Recent advances in event camera research emphasize processing data in its original sparse form, which allows the use of its unique features such as high temporal resolution, high dynamic range, low latency, and resist...
Recent advances in event camera research emphasize processing data in its original sparse form, which allows the use of its unique features such as high temporal resolution, high dynamic range, low latency, and resistance to image blur. One promising approach for analyzing event data is through graph convolutional networks (GCNs). However, current research in this domain primarily focuses on optimizing computational costs, neglecting the associated memory costs. In this paper, we consider both factors together in order to achieve satisfying results and relatively low model complexity. For this purpose, we performed a comparative analysis of different graph convolution operations, considering factors such as execution time, the number of trainable model parameters, data format requirements, and training outcomes. Our results show a 450-fold reduction in the number of parameters for the feature extraction module and a 4.5-fold reduction in the size of the data representation while maintaining a classification accuracy of 52.3%, which is 6.3% higher compared to the operation used in state-of-the-art approaches. To further evaluate performance, we implemented the object detection architecture and evaluated its performance on the N-Caltech101 dataset. The results showed an accuracy of 53.7% mAP@0.5 and reached an execution rate of 82 graphs per second.
This paper investigates the simultaneous design of a controller and Luenberger state observer for systems with time-delays, external disturbances, uncertainties, modeling errors, and unknown nonlinear perturbations. T...
详细信息
Information, such as reliable demand and generation forecasts is crucial for appropriate energy management in microgrids. However, the most valuable data is the aggregate energy flow in the managed network, rather tha...
详细信息
This paper examines the local exponential stability (LES) of trajectories for nonlinear systems on Riemannian manifolds. We present necessary and sufficient conditions for LES of a trajectory on a Riemannian manifold ...
详细信息
The emergence of new areas of human-robot cooperation creates the need to ensure human safety in this regard. Therefore, there is a need to develop new sensors to detect the presence of a human in the vicinity of a ro...
详细信息
Delayless control design for time delay systems is an attractive direction for networked control systems as well as other cyber physical applications. In the present paper, the problem of Exact Model Matching with sim...
Delayless control design for time delay systems is an attractive direction for networked control systems as well as other cyber physical applications. In the present paper, the problem of Exact Model Matching with simultaneous Disturbance Rejection (EMMDR) is studied for the case of left-invertible general neutral multi delay systems with measurable and non-measurable disturbances, via two types of delayless controllers. The first type of controllers is a dynamic delayless controller feeding back the measurement outputs, the measurable disturbances and the external commands. The number of the external commands is equal to the number of the control inputs. The second type of controllers is the static delayless version of the first type. For both types of controllers, the necessary and sufficient conditions for the solvability of the problem are established, and the general solutions of the controller matrices are derived. The results are illustrated through a numerical example.
In paper, forecasting models using Prophet algorithm for occupational diseases incidence rate for Polish coal mining are presented. Prior to this, data is analyzed and approach for building forecasting models in Proph...
In paper, forecasting models using Prophet algorithm for occupational diseases incidence rate for Polish coal mining are presented. Prior to this, data is analyzed and approach for building forecasting models in Prophet is described in details. Forecasting models for occupational diseases incidence rate are revealed, respectively for all sectors in Poland, mining industry and finally for coal mining including only pneumoconiosis. Improved forecast accuracy with presented models might provide coal mine enterprises more precise data, supporting safety management in those organizations.
We establish a layer-wise parameterization for 1D convolutional neural networks (CNNs) with built-in end-to-end robustness guarantees. In doing so, we use the Lipschitz constant of the input-output mapping characteriz...
详细信息
Deep reinforcement learning (DRL) is currently the most popular AI-based approach to autonomous vehicle control. An agent, trained for this purpose in simulation, can interact with the real environment with a human-le...
详细信息
暂无评论