Machine learning has achieved great success in electroencephalogram (EEG) based brain-computer interfaces (BCIs). Most existing BCI studies focused on improving the decoding accuracy, with only a few considering the a...
详细信息
Proton Exchange Membrane Fuel Cells(PEMFCs) are prone to decreased lifespan due to the degradation of the platinum(Pt) catalyst during *** this study,we have established a one-dimensional model to investigate the effe...
Proton Exchange Membrane Fuel Cells(PEMFCs) are prone to decreased lifespan due to the degradation of the platinum(Pt) catalyst during *** this study,we have established a one-dimensional model to investigate the effects of different voltage conditions on Pt *** potential is found to be the most significant factor affecting the *** exposure to high potentials will significantly reduce the PEMFC's lifespan,and frequent voltage changes will exacerbate the *** mitigate this issue,we have designed three energy management strategies with different limitations and simulated their performance in the operating scenario of a fuel-cell hybrid electric vehicle(FCHEV).The results demonstrate that strategies restricting high potential occurrences and voltage variations can effectively alleviate Pt degradation.
Temporal concept shift (TCS) is an unavoidable problem in physiological signal-based emotion recognition tasks, i.e., the data distribution of physiological signals is constantly changing over time, which gradually de...
Temporal concept shift (TCS) is an unavoidable problem in physiological signal-based emotion recognition tasks, i.e., the data distribution of physiological signals is constantly changing over time, which gradually degrades the model accuracy. To this end, we propose a method based on a combination of domain adaptation and incremental learning to reduce the impact of temporal concept drift. In this paper, domain adaptation is used to reduce the distribution differences and incremental learning is used to prevent the learned knowledge from being forgotten. Finally, we validate the effectiveness of our approach on two real datasets.
We present 3D Cinemagraphy, a new technique that mar-ries 2D image animation with 3D photography. Given a single still image as input, our goal is to generate a video that contains both visual content animation and ca...
We present 3D Cinemagraphy, a new technique that mar-ries 2D image animation with 3D photography. Given a single still image as input, our goal is to generate a video that contains both visual content animation and camera motion. We empirically find that naively combining existing 2D image animation and 3D photography methods leads to obvious artifacts or inconsistent animation. Our key insight is that representing and animating the scene in 3D space offers a natural solution to this task. To this end, we first convert the input image into feature-based layered depth images using predicted depth values, followed by unprojecting them to a feature point cloud. To animate the scene, we perform motion estimation and lift the 2D motion into the 3D scene flow. Finally, to resolve the problem of hole emer-gence as points move forward, we propose to bidirectionally displace the point cloud as per the scene flow and synthe-size novel views by separately projecting them into target image planes and blending the results. Extensive experiments demonstrate the effectiveness of our method. A user study is also conducted to validate the compelling rendering results of our method.
When chaotic systems are implemented on finite precision machines, it will lead to the problem of dynamical degradation. Aiming at this problem, most previous related works have been proposed to improve the dynamical ...
详细信息
When chaotic systems are implemented on finite precision machines, it will lead to the problem of dynamical degradation. Aiming at this problem, most previous related works have been proposed to improve the dynamical degradation of low-dimensional chaotic maps. This paper presents a novel method to construct high-dimensional digital chaotic systems in the domain of finite computing precision. The model is proposed by coupling a high-dimensional digital system with a continuous chaotic system. A rigorous proof is given that the controlled digital system is chaotic in the sense of Devaney's definition of chaos. Numerical experimental results for different high-dimensional digital systems indicate that the proposed method can overcome the degradation problem and construct high-dimensional digital chaos with complicated dynamical properties. Based on the construction method, a kind of pseudorandom number generator (PRNG) is also proposed as an application.
Few-shot action recognition is a challenging but practical problem aiming to learn a model that can be easily adapted to identify new action categories with only a few labeled samples. Recent attempts mainly focus on ...
