Forecasting in Non-stationary Environments with Fuzzy Time Series
Federal University of Minas Gerais（米纳斯吉拉斯联邦大学）；Federal Institute of Education Science and Technology of Northern Minas Gerais（北米纳斯吉拉斯联邦教育、科学与技术学院）；Federal Institute of Education Science and Technology of Minas Gerais（米纳斯吉拉斯联邦教育、科学与技术学院）；Federal University of Ouro Preto（欧鲁普雷图联邦大学）；Braude College of Engineering（布劳德工程学院）
Petrônio Cândido de Lima e Silva, Carlos Alberto Severiano Junior, Marcos Antonio Alves, Rodrigo Silva, Miri Weiss Cohen, Frederico Gadelha Guimarães
备注：
21 pages, 7 figures, submitted to Applied Soft Computing
In this paper we introduce a Non-Stationary Fuzzy Time Series (NSFTS) method with time varying parameters adapted from the distribution of the data. In this approach, we employ Non-Stationary Fuzzy Sets, in which perturbation functions are used to adapt the membership function parameters in the knowledge base in response to statistical changes in the time series. The proposed method is capable of dynamically adapting its fuzzy sets to reflect the changes in the stochastic process based on the residual errors, without the need to retraining the model. This method can handle non-stationary and heteroskedastic data as well as scenarios with concept-drift. The proposed approach allows the model to be trained only once and remain useful long after while keeping reasonable accuracy. The flexibility of the method by means of computational experiments was tested with eight synthetic non-stationary time series data with several kinds of concept drifts, four real market indices (Dow Jones, NASDAQ, SP500 and TAIEX), three real FOREX pairs (EUR-USD, EUR-GBP, GBP-USD), and two real cryptocoins exchange rates (Bitcoin-USD and Ethereum-USD). As competitor models the Time Variant fuzzy time series and the Incremental Ensemble were used, these are two of the major approaches for handling non-stationary data sets. Non-parametric tests are employed to check the significance of the results. The proposed method shows resilience to concept drift, by adapting parameters of the model, while preserving the symbolic structure of the knowledge base.
Differential Convolutional Fuzzy Time Series Forecasting
University of Electronic Science and Technology of China（电子科技大学）；Huawei Cloud（华为云）；China Mobile Information Technology Center（中国移动信息技术中心）；Vanderbilt University（范德堡大学）
G. B. Pant University of Agriculture and Technology（GB潘特农业技术大学）
Fuzzy time series forecasting methods are very popular among researchers for predicting future values as they are not based on the strict assumptions of traditional time series forecasting methods. Non-stochastic methods of fuzzy time series forecasting are preferred by the researchers as they provide more significant forecasting results. There are generally, four factors that determine the performance of the forecasting method (1) number of intervals (NOIs) and length of intervals to partition universe of discourse (UOD) (2) fuzzification rules or feature representation of crisp time series (…
Federal University of Minas Gerais（米纳斯吉拉斯联邦大学）；Federal Institute of Education Science and Technology of Northern Minas Gerais（北米纳斯吉拉斯联邦教育科学与技术学院）
Among various soft computing approaches for time series forecasting, Fuzzy Cognitive Maps (FCM) have shown remarkable results as a tool to model and analyze the dynamics of complex systems. FCM have similarities to recurrent neural networks and can be classified as a neuro-fuzzy method. In other words, FCMs are a mixture of fuzzy logic, neural network, and expert system aspects, which act as a powerful tool for simulating and studying the dynamic behavior of complex systems. The most interesting features are knowledge interpretability, dynamic characteristics and learning capability. The goal …
Universidade Federal de Minas Gerais（米纳斯吉拉斯联邦大学）；Federal University of Minas Gerais（米纳斯吉拉斯联邦大学）；Federal Institute of Education Science and Technology of Northern Minas Gerais（北米纳斯吉拉斯联邦教育科学技术学院）
The prediction of residential power usage is essential in assisting a smart grid to manage and preserve energy to ensure efficient use. An accurate energy forecasting at the customer level will reflect directly into efficiency improvements across the power grid system, however forecasting building energy use is a complex task due to many influencing factors, such as meteorological and occupancy patterns. In addiction, high-dimensional time series increasingly arise in the Internet of Energy (IoE), given the emergence of multi-sensor environments and the two way communication between energy con…
Causal Graph Fuzzy LLMs: A First Introduction and Applications in Time Series Forecasting
Federal Institute of Northern Minas Gerais（巴西北矿联邦理工学院）；Graduate Program in Electrical Engineering（电气工程研究生项目）；Universidade Federal de Minas Gerais（伯南巴西联邦大学）；Graduate Program in Computer Science（计算机科学研究生项目）；Federal University of Minas Gerais（伯南巴西联邦大学）；Future Lab（未来实验室）
In Internet of things (IoT), data is continuously recorded from different data sources and devices can suffer faults in their embedded electronics, thus leading to a high-dimensional data sets and concept drift events. Therefore, methods that are capable of high-dimensional non-stationary time series are of great value in IoT applications. Fuzzy Time Series (FTS) models stand out as data-driven non-parametric models of easy implementation and high accuracy. Unfortunately, FTS encounters difficulties when dealing with data sets of many variables and scenarios with concept drift. We present a ne…
Risk-Aware Financial Forecasting Enhanced by Machine Learning and Intuitionistic Fuzzy Multi-Criteria Decision-Making
Sakarya University（萨卡里亚大学）；University of East Sarajevo（东萨拉热窝大学）；Korea University（高丽大学）；Necmettin Erbakan University（内吉梅丁·埃尔巴坎大学）；Singapore University of Social Sciences（新加坡社会科学大学）
Ivan Franko National University of Lviv（利沃夫伊万·弗兰科国立大学）
The paper describes the deep learning approach for forecasting non-stationary time series with using time trend correction in a neural network model. Along with the layers for predicting sales values, the neural network model includes a subnetwork block for the prediction weight for a time trend term which is added to a predicted sales value. The time trend term is considered as a product of the predicted weight value and normalized time value. The results show that the forecasting accuracy can be essentially improved for non-stationary sales with time trends using the trend correction block i…
