To meet the electricity, hydrogen, and freshwater demands of isolated island users, and coping with the intermittent and fluctuating nature of renewable energies, this paper proposes a hybrid system of combining a rev...
详细信息
To meet the electricity, hydrogen, and freshwater demands of isolated island users, and coping with the intermittent and fluctuating nature of renewable energies, this paper proposes a hybrid system of combining a reversible solid oxide cell (rSOC) with direct contact membrane distillation (DCMD). The rSOC technology is used to achieve energy time-shifting. The waste heat from the operation of rSOC is recovered through DCMD to improve the system's overall performance and produce freshwater. A high-fidelity model of the rSOC-DCMD hybrid system is established and validated. Based on this model, a comprehensive sensitivity analysis including single-parameter sensitivity analysis, Spearman correlation analysis, and multi-parameter sensitivity analysis was performed. The analysis results indicate that current density is the critical factor influencing system performance while fuel utilization and fuel mole fraction primarily affect operating costs. The air excess ratio is crucial for optimizing system efficiency and freshwater productivity by balancing parasitic power and waste heat, however, adjusting the feed flow rate can further improve performance by regulating the temperature of the seawater entering the DCMD. Additionally, spearman correlation analysis further quantifies the conflicting relationship between any two of the performance indicators in the electrolysis cell/fuel cell (EC/FC) mode. In both modes, minimizing operating costs shows a weak conflict with maximizing system efficiency (correlation coefficient < 0.1) but a strong conflict with maximizing freshwater yield (correlation coefficient > 0.3). Through multi-objective optimization and optimal point decision-making, the optimal solution for three performance indicators is identified at each power level, ensuring optimal hybrid system operation under any condition. As a result, within the full power range of the EC/FC mode, the hybrid system can achieve average system efficiencies of 82.2 %/76.6 %, avera
The conventional text-based person re-identification methods heavily rely on identity annotations. However, this labeling process is costly and time-consuming. In this paper, we consider a more practical setting calle...
详细信息
ISBN:
(纸本)9781665428132
The conventional text-based person re-identification methods heavily rely on identity annotations. However, this labeling process is costly and time-consuming. In this paper, we consider a more practical setting called weakly supervised text-based person re-identification, where only the text-image pairs are available without the requirement of annotating identities during the training phase. To this end, we propose a Cross-Modal Mutual Training (CMMT) framework. Specifically, to alleviate the intra-class variations, a clustering method is utilized to generate pseudo labels for both visual and textual instances. To further re-fine the clustering results, CMMT provides a Mutual Pseudo label Refinement module, which leverages the clustering results in one modality to refine that in the other modality constrained by the text-image pairwise relationship. Mean-while, CMMT introduces a Text-IoU Guided Cross-Modal Projection Matching loss to resolve the cross-modal matching ambiguity problem. A Text-IoU Guided Hard Sample Mining method is also proposed for learning discriminative textual-visual joint embeddings. We conduct extensive experiments to demonstrate the effectiveness of the proposed CMMT, and the results show that CMMT performs favorably against existing text-based person re-identification methods. Our code will be available at https://***/X-Brainlab/WS_Text-ReID.
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
Most recent approaches for online action detection tend to apply Recurrent Neural Network (RNN) to capture long-range temporal structure. However, RNN suffers from non-parallelism and gradient vanishing, hence it is h...
详细信息
ISBN:
(纸本)9781665428132
Most recent approaches for online action detection tend to apply Recurrent Neural Network (RNN) to capture long-range temporal structure. However, RNN suffers from non-parallelism and gradient vanishing, hence it is hard to be optimized. In this paper, we propose a new encoder-decoder framework based on Transformers, named OadTR, to tackle these problems. The encoder attached with a task token aims to capture the relationships and global inter-actions between historical observations. The decoder extracts auxiliary information by aggregating anticipated future clip representations. Therefore, OadTR can recognize current actions by encoding historical information and predicting future context simultaneously. We extensively evaluate the proposed OadTR on three challenging datasets: HDD, TVSeries, and THUMOS14. The experimental results show that OadTR achieves higher training and inference speeds than current RNN based approaches, and significantly outperforms the state-of-the-art methods in terms of both mAP and mcAP. Code is available at https://***/wangxiang1230/OadTR.
Temporal action localization aims to localize starting and ending time with action category. Limited by GPU memory, mainstream methods pre-extract features for each video. Therefore, feature quality determines the upp...
详细信息
Bootstrap aggregating (Bagging) and boosting are two popular ensemble learning approaches, which combine multiple base learners to generate a composite model for more accurate and more reliable performance. They have ...
详细信息
As a promising energy storage matter, two-dimensional (2D) layered double hydroxides (LDHs) suffer from a lower specific capacitance and poor retention. Morphology engineering is deemed to be an effective means. Herei...
详细信息
This paper studies the consensus in fractional-order multiagent systems over directed graph via sampled-data control method. A distributed control protocol using the sampled position and velocity data is designed. By ...
详细信息
This paper studies the consensus in fractional-order multiagent systems over directed graph via sampled-data control method. A distributed control protocol using the sampled position and velocity data is designed. By virtue of the Mittag-Leffler function, Laplace transform, and matrix theory, some necessary and sufficient conditions associated with the sampling period, the fractional order, the coupling strengths, and the network structure to obtain consensus of the systems are obtained. Then, some detailed discussions are presented about how to select the sampling period and how to design the coupling strengths to attain the consensus of the systems, respectively. Lastly, some numerical simulation results are illustrated to reflect the availability of the theoretical analysis.
Emotion recognition, which aims to identify an individual’s emotional state from the acquired physiological or body signals, is very important in affective computing. Emotions have two common representations: categor...
详细信息
ISBN:
(纸本)9781665442084
Emotion recognition, which aims to identify an individual’s emotional state from the acquired physiological or body signals, is very important in affective computing. Emotions have two common representations: categorical, e.g., happy, sad, etc., and dimensional (continuous), e.g., valence, arousal and dominance. Training a good emotion classification or regression model usually requires a large number of labeled data. However, the labeling process is very difficult. As emotions are subtle and uncertain, it usually requires multiple assessors to label each emotional instance to obtain the groundtruth categorical label or dimensional values. In this paper, we propose a multi-task active learning (MTAL) framework to query the most useful samples for labeling, which enables the efficient training of an emotion classification model and multiple emotion regression models simultaneously. This is novel and challenging, as all previous research considered only emotion classification or regression alone, but not simultaneously. Experimental results on the IEMOCAP dataset demonstrated that MTAL outperformed random selection and several state-of-the-art single task active learning approaches, i.e., with the same number of labeled samples, MTAL can obtain better emotion classification and regression models simultaneously.
This technical report presents our solution for temporal action detection task in AcitivityNet Challenge 2021. The purpose of this task is to locate and identify actions of interest in long untrimmed videos. The cruci...
详细信息
暂无评论