Search

The utilization of a Memristor in a chaotic circuit paves the way for random number generation. Across other research, authors detected, through simulation tools, the presence of monofractal/multifractal behavior of a memristorbased random number generation. Despite the novelty of the finding, the logical step to follow requires the hardware implementation of the memristor and the chaotic circuit that uses it to investigate the details, limitations, and difficulties not contemplated in the advanced simulations. In light of this objective, this article systematically reviews five memristor emulator circuits, comparing them in terms of cost and frequency of operation. This study proposes a memristor emulator circuit that uses a wave rectifier based on operational amplifiers as a nonlinear element. This memristor and a corresponding reference unit were utilized in a hardware implementation of a chaotic Chua-based circuit. The modifications that are made in conjunction with the measurements made in the laboratory provide evidence that the chaotic system obtained satisfies the essential conditions to be used in a future generator otherwise implemented in hardware that exhibits monofractal/multifractal behavior. [ABSTRACT FROM AUTHOR]

Metaheuristic algorithms are particularly useful for maximum power point tracking (MPPT) applications, because they can adapt to changes in operating conditions and effectively handle partial shading conditions. However, metaheuristic algorithms also have some limitations that need to be addressed to make them suitable for MPPT applications. The problems associated with metaheuristic algorithm-based MPPT applications include being trapped in local optima, slow convergence speed, shading condition variability, computational complexity and robustness. These problems lead to reduced efficiency in MPPT applications. In the literature, the solution of the aforementioned problems is partially addressed and some of them are solved via an additional irradiation sensor. The motivation of this study is to develop a control algorithm that covers all problems that have been partially solved in the literature and includes an original re-initialization modeling method in accordance with visual programing concept, without using any additional radiation sensor. The proposed control algorithm has the flexibility to be easily adapted to other metaheuristic algorithms and does not require any radiation sensors. The re-initialization model created via Matlab/Simulink and "Embedded Coder Support Package for TI C2000 Processors" allows easy tracking of the global maximum power point (GMPP) by detecting variable radiation conditions. The proposed model was implemented on the Cuckoo Search Algorithm (CSA) and verified through experimental studies carried out with a TI-TMS320f28069 microcontroller and PV emulator. The experimental results confirm that issue 1 is solved with 100%, issue 2 is solved with 99.5%, issue 3 is solved with 99.84%, and issue 4 is solved with 100% MPPT efficiency. [ABSTRACT FROM AUTHOR]

The mysterious nature of the dark sector of the Λ-cold-dark-matter (ΛCDM) model is one of the main motivators behind the study of alternative cosmological models. A central quantity of interest for these models is the matter power spectrum, which quantifies structure formation on various scales and can be cross-validated through theory, simulations, and observations. Here, we present a tool that can be used to create emulators for the non-linear matter power spectrum, and similar global clustering statistics, for models beyond ΛCDM with very little computation effort and without the need for supercomputers. We use fast approximate N-body simulations to emulate the boost, B(k, z) = Pbeyond − ΛCDM(k, z)/PΛCDM(k, z), and then rely on existing high-quality emulators made for ΛCDM to isolate Pbeyond − ΛCDM(k, z). Since both the ΛCDM and beyond-ΛCDM models are simulated in our approach, some of the lack of power on small scales due to the low force-resolution in the simulations is factored out, allowing us to extend the emulator to k ∼ 3 − 5 h Mpc−1 and still maintain good accuracy. In addition, errors from the simulation and emulation process can easily be estimated and factored into the covariance when using the emulator on data. As an example of using the pipeline, we create an emulator for the well-studied f(R) model with massive neutrinos, using approximately 3000 CPU hours of computation time. Provided with the paper is a fully functioning pipeline that generates parameter samples, runs a Boltzmann solver to produce initial conditions, runs the simulations, and then gathers all the data and runs it through a machine learning module to develop the emulator. This tool, named Sesame, can be used by anyone to generate a power spectrum emulator for the cosmological model of their choice. [ABSTRACT FROM AUTHOR]

With advances in scientific computing and mathematical modeling, complex scientific phenomena such as galaxy formations and rocket propulsion can now be reliably simulated. Such simulations can however be very time-intensive, requiring millions of CPU hours to perform. One solution is multi-fidelity emulation, which uses data of different fidelities to train an efficient predictive model which emulates the expensive simulator. For complex scientific problems and with careful elicitation from scientists, such multi-fidelity data may often be linked by a directed acyclic graph (DAG) representing its scientific model dependencies. We thus propose a new Graphical Multi-fidelity Gaussian Process (GMGP) model, which embeds this DAG structure (capturing scientific dependencies) within a Gaussian process framework. We show that the GMGP has desirable modeling traits via two Markov properties, and admits a scalable algorithm for recursive computation of the posterior mean and variance along at each depth level of the DAG. We also present a novel experimental design methodology over the DAG given an experimental budget, and propose a nonlinear extension of the GMGP via deep Gaussian processes. The advantages of the GMGP are then demonstrated via a suite of numerical experiments and an application to emulation of heavy-ion collisions, which can be used to study the conditions of matter in the Universe shortly after the Big Bang. The proposed model has broader uses in data fusion applications with graphical structure, which we further discuss. [ABSTRACT FROM AUTHOR]

The rich and complex physics of inertial confinement fusion provides a unique and challenging space for high-fidelity first-principles modeling. Consequently, simulation codes that are used to design experiments are computationally expensive and lack the predictive capability required for extensive parameter exploration in search of a high-performing design for laser direct drive. In this article, we present two deep-learning-based predictive models intended to address these difficulties. The first model (TL DNN) acts as a fast emulator of simulations as well as experiments at the Omega Laser Facility. This model is trained on a simulation database and subsequently calibrated on experimental data using transfer learning. To facilitate the development of this model, an autoencoder is developed to reduce the dimensionality of the input space by compressing the laser pulse input. The model predicts key experimental scalar observables of Omega experiments with high accuracy and minimal computational cost. This deep neural net enables rapid exploration of a high-dimensional input parameter space for an optimal implosion design. The second model (DNN SM+) aims to extend the statistical modeling work of Lees et al. [Phys. Rev. Lett. 127, 105001 (2021)], by increasing the complexity of the model space and allowing for coupling between degradation terms. Since the model capacity of DNN SM+ is higher than the model of Lees et al., DNN SM+ can potentially provide an improvement in predictive capability, and we use this model to provide insight into complicated degradation dependencies. [ABSTRACT FROM AUTHOR]

