Query：
学者姓名：林甲祥
Refining：
Year
Type
Indexed by
Source
Complex
Co-Author
Language
Clean All
Abstract ：
Recent studies report that gradient guidance extracted from a single-reference model can improve Limited-Sample regression. However, one reference model may not capture all relevant characteristics of the target function, which can restrict the capacity of the learner. To address this issue, we introduce the Multi-Gradient Guided Network (MGGN), an extension of single-gradient guidance that combines gradients from several reference models. The gradients are merged through an adaptive weighting scheme, and an orthogonal-projection step is applied to reduce potential conflicts between them. Experiments on sine regression are used to evaluate the method. The results indicate that MGGN achieves higher predictive accuracy and improved stability than existing single-gradient guidance and meta-learning baselines, benefiting from the complementary information provided by multiple reference models. © 2025 by the authors.
Keyword ：
Regression analysis Regression analysis
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Lin, Yu , Lin, Jiaxiang , Zhang, Keju et al. Adaptive Multi-Gradient Guidance with Conflict Resolution for Limited-Sample Regression [J]. | Information (Switzerland) , 2025 , 16 (7) . |
| MLA | Lin, Yu et al. "Adaptive Multi-Gradient Guidance with Conflict Resolution for Limited-Sample Regression" . | Information (Switzerland) 16 . 7 (2025) . |
| APA | Lin, Yu , Lin, Jiaxiang , Zhang, Keju , Zheng, Qin , Lin, Liqiang , Chen, Qianqian . Adaptive Multi-Gradient Guidance with Conflict Resolution for Limited-Sample Regression . | Information (Switzerland) , 2025 , 16 (7) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The majority of existing clustering algorithms, including those algorithms that focus on boundary detection, seldom account for the reasonableness and genuineness of boundaries, consequently, it is difficult to obtain well-defined boundary in clustering-based regional division. A novel boundary search Clustering algorithm integrating Direction Centrality with the Distance of K-nearest-neighbor (DKCDC) is proposed, which is capable of achieving well-defined regional boundaries, to resolve the challenges mentioned above. Firstly, the preliminary boundary of clusters are established on the basis of boundary points and initial cluster labels obtained by the Clustering algorithm using the local Direction Centrality (CDC). Secondly, all the boundary points are further processed and discriminated, to detect noise points concealed within the boundaries, which provides the essential basis for achieving more genuine and reliable cluster boundaries and regional identification. In this process, a fusion strategy is adopted, to subdivide the boundary points into true boundaries and false boundaries by combining voting method and distance metric. Thirdly, a regional division result with well-defined boundary is obtained by DKCDC. In the end, by distinguishing genuine from false boundaries using fusion strategy, DKCDC enhances regional boundary demarcation. Experiments on synthetic and UCI datasets show DKCDC improves silhouette coefficient by at least s4.88% over CDC, K-Means, DBSCAN, OPTICS and HDBSCAN, indicating its broad potential for applications in clustering-based regional division.
