Search

In the increasingly complex urban transportation landscape, the necessity for accurate, multi-step forecasting has never been more apparent to help plan for long-term, strategic transportation initiatives like Intelligent Transportation Systems. This work focuses on resolving uncertainties around the proper training step size for machine learning models performing multi-step traffic flow forecasting. Two strategies are considered: one-step and horizon-step training sizes, which extend from the single-step forecasting method. This paper compares and evaluates two machine learning models: the Support Vector Regression and Long Short-Term Memory (LSTM). Data from two country road locations, including urban roads in Kuala Lumpur and the I5-North freeway in California, are employed to forecast traffic flow in 1-hour increments, projecting from 2 h up to 24 h ahead. The results reveal a significant difference in performance between the two training step sizes, with the one-step training size emerging as the more consistent and optimal strategy for both Direct and Multi-Input Multi-Output forecasting strategies. The proposed model, the Direct Particle Swarm Optimization Grid Search Support Vector Regression (Direct-PSOGS-SVR) model, exhibited comparable or slightly better performance than the LSTM model in both environments. In the I5-North freeway dataset, the Direct-PSOGS-SVR achieved similar Root Mean Squared Error values across most forecasting tasks compared to the LSTM, indicating its effectiveness in stable traffic flow patterns. Notably, in the more dynamic urban environment of Kuala Lumpur, the Direct-PSOGS-SVR model also demonstrated stability and resilience in forecasting accuracy, effectively handling the inherent noise and fluctuations in traffic patterns. These findings serve as a valuable guide for practitioners in selecting the most efficacious combination of training strategies for specific time series forecasting tasks utilizing machine learning models, particularly in traffic flow forecasting. Introducing the Direct-PSOGS-SVR model enriches the landscape of machine learning solutions for traffic forecasting, underscoring the paper's contributions to the broader understanding of time series forecasting dynamics. [ABSTRACT FROM AUTHOR]

The accurate prediction of digging load serves as a fundamental cornerstone for advancing the development of intelligent and unmanned excavators. Given the complex nonlinear dynamics of digging load, this paper proposes a novel prediction model for excavator load power based on the chaos theory and support vector regression (SVR). The presence of chaos in the dynamic digging load system is detected through phase space reconstruction. SVR is utilized for nonparametric modeling and prediction, with the reconstructed phase space capturing the essential characteristics of excavator load and serving as inputs for SVR. To optimize the hyperparameters, an improved particle swarm optimization (IPSO) algorithm is presented. Excavation experiments conducted under two typical load conditions demonstrate the superiority of the proposed chaos-based IPSO-SVR model in terms of prediction accuracy. This research lays a solid foundation for practical load prediction in industrial excavator settings. [ABSTRACT FROM AUTHOR]

Enhancing the accuracy of breast cancer recurrence prediction is crucial, mainly when dealing with genomics data, which presents challenges such as high dimensionality, noise, non-linearity, and limited sample sizes. This paper introduces Semi-Supervised Survival Laplacian Regression (S3LR), a novel feature selection algorithm designed to improve breast cancer recurrence prediction by effectively handling censored, event, and unlabeled data. S3LR modifies the Laplacian Score (LS) by incorporating a distance matrix to calculate the weight matrix, and it integrates heuristic and metaheuristic optimization algorithms to optimize the weighted matrix. These enhancements refine feature selection and overall performance. In our evaluations using three datasets and comparisons with state-of-the-art techniques, S3LR combined with Particle Swarm Optimization (PSO) demonstrates significant improvements in C-index and mean absolute error (MAE). Average C-index values reach 68.80 %, 59.49 %, and 67.66 %, with average MAE values of 15.98, 7.87, and 8.65 months, respectively. These results showcase S3LR's effectiveness in predicting recurrence, even with censored data, for more precise and reliable outcomes. Furthermore, the framework's versatility extends beyond breast cancer and can readily be applied to address other survival and recurrence problems. [ABSTRACT FROM AUTHOR]

High precision PM 2. 5 concentrations (PCs) forecasting modeling is a solid foundation for optimizing the air pollution early warning system. However, the existing studies focus mainly on point forecasting and ignore the importance of uncertainty research. Therefore, this paper proposes a novel hourly PCs multi-step ahead point-interval forecasting system, which quantifies the forecasting uncertainty on the basis of improving the point forecasting accuracy of the target monitoring station. Firstly, the system collects the PCs of surrounding stations and target station, and air pollution indexes of the target station, and adjustments are made for lags in data from surrounding stations. Then, the improved method which combines mutual information with decision tree regressor is used to extract features. Secondly, successive multivariate mode decomposition is used to extract multi-mode components (MMC) to mine potential associations among features while reducing complexity, and the bidirectional gated recurrent unit is used for multi-step ahead point forecasting for each row of MMC. Finally, non-parametric kernel density estimation is used to expand the upper and lower bounds of the prediction interval (PI), and speed-constrained multi-objective particle swarm optimization is used to fine-tune the bounds. And then, the multi-step ahead interval forecasting results with confidence level of 80%, 90% and 99% are obtained. The datasets of three monitoring stations in Beijing-Tianjin-Hebei Region are tested, and the results show that this system can provide a more valuable early warning basis for the future change of PCs from the aspects of point and interval forecasting. [ABSTRACT FROM AUTHOR]