The ability to non‐uniformly weight the input space is desirable for many applications, and has been explored for space‐filling approaches. Increased interests in linking models, such as in a digital twinning framework, increases the need for sampling emulators where they are most likely to be evaluated. In particular, we apply non‐uniform sampling methods for the construction of aerodynamic databases. This paper combines non‐uniform weighting with active learning for Gaussian Processes (GPs) to develop a closed‐form solution to a non‐uniform active learning criterion. We accomplish this by utilizing a kernel density estimator as the weight function. We demonstrate the need and efficacy of this approach with an atmospheric entry example that accounts for both model uncertainty as well as the practical state space of the vehicle, as determined by forward modeling within the active learning loop. [ABSTRACT FROM AUTHOR]

The randomized controlled trial (RCT) forms the basis for drug approval by regulatory agencies. Observational studies using existing data from healthcare databases now also provide real‐world evidence (RWE) in regulatory decision‐making. Several initiatives are assessing the value of RWE by conducting observational studies that emulate published RCTs. While many RCTs are straightforward to emulate, others are challenging. We describe three RCT design aspects that pose challenges for observational studies. First are trials that enrol already treated subjects who must discontinue these treatments at the time of randomization, which can distort the comparison with observational studies. Second is the inclusion of a run‐in phase, especially to exclude non‐compliant subjects from the trial. Third are trials that evaluate the effect of weaning off treatment. In conclusion, future randomized trials that aim to be emulated by observational studies could consider study designs that allow emulation and thus provide valid and complementary RWE. [ABSTRACT FROM AUTHOR]

High-performance computing (HPC) processors are nowadays integrated cyber-physical systems demanding complex and high-bandwidth closed-loop power and thermal control strategies. To efficiently satisfy real-time multi-input multi-output (MIMO) optimal power requirements, high-end processors integrate an on-die power controller system (PCS). While traditional PCSs are based on a simple microcontroller (MCU)-class core, more scalable and flexible PCS architectures are required to support advanced MIMO control algorithms for managing the ever-increasing number of cores, power states, and process, voltage, and temperature variability. This paper presents ControlPULP, an open-source, HW/SW RISC-V parallel PCS platform consisting of a single-core MCU with fast interrupt handling coupled with a scalable multi-core programmable cluster accelerator and a specialized DMA engine for the parallel acceleration of real-time power management policies. ControlPULP relies on FreeRTOS to schedule a reactive power control firmware (PCF) application layer. We demonstrate ControlPULP in a power management use-case targeting a next-generation 72-core HPC processor. We first show that the multi-core cluster accelerates the PCF, achieving 4.9x speedup compared to single-core execution, enabling more advanced power management algorithms within the control hyper-period at a shallow area overhead, about 0.1% the area of a modern HPC CPU die. We then assess the PCS and PCF by designing an FPGA-based, closed-loop emulation framework that leverages the heterogeneous SoCs paradigm, achieving DVFS tracking with a mean deviation within 3% the plant's thermal design power (TDP) against a software-equivalent model-in-the-loop approach. Finally, we show that the proposed PCF compares favorably with an industry-grade control algorithm under computational-intensive workloads. [ABSTRACT FROM AUTHOR]

Dynamic binary translation (DBT) is a core technology that enables the migration of legacy software to different instruction set architectures while maintaining the original semantics. However, the development and maintenance of an efficient cross-DBT system are challenging. Key challenges include memory access overhead, inefficient instruction simulation, and frequent context switches. In this paper, we propose three novel optimization techniques. First, we formalize a register mapping cost model and investigate a hierarchical register mapping approach to bridge the memory access overhead. Second, we accelerate floating point (FP) emulation by surrounding the use of hardware FP unit with high-efficiency non-FP code. Third, we present a function inlining approach to alleviating the overhead associated with indirect control lookup. On the system side, we implement our approach on ARM64 and SW64 architectures based on QEMU and extensively evaluate the effectiveness with the SPEC2006 benchmark suite. The experimental results show that an average of 1.28× performance speedup and 13.41% code size reduction can be achieved on SW64. Similarly, on ARM64, we achieve an average of 1.15× performance speedup and 11.48% code size reduction. [ABSTRACT FROM AUTHOR]

This work presents a novel approach to quantum computing by proposing a customizable hardware design of a dedicated processor that emulates the execution of quantum algorithms. Unlike software-based quantum computation simulators, which run on standard general-purpose computers and suffer from reduced performance, this hardware design, which is based on classical concepts of bits, registers and memories, aims to leverage pure parallelism and pipelined execution for efficient quantum computations via emulation. The architecture includes several key components: memories, computation unit, measurement unit and control unit. The quantum state memory stores the individual and group states of qubits. This memory is crucial for maintaining the quantum information required for quantum operations. Basic operators are stored in dedicated operator memory. Additionally, a scratch memory allows for larger operators to be dynamically built at runtime. The computation unit is responsible for performing complex number multiplications, which form the basis of tensor and matrix products necessary for executing quantum operations. A measurement unit enables quantum state sampling, which is an essential aspect of quantum computation. Furthermore, a control unit is incorporated to ensure the correct operation of the quantum processor's data path. It utilizes a microprogram to manage and coordinate the functional units. All the functional units communicate with each other through dedicated and shared data buses, depending on the frequency of information exchange. This enables efficient data transfer and coordination among the components. The proposed hardware design has been simulated and proved to be effective in executing quantum operations. By exploiting parallelism and employing a pipelined execution, this architecture overcomes the limitations of software-based simulators, delivering improved performance for emulating quantum algorithms. We use Grover's search algorithm as a benchmark to evaluate the performance of the proposed hardware design and compare it to software-based simulation and to hardware-based algorithm-dedicated emulation. [ABSTRACT FROM AUTHOR]

Motivation Emergent biological dynamics derive from the evolution of lower-level spatial and temporal processes. A long-standing challenge for scientists and engineers is identifying simple low-level rules that give rise to complex higher-level dynamics. High-resolution biological data acquisition enables this identification and has evolved at a rapid pace for both experimental and computational approaches. Simultaneously harnessing the resolution and managing the expense of emerging technologies—e.g. live cell imaging, scRNAseq, agent-based models—requires a deeper understanding of how spatial and temporal axes impact biological systems. Effective emulation is a promising solution to manage the expense of increasingly complex high-resolution computational models. In this research, we focus on the emulation of a tumor microenvironment agent-based model to examine the relationship between spatial and temporal environment features, and emergent tumor properties. Results Despite significant feature engineering, we find limited predictive capacity of tumor properties from initial system representations. However, incorporating temporal information derived from intermediate simulation states dramatically improves the predictive performance of machine learning models. We train a deep-learning emulator on intermediate simulation states and observe promising enhancements over emulators trained solely on initial conditions. Our results underscore the importance of incorporating temporal information in the evaluation of spatio-temporal emergent behavior. Nevertheless, the emulators exhibit inconsistent performance, suggesting that the underlying model characterizes unique cell populations dynamics that are not easily replaced. Availability and implementation All source codes for the agent-based model, emulation, and analyses are publicly available at the corresponding DOIs: 10.5281/zenodo.10622155, 10.5281/zenodo.10611675, 10.5281/zenodo.10621244, respectively. [ABSTRACT FROM AUTHOR]