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zheng, Qin , Zhang, Keju , Chen, Qianqian et al. DKCDC: A clustering algorithm focusing on genuine boundary search for regional division [J]. | PLOS ONE , 2025 , 20 (9) . |
| MLA | Zheng, Qin et al. "DKCDC: A clustering algorithm focusing on genuine boundary search for regional division" . | PLOS ONE 20 . 9 (2025) . |
| APA | Zheng, Qin , Zhang, Keju , Chen, Qianqian , Wu, Jianwei , Lin, Jiaxiang . DKCDC: A clustering algorithm focusing on genuine boundary search for regional division . | PLOS ONE , 2025 , 20 (9) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
现有降水监测自动气象观测站、天气雷达、卫星等技术的建设投入与空间分辨率差异较大且有限，导致区域降水预测精度和时效性的差异。本研究以大数据5G通信链路和降水数据为基础，采用相关性与回归分析法，探讨移动终端信号衰减特征与降水相关关系；在核心伪代码算法基础上，构建线性回归、决策树回归和随机森林回归降水模型，并对模型性能进行评估，以期提高降水预测准确性。结果表明：大数据5G通信链路的通信数据与降水数据存在弱相关性；线性回归、决策树回归和随机森林回归降水模型的纳什效率系数（NSE）分别为-0.115444、-1.065824和0.310811；福州城区2022年5-6月大数据5G通信链路通信与降水监测联合数据，随机森林回归模型的平均准确性最优，验证精度为95.86%，表明大数据5G通信链路的通信数据，随机森林回归降水预测模型可对降水进行高分辨率、高准确性预测。本研究结果为高时空分辨率气象预测提供了一种科学的可选方案。
Keyword ：
5G通信链路 5G通信链路 回归模型 回归模型 相关性 相关性 降水 降水 随机森林 随机森林
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 陈建云 , 杨家珠 , 林甲祥 et al. 基于大数据5G通信链路的福州地区高分辨率降水模型 [J]. | 中国农业气象 , 2025 , 46 (02) : 157-168 . |
| MLA | 陈建云 et al. "基于大数据5G通信链路的福州地区高分辨率降水模型" . | 中国农业气象 46 . 02 (2025) : 157-168 . |
| APA | 陈建云 , 杨家珠 , 林甲祥 , 吴启树 . 基于大数据5G通信链路的福州地区高分辨率降水模型 . | 中国农业气象 , 2025 , 46 (02) , 157-168 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Accurate identification of urban flood-prone zone is of critical importance for enhancing emergency response efficiency and optimizing the allocation of disaster relief resources, particularly in developing countries facing increasingly severe urban flood challenges. Despite the widespread application of clustering algorithms in regional identification, most existing methods generally ignore the rationality of the resulting region boundaries, making it difficult to meet the practical requirements of boundary accuracy in disaster management. Accordingly, this paper proposes a noise-insensitive clustering algorithm based on boundary processing called CDC+, which obtain regional boundary while effectively eliminating potential noise. Furthermore, to further improve the accuracy of region boundary delineation, a planar scanning constraint algorithm based on Delaunay Triangulation (referred to as DSC) is introduced, overcoming the limitation of conventional Delaunay Triangulation, which can only generate convex hull boundaries, thereby enhancing the scientificity of spatial representation. Finally, CDC+ and DSC are integrated to establish a regional identification framework, and applying to a flood-prone zone from Zhejiang Province. Experimental results demonstrate that the proposed method can effectively identify spatially clustered regions with rational boundaries, providing strong support for scientifically managing flood disasters and facilitating the precise allocation of emergency response resources.
Keyword ：
Clustering algorithm Clustering algorithm Delaunay triangulation Delaunay triangulation Disaster management Disaster management Flood-prone zone Flood-prone zone Regional boundary Regional boundary
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zheng, Qin , Lin, Jiaxiang , Zhang, Aiguo et al. A novel regional identification framework integrating clustering and delaunay for urban flood-prone zones [J]. | JOURNAL OF ENVIRONMENTAL MANAGEMENT , 2025 , 395 . |
| MLA | Zheng, Qin et al. "A novel regional identification framework integrating clustering and delaunay for urban flood-prone zones" . | JOURNAL OF ENVIRONMENTAL MANAGEMENT 395 (2025) . |
| APA | Zheng, Qin , Lin, Jiaxiang , Zhang, Aiguo , Lin, Lizheng , Zhang, Keju , Lin, Yu . A novel regional identification framework integrating clustering and delaunay for urban flood-prone zones . | JOURNAL OF ENVIRONMENTAL MANAGEMENT , 2025 , 395 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Fiber optic vibration identification has significant applications in engineering fields, like security surveillance and structural health assessment. However, present methods primarily depend on either temporal-frequency domain or image features simply, challenging the simultaneous consideration of both image attributes and the temporal dependencies of vibration signals. Consequently, the performance of fiber optic vibration recognition remains subject to improvement, and its effectiveness further diminishes under conditions of uneven data distribution. Therefore, this study integrates residual neural networks, long short-term memory networks, and diffusion denoising probabilistic models to propose a fiber optic vibration recognition method DR-LSTM, which incorporates both image and temporal features while ensuring high recognition accuracy across balanced and imbalanced data distributions. Firstly, features of the Mel spectrum image and temporal characteristics of fiber optic vibration events are extracted. Subsequently, specialized neural network models are developed for categories with scarce data to produce similar images for data augmentation. Finally, the retrieved composite characteristics are employed to train recognition models, thereby improving recognition accuracy. Experiments were performed on datasets from natural environment and anthropogenic vibration, including for both balanced and imbalanced data distributions. The results show that on the two balanced datasets, the proposed model achieves improvements in classification accuracy of at least 0.67% and 7.4% compared to conventional methods. In the two imbalanced datasets, the model's accuracy exceeds that of conventional models by a minimum of 18.79% and 2.4%. This validates the effectiveness and feasibility of DR-LSTM in enhancing recognition accuracy and addressing issues with imbalanced data distribution.
