Pedestrian trajectory prediction is critical for autonomous driving, crowd analysis, and urban surveillance. To address insufficient interaction modeling in existing methods, we propose two enhancements. First, a fiel...
详细信息
ISBN:
(数字)9798331533113
ISBN:
(纸本)9798331533120
Pedestrian trajectory prediction is critical for autonomous driving, crowd analysis, and urban surveillance. To address insufficient interaction modeling in existing methods, we propose two enhancements. First, a field-of-view(FoV)-aware masking mechanism filters irrelevant interactions by dynamically adjusting to pedestrian distances and motion directions. Second, we introduce a more detailed modeling of the influence among pedestrians, replacing the traditional modeling based on reciprocal of distance. This model, integrated with FoV masks to construct sparse adjacency matrices for graph convolution. A temporal convolutional network then predicts trajectories as bivariate Gaussian distributions. Evaluations on ETH and UCY benchmarks demonstrate the effectiveness of our method.
This paper considers the modulation classification of radio frequency (RF) signals. An external attention mechanism-based convolution neural network (EACNN) is proposed. Thanks to the external attention layers, the EA...
详细信息
In order to solve the problem of rapid switching of space equipment in the cultural complex, this paper combines Moth-Flame optimization Algorithm (MFO) and Dynamic Window Approach (DWA) to realize the hybrid path pla...
详细信息
To meet the specific demands of airborne radar and communication systems, this study introduces an integrated radar-communication waveform design based on selecting the optimal dual sequence of complementary P4-OFDM s...
详细信息
The formation control of multi-agent system has become a hotspot in recent years. One of the most commonly used methods is to use artificial potential field(APF) to generate the attractive and repulsive force to organ...
The formation control of multi-agent system has become a hotspot in recent years. One of the most commonly used methods is to use artificial potential field(APF) to generate the attractive and repulsive force to organize the agents into a low-energy and stable formation. In this paper, we regard the APF as the difference in the desired position, and introduce the derivative of the gradient of the APF with respect to time, which is simplified as the Hessian matrix of the APF, into the formation control from the perspective of trajectory tracking. The energy-based Lyapunov function is selected to prove the stability and collision avoidance ability of the proposed control law. Moreover, we show that the maneuverability of the multi-agent system is enormously improved with the additional Hessian matrix term.
With the increasing demand for stage performance activities, the quality and safety of performance equipment, especially for the temporarily constructed stage, have become important topics that cannot be ignored. In o...
With the increasing demand for stage performance activities, the quality and safety of performance equipment, especially for the temporarily constructed stage, have become important topics that cannot be ignored. In order to enhance the safety of performance equipment and improve the service quality, this article mainly conducts risk analysis and safety assessment on the lighting and sound equipment for stage of temporary perform site without protective measures, and uses Analytic Hierarchy Process (AHP) with Fuzzy Comprehensive Evaluation (FCE) to conduct risk analysis and evaluation. The calculated risk level of stage lighting and sound equipment is given, and relevant safety measures are proposed to reduce the potential risks.
The injection of false data attack (FDIA) poses a serious threat to smart grids, and accurate detection of FDIAs is crucial for the secure and stable operation of the grid. A promising approach for FDIA detection base...
详细信息
In cognitive radio, spectrum sensing is used to determine whether the primary user is using the spectrum based on the signal received on a specific frequency band, thereby determining whether the secondary user can us...
详细信息
The safety assessment of stage performing arts equipment for the temporary site is an urgent task to be solved. In this paper, the lifting equipment is chosen for risk analysis, safety circuit identification and safet...
The safety assessment of stage performing arts equipment for the temporary site is an urgent task to be solved. In this paper, the lifting equipment is chosen for risk analysis, safety circuit identification and safety integrity level (SIL) calculation. The Hazard and Operability Study(HAZOP) and Layer Of Protection Analysis(LOPA)-based method is studied to get the expected SIL level of the related safety loops. In addition, the fault tree and Markov model methods are used to verify the actual SIL level under the existing loop structure respectively. This study provides the theory and data basis for the development of safety requirements and evaluation standards for the temporary theater of stage machinery, which has certain theoretical significance and application value.
Oral history involves conveying experienced events through spoken narratives, typically preserved and later studied by converting spoken language into text. Named entity recognition (NER) is the recognition of meaning...
详细信息
ISBN:
(数字)9798350380347
ISBN:
(纸本)9798350380354
Oral history involves conveying experienced events through spoken narratives, typically preserved and later studied by converting spoken language into text. Named entity recognition (NER) is the recognition of meaningful named entities in text, such as person names, locations, organizations, etc. Conducting NER research on oral history text is significant as it not only facilitates the verification of named entities by researchers but also allows for the extraction of key information from texts through named entities. By collecting oral history corpus, we establish an oral history text dataset, manually annotating all texts with six entity labels and repeatedly verifying them manually. Utilizing the concept of machine reading comprehension (MRC), a semantic fusion module was added, integrating label information into text information using a cross-attention mechanism, and decoding the corresponding entity labels through span decoding. The final model performs well on the oral history text dataset and also showed good performance on general Chinese datasets.
暂无评论