High performance computing (HPC) electromagnetic (EM) emulators are used to simulate real-time EM wave interactions between numerous radar targets. Radar Cross Section (RCS) data stores reflection profiles of radar targets as a table; however, the needed storage size increases with frequency sampling density, aspect angle sampling density, and number of target types. The large quantity of data often exceeds storage capability and limits manipulation and representation feasibility. The spherical harmonic based monostatic anisotropic point scatterer model is proposed for HPC EM simulations where scattering responses can be computed with finite impulse response (FIR) filters. An efficient algorithm constructing this model with large scale RCS data is discussed. The scatterer position and the reflection profile of each scatterer are solved using least squares methods and particle swarm optimization (PSO). In addition, the function evaluations in PSO are accelerated by taking advantage of the matrix structure, making the algorithm 22 times faster [ABSTRACT FROM AUTHOR]

This paper proposes an improved Wind Turbine Emulator (WTE) structure using Sliding Mode Control (SMC) technique based on the Two-Phase Induction Motor (TPIM) for software simulation laboratory purposes. Since the power electronic converters application with various control strategies in the AC machine drive field facilitates the wind turbine characteristics imitation, an advanced SVM controlled-2ϕ-inverter is adopted. Considering the asymmetry between the TPIM main and auxiliary windings, mathematical equations were studied allowing control of the speed and the torque under different conditions. The 2-phase-inverter is controlled through an appropriate adjustment of four space voltage vectors. In order to enhance the speed and flux regulation loops and to increase the system robustness against the motor parameters variation and the wind sudden fluctuations, the SMC theory, which contains the adaptive rotor flux observer is used here to develop a control law that governs the system to track the reference speed set by the WT mathematical model to obtain the desired output. Several parameters, such as electromagnetic torque, rotor fluxes, stator currents, and rotor speed, were analyzed. Static and dynamic characteristics and the WTE transient and steady-state responses are satisfactorily reproduced by the proposed emulator scheme. [ABSTRACT FROM AUTHOR]

We present a detailed investigation of various routes to optimize the power consumption of the spintronic-based devices for implementing rectified linear activation (ReLU) and max-pooling functions. We examine the influence of various spin Hall effect layers, and their input resistances on the power consumption of the ReLU-max pooling functions, we also access the impact of the thermal stability factor of the free-ferromagnet layer on the power consumption and accuracy of the device. The design for ReLU-max pooling relies on the continuous rotation of magnetization, which is accomplished by applying orthogonal spin current to the free-FM layer. We also demonstrate the non-trivial power-resistance relation, where the power consumption decreases with an increase in SHE resistance. We utilize the hybrid spintronic-CMOS simulation platform that combines Keldysh non-equilibrium Green's function (NEGF) with Landau-Lifshitz-Gilbert-Slonzewski (LLGS) equations and the HSPICE circuit simulator to evaluate our network. Our design takes 0.343 μW of power for ReLU emulation and 17.86 μW of power for ReLU-max pooling network implementation at a thermal stability factor of 4.58, all while maintaining reliable results. We validate the efficiency of our design by implementing a convolutional neural network that classifies the handwritten-MNIST and fashion-MNIST datasets. This implementation illustrates that the classification accuracies achieved are on par with those attained using the ideal software ReLU-max pooling functions, with an energy consumption of 167.31 pJ per sample. [ABSTRACT FROM AUTHOR]

The increasing heterogeneity and scalability of the Internet of everything, especially, the Energy Internet (EI), is a prompt for novel engineering paradigms. The current infrastructure of hardware technologies besides the available software stack is becoming obsolete for handling the advanced requirements of the smart energy ecosystem. Accordingly, software definitions of the Internet of Things (IoT) stack functions are gaining interest to provide more flexible and scalable implementations. This paper investigates a sophisticated softwarization explicit hybrid model predictive control strategy for energy storage facility systems through the accessor design pattern. This strategy is presumed to support and facilitate the integration of higher-level analytic and control functionalities within the IoT stack at edges and nodes. Simulation is conducted with the Ptolemy II software to evaluate the execution semantics of the proposed strategy. In addition, real-time experiments on a lab-scale hydraulic tank process with both abrupt and gradual commands test scenarios showed the efficiency and reliability of the accessor-based controllers for achieving the control objectives for the benchmark storage facility with an abstract implementation. The analysis shows that this process can serve as a benchmark to mimic the charge and discharge cycles of storage elements in EI ecosystems. • A new paradigm for hydrogen energy storage interfacing within energy Internet ecosystems is proposed and investigated. • An actor-oriented approach is applied for implementing real-time control systems of hydrogen storage. • Software-defined model predictive control is implemented within a Node.js accessor host. • A benchmark process is developed as an emulator for hydrogen energy storage to evaluate the accessors design pattern. [ABSTRACT FROM AUTHOR]

The article "Who Are You? Nintendo's Game Boy Advance Platform" by Alex Custodio explores the historical and cultural significance of Nintendo's Game Boy Advance (GBA) through the lens of embodiment, social circulation, materiality of nostalgia, and practicality. The book is divided into six chapters that cover various aspects of the GBA's legacy, including its creation, design, inspiration, and marketing. It also delves into the archeological perspective of gaming consoles and their interaction with players, the impact of popular game franchises on the GBA's popularity, the rise of emulators and ROMs, and fan-generated content through homebrewing, hacking, and hardware modding. Custodio argues for alternative perspectives in platform studies and highlights the GBA's role as a historical and cultural artifact in gaming history. The book expands on ongoing conversations in media archaeology, game history, and platform studies, and offers new ways to think about portable gaming consoles and their impact on public and private spaces. [Extracted from the article]

This article explores the challenges faced by libraries, archives, and museums in preserving and providing access to software and software-dependent information. It discusses the implementation of software emulation workflows in three information institutions and examines the technical and social constraints of emulation. The article emphasizes the importance of transparency and accountability in preservation workflows and highlights the complexities of providing access to emulated software, including the challenges of emulating unique controllers. It also discusses the concept of "automagic" access and the need for further research on intervention and visibility strategies in software preservation. [Extracted from the article]