Abstract: The ε-insensitive loss function has no penalizing capability for white (Gaussian) noise from training series in support vector regression machine (SVRM). To overcome the disadvantage, the relation between Gaussian noise model and loss function of SVRM is studied. And then, a new loss function is proposed to penalize the Gaussian noise in this paper. Based on the proposed loss function, a new ν-SVRM, which is called g-SVRM, is put forward to deal with training set. To seek the optimal parameters of g-SVRM, an improved particle swarm optimization is also proposed. The results of application in car sale forecasts show that the forecasting approach based on the g-SVRM model is effective and feasible, the comparison between the method proposed in this paper and other ones is also given, which proves this method is better than ν-SVRM and other traditional methods. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a new load forecasting model based on hybrid particle swarm optimization with Gaussian and adaptive mutation (HAGPSO) and wavelet v-support vector machine (Wv-SVM). Firstly, it is proved that mother wavelet function can build a set of complete base through horizontal floating and form the wavelet kernel function. And then, Wv-SVM with wavelet kernel function is proposed in this paper. Secondly, aiming to the disadvantage of standard PSO, HAGPSO is proposed to seek the optimal parameter of Wv-SVM. Finally, the load forecasting model based on HAGPSO and Wv-SVM is proposed in this paper. The results of application in load forecasts show the proposed model is effective and feasible. [Copyright &y& Elsevier]

• A heterogeneous ensemble forecasting model of nonlinear time series is proposed. • Both forecasting error and model divergence are considered. • Dynamic heterogeneous mutation operator is introduced to improve MOPSO. • The proposed model has excellent prediction performance and robustness. The excellent generalization performance of time series ensemble forecasting depends on the accuracy and diversity of the individual models. In this paper, a heterogeneous ensemble forecasting model with multi-objective programming for nonlinear time series is proposed. Accordingly, an improved multi-objective particle swarm optimization (MOPSO) algorithm integrated with a dynamic heterogeneous mutation operator is designed. The nonlinear time series of the Baltic Dry Index (BDI) is selected as the forecasting object to train, validate and test the ensemble forecasting model established in this paper. To verify the superior forecasting performance of the proposed model, 20 forecasting models including statistical models, machine learning models, and optimization algorithm–based ensemble models are utilized and compared. The experimental results under different lead times revealed that: 1) the forecasting approach with multi-objective programming has excellent robustness and can effectively exert out-of-sample prediction under different lead times for nonlinear time series; 2) with the increase of lead time, the out-of-sample forecasting performance would gradually decrease for all models, and the precision of the ensemble forecasting model is better than that of the individual forecasting model; 3) the forecasting performance of the MOPSO with crowding distance (MOPSOCD)-based ensemble forecasting model is better than that of benchmark machine learning models and other optimal ensemble forecasting models in terms of the prediction accuracy and statistical test results. [ABSTRACT FROM AUTHOR]

• A novel structure-adaptive grey model is initially designed. • The proposed model can grasp the nonlinear and seasonal patterns. • This method exhibits generalizability in predicting renewable energy generation. • The proposed technique strikingly outperforms many prevalent benchmarks. To provide accurate renewable energy forecasts that adapt to the country's sustainable development, a novel seasonal model combined with the data-restacking technique is proposed in this paper. Specifically, the data-restacking technique is initially utilized to eliminate the seasonal fluctuations of the collected observations, which can eliminate the fundamental flaws in conventional seasonal grey models. Subsequently, the time function term is originally designed to incorporate into the dynamic structure to reflect the cumulative time effects, which can smoothly describe the dynamic changes and significantly improve the robustness of the novel model. Further, the self-adaptive parameters optimized using particle swarm optimization can effectively enhance the adaptability and generalization of the proposed model. For elaboration and verification purposes, experiments on forecasting American monthly renewable energy consumption in the commercial sector and industrial solar energy have been implemented compared to a range of benchmark models, including other prevalent grey prediction models, statistical approaches, and machine learning methods. Experimental results demonstrate that this new model presents more successful outcomes than the other benchmarks in overall and restacking performance. [ABSTRACT FROM AUTHOR]

