Optimal Learning Method Research Articles

The Practical of Interactive Online Learning in the Japanese Language by Using LoiLoNote School Application

This paper introduces a practical example of applying it to language learning based on the author’s experience in the Japanese curriculum at Bina Nusantara University, Indonesia. In 2020, due to the pandemic, it was decided to conduct all classes, and faculty collaboration would be conducted online from Japan. This study proposes a three-year interactive Japanese language learning class, including a face-to- face comparison from February 2021 to February 2023. The approach to classroom practice is only from Japan application presented in this paper. This application, demonstrated in this study, was used in each semester’s classes, and the author found the optimal individual learning method. It should be added that the application was used in grammar and reading classes. The survey results of this study were obtained from two types of surveys, a quantitative survey and a qualitative survey of the students. Students did not find the new learning method as “new” and could use it smoothly. The effectiveness of this application was discussed based on the difference in learning ability and students’ comments after using it. Therefore, this research shows how practical this application is in ensuring interactivity in students’ language learning.

Combining Gradient Optimization and Machine Learning Methods for Inverse Problems in Layered Heterogeneous Media

Combining Gradient Optimization and Machine Learning Methods for Inverse Problems in Layered Heterogeneous Media

Reservoir optimization and machine learning methods

Optimization of storage using neural networks is now commonly achieved by solving a single optimization problem. We first show that this approach allows solving high-dimensional storage problems, but is limited by memory issues. We propose a modification of this algorithm based on the dynamic programming principle and propose neural networks that outperform classical feedforward networks to approximate the Bellman values of the problem. Finally, we study the stochastic linear case and show that Bellman values in storage problems can be accurately approximated using conditional cuts computed by a very recent neural network proposed by the author. This new approximation method combines linear problem solving by a linear programming solver with a neural network approximation of the Bellman values.

Heterogeneous graph construction and node representation learning method of Treatise on Febrile Diseases based on graph convolutional network

ObjectiveTo construct symptom-formula-herb heterogeneous graphs structured Treatise on Febrile Diseases (Shang Han Lun,《伤寒论》) dataset and explore an optimal learning method represented with node attributes based on graph convolutional network (GCN). MethodsClauses that contain symptoms, formulas, and herbs were abstracted from Treatise on Febrile Diseases to construct symptom-formula-herb heterogeneous graphs, which were used to propose a node representation learning method based on GCN − the Traditional Chinese Medicine Graph Convolution Network (TCM-GCN). The symptom-formula, symptom-herb, and formula-herb heterogeneous graphs were processed with the TCM-GCN to realize high-order propagating message passing and neighbor aggregation to obtain new node representation attributes, and thus acquiring the nodes’ sum-aggregations of symptoms, formulas, and herbs to lay a foundation for the downstream tasks of the prediction models. ResultsComparisons among the node representations with multi-hot encoding, non-fusion encoding, and fusion encoding showed that the Precision@10, Recall@10, and F1-score@10 of the fusion encoding were 9.77%, 6.65%, and 8.30%, respectively, higher than those of the non-fusion encoding in the prediction studies of the model. ConclusionNode representations by fusion encoding achieved comparatively ideal results, indicating the TCM-GCN is effective in realizing node-level representations of heterogeneous graph structured Treatise on Febrile Diseases dataset and is able to elevate the performance of the downstream tasks of the diagnosis model.

A structural optimization algorithm with stochastic forces and stresses.

We propose an algorithm for optimizations in which the gradients contain stochastic noise. This arises, for example, in structural optimizations when computations of forces and stresses rely on methods involving Monte Carlo sampling, such as quantum Monte Carlo or neural network states, or are performed on quantum devices that have intrinsic noise. Our proposed algorithm is based on the combination of two ingredients: an update rule derived from the steepest-descent method, and a staged scheduling of the targeted statistical error and step size, with position averaging. We compare it with commonly applied algorithms, including some of the latest machine learning optimization methods, and show that the algorithm consistently performs efficiently and robustly under realistic conditions. Applying this algorithm, we achieve full-degree optimizations in solids using ab initio many-body computations, by auxiliary-field quantum Monte Carlo with plane waves and pseudopotentials. A potential metastable structure in Si is discovered using density-functional calculations with synthetic noisy forces.

