Short-term Prediction Algorithm Research Articles

Research on Short Term Prediction Algorithm for Freeway Pavement Ice

This article focuses on the short-term prediction algorithm for ice condensation on highway pavement. Solar radiation, ground long wave radiation, and atmospheric inverse radiation are the main factors affecting road surface temperature changes. According to the principle of radiation heat transfer, there is a radiation balance relationship among these three factors. Therefore, based on the balance relationship between these three radiations and the physical heat formula, this article designs a short-term prediction algorithm for road icing. Based on the basic theory of radiation heat transfer, the energy balance between solar shortwave radiation, atmospheric inverse radiation, and ground longwave radiation is calculated to predict the temperature of highway road surfaces.

A Real-Time Linear Prediction Algorithm for Detecting Abnormal BDS-2/BDS-3 Satellite Clock Offsets

Due to space environment interference, imperfect data processing model, and the performance of atomic clocks, real-time satellite clock products often contain outliers or irregular biases. We propose a real-time linear moving short-term prediction algorithm to predict clock offsets and detect abnormalities. The proposed algorithm mainly includes phase/frequency anomaly detection and real-time prediction part. Both the phase and frequency domains are used to detect abnormal clock offsets with previous epochs for building the clock prediction model accurately. The real-time moving prediction module utilizes the high short-term prediction performance to check the clock abnormality. The performance of the algorithm is then evaluated for all satellites with real-time estimated satellite clock offsets. To verify the feasibility and effectiveness of the proposed linear moving model and algorithm, the results of the grey model GM(1,1) and the ARIMA model are also compared. The experimental results indicated that the algorithm can detect clock outliers, frequency modulation, and phase jumps, and the linear model has a better clock performance improvement. After the abnormalities are removed with the proposed algorithm, the average STD accuracy of the real-time clock offsets for all satellites is improved by 15.5%, compared to an improvement of 11.4% by the GM(1,1) model and 11.5% by the ARIMA model. The PPP results demonstrate that the proposed clock prediction algorithm improves the positioning accuracy by 8.1%, 13.3%, and 16.9% in the east, north, and up components, respectively.

Prediction of Septic Shock Onset in ICU by Instantaneous Monitoring of Vital Signs.

Septic Shock is a critical pathological state that affects patients entering the intensive care unit (ICU). Many studies have been directed to characterize and predict the onset of the septic shock, both in ICU and in the Emergency Department employing data extracted from the Electronic Health Records. Recently, machine learning algorithms have been successfully employed to help characterize septic shock in a more objective and automatic fashion. Only a few of these studies employ information contained in the continuously recorded vital signs such as electrocardiogram and arterial blood pressure. In particular, we have devised a novel feature estimation procedure able to consider instantaneous dynamics related to cardiovascular control. This work aims at developing a short-term prediction algorithm for identifying patients experiencing septic shock among a population of 100 septic patients extracted from the MIMIC-III clinical and waveform database. Among all the results obtained from several trained machine learning models, the best performance reached an AUC on the test set equal to 0.93 (Accuracy=0.85, Sensitivity=0.89 and Specificity=0.82).

Correlations in Spatiotemporal Headway Dynamics of Road Traffic Using Extremely Accurate Microscopic Empirical Data

As we recently showed by using empirical data there is a certain behavior referring to the development of the headway between two consecutive human driven vehicles. Following on from this, we investigate correlations of the change in temporal headway over two subsequent road segments as the main goal of the present work and found a strongly correlated behaviour for increasing temporal headways. In this way a strong improvement for short-term prediction algorithms of conventional road users should be achieved. A stationary infrared-based sensor system was developed for this purpose, which has been mounted at reflector posts next to an urban street over a distance of about 50m. Due to its good accuracy, we are able to resolve vehicle following times down to 25 milliseconds and to determine speeds more precisely. In 45 hours of measurement the system detected over 20,000 passing vehicles.

An Adaptive Short-Term Prediction Algorithm for Resource Demands in Cloud Computing

Cloud computing has been widely applied in various fields with the development of big data and artificial intelligence. The associated resource demands exhibit characteristics such as diversity, large scale, burst and uncertainty. This paper analyzes these characteristics of cloud resource demands based on Alibaba cluster data, and proposes an adaptive short-term prediction algorithm for those demands. The proposed algorithm uses a principal component analysis method to extract the primary types of container demands from a time series of resource demands, and executes outlier detection and replacement to obtain a more stationary sequence. An adaptive short-term prediction strategy is proposed to adaptively select a higher-accuracy short-term prediction method to implement the prediction. Further, an error adjustment factor is proposed to reduce the prediction error. Thus, the short-term prediction accuracy of cloud resource demands is improved via outlier detection and replacement, an adaptive selection strategy and an error adjustment. We evaluated the effectiveness of these improvements, and compared our algorithm with existing algorithms in terms of effectiveness and time cost. The experimental results demonstrate that the proposed algorithm improves short-term prediction accuracy effectively.

