Search results

This paper aims to Solar photovoltaic (PV) power can significantly impact the power system because of its intermittent nature. Hence, an accurate solar PV power forecasting model is required for appropriate power system planning.

In this paper, a long short-term memory (LSTM)-based double deep Q-learning (DDQL) neural network (NN) is proposed for forecasting solar PV power indirectly over the long-term horizon. The past solar irradiance, temperature and wind speed are used for forecasting the solar PV power for a place using the proposed forecasting model.

The LSTM-based DDQL NN reduces over- and underestimation and avoids gradient vanishing. Thus, the proposed model improves the forecasting accuracy of solar PV power using deep learning techniques (DLTs). In addition, the proposed model requires less training time and forecasts solar PV power with improved stability.

The proposed model is trained and validated for several places with different climatic patterns and seasons. The proposed model is also tested for a place with a temperate climatic pattern by constructing an experimental solar PV system. The training, validation and testing results have confirmed the practicality of the proposed solar PV power forecasting model using LSTM-based DDQL NN.

The purpose of this paper is mainly to develop the adjoint method within the method of magnetic moment (MMM) and thus, to provide an efficient new way to solve topology optimization problems in magnetostatic to design 3D-magnetic circuits.

First, the MMM is recalled and the optimization design problem is reformulated as a partial derivative equation-constrained optimization problem where the constraint is the Maxwell equation in magnetostatic. From the Karush–Khun–Tucker optimality conditions, a new problem is derived which depends on a Lagrangian parameter. This problem is called the adjoint problem and the Lagrangian parameter is called the adjoint parameter. Thus, solving the direct and the adjoint problems, the values of the objective function as well as its gradient can be efficiently obtained. To obtain a topology optimization code, a semi isotropic material with penalization (SIMP) relaxed-penalization approach associated with an optimization based on gradient descent steps has been developed and used.

In this paper, the authors provide theoretical results which make it possible to compute the gradient via the continuous adjoint of the MMMs. A code was developed and it was validated by comparing it with a finite difference method. Thus, a topology optimization code associating this adjoint based gradient computations and SIMP penalization technique was developed and its efficiency was shown by solving a 3D design problem in magnetostatic.

This research is limited to the design of systems in magnetostatic using the linearity of the materials. The simple examples, the authors provided, are just done to validate our theoretical results and some extensions of our topology optimization code have to be done to solve more interesting design cases.

The problem of design is a 3D magnetic circuit. The 2D optimization problems are well known and several methods of resolution have been introduced, but rare are the problems using the adjoint method in 3D. Moreover, the association with the MMMs has never been treated yet. The authors show in this paper that this association could provide gains in CPU time.

This study aims to propose novel edge device-tailored federated learning algorithms of local classifiers (stochastic gradient descent, support vector machines), namely, FL-lSGD and FL-lSVM. These algorithms are designed to address the challenge of large-scale ImageNet classification.

The authors’ FL-lSGD and FL-lSVM trains in a parallel and incremental manner to build an ensemble local classifier on Raspberry Pis without requiring data exchange. The algorithms load small data blocks of the local training subset stored on the Raspberry Pi sequentially to train the local classifiers. The data block is split into k partitions using the k-means algorithm, and models are trained in parallel on each data partition to enable local data classification.

Empirical test results on the ImageNet data set show that the authors’ FL-lSGD and FL-lSVM algorithms with 4 Raspberry Pis (Quad core Cortex-A72, ARM v8, 64-bit SoC @ 1.5GHz, 4GB RAM) are faster than the state-of-the-art LIBLINEAR algorithm run on a PC (Intel(R) Core i7-4790 CPU, 3.6 GHz, 4 cores, 32GB RAM).

Efficiently addressing the challenge of large-scale ImageNet classification, the authors’ novel federated learning algorithms of local classifiers have been tailored to work on the Raspberry Pi. These algorithms can handle 1,281,167 images and 1,000 classes effectively.

To improve the position tracking efficiency of the upper-limb rehabilitation robot for stroke hemiplegia patients, the optimization Learning rate of the membership function based on the fuzzy impedance controller of the rehabilitation robot is propose.