Multisensor information fusion method for intelligent fault diagnosis of reciprocating compressor in shale gas development

To address the problems of the poor feature extraction ability and weak data generalization ability of traditional fault diagnosis methods in reciprocating shale gas compressor fault diagnosis applications, in this study, a fault diagnosis method for reciprocating shale gas was developed. This method uses a novel optimized learning method, free energy in persistent contrastive divergence, in deep belief network learning and training. It solves the problem of the deep belief network classification ability degradation in long-term training. The root mean square error is used as the fitness function to search for the optimal parameter combination of the DBN network by using the sparrow search algorithm. At the same time, the learning rate and batch size of the deep belief network, which have a large impact on the training error, are selected for optimization. Then, the original vibration signal is preprocessed by calculating 13 different time domain indicators, and feature-level data and decision-level data are fused in a parallel superposition method to obtain a fused time domain index dataset. Finally, combined with the powerful adaptive feature extraction and nonlinear mapping ability of deep learning, the constructed sample dataset is input to the deep belief network for training, and the deep belief network based on reciprocating shale gas compressor fault diagnosis model is established.

Efficient one-dimensional turbomachinery design method based on transfer learning and Bayesian optimization

Aerodynamic optimization is a powerful approach used in turbomachinery design to shorten design cycles and reduce manual intervention. The design task is to find the optimal design variables with optimal efficiency. However, most design optimization algorithms must start from scratch for each new design task because they cannot reuse previous design experience, in contrast to human experts, who can identify a near-optimal solution based on prior design experience. To address this issue, this paper proposes a transfer optimization learning method for one-dimensional (1D) turbine aerodynamic design. It can transfer the knowledge from the samples accumulated from past design optimizations (source tasks) to accelerate the target design optimization (target task). For each task, a Gaussian process-based surrogate model is established. These models are combined by a probability weighting strategy to build an ensemble model that achieves knowledge transfer. The method is validated on a 1D design case of a single-stage turbine. The results show that, compared with other state-of-the-art optimization algorithms that do not use prior design experience, the proposed method can reduce the computational cost by more than 30% while maintaining the same aerodynamic performance. This paper demonstrates an efficient transfer optimization method for the high-nonlinear 1D turbine design problem.

A novel sowing operation parameter learning optimization method using dataset of sown seeds with similar properties

A learning optimization method used for the pneumatic roller-type seeder was put forward to determine optimal sowing operation parameters of a new type of seed without conducting performance tests. A feedforward neural network structure with two hidden layers were firstly optimized with Genetic Algorithm (GA) to establish predictive relationships among sowing operation parameters and performance indices. Then particle swarm optimization (PSO) was utilized to search the optimal sowing operation parameters for the new type of seed. Sowing data of ten types of seed from previous study with the 2BS-6 pneumatic roller seeder were gathered as dataset of sown seeds. Cosine similarity of seed physical properties was analyzed to extract training datasets for eggplant and mustard. The lowest R-value of 0.85 and the largest MAE value of 4.38 were obtained by regression analysis of the eggplant and mustard predictive model. The smallest R2 of 0.731of optimized sowing performance indices were reported. Optimized fitness values were 83.15% for eggplant and 87.44% for mustard. Fitness value deviations of eggplant and mustard were 6.51% and 1.58% respectively. For eggplant, experimental deviations of single-seeding rate, multi-seeding rate and miss-seeding rate were 2.1%, 2.39% and 0.29% respectively. All experimental deviations of mustard were less than that of eggplant. The study demonstrated high predictive accuracy, strong optimal ability, and promising applicability of the proposed method to determine sowing operation parameters efficiently for the pneumatic roller-type seeder.

