Multivariate Problem Research Articles

Use of machine-learning for monitoring solar thermal plants

A machine-learning algorithm (MLA) was developed to assess the operational state of solar thermal plants, based on the data of only one temperature sensor, and the irradiance and ambient temperature data from the nearest weather station. A detailed requirements analysis of the situation results in the classification of a multivariate time series problem. Neural networks used in the field of data science are ideally suited for problems of this type. Data from the operational monitoring system, which runs a rule-based algorithm, were used to train the neural network using the software framework TensorFlow. It was shown that the chosen MLA can detect malfunctions such as heat loss due to gravity-driven circulation during night. However, further development towards a practical tool requires not only far more data for training and validation. It became clear that corresponding pressure data are needed to classify temperature transients and to attribute these classes to certain malfunctions.

Beam Pointing Optimization Based Downlink Interference Mitigation Technique Between NGSO Satellite Systems

This letter proposes a novel interference mitigation technique for spectral coexistence between large-scale non-geostationary orbit (NGSO) satellite systems by optimizing satellite antenna beam pointing. Firstly, a dynamic exclusion zone of NGSO satellite antenna beam pointing is defined. Secondly, we transfer frequency compatibility problem between NGSO systems into a constrained nonlinear multivariate optimization problem considering the joint effect of link distances as well as angles between links and solve it using Genetic Algorithm (GA). Then we select actual working parameters of Starlink and OneWeb satellite systems to verify the effectiveness of proposed interference mitigation technique in the worldwide. The available time of the interfered system is up to 98.5% of total simulation run time after interference mitigation. The results show that the proposed interference mitigation technique can effectively mitigate the interference between NGSO satellite systems and guarantee signal to interference plus noise ratio (SINR) at the interfered earth station.

A vibration-based approach for health monitoring of tie-rods under uncertain environmental conditions

This work proposes a vibration-based damage detection approach for axially loaded beam-type structures. The potential of the adopted approach is shown with an application to structural health monitoring of tie-rods: these elements, widely used in civil structures to balance horizontal forces in arches, are normally subject to a significant change of the axial load under environmental and operating conditions. The related changes in the modal parameters are usually greater than those caused by damage, at least at an early stage, making it hard to separate the different effects. In this work, the confounding effect of environmental factors is filtered out by considering more than one vibration mode at a time, thus framing damage detection as a multivariate outlier detection problem. Two damage indexes are presented, based on modal parameters (eigenfrequencies and mode shapes) and a multivariate metric (the Mahalanobis squared distance). The reasons behind the potential of the proposed framework are shown on simulated data first. Then, this strategy is validated on data coming from experimental tests, where two nominally identical tie-rods have been monitored for several months under the effects of realistic environmental and operational conditions. Both indexes proved to be weakly influenced by environmental variations, mainly related to temperature, and thus suitable for automatic damage detection.

Dual-UAV Enabled Secure Data Collection With Propulsion Limitation

Unmanned aerial vehicles (UAVs) have been widely utilized to improve the end-to-end performance of wireless communications. However, its line-of-sight makes UAV communication vulnerable to malicious eavesdroppers. In this paper, we propose two cooperative dual-UAV enabled secure data collection schemes to ensure security, with the practical propulsion energy consumption considered. We first maximize the worst-case average secrecy rate with the average propulsion power limitation, where the scheduling, the transmit power, the trajectory and the velocity of the two UAVs are jointly optimized. To solve the non-convex multivariable problem, we propose an iterative algorithm based on block coordinate descent and successive convex approximation. To further save the on-board energy and prolong the flight time, we then maximize the secrecy energy efficiency of UAV data collection, which is a fractional and mixed integer nonlinear programming problem. Based on the Dinkelbach method, we transform the objective function into an integral expression and propose an iterative algorithm to obtain a suboptimal solution to secrecy energy efficiency maximization. Numerical results show that the average secrecy rate is maximized in the first scheme with propulsion limitation, while in the second scheme, the secrecy energy efficiency is maximized with the optimal velocity to save propulsion power and improve secrecy rate simultaneously.