The emergence of digital computers has profoundly reshaped our interactions with technology and the processing of information. Despite excelling in data processing and arithmetics, these computers face limitations in tackling complex nondeterministic-polynomial (NP) problems. In response, researchers have started searching for new computational paradigms that possess the natural tendency of solving these problems. Oscillator-based optimizers are one such paradigm, where the idea is to exploit the parallelism of oscillators networks in order to efficiently solve NP problems. This involves a process of mapping a given optimization task to a quadratic unconstrained binary optimization program and then mapping the resulting program onto an inter-oscillator coupling circuit encoding its coefficients. This paper presents a comprehensive approach to constructing oscillator-based optimizers, offering both the rationale for employing oscillator networks and formulas for linking optimization coefficients to inter-oscillator coupling. Here, we cover most aspects of oscillator-based optimization starting from the design of the network up to its technical implementation. Moreover, we provide a platform-independent wave digital algorithm, which allows for emulating our network's behavior in a highly parallel fashion. [ABSTRACT FROM AUTHOR]

Code analysis for defect detection is very important in the modern world, especially in the case of complex multi-thread applications. An example of a tool, suitable for software of high complexity, is the famous S2E, which allows for full-system emulation with symbolic execution. This paper presents several major enhancements for S2E, including: firstly, support for multiple virtual cores, allowing to have parallel speed-up; secondly, on this basis, a race checker plugin to detect defects of this sort in multi-thread programs. This development has concerned such interesting points of research as scheduling in multi-core emulation and race detection with symbolic execution. [ABSTRACT FROM AUTHOR]

As technologies like the Internet, artificial intelligence, and big data evolve at a rapid pace, computer architecture is transitioning from compute-intensive to memory-intensive. However, traditional von Neumann architectures encounter bottlenecks in addressing modern computational challenges. The emulation of the behaviors of a synapse at the device level by ionic/electronic devices has shown promising potential in future neural-inspired and compact artificial intelligence systems. To address these issues, this review thoroughly investigates the recent progress in metal-oxide heterostructures for neuromorphic applications. These heterostructures not only offer low power consumption and high stability but also possess optimized electrical characteristics via interface engineering. The paper first outlines various synthesis methods for metal oxides and then summarizes the neuromorphic devices using these materials and their heterostructures. More importantly, we review the emerging multifunctional applications, including neuromorphic vision, touch, and pain systems. Finally, we summarize the future prospects of neuromorphic devices with metal-oxide heterostructures and list the current challenges while offering potential solutions. This review provides insights into the design and construction of metal-oxide devices and their applications for neuromorphic systems. [ABSTRACT FROM AUTHOR]

The Antarctic ice sheet (AIS) will be a dominant contributor to global mean sea level rise in the 21st century but remains a major source of uncertainty. The Ice Sheet Model Intercomparison for CMIP6 (ISMIP6) is an ensemble of continental‐scale models for studying the evolution of the AIS and projecting its future contribution to sea level. Due to their complexity and computational cost, ISMIP6 simulations are sparse and generated infrequently. Emulators are smaller‐scale models that approximate ISMs and enable experimentation and exploration into the drivers of sea level change. We introduce a neural network (NN) emulator to approximate the ISMIP6 ensemble, using a variational Long Short‐Term Memory (LSTM) with Monte Carlo dropout to quantify single‐projection uncertainty. The proposed NN emulator is compared to a Gaussian Process (GP) emulator on four criteria: accuracy of point estimates and predictive distributions of individual model projections, approximation of the ensemble projections, and model training time. The NN predicts more accurately on single projections, with a mean absolute error of 0.46 mm Sea Level Equivalent (SLE) versus 0.73 mm SLE for the GP, and has more accurate uncertainty estimates. The NN emulator also better approximates the ensemble distribution of ISMIP6 model projections, with a Kullback‐Leibler divergence of 18.26 versus 199.14 for GP at the projection year 2100. The NN enables more accurate experimentation with a reduced runtime, offering a new tool for understanding the important role of regional precipitation, ice sheet drainage systems, and interannual and longer timescale dynamics. Plain Language Summary: An emulator is a computational model that is designed to rapidly approximate another more complex, computationally intensive model. In this work, we propose a new emulator of the Antarctic ice sheet that provides faster and more accurate projections of the future sea level rise due to the melting of the ice sheet. This new emulator uses a technology called neural networks (NNs), a common tool within the field of artificial intelligence. We show that the NN‐based emulator produces accurate sea level projections while also being able to quantify the inherent uncertainty associated with future sea level rise. With these improvements, this emulator will enable scientists to better investigate the ice sheet itself and learn how it connects to Earth's dynamic behavior. In addition, due to the efficiency of the proposed emulator, not only are many avenues of research opened for further improvements of ice sheet emulators, but also a wider range of scientists will be able to contribute to future development. This will lead to a better understanding of the drivers of sea level rise as well as more informed decision‐making and mitigation efforts. Key Points: A neural network (NN)‐based emulator of Antarctic ice sheet mass loss over the 21st century is introducedThe proposed emulator is fast to train, handles large inputs, models temporal correlations and quantifies uncertaintyThe proposed NN emulator outperforms a standard Gaussian Process emulator on a range of metrics, including computational cost and accuracy [ABSTRACT FROM AUTHOR]

The immense computational cost of traditional numerical weather and climate models has sparked the development of machine learning (ML) based emulators. Because ML methods benefit from long records of training data, it is common to use data sets that are temporally subsampled relative to the time steps required for the numerical integration of differential equations. Here, we investigate how this often overlooked processing step affects the quality of an emulator's predictions. We implement two ML architectures from a class of methods called reservoir computing: (a) a form of Nonlinear Vector Autoregression (NVAR), and (b) an Echo State Network (ESN). Despite their simplicity, it is well documented that these architectures excel at predicting low dimensional chaotic dynamics. We are therefore motivated to test these architectures in an idealized setting of predicting high dimensional geophysical turbulence as represented by Surface Quasi‐Geostrophic dynamics. In all cases, subsampling the training data consistently leads to an increased bias at small spatial scales that resembles numerical diffusion. Interestingly, the NVAR architecture becomes unstable when the temporal resolution is increased, indicating that the polynomial based interactions are insufficient at capturing the detailed nonlinearities of the turbulent flow. The ESN architecture is found to be more robust, suggesting a benefit to the more expensive but more general structure. Spectral errors are reduced by including a penalty on the kinetic energy density spectrum during training, although the subsampling related errors persist. Future work is warranted to understand how the temporal resolution of training data affects other ML architectures. Plain Language Summary: The computer models that govern weather prediction and climate projections are extremely costly to run, causing practitioners to make unfortunate tradeoffs between accuracy of the physics and credibility of their statistics. Recent advances in machine learning have sparked the development of neural network‐based emulators, that is, low‐cost models that can be used as drop‐in replacements for the traditional expensive models. Due to the cost of storing large weather and climate data sets, it is common to subsample these fields in time to save disk space. This subsampling also reduces the computational expense of training emulators. Here, we show that this pre‐processing step hinders the fidelity of the emulator. We offer one method to mitigate the resulting errors, but more research is needed to understand and eventually overcome them. Key Points: Reducing training data temporal resolution by subsampling leads to overly dissipative small spatial scales in neural network emulatorsA quadratic autoregressive architecture is shown to be inadequate at capturing small scale turbulence, even when data are not subsampledSubsampling bias in Echo State Networks is mitigated but not eliminated by prioritizing kinetic energy spectrum during training [ABSTRACT FROM AUTHOR]

