Maskless Preparation of Spatially-Resolved Plasmonic Nanoparticles on Polydimethylsiloxane via In Situ Fluoride-Assisted Synthesis

Here, a fluoride-assisted route for the controlled in-situ synthesis of metal nanoparticles (NPs) (i.e., AgNPs, AuNPs) on polydimethylsiloxane (PDMS) is reported. The size and coverage of the NPs on the PDMS surface are modulated with time and over space during the synthetic process, leveraging the improved yield (10×) and faster kinetics (100×) of NP formation in the presence of F⁻ ions, compared to fluoride-free approaches. This enables the maskless preparation of both linear and step gradients and patterns of NPs in 1D and 2D on the PDMS surface. As an application in flexible plasmonics/photonics, continuous and step-wise spatial modulations of the plasmonic features of PDMS slabs with 1D and 2D AgNP gradients on the surface are demonstrated. An excellent spatially resolved tuning of key optical parameters, namely, optical density from zero to 5 and extinction ratio up to 100 dB, is achieved with AgNP gradients prepared in AgF solution for 12 minutes; the performance are comparable to those of commercial dielectric/interference filters. When used as a rejection filter in optical fluorescence microscopy, the AgNP-PDMS slabs are able to reject the excitation laser at 405 nm and retain the green fluorescence of microbeads (100 µm) used as test cases.     

Identifying catalyst layer compositions of proton exchange membrane fuel cells through machine-learning-based approach

Membrane electrode assembly (MEA) is considered a key component of a proton exchange membrane fuel cell (PEMFC). However, developing a new MEA to meet desired properties, such as operation under low-humidity conditions without a humidifier, is a time- and cost-consuming process. This study employs a machine-learning-based approach using K-nearest neighbor (KNN) and neural networks (NN) in the MEA development process by identifying a suitable catalyst layer (CL) recipe in MEA. Minimum redundancy maximum relevance and principal component analysis were implemented to specify the most important predictor and reduce the data dimension. The number of predictors was found to play an essential role in the accuracy of the KNN and NN models although the predictors have self-correlations. The KNN model with a K of 7 was found to minimize the model loss with a loss of 11.9%. The NN model constructed by three corresponding hidden layers with nine, eight, and nine nodes can achieve the lowest error of 0.1293 for the Pt catalyst and 0.031 for PVA as a good additive blending in the CL of the MEA. However, even if the error is low, the prediction of PVA seems to be inaccurate, regardless of the model structure. Therefore, the KNN model is more appropriate for CL recipe prediction.     

Neural network-based flight control systems: Present and future

As the first review in this field, this paper presents an in-depth mathematical view of Intelligent Flight Control Systems (IFCSs), particularly those based on artificial neural networks. The rapid evolution of IFCSs in the last two decades in both the methodological and technical aspects necessitates a comprehensive view of them to better demonstrate the current stage and the crucial remaining steps towards developing a truly intelligent flight management unit. To this end, in this paper, we will provide a detailed mathematical view of Neural Network (NN)-based flight control systems and the challenging problems that still remain. The paper will cover both the model-based and model-free IFCSs. The model-based methods consist of the basic feedback error learning scheme, the pseudocontrol strategy, and the neural backstepping method. Besides, different approaches to analyze the closed-loop stability in IFCSs, their requirements, and their limitations will be discussed in detail. Various supplementary features, which can be integrated with a basic IFCS such as the fault-tolerance capability, the consideration of system constraints, and the combination of NNs with other robust and adaptive elements like disturbance observers, would be covered, as well. On the other hand, concerning model-free flight controllers, both the indirect and direct adaptive control systems including indirect adaptive control using NN-based system identification, the approximate dynamic programming using NN, and the reinforcement learning-based adaptive optimal control will be carefully addressed. Finally, by demonstrating a well-organized view of the current stage in the development of IFCSs, the challenging issues, which are critical to be addressed in the future, are thoroughly identified. As a result, this paper can be considered as a comprehensive road map for all researchers interested in the design and development of intelligent control systems, particularly in the field of aerospace applications.     

Deep reinforcement learning-based cooperative interactions among heterogeneous vehicular networks

Most real-world vehicle nodes can be structured into an interconnected network of vehicles. Through structuring these services and vehicle device interactions into multiple types, such internet of vehicles becomes multidimensional heterogeneous overlay networks. The heterogeneousness of the overlays makes it difficult for the overlay networks to coordinate with each other to improve their performance. Therefore, it poses an interesting but critical challenge to the effective analysis of heterogeneous virtual vehicular networks. A variety of virtual vehicular networks can be easily deployed onto the native network by applying the concept of SDN (Software Defined Networking). These virtual networks reflect their heterogeneousness due to their different performance goals, and they compete for the same physical resources of the underlying network, so that a sub-optimal performance of the virtual networks may be achieved. Therefore, we propose a Deep Reinforcement Learning (DRL) approach to make the virtual networks cooperate with each other through the SDN controller. A cooperative solution based on the asymmetric Nash bargaining is proposed for co-existing virtual networks to improve their performance. Moreover, the Markov Chain model and DRL resolution are introduced to leverage the heterogeneous performance goals of virtual networks. The implementation of the approach is introduced, and simulation results confirm the performance improvement of the latency sensitive, loss-rate sensitive and throughput sensitive heterogeneous vehicular networks using our cooperative solution.     

