Hybrid Adaptive Algorithm Research Articles

Adaptive Filtering for Channel Estimation in RIS-Assisted mmWave Systems

The advent of millimeter-wave (mmWave) massive multiple-input multiple-output (MIMO) systems, coupled with reconfigurable intelligent surfaces (RISs), presents a significant opportunity for advancing wireless communication technologies. This integration enhances data transmission rates and broadens coverage areas, but challenges in channel estimation (CE) remain due to the limitations of the signal processing capabilities of RIS. To address this, we propose an adaptive channel estimation framework comprising two algorithms: log-sum normalized least mean squares (Log-Sum NLMS) and hybrid normalized least mean squares-normalized least mean fourth (Hybrid NLMS-NLMF). These algorithms leverage the sparse nature of mmWave channels to improve estimation accuracy. The Log-Sum NLMS algorithm incorporates a log-sum penalty in its cost function for faster convergence, while the Hybrid NLMS-NLMF employs a mixed error function for better performance across varying signal-to-noise ratio (SNR) conditions. Our analysis also reveals that both algorithms have lower computational complexity compared to existing methods. Extensive simulations validate our findings, with results illustrating the performance of the proposed algorithms under different parameters, demonstrating significant improvements in channel estimation accuracy and convergence speed over established methods, including NLMS, sparse exponential forgetting window least mean square (SEFWLMS), and sparse hybrid adaptive filtering algorithms (SHAFA).

Hybrid adaptive control for vibration reduction in the floating raft system based on FxLMS

To enhance the real-time performance of multi-frequency line spectrum vibration control within the floating raft system and minimize the vibration of the floating raft, a hybrid adaptive active vibration control algorithm based on the FxLMS algorithm is introduced. Focusing on the bottom degree of freedom in the floating raft system, a horizontal two-degree of freedom system is established. Initially, the dynamic model of this system is analyzed; subsequently, the hybrid adaptive control algorithm is analyzed theoretically, and its stability is verified by simulation under normal condition, shock disturbance condition, and random signal disturbance condition. The results reveal that the average control effects of feedforward control across each line spectrum under these conditions are −9.55 dB, −10.88 dB, and −9.91 dB, respectively. In contrast, hybrid adaptive control demonstrates stronger performance with average control effects of −23.19 dB, −21.65 dB, and −21.48 dB. Lastly, an experimental platform was established to assess the performance of the proposed control algorithm. The experimental results demonstrate that the hybrid adaptive control successfully mitigates vibrations arising from multiple frequency spectra. The hybrid adaptive control achieves average control effects of −14.77 dB, −15.13 dB, and −14.63 dB across the three conditions, demonstrating superior control efficacy.

Implementation of Hybrid Adaptive Learning Algorithm for Task Offloading

Objectives: Offloading tasks in edge computing (EC) plays an important role in optimizing resource utilization and enhancing the system performance. This paper studies various AI-based computation offloading (CO) strategies and proposes a hybrid Adaptive Learning Algorithm, that reduces the latency significantly compared to traditional RL-based on-policy and off-policy algorithms namely Q-Learning (QL) and State Action Reward State Action (SARSA) for CO in an EC environment. The paper evaluates and compares the efficiency of the proposed algorithms in optimizing dynamic offloading decisions, focusing on factors such as latency. Methods: The research is inspired by existing literature that has discovered the various applications of QL and SARSA in CO and mobile EC. This paper inspects how these algorithms perform in terms of reducing overall latency and proposes an adaptive hybrid algorithm. Novelty: Although other AI-based techniques exist in earlier research on CO in EC, the primary novelty proposed is the addition of a hybrid adaptive RL algorithm. Factors impacting the task offloading decision are crucial in the proposed algorithm. Moreover, the decision is not based only on static policies; the current state is the driving factor for decision-making. Findings: The exploration and exploitation handshake is very promising in reducing latency, as seen in the simulation results. The proposed algorithm outperforms Q-Learning and SARSA in terms of latency. Keywords: Computation offloading, Mobile Edge Computing, Reinforcement learning, Q­learning, SARSA

A New Hybrid Adaptive Optimization Algorithm Based Wavelet Neural Network for Severity Level Prediction for Lung Cancer Dataset

A New Hybrid Adaptive Optimization Algorithm Based Wavelet Neural Network for Severity Level Prediction for Lung Cancer Dataset

