Zobrazeno 1 - 10
of 860
pro vyhledávání: '"Xu Hongli"'
Publikováno v:
Foundations of Computing and Decision Sciences, Vol 49, Iss 1, Pp 95-118 (2024)
Automatic crack detection in construction facilities is a challenging yet crucial task. However, existing deep learning (DL)-based semantic segmentation methods for this field are based on fully supervised learning models and pixel-level manual annot
Externí odkaz:
https://doaj.org/article/62317abc42c14c2caa3cf16131515499
In 5G smart cities, edge computing is employed to provide nearby computing services for end devices, and the large-scale models (e.g., GPT and LLaMA) can be deployed at the network edge to boost the service quality. However, due to the constraints of
Externí odkaz:
http://arxiv.org/abs/2412.08284
Edge inference is a technology that enables real-time data processing and analysis on clients near the data source. To ensure compliance with the Service-Level Objectives (SLOs), such as a 30% latency reduction target, caching is usually adopted to r
Externí odkaz:
http://arxiv.org/abs/2412.10382
Large language models (LLMs) typically employ greedy decoding or low-temperature sampling for reasoning tasks, reflecting a perceived trade-off between diversity and accuracy. We challenge this convention by introducing top-$n\sigma$, a novel samplin
Externí odkaz:
http://arxiv.org/abs/2411.07641
Mobile devices contribute more than half of the world's web traffic, providing massive and diverse data for powering various federated learning (FL) applications. In order to avoid the communication bottleneck on the parameter server (PS) and acceler
Externí odkaz:
http://arxiv.org/abs/2410.01256
Autor:
Bai, Kaixin, Zeng, Huajian, Zhang, Lei, Liu, Yiwen, Xu, Hongli, Chen, Zhaopeng, Zhang, Jianwei
Transparent object depth perception poses a challenge in everyday life and logistics, primarily due to the inability of standard 3D sensors to accurately capture depth on transparent or reflective surfaces. This limitation significantly affects depth
Externí odkaz:
http://arxiv.org/abs/2409.08926
Publikováno v:
Zhongliu Fangzhi Yanjiu, Vol 45, Iss 9, Pp 672-675 (2018)
Objective To examine clinicopathologic characteristics and survival differences of colon cancer patients by different primary locations. Methods We retrospectively analyzed the medical records of 1088 colon cancer patients. Kaplan-Meier curves were g
Externí odkaz:
https://doaj.org/article/04efb783741f4f658e0b2dd5de122c4a
Autor:
XU Hongli, WEI Shaozhong
Publikováno v:
Zhongliu Fangzhi Yanjiu, Vol 45, Iss 7, Pp 437-440 (2018)
Multidisciplinary treatment(MDT) is a new treatment pattern of oncology medicine. It is an inevitable result for the development of multidisciplinary medicine and a demand of cancer patients for high-quality treatment. Specialist clinical diagnosis a
Externí odkaz:
https://doaj.org/article/fb292e64e06646d2b9f866539fb9d7ca
Federated Learning (FL) enables distributed clients to collaboratively train models without exposing their private data. However, it is difficult to implement efficient FL due to limited resources. Most existing works compress the transmitted gradien
Externí odkaz:
http://arxiv.org/abs/2312.01617
Recently, federated learning (FL) has emerged as a popular technique for edge AI to mine valuable knowledge in edge computing (EC) systems. To mitigate the computing/communication burden on resource-constrained workers and protect model privacy, spli
Externí odkaz:
http://arxiv.org/abs/2311.13348