Recursive Method Research Articles

Feature selection using non-parametric correlations and important features on recursive feature elimination for stock price prediction

Stock price prediction using machine learning is a rapidly growing area of research. However, the large number of features that can be used can complicate the learning process. The feature selection method that can be used to overcome this problem is recursive feature elimination. Standard recursive feature elimination carries the risk of producing inaccurate algorithms because the top-ranked features are not necessarily the most important features. This research proposes a feature selection method that combines important features and nonparametric correlation in recursive feature elimination for stock price prediction. The data features used are technical indicators and stock price history. The recursive feature elimination method is modified with important features and nonparametric correlation features. The strategy for combining important features and non-parametric features is average weight, 25:75% weight, 75:25% weight, maximum weight, and minimum weight. The performance evaluation results show that the proposed feature selection method succeeded in obtaining small error values. The proposed method for predicting PT Bank Rakyat Indonesia Tbk (BBRI) stock prices obtains mean squared error, root mean square error, mean absolute error, and mean absolute percentage error evaluation values of 0.0000336, 0.00577, 0.00459, and 1.78%, respectively. This shows that recursive feature elimination with feature selection that combines important features and non-parametric correlation works better than the original recursive feature elimination at predicting stock prices.

Response spectrum-based analysis of airborne radar random vibration and multi-point control improvement

During the flight of a UAV (unmanned aerial vehicle), the LiDAR device undergoes random vibrations due to the changing flight attitude and wind speed conditions of the UAV. It is important to control the frequency and amplitude of the vibrations within a reasonable range by means of a damping structure. As the vibrations caused by various factors during flight are random and non-linear, this paper innovates the analysis principle and damping control means for the random vibrations of airborne optoelectronic devices. The response spectrum analysis theory is used to establish the shock response spectrum, and an optimised and improved recursive digital filtering method is used to fit the frequencies of random vibration to the synthetic shock response. Considering the uncertainty of the vibration excitation signal, a virtual excitation method is used for the first time to simulate the random vibration to which the radar may be subjected in the air, and to simplify the calculation steps. The shock plate structure is designed using a multi-point control method to innovate a passive response to the random excitation. Finally, a modal analysis of the synthesised impact response was carried out. It is verified that the first six modal frequencies are controlled within 220 Hz, realising the frequency reduction. The amplitude of the three x, y, and z directions is controlled to within 0.5 mm, thus achieving vibration damping.

Sequential Detection under Correlated Observations using Recursive Method

Sequential analysis has been used in many cases when the decision is supposed to be taken quickly such as for signal detection in statistical signal processing, namely sequential detector. For identical error probabilities, a sequential detector needs a smaller average sample number (ASN) than its counterpart of a fixed sample number quadrature detector based on Neyman-Pearson criteria. The optimum sequential detector was derived based on the assumption that the observations are uncorrelated (independent). However, in realistic scenario, such as in radar, the assumption is commonly violated. Using a sequential detector under correlated observations is sub-optimal and it poses a problem. It demands a high computational complexity, since it needs to recalculate the inverse and the determinant of the signal covariance matrix for each new sample taken. This paper presents a technique for reducing the computational complexity, which involves using recursive matrix inverse to subsequently calculate conditional probability density functions (pdf). This eliminates the need to recalculate the inverse and determinant, leading to a more reasonable solution in real-world scenario. We evaluate the performance of the proposed (recursive) sequential detector by using Monte-Carlo simulations and we use the conventional and non-recursive sequential detectors for comparisons. The results show that the recursive sequential detector has equal probabilities of false alarm and miss-detection with the conventional sequential detector and performs better than the non-recursive sequential detector. In terms of ASN, it maintains comparable results to the two conventional detectors. The recursive approach has reduced the computational complexity for matrix multiplication to from and it also has rendered the calculation of matrix determinant to be unnecessary. Therefore, by having better probabilities of error and reduced computational complexities under correlated observations, the proposed recursive sequential detector may become a viable alternative to obtain a more agile detection system as required in future applications, such as in radar and cognitive radio.