Predicting the future location of cars on urban street network by chaining spatial web services

The use of web services for analysing and visualising maps has received great attention recently, because the complicated analysis of spatial data requires different processes to be run consecutively. Predicting the future location of a vehicle on a street network is one of the most challenging analyses used for improving context-aware location-based services, intelligent transportation systems and criminology. In this research, the authors present a new short-term prediction algorithm and explore the required analyses and web services. They present an appropriate method for chaining these web services to predict location(s). To assess their methodology, they developed a prototype system and tested for trajectories in Beijing. This system calculates the prediction time for a specified car to show the predicted future location in the street network. Their results showed that the average transferred data volume increases as the prediction period increases. The results also showed that the prediction algorithm has 75% accuracy at 1 min and 87.5% accuracy at 2 and 3 min. The implemented chaining method reduces the complexity of the location prediction algorithm for users because they do not need to know the processes. The outputs from this system can be used as input parameters for other web-based applications.

Prediction of Indoor Temperature in an Institutional Building

The importance of predicting building indoor temperature is inevitable to execute an effective energy management strategy in an institutional building. An accurate prediction of building indoor temperature not only contributes to improved thermal comfort conditions but also has a role in building heating and cooling energy conservation. To predict the indoor temperature accurately, Artificial Neural Network (ANN) has been used in this study because of its performance superiority to deal with the time-series data as cited in past studies. Network architecture is the most important part of ANN for predicting accurately without overfitting the data. In this study, as a part of determining the optimal network architecture, important input parameters related to the output has been sorted out first. Next, prediction models have been developed for building indoor temperature using real data. Initially, spring season of Australia was selected for data collection. During model development three different training algorithms have been used and the performance of these training algorithms has been evaluated in this study based on prediction accuracy, generalization capability and iteration time to train the algorithm. From results Lovenberg-Marquardt has been found the best-suited training algorithm for short-term prediction of indoor space temperature. Afterwards, residual analysis has been used as a technique to verify the validation result. Finally, the result has been justified by applying a similar approach to another building case and using two different weather data-sets of two different seasons: summer and winter of Australia.

Operational oil spill trajectory modelling using HF radar currents: A northwest European continental shelf case study

This paper presents a novel operational oil spill modelling system based on HF radar currents, implemented in a northwest European shelf sea. The system integrates Open Modal Analysis (OMA), Short Term Prediction algorithms (STPS) and an oil spill model to simulate oil spill trajectories. A set of 18 buoys was used to assess the accuracy of the system for trajectory forecast and to evaluate the benefits of HF radar data compared to the use of currents from a hydrodynamic model (HDM). The results showed that simulated trajectories using OMA currents were more accurate than those obtained using a HDM. After 48h the mean error was reduced by 40%. The forecast skill of the STPS method was valid up to 6h ahead. The analysis performed shows the benefits of HF radar data for operational oil spill modelling, which could be easily implemented in other regions with HF radar coverage.

Closed Loop System on the Base of Non-Invasive Optical Glucometer

Closed loop system for diabetes mellitus compensation was developed. The system comprises a non-invasive optical glucose meter, an insulin infusion device and algorithm for blood glucose prediction. Glucometer consists of the control unit connected to the earlap clip by optical fiber. Experimental trials show that inherent accuracy of the optical system is 0.012 %, reproducibility – 0.06 %, RMSE in the blood glucose physiological area ­– 17 %. The system was provided with the short-term prediction algorithm, which corrects 96.5 % cases of inaccurate operation of the glucometer that makes insulin infusion more physiological. The system is aimed for personal continuous blood glucose control for patients with diabetes mellitus type I.

