Article
Computer Science, Artificial Intelligence
Salihu A. Abdulkarim, Andries P. Engelbrecht
Summary: Several studies have applied particle swarm optimization algorithms to train neural networks for time series forecasting, with good performance results. This study introduces a dynamic PSO algorithm for training NNs in forecasting non-stationary time series, outperforming standard PSO and Rprop algorithms. These findings suggest the potential of dynamic PSO in real-world forecasting applications.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Naresh Kumar, Seba Susan
Summary: The study optimizes the hyperparameters of fuzzy time series forecasting for the COVID-19 pandemic using Particle Swarm Optimization, proposing nested FTS-PSO and exhaustive search FTS-PSO techniques. The exhaustive search FTS-PSO outperformed all methods in forecasting coronavirus confirmed cases, demonstrating its effectiveness in achieving optimal hyperparameter values.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Artificial Intelligence
Erol Egrioglu, Eren Bas
Summary: A new hybrid recurrent artificial neural network is proposed for nonlinear time series forecasting in this study. The network combines simple exponential smoothing and a single multiplicative neuron model to solve the insufficiency of classical forecasting methods in forecasting nonlinear and complex time series structures. The proposed method outperforms other artificial neural networks in terms of performance.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Shivani Pant, Sanjay Kumar
Summary: This study proposes a novel computational fuzzy time series forecasting method based on intuitionistic fuzzy sets and self-organized direction aware clustering. The method shows good performance in forecasting accuracy with optimized weights using grey wolf optimization, applied to predict enrolments of the University of Alabama and market price of SBI share at Bombay stock exchange.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Computer Science, Artificial Intelligence
Xinghan Xu, Weijie Ren
Summary: This paper proposes a hybrid model using stacked autoencoder and modified particle swarm optimization for multivariate chaotic time series forecasting. Experimental results show that the hybrid model performs well on multiple datasets.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Arun Kumar, Tanya Chauhan, Srinivasan Natesan, Nhat Truong Pham, Ngoc Duy Nguyen, Chee Peng Lim
Summary: In this study, we propose an efficient machine learning model for financial time series forecasting through carefully designed feature extraction, elimination, and selection strategies. We leverage a binary particle swarm optimization algorithm to select the appropriate features and propose new evaluation metrics for better performance assessment in handling financial time series data. Our proposed model outperforms several existing methods in benchmark studies, confirming its effectiveness.
Article
Automation & Control Systems
Yu An, Di Wang, Lili Chen, Xi Zhang
Summary: Analysis of complex data structures in the form of matrix or tensor format data has gained immense popularity in diverse fields. However, forecasting time series based on high-order historical tensor data presents significant challenges. This paper proposes a Tensor-variate method with Compressed Parameters in Auto-Regressive Moving Average (TCP-ARMA) model for time series forecasting, which integrates a smoothed mean and a tensor-variate autoregressive moving average (ARMA) model with a parameter reduction technique. The proposed method captures the global trend within each dimension of tensors as well as the time-dimension by a tensor-based smoothed mean.
IEEE TRANSACTIONS ON AUTOMATION SCIENCE AND ENGINEERING
(2023)
Article
Automation & Control Systems
Eren Bas, Erol Egrioglu, Emine Kolemen
Summary: Intuitionistic fuzzy time series forecasting methods use both membership and non-membership values as auxiliary variables, providing more information compared to traditional fuzzy time series models. This study proposes a novel intuitionistic fuzzy time series method and applies it to stock exchange time series, achieving more accurate forecasts than established benchmarks.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Economics
Eren Bas, Erol Egrioglu, Taner Tunc
Summary: This study defines a high order multivariate picture fuzzy time series forecasting model and introduces a forecasting algorithm based on this model. The proposed method uses picture fuzzy clustering and Pi-Sigma artificial neural networks for modeling and estimation, achieving better forecasting results than established benchmarks.
COMPUTATIONAL ECONOMICS
(2023)
Article
Computer Science, Artificial Intelligence
Yaoguo Dang, Yifan Zhang, Junjie Wang
Summary: To address the problem of the grey multivariate prediction model's inability to accurately simulate systems with periodic oscillations, a novel multivariate grey model named the GM(1,N|sin) power model is proposed. This model incorporates a power exponential term and dynamic sinusoidal function to represent the nonlinear relationship and periodic oscillations of the independent and dependent variables, respectively. Through case studies on electricity consumption and PM2.5 concentrations, the GM(1,N|sin) power model outperforms alternative models in accurately predicting time series with periodic oscillations.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Pritpal Singh
Summary: The study proposed an improved quantum optimization algorithm to address the issues of universe of discourse selection and fuzzy degree determination in fuzzy time series models. By integrating this algorithm with the FTS modeling approach, a hybrid model called FQTSFM was developed, which shows fast convergence and accurate forecasting results.
INFORMATION SCIENCES
(2021)
Article
Computer Science, Artificial Intelligence
Yue Yin, Yehua Sheng, Jiarui Qin
Summary: This study proposes a new fuzzy time-series (FTS) prediction model, IT2-FCM-FTS, which utilizes the interval type-2 (IT2) FCM algorithm to enhance model performance. Experimental results demonstrate that the proposed model achieves superior prediction accuracy compared to the traditional ARIMA model and the FCM-based model.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Gourav Kumar, Uday Pratap Singh, Sanjeev Jain
Summary: This paper proposes a hybrid evolutionary intelligent system for predicting the future close price of stock market, comparing its forecasting efficiency with other methods, and showing superior accuracy.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2021)
Article
Economics
Hao Wu, Haiming Long, Yue Wang, Yanqi Wang
Summary: This paper introduces a new fuzzy time series forecasting model based on technical analysis, AP clustering, and SVR model, which outperforms some classic models on stock index datasets.