详细信息
Few-shot action recognition is a challenging but practical problem aiming to learn a model that can be easily adapted to identify new action categories with only a few labeled samples. Recent attempts mainly focus on learning deep representations for each video individually under the episodic meta-learning regime and then performing temporal alignment to match query and support videos. However, they still suffer from two drawbacks: (i) learning individual features without considering the entire task may result in limited representation capability, and (ii) existing alignment strategies are sensitive to noises and misaligned instances. To handle the two limitations, we propose a novel Hybrid Relation guided temporal Set Matching (HyRSM++) approach for few-shot action recognition. The core idea of HyRSM++ is to integrate all videos within the task to learn discriminative representations and involve a robust matching technique. To be specific, HyRSM++ consists of two key components, a hybrid relation module and a temporal set matching metric. Given the basic representations from the feature extractor, the hybrid relation module is introduced to fully exploit associated relations within and cross videos in an episodic task and thus can learn task-specific embeddings. Subsequently, in the temporal set matching metric, we carry out the distance measure between query and support videos from a set matching perspective and design a bidirectional Mean Hausdorff Metric to improve the resilience to misaligned instances. In addition, we explicitly exploit the temporal coherence in videos to regularize the matching process. In this way, HyRSM++ facilitates informative correlation exchanged among videos and enables flexible predictions under the data-limited scenario. Furthermore, we extend the proposed HyRSM++ to deal with the more challenging semi-supervised few-shot action recognition and unsupervised few-shot action recognition tasks. Experimental results on multiple benchmark
Brain-computer interfaces (BCIs) enable direct communication between the brain and external devices. This review highlights the core decoding algorithms that enable multimodal BCIs, including a dissection of the eleme...
详细信息
A lithium-sulfur(Li-S)system is an important candidate for future lithium-ion system due to its low cost and high specific theoretical capacity(1675 m Ah/g,2600 Wh/kg),which is greatly hindered by the poor conductivit...
详细信息
A lithium-sulfur(Li-S)system is an important candidate for future lithium-ion system due to its low cost and high specific theoretical capacity(1675 m Ah/g,2600 Wh/kg),which is greatly hindered by the poor conductivity of sulfur,large volume change and dissolution of lithium ***-dimensional(2D)materials with monolayers or few-layers usually have peculiar structures and physical/chemical properties,which can resolve the critical issues in Li-S ***,the metal-based 2D nanomaterials,including ferrum,cobalt or other metal-based composites with various anions,can provide high conductivity,large surface area and abundant reaction sites for restraining the diffusion for lithium *** this mini-review,we will present an overview of recent developments on metal-based 2D nanomaterials with various anions as the electrode materials for Li-S *** the main bottleneck for the Li-S system is the shuttle of polysulfides,emphasis is placed on the structure and components,physical/chemical interaction and interaction mechanisms of the 2D ***,the challenges and prospects of metal-based 2D nanomaterials for Li-S batteries are discussed and proposed.
Aiming at the shortcomings of traditional point cloud segmentation algorithms, this paper proposes a 3D lidar point cloud segmentation method combining ground filtering and multi-scale twin range image construction. T...
Aiming at the shortcomings of traditional point cloud segmentation algorithms, this paper proposes a 3D lidar point cloud segmentation method combining ground filtering and multi-scale twin range image construction. This method fully considers the geometric space distribution characteristics of the point cloud and the randomness of the positions between *** on the assumption of multi plane model, the point cloud is divided into sectors. The ground points are removed through region ground plane fitting and growth, and then the multi-scale twin range image is constructed according to non-ground *** the basis of the twin range image, the Breadth First Search algorithm is improved, the depth-breadth joint search strategy is proposed, all the points to be clustered are traversed, and the adaptive clustering threshold is used for point cloud clustering,which realizes a point cloud segmentation method with higher accuracy and robustness. Through the experimental analysis of KITTI dataset and collected campus outdoor scene dataset, compared with the traditional point cloud segmentation algorithm,the method proposed in this paper can effectively improve the point cloud segmentation accuracy and robustness of mobile robots in complex environments.
暂无评论