Multi-Variable Multi-Objective Optimization Algorithm for Optimal Design of PMa-SynRM for Electric Bicycle Traction Motor

In this paper, internal division point genetic algorithm (IDP-GA) was proposed to lessen the computational burden of multi-variable multi-objective optimization problem using finite element analysis such as optimal design of electric bicycles. The IDP-GA could consider various objectives with normalized weighted sum method and could reduce the number of function calls with novel crossover strategy and vector-based pattern search method. The superiority of the proposed algorithm was verified by comparing performances with conventional optimization method at two mathematical test functions. Finally, the applicability of the IDP-GA in practical electric machine design was verified by successfully deriving an improved design of electric bicycle propulsion motor.

Identifying local barriers to access to healthcare services in Chile using a communitarian approach.

IntroductionPrevious research has used proxy variables or a unique construct to quantify healthcare access. However, there is a need for a different model that can handle this multivariable problem. This study seeks to develop a way to measure access to the local healthcare system with higher local resolution.MethodsA new survey was developed based on communitarian claims, following a behavioural model and an ontological framework. The survey was used to identify local barriers to healthcare services and the local preferences for priority settings. The results were analysed using multiattribute utility functions and individual weights were assigned by a panel of experts. National and regional indexes of access to healthcare were developed.ResultsThe survey contained seven modules and 104 questions. It was conducted on 1885 participants at 42 rural and 231 urban locations in three regions of Chile. The total disutility of the identified barriers to healthcare access at the national level was low (0.1448; values ranged between 0 and 1, with 1 representing a higher barrier) and was higher in the northern region (0.1467). The barriers associated with the health‐policy component showed the highest disutility value, and specific barriers for each community were identified.ConclusionsThese results have the potential to improve health decision‐making in Chile and can be used to assess the impacts of new health policy reforms. Although this model was tested in Chile, it can be adapted for use in any other country.Patient or Public ContributionParticipants contributed to this study by completing a survey, participating in general talks and receiving brochures with the results obtained from this study.

Graph-based algorithmic design and decision-making framework for district heating and cooling plant positioning and network planning

Although buildings are the single largest users of energy in cities, many individual building HVAC (heating, ventilation, and air conditioning) systems are energy inefficient. Sustainable district heating and cooling systems have been developed to address this inefficiency, however, the implementation of district heating and cooling systems is a complex, capital intensive multivariate problem. One critical engineering problem, the location of energy production plant and pipe network topology, has a major influence on the system performance as well as the life cycle cost, and therefore should be comprehensively studied and chosen. This paper proposes a novel algorithmic design and decision-making framework that uses multiple simultaneous criteria to generate and evaluate design alternatives of site selection and pipe network layout. The framework consists of three components: site location and topology generation, network sizing and evaluation, and multi-objective decision-making assistance. The proposed framework has been validated in a real-world district cooling greenfield project in China's metropolitan area. Results were compared against the engineers’ best practices. It has shown that the proposed framework could find equally good or better designs in engineering and financial performance with CAPEX reduction of up to 15%.

General approach to precise deformable mirror control.

We develop a simple and effective control method for accurate control of deformable mirrors (DMs). For a desired DM surface profile and using batches of observed surface profile data, the proposed method adaptively determines both a DM model (influence matrix) and control actions that produce the desired surface profile with good accuracy. In the first iteration, the developed method estimates a DM influence matrix by solving a multivariable least-squares problem. This matrix is then used to compute the control actions by solving a constrained least-squares problem. Then, the computed actions are randomly perturbed and applied to the DM to generate a new batch of surface profile data. The new data batch is used to estimate a new influence matrix that is then used to re-compute control actions. This procedure is repeated until convergence is achieved. The method is experimentally tested on a Boston Micromachines DM with 140 micro-electronic-mechanical-system actuators. Our experimental results show that the developed control approach can achieve accurate correction despite significant DM nonlinearities. Using only a few control iterations, the developed method is able to produce a surface profile root-mean-square error that varies from 5 - 30 [nm] for most of the tested Zernike wave-front modes without using direct feedback control. These results can additionally be improved by using larger data batches and more iterations or by combining the developed approach with feedback control. Finally, as we experimentally demonstrate, the developed method can be used to estimate a DM model that can effectively be used for a single-step open-loop DM control.

Internet traffic matrix prediction with convolutional LSTM neural network

With the rapid growing trend of Internet, prediction‐based network operation optimization and management has drawn the attention from both the academia and the industry. For predicting Internet traffic, deep learning models have been proven more effective than linear and statistical models. However, some of the previous studies model the Internet traffic prediction as a multivariate time series prediction problem simply, without using the Internet traffic matrix structure. In this letter, the Internet traffic matrix prediction problem is firstly modeled as a video prediction task. Then a ConvLSTM‐based Seq2Seq model named ConvLSTM‐TM is proposed for predicting the traffic matrix in the next time slot. Based on three real‐world traffic matrix datasets, ConvLSTM‐TM outperforms five deep learning baselines with a lower prediction error. For replication, the dataset, code, and results are publicly available in a Github repository.