First, the impaired limb’s damping and stiffness parameters for evaluating its physical recovery condition are online estimated by using weighted least squares method based on recursive algorithm. Second, the fuzzy impedance control with the rule has been designed with the optimal impedance parameters. Finally, the membership function learning rate online optimization strategy based on Takagi-Sugeno (TS) fuzzy impedance model was proposed to improve the position tracking speed of fuzzy impedance control.

This method provides a solution for improving the membership function learning rate of the fuzzy impedance controller of the upper limb rehabilitation robot. Compared with traditional TS fuzzy impedance controller in position control, the improved TS fuzzy impedance controller has reduced the overshoot stability time by 0.025 s, and the position error caused by simulating the thrust interference of the impaired limb has been reduced by 8.4%. This fact is verified by simulation and test.

The TS fuzzy impedance controller based on membership function online optimization learning strategy can effectively optimize control parameters and improve the position tracking speed of upper limb rehabilitation robots. This controller improves the auxiliary rehabilitation efficiency of the upper limb rehabilitation robot and ensures the stability of auxiliary rehabilitation training.

The purpose of this paper is to present a new approach to optimizing the design of 3D magnetic circuits. This approach is based on topology optimization, where derivative calculations are performed using the continuous adjoint method. Thus, the continuous adjoint method for magnetostatics has to be developed in 3D and has to be combined with penalization, filtering and homotopy approaches to provide an efficient optimization code.

To provide this new topology optimization code, this study starts from 2D magnetostatic results to perform the sensitivity analysis, and this approach is extended to 3D. From this sensitivity analysis, the continuous adjoint method is derived to compute the gradient of an objective function of a 3D topological optimization design problem. From this result, this design problem is discretized and can then be solved by finite element software. Thus, by adding the solid isotropic material with penalization (SIMP) penalization approach and developing a homotopy-based optimization algorithm, an interesting means for designing 3D magnetic circuits is provided.

In this paper, the 3D continuous adjoint method for magnetostatic problems involving an objective least-squares function is presented. Based on 2D results, new theoretical results for developing sensitivity analysis in 3D taking into account different parameters including the ferromagnetic material, the current density and the magnetization are provided. Then, by discretizing, filtering and penalizing using SIMP approaches, a topology optimization code has been derived to address only the ferromagnetic material parameters. Based on this efficient gradient computation method, a homotopy-based optimization algorithm for solving large-scale 3D design problems is developed.

In this paper, an approach based on topology optimization to solve 3D magnetostatic design problems when an objective least-squares function is involved is proposed. This approach is based on the continuous adjoint method derived for 3D magnetostatic design problems. The effectiveness of this topology optimization code is demonstrated by solving the design of a 3D magnetic circuit with up to 100,000 design variables.

The purpose of this study is to compare the prediction models for half-cell potential (HCP) of RCC slabs cathodically protected using pure magnesium anodes and subjected to chloride ingress.The models for HCP using 1,134 data set values based on experimentation are developed and compared using ANFIS, artificial neural network (ANN) and integrated ANN-GA algorithms.

In this study, RCC slabs, 1000 mm × 1000 mm × 100 mm were cast. Five slabs were cast with 3.5% NaCl by weight of cement, and five more were cast without NaCl. The distance of the point under consideration from the anode in the x- and y-axes, temperature, relative humidity and age of the slab in days were the input parameters, while the HCP values with reference to the Standard Calomel Electrode were the output. Experimental values consisting of 80 HCP values per slab per day were collected for 270 days and were averaged for both cases to generate the prediction model.

In this study, the premise and consequent parameters are trained, validated and tested using ANFIS, ANN and by using ANN as fitness function of GA. The MAPE, RMSE and MAE of the ANFIS model were 24.57, 1702.601 and 871.762, respectively. Amongst the ANN algorithms, Levenberg−Marquardt (LM) algorithm outperforms the other methods, with an overall R-value of 0.983. GA with ANN as the objective function proves to be the best means for the development of prediction model.

Based on the original experimental values, the performance of ANFIS, ANN and GA with ANN as objective function provides excellent results.

The Chinese housing market has gone through rapid growth during the past decade, and house price forecasting has evolved to be a significant issue that draws enormous attention from investors, policy makers and researchers. This study investigates neural networks for composite property price index forecasting from ten major Chinese cities for the period of July 2005–April 2021.