Keyword ：
DDPM DDPM feature fusion feature fusion fiber optic vibration fiber optic vibration long and short-term memory network long and short-term memory network residual network residual network
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zhang, Keju , Wang, Tingshuo , Wu, Jianwei et al. Multi-Feature Fusion for Fiber Optic Vibration Identification Based on Denoising Diffusion Probabilistic Models [J]. | SENSORS , 2025 , 25 (22) . |
| MLA | Zhang, Keju et al. "Multi-Feature Fusion for Fiber Optic Vibration Identification Based on Denoising Diffusion Probabilistic Models" . | SENSORS 25 . 22 (2025) . |
| APA | Zhang, Keju , Wang, Tingshuo , Wu, Jianwei , Zheng, Qin , Chen, Caiyi , Lin, Jiaxiang . Multi-Feature Fusion for Fiber Optic Vibration Identification Based on Denoising Diffusion Probabilistic Models . | SENSORS , 2025 , 25 (22) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
Rainfall intensity prediction based on commercial microwave link data has received significant attention in recent years due to the higher spatial resolution and lower energy consumption. However, the predictive performance is inferior to the model based on meteorological data by reason of the high noise in commercial microwave link data, further exacerbated by the imbalance in the number of samples across different rainfall intensities. Hence, a cost-sensitive rainfall intensity prediction model (CSRFP) is proposed to achieve better predictive performance in high-noise commercial microwave link data. First, the spatiotemporal scene information is encoded, and its weights are trained to provide the model with correlations between signal data from different stations, which helps the model to better capture potential patterns between the data and thus reduce the effect of noise. Next, the rainfall cross-entropy loss based on the rainfall distribution provides the model with the probability of different rainfall intensities occurring and back-calculates the signal attenuation at a specific rainfall intensity, assigning more reasonable weights to different samples considering signal attenuation, which makes the model cost-sensitive and can address the class imbalance problem. Extensive experiments are carried out on high-noise communication data and imbalanced rainfall data in Fuzhou. Compared to typical prediction methods such as RNN applied to rainfall and communication data, CSRFP improves Recall, Precision, AUCROC, AUCPR and F1 and Accuracy by approximately 19%, 37%, 8%, 22%, 30%, and 17%, respectively. Significantly, the model's prediction accuracy for heavy rain with the smallest number of samples improves by about 13%.