A model-based sustainable productivity concept for the best decision-making in rough milling operations

There is a need in manufacturing as in machining of being more productive. However, at the same time, workshops are also urged for lesser energy waste in cutting operations. Specially, rough milling of impellers and bladed integrated disks of aircraft engines need an efficient use of energy due to the long cycle times. Indeed, to avoid dramatic tool failures and idle times, cutting conditions and operations tend to be very conservative. This is a multivariable problem, where process engineers need to handle several aspects such as milling operation type, toolpath strategies, cutting conditions, or clamping systems. There is no criterion embracing productivity and power consumption.In this sense, this work proposes a methodology that meets productivity and sustainability by using a specific cutting energy or sustainable productivity gain (SPG) factor. Three rough milling operations -slot, plunge nad trochoidal milling- were modelled and verified. A bottom-up approach based on data from developed mechanistic force models evaluated and compared different alternatives for making a slot, which is a common operation in that king of workpieces. Experimental data confirmed that serrated end milling with the highest SPG value of 1 is the best milling operation in terms of power consumption and mass removal rate (MRR). In the case of plunge milling technique achieve an SPG < 0.51 while trochoidal milling produces a very low SPG value.

Multivariate normality test based on kurtosis with two-step monotone missing data

This paper deals with a sample measure of multivariate kurtosis, which is used as a test statistic in multivariate normality testing problems. We define a new multivariate sample kurtosis measure to provide a multivariate normality test for data with a two-step monotone missing structure. Furthermore, we derive its expectation and variance using a perturbation method. To evaluate the accuracy of a normal approximation, we conducted a Monte Carlo simulation for certain parameters. Finally, we present a numerical example to illustrate the proposed procedure.

Real-time prediction of nuclear power plant parameter trends following operator actions

Operators in the main control room of a nuclear power plant (NPP) oversee all plant operations, and thus any human error committed by the operators can be critical. If the operators can be informed about the future trends of the significant plant parameters that will follow their actions, they will be able to detect a human error in a short time or even prevent it. Future parameter trends, in addition, can be used to confirm the appropriate operational plan and support accident diagnosis. To achieve fast and accurate future parameter trend prediction in NPPs, we propose a data-driven prediction model composed of a multi-step prediction strategy and artificial neural networks. To find the optimal model performance, we applied a multilayered perceptron, vanilla recurrent neural network, and long short-term memory (LSTM) network, and trained the various candidate models with emergency operation data generated from an NPP simulator. Application results showed that the prediction model with the multi-input multi-output strategy and LSTM networks was able to successfully address the multivariate problem of future parameter trend estimation considering operator action in multiple emergency situations. It is believed that the proposed model may support NPP operators in coping with human errors and diagnosing accidents.

Approximate Solutions of Nonlinear Partial Differential Equations Using B-Polynomial Bases

A multivariable technique has been incorporated for guesstimating solutions of Nonlinear Partial Differential Equations (NPDE) using bases set of B-Polynomials (B-polys). To approximate the anticipated solution of the NPD equation, a linear product of variable coefficients ai(t) and Bi(x) B-polys has been employed. Additionally, the variable quantities in the anticipated solution are determined using the Galerkin method for minimizing errors. Before the minimization process is to take place, the NPDE is converted into an operational matrix equation which, when inverted, yields values of the undefined coefficients in the expected solution. The nonlinear terms of the NPDE are combined in the operational matrix equation using the initial guess and iterated until converged values of coefficients are obtained. A valid converged solution of NPDE is established when an appropriate degree of B-poly basis is employed, and the initial conditions are imposed on the operational matrix before the inverse is invoked. However, the accuracy of the solution depends on the number of B-polys of a certain degree expressed in multidimensional variables. Four examples of NPDE have been worked out to show the efficacy and accuracy of the two-dimensional B-poly technique. The estimated solutions of the examples are compared with the known exact solutions and an excellent agreement is found between them. In calculating the solutions of the NPD equations, the currently employed technique provides a higher-order precision compared to the finite difference method. The present technique could be readily extended to solving complex partial differential equations in multivariable problems.