Research on Strategies to Improve the Dynamic Response Capability of Photovoltaic Inverters Based on Model Predictive Systems

While electronic technology has facilitated production and daily life, it has also brought certain issues, with leakage current being one of the most typical problems. Excessive leakage current can damage electrical equipment and even threaten the safety of personnel. Achieving maximum electrical safety has become a research hotspot in recent years. This paper, based on photovoltaic power generation systems, aims to improve the dynamic response capability of photovoltaic inverters through the establishment of predictive systems. The paper first analyzes the working principle and existing problems of model prediction, then lists the principles of three optimization schemes, including the introduction of virtual voltage, the two-step prediction method, and the recursive least squares method. It also analyzes the advantages and disadvantages of these three schemes and finally proposes the future development direction of using model prediction to suppress leakage current issues.

Branch error reduction criterion-based signal recursive decomposition and its application to wind power generation forecasting.

Due to the ability of sidestepping mode aliasing and endpoint effects, variational mode decomposition (VMD) is usually used as the forecasting module of a hybrid model in time-series forecasting. However, the forecast accuracy of the hybrid model is sensitive to the manually set mode number of VMD; neither underdecomposition (the mode number is too small) nor over-decomposition (the mode number is too large) improves forecasting accuracy. To address this issue, a branch error reduction (BER) criterion is proposed in this study that is based on which a mode number adaptive VMD-based recursive decomposition method is used. This decomposition method is combined with commonly used single forecasting models and applied to the wind power generation forecasting task. Experimental results validate the effectiveness of the proposed combination.

On computing finite index subgroups of PSL2(ℤ)

We present a method to compute finite index subgroups of PSL2(ℤ). Our strategy follows Kulkarni’s ideas, the main contribution being a recursive method to compute bivalent trees as well as their automorphism groups. As a concrete application, we compute all subgroups of index up to [Formula: see text]. We then use this database to produce tables with several arithmetical properties.

Optimizing the methodology for accurate and accessible slip length measurement with atomic force microscopy

The remarkable performance of cooling devices employing nano- and microscale channels has drawn considerable interest, highlighting the need for surfaces with large slip lengths to improve their efficiency. However, the large errors in slip length associated with existing techniques hinder a clear understanding of slip phenomena. In this paper, we evaluate existing analytical methods for slip length measurement with atomic force microscopy (AFM) and propose a new reliable method. We performed force curve measurements on mica, silica and highly ordered pyrolytic graphite surfaces in water using an AFM equipped with a colloidal probe. The obtained force curves were analyzed through three methods: two commonly utilized procedures, namely the recursive and intercept methods, and a novel one called the two-parameter method which we developed. Our analyses showed that the recursive method yielded slip lengths with relatively large errors, fluctuation of ±5.8 nm, which were due to inaccuracies in the cantilever's spring constant and the fluid viscosity. On the other hand, it was found that the intercept method leads to restrictions on the choice of fitting range because of the simplified formula for viscous drag. As a result, by altering the data range, the calculated slip length shows significant variations within the ranges of ±27.5 nm. The two-parameter method, unlike the standard ones, overcome these drawbacks. This method requires no pre-measured parameters, and the slip length fluctuation is independent of the fitting range and only ±3.6 nm, which is around 2/3 of that observed in the recursive method and 1/8 of that in the intercept method. Our study optimizes existing analytical protocols and offers a new way for accessible and reliable calculations of slip lengths.

Forest harvest operations productivity forecasting: a decisions tree approach

ABSTRACT In recent years, machinery used in forest harvesting operations has incorporated the ability to collect data during the harvesting operation automatically. The processing of these data allows for obtaining new perspectives on the harvest characteristics. In this sense, it is that the development of predictive models for harvest productivity is approached by processing the automatically retrieved data. In turn, these new models pave the way to develop new tools for operations management decision-making processes, providing a data-driven approach. In this case, forest productivity is analyzed based on different harvesting operational configurations defined by stand, trees, species, operators, shifts, etc. which make it possible to adequately predict what the wood-harvested volume will be, and thus, synchronize the rest of the supply chain logistics operations. The data processing is done through decision tree methods. Different methods of decision trees based on exhaustive Chi-square automatic interaction detection (CHAID), recursive binary partition, and conditional inference based that also uses binary recursive partition are tested. The results show that decision recursive binary partition methods tend to model the entire spectrum of the target variable in a more balanced manner. While exhaustive CHAID-based methods tend to be more accurate in global terms but more unbalanced. As a general comment of the method, global confusion matrices are around 50% accurate, and some operational configurations and productivity classes are predicted with almost 90% accuracy.

