An assignment-driven multi-consensus problem of multi-agent systems with heterogeneous delays is investigated in this paper. By introducing a concept of intelligent adjustment factor, a distributed impulsive protocol ...
详细信息
ISBN:
(纸本)9781509017393
An assignment-driven multi-consensus problem of multi-agent systems with heterogeneous delays is investigated in this paper. By introducing a concept of intelligent adjustment factor, a distributed impulsive protocol is designed, in which only the delayed sampled relative positions to neighbors and the relative position to the last sampling state are utilized. Combined with the characteristic of impulsive control, three steps of model transformation are performed, and the assignment-driven multi-consensus problem of the original continuous-time system is converted to the stability problem of a discrete-time expanded analogous error system. A necessary and sufficient criterion is derived to guarantee the assignment-driven multi-consensus of the multi-agent system. An interesting simulation is proposed to demonstrate the effectiveness of the theoretical result and reveal the effect of intelligent adjustment factors on the assignment-driven multi-consensus.
In Ultrasound imaging, speckle noise is the most serious problem which affects the performance of images. Non-local mean filter is a nice method to remove the speckle noise, but the algorithm' computational comple...
详细信息
In Ultrasound imaging, speckle noise is the most serious problem which affects the performance of images. Non-local mean filter is a nice method to remove the speckle noise, but the algorithm' computational complexity makes it's a highly time-consuming method. In many applications like image-guided surgical intervention, real-time de-noising is required. This paper implements a NLM method accelerated by GPU for real-time denoising of 3D ultrasound images. The experimental results show the proposed accelerated de-noising method is efficient in terms of denoising quality and real-time.
Aiming at the traditional grasping method for manipulators based on 2D camera, when faced with the scene of gathering or covering, it can hardly perform well in unstructured scenes that appear as gathering and coverin...
详细信息
The cross-task gap presents a significant challenge for multimodal models because of the differences in input-output workflows. For instance, multimodal pre-trained transformers may encounter uni-modal data during tes...
详细信息
ISBN:
(数字)9798350359312
ISBN:
(纸本)9798350359329
The cross-task gap presents a significant challenge for multimodal models because of the differences in input-output workflows. For instance, multimodal pre-trained transformers may encounter uni-modal data during testing. To mitigate the gap, this paper introduces a Transformer in Multimodal Sentiment Analysis under Missing Modalities (TMMM) aims to perform well using missing-modal data during testing. TMMM uses a missing multimodal training approach to prevent accuracy degradation in testing. At the same time, a new network architecture allows the model to reconstruct missing modalities during testing. Classification token fusion and Mixture-of-Experts structures further enhance the model’s performance. A pre-training method utilizing contrastive learning, which can construct negative samples with positive samples, is proposed to overcome insufficient labeled data. Our experiments demonstrated the effectiveness of TMMM on two datasets with no modalities missing, i.e., it consistently achieved the highest classification accuracy and Macro-F1, which outperformed the best state-of-the-art baseline on each dataset by about 2% and 2.5%. Additionally, TMMM usually performs better than other baselines on datasets with missing modalities during testing.
This paper studies the secondary frequency control among non-synchronous AC areas interconnected by High Voltage Direct Current (HVDC). A distributed second order sliding mode control scheme is adopted to secondary fr...
详细信息
ISBN:
(数字)9781728176871
ISBN:
(纸本)9781728176888
This paper studies the secondary frequency control among non-synchronous AC areas interconnected by High Voltage Direct Current (HVDC). A distributed second order sliding mode control scheme is adopted to secondary frequency control of HVDC transmission systems to adjust the frequency of power grid to rated value, which solves the frequency disturbance caused by load power change of the DC power grid. And on this basis, the power generation in each region is reasonably distributed, so as to minimize the cost of power generation. Finally, the stability of the system is proved on an appropriate sliding manifold.
—In many real-world machine learning applications, unlabeled samples are easy to obtain, but it is expensive and/or time-consuming to label them. Active learning is a common approach for reducing this data labeling e...