Analytical approach for maximizing self-consumption of nearly zero energy buildings- case study: Baltic region

Deployment of photovoltaic (PV) systems in nearly zero energy buildings is rapidly increasing, negatively affecting grid stability and power quality. Therefore, many utilities favour policies that limit the power injection to the grid and increase PV self-consumption. A battery energy storage system (BESS) could constitute a possible solution. However, BESS optimal scheduling to increase PV self-consumption and minimize potential purchased energy from the grid in the situation of non-supported demand by PV is a non-linear multi-variable decision-making problem. Previous works have used optimization algorithms to overcome this problem. Due to these algorithms' nature, instead of global optimum scheduling, just near-optimal results are achieved and the consistency of the results, which is essential especially for sensitivity analysis is not guaranteed. The main goal of this paper is to present an analytical approach to maximize the PV self-consumption and optimize BESS scheduling to minimize electricity costs for a two-level electricity tariff energy system. The effectiveness of the proposed analytical scheduling of the BESS-PV energy system is demonstrated through simulation on real data of a Nearly Zero Energy Building (nZEB) in the Baltic region, Estonia, as the case study. Compared with alternative optimization algorithms, the proposed approach leads to a significant reduction in the purchased energy from the grid, while maximizing PV self-consumption and also noticeably reducing computation complexity and time for reaching the global solution.

Functional ANOVA approaches for detecting changes in air pollution during the COVID-19 pandemic

Faced with novel coronavirus outbreak, the most hard-hit countries adopted a lockdown strategy to contrast the spread of virus. Many studies have already documented that the COVID-19 control actions have resulted in improved air quality locally and around the world. Following these lines of research, we focus on air quality changes in the urban territory of Chieti-Pescara (Central Italy), identified as an area of criticality in terms of air pollution. Concentrations of hbox {NO}_{{2}}, hbox {PM}_{{10}}, hbox {PM}_{2.5} and benzene are used to evaluate air pollution changes in this Region. Data were measured by several monitoring stations over two specific periods: from 1st February to 10 th March 2020 (before lockdown period) and from 11st March 2020 to 18 th April 2020 (during lockdown period). The impact of lockdown on air quality is assessed through functional data analysis. Our work makes an important contribution to the analysis of variance for functional data (FANOVA). Specifically, a novel approach based on multivariate functional principal component analysis is introduced to tackle the multivariate FANOVA problem for independent measures, which is reduced to test multivariate homogeneity on the vectors of the most explicative principal components scores. Results of the present study suggest that the level of each pollutant changed during the confinement. Additionally, the differences in the mean functions of all pollutants according to the location and type of monitoring stations (background vs traffic), are ascribable to the hbox {PM}_{{10}} and benzene concentrations for pre-lockdown and during-lockdown tenure, respectively. FANOVA has proven to be beneficial to monitoring the evolution of air quality in both periods of time. This can help environmental protection agencies in drawing a more holistic picture of air quality status in the area of interest.

A Multivariate Load Trading Optimization Method for Energy Internet Based on LSTM and Gaming Theory

Energy Internet is a complex nonlinear system. There are many stakeholders in the load trading market, which is usually regarded as a multi-player gaming. Although gaming theory has been introduced to solve Multivariate Load trading problems, different conditions should be considered to accurately optimize the multivariate load trading problem. For example, the selling side needs to reduce the reserve capacity and improve profits, but the consumer side needs to reduce costs and minimize the impact on its own electricity consumption. These contradictory conditions require multiple Nash equilibrium to achieve obviously. To address this issue, a unified architecture of the power system cloud trading is constructed in this paper, which is combined with the multiple load classification of the power system. In addition, according to the power market operation mechanism, a price-guided multivariate load trading game strategy is designed. More importantly, a multivariate load trading optimization method based on LSTM (Long Short-Term Memory) and gaming theory is proposed in this work. LSTM is introduced for real time prediction, which can be combined with the game theory for strategy searching. The global stability and optimal solution theory prove the feasibility of the proposed neural network, and finally the effectiveness of the proposed method is verified by using numerical simulation.