JOURNAL OF FORECASTING
(2021)
Article
Economics
Ayse Yilmaz, Ufuk Yolcu
Summary: Different types of artificial neural networks are widely used in time-series forecasting, with some using additive aggregation functions and others using multiplicative aggregation functions in neuron models. The study focuses on utilizing the dendritic neuron model neural network (DNM-NN) for forecasting, trained by a modified particle swarm optimization to improve accuracy. Evaluation is done using the Taiwan Stock Exchange Capitalization Weighted Stock Index (TAIEX).
JOURNAL OF FORECASTING
(2022)
Article
Computer Science, Artificial Intelligence
Ufuk Yolcu, Erol Egrioglu, Eren Bas, Ozge Cagcag Yolcu, Ali Zafer Dalar
Summary: The study proposed a method for forecasting both linear and nonlinear components in time series, and conducted a series of hypothesis tests. By comparing with different conventional methods, it was found that the proposed method performed well overall.
JOURNAL OF EXPERIMENTAL & THEORETICAL ARTIFICIAL INTELLIGENCE
(2021)
Article
Computer Science, Artificial Intelligence
Cem Kocak, Ali Zafer Dalar, Ozge Cagcag Yolcu, Eren Bas, Erol Egrioglu
Article
Mathematics, Applied
Eren Bas, Ufuk Yolcu, Erol Egrioglu
JOURNAL OF COMPUTATIONAL AND APPLIED MATHEMATICS
(2020)
Editorial Material
Computer Science, Artificial Intelligence
Mu-Yen Chen, Hsiu-Sen Chiang, Edwin Lughofer, Erol Egrioglu
Article
Computer Science, Hardware & Architecture
Cem Kocak, Erol Egrioglu, Eren Bas
Summary: This paper introduces a new intuitionistic fuzzy time series forecasting method based on LSTM, which merges membership and non-membership values as inputs to the LSTM model using a minimum operator, thereby achieving a high-order IFTS model.
JOURNAL OF SUPERCOMPUTING
(2021)
Article
Oncology
Yilmaz Ba, Nermin Koc, Kaan Helvac, Cem Kocak, Rasit Akdeniz, Havva Hande Keser Sahin
Summary: This study investigated the expression of PD-1 and PD-L1 in high grade serous ovarian cancer and their relationship with tumor infiltrating lymphocytes and prognosis. High PD-L1 staining ratio was associated with lower survival, and there was a significant correlation between high PD-1 scores and cases with PD-L1 expression >= 5%. Cases with higher PD-L1 positive stromal TIL score had lower survival rates.
TRANSLATIONAL ONCOLOGY
(2021)
Article
Computer Science, Artificial Intelligence
Ozge Cagcag Yolcu, Erol Egrioglu, Eren Bas, Ufuk Yolcu
Summary: This study presents a multivariate intuitionistic fuzzy time-series definition and its prediction models, as well as a multivariate intuitionistic fuzzy inference system (M-IFIS). It introduces the use of Sigma-pi neural network as an inference tool and demonstrates the superior predictive accuracy of M-IFIS compared to other methods. The article contributes to the literature by providing a novel analysis mechanism for multivariate intuitionistic fuzzy time series.
APPLIED SOFT COMPUTING
(2022)
Article
Economics
Eren Bas, Erol Egrioglu, Taner Tunc
Summary: This study defines a high order multivariate picture fuzzy time series forecasting model and introduces a forecasting algorithm based on this model. The proposed method uses picture fuzzy clustering and Pi-Sigma artificial neural networks for modeling and estimation, achieving better forecasting results than established benchmarks.
COMPUTATIONAL ECONOMICS
(2023)
Article
Automation & Control Systems
Eren Bas, Erol Egrioglu, Emine Kolemen
Summary: Intuitionistic fuzzy time series forecasting methods use both membership and non-membership values as auxiliary variables, providing more information compared to traditional fuzzy time series models. This study proposes a novel intuitionistic fuzzy time series method and applies it to stock exchange time series, achieving more accurate forecasts than established benchmarks.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2022)
Article
Computer Science, Hardware & Architecture
Erol Egrioglu, Crina Grosan, Eren Bas
Summary: In this study, a new genetic algorithm with a statistical-based chromosome replacement strategy is proposed and applied in the training process of a multiplicative neuron model artificial neural network. Results show that this algorithm outperforms other artificial intelligence optimization methods in time-series prediction tasks.
JOURNAL OF SUPERCOMPUTING
(2023)
Article
Engineering, Geological
C. Gokceoglu, C. Bal, C. H. Aladag
Summary: Prediction of tunnel boring machine (TBM) performance is still a challenging research subject. In this study, geological and geotechnical parameters were used to predict TBM performance. The random forest algorithm showed superior performance compared to other methods.
GEOTECHNICAL AND GEOLOGICAL ENGINEERING
(2023)
Article
Multidisciplinary Sciences
Eren Bas, Erol Egrioglu, Ufuk Yolcu
Summary: Exponential smoothing methods are powerful forecasting techniques, with the Holt method being particularly effective for time series with trends. This study modifies the Holt method by using time-varying smoothing parameters obtained from autoregressive models, estimated with a harmony search algorithm and bootstrap approach. The proposed method shows improved forecasting performance on real-world time series.
Article
Education & Educational Research
Ayhan Babaroglu, Cem Kocak
EDUCATION RESEARCH INTERNATIONAL
(2020)