检索结果-内蒙古大学图书馆

Research on Material Demand forecasting algorithm Based on Multi-Dimensional Feature Fusion

INTERNATIONAL JOURNAL OF INFORMATION SYSTEM MODELING AND DESIGN 2023年第1期14卷 1页

作者： She, Shi-Yao Yuan, Fang-Fang Li, Jun-Ke Dai, Hong-Wei China Shipbuilding Ind Corp Purificat Equipment Res Inst Beijing Peoples R China Dongfang Elect Co Ltd Harbin Peoples R China

Material demand forecasting has a profound impact on the supply chain and is an important prerequisite for manufacturing enterprises to produce. In order to accurately predict the material demand of enterprises, this paper proposes a material demand forecasting algorithm based on multi-dimensional feature fusion (DFMF). Secondly, in order to obtain the spatial features, the vector representation of the relevant materials of a material is obtained through the attention mechanism. Then, the authors aggregate the relevant material representation and material vector representation of materials to obtain the final material vector representation through aggregation function. Then the final material vector representation under different time scales is used as input, and the prediction value of material demand is obtained by using BP neural network. Finally, experiments show that the model can effectively obtain multi-dimensional features of materials for prediction, and the prediction results have high accuracy.

关键词： Cycle Features forecasting algorithm Historical Information Multi-Dimensional Feature Fusion Neural Network

来源：评论

学校读者我要写书评

暂无评论

A Frequency Decomposition-Based Hybrid forecasting algorithm for Short-Term Reactive Power

引用

ENERGIES 2021年第20期14卷 6606页

作者： Du, Jiabao Yue, Changxi Shi, Ying Yu, Jicheng Sun, Fan Xie, Changjun Su, Tao Wuhan Univ Technol Sch Automat Wuhan 430070 Peoples R China China Elect Power Res Inst Wuhan 430070 Peoples R China Xinjiang Elect Power Res Inst State Gird Urumqi 830000 Peoples R China

This paper proposes a new frequency decomposition-based hybrid reactive power forecasting algorithm, EEMD-LSTM-RFR (ELR), which adopts a strategy of frequency decomposition prediction after ensemble empirical mode decomposition and then data reconstruction to improve the prediction ability of reactive power. This decomposition process can compress the high frequency of reactive power and benefits the following separate forecasting. Long short-term memory is proposed for the high-frequency feature of reactive power to deal with the forecasting difficulty caused by strong signal disturbance and randomness. In contrast, random forest regression is applied to the low-frequency part in order to speed up the forecasting. Four classical algorithms and four hybrid algorithms based on different signal decompositions are compared with the proposed algorithm, and the results show that the proposed algorithm outperforms those algorithms. The predicting index RMSE decreases to 0.687, while the fitting degree R-2 gradually approaches 1 with a step-by-step superposition of high-frequency signals, indicating that the proposed decomposition-predicting reconstruction strategy is effective.

关键词： reactive power forecasting algorithm ensemble empirical mode decomposition long short-term memory random forest regression

来源：评论

学校读者我要写书评

暂无评论

A forecasting algorithm for Latency Compensation in Indirect Human-Computer Interactions

A Forecasting Algorithm for Latency Compensation in Indirect...

引用

European Control Conference

作者： Rosane Ushirobira Denis Efimov Géry Casiez Nicolas Roussel Wilfrid Perruquetti Inria Non-A team 40 av. Halley 59650 Villeneuve d'Ascq France Inria Mjolnir team 40 av. Halley 59650 Villeneuve d'Ascq France

ISBN: (纸本)9781509025923

Human-computer interactions are greatly affected by the latency between the human input and the system visual response. The compensation of this latency is an important problem for the HCI (human-computer interaction) community. In this work, a simple forecasting algorithm is developed for latency compensation in indirect interaction using a mouse, based on numerical differentiation. Several differentiators are compared, including a novel algebraic version. An optimized procedure is developed for tuning the parameters of the algorithm. The efficiency is demonstrated on real data, measured with a 1 ms sampling time.

关键词： forecasting algorithm Latency Compensation Indirect Human-Computer Interactions

来源：评论

学校读者我要写书评

暂无评论

Aviation Turbulence forecasting over the Portuguese Flight Information Regions: algorithm and Objective Verification

引用

ATMOSPHERE 2022年第3期13卷 422页

作者： Belo-Pereira, Margarida Inst Portugues Mar & Atmosfera Div Meteorol Aeronaut Rua C Aeroporto P-1749077 Lisbon Portugal Univ Tras Os Montes & Alto Douro Ctr Res Agroenvironm & Biol Sci UTAD CITAB P-5000801 Vila Real Portugal

