Bayesian Optimization Model Research Articles

Cell viability prediction and optimization in extrusion-based bioprinting via neural network-based Bayesian optimization models

The fields of regenerative medicine and cancer modeling have witnessed tremendous growth in the application of 3D bioprinting. Maintaining high cell viability throughout the bioprinting process is crucial for the success of this technology, as it directly affects the accuracy of the 3D bioprinted models, the validity of experimental results, and the discovery of new therapeutic approaches. Therefore, optimizing bioprinting conditions, which include numerous variables influencing cell viability during and after the procedure, is of utmost importance to achieve desirable results. So far, these optimizations have been accomplished primarily through trial and error and repeating multiple time-consuming and costly experiments. To address this challenge, we initiated the process by creating a dataset of these parameters for gelatin and alginate-based bioinks and the corresponding cell viability by integrating data obtained in our laboratory and those derived from the literature. Then, we developed machine learning models to predict cell viability based on different bioprinting variables. The trained neural network yielded regression R2 value of 0.71 and classification accuracy of 0.86. Compared to models that have been developed so far, the performance of our models is superior and shows great prediction results. The study further introduces a novel optimization strategy that employs the Bayesian optimization model in combination with the developed regression neural network to determine the optimal combination of the selected bioprinting parameters to maximize cell viability and eliminate trial-and-error experiments. Finally, we experimentally validated the optimization model’s performance.

Reducing the Environmental Impact of Wireless Communication via Probabilistic Machine Learning

Machine learning methods are increasingly adopted in communications problems, particularly those arising in next generation wireless settings. Though seen as a key climate mitigation and societal adaptation enabler, communications related energy consumption is high and is expected to grow in future networks in spite of anticipated efficiency gains in 6G due to exponential communications traffic growth. To make meaningful climate mitigation impact in the communications sector, a mindset shift away from maximizing throughput at all cost and towards prioritizing energy efficiency is needed. Moreover, this must be adopted in both existing (without incurring further embodied carbon costs through equipment replacement) and future network infrastructure, given the long development time of mobile generations. To that end, we present summaries of two such problems, from both current and next generation network specifications, where probabilistic inference methods were used to great effect: using Bayesian parameter tuning we are able to safely reduce the energy consumption of existing hardware on a live communications network by 11% whilst maintaining operator specified performance envelopes; through spatiotemporal Gaussian process surrogate modeling we reduce the overhead in a next generation hybrid beamforming system by over 60%, greatly improving the networks' ability to target highly mobile users such as autonomous vehicles. The Bayesian paradigm is itself helpful in terms of energy usage, since training a Bayesian optimization model can require much less computation than, say, training a deep neural network.

Artificial intelligence in healthcare: combining deep learning and Bayesian optimization to forecast COVID-19 confirmed cases.

Healthcare is a topic of significant concern within the academic and business sectors. The COVID-19 pandemic has had a considerable effect on the health of people worldwide. The rapid increase in cases adversely affects a nation's economy, public health, and residents' social and personal well-being. Improving the precision of COVID-19 infection forecasts can aid in making informed decisions regarding interventions, given the pandemic's harmful impact on numerous aspects of human life, such as health and the economy. This study aims to predict the number of confirmed COVID-19 cases in Saudi Arabia using Bayesian optimization (BOA) and deep learning (DL) methods. Two methods were assessed for their efficacy in predicting the occurrence of positive cases of COVID-19. The research employed data from confirmed COVID-19 cases in Saudi Arabia (SA), the United Kingdom (UK), and Tunisia (TU) from 2020 to 2021. The findings from the BOA model indicate that accurately predicting the number of COVID-19 positive cases is difficult due to the BOA projections needing to align with the assumptions. Thus, a DL approach was utilized to enhance the precision of COVID-19 positive case prediction in South Africa. The DQN model performed better than the BOA model when assessing RMSE and MAPE values. The model operates on a local server infrastructure, where the trained policy is transmitted solely to DQN. DQN formulated a reward function to amplify the efficiency of the DQN algorithm. By examining the rate of change and duration of sleep in the test data, this function can enhance the DQN model's training. Based on simulation findings, it can decrease the DQN work cycle by roughly 28% and diminish data overhead by more than 50% on average.

Machine Learning Driven Channel Thickness Optimization in Dual-Layer Oxide Thin-Film Transistors for Advanced Electrical Performance.