Supporting primary students' learning of fraction conceptual knowledge through digital games

With the advent of mobile technologies, well-designed fraction apps can be used to help children gain fraction knowledge, a challenging topic for both teachers and students. The present pilot study adopted a quasi-experimental design to investigate whether children can learn fraction concepts equally well if half of the lesson time (20 min) is replaced with game-based learning. Keeping the total lesson time (40 min) identical, the control group (N = 33) received traditional instruction, and the experimental group (N = 32) was presented with a blended learning approach spending half of the class time (20 min) playing tablet-based fraction games, where each of the learners had their own tablet. The results suggested that in the posttest, the experimental group achieved similar learning gains to the control group and appear to have achieved better performance in the transfer test than the control group. This paper also discusses the efficiency of game-based learning, the mechanism of how fraction games might enhance learning, and the potential of integrating game-based learning in educational settings.     

Event-triggered variable horizon Supervisory Predictive control of hybrid power plants

The supervision of a hybrid power plant, including solar panels, a gas microturbine and a storage unit operating under varying solar power profiles is considered. The Economic Supervisory Predictive controller assigns the power references to the controlled subsystems of the hybrid cell using a financial criterion. A prediction of the renewable sources power is embedded into the supervisor. Results deteriorate when the solar power is unsteady, owing to the inaccuracy of the predictions for a long-range horizon of 10 s. The receding horizon is switched between an upper and a lower value according to the amplitude of the solar power trend. Theoretical results show the relevance of horizon switching, according to a tradeoff between performance and prediction accuracy. Experimental results, obtained in a Hardware In the Loop (HIL) framework, show the relevance of the variable horizon approach. Power amplifiers allow us to simulate virtual components, such as a gas microturbine, and to blend their powers with that of real devices (storage unit, real solar panels). In this case, fuel savings, reaching 15%, obtained under unsteady operating conditions lead to a better overall performance of the hybrid cell. The overall savings obtained in the experiments amount to 12%.     

A new reverse reduce-error ensemble pruning algorithm

Although greedy algorithms possess high efficiency, they often receive suboptimal solutions of the ensemble pruning problem, since their exploration areas are limited in large extent. And another marked defect of almost all the currently existing ensemble pruning algorithms, including greedy ones, consists in: they simply abandon all of the classifiers which fail in the competition of ensemble selection, causing a considerable waste of useful resources and information. Inspired by these observations, an interesting greedy Reverse Reduce-Error (RRE) pruning algorithm incorporated with the operation of subtraction is proposed in this work. The RRE algorithm makes the best of the defeated candidate networks in a way that, the Worst Single Model (WSM) is chosen, and then, its votes are subtracted from the votes made by those selected components within the pruned ensemble. The reason is because, for most cases, the WSM might make mistakes in its estimation for the test samples. And, different from the classical RE, the near-optimal solution is produced based on the pruned error of all the available sequential subensembles. Besides, the backfitting step of RE algorithm is replaced with the selection step of a WSM in RRE. Moreover, the problem of ties might be solved more naturally with RRE. Finally, soft voting approach is employed in the testing to RRE algorithm. The performances of RE and RRE algorithms, and two baseline methods, i.e., the method which selects the Best Single Model (BSM) in the initial ensemble, and the method which retains all member networks of the initial ensemble (ALL), are evaluated on seven benchmark classification tasks under different initial ensemble setups. The results of the empirical investigation show the superiority of RRE over the other three ensemble pruning algorithms.     

Evolutionary collective behavior decomposition model for time series data mining

In this research, we propose a novel framework referred to as collective game behavior decomposition where complex collective behavior is assumed to be generated by aggregation of several groups of agents following different strategies and complexity emerges from collaboration and competition of individuals. The strategy of an agent is modeled by certain simple game theory models with limited information. Genetic algorithms are used to obtain the optimal collective behavior decomposition based on history data. The trained model can be used for collective behavior prediction. For modeling individual behavior, two simple games, the minority game and mixed game are investigated in experiments on the real-world stock prices and foreign-exchange rate. Experimental results are presented to show the effectiveness of the new proposed model.