TIME SERIES FORECASTING USING ARTIFICIAL NEURAL NETWORK WITH EXTENDED ADAPTIVE LEARNING

Artificial neural network (ANN) mainly consists of learning algorithms, which are require to optimize the convergence of neural networks. We need to optimize the convergence of neural networks in order to improve the speed and accuracy of decision making process. To enable the optimization process one of the widely used algorithm is back propagation learning algorithm. Objective of study is to applied backpropagation algorithm for solving multivariate time series problem. To better the accuracy of neural network it is important to find optimized architecture for the problem under consideration. The learning rate is also an important factor which affects the performance of result. In this study, we proposed extended adaptive learning approach in which learning rate is adapted from number of previous iteration error trend in first half of training. In next half of training learning rate is adapted as per adaptive learning rate algorithm. Compare performance of three variation of backpropagationalgorithm. All these variation experimented on two standard dataset. Experimental result shows that during validation and training ANN with extended adaptive learning rate outperforms other than two variations.

Multivariate locally adaptive kernel density estimation

When the underlying density exhibits multiple modes with different scales and orientations, density estimators with locally adaptive smoothing parameters show substantial gains over those with fixed bandwidths. However, it is a concern that the local smoothing matrices may not be well parameterized, and the corresponding optimization problems will be difficult. In this paper, we build a more promising and practical algorithm. The local bandwidth factors are chosen through clustering, and the global smoothing parameter is achieved by optimizing the Asymptotic Mean Integrated Squared Error. Most importantly, our locally adaptive estimator involves optimizing a scalar rather than solving a costly multivariate optimization problem. Our method, which can also be applied to manifold density estimation, is an improvement and generalization of the binned version estimator of Sain.

A heuristic scheme for multivariate set partitioning problems with application to classifying heterogeneous populations for multiple binary attributes

We provide a novel heuristic approach to solve a class of multivariate set partitioning problems in which each item is characterized by three attribute values. The scheme first identifies a series of orderings of the items and then solves a corresponding sequence of shortest path problems. We provide theoretical findings on the structure of an optimal solution that motivate the design of the proposed heuristic scheme. The proposed algorithm runs in polynomial-time and is independent of the number of groups in the partition, making it more efficient than existing algorithms. To measure the performance of our solutions, we construct bounds for special instances which allow us to provide optimality gaps. We conduct an extensive numerical experiment in which we solve a large number of problem instances and show that our proposed approach converges to the global optimal solution in the vast majority of cases and in the case it does not, it yields very low optimality gaps. We demonstrate our findings with an application in the context of classifying a large heterogeneous population as positive or negative for multiple binary attributes as efficiently as possible. We conduct a case study on the screening of three of the most prevalent sexually transmitted diseases in the United States. The resulting solutions are shown to be within 2.6% of optimality and lead to a 26% cost saving over current screening practices.

Multivariate semi-blind deconvolution of fMRI time series

Whole brain estimation of the haemodynamic response function (HRF) in functional magnetic resonance imaging (fMRI) is critical to get insight on the global status of the neurovascular coupling of an individual in healthy or pathological condition. Most of existing approaches in the literature works on task-fMRI data and relies on the experimental paradigm as a surrogate of neural activity, hence remaining inoperative on resting-stage fMRI (rs-fMRI) data. To cope with this issue, recent works have performed either a two-step analysis to detect large neural events and then characterize the HRF shape or a joint estimation of both the neural and haemodynamic components in an univariate fashion. In this work, we express the neural activity signals as a combination of piece-wise constant temporal atoms associated with sparse spatial maps and introduce an haemodynamic parcellation of the brain featuring a temporally dilated version of a given HRF model in each parcel with unknown dilation parameters. We formulate the joint estimation of the HRF shapes and spatio-temporal neural representations as a multivariate semi-blind deconvolution problem in a paradigm-free setting and introduce constraints inspired from the dictionary learning literature to ease its identifiability. A fast alternating minimization algorithm, along with its efficient implementation, is proposed and validated on both synthetic and real rs-fMRI data at the subject level. To demonstrate its significance at the population level, we apply this new framework to the UK Biobank data set, first for the discrimination of haemodynamic territories between balanced groups (n=24 individuals in each) patients with an history of stroke and healthy controls and second, for the analysis of normal aging on the neurovascular coupling. Overall, we statistically demonstrate that a pathology like stroke or a condition like normal brain aging induce longer haemodynamic delays in certain brain areas (e.g. Willis polygon, occipital, temporal and frontal cortices) and that this haemodynamic feature may be predictive with an accuracy of 74 % of the individual’s age in a supervised classification task performed on n=459 subjects.