Understanding the impact of climate change on year-to-year variation of crop yield is critical to global food stability and security. While crop model emulators are believed to be lightweight tools to replace the models, few emulators have been developed to capture such interannual variation of crop yield in response to climate variability. In this study, we developed a statistical emulator with a machine learning algorithm to reproduce the response of year-to-year variation of four crop yields to CO2 (C), temperature (T), water (W), and nitrogen (N) perturbations defined in the Global Gridded Crop Model Intercomparison Project (GGCMI) phase 2. The emulators were able to explain more than 52 % of the variance of simulated yield and performed well in capturing the year-to-year variation of global average and gridded crop yield over current croplands in the baseline. With the changes in CO2 –temperature–water–nitrogen (CTWN) perturbations, the emulators could reproduce the year-to-year variation of crop yield well over most current cropland. The variation of R and the mean absolute error was small under the single CTWN perturbations and dual-factor perturbations. These emulators thus provide statistical response surfaces of yield, including both its mean and interannual variability, to climate factors. They could facilitate spatiotemporal downscaling of crop model simulation, projecting the changes in crop yield variability in the future and serving as a lightweight tool for multi-model ensemble simulation. The emulators enhanced the flexibility of crop yield estimates and expanded the application of large-ensemble simulations of crop yield under climate change. [ABSTRACT FROM AUTHOR]

We present a machine learning (ML) method for emulating seismic-phase traveltimes that are computed using a global-scale 3-D earth model and physics-based ray tracing. Accurate traveltime predictions based on 3-D earth models are known to reduce the bias of event location estimates, increase our ability to assign phase labels to seismic detections and associate detections to events. However, practical use of 3-D models is challenged by slow computational speed and the unwieldiness of pre-computed lookup tables that are often large and have prescribed computational grids. In this work, we train a ML emulator using pre-computed traveltimes, resulting in a compact and computationally fast way to approximate traveltimes that are based on a 3-D earth model. Our model is trained using approximately 850 million P -wave traveltimes that are based on the global LLNL-G3D-JPS model, which was developed for more accurate event location. The training-set consists of traveltimes between 10 393 global seismic stations and randomly sampled event locations that provide a prescribed, distance-dependent geographic sample density for each station. Prediction accuracy is dependent on event-station distance and whether the station was included in the training set. For stations included in the training set the mean absolute deviation (MAD) of the difference between traveltimes computed using ray tracing through the 3-D model and the ML emulator for local, regional, and teleseismic distances are 0.090, 0.125 and 0.121 s, respectively. For tested station locations not included in the training set, MAD values for the three distance ranges increase to 0.173, 0.219 and 0.210 s, respectively. Empirical traveltime residuals for a global reference data are indistinguishable when ML emulation or the 3-D model is used to compute traveltimes. This result holds regardless of whether the recording station is used in ML training or not. [ABSTRACT FROM AUTHOR]

Multipath propagation is a major source of error in global navigation satellite systems (GNSSs), especially in urban environments. This is because conventional GNSS receivers can provide biased range estimates that lead to positioning errors. In this paper, an Extended Kalman Filter (EKF)-based solution that relies on a multi-correlator structure is proposed to replace the conventional delay locked loop (DLL). The underlying signal model incorporates the radio propagation channel between the satellite and receiver and thus inherently accounts for reflected signal replicas. The algorithm was evaluated with simulations and hardware emulations and a measurement campaign was conducted in road traffic with different multipath environments. Our results revealed that the proposed EKF was very effective against multipath-associated error. [ABSTRACT FROM AUTHOR]

Machine learning (ML) algorithms can be used in Earth System models (ESMs) to emulate sub-grid-scale processes. Due to the statistical nature of ML algorithms and the high complexity of ESMs, these hybrid ML-ESMs require careful validation. Simulation stability needs to be monitored in fully coupled simulations, and the plausibility of results needs to be evaluated in suitable experiments. We present the coupling of SuperdropNet, a machine learning model for emulating warm rain processes in cloud microphysics, into ICON 2.6.5. SuperdropNet is trained on computationally expensive droplet based simulations and can serve as an inexpensive proxy within weather prediction models. SuperdropNet emulates the collision-coalescence of rain and cloud droplets in a warm rain scenario and replaces the collision-coalescence process in the two-moment cloud microphysics scheme. We address the technical challenge of integrating SuperdropNet, developed in Python and PyTorch, into ICON, written in Fortran, by implementing three different coupling strategies: embedded Python via the C Foreign Function Interface, pipes, and coupling of program components via YetAnotherCoupler (YAC). We validate the emulator in the warm bubble scenario and find that SuperdropNet runs stable within the experiment. In comparing experiment outcomes from the bulk moment scheme and SuperdropNet, we find that the results are physically consistent, and discuss differences that are observed for several diagnostic variables. In addition, we provide a quantitative and qualitative computational benchmark for three different coupling strategies— embedded Python, coupler YAC, and pipes—and find that embedded Python is a useful software tool for validating hybrid ML-ESMs. [ABSTRACT FROM AUTHOR]

Emerging intelligence applications, such as brain-inspired and in-memory computing, require memory with faster read/write speeds, higher integration, and lower energy consumption. To tackle these challenges, memristors, a type of synaptic device, are considered ideal candidates due to their potential for emulating biological synaptic connections. In this study, a two-dimensional (2D) heterostructure of tellurene/Nb-doped MoS2 (MoS2:Nb) was used as the resistive switching layer to fabricate memristors. By varying the maximum working voltage, the fabricated device can switch between one and two-memory windows, which can be used to imitate the postsynaptic inhibition effect. This is attributed to the competition between the drift and diffusion of the S vacancy in the MoS2:Nb layer, which can modulate the contact Schottky barrier in the material interfaces. Furthermore, biological synapse effects, such as long-term depression and long-term potentiation, can be well mimicked by applying several voltage pulses to the device with good repeatability. This study advances the device physics for understanding the physical working mechanism of the 2D memristor, which can benefit the realization of bio-realistic neuromorphic computing systems based on such memristors. [ABSTRACT FROM AUTHOR]