Machine learning (ML) provides temporal advantage and performance improvement in practical electronic device design by adaptive learning. Herein, Bayesian optimization (BO) is successfully applied to the design of optimal dual-layer oxide semiconductor thin film transistors (OS TFTs). This approach effectively manages the complex correlation and interdependency between two oxide semiconductor layers, resulting in the efficient design of experiment (DoE) and reducing the trial-and-error. Considering field effect mobility (𝜇) and threshold voltage (Vth ) simultaneously, the dual-layer structure designed by the BO model allows to produce OS TFTs with remarkable electrical performance while significantly saving an amount of experimental trial (only 15 data sets are required). The optimized dual-layer OS TFTs achieve the enhanced field effect mobility of 36.1cm2 V-1 s-1 and show good stability under bias stress with negligible difference in its threshold voltage compared to conventional IGZO TFTs. Moreover, the BO algorithm is successfully customized to the individual preferences by applying the weight factors assigned to both field effect mobility (𝜇) and threshold voltage (Vth ).

Bayesian optimization of 3D bioprinted polycaprolactone/magnesium oxide nanocomposite scaffold using a machine learning technique

3D bioprinting of polycaprolactone (PCL) is an additive manufacturing technique, fabricating 3D scaffolds with widespread applications in biomedical bone regeneration. PCL has favorable properties such as tunable mechanical, biological, cytocompatibility, and good printability. In addition, adding magnesium oxide (MgO) nanoparticles effectively enhance bioactivities and bone formation. However, several researchers are reported that PCL-MgO nanocomposite may face challenges in printability. Therefore, this study has focused on optimizing printing parameters to achieve enhanced mechanical and osteoconductivity properties, printability, and print resolution. A newly developed and cost-effective method, Bayesian optimization (BO), has been applied to achieve this objective. The developed model investigates and accelerates the optimization of printing parameters, including air pressure, printing speed, and nozzle temperature on printability and print resolution. Despite the wide search spaces of printing parameters, the BO model drastically reduces the number of experiments to 11 iterations in each target width. There is a good agreement between the model-predicted and actual values (91% in width). Besides, this model can be used to find optimum process parameters in printing gradient width filament to fabricate 3D gradient scaffolds.

PROBABILISTIC PREDICTIONS OF EQUILIBRIUM RIPPLE GEOMETRY FOR TIME-DEPENDENT SEAFLOOR MODELING

We present a new equilibrium ripple predictor using a machine learning approach that outputs a probability distribution of wave-generated equilibrium wavelengths and statistics including an estimate of ripple height, the most probable ripple wavelength, and sediment and flow parameterizations. The Bayesian Optimal Model System (BOMS) is an ensemble machine learning system that combines two machine learning algorithms and two deterministic empirical ripple predictors with a Bayesian meta-learner to produce probabilistic wave-generated equilibrium ripple wavelength estimates in sandy locations.

A Bayesian Optimization Model for Locating Emergency Service Units

A Bayesian Optimization Model for Locating Emergency Service Units

Deep Learning Method for Evaporation Duct Inversion Based on GPS Signal

Accurate evaporation duct prediction is one of the critical technologies for realizing the over-the-horizon impact of marine communication, ship radar, and other systems. Using GPS signals to invert evaporation ducts provides more benefits in terms of method realization and ease. In order to invert the evaporation duct from GPS-received power data, a deep learning technique based on Bayesian optimization is proposed to increase the prediction accuracy of evaporation ducts. The evaporation duct propagation mechanism of the GPS signal is explored. The GPS-received power is estimated using the two-parameter evaporation duct model, and a better neural network structure is built using Bayesian optimization. The study results show that the Bayesian optimization model has a smaller root mean square error (RMSE) than the human empirical model, which allows for rapid and accurate inversion of duct parameters even in noisy interference.

A machine learning approach to predicting equilibrium ripple wavelength

Sand ripples are geomorphic features on the seafloor that affect bottom boundary layer dynamics including wave attenuation and sediment transport. We present a new equilibrium ripple predictor using a machine learning approach that outputs a probability distribution of wave-generated equilibrium wavelengths and statistics including an estimate of ripple height, the most probable ripple wavelength, and sediment and flow parameterizations. The Bayesian Optimal Model System (BOMS) is an ensemble machine learning system that combines two machine learning algorithms and two deterministic empirical ripple predictors with a Bayesian meta-learner to produce probabilistic wave-generated equilibrium ripple wavelength estimates in sandy locations. A ten-fold cross validation of BOMS resulted in an adjusted R-squared value of 0.93 and an average root mean square error (RMSE) of 8.0 cm. During both cross validation and testing on three unique field datasets, BOMS provided more accurate wavelength predictions than each individual base model and other common ripple predictors.