Deep Frequency Derivative Learning for Non-stationary Time Series Forecasting
University of Oxford（牛津大学）；Beijing Institute of Technology（北京理工大学）；Jilin University（吉林大学）；Chinese Academy of Science（中国科学院）；Tongji University（同济大学）；Hefei University of Technology（合肥工业大学）
Time series with long-term structure arise in a variety of contexts and capturing this temporal structure is a critical challenge in time series analysis for both inference and forecasting settings. Traditionally, state space models have been successful in providing uncertainty estimates of trajectories in the latent space. More recently, deep learning, attention-based approaches have achieved state of the art performance for sequence modeling, though often require large amounts of data and parameters to do so. We propose Stanza, a nonlinear, non-stationary state space model as an intermediate…
The electricity consumption of buildings composes a major part of the city's energy consumption. Electricity consumption forecasting enables the development of home energy management systems resulting in the future design of more sustainable houses and a decrease in total energy consumption. Energy performance in buildings is influenced by many factors like ambient temperature, humidity, and a variety of electrical devices. Therefore, multivariate prediction methods are preferred rather than univariate. The Honda Smart Home US data set was selected to compare three methods for minimizing forec…
Accurate forecasting of the U.K. gross value added (GVA) is fundamental for measuring the growth of the U.K. economy. A common nonstationarity in GVA data, such as the ABML series, is its increase in variance over time due to inflation. Transformed or inflation-adjusted series can still be challenging for classical stationarity-assuming forecasters. We adopt a different approach that works directly with the GVA series by advancing recent forecasting methods for locally stationary time series. Our approach results in more accurate and reliable forecasts, and continues to work well even when the…
Nonstationary Time Series Forecasting via Unknown Distribution Adaptation
Mohamed bin Zayed University of Artificial Intelligence（穆罕默德·本·扎耶德人工智能大学）；Guangdong University（广东大学）；Carnegie Mellon University（卡内基梅隆大学）；Shantou University（汕头大学）
PULSE: Generative Phase Evolution for Non-Stationary Time Series Forecasting
College of Computer Science, Sichuan University, Chengdu, China（四川大学计算机学院）；University of Chinese Academy of Sciences, Beijing, China（中国科学院大学）；Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China（中国科学院计算技术研究所）；Institute of Artificial Intelligence, University of Central Florida, Orlando, USA（佛罗里达大学人工智能研究所）
Quantitative evaluation of the performance of discrete-time reservoir computers in the forecasting, filtering, and reconstruction of stochastic stationary signals
Birla Institute of Technology and Science Pilani（比拉理工学院与科学大学皮拉尼分校）
The problem of automatic and accurate forecasting of time-series data has always been an interesting challenge for the machine learning and forecasting community. A majority of the real-world time-series problems have non-stationary characteristics that make the understanding of trend and seasonality difficult. Our interest in this paper is to study the applicability of the popular deep neural networks (DNN) as function approximators for non-stationary TSF. We evaluate the following DNN models: Multi-layer Perceptron (MLP), Convolutional Neural Network (CNN), and RNN with Long-Short Term Memor…
TwinS: Revisiting Non-Stationarity in Multivariate Time Series Forecasting
Hong Kong University of Science and Technology (Guangzhou)（香港科技大学（广州））；Squirrel AI（松鼠AI）；Beijing Institute of Technology（北京理工大学）；Chongqing University（重庆大学）
Time series forecasting (TSF) is one of the most important tasks in data science given the fact that accurate time series (TS) predictive models play a major role across a wide variety of domains including finance, transportation, health care, and power systems. Real-world utilization of machine learning (ML) typically involves (pre-)training models on collected, historical data and then applying them to unseen data points. However, in real-world applications, time series data streams are usually non-stationary and trained ML models usually, over time, face the problem of data or concept drift…
Singapore Management University（新加坡管理大学）；Salesforce Research Asia（赛富时亚洲研究院）
The fast adaptation capability of deep neural networks in non-stationary environments is critical for online time series forecasting. Successful solutions require handling changes to new and recurring patterns. However, training deep neural forecaster on the fly is notoriously challenging because of their limited ability to adapt to non-stationary environments and the catastrophic forgetting of old knowledge. In this work, inspired by the Complementary Learning Systems (CLS) theory, we propose Fast and Slow learning Networks (FSNet), a holistic framework for online time-series forecasting to s…
IN-Flow: Instance Normalization Flow for Non-stationary Time Series Forecasting
University of Oxford（牛津大学）；Microsoft Research Asia（微软亚洲研究院）；University of Macau（澳门大学）；University of Central Florida（中佛罗里达大学）；State Information Center（国家信息中心）；Tongji University（同济大学）；Arizona State University（亚利桑那州立大学）
Northeastern University（东北大学）；Abiomed（艾比奥医疗公司）；UC San Diego（加利福尼亚大学圣迭戈分校）
Mean aortic pressure (MAP) is a major determinant of perfusion in all organs systems. The ability to forecast MAP would enhance the ability of physicians to estimate prognosis of the patient and assist in early detection of hemodynamic instability. However, forecasting MAP is challenging because the blood pressure (BP) time series is noisy and can be highly non-stationary. The aim of this study was to forecast the mean aortic pressure five minutes in advance, using the 25 Hz time series data of previous five minutes as input. We provide a benchmark study of different deep learning models for B…
