Parameter Tuning Research Articles

MS3D: A Multi-Scale Feature Fusion 3D Object Detection Method for Autonomous Driving Applications

With advancements in autonomous driving, LiDAR has become central to 3D object detection due to its precision and interference resistance. However, challenges such as point cloud sparsity and unstructured data persist. This study introduces MS3D (Multi-Scale Feature Fusion 3D Object Detection Method), a novel approach to 3D object detection that leverages the architecture of a 2D Convolutional Neural Network (CNN) as its core framework. It integrates a Second Feature Pyramid Network to enhance multi-scale feature representation and contextual integration. The Adam optimizer is employed for efficient adaptive parameter tuning, significantly improving detection performance. On the KITTI dataset, MS3D achieves average precisions of 93.58%, 90.91%, and 88.46% in easy, moderate, and hard scenarios, respectively, surpassing state-of-the-art models like VoxelNet, SECOND, and PointPillars.

Automatic Conditioning of Marine Seismic Angle Stack Data With a Convolutional Neural Network

Misalignment of reflections is a common problem in migrated prestack seismic data, which occurs due to moveout correction with incomplete knowledge of the velocity model. This issue persists in partial angle stack data often used for amplitude versus offset (AVO) analyses, and is traditionally treated with residual moveout and trim static corrections. However, these methods require time-consuming velocity selection and parameter tuning, and commonly lead to spurious alignment of reflections with noise. Therefore, we train a convolutional neural network (CNN) on synthetic examples to automatically perform conditioning and alignment of angle stack data. First, two-dimensional synthetic common depth point (CDP) gathers are created using a convolutional modeling method, and then made into input-target pairs where the inputs are poorly moveout-corrected (using inaccurate normal moveout velocities) and the targets are accurately moveout-corrected. These input-target examples are split into angle stacks for the near, mid, and far offsets, and then used to train a CNN to transform the misaligned angle stacks into their more-aligned counterparts. In testing, the trained network increases the alignment of unseen synthetic data, improving the correlation with the target far offset trace from 0.76 to 0.85 on average. The network is applied on two field examples from offshore Norway with Class 3 and Class 2P AVO responses, respectively. In both cases, the angle stack data predicted by the network shows improved alignment, greater resolution in the far offset stacked section, and increased correspondence to a well-tie synthetic seismogram, all while retaining the AVO responses. The CNN predictions are compared to angle stack data following traditional conditioning (residual moveout and trim static corrections), with the results being of similar or greater quality. This method enables high quality conditioning of angle stack data at a fraction of the time required for conventional methods, and is easily adaptable to different datasets.

Variable resolution machine learning optimization of antennas using global sensitivity analysis.

The significance of rigorous optimization techniques in antenna engineering has grown significantly in recent years. For many design tasks, parameter tuning must be conducted globally, presenting a challenge due to associated computational costs. The popular bio-inspired routines often necessitate thousands of merit function calls to converge, generating prohibitive expenses whenever the design process relies on electromagnetic (EM) simulation models. Surrogate-assisted methods offer acceleration, yet constructing reliable metamodels is hindered in higher-dimensional spaces and systems with highly nonlinear characteristics. This work suggests an innovative technique for global antenna optimization embedded within a machine-learning framework. It involves iteratively refined kriging surrogates and particle swarm optimization for generating infill points. The search process operates within a reduced-dimensionality region established through fast global sensitivity analysis. Domain confinement enables the creation of accurate behavioral models using limited training data, resulting in low CPU costs for optimization. Additional savings are realized by employing variable-resolution EM simulations, where low-fidelity models are utilized during the global search stage (including sensitivity analysis), and high-fidelity ones are reserved for final (gradient-based) tuning of antenna parameters. Comprehensive verification demonstrates the consistent performance of the proposed procedure, its superiority over benchmark techniques, and the relevance of the mechanisms embedded into the algorithm for enhancing search process reliability, design quality, and computational efficiency.