Distributed, small-scale solar photovoltaic (PV) systems are being installed at a rapidly increasing rate. This can cause major impacts on distribution networks and energy markets. As a result, there is a significant need for improved forecasting of the power generation of these systems at different time resolutions and horizons. However, the performance of forecasting models depends on the resolution and horizon. Forecast combinations (ensembles), that combine the forecasts of multiple models into a single forecast may be robust in such cases. Therefore, in this paper, we provide comparisons and insights into the performance of five state-of-the-art forecast models and existing forecast combinations at multiple resolutions and horizons. We propose a forecast combination approach based on particle swarm optimization (PSO) that will enable a forecaster to produce accurate forecasts for the task at hand by weighting the forecasts produced by individual models. Furthermore, we compare the performance of the proposed combination approach with existing forecast combination approaches. A comprehensive evaluation is conducted using a real-world residential PV power data set measured at 25 houses located in three locations in the United States. The results across four different resolutions and four different horizons show that the PSO-based forecast combination approach outperforms the use of any individual forecast model and other forecast combination counterparts, with an average Mean Absolute Scaled Error reduction by 3.81% compared to the best performing individual model. Our approach enables a solar forecaster to produce accurate forecasts for their application regardless of the forecast resolution or horizon. • Five solar forecasting models were analysed across multiple resolutions and horizons. • No model is consistently the best, and a forecast combination is necessary. • A forecast combination approach based on particle swarm optimization is proposed. • This approach can be adapted to any resolution or horizon. • In an extensive evaluation, it outperforms individual models and other combinations. [ABSTRACT FROM AUTHOR]

• An IoT-based monitoring and prediction system for PM 10. • Six IAQ and thermal comfort parameters have been recorded. • Novel approach using Fuzzy Inference System Tree optimized with PSO and GA. • Result comparison indicates that proposed model outperformed conventional models. • The proposed GA optimized FIST model shows RMSE = 1.2101. World health organization's estimates reveal that air pollution kills almost 6.5 million people in the world every year. As human beings, on average, spend 80–90% of their routine time in closed spaces, indoor air pollution has been a prime concern for their health and well-being. Primary and secondary pollutants are present in indoor environments, and they leave a considerable impact on human health. However, PM 10 has attracted special scientific and legislative attention due to its close association with chronic health problems such as respiratory illness, lung cancer, and asthma attacks. Therefore, it is critical to develop a reliable model to analyze PM 10 pollutants in the indoor environment so that building occupants can take relevant preventive measures. This paper focuses on the monitoring and predicting PM 10 pollutant concentration in the indoor environments using the Fuzzy Inference System Tree (FIST) model. The forecasting model was trained using five different input parameters (PM 2.5 , CO 2 , VOC, temperature, and humidity) while considering PM 10 as the target variable. The system performance was measured in terms of four performance indicators where MSE = 1.8126; MAE = 1.1821; MAPE = 4.4372%; RMSE = 1.3463 using normalized data. The model performance was further improved using Particle Swarm Optimization (PSO) and Genetic Algorithm (GA). Results show that the proposed aggregated FIS optimized with GA (RMSE = 1.2101) outperformed the PSO (RMSE = 1.2202) based model in terms of performance indicators. The proposed model can be installed in real-time environments to forecast PM 10 concentration for improved public health and well-being. [ABSTRACT FROM AUTHOR]

Abstract: A time series forecasting is an active research applied significantly in a variety of economics areas. Over the past three decades an auto-regressive integrated moving average (ARIMA) model, as one of the most important time series models, has been applied in financial markets forecasting. Recent researches in time series forecasting ARIMA models indicate some basic limitations which detract from their popularities for financial time series forecasting: One limitation of an ARIMA model is that it requires a large amount of historical data to generate an accurate result. Both theoretical and empirical findings suggest that combining different time series models may be an effective method of improving the predictive performances of data especially when the models in the ensemble are quite different. The main purpose of present paper is to combine the ARIMA model with the particle swarm optimization (PSO) model in order to improve and generate more accurate forecasting results. Under small data information, combining the PSO and ARIMA models performs better performance results compared to an ARIMA model itself. The proposed model is robust and it may be used as an alternative forecasting tool in economics areas. [Copyright &y& Elsevier]

Abstract: This paper presents a new version of fuzzy support vector machine to forecast the nonlinear fuzzy system with multi-dimensional input variables. The input and output variables of the proposed model are described as triangular fuzzy numbers. Then by integrating the triangular fuzzy theory and v-support vector regression machine, the triangular fuzzy v-support vector machine (TFv-SVM) is proposed. To seek the optimal parameters of TFv-SVM, particle swarm optimization is also applied to optimize parameters of TFv-SVM. A forecasting method based on TFv-SVRM and PSO are put forward. The results of the application in sale system forecasts confirm the feasibility and the validity of the forecasting method. Compared with the traditional model, TFv-SVM method requires fewer samples and has better forecasting precision. [Copyright &y& Elsevier]

