Detection of unsafe workplace behaviors: Sec-YOLO model with FEHA attention [0.03%]
基于FEHA注意力的Sec-YOLO模型的不安全工作行为检测方法研究
Yang Liu,Shuaixian Liu,Jie Gao et al.
Yang Liu et al.
Detecting unsafe human behaviors is crucial for enhancing safety in industrial production environments. Current models face limitations in multi-scale target detection within such settings. This study introduces a novel model, Sec-YOLO, whi...
An enhanced approach for automatic annotation of error codes based on Seq2edit [0.03%]
一种基于Seq2edit的自动注释错误代码的方法
Jian Wang,Tao Lin,Rongsen Zhao et al.
Jian Wang et al.
The deep natural language translation models have been used for automatic code error correction and have demonstrated outstanding potential. However, a large and accurately annotated training dataset is essential for these models to perform...
DA-FIS: A high-speed dynamic adaptive fault injection server framework for reliable FPGA-based embedded systems [0.03%]
基于FPGA的嵌入式系统可靠性的高速动态自适应故障注入服务器框架研究
Fatimah Alhayan,Gaganjot Kaur,Sultan Alanazi et al.
Fatimah Alhayan et al.
Fault injection is a critical technique for assessing the reliability of field programmable gate array (FPGA)-based embedded systems, particularly in radiation-prone and safety-critical applications. Conventional fault injection methods, su...
A novel deep learning approach for predicting stone-free rates post-ESWL on uncontrasted CT [0.03%]
一种新的深度学习方法：基于非造影CT预测体外冲击波碎石后无石率
Ozgur Efiloglu,Muhammed Yildirim,Kadir Yildirim et al.
Ozgur Efiloglu et al.
Extracorporeal shock wave lithotripsy (ESWL) is one of the most often employed therapy methods for managing kidney stones. In our work, we sought to assess the efficacy of the artificial intelligence model developed using non-contrast compu...
Intelligent educational systems based on adaptive learning algorithms and multimodal behavior modeling [0.03%]
基于自适应学习算法和多模态行为建模的智能教育系统
Yuwei Li,Botao Lu
Yuwei Li
With the rapid advancement of artificial intelligence, the demand for personalized and adaptive learning has driven the development of intelligent educational systems. This article proposes a novel adaptive learning-driven architecture that...
Dynamic token encryption for preventing permission leakage in serverless architectures [0.03%]
用于防止无服务器架构中权限泄漏的动态令牌加密技术研究
Yu Liu,Fu Li,Chenhao Sun
Yu Liu
Serverless architecture simplifies application development and operation, but its permission control model based on static execution roles struggles to adapt to highly dynamic runtime environments, which can easily lead to the risk of permi...
EquiRate: balanced rating injection approach for popularity bias mitigation in recommender systems [0.03%]
等效率：推荐系统中的流行度偏差缓解方法
Mert Gulsoy,Emre Yalcin,Alper Bilge
Mert Gulsoy
Recommender systems often suffer from popularity bias problem, favoring popular items and overshadowing less known or niche content, which limits recommendation diversity and content exposure. The root reason for this issue is the imbalance...
An enhanced BERT model with improved local feature extraction and long-range dependency capture in promoter prediction for hearing loss [0.03%]
一种改进的BERT模型在听力损失启动子预测中的局部特征提取和长程依赖捕捉能力增强研究
Jing Sun,Yangfan Huang,Jiale Fu et al.
Jing Sun et al.
Promoter prediction has a key role in helping to understand gene regulation and in developing gene therapies for complex diseases such as hearing loss (HL). While traditional Bidirectional Encoder Representations from Transformers (BERT) mo...
MDMU-Net: 3D multi-dimensional decoupled multi-scale U-Net for pancreatic cancer segmentation [0.03%]
基于3D多维解耦多尺度U形网络的胰腺癌分割方法
Lian Lu,Miao Wu,Gan Sen et al.
Lian Lu et al.
Pancreatic cancer, as a highly lethal malignant tumor, presents significant challenges for early diagnosis and treatment. Accurate segmentation of the pancreas and tumors is crucial for surgical planning and treatment strategy development. ...
HTCNN-Attn: a fine-grained hierarchical multi-label deep learning model for disaster emergency information intelligent extraction from social media [0.03%]
HTCNN-Attn：一种细粒度层次化多标签深度学习模型用于灾害应急信息的智能抽取
Shanshan Li,Qingjie Liu,Xiaoling Sun
Shanshan Li
To address the challenge of extracting fine-grained emergency information from noisy social media during disasters, we propose HTCNN-Attn, a hierarchical multi-label deep learning model. It integrates a three-level tree-structured labeling ...