Keyword ：
class imbalance class imbalance commercial microwave links commercial microwave links cost sensitive cost sensitive time series prediction time series prediction
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Zheng, Liankai , Lin, Jiaxiang , Huang, Zhixin et al. Cost-Sensitive Rainfall Intensity Prediction with High-Noise Commercial Microwave Link Data [J]. | SUSTAINABILITY , 2024 , 16 (18) . |
| MLA | Zheng, Liankai et al. "Cost-Sensitive Rainfall Intensity Prediction with High-Noise Commercial Microwave Link Data" . | SUSTAINABILITY 16 . 18 (2024) . |
| APA | Zheng, Liankai , Lin, Jiaxiang , Huang, Zhixin , Lin, Yu , Zheng, Qin , Chen, Qianqian et al. Cost-Sensitive Rainfall Intensity Prediction with High-Noise Commercial Microwave Link Data . | SUSTAINABILITY , 2024 , 16 (18) . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
This paper addresses the problem of mapping, scheduling, and routing of virtual network functions (VNF) on a service function chain (SFC) that is sensitive to latency in a virtual network. A scheduling algorithm for VNF is proposed, which aims to minimize the SFC rejection rate while taking into account VNF mapping, scheduling, and traffic routing during the scheduling process. To achieve this goal, a Markov decision process (MDP)-based VNF scheduling model is established that guarantees SFC resource requirements are met. The model uses the D3QN (Dueling Double DQN) algorithm based on composite rules to select the SFC at each scheduling time point, and selects virtual nodes and routes using a routing optimization algorithm to minimize the SFC rejection rate. We compare our algorithm with the single rule, DQN and genetic algorithm, and the simulation results show that the proposed algorithm can reduce the rejection rate of SFC by approximately 8% compared to genetic algorithms.
Keyword ：
Deep reinforcement learning Deep reinforcement learning Delay-aware Delay-aware Service function chain Service function chain Virtual network functions Virtual network functions VNF scheduling VNF scheduling
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Liu, Zhiwei , Shu, Zhaogang , Chen, Shuwu et al. Low-latency Virtual Network function Scheduling Algorithm Based on Deep Reinforcement Learning [J]. | COMPUTER NETWORKS , 2024 , 246 . |
| MLA | Liu, Zhiwei et al. "Low-latency Virtual Network function Scheduling Algorithm Based on Deep Reinforcement Learning" . | COMPUTER NETWORKS 246 (2024) . |
| APA | Liu, Zhiwei , Shu, Zhaogang , Chen, Shuwu , Zhong, Yiwen , Lin, Jiaxiang . Low-latency Virtual Network function Scheduling Algorithm Based on Deep Reinforcement Learning . | COMPUTER NETWORKS , 2024 , 246 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
The introduction of Network Function Virtualization (NFV) and Software-Defined Network (SDN) architectures has significantly reduced the Operational Expenditure (OPEX) and Capital Expenditure (CAPEX) of network system. However, NFV orchestration management also brings about challenges. After the initial deployment of VNFs, due to the volatility of network requests, the original deployment may not be able to meet user resource demands. The key issue is how to readjust resources dynamically to accommodate more network requests without violating Quality of Service (QoS) for users. Several existing techniques can be used to achieve this goal, such as horizontal scaling, vertical scaling, and virtual network function (VNF) migration. However, these techniques inevitably incur some overhead, such as the cost of instantiating VNF and link rerouting. Additionally, resource adjustment may also result in unbalanced distribution of network resources. In this paper, an Intelligent Service Function Chain Dynamic Adjustment Algorithm (ISFCDAA) is proposed to address the above challenges. Firstly, an Integer Linear Programming (ILP) model is established with the objective of minimizing the long-term adjustment cost and reducing the imbalance of resource distribution. Then we transform the optimization process into a Markov Decision Process (MDP). Secondly, to solve the problems that the state and action space is too large and the state transition probability is uncertain in MDP, a SFC dynamic adjustment algorithm based on deep reinforcement learning is proposed. This algorithm can obtain an approximate optimal adjustment strategy for ILP model. The simulation results show that ISFCDAA can reduce the adjustment overhead and maintain a balanced distribution of network resources while ensuring the QoS. Compared with the existing algorithms, the average standard deviation of resource distribution of ISFCDAA is reduced by up to 9.90%, the average acceptance rate of ISFCDAA is improved by up to 39.57%, and the average long-term profit is improved by up to 42.92%. The incorporation of cost and demand-sensitive considerations into ISFCDAA enhances its responsiveness to fluctuating network demands, solidifying its effectiveness in dynamic resource management scenarios.
