liangyimingcom / Use-SageMaker_XGBoost-convert-Time-Series-into-Supervised-Learning-for-predictive-maintenance
使用SageMaker+XGBoost,将时间序列转换为监督学习,完成预测性维护的实践
☆70Updated 3 years ago
Related projects: ⓘ
- 这个开源项目主要是对经典的时间序列预测算法论文进行复现,模型主要参考自GluonTS,框架主要参考自Informer☆121Updated 3 years ago
- 基于keras实现的transformer☆97Updated 3 years ago
- Attention Feature Fusion base on spatial-temporal Graph Convolutional Network(AFFGCN)☆34Updated 8 months ago
- An official implementation of "WFTNet: Exploiting Global and Local Periodicity in Long-term Time Series Forecasting" (ICASSP 2024)☆19Updated 6 months ago
- An official implementation of "Periodicity Decoupling Framework for Long-term Series Forecasting" (ICLR 2024)☆95Updated 3 months ago
- 基于国内大学构造的neo4j知识图谱,并进行简单问答,帮助了解大学,填报高考志愿☆57Updated 2 years ago
- Sequential data using RNN (LSTM, GRU, etc) CNN and RCNN. Adaptable to variable length input sequence.☆66Updated last year
- This is an official Pytorch implementation of Conditional Local Convolution for Spatio-temporal Meteorological Forecasting, AAAI 2022☆128Updated 2 years ago
- provide a new methods for the Chinese stock comment sentiment analysis☆30Updated last year
- Predict stock prices using Long Short-Term Memory (LSTM) networks.☆66Updated 11 months ago
- Human Activity Recognition by Sensor on Smartphone☆52Updated 4 years ago
- This resp presents a probabilistic and online forecasting model. In detail, a deep kernel is proposed by integrating the deep soft Spiki…☆32Updated last week
- Paper A 3D-Temporal Convolutional Transformer Network for Spatiotemporal Predictive Learning☆100Updated 2 years ago
- ☆73Updated this week
- Optimisation of wastewater treatment strategies based on mixed integer linear programming☆11Updated 4 years ago
- 基于ARIMA时间序列的销量预测模型,实际预测准确率达90%以上,内含有测试记录和实际上线效果。☆94Updated 5 years ago
- This data set contains flow-based network security data sets extracted from satellite networks and terrestrial networks. We named the dat…☆24Updated 3 years ago
- [PVLDB 2024 Best Paper Nomination] TFB: Towards Comprehensive and Fair Benchmarking of Time Series Forecasting Methods☆274Updated 2 weeks ago
- 使用支持向量机、弹性网络、随机森林、LSTM、SARIMA等多种算法进行时间序列的回归预测,除此以外还采取了多种组合方法对以上算法输出的结果进行组合预测。Support vector machine, elastic network, random forest, LSTM…☆42Updated 4 years ago
- ☆24Updated this week
- 个人仓库,存放玩具☆19Updated 2 years ago
- 多元多步时间序列的LSTM模型预测——基于Keras☆75Updated 2 years ago
- [CIKM 2021 Resource Paper] DL-Traff: Survey and Benchmark of Deep Learning Models for Urban Traffic Prediction (Graph Part)☆170Updated 2 years ago
- 预问诊定制AI,可以从电子病历学习临床经验,自动与患者对话诊断并解释病情,提高医患沟通书写病历的效率。微信小程序扫码即用。☆48Updated 3 years ago
- Code for TH-GNN (paper accepted by KDD2022)☆66Updated 5 months ago
- ☆34Updated 7 months ago
- A Large-scale Hierarchical Dynamic Financial Knowledge Base☆55Updated 2 months ago
- SFMGTL for corss-city knowledge transfer☆20Updated 5 months ago
- ☆38Updated 3 years ago