Improved Droop Control Strategy for Microgrids Based on Auto Disturbance Rejection Control and LSTM

This thesis proposes an improved droop control strategy design based on active disturbance rejection control and LSTM. This strategy uses the droop control method to coordinately control the distributed generation units (DGs) in a microgrid to achieve stable operation of the microgrid system. Linear-Auto Disturbance Rejection Control (LADRC) is introduced and an improved LADRC is designed based on the error principle. A disturbance compensation link is introduced on the basis of traditional LADRC to form ILADRC and a droop control strategy is used. Instead of improving the PD controller in LADRC, an improved droop control strategy is formed, which not only achieves natural decoupling between powers, but also improves the system’s immunity and transient operation capabilities. At the same time, in order to achieve adaptive parameter tuning in the improved droop control strategy, this article introduces long short-term memory (LSTM) to form an adaptive improved droop control strategy which further improves the system’s immunity and robustness. This article builds a simulation model through the MATLAB/Simulink simulation experiment platform and tests PI control and traditional droop control. The strategy and the improved droop control strategy designed in this thesis are experimentally compared and verified, and simulation analysis and verification are conducted on the two working conditions. The simulation results clearly demonstrate the superiority of the improved droop control strategy over PI control and traditional droop control, indicating that the correctness and reliability under various working conditions are verified.

Generalized kudryashov and extended auxiliary equation methods for novel solitons solutions to (1+1)-dimensional doubly dispersive equation of murnaghan’s rod

Abstract In this study, the Generalized Kudryashov method and the Extended Auxiliary Equations method are employed to investigate the strongly nonlinear (1+1)-dimensional Doubly Dispersive equation model of inhomogeneous Murnaghan’s rod for developing novel soliton solutions. These symbolic methods are famous for solving various problems involving nonlinear partial differential equations. The study finds novel solitons like hyperbolic, exponential, rational, and trigonometric. Moreover, 2D, 3D, and contour plots under tunable parameters depict graphical representations of the solutions that furnish dynamic wave behavior and insights into the material’s elastic properties under strain and stress.

Topology in a one-dimensional plasmonic crystal: the optical approach

Abstract In this paper we study the topology of the bands of a plasmonic crystal composed of graphene and of a metallic grating. Firstly, we derive a Kronig–Penney type of equation for the plasmonic bands as function of the Bloch wavevector and discuss the propagation of the surface plasmon polaritons on the polaritonic crystal using a transfer-matrix approach considering a finite relaxation time. Second, we reformulate the problem as a tight-binding model that resembles the Su–Schrieffer–Heeger (SSH) Hamiltonian, one difference being that the hopping amplitudes are, in this case, energy dependent. In possession of the tight-binding equations it is a simple task to determine the topology (value of the winding number) of the bands. This allows to determine the existense or absence of topological end modes in the system. Similarly to the SSH model, we show that there is a tunable parameter that induces topological phase transitions from trivial to non-trivial. In our case, it is the distance d between the graphene sheet and the metallic grating. We note that d is a parameter that can be easily tuned experimentally simply by controlling the thickness of the spacer between the grating and the graphene sheet. It is then experimentally feasible to engineer devices with the required topological properties. Finally, we suggest a scattering experiment allowing the observation of the topological states.

Inverse modeling of electromagnetic emissions using grey wolf optimization

The paper proposes an inverse modeling approach for evaluating radiated electromagnetic compatibility (EMC) in electronic components and circuits. To imitate the electromagnetic behavior of real devices, the suggested methodology generates an equivalent model using elementary dipoles. The Grey Wolf Optimization (GWO) algorithm solves an inverse problem to identify dipole parameters such as locations, intensities, and orientations. This technique improves model accuracy and robustness through a two-phase exploration and exploitation process that allows for effective parameter tuning while reducing simulation time and computational resources. Recent research in near-field measurement techniques illustrates the importance of reliable predictive methodologies in EMC evaluation. This method provides significant information on the impacts of power systems on surrounding electronic circuits, making it a useful tool for EMC testing. It also promotes the development of immunity models for high-frequency applications. Overall, this methodology simplifies the examination procedure, resulting in higher design efficiency for a wide range of electronic systems.