Abstract: The paper is concerned with practices for tuning the parameters of metaheuristics. Settings such as, e.g., the cooling factor in simulated annealing, may greatly affect a metaheuristic’s efficiency as well as effectiveness in solving a given decision problem. However, procedures for organizing parameter calibration are scarce and commonly limited to particular metaheuristics. We argue that the parameter selection task can appropriately be addressed by means of a data mining based approach. In particular, a hybrid system is devised, which employs regression models to learn suitable parameter values from past moves of a metaheuristic in an online fashion. In order to identify a suitable regression method and, more generally, to demonstrate the feasibility of the proposed approach, a case study of particle swarm optimization is conducted. Empirical results suggest that characteristics of the decision problem as well as search history data indeed embody information that allows suitable parameter values to be determined, and that this type of information can successfully be extracted by means of nonlinear regression models. [Copyright &y& Elsevier]

Abstract: In this paper, we proposed a modified turbulent particle swarm optimization (named MTPSO) method for the temperature prediction and the Taiwan Futures Exchange (TAIFEX) forecasting, based on the two-factor fuzzy time series and particle swarm optimization. The MTPSO model can be dealt with two main factors easily and accurately, which are the lengths of intervals and the content of forecast rules. The experimental results of the temperature prediction and the TAIFEX forecasting show that the proposed model is better than any existing models and it can get better quality solutions based on the high-order fuzzy time series, respectively. [Copyright &y& Elsevier]

Abstract: Forecasting has always been a crucial challenge for organizations as they play an important role in making many critical decisions. Much effort has been devoted over the past several decades to develop and improve the time-series forecasting models. In these models most researchers assumed linear relationship among the past values of the forecast variable. Although the linear assumption makes it easier to manipulate the models mathematically, it can lead to inappropriate representation of many real-world patterns in which non-linear relationship is prevalent. This paper introduces a new time-series forecasting model based on non linear regression which has high flexibility to fit any number of data without pre-assumptions about real patterns of data and its fitness function. To estimate the model parameters, we have used hybrid metaheuristic which has the ability of estimating the optimal value of model parameters. The proposed hybrid approach is simply structured, and comprises two components: a particle swarm optimization (PSO) and a simulated annealing (SA). The hybridization of a PSO with SA, combining the advantages of these two individual components, is the key innovative aspect of the approach. The performance of the proposed method is evaluated using standard test problems and compared with those of related methods in literature, ARIMA and SARIMA models. The results in solving on 11 problems with different structure reveal that the proposed model yields lower errors for these data sets. [Copyright &y& Elsevier]

Abstract: Many forecasting models based on the concept of fuzzy time series have been proposed in the past decades. Two main factors, which are the lengths of intervals and the content of forecast rules, impact the forecasted accuracy of the models. How to find the proper content of the main factors to improve the forecasted accuracy has become an interesting research topic. Some forecasting models, which combined heuristic methods or evolutionary algorithms (such as genetic algorithms and simulated annealing) with the fuzzy time series, have been proposed but their results are not satisfied. In this paper, we use the particle swarm optimization to find the proper content of the main factors. A new hybrid forecasting model which combined particle swarm optimization with fuzzy time series is proposed to improve the forecasted accuracy. The experimental results of forecasting enrollments of students of the University of Alabama show that the new model is better than any existing models, and it can get better quality solutions based on the first-order and the high-order fuzzy time series, respectively. [Copyright &y& Elsevier]

Cloud services have become a popular and flexible solution for providing components to build service-based systems. A component's trustworthiness is a key measure that can guide service requesters when making a service selection decision. Prediction of this trustworthiness, based on the component's multi-faceted quality of service (QoS) attributes, is therefore an important problem to address. In this paper, selective ensemble learning is introduced to address the trust problem for cloud services: We use back-propagation neural networks (BPNNs) as the basic classifiers, with two swarm intelligence algorithms adapted to search for the optimal aggregation weights to create the ensemble: Basic particle swarm optimization (PSO) is used for decimal weights; and quantum discrete PSO (QPSO) is used for binary (0-1) weights. The optimized ensemble learning model, based on BPNNs, is then used to predict the trustworthiness of a given cloud service. Extensive experiments are performed on a well-known, public dataset to verify the effectiveness of the proposed trust prediction algorithms. The experimental results show that our algorithms are not only better than the basic BPNN method in prediction precision, but also outperform current state-of-the-art trust prediction algorithms. The proposed algorithms also exhibit a strong robustness. • A new trustworthiness prediction framework for cloud services is proposed. • An ensemble prediction model is built, combining a subset of potential ANNs. • Two ANN subset selection algorithms, based on two swarm intelligence algorithms, are presented. • Extensive experiments conducted to verify the effectiveness of the proposed algorithms are reported on. [ABSTRACT FROM AUTHOR]