A Glucose Model Based on Support Vector Regression for the Prediction of Hypoglycemic Events Under Free-Living Conditions

The prevention of hypoglycemic events is of paramount importance in the daily management of insulin-treated diabetes. The use of short-term prediction algorithms of the subcutaneous (s.c.) glucose concentration may contribute significantly toward this direction. The literature suggests that, although the recent glucose profile is a prominent predictor of hypoglycemia, the overall patient's context greatly impacts its accurate estimation. The objective of this study is to evaluate the performance of a support vector for regression (SVR) s.c. glucose method on hypoglycemia prediction. We extend our SVR model to predict separately the nocturnal events during sleep and the non-nocturnal (i.e., diurnal) ones over 30-min and 60-min horizons using information on recent glucose profile, meals, insulin intake, and physical activities for a hypoglycemic threshold of 70 mg/dL. We also introduce herein additional variables accounting for recurrent nocturnal hypoglycemia due to antecedent hypoglycemia, exercise, and sleep. SVR predictions are compared with those from two other machine learning techniques. The method is assessed on a dataset of 15 patients with type 1 diabetes under free-living conditions. Nocturnal hypoglycemic events are predicted with 94% sensitivity for both horizons and with time lags of 5.43 min and 4.57 min, respectively. As concerns the diurnal events, when physical activities are not considered, the sensitivity is 92% and 96% for a 30-min and 60-min horizon, respectively, with both time lags being less than 5 min. However, when such information is introduced, the diurnal sensitivity decreases by 8% and 3%, respectively. Both nocturnal and diurnal predictions show a high (>90%) precision. Results suggest that hypoglycemia prediction using SVR can be accurate and performs better in most diurnal and nocturnal cases compared with other techniques. It is advised that the problem of hypoglycemia prediction should be handled differently for nocturnal and diurnal periods as regards input variables and interpretation of results.

Artificial immune algorithm applied to short-term prediction for mobile object location

Mobility prediction is one of the most essential issues that need to be explored for management in a location-based service. The purpose of this study is to present a novel approach for predicting the next location of a mobile object. Existing prediction methods are generally based on mass history information. However, they cannot work well on the prediction of an object which has the features of short moving time and an elusive moving tendency. Taking into account these characteristics, proposed is a short-term prediction algorithm based on the artificial immune system. Simulated experimental results show that the proposed algorithm obtains higher accuracy and scalability than the traditional method.

Neural Network Incorporating Meal Information Improves Accuracy of Short-Time Prediction of Glucose Concentration

Diabetes mellitus is one of the most common chronic diseases, and a clinically important task in its management is the prevention of hypo/hyperglycemic events. This can be achieved by exploiting continuous glucose monitoring (CGM) devices and suitable short-term prediction algorithms able to infer future glycemia in real time. In the literature, several methods for short-time glucose prediction have been proposed, most of which do not exploit information on meals, and use past CGM readings only. In this paper, we propose an algorithm for short-time glucose prediction using past CGM sensor readings and information on carbohydrate intake. The predictor combines a neural network (NN) model and a first-order polynomial extrapolation algorithm, used in parallel to describe, respectively, the nonlinear and the linear components of glucose dynamics. Information on the glucose rate of appearance after a meal is described by a previously published physiological model. The method is assessed on 20 simulated datasets and on 9 real Abbott FreeStyle Navigator datasets, and its performance is successfully compared with that of a recently proposed NN glucose predictor. Results suggest that exploiting meal information improves the accuracy of short-time glucose prediction.

Premonitory patterns of seismicity months before a large earthquake: five case histories in Southern California.

This article explores the problem of short-term earthquake prediction based on spatio-temporal variations of seismicity. Previous approaches to this problem have used precursory seismicity patterns that precede large earthquakes with "intermediate" lead times of years. Examples include increases of earthquake correlation range and increases of seismic activity. Here, we look for a renormalization of these patterns that would reduce the predictive lead time from years to months. We demonstrate a combination of renormalized patterns that preceded within 1-7 months five large (M > or = 6.4) strike-slip earthquakes in southeastern California since 1960. An algorithm for short-term prediction is formulated. The algorithm is self-adapting to the level of seismicity: it can be transferred without readaptation from earthquake to earthquake and from area to area. Exhaustive retrospective tests show that the algorithm is stable to variations of its adjustable elements. This finding encourages further tests in other regions. The final test, as always, should be advance prediction. The suggested algorithm has a simple qualitative interpretation in terms of deformations around a soon-to-break fault: the blocks surrounding that fault began to move as a whole. A more general interpretation comes from the phenomenon of self-similarity since our premonitory patterns retain their predictive power after renormalization to smaller spatial and temporal scales. The suggested algorithm is designed to provide a short-term approximation to an intermediate-term prediction. It remains unclear whether it could be used independently. It seems worthwhile to explore similar renormalizations for other premonitory seismicity patterns.