Airborne wind energy systems (AWES) are more efficient than traditional wind turbines because they can capture higher wind speeds at higher altitudes using connected kite generators. Securing a real wind turbine or a site with favorable wind conditions is not always an assured opportunity for conducting research. Hence, the Research and Development of the Laboratory Scale Airborne Wind Energy Conversion System (LAWECS) require a better understanding of airborne wind turbine dynamics and emulation. Therefore, an airborne wind turbine emulation system was designed, implemented, simulated, and experimentally tested with ground data for the real time simulation. The speed and torque of a permanent magnet synchronous motor (PMSM) connected to a kite are regulated to maximize wind energy harvesting. A field-oriented control technique is then used to control the PMSM's torque, while a three-phase power inverter is utilized to drive the PMSM with PI controllers in a closed loop. The proposed framework was tested, and the emulated airborne wind energy conversion system results were proven experimentally for different wind speeds and generator loads. Further, the LAWECS emulator simulated a 2 kW, 20 kW, and 60 kW designed with a projected kite area of 5, 25, and 70 square meters, respectively. This system was simulated using the Matlab/Simulink software and tested with the experimental data. Furthermore, the evaluation of the proposed framework is validated using a real-time hardware-in-the-loop environment, which uses the FPGA-based OPAL-RT Simulator. [ABSTRACT FROM AUTHOR]

Physics-based simulations are important for elucidating the fundamental mechanisms behind the time-varying complex ionospheric conditions, such as ionospheric potential, against unprecedented solar wind variations incident on the Earth's magnetosphere. However, carrying out an extensive parameter survey for comprehending the nonlinear solar wind density dependence of the ionospheric potential, for example, requires state-of-the-art global magnetohydrodynamic (MHD) simulations, which cannot be executed efficiently even on large-scale cluster computers. Here, we report the performance of a machine-learning based surrogate model for estimating the ionospheric potential outputs of a global MHD simulation, using the reservoir computing technique called echo state network (ESN). The trained ESN-based emulator demonstrates exceptional speed in conducting the parameter survey, which can lead to the identification of a solar wind density dependence of the ionospheric polar cap potential. Finally, we discuss future directions including the promising application for space weather forecasting. [ABSTRACT FROM AUTHOR]

In this research paper, we study the capability of artificial neural network models to emulate storm surge based on the storm track/size/intensity history, leveraging a database of synthetic storm simulations. Traditionally, computational fluid dynamics (CFD) solvers are employed to numerically solve the storm surge governing equations that correspond to expensive to evaluate partial differential equations (PDE). This study presents a neural network model that can predict storm surge, informed by a database of synthetic storm simulations. This model can serve as a fast and affordable emulator for the expensive CFD solvers creating the original database. The neural network model is trained with the storm track parameters used to drive the CFD solvers, and the output of the model is the time-series evolution of the predicted storm surge across multiple nodes within the spatial domain of interest. Once the model is trained, it can be deployed for further predictions based on new storm track inputs. The developed neural network model is a time-series model, composed of a long short-term memory (LSTM), a variation of recurrent neural network (RNN), further enriched with convolutional neural networks (CNNs). The convolutional neural network is employed to capture the correlation of data spatially (across the aforementioned nodes). Therefore, the temporal and spatial correlations of data are captured by the combination of the mentioned models, representing the ConvLSTM model. As the problem is a sequence to sequence time-series problem, an encoder–decoder ConvLSTM model is designed. Furthermore, the performance of the developed convolutional recurrent neural network model is improved by residual connection networks. Additional techniques are employed in the process of model training to enrich the model performance that the model can learn from the data in a more effective way. The performance of the developed model is compared with the results provided by a Gaussian process (GP) implementation, representing a state-of-the-art alternative for establishing time-series emulation of storm surge predictions. The results show that the proposed convolutional recurrent neural network outperforms the GP implementation for the examined synthetic storm database. [ABSTRACT FROM AUTHOR]

Indoor agriculture is emerging as a promising approach for increasing the efficiency and sustainability of agri-food production processes. It is currently evolving from a small-scale horticultural practice to a large-scale industry as a response to the increasing demand. This led to the appearance of plant factories where agri-food production is automated and continuous and the plant environment is fully controlled. While plant factories improve the productivity and sustainability of the process, they suffer from high energy consumption and the difficulty of providing the ideal environment for plants. As a small step to address these limitations, in this article we propose to use internet of things (IoT) technologies and automatic control algorithms to construct an energy-efficient remote control architecture for grow lights monitoring in indoor farming. The proposed architecture consists of using a master–slave device configuration in which the slave devices are used to control the local light conditions in growth chambers while the master device is used to monitor the plant factory through wireless communication with the slave devices. The devices all together make a 6LoWPAN network in which the RPL protocol is used to manage data transfer. This allows for the precise and centralized control of the growth conditions and the real-time monitoring of plants. The proposed control architecture can be associated with a decision support system to improve yields and quality at low costs. The developed method is evaluated in emulation software (Contiki-NG v4.7),its scalability to the case of large-scale production facilities is tested, and the obtained results are presented and discussed. The proposed approach is promising in dealing with control, cost, and scalability issues and can contribute to making smart indoor agriculture more effective and sustainable. [ABSTRACT FROM AUTHOR]

The NASA Ames Mars Global Climate Model (MGCM) software has been in steady use at NASA for decades and was recently released to the public. This model simulates the complex interactions of various weather cycles that exist on Mars, namely the Dust Cycle, the CO2 Cycle, and the Water cycle. Utilized by NASA, the MGCM is used to help understand their empirically observed data through the use of sensitivity studies. However, these sensitivity studies are computationally taxing, requiring weeks to run. To address this issue, we have trained a surrogate model using Gaussian processes (GP) that can emulate the output of this model with relatively small amounts of data in a reduced amount of time (on the order of minutes). We demonstrate the effectiveness of our emulator using backward error. Plain Language Summary: The NASA Ames Mars Global Climate Model (MGCM) is a computer model that simulates the weather on Mars. The MGCM is used by NASA to help understand weather data collected from satellites and other sources. The model has many inputs, the correct values of which are unknown, so it is often run many times with varying input values. Each run of the MGCM takes a long time, so running enough times to gather all of the desired outputs can take weeks. To address this issue, we have developed a method to approximate the output of the MGCM through the use of a machine learning model. This model requires a relatively small amount of data to train and once trained can approximate the MGCM output accurately and very quickly. Key Points: Gaussian Process emulation is effective at vastly decreasing the required runtime for sensitivity studies using the Mars Global Climate Model (MGCM)The use of Gaussian Process emulation is remarkably accurate for the MGCMGaussian Process emulation has significant potential to support more refined studies that would otherwise be computationally unfeasible [ABSTRACT FROM AUTHOR]