Fourier series method for the stability solution of simply supported thin beams on two-parameter elastic foundations of the Pasternak, Filonenko-Borodich, Hetenyi or Vlasov models

The analysis of stability problems of beams on two-parameter foundations (Bo2PFs) is an important part of their design for compressive loads. This work presents novel first principles derivation of the governing differential equations of elastic stability (GDES) of thin beams resting on two-parameter elastic foundations of the Pasternak, Filonenko-Borodich, Hetenyi or Vlasov models. The requirements of translational and rotational equilibrium of all the applied, reactive and internal forces on an infinitesimal segment of the Bo2PF and the laws of infinitesimal calculus were used to formulate the GDES as a fourth order ordinary differential equation (ODE) in terms of the transverse displacement function ux. The GDES is non-homogeneous in the presence of applied transverse load qx but homogeneous when qx vanishes. This study presents the Fourier series method (FSM) for solving the governing differential equation of stability (GDES) for the case of Dirichlet boundary conditions. The FSM has the advantage of amenability to differentiation, and integration due to the orthogonality properties of the sinusoidal functions. Implementation of the FSM by assuming the unknown function in the GDES as a Fourier series of infinite terms and the exploitation of orthogonalization simplifies the problem to an algebraic eigenvalue problem which is the characteristic buckling equation. The exact eigenvalues are found by algebraic solution of the buckling equation. The exact eigenvalues were used to find the exact buckling loads and the exact buckling load coefficients. The critical buckling load was found to correspond to the first buckling mode (n= 1), and is identical with previous solutions in the literature. Numerical calculations for the critical buckling load parameters Kcr were presented for the Bo2PF problem for values of the dimensionless foundation parameters k-1= 0, k-2= 0; k-1= 100, k-2= 0; k-1= 0, k-2= 1; k-1= 100, k-2= 100; k-1= 0, k-2= 2.5; k-1= 100, k-2= 2.5. The present solutions were compared with previous solutions for Kcr in the literature. The comparison shows that the present FSM results are identical with previous results obtained using various other methods such as Recursive Differentiation Method, Finite Element Method, Generalized Integral Transform Method (GITM) and Stodola-Vianello Iteration Method. The study has illustrated the effectiveness of the FSM for solving Bo2PFs.

Quantization-based distributed design strategy for adaptive consensus tracking of asynchronously switched nonlinear multiagent systems

We propose a quantization-based distributed consensus tracking design to resolve the unknown control direction problem of uncertain switched nonlinear multiagent systems under a fully quantized environment. All feedback and communication signals for the local control design are quantized and the control coefficient functions and directions of agents are unknown. Differing from the previous literature results, the primary contribution of this work is to present a quantization-based distributed design solution to the unknown control direction problem of asynchronously switched agents in the consensus tracking field. The non-differentiability problem of virtual control laws using quantized feedback signals is addressed by employing the filter-based recursive method and developing the analysis technique of the quantization errors of Nussbaum functions. Quantization effects in local adaptive neural control laws are compensated via the adaptive tuning mechanism using quantized states. The practical stability of the overall closed-loop system is established by the common Lyapunov theory. Illustrative simulations verify the efficacy of the proposed quantization-based consensus tracking approach.

