We introduce deep switching auto-regressive factorization (DSARF), a generative model for spatio-temporal data with the capability to unravel recurring patterns in and perform robust short- long-term predictions. Similar other factor analysis methods, DSARF approximates high dimensional by product between time dependent weights spatially factors. These factors are turn represented terms of lowe...

Energy consumption is vital to the global costs of wastewater treatment plants (WWTPs). With increase installed WWTPs worldwide, modeling and forecast their energy have become a critical factor in WWTP design meet environmental economic requirements. The accurate swift forecasting soft-sensors are not only supportive daily electric financial budgeting by practitioners on micro-scale, but also b...

The dynamic response analysis of structures subjected to a stochastic wind field is carried out in the time domain by a step-by-step integration approach. The loading is represented by simulated time histories of the aerodynamic force. The auto-regressive and moving average (ARMA) recursive models are utilized to simulate time series of wind loads. Depending on the system dynamic characteristic...

this paper presents the prediction of vehicle's velocity time series using neural networks. for this purpose, driving data is firstly collected in real world traffic conditions in the city of tehran using advance vehicle location devices installed on private cars. a multi-layer perceptron network is then designed for driving time series forecasting. in addition, the results of this study a...

India is basically an agricultural country and the success or failure of the harvest and water scarcity in any year is always considered with the greatest concern. The average annual or seasonal rainfall at a place does not give sufficient information regarding its capacity to support crop production. Rainfall distribution pattern is the most important. The rainfall forecasting is scientificall...

C. L. Wu and K. W. Chau* 2 Dept. of Civil and Structural Engineering, Hong Kong Polytechnic University, 3 Hung Hom, Kowloon, Hong Kong, People’s Republic of China 4 5 *Email: [email protected] 6 ABSTRACT 7 Data-driven techniques such as Auto-Regressive Moving Average (ARMA), K-Nearest-Neighbors (KNN), and 8 Artificial Neural Networks (ANN), are widely applied to hydrologic time series predi...

Air pollution is a worldwide issue that affects the lives of many people in urban areas. It considered air may lead to heart and lung diseases. A careful timely forecast quality could help reduce exposure risk for affected people. In this paper, we use data-driven approach predict based on historical data. We compare three popular methods time series prediction: Exponential Smoothing (ES), Auto...

The present study emphasizes the forecast of Andhra Pradesh's total marine fish production and catch commercially important fishes, viz., Indian Mackerel, Oil Sardine, Horse Lesser Sardines for next 5 years by different statistical machine learning approaches under climate change scenario. Forecasting is done with without inclusion climatic environmental parameters in models. Exogenous variable...