Aviation turbulence remains one of the leading causes of weather-related aviation accidents. Therefore, turbulence prediction is a major concern of aviation forecasters. This paper describes the turbulence index (TURBIPMA) developed and used operationally at the Portuguese Institute of Sea and Atmosphere (IPMA), based on several diagnostics derived from ECMWF forecasts, using a new calibration approach. The forecast skill of the TURBIPMA and of individual diagnostics are evaluated using turbulence observations over the Portuguese Flight Information Regions and surrounding areas, for 12 months between February 2020 and March 2021 (excluding May and June). The forecasting skill of the predictors is discussed in terms of the Relative Operating Characteristic (ROC) curves, which is widely applied, but also in terms of novel measures such as the Symmetric Extremal Dependence Index (SEDI) and Symmetric Extreme Dependency Score (SEDS). The new measures are particularly relevant in assessing forecasts of rare events, such as moderate-or-greater turbulence. The operational index outperforms individual diagnostics (such as Ellrod) in terms of all verification measures. Furthermore, the use of a new Richardson number function was proven to be beneficial. Finally, the turbulence prediction by IPMA was comparable to that of the London WAFC for one turbulence episode.

关键词： aviation turbulence turbulence diagnostics ECMWF model forecasting algorithm objective scores forecast verification AIREP AMDAR prediction skill flight information regions

来源：评论

学校读者我要写书评

暂无评论

Large Scale Financial Time Series forecasting with Multi-faceted Model 23

Large Scale Financial Time Series Forecasting with Multi-fac...

引用

4th ACM International Conference on AI in Finance (ICAIF)

作者： Cao, Defu Zheng, Yixiang Hassanzadeh, Parisa Lamba, Simran Liu, Xiaomo Liu, Yan Univ Southern Calif Los Angeles CA 90007 USA JP Morgan AI Res New York NY USA

ISBN: (纸本)9798400702402

Data-driven approaches using deep neural networks have been successful in modeling complex financial time series and generating accurate predictions without requiring extensive domain knowledge. However, most of the existing models that assume independent and identically distributed (i.i.d) data may not generalize well to novel situations or distributional shifts across or inside financial scenarios. To address this challenge, we introduce an invariant learning-based regularizer with relaxed bounds that expands the range of feasible solutions and mitigates over-convergence issues in Invariant Risk Minimization (IRM). In practice, the regularizer can be incorporated into both linear and nonlinear financial time series forecasting models. Experimental results on real-world large-scale financial datasets show that our proposed method enables more robust and adaptable financial forecasting models, enhancing the overall performance and generalizability of financial forecasting on both in-distribution and out-of-distribution (OOD) samples.

关键词： Financial time series forecasting algorithm Distributional shifts

来源：评论

学校读者我要写书评

暂无评论

New algorithm for Predicting the States of a Computer Network Using Multivalued Dependencies

引用

AUTOMATIC CONTROL AND COMPUTER SCIENCES 2023年第1期57卷 48-60页

作者： Sheluhin, O. I. Osin, A. V. Rakovsky, D. I. Moscow Tech Univ Commun & Informat MTUCI Informat Secur Dept Moscow 123423 Russia

The algorithm that allows based on the analysis of monitoring historical data to predict the state of the network has been proposed. It is aimed to evaluate the state of the network using the service level indicators Service Level Objectives, SLO. The algorithm is based on the search for statistically stable multivalued dependencies. For forecasting, combinations of arguments are calculated, obtained by imposing masks, on the basis of which, in turn, statistical patterns are formed. To search for repeating patterns a history data size is determined. Each stage of the algorithm is illustrated with pseudocode.

关键词： quality of service forecasting algorithm sequential analysis pattern multivalued dependency network traffic

来源：评论

学校读者我要写书评

暂无评论

forecasting of Computer Network Anomalous States Based on Sequential Pattern Analysis of "Historical Data"

引用

AUTOMATIC CONTROL AND COMPUTER SCIENCES 2021年第6期55卷 522-533页

作者： Sheluhin, O., I Kostin, D., V Polkovnikov, M., V Moscow Tech Univ Commun & Informat Moscow Russia

To solve the problems of diagnosing the "health" of a computer network (CN), it is proposed to use the methods of intellectual analysis of historical data obtained by studying the behavior of the network in the past and formalizing this information in the form of sequential patterns. Service level objectives (SLO) and service level agreement (SLA) are used as system indicators characterizing the health of a computer network. An algorithm for calculating the forecast of the current abnormal state of the CN based on sequential pattern predictor (PP) patterns and the structure of the implemented algorithm have been developed and implemented. It is shown that the pattern predictor (PP) algorithm proposed in this work is more than 1000 times superior to the compact prediction tree (CPT) algorithm in terms of the computational complexity of learning and forecasting and the CPT+ algorithm by more than 100 times. The PP algorithm, on average, made 40 and 43% fewer type II errors than the CPT+ and CPT algorithms.