Keyword ：
Network function virtualization orchestrator Network function virtualization orchestrator Resource management Resource management Service function chain Service function chain
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | Wang, Yuantao , Shu, Zhaogang , Chen, Shuwu et al. A cost and demand sensitive adjustment algorithm for service function chain in data center network [J]. | COMPUTER NETWORKS , 2024 , 242 . |
| MLA | Wang, Yuantao et al. "A cost and demand sensitive adjustment algorithm for service function chain in data center network" . | COMPUTER NETWORKS 242 (2024) . |
| APA | Wang, Yuantao , Shu, Zhaogang , Chen, Shuwu , Lin, Jiaxiang , Zhang, Zhenchang . A cost and demand sensitive adjustment algorithm for service function chain in data center network . | COMPUTER NETWORKS , 2024 , 242 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
本发明涉及物联网技术领域，公开了一种基于AI和物联网的洗衣机管理系统、方法及介质，包括：物联网传感器模块，其用于采集洗衣机的运行信息；物联网图像采集模块，其用于采集衣物的图像信息和使用者的面部信息；物联网通讯模块，其用于将物联网传感器模块和物联网图像采集模块采集的信息发送到数据处理模块；数据处理模块包括：运行信息处理模块，其基于洗衣机的运行信息来处理获得运行特征数据；异常分析模块，其用于将洗衣机的运行信息和衣物的图像信息输入异常分析模型，输出洗衣机的故障类型；本发明能够通过衣物特征信息的识别来降低仅依靠洗衣机运行数据来判断故障类型的误差。
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 张振昌 , 林甲祥 , 李小林 et al. 一种基于AI和物联网的洗衣机管理系统、方法及介质 : CN202410677583.5[P]. | 2024-05-29 . |
| MLA | 张振昌 et al. "一种基于AI和物联网的洗衣机管理系统、方法及介质" : CN202410677583.5. | 2024-05-29 . |
| APA | 张振昌 , 林甲祥 , 李小林 , 陈宏方 , 林清波 , 方艳 et al. 一种基于AI和物联网的洗衣机管理系统、方法及介质 : CN202410677583.5. | 2024-05-29 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Abstract ：
本发明涉及了一种基于YOLOV7目标检测算法的实时违规旗帜检测方法，包括以下步骤：通过编写爬虫收集违规旗帜图片，确定违规旗帜检测的特征，利用图片标注工具对收集到的图片进行标注，制作违规旗帜数据集，同时，收集与违规旗帜具有相似特征的正常旗帜，制作混淆特征旗帜数据集；对模型算法进行优化，基于焦点和全局目标检测蒸馏，对YOLOV7目标检测算法进行改进，获得自适应孪生蒸馏YOLOV7‑tiny目标检测算法模型；区别于现有技术，本发明通过制作混淆特征旗帜数据集，提高违规旗帜识别能力，通过基于焦点和全局目标检测蒸馏，对YOLOV7目标检测算法进行改进，获得孪生蒸馏YOLOV7‑tiny目标检测算法模型，提高检测精度，可以达到实时检测。
Cite：
Copy from the list or Export to your reference management。
| GB/T 7714 | 张振昌 , 刘金强 , 薛弘晖 et al. 基于YOLOV7目标检测算法的实时违规旗帜检测方法 : CN202310327582.3[P]. | 2023-03-30 . |
| MLA | 张振昌 et al. "基于YOLOV7目标检测算法的实时违规旗帜检测方法" : CN202310327582.3. | 2023-03-30 . |
| APA | 张振昌 , 刘金强 , 薛弘晖 , 林甲祥 , 林清波 , 李小林 et al. 基于YOLOV7目标检测算法的实时违规旗帜检测方法 : CN202310327582.3. | 2023-03-30 . |
| Export to | NoteExpress RIS BibTex |
Version ：
Export
| Results： |
Selected to |
| Format： |
