Use Of Adaptive Methods Research Articles

Development of a simulation model and adjustment of hyperparameters of a neural network for predicting possible states of a network of small space carriages

The purpose of the research is to develop a simulation model and tune the hyperparameters of a neural network to predict possible states of a network of small spacecraft.The research methods are based on the concepts of the theory of artificial intelligence to control a group of small spacecraft (SSV) – the use of adaptive methods and tools to make decisions, similar to the mechanisms of human thinking. In relation to space communication systems with a heterogeneous structure, artificial intelligence methods and technologies are aimed at predicting the state of communication channels between network nodes and automatically reconfiguring a network of devices based on neural network learning processes. One of the most important functions of network software for the application of cognitive algorithms is to predict the quality of communication between pairs of SSVs.Results. A method has been developed for using the Transformer architecture neural network to predict possible states of the SSV network, which provides aggregation and time synchronization of data on the state of the SSV network, their use for training the neural network, as well as using the neural network to predict the quality of communication. The data format for the training sample has been created, based on the representation of the state of the SSV network, which ensures the generation of the initial state of the network, modeling the proactive mode of its operation, collecting SSV network state markers to generate training data sets in the form of chronological sequences grouped into frames, and allowing to reduce the amount of data transferred between SSVs when creating a training set. A simulation model of the SSV network has been developed, which provides generation of the initial state of the network, modeling of the proactive mode of its operation, and collection of information about the state of the SSV network to generate sets of synthetic training data.Conclusion. The article develops a simulation model of the SSV network for generating synthetic training data and predicting possible states of the SSV network, as well as a method for using a neural network to predict possible states of the SSV network.

Selection of a Neural Network Architecture for Implementation of Cognitive Functions of Network Software for Control of a Group of Interacting Small Space Vehicles

The purpose of the research is to substantiate and select the architecture of a neural network for the possibility of implementing the cognitive functions of network software for controlling a grouping of interacting small spacecraft.Methods are based on the concepts of AI theory for managing the grouping of small spacecraft - the use of adaptive methods and tools that allow making decisions, similar to the mechanisms of human thinking. With regard to space communication systems with a heterogeneous structure, AI methods and technologies are aimed at the processes of predicting the state in communication channels between network nodes and automatic reconfiguration of the network of devices based on the learning processes of a neural network (NN).Results. In the learning and forecasting mode, it is necessary to use time series of parameters and coordinates of specific pairs of small spacecraft with non-zero line of sight. Especially for time series analysis, recurrent neural networks (RNN) are used, in particular, LSTM. The idea of RNN operation is to use as input data for the current forecast not only the state vectors of the SVs and their coordinates, but also the previous value of the communication quality, actual or predictive. The paper shows that the onboard computing power of a separate MSC does not allow performing forecasting and training on board. Therefore, a dedicated ground segment of forecasting and monitoring is required, which will collect a posteriori information, periodically train the cognitive model, use it to predict the quality of communication, and transmit the results to the network nodes to build data transmission routes.Conclusion. The analysis of modern solutions and the choice of neural network architecture for the implementation of the cognitive functions of the network software for controlling the grouping of interacting small spacecraft showed that the neural networks of the Transformer architecture, which are based on the mechanism of internal attention, most fully meet the requirements of the project. The Transformer architecture allows using the entirety of a priori data, has a high learning and forecasting speed.

Synthesis of an adaptive control system for unstable and deterministic chaotic processes with m-inputs and n-outputs

The paper proposes a method for solving the problem of synthesis of an adaptive control system for unstable and deterministic chaotic processes in the class of ‘dovetail’ catastrophes for objects with m-inputs and n-outputs. The synthesis problem is solved by the gradient-velocity method of Lyapunov vector functions. From the conditions of the aperiodic robust stability of the etalon model with the desired dynamics of the main control loop and the generalised configurable object, the control goal is achieved. One of the most promising ways of solving the problem of managing unstable and deterministic chaotic processes is the synthesis of a control system in the class of ‘swallowtail’ catastrophes and the use of adaptation methods. Selecting and studying a reference model, and employing the gradient-velocity method for a generalised configurable control object ensure robust stability, utilise current information effectively, and achieve desired system quality and management goals.