Fast forward modeling of grounded electrical-source transient electromagnetic based on inverse Laplace transform adaptive hybrid algorithm

Frequency–time conversion is a crucial step in grounded electrical-source transient electromagnetic response calculation, and the performance of the algorithm is directly related to the overall accuracy and speed of forward modeling. In mainstream algorithms, algorithms with high accuracy often have slow computation speed while algorithms with high efficiency have unsatisfactory accuracy, especially when facing inversion problems that are difficult to meet requirements. This paper introduces three inverse Laplace transform algorithms for this problem: the Gaver–Stehfest algorithm, the Euler algorithm, and the Talbot algorithm. The performance of each algorithm in forward modeling was analyzed using half-space and layered models, and the optimal selection schemes for algorithm weight coefficients were provided. The numerical calculation results show that the Gaver–Stehfest algorithm has a unique advantage in computational efficiency, while the Talbot algorithm and Euler algorithm meet the accuracy requirements. After considering both accuracy and efficiency, the Talbot algorithm is selected to replace conventional algorithms for calculation of grounded electrical-source transient electromagnetic forward modeling. In addition, this paper combines the characteristics of the Gaver–Stehfest algorithm and the Talbot algorithm to implement an adaptive hybrid algorithm. This algorithm uses the Gaver–Stehfest algorithm for forward modeling in the early times and the Talbot algorithm to compensate for the decrease in accuracy in the later times. Through the comparison of forward modeling calculations, it can be seen that the hybrid algorithm proposed in this paper fully utilizes the advantages of both algorithms. The hybrid algorithm greatly improves computational speed while meeting accuracy requirements, and has significant advantages over conventional algorithms.

Medium spatiotemporal characteristics based global optimization method for energy efficiency trade-off issue in variable flow rate HVAC system

During the optimization and control processes of variable flow rate heating, ventilation, and air conditioning (HVAC) systems, the medium temporal and spatial characteristics often significantly influence the control effectiveness and energy efficiency of the overall system. Unfortunately, much of the existing research predominantly concentrates on enhancing the performance of specific individual components, neglecting the impact of medium temporal and spatial characteristics on the overall HVAC system performance. Consequently, issues such as energy efficiency trade-offs in practical systems remain inadequately addressed. In this paper, the medium spatiotemporal characteristics of HVAC systems are systematically illustrated and modeled. A novel optimization method based on these characteristics is proposed to improve the overall performance of the HVAC system. This method adopts an event-driven optimization strategy to determine the optimal timing with consideration of temporal characteristics, and an adaptive hybrid algorithm is proposed to determine the optimal setpoints with consideration of spatial characteristics. By comparing to conventional methods with constant setpoints, genetic algorithm (GA) based setpoints, and differential evolution (DE) based setpoints in both simulation test and experiment, the proposed method demonstrates the ability to reduce electricity consumption by 21.2%, 13.1%, and 10.0%, respectively. The methodology in this research provides significant guidance for engineers to promote the decoupling control and overall optimization of HVAC systems. Additionally, the results have referable values for implementing the most appropriate algorithm in practice.

Sunspot activity prediction based on adaptive hybrid algorithms

Sunspot activity prediction based on adaptive hybrid algorithms

Hybrid predictor-corrector numerical schemes: λ-tracking, sampled-data observers and data assimilation

This paper considers hybrid ordinary differential equation (ODE) solvers for process dynamics constructed by combining standard numerical schemes with standard observers. Specifically, we combine the first-order Euler scheme with a Luenberger observer. The key ideas are to take advantage of available process output information and to switch from the numerical scheme to the process output-driven observer when the numerical scheme alone would produce inadequate results. Within this setup, two tasks emerge: How to choose the observer gain? How to choose the step size in the numerical scheme? Underpinning our approach is a λ tracking-based sampled-data observer that invokes a λ dead zone. This λ tracking observer determines the observer gain and the numerical step-size adaptively. The resulting adaptive hybrid algorithm is a time-stepping numerical scheme. Using a sampled-data observer allows for process measurements to be only available at some discrete times, whilst adaptive tuning allows the gains and sampling times to adjust automatically to each other – rather than both being subjected to designer's choice. Results are illustrated with examples of simulation.

