Wearable flexible electronic devices have been developed rapidly driven by their distinctive characteristics, such as portability, flexibility, comfort, and diverse forms. However, the accelerated pace of technologica...
详细信息
As artificial intelligence methods are increasingly applied to complex task scenarios, high dimensional multi-label learning has emerged as a prominent research focus. At present, the curse of dimensionality remains o...
详细信息
Recent advancements in ophthalmology foundation models such as RetFound have demonstrated remarkable diagnostic capabilities but require massive datasets for effective pre-training, creating significant barriers for d...
详细信息
Accurate tumor segmentation is crucial for cancer diagnosis and treatment. While foundation models have advanced general-purpose segmentation, existing methods still struggle with: (1) limited incorporation of medical...
详细信息
Residual computation is an effective method for gray-scale image steganalysis. For binary images, the residual computation calculated by the XOR operation is also employed in the local residual patterns(LRP) model for...
详细信息
Residual computation is an effective method for gray-scale image steganalysis. For binary images, the residual computation calculated by the XOR operation is also employed in the local residual patterns(LRP) model for steganalysis. A binary image steganalytic scheme based on symmetrical local residual patterns(SLRP) is proposed. The symmetrical relationships among residual patterns are introduced that make the features more compact while reducing the dimensionality of the features set. Multi-scale windows are utilized to construct three SLRP submodels which are further merged to construct the final features set instead of a single *** with higher probability to be modified after embedding are emphasized and selected to construct the feature sets for training the support vector machine classifier. The experimental results show that the proposed steganalytic scheme is effective for detecting binary image steganography.
Super spreader detection in high-speed data streams is crucial for numerous applications. Although many methods have emerged, existing works can hardly concurrently achieve high memory efficiency, support online detec...
Super spreader detection in high-speed data streams is crucial for numerous applications. Although many methods have emerged, existing works can hardly concurrently achieve high memory efficiency, support online detection, enable merging data from different measurement points/periods, and offer invertibility. This makes them unable to satisfy flexible application requirements. This paper proposes RGS-Sketch, a novel sketch designed to address this problem. The core of RGS-Sketch lies in a new mergeable memory sharing design called register group sharing. This design organizes registers into groups as basic memory sharing units, accommodating the high skewness of real-world data streams and offering high memory efficiency. Besides, it enables online detection through the real-time acquisition of a group's state, which also facilitates invertibility. To enhance detection accuracy further, we propose a limited register update strategy. It blocks small flows from updating registers, thereby reducing memory overhead and estimation noises. Extensive experimental results based on four real-world datasets show that RGS-Sketch significantly outperforms the most accurate baselines in accuracy while maintaining a high throughput. Specifically, it improves the F1 scores by up to 0.643 for measurements at a single point/period and up to 0.472 across multiple points/periods.
Manganese-based aqueous zinc-ion batteries (AZIBs) have garnered growing interest in the area of adaptable and wearable devices because of their properties of simple manufacturing, superior safety, and ecological comp...
详细信息
Due to the domain shifts between training and testing medical images, learned segmentation models often experience significant performance degradation during deployment. In this paper, we first decompose an image into...
详细信息
Temporal processing is fundamental for both biological and artificial intelligence systems, as it enables the comprehension of dynamic environments and facilitates timely responses. Spiking Neural Networks (SNNs) exce...
详细信息
Neurologists often face challenges in identifying epileptic activities within multichannel EEG recordings, requiring extensive hours of analysis. Computer-aided diagnosis systems have been proposed to reduce manual in...
详细信息
暂无评论