SIMULATION OF THE EXCHANGE RATE USING ECONOMIC AND MATHEMATICAL METHODS

The article is devoted to a comparative analysis of the use of adaptive methods and models, autoregressive models and neural networks in forecasting the exchange rate of the main reserve currencies: the euro, the Swiss franc, the Japanese yen and the British pound against the US dollar. In the course of the research, the works of Ukrainian and foreign scientists on this topic were reviewed and it was determined that the most used methods and models in forecasting the exchange rate based on time series are autoregression models (represented by ARIMA and SARIMA models), neural networks (represented by MLP and ELM architectures) and exponential smoothing methods. In the process of building the models, time series were examined for stationarity based on the Dickey-Fuller test and additive decomposition of the studied time series was performed to determine their main components (trend, seasonality, random component). Construction of forecast models was carried out, on the basis of which their comparative analysis took place. The main shortcomings and problems of using the selected methods are demonstrated and the best predictive models are determined. It is determined that the main drawback of all time series forecasting methods is their "adaptability" to the input data, and the desire to improve the estimation characteristics of the models as a result can lead to the fact that the forecasts differ significantly from the actual values. It was also determined that for forecasting the exchange rate of selected currency pairs, neural networks are best suited, which have both high evaluation characteristics and correspondence of the forecast to real values, and the MLP network shows better results compared to the ELM network. High evaluation characteristics are also demonstrated by adaptive models. However, the linear nature of the forecast does not allow adaptive models to make an accurate forecast in the long term. Although autoregressive models show worse estimation characteristics, they outperform neural networks in terms of matching real values for individual currency pairs.

Solution of the problem of synthesis of the main contour oftheadaptive controlsystem for unstableand deterministic chaotic processes with m-inputs and n-outputs in the «Hyperbolic umbilic» catastrophe class

An urgent problem in the conditions of uncertainty of the parameters of the control object and external influences, for the control of unstable and deterministic chaotic processes, is the use of adaptation methods. In this case, the reference model with the desired dynamics and the main control loop of the adaptive system are constructed in the catastrophe class “hyperbolic umbilic”, and the aperiodic robust stability of the reference model with the desired dynamics and the main control loop of the self-organizing adaptive system with an increased potential for robust stability is studied by the gradient-velocity method of the vector function Lyapunov.

REFERENCE MODEL SELECTION OF THE ADAPTIVE CONTROL SYSTEM FOR AN OBJECT WITH SINGLE-INPUT AND SINGLE-OUTPUT

One of the most promising ways to solve the problem of control in the conditions of uncertainty of the characteristics of the control object and external influences is the use of adaptation methods. The article proposes to investigate the asymptotic robust stability of the reference model with the desired dynamics, using the gradient-velocity method of the Lyapunov vector-function. Considering control systems as gradient systems, and Lyapunov functions as potential functions allowed us to develop a universal gradient-velocity method of the Lyapunov vector-function, which allows to investigate the aperiodic robust stability of the reference model by the desired dynamics.

Influence of a signal description model on the calculations of the efficiency indicators of optoelectronic systems

The work is aimed at establishing the boundaries of the use of models for describing signals in optoelectronic systems in calculating efficiency. A description of the signal formation process is proposed, taking into account the corpuscular and wave properties when registering signals in a wide range of intensities. A description of the statistical features of the output signals depending on the energy properties of the signal and noise components is proposed. It is shown that when describing the output signals of optoelectronic systems that register signals with different properties, Poisson and Gaussian distributions are used. The invariance of Poisson flows determines the description of an additive mixture of signal and background flows using Poisson flow. The efficiency of optoelectronic systems is calculated by the signal-to-noise ratio criterion based on the corpuscular and wave description of signals. Efficiency calculations have shown the expedience of using this criterion, provided that the statistical properties of signal and background flows are stabilized. It is shown that under the condition of changes in the energy characteristics of signals, from the point of view of the wave and corpuscular models, the statistical characteristics of the signals have different descriptions. The analysis of theoretical methods of signal analysis in optoelectronic systems is carried out, which is aimed at an adequate characteristic of the system operation, depending on the conditions of its operation. Taking into account the method of describing the process of receiving and processing signals will take into account additional statistical characteristics of signals, for example, an increase of the variance of the output signal. The use of adaptive methods for describing signals will make it possible to increase the efficiency of systems when receiving strong signals in a difficult interference environment, as well as when receiving weak signals

Development of a guideline for the treatment of generalized anxiety disorder with the ADAPTE method.

