Qing Dong

Isaac J. Cohen, David A. Wetz, Stepfanie Veiga et al.

There is need for an energy storage device capable of transferring high power in transient situations aboard naval vessels. Currently, batteries are used to accomplish this task, but previous research has shown that when utilized at high power rates, these devices deteriorate over time causing a loss in lifespan. It has been shown that a hybrid energy storage configuration is capable of meeting such a demand while reducing the strain placed on individual components. While designing a custom converter capable of controlling the power to and from a battery would be ideal for this application, it can be costly to develop when compared to purchasing commercially available products. Commercially available products offer limited controllability in exchange for their proven performance and lower cost point - often times only allowing a system level control input without any way to interface with low level controls that are frequently used in controller design. This paper proposes the use of fuzzy logic control in order to provide a system level control to the converters responsible for limiting power to and from the battery. A system will be described mathematically, modeled in MATLAB/Simulink, and a fuzzy logic controller will be compared with a typical controller.

Xinjie Liang, Xiangyu Li, Fanding Li et al.

Medical vision-language pretraining (VLP) that leverages naturally-paired medical image-report data is crucial for medical image analysis. However, existing methods struggle to accurately characterize associations between images and diseases, leading to inaccurate or incomplete diagnostic results. In this work, we propose MedFILIP, a fine-grained VLP model, introduces medical image-specific knowledge through contrastive learning, specifically: 1) An information extractor based on a large language model is proposed to decouple comprehensive disease details from reports, which excels in extracting disease deals through flexible prompt engineering, thereby effectively reducing text complexity while retaining rich information at a tiny cost. 2) A knowledge injector is proposed to construct relationships between categories and visual attributes, which help the model to make judgments based on image features, and fosters knowledge extrapolation to unfamiliar disease categories. 3) A semantic similarity matrix based on fine-grained annotations is proposed, providing smoother, information-richer labels, thus allowing fine-grained image-text alignment. 4) We validate MedFILIP on numerous datasets, e.g., RSNA-Pneumonia, NIH ChestX-ray14, VinBigData, and COVID-19. For single-label, multi-label, and fine-grained classification, our model achieves state-of-the-art performance, the classification accuracy has increased by a maximum of 6.69\%. The code is available in https://github.com/PerceptionComputingLab/MedFILIP.

Qing Dong, Pengyuan Liu, Dong Yu et al.

Generative agents have made significant progress in simulating human behavior, but existing frameworks often simplify emotional modeling and focus primarily on specific tasks, limiting the authenticity of the simulation. Our work proposes the Psychological-mechanism Agent (PSYA) framework, based on the Cognitive Triangle (Feeling-Thought-Action), designed to more accurately simulate human behavior. The PSYA consists of three core modules: the Feeling module (using a layer model of affect to simulate changes in short-term, medium-term, and long-term emotions), the Thought module (based on the Triple Network Model to support goal-directed and spontaneous thinking), and the Action module (optimizing agent behavior through the integration of emotions, needs and plans). To evaluate the framework's effectiveness, we conducted daily life simulations and extended the evaluation metrics to self-influence, one-influence, and group-influence, selection five classic psychological experiments for simulation. The results show that the PSYA framework generates more natural, consistent, diverse, and credible behaviors, successfully replicating human experimental outcomes. Our work provides a richer and more accurate emotional and cognitive modeling approach for generative agents and offers an alternative to human participants in psychological experiments.