Deep Neural Network-Based Prediction and Early Warning of Student Grades and Recommendations for Similar Learning Approaches

Studies reported that if teachers can accurately predict students’ follow-up learning effects via data mining and other means, as per their current performances, and explore the difficulty level of students’ mastery of future-related courses in advance, it will help improve students’ scores in future exams. Although educational data mining and learning analytics have experienced an increase in exploration and use, they are still difficult to precisely define. The usage of deep learning methods to predict academic performances and recommend optimal learning methods has not received considerable attention from researchers. This study aims to predict unknown course grades based on students’ previous learning situations and use clustering algorithms to identify similar learning situations, thereby improving students’ academic performance. In this study, the methods of linear regression, random forest, back-propagation neural network, and deep neural network are compared; the prediction and early warning of students’ academic performances based on deep neural network are proposed, in addition to the improved K-nearest neighbor clustering based on association rules (Pearson correlation coefficient). The algorithm performs a similar category clustering for early-warning students. Using the mean square error, standard deviation, mean absolute percentage error, and prediction of ups-and-downs accuracy as evaluation indicators, the proposed method achieves a steady improvement of 20% in the prediction of ups-and-downs accuracy, and demonstrates improved prediction results when compared under similar conditions.

Real-time physical field reconstruction for nanofluids convection using deep learning with auxiliary tasks

Nanofluids has become one of the most promising cooling fluids due to its great thermophysical properties, especially for microchannels. In recent years, to avoid prohibitively expensive simulations in design process or iterative optimization, massive data-driven and machine learning methods have been employed to construct surrogate models for thermophysical properties or concerned performance characteristics. Though the favorable accuracy is validated, this kind of surrogate models ignore the importance of physical fields, which are also an evaluating criterion in heat transfer design scenarios. In this article, we develop a deep learning framework to achieve the main task of real-time reconstruction mapping from design variables to physical fields. In addition, the auxiliary tasks of prediction mapping from physical fields to performance characteristics are tailored to improve the accuracy and generalization of reconstruction mapping. To validate the feasibility of this framework, we assess the ability of the generator alone to reconstruct physical fields and predict performance characteristics for the flow and heat transfer of nanofluid first. The results show that the introduction of auxiliary task can greatly improve the performance of main task. The computational performance analysis indicates that a well-trained deep learning model with GPU-accelerated has three orders of magnitude faster than CFD solver. This proposed approach was expected to provide a real-time predictor with a reasonable level of accuracy for nanofluid convective heat transfer.

A new active learning approach for adsorbate-substrate structural elucidation in silico.

Adsorbate interactions with substrates (e.g. surfaces and nanoparticles) are fundamental for several technologies, such as functional materials, supramolecular chemistry, and solvent interactions. However, modeling these kinds of systems in silico, such as finding the optimum adsorption geometry and energy, is challenging, due to the huge number of possibilities of assembling the adsorbate on the surface. In the current work, we have developed an artificial intelligence (AI) approach based on an active learning (AL) method for adsorption optimization on the surface of materials. AL uses machine learning (ML) regression algorithms and their uncertainties to make a decision (based on a policy) for the next unexplored structures to be computed, increasing, though, the probability of finding the global minimum with a small number of calculations. The methodology allows an accurate and automated structural elucidation of the adsorbate on the surface, based on the minimization of the total electronic energy. The new AL method for adsorption optimization was developed and implemented in the quantum machine learning software/agent for material design and discovery (QMLMaterial) program and was applied for C60@TiO2 anatase (101). It marks another software extension with a new feature in addition to the automatic structural elucidation of defects in materials and of nanoparticles as well. SCC-DFTB calculations were used to build the complex search surfaces with a reasonably low computational cost. An artificial neural network (NN) was employed in the AL framework evaluated together with two uncertainty quantification methods: K-fold cross-validation and non-parametric bootstrap (BS) resampling. Also, two different acquisition functions for decision-making were used: expected improvement (EI) and the lower confidence bound (LCB).