The aim was to develop a clinical guideline for managing generalised anxiety disorder in Primary Health Care and Mental Health, using guideline adaptation methods. A clinical guideline was developed, following the methods of the ADAPTE group, and implemented in a Primary Health Care District and in Mental Health Services in Spain. Regional University Hospital of Málaga and District of Primary Health Care Málaga-Guadalhorce (Spain). The participants were family physicians, psychiatrists and clinical psychologists. The phases of the process included definition of clinical scenarios, literature search and guidelines appraisal, elaboration of recommendations, conducting focus groups with users diagnosed with generalised anxiety disorder, linking the testimonials of users with recommendations, external review and implementation by multifaceted interventions. The final release included 49 Recommendations, of which 47 are from the 2011 NICE guidance for GAD and 2 of the 2011 NICE guideline for common mental disorder. Finally, seven recommendations needed to be adapted to the Spanish health care context, and three recommendations were excluded. A guideline aimed to improve the quality and effectiveness of the care provided to people with generalised anxiety disorder has been released. The use of adaptation methods has simplified the use of resources and time. This guideline and the process designed for its implementation constitute a suitable collection of resources for the improvement on detection and treatment of GAD in primary health care. Adaptation methods play a key role in the knowledge translation continuum.

The association of adaptive early phase study design and late phase study results in oncology using clinicaltrials.gov data.

e14078 Background: Traditional methods such as the 3+3 design developed in the 1940s continue to be used in the majority of early phase oncology studies. Researchers have found that the traditional methods identify the appropriate dose level only 30% of the time. Patients are also exposed to sub-therapeutic doses due to the conservative methods. With these limitations on traditional design options, innovative methods need to be developed, adopted and assessed. Methods: This quantitative study assessed the association of the design methods (adaptive versus traditional) used for early phase oncology studies (adaptive versus traditional) and the outcome of late stage clinical trials. Differences by cancer type and by drug classification were also assessed. A sample of studies for this analysis was extracted from the National Institute of Health Clinical registry and results database. The data used for the analysis was extracted by the Clinical Trials Transformation Initiative (CTTI) Aggregate Analysis of ClinicalTrials.gov (AACT). Results: When assessing study design and outcome, there were lower odds of a positive outcome when adaptive methods were used though this association was not statistically significant (OR [95% highest posterior density (HPD)]:0.66 [0.20, 1.21]). Among the different drug types, using adaptive compared to traditional methods was associated with significantly higher odds of a positive outcome for taxanes, OR: 2.75, 95% HPD: 1.01, 5.16) and other, OR: 3.23, 95% HPD: 1.58, 5.46) but no association among studies of monoclonal antibodies or protein kinase inhibitors. There were no significant associations between early phase study design and outcome in late phase studies by cancer type (lung, breast, other). Conclusions: While results associated with the use of adaptive methods were not significant, further research should be conducted using all completed oncology clinical trials in the database to more precisely determine the relationship between adaptive study design in early phase oncology studies and outcomes in late stage studies. In addition, improvements in traditional versus adaptive design capture in the ClinicalTrials.gov database needs to be considered.

Order effects in two-alternative forced-choice tasks invalidate adaptive threshold estimates.

Adaptive psychophysical methods are widely used for the quick estimation of percentage points (thresholds) on psychometric functions for two-alternative forced-choice (2AFC) tasks. The use of adaptive methods is supported by numerous simulation studies documenting their performance, which have shown that thresholds can be reasonably estimated with them when their founding assumptions hold. One of these assumptions is that the psychometric function is invariant, but empirical evidence is mounting that human performance in 2AFC tasks needs to be described by two different psychometric functions, one that holds when the test stimulus is presented first in the 2AFC trial and a different one that holds when the test is presented second. The same holds when presentations are instead simultaneous at two spatial locations rather than sequential. We re-evaluated the performance of adaptive methods in the presence of these order effects via simulation studies and an empirical study with human observers. The simulation study showed that thresholds are severely overestimated by adaptive methods in these conditions, and the empirical study corroborated these findings. These results question the validity of threshold estimates obtained with adaptive methods that incorrectly assume the psychometric function to be invariant with presentation order. Alternative ways in which thresholds can be accurately estimated in the presence of order effects are discussed.