An Improved On-Line Recursive Subspace Identification Method Based on Principal Component Analysis and Sliding Window for Polymerization

Polymerization products are indispensable for our daily life, and the relevant modeling process plays a vital role in improving product quality. However, the model identification of the related process is a difficult point in industry due multivariate, nonlinear and time-varying characteristics. As for the conventional offline subspace identification methods, the identification accuracy may be not satisfying. To handle such a problem, an enhanced on-line recursive subspace identification method is presented on the basis of principal component analysis and sliding window (RSIMPCA-SW) in this paper to obtain the state space model for polymerization. In the proposed on-line subspace identification approach, the initial L-factor is acquired by the LQ decomposition of the sampled historical data, firstly, and then it is updated recursively through the bona fide method after the new data have been handled by the sliding window rule. Subsequently, principal component analysis (PCA) is introduced to calculate the extended observation matrix, and finally the on-line model parameters are extracted. Compared with the traditional subspace schemes, smaller computation complexity and higher identification precision are anticipated in the proposed method. A case study on the modeling of the ethylene polymerization verifies the effectiveness of the developed approach, in which the related statistical indexes of the obtained identification model are better.

Cost optimal analysis for a differentiated vacation machining system with discouragement under the two threshold control policies

The present study explores the cost analysis for machine repair problem of queueing system using two-threshold control policies with discouragement and differentiated vacation. The way repairmen offer service has been established by two-threshold control policies based on queue size, with randomly distributed vacations of type A1 (full vacation) and type A2 (working vacation). Prior to the queue length being less than the lower threshold, both repairmen are on A1 type vacations. One repairman remains on A1 type vacation while the second repairman takes A2 type vacation if the queue length is in the intermediate range of the two thresholds. If the queue length is at or exceeds the upper threshold, both repairmen serve the queue to the best of their abilities. Meanwhile, during A1 and A2 types of vacations, failing machines exhibit impatience, which is a common occurrence in getting the service. It is supposed that vacation and repair time are exponentially distributed. The recursive method is utilized to calculate steady-state system probabilities. Furthermore, several metrics have been defined to measure the effectiveness of the system. A cost model is developed using system performance data for cost analysis. The Fibonacci search algorithm (FSA) and an artificial bee colony (ABC) are used to find the optimal value for the choice of variables with the lowest expected cost. A real-world instance demonstrating the implementation of the proposed model in practice will be shown at the end.

Whittaker vectors for W\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\mathcal {W}$$\\end{document}-algebras from topological recursion

We identify Whittaker vectors for Wk(g)\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\mathcal {W}^{\ extsf{k}}(\\mathfrak {g})$$\\end{document}-modules with partition functions of higher Airy structures. This implies that Gaiotto vectors, describing the fundamental class in the equivariant cohomology of a suitable compactification of the moduli space of G-bundles over P2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\mathbb {P}^2$$\\end{document} for G a complex simple Lie group, can be computed by a non-commutative version of the Chekhov–Eynard–Orantin topological recursion. We formulate the connection to higher Airy structures for Gaiotto vectors of type A, B, C, and D, and explicitly construct the topological recursion for type A (at arbitrary level) and type B (at self-dual level). On the physics side, it means that the Nekrasov partition function for pure N=2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$\\mathcal {N} = 2$$\\end{document} four-dimensional supersymmetric gauge theories can be accessed by topological recursion methods.

Optimal maintenance over a finite time horizon for a system under imperfect inspection and dynamic working environment

Inspections play a crucial role in determining the state of a system and informing timely maintenance decisions. However, due to the limitations of adopted inspection technologies, inspection errors are often inevitable. More importantly, the likelihood of such errors is often influenced by the system's working environment that varies over time and space. Despite this, most studies on imperfect inspections largely overlook the effects of such dynamic working environments on inspection errors. To address this gap, this paper proposes a maintenance policy accounting for imperfect inspections for a degrading system with hidden failures under a dynamic working environment. We develop two models based on a recursive method. The first model examines a case where the working environment affects only inspection errors, whereas the second one accounts for its impact on both inspection errors and the system's degradation process. Our focus is to determine the optimal interval and number of inspections that minimize the expected maintenance cost over a finite time horizon. Numerical examples are provided to illustrate the proposed method to ensure the effectiveness of maintenance actions. The optimization outcomes not only offer a valuable tool for engineers seeking to reduce maintenance costs but also shed light on broader managerial implications.