Forecasting age distribution of life-table death counts via α-transformation

We introduce a compositional power transformation, known as an α-transformation, to model and forecast a time series of life-table death counts, possibly with zero counts observed at older ages. As a generalisation of the isometric log-ratio transformation (i.e. α = 0 ), the α transformation relies on the tuning parameter α, which can be determined in a data-driven manner. Using the Australian age-specific period life-table death counts from 1921 to 2020, the α transformation can produce more accurate short-term point and interval forecasts than the log-ratio transformation. The improved forecast accuracy of life-table death counts is of great importance to demographers and government planners for estimating survival probabilities and life expectancy and actuaries for determining annuity prices and reserves for various initial ages and maturity terms.

Analysis of Fractional Resonant Controllers for Voltage-Controlled Applications

This paper investigates the application of fractional proportional–resonant controllers within the voltage control loop of grid-forming inverters. The use of such controllers introduces an additional degree of freedom, enabling greater flexibility in manipulating frequency trajectories. This flexibility can be harnessed to improve tracking error and enhance disturbance rejection, particularly in applications requiring precise voltage regulation. The paper conducts a conceptual stability analysis of ideal fractional proportional–resonant controllers using the Nyquist criterion. A tuning procedure based on robustness criteria for the proposed controller is also addressed. This tuning strategy is used to compare different controllers under the same conditions. In addition, a sensitivity analysis is provided, comparing the performance of fractional proportional–resonant controllers with traditional proportional–resonant controllers equipped with harmonic compensation. The controller’s formulation and performance are validated through simulations and tested with a 20 kVA inverter under high non-linear loads. Compared to classical control approaches, the fractional tuning parameter enhances tracking performance, reduces phase delay, and improves disturbance rejection. These improvements are achieved with a controller designed to minimise computational demands in terms of memory usage and execution time.

Generalized Fused Lasso for Treatment Pooling in Network Meta-Analysis.

This work develops a generalized fused lasso (GFL) approach to fitting contrast-based network meta-analysis (NMA) models. The GFL method penalizes all pairwise differences between treatment effects, resulting in the pooling of treatments that are not sufficiently different. This approach offers an intriguing avenue for potentially mitigating biases in treatment rankings and reducing sparsity in networks. To fit contrast-based NMA models within the GFL framework, we formulate the models as generalized least squares problems, where the precision matrix depends on the standard error in the data, the estimated between-study heterogeneity and the correlation between contrasts in multi-arm studies. By utilizing a Cholesky decomposition of the precision matrix, we linearly transform the data vector and design matrix to frame NMA within the GFL framework. We demonstrate how to construct the GFL penalty such that every pairwise difference is penalized similarly. The model is straightforward to implement in R via the "genlasso" package, and runs instantaneously, contrary to other regularization approaches that are Bayesian. A two-step GFL-NMA approach is recommended to obtain measures of uncertainty associated with the (pooled) relative treatment effects. Two simulation studies confirm the GFL approach's ability to pool treatments that have the same (or similar) effects while also revealing when incorrect pooling may occur, and its potential benefits against alternative methods. The novel GFL-NMA method is successfully applied to a real-world dataset on diabetes where the standard NMA model was not favored compared to the best-fitting GFL-NMA model with AICc selection of the tuning parameter ( .

Improvement of Electric Fish Optimization Algorithm for Standstill Label Combined with Levy Flight Strategy

The Electric Fish Optimization (EFO) algorithm is inspired by the predation behavior and communication of weak electric fish. It is a novel meta-heuristic algorithm that attracts researchers because it has few tunable parameters, high robustness, and strong global search capabilities. Nevertheless, when operating in complex environments, the EFO algorithm encounters several challenges including premature convergence, susceptibility to local optima, and issues related to passive electric field localization stagnation. To address these challenges, this study introduces Adaptive Electric Fish Optimization Algorithm Based on Standstill Label and Level Flight (SLLF-EFO). This hybrid approach incorporates the Golden Sine Algorithm and good point set theory to augment the EFO algorithm’s capabilities, employs a variable-step-size Levy flight strategy to efficiently address passive electric field localization stagnation problems, and utilizes a standstill label strategy to mitigate the algorithm’s tendency to fall into local optima during the iterative process. By leveraging multiple solutions to optimize the EFO algorithm, this framework enhances its adaptability in complex environments. Experimental results from benchmark functions reveal that the proposed SLLF-EFO algorithm exhibits improved performance in complex settings, demonstrating enhanced search speed and optimization accuracy. This comprehensive optimization not only enhances the robustness and reliability of the EFO algorithm but also provides valuable insights for its future applications.