This article presents an area- and power-efficient hardware architecture for the brain-implantable spiking neural networks (SNNs). The proposed generalized hardware architecture is parameterizable and reconfigurable such that the maximum supported number of neurons, the interconnection structure among neurons, and the resolution of the time step can be readily adjusted for realizing various SNN topologies. The designed SNN hardware architecture is capable of emulating moderately-sized SNNs with tens of thousands of neurons in real-time with varying degrees of parallelism, while reducing the resource utilization by 34% for similarly sized SNNs implemented on a single field-programmable gate array (FPGA). We evaluate the model using the MNIST digit recognition benchmark and show that the network can accurately classify handwritten digits with 89.8% accuracy. Compared to the other recently implemented SNN emulators based on FPGAs, the designed and implemented single-FPGA system is able to emulate moderately-sized SNNs instead of using a cluster of FPGAs or CPUs. The application-specific integrated circuit (ASIC) implementation of a moderately-sized SNN is estimated to occupy 3.6 mm2 of silicon area. Post-layout synthesis and simulation results show that the ASIC will dissipate 3.6 mW of power from a 1.16 V supply while operating at 34.7 MHz in a standard 32-nm CMOS process. [ABSTRACT FROM AUTHOR]

The simulation of the operation of the wind turbine was performed using two programming media: LabVIEW and MATLAB/Simulink, respectively. MATLAB is a high–level programming environment and language specializing in numerical computing, while LabVIEW is a graphical media and programming language that specializes in interfacing with hardware components. MATLAB/Simulink is predominantly used in simulation because it contains libraries with high–level functions, specialized in fields, which help to quickly develop advanced applications. LabVIEW is mainly used for measurement and data acquisition since it features exceptional compatibility with a large variety of hardware. The goal of this study is to determine which medium is better suited for developing the software component of a wind turbine emulator. The requirement for this task are: complex numerical computing, simplicity and observability, hardware compatibility, data acquisition and storage and the possibility of creating a HMI. These constitute the criteria by which the better suited medium is chosen. [ABSTRACT FROM AUTHOR]

In recent years, the Industrial Internet of Things (IIoT) has grown rapidly, a fact that has led to an increase in the number of cyberattacks that target this environment and the technologies that it brings together. Unfortunately, when it comes to using tools for stopping such attacks, it can be noticed that there are inherent weaknesses in this paradigm, such as limitations in computational capacity, memory and network bandwidth. Under these circumstances, the solutions used until now in conventional scenarios cannot be directly adopted by the IIoT, and so it is necessary to develop and design new ones that can effectively tackle this problem. Furthermore, these new solutions must be tested in order to verify their performance and viability, which requires testing architectures that are compatible with newly introduced IIoT topologies. With the aim of addressing these issues, this work proposes MECInOT, which is an architecture based on openLEON and capable of generating test scenarios for the IIoT environment. The performance of this architecture is validated by creating an intelligent threat detector based on tree-based algorithms, such as decision tree, random forest and other machine learning techniques. Which allows us to generate an intelligent and to demonstrate, we could generate an intelligent threat detector and demonstrate the suitability of our architecture for testing solutions in IIoT environments. In addition, by using MECInOT, we compare the performance of the different machine learning algorithms in an IIoT network. Firstly, we present the benefits of our proposal, and secondly, we describe the emulation of an IIoT environment while ensuring the repeatability of the experiments. [ABSTRACT FROM AUTHOR]

A decentralized power distribution network consisting of smart microgrids introduces opportunities to trade with energy called transactive energy. However, research studies in the existing literature suggest that several standardized information models for TE do not meet the network architecture's reliability, flexibility, and security requirements. This limitation is mainly due to the static nature of traditional IP infrastructure. To achieve these requirements in the network architecture, this study investigates the optimized application of software-defined network architecture for transactive energy in smart microgrid systems. Through literature research, unique design approaches in an SDN architecture are identified that improve the reliability, flexibility, and security of the SDN architecture. These design approaches include a decentralized controller network layout, redundant link configuration, a mesh network topology, and data encryption. The proposed solution uniquely combines these design approaches into a single optimized SDN solution for TESMS. To validate the improvements of the findings from the literature research, each design approach is simulated in this study using Mininet SDN emulator and AnyLogic system simulation software. The proposed solution is then applied to a use-case scenario that shows the improvements required for TESMS. The use-case scenario shows significant improvement in the data path uptime. An improvement of 0.27% is achieved, which equates to a 2 h per month increase in the data path uptime. The results of the simulation show that the proposed SDN architecture improves the reliability and flexibility of a traditional SDN network. Furthermore, enabling encryption between the nodes improves the security of the SDN architecture. [ABSTRACT FROM AUTHOR]

Small-scale wind turbines play an important role in distributed generation since customers can use their houses, farms, and business to produce electric energy. The development of the power electronics system that processes the electric energy from small-scale wind turbines is a concern due to cost, simplicity, efficiency, and performance trade-offs. This paper presents the results of applying a three-phase phase-modular single-ended primary-inductance converter rectifier to processing the energy of a small-scale wind turbine system. The rectifier was designed according to the specifications of a commercial small-scale wind turbine system and tested in an emulator workbench, providing experimental data on the operation of the rectifier in this application. The rectifier can process the energy of a non-sinusoidal three-phase system since the permanent magnet synchronous generator has trapezoidal waveforms. The results show that the rectifier has the advantages of (i) using the inductance of the generator as the input filter inductor of the rectifier, (ii) providing input currents with the same shape as the voltages and in phase without the use of a current control system, (iii) simplicity of control of the DC output voltage and PWM modulation, and (iv) phase-modular characteristics that allow operating with phase fault without any additional control techniques. Due to the operation in discontinuous conduction mode, low efficiency in high power and/or low input voltage specifications are disadvantages. [ABSTRACT FROM AUTHOR]

Understanding the impact of climate change on year-to-year variation of crop yield is critical to global food stability and security. While crop model emulators are believed to be lightweight tools to replaces the models per se, few emulators have been developed to capture such interannual variation of crop yield in response to climate variability. In this study, we developed a statistical emulator with machine learning algorithm to reproduce the response of year-to-year variation of four crop yield to CO2 (C), temperature (T), water (W) and nitrogen (N) perturbations defined in the Global Gridded Crop Model Intercomparison Project (GGCMI) phase 2 experiment. The emulators were able to explain more than 92% variance of simulated yield and performed well in capturing the year-to-year variation of global average and gridded crop yield over current croplands in the baseline. With the changes in CTWN perturbations, the emulators could well reproduce the year-to-year variation of crop yield over most current cropland. The variation of R and the mean absolute error was small under the single CTWN perturbations and dual factor perturbations. These emulators thus provide statistical response surfaces of yield, including both its mean and interannual variability, to climate factors. They could facilitate spatiotemporal downscaling of crop model simulation, projecting the changes in crop yield variability in the future, and serving as a lightweight tool of multi-model ensemble simulation. The emulators enhanced the flexibility of crop yield estimates and expanded the application of large-ensemble simulation of crop yield under climate change. [ABSTRACT FROM AUTHOR]