A characterization of sets realizable by compensation in the SNIEP

The symmetric nonnegative inverse eigenvalue problem (SNIEP) is the problem of characterizing all possible spectra of entry-wise nonnegative symmetric matrices of given dimension. A list of real numbers is said to be symmetrically realizable if it is the spectrum of some nonnegative symmetric matrix. One of the most general sufficient conditions for realizability is the so-called C-realizability, which amounts to some kind of compensation between the positive and negative entries of the list of real numbers whose realizability one is trying to decide. A combinatorial characterization of C-realizable lists with zero trace was given in [11]. In this paper we make use of a recursive method for constructing simmetrically realizable lists due to Ellard and Šmigoc [3] to extend this combinatorial characterization of C-realizability to general lists with nonnegative trace. One consequence of this characterization is that the set of nonnegative C-realizable lists is a union of polyhedral cones whose faces are described by equations involving only linear combinations with coefficients 1 and −1 of the entries in the list. Another remarkable consequence is the monotonicity of C-realizability, i.e., the operation of increasing any positive entry of a C-realizable list preserves C-realizability.

Implementation of Kalman filter algorithm to optimize the calculation of ultrasonic sensor distance value in Hooke law props system

The Kalman filter algorithm is very important as a recursive algorithm method to optimize sensor output from physical parameter measurement systems, especially physics practicum demonstration systems. One of the distance parameter measurement demonstration systems used in Hooke’s law demonstration system is applied in physics practicum, the system has problems related to fluctuating or unstable sensor output. This research implements the Kalman filter algorithm on the Arduino IDE sketch to reduce noise that appears at the ultrasonic sensor output. The methodology used in this study includes the application of the Kalman filter algorithm to the Arduino IDE sketch with the variable value of the Kalman filter algorithm equation modified with a value of R=10, H=1, and Q=1, and returns the filtered Kalman out value. The Arduino output results are exported to Ms. Excel for further analysis and generate a filtered ultrasonic sensor output signal graph compared without using the Kalman filter. The ultrasonic sensor output noise filtration effectively reduces noise by showing a decrease in the mean squared error (MSE) value and obtaining the best performance of up to 89.23 %. The accuracy of Kalman filter filtration results can be seen from the calculation that the spring constant of filtered metal materials is smaller than the conventional measurement spring constant. Accurate and effective results with the implementation of the Kalman filter algorithm can be developed for the variation values of distance parameters and Kalman filter algorithm variables (R, Q, and H) with other value variations, especially variables that produce filtering curves close to straight lines. It was concluded that the Kalman filter algorithm was able to improve the performance of Hooke’s law prop system

Integrating Meteorological and Remote Sensing Data to Simulate Cropland Nocturnal Evapotranspiration Using Machine Learning

Evapotranspiration (ET) represents a significant component of the global water flux cycle, yet nocturnal evapotranspiration (ETn) is often neglected, leading to underestimation of global evapotranspiration. As for cropland, accurate modeling of ETn is essential for rational water management and is important for sustainable agriculture development. We used random forest (RF) to simulate ETn at 16 globally distributed cropland eddy covariance flux sites along with remote sensing and meteorological factors. The recursive feature elimination method was used to remove unimportant variables. We also simulated the ETn of C3 and C4 crops separately. The trained RF resulted in a determination coefficient (R2) (root mean square error (RMSE)) of 0.82 (7.30 W m−2) on the testing dataset. C3 and C4 crops on the testing dataset resulted in an R2 (RMSE) of 0.86 (5.59 W m−2) and 0.55 (4.86 W m−2) for the two types of crops. We also showed that net radiation is the dominant factor in regulating ETn, followed by 2 m horizontal wind speed and vapor pressure deficit (VPD), and these three meteorological factors showed a significant positive correlation with ETn. This research demonstrates that RF can simulate ETn from crops economically and accurately, providing a methodological basis for improving global ETn simulations.