Optimal Policy of Multiplayer Poker via Actor-Critic Reinforcement Learning

Poker has been considered a challenging problem in both artificial intelligence and game theory because poker is characterized by imperfect information and uncertainty, which are similar to many realistic problems like auctioning, pricing, cyber security, and operations. However, it is not clear that playing an equilibrium policy in multi-player games would be wise so far, and it is infeasible to theoretically validate whether a policy is optimal. Therefore, designing an effective optimal policy learning method has more realistic significance. This paper proposes an optimal policy learning method for multi-player poker games based on Actor-Critic reinforcement learning. Firstly, this paper builds the Actor network to make decisions with imperfect information and the Critic network to evaluate policies with perfect information. Secondly, this paper proposes a novel multi-player poker policy update method: asynchronous policy update algorithm (APU) and dual-network asynchronous policy update algorithm (Dual-APU) for multi-player multi-policy scenarios and multi-player sharing-policy scenarios, respectively. Finally, this paper takes the most popular six-player Texas hold ’em poker to validate the performance of the proposed optimal policy learning method. The experiments demonstrate the policies learned by the proposed methods perform well and gain steadily compared with the existing approaches. In sum, the policy learning methods of imperfect information games based on Actor-Critic reinforcement learning perform well on poker and can be transferred to other imperfect information games. Such training with perfect information and testing with imperfect information models show an effective and explainable approach to learning an approximately optimal policy.

Optimization and Operations Research in Mitigation of a Pandemic

The pandemic of COVID-19 initiated in 2019 and spread all over the world in 2020 has caused significant damages to the human society, making troubles to all aspects of our daily life. Facing the serious outbreak of the virus, we consider possible solutions from the perspectives of both governments and enterprises. Particularly, this paper discusses several applications of supply chain management, public resource allocation, and pandemic prevention using optimization and machine learning methods. Some useful insights in mitigating the pandemic and economy reopening are provided at the end of this paper. These insights might help governments to reduce the severity of the current pandemic and prevent the next round of outbreak. They may also improve companies’ reactions to the increasing uncertainties appearing in the business operations. Although the coronavirus imposes challenges to the entire society at the moment, we are confident to develop new techniques to prevent and eradicate the disease.

Optimal SVM learning method based on adaptive sparse sampling and granularity shift factor

Optimal SVM learning method based on adaptive sparse sampling and granularity shift factor

Simulation of Soil Organic Carbon Content Based on Laboratory Spectrum in the Three-Rivers Source Region of China

Soil organic carbon (SOC) changes affect the land carbon cycle and are also closely related to climate change. Visible-near infrared spectroscopy (Vis-NIRS) has proven to be an effective tool in predicting soil properties. Spectral transformations are necessary to reduce noise and ensemble learning methods can improve the estimation accuracy of SOC. Yet, it is still unclear which is the optimal ensemble learning method exploiting the results of spectral transformations to accurately simulate SOC content changes in the Three-Rivers Source Region of China. In this study, 272 soil samples were collected and used to build the Vis-NIRS simulation models for SOC content. The ensemble learning was conducted by the building of stack models. Sixteen combinations were produced by eight spectral transformations (S-G, LR, MSC, CR, FD, LRFD, MSCFD and CRFD) and two machine learning models of RF and XGBoost. Then, the prediction results of these 16 combinations were used to build the first-step stack models (Stack1, Stack2, Stack3). The next-step stack models (Stack4, Stack5, Stack6) were then made after the input variables were optimized based on the threshold of the feature importance of the first-step stack models (importance > 0.05). The results in this study showed that the stack models method obtained higher accuracy than the single model and transformations method. Among the six stack models, Stack 6 (5 selected combinations + XGBoost) showed the best simulation performance (RMSE = 7.3511, R2 = 0.8963, and RPD = 3.0139, RPIQ = 3.339), and obtained higher accuracy than Stack3 (16 combinations + XGBoost). Overall, our results suggested that the ensemble learning of spectral transformations and simulation models can improve the estimation accuracy of the SOC content. This study can provide useful suggestions for the high-precision estimation of SOC in the alpine ecosystem.

