Type recovery in stripped binaries is a critical and challenging task in reverse engineering, as it is the basis for many security applications (e.g., vulnerability detection). Traditional analysis methods are limited by software complexity and emerging ...

Pixel-level dense labeling is both resource-intensive and time-consuming, whereas weak labels such as scribble present a more feasible alternative to full annotations. However, training segmentation networks with weak supervision from scribbles ...

Frailty evaluation is of great significance for the specific population, which can speed up the treatment process and reduce the adverse effects after treatment. In this article, in order to make up for the shortcomings of the traditional ...

• A novel and comprehensive evaluation method for frailty is proposed.
• A recurrent stepping semi-supervised learning framework is proposed.
• A subspace transfer learning integrating with heterogeneous features algorithm.

Evacuation path planning is a critical task to enable the safety of individuals in a fire hazard. Current evacuation planning approaches mainly calculate a fixed optimal path given a deterministic task. Nevertheless, fire evacuation guidance ...

Runoff generation in humid and semi-arid regions are usually dominated by saturation-excess mechanism and infiltration-excess mechanism, respectively. However, both mechanisms can co-exist in semi-humid regions. Therefore, we proposed a unified ...

• A unified runoff generation scheme was proposed to represent mixed rainfall-runoff process especially in semi-humid areas.
• GXAJ-IE model is also adaptable to humid and semi-arid areas usually dominated by single runoff generation ...

Saturation-excess and infiltration-excess runoff generation mechanisms are known as the main runoff generation mechanisms respectively in humid watershed and semi-arid watershed. However, they could coexist in some semi-humid regions. Conceptual models ...

Transformer, which is notable for its ability of global context modeling, has been used to remedy the shortcomings of Convolutional neural networks (CNN) and break its dominance in medical image segmentation. However, ...

• We design a memory- and computation-efficient self-attention module through which our Transformer branch can directly inference on relatively high-resolution feature maps, maintaining a grasp of fine spatial details and enabling a more ...

Vertical Federated Learning (VFL) has garnered significant attention due to its applicability in multi-party collaborative learning and the increasing demand for privacy-preserving measures. Most existing VFL algorithms primarily focus on accuracy as the ...

We present a simple yet efficient two-stage extended Kaczmarz-type algorithm for solving large least squares problem. During each stage, the current iterate is projected onto a surrogate hyperplane instead of a single one, yielding remarkable ...

Deep learning recommendation models (DLRM) rely on large embedding tables to manage categorical sparse features. Expanding such embedding tables can significantly enhance model performance, but at the cost of increased GPU/CPU/memory usage. Meanwhile, ...

In the business scenarios at Ant Group, there is a rising demand for collaborative data analysis among multiple institutions, which can promote health insurance, financial services, risk control, and others. However, the increasing concern about privacy ...

Attaining consensus tracking within a given short time frame for uncertain heterogeneous systems in the framework of the fully actuated system approach is highly desirable and challenging. This study introduces a general practical prescribed-time ...

This paper explores how to optimize university textbook recommendation systems using clustering analysis methods based on the ISODATA algorithm. It first introduces the basic principles of the ISODATA algorithm and its application in data clustering. ...

Endoscopic ultrasonography (EUS) is commonly utilized in preoperative staging of esophageal cancer, however with additional pain and cost as well as adverse events. Meanwhile, the accuracy of EUS is highly depend on the training and practice of ...

Complex-valued neural networks (CVNNs) have become a powerful modelling tool for complex-valued data processing. Because most of the critical points of CVNNs are saddle points, the gradient-based learning algorithms for CVNNs enjoy more chances ...

Rumors circulating on social media platforms have consistently represented a substantial threat to societal security and stability. Both academia and the industry have dedicated heightened focus to addressing the issue of rumor detection. Recent ...

• BERTWeet and saliency learning for fine-grained modelling of rumour text.
• Using attention mechanisms to learn the temporal structure of rumours.
• As a complementary task to rumour detection, segmentation of users into different ...

Reclaimed water can alleviate water scarcity and is an inevitable choice to promote green development and ecological civilization. Its development has attracted much attention from national and international scholars. An in-depth understanding of the ...

Deep learning models have been applied in baby cry recognition to enhance the recognition accuracy. However, the current research still suffers from data imbalance problem, which leads to bias in model learning. Sparse Autoencoder Long Short-Term ...

Display Omitted

• A SLGAN model is proposed to solve data imbalance problem by generating new cry data.
• Deep features extracted using transfer learning models are fused using SAE model.
• Our proposed method outperforms existing studies in classifying ...

Large-scale deep neural networks (DNNs), such as large language models (LLMs), have revolutionized the artificial intelligence (AI) field and become increasingly popular. However, training or fine-tuning such models requires substantial computational ...

In order to reduce network energy consumption and prolong the network lifetime in wireless sensor networks, a data fusion algorithm named CFLDF is proposed. Firstly, upon completion of the arrangement of network nodes, network clustering is ...

Neoadjuvant chemotherapy (NACT) is one kind of treatment for advanced stage ovarian cancer patients. However, due to the nature of tumor heterogeneity, the clinical outcomes to NACT vary significantly among different subgroups. Partial ...

• Developed a novel clinical marker to identify ovarian cancer patients who will receive sub-optimal debulking surgery after NACT treatment.
• Extracted a large amount of radiomics features to uncover the prognostic information for patient ...