Automated measurement and hybrid adaptive identification method for kinematic calibration of hybrid machine tools

Kinematic calibration is an effective method for ensuring the accuracy of hybrid machine tools. Traditional calibration methods are limited by cumbersome operations and poor algorithm robustness. In this study, measurement methods and identification algorithms are studied, and a new calibration method is proposed. First, the configuration of the hybrid machine tool is described, and an error model is constructed. Then, an automated measurement method of tool center point position error for multiple test arbors is proposed using the R-test device. Subsequently, a hybrid adaptive identification algorithm is proposed by sequentially solving the unit inhomogeneity of the identification model, the rank deficiency produced by incomplete measurements, and the multicollinearity between error parameters. Finally, the efficacy of the proposed calibration method is verified through simulations and experiments. The proposed method significantly improves the calibration efficiency and accuracy and proposes a new solution for automated calibration.

DEVELOPMENT OF A METHOD FOR STUDYING TRAFFIC OF MULTISERVICE NETWORKS

Context. The constant growth in the volume of information, the increase in the speed of information flows in digital communication networks, as before, makes the task of assessing the service stability for traffic flows an urgent one. A simple solution to ensure high service stability is to build a network of sufficient capacity for any traffic that will be thrown at it. To solve the problems of analyzing telecommunication systems, it is necessary to have appropriate models and engineering methods that allow to assess the service stability and predict the characteristics of their operation based on measurement data. In these conditions, the development of new methods for analyzing the traffic of multiservice networks that provide simplicity of calculations and their acceptable accuracy becomes especially relevant.
 Objective. The purpose of this paper is to study the traffic and service stability for users.
 Method. We propose a hybrid method for detecting anomalies in multiservice network traffic that uses algorithms without identification, adaptation and Mamdani fuzzy inference. The peculiarity of multiservice traffic as an object for assessing the existence of anomalies is the presence of stochastic processes in it subject to different distribution laws. For the experimental evaluation of the proposed method and algorithms, we have chosen the Poisson and Pareto distribution laws that define the limiting cases of traffic regularity. The method allows for monitoring and managing faults in a multiservice network in order to determine the causes of their occurrence. The following requirements are imposed on the developed algorithms for detecting anomalies in the traffic on multiservice networks: functioning in real or near real time; maintaining a given service stability; simplicity of implementation. The algorithms belong to the class of adaptive hybrid algorithms for identifying traffic parameters. They are used for both stationary and nonstationary traffic. Traffic is modeled as stochastic processes. Each belongs to the corresponding class, which is determined by the law of distribution of stochastic processes.
 Results. Experimental evaluation of the proposed method and algorithms has shown that they allow us to estimate the trends of these stochastic processes in real time, with high accuracy and while maintaining the service stability.
 Conclusions. The application of the developed method of troubleshooting management in a multiservice environment helps to improve the service stability by timely detecting problems, reducing the time of their elimination and reducing downtime, which, in turn, affects the increase in service reliability.

Synchronization of train timetables in an urban rail network: A bi-objective optimization approach

As urban rail networks in big cities tend to expand, the synchronization of trains has become a key issue for improving the service quality of passengers because most urban rail transit systems in the world involve more than one connected line, and passengers must transfer between these lines. In contrast to most existing studies that focus on a single line, in this study, we focus on synchronized train timetable optimization in an urban rail transit network, considering the dynamic passenger demand with transfers as well as train loading capacity constraints. First, we propose a mixed-integer programming (MIP) formulation for the synchronization of training timetables, in which we consider the optimization of two objectives. The first objective is to minimize the total waiting time of passengers, involving arriving and transfer passengers. Our second objective is a synchronization quality indicator (SQI) with piecewise linear formulation, which we propose to evaluate the transfer convenience of passengers. Subsequently, we propose several linearization techniques to handle the nonlinear constraints in the MIP formulation, and we prove the tightness of our reformulations. To solve large-scale instances more efficiently, we also develop a hybrid adaptive large neighbor search algorithm that is compared with two benchmarks: the commercial solver CPLEX and a metaheuristic. Finally, we focus on a series of real-world instances based on historical data from the Beijing metro network. The results show that our algorithm outperforms both benchmarks, and the synchronized timetable generated by our approach reduces the average waiting time of passengers by 1.5% and improves the connection quality of the Beijing metro by 14.8%.