Examination of the Efficiency of Algorithms for Increasing the Reliability of Information on Criteria of Harness and the Cost of Processing Electronic Documents

The task of analyzing the effectiveness of the functioning of electronic document management systems (EDMS) is formulated and the methodological basis for optimization is developed according to the criteria of reliability, complexity and cost of information processing. A technique for estimating the time of input, transmission, storage, processing, exchange of documents and increasing the reliability of information based on implemented and traditional approaches aimed at using statistical, logical, semantic and structural - technological relationships of document elements is proposed. Models and algorithms for optimizing the placement of electronic documents (ED) in databases and other information systems associated with the system have been developed. Methods are proposed to minimize the time of searching, processing, increasing the reliability of information and presenting the required document to the user. A computational scheme for solving the optimization problem based on the use of adaptive methods of stochastic random search, modeling by a truncated Markov chain and dynamic programming has been developed and implemented. The conditions for optimizing the values of the labor-intensiveness coefficients and the cost of information processing algorithms based on the application of linear constraints on their efficiency areas are studied. The experimental results of the gain coefficient in the reliability of the information obtained by the maximum rating score are obtained. The software package has been implemented and the values of the coefficient of efficiency of algorithms for increasing the reliability of information based on the use of adaptive random search, segmentation, semantic redundancy and lexicological synthesis of the structure of electronic documents have been analyzed

Use of Adaptive Methods to Solve the Inverse Problem of Determination of Composition of Multi-Component Solutions

This study considers solving the inverse problem of determination of salt or ionic composition of multi-component solutions of inorganic salts by their Raman spectra using artificial neural networks. From the point of view of data analysis, one of the key problems here is high input dimensionality of the data, as the spectrum is usually recorded in 1–2 thousand channels. The two main approaches used for dimensionality reduction are feature selection and feature extraction. In this paper, three feature extraction methods are compared: channel aggregation, principal component analysis, and discrete wavelet transformation. It is demonstrated that for neural network solution of the inverse problem of determination of salt composition, the best results are provided by channel aggregation.

Researching in volatile environments and the importance of adaptive methods for junior researchers

PurposeThe purpose of this paper is to examine the importance of adaptive methods for junior researchers undertaking research in volatile and dangerous environments.Design/methodology/approachThrough the presentation of two case studies of the authors’ own experiences in the field, the authors demonstrate the way the use of adaptive methods is crucial for junior researchers to overcome unforeseen obstacles and day-to-day difficulties presented by field studies in volatile locations. Finally, the authors address the gap in the methodological literature on how junior researchers can best communicate adaptive methods in the methodology section of his/her research project.FindingsThe authors argue the importance of embedding a first-person narrative into the methodology sections of the project as a clear way for a junior researcher to demonstrate elements fundamental to the data collection experience, thereby engaging the reader with crucial aspects of the research findings.Originality/valueThe need for junior researchers to draw on a greater degree of flexibility in the field when confronted by the challenges of conducting research in volatile environments is paramount to the success of the project. The authors offer, based on the experiences in the field, pragmatic techniques to addresses some of the “messiness” of field studies that allows the researcher to demonstrate the crucial importance of adaptive methods in the doctoral projects.

Planning Beyond the Next Trial in Adaptive Experiments: A Dynamic Programming Approach.

Experimentation is at the heart of scientific inquiry. In the behavioral and neural sciences, where only a limited number of observations can often be made, it is ideal to design an experiment that leads to the rapid accumulation of information about the phenomenon under study. Adaptive experimentation has the potential to accelerate scientific progress by maximizing inferential gain in such research settings. To date, most adaptive experiments have relied on myopic, one-step-ahead strategies in which the stimulus on each trial is selected to maximize inference on the next trial only. A lingering question in the field has been how much additional benefit would be gained by optimizing beyond the next trial. A range of technical challenges has prevented this important question from being addressed adequately. This study applies dynamic programming (DP), a technique applicable for such full-horizon, "global" optimization, to model-based perceptual threshold estimation, a domain that has been a major beneficiary of adaptive methods. The results provide insight into conditions that will benefit from optimizing beyond the next trial. Implications for the use of adaptive methods in cognitive science are discussed.

Adaptive methods of solving inverse problems for improvement of fidelity of molecular DNA computations

Elaboration of methods of monitoring of biochemical reactions with DNA strands is necessary to solve one of the main problems in creation of biocomputers--improvement of fidelity of molecular DNA computations. In this paper, the results of solution of inverse two-parameter problems of laser Raman spectroscopy on determination of the types and concentration of DNA nitrogenous bases in multicomponent solutions are presented. Comparative analysis of the three used methods of solving these problems has demonstrated convincing advantages of artificial neural networks and of the method of projection to latent structures. Use of adaptive methods allowed achieving the accuracy of determining the concentration of each base in two-component solutions about 0.2---0.4 g/L.

