fall into the local optimum,so t...
详细信息
Purpose-Path planning is an important part of UAV mission *** main purpose of this paper is to overcome the shortcomings of the standard particle swarm optimization(PSO)such as easy to fall into the local optimum,so that the improved PSO applied to the UAV path planning can enable the UAV to plan a better quality ***/methodology/approach-Firstly,the adaptation function is formulated by comprehensively considering the performance constraints of the flight target as well as the UAV ***,the standard PSO is improved,and the improved particle swarm optimization with multi-strategy fusion(MFIPSO)is *** method introduces class sigmoid inertia weight,adaptively adjusts the learning factors and at the same time incorporates K-means clustering ideas and introduces the Cauchy perturbation ***,MFIPSO is applied to UAV path ***-Simulation experiments are conducted in simple and complex scenarios,respectively,and the quality of the path is measured by the fitness value and straight line rate,and the experimental results show that MFIPSO enables the UAV to plan a path with better ***/value-Aiming at the standard PSO is prone to problems such as premature convergence,MFIPSO is proposed,which introduces class sigmoid inertia weight and adaptively adjusts the learning factor,balancing the global search ability and local convergence ability of the *** idea of K-means clustering algorithm is also incorporated to reduce the complexity of the algorithm while maintaining the diversity of particle *** addition,the Cauchy perturbation is used to avoid the algorithm from falling into local ***,the adaptability function is formulated by comprehensively considering the performance constraints of the flight target as well as the UAV itself,which improves the accuracy of the evaluation model.
暂无评论