New Energy Power System Dynamic Security and Stability Region Calculation Based on AVURPSO-RLS Hybrid Algorithm

Using a high proportion of new energy is becoming the development trend of the modern power industry, with broad application prospects and potential threats to power system operation safety. This paper proposes a hybrid adaptive velocity update relaxation particle swarm optimization algorithm (AVURPSO) and recursive least square (RLS) method to quickly estimate the DSSR boundary using hyper-plane expression. Firstly, the operating point data in the high-dimension nodal injection space are analyzed using the AVURPSO algorithm to identify the key generators, equivalent search space, and critical points, which have relatively great effects on transient angle stability. The hyper-plane expression of the DSSR boundary, which matches the critical points best, is finally fitted by the RLS approach. Hence, the adopted algorithm is applied to rapidly approximate the DSSR boundary by hyper-plane expression in power injection spaces. Finally, the proposed algorithm is validated using a simulation case study on three wind farm regions of the actual Hami Power Grid of China using the DIgSILENT/Power Factory software. Consequently, the mentioned method effectively captures the security stability boundary of the new energy power system and realizes the three-dimensional visualization space of DSSR. By leveraging the DSSR, the state analysis can be conducted rapidly on several parameters, including security and stability assessments in relation to various energy supply capabilities. Meanwhile, these indices are calculated offline and applied online. The findings of this investigation confirm the efficacy and accuracy of the suggested modeling used in the analyzed system, offering technical assistance ensuring the stability of the new energy power system. The DSSR allows the rapid analysis of several parameters, including security and stability assessments with various energy supply capabilities.

Research on Ship Thrust Distribution Based on Adaptive Particle Swarm Bee Colony Hybrid Algorithm

Aiming at the thrust distribution problem of nonlinear constraint in ship dynamic positioning system, an adaptive hybrid particle swarm optimization and bee colony algorithm was proposed, which was based on particle swarm optimization and bee colony algorithm, and introduced by the adaptive idea and bidirectional stochastic optimization mechanism. The optimization objective function with the minimum energy consumption and the minimum error of the thruster system was established by fully considering the thrust feasible region, the change rate of thrust and rudder angle and other constraints. Simulation results show that this algorithm can solve the thrust distribution problem reasonably and efficiently.

Development of Hybrid Adaptive Neural Fuzzy Inference System-Based Evolutionary Algorithms for Flexural Capacity Prediction in Corroded Steel Reinforced Concrete Beam

Development of Hybrid Adaptive Neural Fuzzy Inference System-Based Evolutionary Algorithms for Flexural Capacity Prediction in Corroded Steel Reinforced Concrete Beam

Load Optimization Scheduling of Chip Mounter Based on Hybrid Adaptive Optimization Algorithm

A chip mounter is the core equipment in the production line of the surface-mount technology, which is responsible for finishing the mount operation. It is the most complex and time-consuming stage in the production process. Therefore, it is of great significance to optimize the load balance and mounting efficiency of the chip mounter and improve the mounting efficiency of the production line. In this study, according to the specific type of chip mounter in the actual production line of a company, a maximum and minimum model is established to minimize the maximum cycle time of the chip mounter in the production line. The production efficiency of the production line can be improved by optimizing the workload scheduling of each chip mounter. On this basis, a hybrid adaptive optimization algorithm is proposed to solve the load scheduling problem of the mounter. The hybrid algorithm is a hybrid of an adaptive genetic algorithm and the improved ant colony algorithm. It combines the advantages of the two algorithms and improves their global search ability and convergence speed. The experimental results show that the proposed hybrid optimization algorithm has a good optimization effect and convergence in the load scheduling problem of chip mounters.

Integrated proactive-reactive approach and a hybrid adaptive large neighborhood search algorithm for berth and quay crane scheduling under uncertain combination

<p style='text-indent:20px;'>The integrated berth and quay crane scheduling problem is frequently encountered in port management issue, and the dynamic random data obtained by the container terminals under uncertain combination usually makes it unworkable to execute the scheduling. To promote sustainability and adaptivity of container terminals, this paper focuses on developing an integrated proactive-reactive approach for berth and quay crane scheduling under the fluctuation of vessels' arrival time and breakdown of quay crane. The problem is modelled as a two-stage mixed integer program where the baseline schedule with robustness is established in the first stage, and the recovery schedule is established in the second stage. This study aims to minimize the total management cost deviation and total time deviation of the terminal scheduling, so as to implement minimal changes compared with the baseline schedule. Therefore, the scheduling performance such as robustness, recoverability and adaptability is considered. To solve this model, a hybrid adaptive large neighborhood search (HALNS) algorithm framework combined with variable neighborhood search is developed, and the greedy algorithm is developed to construct the initial feasible solution. The performance evaluation tests of the proposed algorithm are performed on the three scales of benchmark. Computational results indicate the strength of solution methods and effectiveness of the proposed model.</p>