Optimal Bayesian design for model discrimination via classification

Performing optimal Bayesian design for discriminating between competing models is computationally intensive as it involves estimating posterior model probabilities for thousands of simulated data sets. This issue is compounded further when the likelihood functions for the rival models are computationally expensive. A new approach using supervised classification methods is developed to perform Bayesian optimal model discrimination design. This approach requires considerably fewer simulations from the candidate models than previous approaches using approximate Bayesian computation. Further, it is easy to assess the performance of the optimal design through the misclassification error rate. The approach is particularly useful in the presence of models with intractable likelihoods but can also provide computational advantages when the likelihoods are manageable.

The Optimization Analysis of Phishing Email Filtering in Network Fraud based on Improved Bayesian Algorithm

Mail transmission was not only the main function of information system, but also the main way of network virus and Trojan horse transmission, which has a key impact on the running state of information. In order to deal with the threats of network viruses and Trojans and improve the level of e-mail management, this paper studies the filtering of information system, and proposes a phishing e-mail filtering method based on Improved Bayesian model. MATLAB simulation results show that the consistency p between the amount of data sent by e-mail and the amount received is good, the consistency rate reached 92.3%. the data security level is 95%, encryption proportion / data proportion ratio under Bayesian optimization are higher than those of unfiltered method，which up to 97.2%. Therefore, the Bayesian optimization model constructed in this paper can meet the needs of phishing email filtering in information communication at this stage.

Progressive Sampling-Based Joint Automatic Model Selection of Machine Learning and Feature Selection

In most machine learning applications, selecting an appropriate machine learning model requires advanced knowledge and many labor-intensive manual iterations. As a result, automatic machine learning is particularly important in order to lower the threshold for machine learning. In addition, feature selection is a very important data preprocessing process. Selecting important features can alleviate the dimension disaster problem, and removing irrelevant features can reduce the difficulty of learning tasks. The existing automatic selection methods cannot perform the automatic selection of machine learning model and feature selection model simultaneously on large-scale data. Therefore, in order to adapt to the rapid development of the era of big data, this paper proposes to establish a unified hyperparameter space for machine learning and feature selection, and adopt Bayesian optimization model based on progressive sampling for automatic model selection. By extensive experiments, we show that our approach can significantly reduce search time and classification error rates compared to the most advanced automated model selection methods.

Cryptocurrency direction forecasting using deep learning algorithms

Recently, the deep learning architecture has been used with an increasing rate for forecasting in financial markets. In this paper, the LSTM model is used to forecast the daily closing price direction of the BTC/USD. Both model accuracy and the profit or loss of the trades made based on the proposed model are analyzed. In addition, the effects of the MACD indicator and the input matrix dimension on forecasting accuracy are evaluated. The potential risks and actual risks encountered by the trader who trades based on the proposed model were also analyzed. The obtained results indicate that the optimization of the LSTM parameters using the Bayesian optimization model has enhanced the model’s accuracy. The results obtained from analyzing the drawdown and reward/risk resulting from the trades made based on the model show that the model enables the trader to trade with peace of mind due to the low level of actual risks and potential risks.

Bayesian forecasting with the structural damped trend model

In this paper we consider the structural damped trend model which is standard in the arsenal of forecasting analysis. We consider both the multiple sources of error (MSOE) as well as the single source of errors (SSOE). Relative to existing research, we propose Bayesian analysis for estimation and forecasting based on Markov Chain Monte Carlo techniques and, especially, the Gibbs sampler with data augmentation. Monte Carlo and empirical applications (from the M3 competition as well as data from the Bank of International Settlements) show the superior performance of the MOSE versus the SSOE model. We also document superior performance of the Bayesian MSOE model versus its sampling-theory counterpart. Additional evidence is provided by a Bayesian optimal model pool approach which determines optimal weights in combining predictive posterior distributions.

It's new, but is it good? How generalization and uncertainty guide the exploration of novel options.

How do people decide whether to try out novel options as opposed to tried-and-tested ones? We argue that they infer a novel option's reward from contextual information learned from functional relations and take uncertainty into account when making a decision. We propose a Bayesian optimization model to describe their learning and decision making. This model relies on similarity-based learning of functional relationships between features and rewards, and a choice rule that balances exploration and exploitation by combining predicted rewards and the uncertainty of these predictions. Our model makes 2 main predictions. First, decision makers who learn functional relationships will generalize based on the learned reward function, choosing novel options only if their predicted reward is high. Second, they will take uncertainty about the function into account, and prefer novel options that can reduce this uncertainty. We test these predictions in 3 preregistered experiments in which we examine participants' preferences for novel options using a feature-based multiarmed bandit task in which rewards are a noisy function of observable features. Our results reveal strong evidence for functional exploration and moderate evidence for uncertainty-guided exploration. However, whether or not participants chose a novel option also depended on their attention, as well as reflecting on the value of the options. These results advance our understanding of people's reactions in the face of novelty. (PsycInfo Database Record (c) 2020 APA, all rights reserved).