Cooling effects of the derived coolant-film layer from partitioned porous injectors for transpiration cooling

This study aims to reveal the cooling benefits of the derived coolant film from partitioned porous injectors for transpiration cooling. The near-wall flow development and the cooling performance are investigated based on various layouts of porous injectors. The numerical investigation is conducted using an in-house recursive regularized thermal lattice Boltzmann method (RR-TLBM). The validated RR-TLBM solver is accelerated by three Tesla V100 graphic processing units (GPUs) for the simulation of incompressible and coupled-domain transpiration cooling at high Reynolds numbers, based on high-resolution grids with 2.65 × 108 nodes. The results indicate that the near-wall flow shows high momentum with the partitioned porous injectors. And the mean velocity increases by more than 23 % with the same coolant consumption per unit blowing area, which contributes to the coolant-film development and cooling uniformity downstream. Moreover, the partitioned porous layout shows the possibilities of coolant reduction as compared to the single continuous porous injector in Case 1. A reduction of 43 % in total coolant consumption with the partitioned porous layout only results in a decrease of 6 % in cooling performance downstream. Additionally, the partitioned coolant injection improves local cooling performance by roughly 22 %, with better cooling homogeneity at the same total coolant consumption. Turbulent fluctuations are weakened in the partitioned coolant injection zones, which contributes to an improvement in cooling evenness. The partitioned porous layout can be an appropriate choice for transpiration cooling systems.

Controllable spin transport in a zigzag silicene nanoribbon embedding multiple rectangular quantum dots

Based on the recursive Green-function method together with Landauer–Büttiker formalism, the spin-dependent transport properties of electrons in a zigzag silicene nanoribbon embedding multiple rectangular quantum dots (QDs) are investigated. According to an analysis of the energy band under the periodically distributed electric field and exchange ferromagnetic field, the parallel exchange field induced by the ferromagnetic insulators eliminates the spin degeneracy, which leads to spin-polarized transport in the proposed structure. By tuning a periodic electric field, we found the relationship between the number of QDs and the splitting peak for conductance in the anti-parallel exchange field. We discover the population of electrons near QDs by calculating the local density of states. The effect of the geometry of periodic QDs on the shift of resonance peak is evaluated. The spin polarization is further explored for various configurations of electric field and exchange field in order to manipulate the spin filtering more effectively. The results provide an avenue to design a controllable spin bandpass filter with the modulation of electric field and exchange field.

Cost optimization and machine learning-based prediction of waiting time for fault-tolerance machining system with general vacation and F-policy

This study focuses on the queueing management, performance analysis, and cost optimization of a fault tolerance machining system (FTMS) that incorporates the multiple vacations of repairman and admission control F-policy (ACFP). The ACFP is an effective tool for managing the congestion problem that arises due to the arrival of failed machines for repair jobs in a system. This effectively controls the influx of failed machines and enhances the efficiency of the repair process. Furthermore, when there are no failed machines available in the system (i.e., the system is empty), the repairman may choose to take a vacation. After returning from vacation, if there are no failed machines available for repair, the repairman can take another vacation. For the mathematical analysis of the proposed model, the Chapman–Kolmogorov (C-K) steady-state equations are constructed and solved. This is achieved by introducing supplementary variables corresponding to vacation times, followed by using the Laplace-Stieltjes transform (LST) and recursive method to establish probability distributions. Furthermore, using the established probability distributions, various performance measures are developed to gain insights into the system’s behavior. These performance measures include the expected number of failed machines in the system, waiting time, machine availability, and other relevant metrics. Numerical simulation is carried out to assess the influence of input parameters on performance measures. Moreover, a machine learning approach employing regression methods is employed to predict the waiting time for failed machines to initiate their repair within the system. This combination of numerical simulation and machine learning analysis provides a comprehensive understanding of the system’s performance and enables accurate predictions of waiting times. Cost optimization is also performed for the FTMS using trapezoidal fuzzy numbers as cost elements by employing meta-heuristic techniques based on particle swarm optimization (PSO) and artificial bee colony (ABC) algorithms.