详细信息
The paper proposes an improved approach to state estimation for nonlinear discrete-time systems based on zonotopes. To overcome the inherent defect of Taylors formula, a lower-order multi-dimensional extension of Stir...
详细信息
The paper proposes an improved approach to state estimation for nonlinear discrete-time systems based on zonotopes. To overcome the inherent defect of Taylors formula, a lower-order multi-dimensional extension of Stirling's interpolation formula is used to realize the linearization of nonlinear models. A nonlinear programming method is used to optimize the guaranteed margin of linearization error to obtain a more compact bound estimation, thereby reducing the conservativeness of the algorithm. Simulation results have shown the effectiveness and improved performance of the proposed algorithm.
In this paper, an automatic reading system for analog instruments has been designed for monitoring in power plants. In a general automatic reading system, there are many limitations to the reading correctness and syst...
详细信息
In this paper, an automatic reading system for analog instruments has been designed for monitoring in power plants. In a general automatic reading system, there are many limitations to the reading correctness and system robustness such as the high cost for the reason that there is only one instrument could be monitored by a single system, the strict restrict of the camera angle, and being not suitable for instruments with dense scales and so on. We present some solutions to overcome these limitations. Firstly, we combine a mobile inspection robot with an image capture device and the imageprocessing method to cut the cost of the monitoring of analog instruments in power plants. Then, we use Hough transform and perspective transform to correct the geometric distortion of images caused by camera angle. Eventually, we get the result of dense scaled instruments based on polar transform. Experiments show that our system performs quite well, and the reading error is less than the results which obtained from the general automatic reading system.
Learning-based multi-view stereo (MVS) method heavily relies on feature matching, which requires distinctive and descriptive representations. An effective solution is to apply non-local feature aggregation, e.g., Tran...
Learning-based multi-view stereo (MVS) method heavily relies on feature matching, which requires distinctive and descriptive representations. An effective solution is to apply non-local feature aggregation, e.g., Transformer. Albeit useful, these techniques introduce heavy computation overheads for MVS. Each pixel densely attends to the whole image. In contrast, we propose to constrain nonlocal feature augmentation within a pair of lines: each point only attends the corresponding pair of epipolar lines. Our idea takes inspiration from the classic epipolar geometry, which shows that one point with different depth hypotheses will be projected to the epipolar line on the other view. This constraint reduces the 2D search space into the epipolar line in stereo matching. Similarly, this suggests that the matching of MVS is to distinguish a series of points lying on the same line. Inspired by this point-toline search, we devise a line-to-point non-local augmentation strategy. We first devise an optimized searching algorithm to split the 2D feature maps into epipolar line pairs. Then, an Epipolar Transformer (ET) performs non-local feature augmentation among epipolar line pairs. We incorporate the ET into a learning-based MVS baseline, named ET-MVSNet. ET-MVSNet achieves state-of-the-art reconstruction performance on both the DTU and Tanks-and-Temples benchmark with high efficiency. Code is available at https://***/TQTQliu/ET-MVSNet.
The traditional Pavlov associative memory circuit realizes the law of learning and forgetting in classical conditioned reflex. In addition, the law of generalization and differentiation also belongs to classical condi...
详细信息
The traditional Pavlov associative memory circuit realizes the law of learning and forgetting in classical conditioned reflex. In addition, the law of generalization and differentiation also belongs to classical conditioned reflex, so the process of associative memory can be more effectively simulated by adding generalization and differentiation theory on the basis of traditional associative memory. In this paper, a memristor-based circuit is designed to implement generalization and differentiation based on Pavlov associative memory. The circuit can be applied to simple classification recognition. Based on the features of objects as input, the output of the circuit is used as the classification result to achieve the function of classification and recognition. Finally,the accuracy of classification recognition on the generalization and differentiation circuit proposed in this paper can be verified by the simulation results in PSPICE.
暂无评论