Smoothness and continuity of cost functionals for ECG mismatch computation

The field of cardiac electrophysiology tries to abstract, describe and finally model the electrical characteristics of a heartbeat. With recent advances in cardiac electrophysiology, models have become more powerful and descriptive as ever. However, to advance to the field of inverse electrophysiological modeling, i.e. creating models from electrical measurements such as the ECG, the less investigated field of smoothness of the simulated ECGs w.r.t. model parameters need to be further explored. The present paper discusses smoothness in terms of the whole pipeline which describes how from physiological parameters, we arrive at the simulated ECG. Employing such a pipeline, we create a test-bench of a simplified idealized left ventricle model and demonstrate the most important factors for efficient inverse modeling through smooth cost functionals. Such knowledge will be important for designing and creating inverse models in future optimization and machine learning methods.

A Novel Sowing Operation Parameter Learning Optimization Method Using Dataset of Sown Seeds with Similar Properties

A Novel Sowing Operation Parameter Learning Optimization Method Using Dataset of Sown Seeds with Similar Properties

Evaluating the capability of municipal solid waste separation in China based on AHP-EWM and BP neural network

With the increase in municipal solid waste (MSW), most cities face solid waste management issues. In this study, the analytic hierarchy process (AHP) and artificial neural network (ANN) models were improved to assess the MSW separation capability based on 18 selected indicators of solid waste separation in 15 cities in China. The entropy weight method (EWM) was used in AHP to optimize and determine the indicators and then evaluate their weights, which showed that the general public budget expenditure had the highest weight (0.5239). This implied that the MSW separation capability could be mainly influenced by government financial support. ANN based on scan optimization and machine learning methods were established (R2 = 0.9992) to predict the missing indicators. The mapping relationship between MSW separation indicators and capabilities was also significantly improved from R2 = 0.5317 to R2 = 0.9993, thereby increasing the prediction accuracy of MSW separation capabilities to 95.15%. Thus, this research provides a new avenue for MSW separation and establishes a combined model to predict the separation capability in practical applications.

Unsupervised domain adaptation pedestrian re-identification based on an improved dissimilarity space

Pedestrian re-identification is a key and challenging research topic in intelligent security applications. Because of the need for large-scale manual labeling, pedestrian re-identification methods based on supervised learning cannot be widely used in practical applications. Research on unsupervised pedestrian re-identification has therefore become a hot topic. The DMMD model published in ECCV2020 successfully applied the dissimilarity space to unsupervised pedestrian re-identification. Based on the analysis of the deficiencies of DMMD, a new strong baseline model is composed, an improved dissimilarity space is constructed, a new transfer learning optimization method is proposed, and a time-space-appearance constraint is proposed. The test results show that the R1 accuracy of our model is improved by 21.4% compared with DMMD in the experiment from Market1501 to DukeMTMC.

Resolving Economic Dispatch with Uncertainty Effect in Microgrids Using Hybrid Incremental Particle Swarm Optimization and Deep Learning Method

Microgrids are one example of a low voltage distributed generation pattern that can cover a variety of energy, such as conventional generators and renewable energy. Economic dispatch (ED) is an important function and a key of a power system operation in microgrids. There are several procedures to find the optimum generation. The first step is to find every feasible state (FS) for thermal generator ED. The second step is to find optimum generation based on FS using incremental particle swarm optimization (IPSO), FS is assumed that all units are activated. The third step is to train the input and output of the IPSO into deep learning (DL). And the last step is to compare DL output with IPSO. The microgrids system in this paper considered 10 thermal units and a wind plant with power generation based on probabilistic data. IPSO shows good results by being capable to generate a total generation as the load requirement every hour for 24 h. However, IPSO has a weakness in execution times, from 10 experiments the average IPSO process takes 30 min. DL based on IPSO can make the execution time of its ED function faster with an 11 input and 10 output architecture. From the same experiments with IPSO, DL can produce the same output as IPSO but with a faster execution time. From the total cost side, wind energy is affecting to reduce total cost until USD 22.86 million from IPSO and USD 22.89 million from DL.