Detection of hidden drawings using multi-wavelength dynamic speckle, tuneable algorithms, and unsupervised learning

Abstract We implemented an experiment to reveal hidden drawings on papyrus, utilizing an optical technique based on the speckle phenomenon. The goal is to optimize the detection of hidden objects. Our approach proposes using multiple wavelengths for illumination and tuneable algorithms to process the dynamic speckle images. By implementing the suggested method, we generated various results with varying quality, contingent upon the tuneable algorithm parameters. It's feasible to identify the optimal parameter combination to achieve the most effective visualization of the recovered image. To streamline the selection of tuneable algorithms and mitigate reliance on subjective visual judgment, we employed unsupervised machine learning techniques to determine the conditions necessary to achieve optimal results. This approach simplifies the selection procedure and offers an objective and non-invasive method. Furthermore, the proposed procedure holds promise for extending its application to uncover hidden paintings, subsurface archaeological artefacts, and other dynamic speckle experiments.

Multi-classification prediction of PM2.5 concentration based on improved adaptive boosting rotation forest

Developing efficient, stable, and user-friendly methods and technologies for predicting air quality has contributed to environmental research and management. Most traditional machine learning (ML) models often struggle to efficiently process extensive air quality data and grapple with the challenge of imbalanced data distributions. To this end, we introduced a novel multi-strategy collaborative approach that incorporates weighted feature selection, an adaptive enhanced rotation forest algorithm, and Bayesian Optimization for parameter tuning. Moreover, to improve the transparency in black box ML models, the novel Shapley Additive Explanations (SHAP) method was applied to interpret the outputs and analyze the importance of individual variables. Through experiments on real air quality datasets, we have verified the accuracy of our proposed method in classifying air quality levels. Notably, our model demonstrated an average test set accuracy improvement of approximately 10 % in cities like Beijing, Tianjin, Shijiazhuang, and Baoding after hyperparameter optimization using Bayesian methods. Furthermore, compared to alternative algorithms, our model showed an improvement of 1–2 % in evaluation metrics. By introducing novel methodologies and tools, our research contributes significantly to the advancement of air quality classification technology and holds profound implications for informing environmental policy decisions.

Quantifying tumor specificity using Bayesian probabilistic modeling for drug and immunotherapeutic target discovery.

In diseases such as cancer, the design of new therapeutic strategies requires extensive, costly, and unfortunately sometimes deadly testing to reveal life threatening off-target effects. We hypothesized that the disease specificity of targets can be systematically learned for all genes by jointly evaluating complementary molecular measurements of healthy tissues using a hierarchical Bayesian modeling approach. Our method, BayesTS, integrates protein and gene expression evidence and includes tunable parameters to moderate tissue essentiality. Applied to all protein coding genes, BayesTS outperforms alternative strategies to define therapeutic targets and nominates previously unknown targets while allowing for incorporation of new types of modalities. To expand target repertoires, we show that extension of BayesTS to splicing antigens and combinatorial target pairs results in more specific targets for therapy. We expect that BayesTS will facilitate improved target prioritization for oncology drug development, ultimately leading to the discovery of more effective and safer treatments.

Optimised Deep Learning for Time-Critical Load Forecasting Using LSTM and Modified Particle Swarm Optimisation

Short-term electric load forecasting is critical for power system planning and operations due to demand fluctuations driven by variable energy resources. While deep learning-based forecasting models have shown strong performance, time-sensitive applications require improvements in both accuracy and convergence speed. To address this, we propose a hybrid model that combines long short-term memory (LSTM) with a modified particle swarm optimisation (mPSO) algorithm. Although LSTM is effective for nonlinear time-series predictions, its computational complexity increases with parameter variations. To overcome this, mPSO is used for parameter tuning, ensuring accurate forecasting while avoiding local optima. Additionally, XGBoost and decision tree filtering algorithms are incorporated to reduce dimensionality and prevent overfitting. Unlike existing models that focus mainly on accuracy, our framework optimises accuracy, stability, and convergence rate simultaneously. The model was tested on real hourly load data from New South Wales and Victoria, significantly outperforming benchmark models such as ENN, LSTM, GA-LSTM, and PSO-LSTM. For NSW, the proposed model reduced MSE by 91.91%, RMSE by 94.89%, and MAPE by 74.29%. In VIC, MSE decreased by 91.33%, RMSE by 95.73%, and MAPE by 72.06%, showcasing superior performance across all metrics.