An algorithm named InterOpt for optimizing operational parameters is proposed based on interpretable machine learning, and is demonstrated via optimization of shale gas development. InterOpt consists of three parts: a neural network is used to construct an emulator of the actual drilling and hydraulic fracturing process in the vector space (i.e., virtual environment); the Sharpley value method in interpretable machine learning is applied to analyzing the impact of geological and operational parameters in each well (i.e., single well feature impact analysis); and ensemble randomized maximum likelihood (EnRML) is conducted to optimize the operational parameters to comprehensively improve the efficiency of shale gas development and reduce the average cost. In the experiment, InterOpt provides different drilling and fracturing plans for each well according to its specific geological conditions, and finally achieves an average cost reduction of 9.7% for a case study with 104 wells. [ABSTRACT FROM AUTHOR]

This paper seeks to use eye-tracking emulation software to understand and forecast the human responses to signage and directional cues in Massachusetts, USA. Using eye-tracking emulation software, this study measured the unconscious visual responses people are projected to have to designs and layouts in new built environments, focusing on what makes streets most walkable. The study found differences between the way the brain takes in conventional automobile-oriented residential developments versus new urbanist layouts, with the former lacking key fixation points. The study's discoveries explain why new urbanist layouts promote walking effortlessly and conventional automobile-oriented residential developments cannot. [ABSTRACT FROM AUTHOR]

Android is currently the most dominant platform in the market in comparison with all other operating systems (OS) such as iOS, Windows, and Blackberry. As the scope of Android value-added applications has grown, so also the increased risk of exploitation; thus, highlighting the dire need to protect user's privacy and data through malware detection and prevention. Among the two options—static and dynamic android malware detection, static has the inherent advantages of being fast and the first line of defense before application installation/execution; thus, same has been the focus of our work. Static malware analysis has been previously targeted in a number of works, with approaches ranging from machine learning (ML)-based models to statistical analysis techniques; however, the former has been determined to be more promising thus leading to our proposed neural network (NN)-based Real-device Malware Solution (RealMalSol). Our proposed solution not only provides improved accuracy of 96.4% with respect to the contemporary options but also ensures customized, scalable and optimized deployment for on-device analysis in contrast to emulator-based methods. To cater for limited computational capability of Android devices; we considered model optimization in two steps; as a first efficient Feature Reduction (FR) is applied to reduce the model complexity without adversely impacting the accuracy, and next optimized transformation of the model to a lightweight construct has been analyzed in TensorFlow Lite. The accuracy of RealMalSol improved from 95.2% to 96.40% using feature reduction in the full dataset. Moreover, the resultant model also performed proficiently on Android devices due to the careful selection of the best quantization-based optimization after rigorous analysis. [ABSTRACT FROM AUTHOR]

A novel robust Kalman filter (KF)-based controller design approach is proposed to accurately track a specified trajectory under unknown stochastic disturbance, known deterministic disturbance, and measurement noise. The system is nonlinear and is approximated by a piecewise-linear dynamic model. The Box–Jenkins model is an augmented model of the signal and the disturbance, is non-controllable and observable, while the signal model is controllable and observable. An emulator-based two-stage identification is employed to obtain an accurate system model needed to design the robust controller. The system and its KF are identified, and the signal and output errors are estimated. From the identified models, the signal, its KF, the disturbance model, and the whitening filter are all obtained using balanced model reduction techniques. It is shown that the signal model is a transfer matrix description relating the system output and KF residual, and the residual is the whitened output error. The disturbance model is identified by inverse filtering. A new combined feedforward–feedback controller is designed and implemented using an internal model of the reference driven by both the error between the reference and the signal estimate, and by the feedforwarded reference signal. The proposed scheme was successfully evaluated on a simulated autonomously guided drone. [ABSTRACT FROM AUTHOR]

The complete automation of materials manufacturing with high productivity is a key problem in some materials processing. In floating zone (FZ) crystal growth, which is a manufacturing process for semiconductor wafers such as silicon, an operator adaptively controls the input parameters in accordance with the state of the crystal growth process. Since the operation dynamics of FZ crystal growth are complicated, automation is often difficult, and usually the process is manually controlled. Here we demonstrate automated control of FZ crystal growth by reinforcement learning using the dynamics predicted by Gaussian mixture modeling (GMM) from small numbers of trajectories. Our proposed method of constructing the control model is completely data-driven. Using an emulator program for FZ crystal growth, we show that the control model constructed by our proposed model can more accurately follow the ideal growth trajectory than demonstration trajectories created by human operation. Furthermore, we reveal that policy optimization near the demonstration trajectories realizes accurate control following the ideal trajectory. [ABSTRACT FROM AUTHOR]

Software application when executed on computer systems having disparate hardware features, result in dissimilar performance and power. Therefore, selecting systems with optimal performance and power values for application execution is an essential problem to address. However, access to many physical systems is required to collect performance power, which is a demanding task. Therefore, our first objective is to build an accurate prediction model for physical systems to achieve the second objective of computer system selection. To achieve the first objective, we propose a novel model, "cross performance and power prediction with scaling." We develop a cross prediction model for physical systems by training a decision tree machine learning algorithm on performance and power datasets obtained from a large number of simulation systems built in the Gem5 simulator using emulation mode. However, design differences between Gem5 systems and physical systems lead to large prediction inaccuracies. We determine the application-specific "scaling factor" to compensate for the prediction inaccuracies and apply it to the predicted values for accurate physical systems predictions. We evaluate our model on well-known applications from SD-VBS and MiBench benchmarks achieving errors of 10–25% and 6–40% for performance and power for general-purpose systems. With accurate predictions for physical systems from our model, we achieve the second goal of computer system selection. [ABSTRACT FROM AUTHOR]

In current years, increased number of cyberspace users cause rapid ascends of network traffics. For instance: probability of receiving network traffic ever since software technologies that linked with devices produced massive amounts of data which are unable to accommodate through conventional schemes port based, payload based and machine learning approaches. Simultaneously SDN technology can alleviate problems of conventional method in classifying network traffic as malicious and benign, resources allocation, network monitoring along with enhancement in overall network performance via activist methods. This research work analyzed the net traffic metadata of 1,04,345 samples gathered from RYU-SDN controller, an OpenFlow controller using mininet emulator with 23 features then performed encrypted metadata categorization into three classes namely TCP, UDP and ICMP attacks through deep CNN with two layers LSTM, CNN-two layers GRU and ConvNet Bidirectional with two layers GRU approaches with hyper parameters tuning appropriate for better network convergence, performance, optimization too. The proposed experimental outcomes reveals that deep based CB-GRU method fulfill traffic classification in SDN environment and accomplished significance enhancement in terms of accuracy 99.97%, and loss rate 0.01. Other evaluation criterias precision, recall, area under curve, were calculated for performance identification in net data traffic classification than conventional methods. [ABSTRACT FROM AUTHOR]