A novel unbalanced weighted KNN based on SVM method for pipeline defect detection using eddy current measurements

Pipeline safety inspections are particularly important because they are the most common means of energy transportation. In order to avoid pipe leakage, eddy current inspection is often used in metal pipe defect detection. However, in practice, due to problems such as noise and interference, a small number of labeled pipeline defect samples, and unbalanced sample distribution, the detection task cannot be completed. To address the above problems, this study proposes an unbalanced weighted k-nearest neighbor (KNN) based on support vector machine (SVM) defect detection algorithm. The multi-segment hybrid adaptive filtering algorithm is adopted to improve the identification of strong interference and large noise eddy current signals in this paper while retaining useful information such as defects. At the same time, the unbalanced weighted KNN based on the SVM defect detection algorithm is used to solve the problems of low accuracy and large limitations of the algorithm. The experimental results show that, compared with the KNN and SVM algorithms, the detection rate, false detection rate, and missed detection rate of defects are significantly improved.

A hybrid bat-genetic algorithm for improving the visual quality of medical images

Efficient repression of noise in a medical image is a very significant issue. This paper proposed a method to denoise medical images by the use of a hybrid adaptive algorithm based on the bat algorithm (BA) and genetic algorithm (GA). Medical images can be often affected by different kinds of noise that decrease the precision of any automatic system for analysis. Therefore, the noise reduction methods are always utilized for increasing the Peak signal-to-noise ratio (PSNR) and the structural similarity index measure (SSIM) of images to optimize the originality. Gaussian noise and salt and pepper noise corrupted the used medical data, separately. The noise level to medical images was added noise variance from 0.1 to 0.5 to compare the performance of the de-noising techniques. In the analytical study, we apply different kinds of noise like Gaussian noise and salt-and-pepper noise to medical images for making these images noisy. The hybrid BA-GA model was applied on medical noisy images to eliminate noise and the performances have been determined by the statistical analyses such as PSNR, values are gotten 63.04 dB and 59.75 dB for CT and MRI images.

Hybrid Reverse Propagation ANN Adaptive Algorithm Based Deep Learning Image Processing for Pneumonia Detection

Pneumonia is a syndrome that is caused by bacterial lung disease. This disease is diagnosed using a chest X-ray. Early diagnosis is important for successful treatment. This disease can be diagnosed using X-rays. Sometimes it can be confused with another bacterial disease due to an unclear chest X-ray. Consequently, we need a computer-aided diagnostic system to guide doctors. In this, amalgam backhaul algorithms are introduced to achieve multilayer network erudition. System noise investigation is done using artificial neural network (ANN). The vgg19 convolution neural network model was used to create a user-friendly website for the diagnosis of this disease. Simulated artificial neural network hybrid adaptive backpropagation algorithm used for deep learning image processing method in our training phase. The test results for the vgg19 network are with an accuracy of 0.91.

Parameters exploration of SOFC for dynamic simulation using adaptive chaotic grey wolf optimization algorithm

One of the most important indicators of solid oxide fuel cells (SOFC) is to maximize their production capacity. In this paper, the optimal values of SOFC unit are achieved using the combined model of the multi-layer perceptron neural network and different meta-heuristic optimization algorithms, including particle swarm optimization, ant colony optimization algorithm, genetic algorithm, Grey Wolf Optimizer, Multi-Verse Optimization algorithm, Accelerated Grey Wolf Optimization, Chaotic Grey Wolf Optimization, and Adaptive Chaotic Grey Wolf optimization hybrid algorithm. This article calculates the optimal decision factors such as power, temperature, voltage, and electrolyte thickness. The fuel cell modeling method is done by neural network training based on available experimental data. And the hyper-parameters of the neural network are obtained by optimization algorithms. Standard Error (SE), Mean Squared Error (MSE), Mean Absolute Percentage Error (MAPE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), Relative absolute error (RAE), Pearson's correlation coefficient (R), and coefficient of determination (R2) are applied as evaluation criteria. Results are presented for testing, learning, and total data mode. Comparison between the proposed method results and other well-known algorithms showed that the Adaptive Chaotic Grey Wolf optimization hybrid algorithm was superior in terms of performance criteria.