Robust adaptive feedforward control and achievable tracking for systems with time delays

A feedback/feedforward controller architecture is developed that characterises the achievable reference tracking of real time inputs for both minimum phase and non-minimum phase systems with time delays, when there are no modelling errors or external disturbances. This characterisation is obtained by factoring the plant into its minimum phase, non-minimum phase, and time delay components, which are used to design two feedforward controllers that inject signals into two points of the feedback loop. Design constraints are provided that determine both the types of signals that may be achieved, and the feedforward controllers that will generate that output. Of course, in practice, both modelling errors and external disturbances will be present. In this case, we develop robust analysis tools that both guide the feedback controller design process, and provide rigorous robust tracking performance that guarantees for the overall resulting closed-loop system. Robust methods for designing the feedforward controllers are presented, and numerical examples are provided. The performance of this architecture depends strongly on the choice of design parameters, and the accuracy of the plant model used. Hence, the use of adaptation methods is also considered, and it is shown that they can readily be employed to improve the performance of this control methodology.

Besov regularity for the Stokes and the Navier‐Stokes system in polyhedral domains

In this paper we study the regularity of solutions to the Stokes and the Navier‐Stokes system in polyhedral domains contained in ℝ3. We consider the scale Bsτ(Lτ), 1/τ = s/3 + 1/2 of Besov spaces which determines the approximation order of adaptive numerical wavelet schemes and other nonlinear approximation methods. We show that the regularity in this scale is large enough to justify the use of adaptive methods. The proofs of the main results are performed by combining regularity results in weighted Sobolev spaces with characterizations of Besov spaces by wavelet expansions.

Planning and Analyzing Adaptive Group Sequential Survival Trials

The use of adaptive methods has experienced increasing interest in the current literature on group sequential designs. Group sequential analysis in survival trials usually apply the error spending function approach due to the unpredictable amount of information available in an interim analysis. An alternative way is to apply adaptive methods where additionally the maximum amount of information and other designing parameters can be changed based on the information available at the interim stage. In this paper, it is shown how the inverse normal method can be used within a survival design using the log-rank test for comparing two survival functions. This method allows for many kinds of design modifications. In case of no modifications, the inverse normal method coincides with the commonly used analysis strategy. It is straightforward to specify effect estimates. Confidence intervals for the hazard ratio that can be calculated at each stage of the trial and intervals that can only be computed by the end of the trial are proposed. The latter also enables the calculation of median unbiased estimates. Overall p-values can be defined analogously. Properties of the analyses techniques are investigated and compared with alternative approaches. It is shown that the proposed analysis technique might help to rescue an underpowered study and opens the way to other types of changes in design. The proposed technique is implemented in the software ADDPLAN Adaptive Design, Plans and Analyses (http://www.addplan.com).

Adaptive control of distributed collector solar fields

Distributed collector solar fields are spatially distributed technical systems which aim at collecting and storing energy from solar radiation. They are formed by mirrors which concentrate direct incident sunlight in a pipe where an oil is able to accumulate thermic energy flows. From the control point of view, the objective consists of making the outlet oil temperature to track a reference signal by manipulating the oil flow, in the possible presence of fast disturbances caused by passing clouds. Significant levels of uncertainty motivate the use of adaptive methods. A confrontation between data-driven and model-driven adaptive control algorithms for distributed collector solar fields is made using experimental results and algorithm structure. A trade-off is shown to exist; i.e. by incorporating more information about plant dynamics, the control algorithms yield an increased performance, but they become plant dependent.

Statistical Consideration of Adaptive Methods in Clinical Development

ABSTRACT In recent years, the use of adaptive methods in clinical development based on accrued data has become very popular due to its flexibility in modifying trial procedures and/or statistical procedures of on-going clinical trials. However, it is a concern that the actual patient population after the modifications could deviate from the originally targeted patient population. Major modifications of trial procedures and/or statistical procedures of on-going trials may result in a totally different trial, which is unable to address the scientific/medical questions that the trial intends to answer. In this article, the impact on the target patient population, statistical inference, and power analysis for sample size adjustment after changes or modifications made to an on-going clinical trial is studied.