The goal is to build simple and accurate neural network models that contribute to pure technical forecasts of composite property prices. To facilitate the analysis, the authors consider different model settings across algorithms, delays, hidden neurons and data spitting ratios.

The authors arrive at a pretty simple neural network with six delays and three hidden neurons, which generates rather stable performance of average relative root mean square errors across the ten cities below 1% for the training, validation and testing phases.

Results here could be utilized on a standalone basis or combined with fundamental forecasts to help form perspectives of composite property price trends and conduct policy analysis.

The Chinese housing market has witnessed rapid growth during the past decade and the significance of housing price forecasting has undoubtedly elevated, becoming an important issue to investors and policymakers. This study aims to examine neural networks (NNs) for office property price index forecasting from 10 major Chinese cities for July 2005–April 2021.

The authors aim at building simple and accurate NNs to contribute to pure technical forecasts of the Chinese office property market. To facilitate the analysis, the authors explore different model settings over algorithms, delays, hidden neurons and data-spitting ratios.

The authors reach a simple NN with three delays and three hidden neurons, which leads to stable performance of about 1.45% average relative root mean square error across the 10 cities for the training, validation and testing phases.

The results could be used on a standalone basis or combined with fundamental forecasts to form perspectives of office property price trends and conduct policy analysis.

For policymakers and participants of financial markets, predictions of trading volumes of financial indices are important issues. This study aims to address such a prediction problem based on the CSI300 nearby futures by using high-frequency data recorded each minute from the launch date of the futures to roughly two years after constituent stocks of the futures all becoming shortable, a time period witnessing significantly increased trading activities.

In order to answer questions as follows, this study adopts the neural network for modeling the irregular trading volume series of the CSI300 nearby futures: are the research able to utilize the lags of the trading volume series to make predictions; if this is the case, how far can the predictions go and how accurate can the predictions be; can this research use predictive information from trading volumes of the CSI300 spot and first distant futures for improving prediction accuracy and what is the corresponding magnitude; how sophisticated is the model; and how robust are its predictions?

The results of this study show that a simple neural network model could be constructed with 10 hidden neurons to robustly predict the trading volume of the CSI300 nearby futures using 1–20 min ahead trading volume data. The model leads to the root mean square error of about 955 contracts. Utilizing additional predictive information from trading volumes of the CSI300 spot and first distant futures could further benefit prediction accuracy and the magnitude of improvements is about 1–2%. This benefit is particularly significant when the trading volume of the CSI300 nearby futures is close to be zero. Another benefit, at the cost of the model becoming slightly more sophisticated with more hidden neurons, is that predictions could be generated through 1–30 min ahead trading volume data.

The results of this study could be used for multiple purposes, including designing financial index trading systems and platforms, monitoring systematic financial risks and building financial index price forecasting.

In the era of artificial intelligence (AI), algorithms have gained unprecedented importance. Scientific studies have shown that algorithms are frequently mentioned in papers, making mention frequency a classical indicator of their popularity and influence. However, contemporary methods for evaluating influence tend to focus solely on individual algorithms, disregarding the collective impact resulting from the interconnectedness of these algorithms, which can provide a new way to reveal their roles and importance within algorithm clusters. This paper aims to build the co-occurrence network of algorithms in the natural language processing field based on the full-text content of academic papers and analyze the academic influence of algorithms in the group based on the features of the network.

We use deep learning models to extract algorithm entities from articles and construct the whole, cumulative and annual co-occurrence networks. We first analyze the characteristics of algorithm networks and then use various centrality metrics to obtain the score and ranking of group influence for each algorithm in the whole domain and each year. Finally, we analyze the influence evolution of different representative algorithms.

The results indicate that algorithm networks also have the characteristics of complex networks, with tight connections between nodes developing over approximately four decades. For different algorithms, algorithms that are classic, high-performing and appear at the junctions of different eras can possess high popularity, control, central position and balanced influence in the network. As an algorithm gradually diminishes its sway within the group, it typically loses its core position first, followed by a dwindling association with other algorithms.

To the best of the authors’ knowledge, this paper is the first large-scale analysis of algorithm networks. The extensive temporal coverage, spanning over four decades of academic publications, ensures the depth and integrity of the network. Our results serve as a cornerstone for constructing multifaceted networks interlinking algorithms, scholars and tasks, facilitating future exploration of their scientific roles and semantic relations.