关键词： distributed computer systems anomalous states historical data health of a computer network forecasting algorithm sequential pattern predictor detecting abnormal system

来源：评论

学校读者我要写书评

暂无评论

Short-term forecasting model for residential indoor temperature in DHS based on sequence generative adversarial network

引用

APPLIED ENERGY 2023年 348卷

作者： Song, Jiancai Bian, Tianxiang Xue, Guixiang Wang, Hanyu Shen, Xingliang Wu, Xiangdong Tianjin Univ Commerce Sch Informat & Engn Tianjin 300134 Peoples R China Hebei Univ Technol Inst Artificial Intelligence Tianjin 300401 Peoples R China Tianjin Inst Nav Instrument Tianjin 300131 Peoples R China Hebei GongDa Keya Energy Technol Co Ltd Shijiazhuang 051130 Peoples R China

With the rapid development of the economy and the continuous improvement of people's living conditions, building thermal comfort has become one of the essential objectives of the development of the smart district heating system (SDHS). The accurate prediction approach of indoor temperature is the primary prerequisite and basis for achieving optimal thermal comfort regulation. However, the buildings' indoor temperature has significant thermal inertia and nonlinear characteristics due to the influence of multiple factors. The traditional time-series prediction algorithm can hardly accurately extract the indoor temperature variation pattern and cannot fully meet the satisfactory regulation requirements of SDHS. Therefore, an indoor temperature prediction model based on a sequence generative adversarial network (SGAN) is proposed in this paper. The new SGAN algorithm is trained by iterative adversarial training of the generator and discriminator, and the LSTM model built into the generator can effectively extract the high-level nonlinear abstract features of indoor temperature to achieve its accurate prediction. The detailed comparative experimental results show that the proposed indoor forecasting algorithm based on SGAN has obvious performance advantages compared to state-of-the-art algorithms, such as random forest regression (RFR), gradient boosting regression (GBR), support vector regression (SVR), adaptive boost (AdaBoost), multilayer perception (MLP), and long-short term memory(LSTM). The SGAN's mean absolute percentage error (MAPE) index reaches 2.3%.

关键词： Indoor temperature prediction forecasting algorithm Generative adversarial network District heating system

来源：评论

学校读者我要写书评

暂无评论

Tuning forecasting algorithms for black swans

引用

IFAC-PapersOnLine 2019年第13期52卷 1496-1501页

作者： Prestwich, S.D. Department of Computer Science University College Cork Ireland

forecasting algorithms based on exponential smoothing have smoothing factors, and it is often recommended that these be tuned to minimise an error measure on observed data. We show that forecasting algorithms such as simple exponential smoothing and Croston's method cannot always be optimally tuned to time series using any of several error measures. We propose a data augmentation approach: adding hypothetical non-stationary time series (which we call "black swans" as they represent unseen pathological cases) to the training data, and minimising a weighted error. The choice of black swans is a form of judgemental forecasting that requires experts to explicitly state their assumptions on unseen data. © 2019, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

关键词： forecasting Errors Time series Time series analysis Black swan Exponential smoothing forecasting algorithm Non stationarities Non stationary time series Optimisations Simple exponential smoothing Smoothing factors

来源：评论

学校读者我要写书评

暂无评论

A generalized grey model with symbolic regression algorithm and its application in predicting aircraft remaining useful life

引用

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE 2024年第PartB期136卷

作者： Liu, Lianyi Liu, Sifeng Yang, Yingjie Guo, Xiaojun Sun, Jinghe Nanjing Univ Aeronaut & Astronaut Coll Econ & Management Nanjing 210016 Peoples R China Nanjing Univ Aeronaut & Astronaut Grey Syst Res Inst Nanjing 211106 Peoples R China Northwestern Polytech Univ Sch Management Xian 710072 Peoples R China De Montfort Univ Inst Artificial Intelligence Leicester LE1 9BH England Nantong Univ Sch Math & Stat Nantong 226019 Peoples R China

As a sparse data analysis method, a grey model faces challenges in interpretability for its effective application in uncertain systems. This study proposes a generalized grey model (GGM) based on symbolic regression, designed to improve the intelligence and adaptability of grey models. The GGM serves as a unified framework, integrating various grey model families and addresses regression challenges to determine the model structure. Symbolic regression in the GGM identifies symbolic input-output relationships, offering an interpretable approach for structure determination. By leveraging the non-uniqueness principle in grey system theory and employing structural penalty parameters, the model balances complexity and interpretability. A comparative analysis between GGM and conventional grey function models is conducted focusing on the differences in modeling, structure identification, and parameter optimization. Validation on the M3 competition dataset demonstrated the GGM's superior performance, achieving a significant reduction in prediction error compared to other grey forecasting models. Additionally, a rigorous analysis of aircraft lifespan data underscored the robustness and accuracy of GGM in practical engineering applications.

关键词： forecasting algorithm Structure identification Time series Model interpretability Grey system theory

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：