China
Africa
Explore chapters and articles related to this topic
Modeling of Circuit Performances
Published in Wai-Kai Chen, Computer Aided Design and Design Automation, 2018
Sung-Mo Kang, Abhijit Dharchoudhury
Several other performance modeling approaches have been proposed, especially in the context of statistical design of integrated circuits. One such approach is based on self-organizing methods [19] and is called the group method of data handling (GMDH) [20]. An interesting application of GMDH for performance modeling is presented in [21,22]. Another interesting approach is called maximally flat quadratic interpolation (MFQI) [23]. A modeling approach combining the advantages of MFQI and GMDH is presented in [24]. It has been tacitly assumed in the discussion so far that a single RSM is sufficiently accurate to approximate the circuits performances over the entire circuit parameter space. This may not be true for many circuits. In such cases, a piecewise modeling approach may be used advantageously [8]. The circuit parameter space is divided into smaller regions, in each of which a single performance model is adequate. The continuous performance models in the various regions are then stitched together to preserve continuity across the regions.
Estimating bus dwell time: A review of the literature
Published in Transport Reviews, 2023
Soroush Rashidi, Shervin Ataeian, Prakash Ranjitkar
Artificial Intelligence (AI)-based methods and Evolutionary Algorithms (EA) such as Genetic Algorithm (GA), Artificial Neural Networks (ANN), and Support Vector Machine (SVM) have been widely used in the field of transportation engineering (Jian and Wei, 2012; Rashidi et al., 2013b; Ding et al., 2014; Rashidi and Ranjitkar, 2015a; Xin and Chen, 2016; Ataeian et al., 2021). Rashidi et al. (2013b) conducted an evaluation study on BDT estimation methods including nine AI-based methods (Artificial Neural Networks, Multilayer Perceptron Networks, General Regression Neural Networks, Radial Basis Functions Networks, Group Method of Data Handling Polynomial Neural Networks, Cascade Correlation Neural Networks, Support Vector Machine, Gene Expression Programming, Decision Tree, and Tree Boost) and Linear Regression using data from Auckland, New Zealand. The authors compared the AI-based methods and summarised the advantages and disadvantages of each method and their accuracy. The results indicated that white box models (GEP and Decision Tree) perform better than Multiple Linear Regression models and General Regression Neural Network, Tree Boost and Cascade Correlation models can estimate BDT more accurately than other methods.
Discharge coefficient prediction of canal radial gate using neurocomputing models: an investigation of free and submerged flow scenarios
Published in Engineering Applications of Computational Fluid Mechanics, 2022
Hai Tao, Mehdi Jamei, Iman Ahmadianfar, Khaled Mohamed Khedher, Aitazaz Ahsan Farooque, Zaher Mundher Yaseen
Within the focus of the current research, several soft computing models have been introduced to predict the Cd of several types of discharge gates (e.g. weir gate, piano key weir, sluice gate, inclined slide gate, and triangular side orifice) such as an adaptive neuro-fuzzy inference system (Parsaie et al., 2017, 2019), Gaussian process regression (Akbari et al., 2019), random forest (Ghorbani et al., 2020; Salmasi et al., 2021), group method of data handling (Parsaie et al., 2018), deep learning (Ghorbani et al., 2020), genetic programming (Salmasi & Abraham, 2020), locally weighted learning regression (Jamei et al., 2021), gene expression programming (Ebtehaj, Bonakdari, Zaji et al., 2015), artificial neural network (Ebtehaj, Bonakdari, Khoshbin et al., 2015), hybrid inclusive multiple model (Norouzi et al., 2020), extreme learning machine (Zarei et al., 2020), multivariate adoptive regression spline (Yousif et al., 2019), support vector machine (Hu et al., 2021), and several others. Although there have been numerous soft computing models implemented for Cd prediction, there is still a need for studies on new robust ML models.
Early detection of riverine flooding events using the group method of data handling for the Bow River, Alberta, Canada
Published in International Journal of River Basin Management, 2022
Mostafa Elkurdy, Andrew D. Binns, Hossein Bonakdari, Bahram Gharabaghi, Edward McBean
The use of a hybrid forecasting model involving the Group Method of Data Handling (GMDH) to determine the useful input variables when time series forecasting for use alongside a least squares support vector machine (LSSVM) model was investigated by Samsudin et al. (2011) and determined to outperform conventional ANN, ARIMA, GMDH and LSSVM models. Moosavi et al. (2017) developed a model using GMDH to estimate daily runoff quantities, but found more accurate results when discrete wavelet and wavelet packet transforms were used to decompose the original data to their corresponding components. Zaji et al. (2018) applied GMDH combined with the minimum description length (MDL) method to develop a practical and functional model for predicting reservoir water levels which proved to outperform other extensively-used methods in hydrologic applications, such as multilayer perceptron (MLP), extreme learning machine (ELM) and radial basis function (RBF).