Machine-Learning Enabled Search for the Next-Generation Catalyst for Hydrogen Evolution Reaction

As a zero-emission, eco-friendly fuel, hydrogen gas can be generated via electrochemical (EC) water splitting. Achieving high-efficiency water splitting requires the use of a catalyst to minimize the overpotential to drive the hydrogen evolution reaction (HER). Noble metals such as platinum (Pt) can provide an excellent catalytic activity for HER but are too expensive and scarce for broad applications. Therefore, the development of active HER catalysts made from low-cost materials constitutes a crucial challenge in the utilization of hydrogen energy. Earth-abundant transition metal dichalcogenides (TMDs), such as molybdenum disulfide (MoS2), have been discovered recently, which exhibit good activity and stability for electrocatalytic reactions. In order to fully explore the untapped potential of MoS2, the synthesis recipe for MoS2needs to be optimized. Such an optimization process needs scientists to search through a combinatorically large space of experimental parameters, which will be time-consuming and costly if using conventional trial-and-error approaches. In this report, MoS2 HER catalytic activity optimization is performed by examining different combinations of synthesis parameters during the hydrothermal process. To investigate the structure-activity relationship, scanning electron microscope (SEM), X-ray diffraction (XRD), Raman spectroscopy and various electrochemical characterizations have been conducted. A strong correlation between hydrothermal conditions and HER performance matrix has been observed. In order toaccelerate the search for the best synthesis recipe, machine-learning (ML) techniques have been introduced to help identify the optimal parameter combinations for producing MoS2. The hydrothermal parameters with the corresponding onset potentials and Tafel slopes are adopted as prior knowledge and are incorporated into the Bayesian Optimization model. The model will be able to guide the wet chemical synthesis of MoS2and yield the most effective HER catalyst eventually.

A hybrid electricity price forecasting model with Bayesian optimization for German energy exchange

Electricity price forecasting affects the operation of the entire electricity market and it is extremely important to every market participant. In this paper, a novel hybrid method, with using empirical wavelet transform (EWT), support vector regression (SVR), Bi-directional long short-term memory (BiLSTM) and Bayesian optimization (BO), is proposed to increase the accuracy of electricity price forecasting. First, EWT is used as a processing tool to decompose the original signal into specific modal components according to the characteristics of the signal itself. Then, considering the complexity of forecasting nonlinear subseries, SVR and BiLSTM are used as basic framework to forecast the nonlinear subseries. At the same time, BO is introduced to adjust parameters and optimize model performance. In last, the final prediction results are combined by the prediction results of different models. The proposed hybrid model is employed on the data gathered from the European Power Exchange Spot (EPEXSPOT). Five different case studies are adopted to verify the effectiveness of BO, EWT and hybrid model respectively. Statistical tests of experimental results compared with other situations demonstrated the proposed hybrid model can achieve a better forecasting performance.

Joint modeling of reaction times and choice improves parameter identifiability in reinforcement learning models

BackgroundReinforcement learning models provide excellent descriptions of learning in multiple species across a variety of tasks. Many researchers are interested in relating parameters of reinforcement learning models to neural measures, psychological variables or experimental manipulations. We demonstrate that parameter identification is difficult because a range of parameter values provide approximately equal quality fits to data. This identification problem has a large impact on power: we show that a researcher who wants to detect a medium sized correlation (r = .3) with 80% power between a variable and learning rate must collect 60% more subjects than specified by a typical power analysis in order to account for the noise introduced by model fitting. New methodWe derive a Bayesian optimal model fitting technique that takes advantage of information contained in choices and reaction times to constrain parameter estimates. ResultsWe show using simulation and empirical data that this method substantially improves the ability to recover learning rates. Comparison with existing methodsWe compare this method against the use of Bayesian priors. We show in simulations that the combined use of Bayesian priors and reaction times confers the highest parameter identifiability. However, in real data where the priors may have been misspecified, the use of Bayesian priors interferes with the ability of reaction time data to improve parameter identifiability. ConclusionsWe present a simple technique that takes advantage of readily available data to substantially improve the quality of inferences that can be drawn from parameters of reinforcement learning models.