Dual-Isometric Projected Entangled Pair States

Efficient characterization of higher dimensional many-body physical states presents significant challenges. In this Letter, we propose a new class of projected entangled pair states (PEPS) that incorporates two isometric conditions. This new class facilitates the efficient calculation of general local observables and certain two-point correlation functions, which have been previously shown to be intractable for general PEPS, or PEPS with only a single isometric constraint. Despite incorporating two isometric conditions, our class preserves the rich physical structure while enhancing the analytical capabilities. It features a large set of tunable parameters, with only a subleading correction compared to that of general PEPS. Furthermore, we analytically demonstrate that this class can encode universal quantum computation and can represent a transition from topological to trivial order. Published by the American Physical Society 2024

High-Q terahertz chirality enhancement using elliptical hole metasurface

Circular dichroism (CD) technology has garnered significant attention due to its extensive applications in ultra-sensitive biosensing and spin-selective optical frequency conversion. However, existing terahertz chiral structures are constrained by linewidth, which limits their effectiveness in narrowband signal processing. In this study, we propose the notion of quasi-bound states in the continuum (quasi-BIC) within a planar elliptical hole all-silicon terahertz metasurface that exhibits broken mirror symmetry. This approach achieves a CD value as high as 0.97, with a linewidth below 0.5 GHz and a Quality (Q)-factor reaching up to 107 in the 1.3 THz to 1.55 THz band, thereby enabling ultra-narrowband terahertz chirality. This method significantly enhances the Q-factor of optical resonant systems, reduces linewidth, and achieves strong CD while addressing the trade-off between high Q-factor and high CD observed in existing structures. The theoretical foundations for achieving ultra-narrow linewidth are established through band structure calculations and far-field polarization analysis. Additionally, the Q-factor of quasi-BIC can be flexibly optimized through parameter tuning, rendering it more practical than perfect BIC in real-world applications. This study presents a novel solution for terahertz narrowband chirality and optical filters, potentially advancing technologies in related fields.© 2024 Optica Publishing Group under the terms of the Optica Publishing Group Open Access Publishing Agreement.

On weighted sum‐rate maximization of full‐duplex systems in presence of STAR‐RIS

AbstractReflecting intelligent surface (RIS) is one of the key enabling technologies for beyond fifth generation wireless networks to further improve coverage, spectral‐ and energy‐efficiency of wireless networks. Recently, a novel simultaneous transmission and reflection RIS (STAR‐RIS) technology is introduced which enables more degrees‐of‐freedom in simultaneously serving users in reflection and transmission regions of RIS. This paper investigates a STAR‐RIS assisted two‐user full‐duplex communication system, wherein multi‐antenna base station (BS) and single‐antenna users are subject to maximum power constraints. Firstly, weighted sum rates are computed for three well‐known STAR‐RIS protocols, e.g. energy splitting, mode selection, and time splitting. Then, for each of the cases, weighted sum rate optimization problem is investigated to find optimal resource allocations, i.e. base station's precoding and combining matrices, coefficients of STAR‐RIS, and power allocations. The optimization problem is transferred into multiple convex sub‐problems using equivalent weighted minimum mean‐square‐error forms. Also, by use of the successive convex approximation method, tunable parameters of the STAR‐RIS are optimized. Although the original problem is a non‐convex one, proposed iterative alternating technique achieves an acceptable sub‐optimal performance. Finally, performance of the system is analysed and compared to some baselines to highlight superiority of the STAR‐RIS compared to the conventional RIS schemes.

Equation of State for Nanopores and Shale: Pore Size–Dependent Acentric Factor

Nanopores pose a challenge to phase-behavior modeling when using the equation of state (EOS), and common methods do not capture their vapor pressure or become difficult to implement because they require additional tuning parameters. This study focuses on improving the vapor-pressure prediction of EOS in nanopores by proposing a pore size–dependent acentric factor (ACF). It determines the ACF from experimental data and implements it in EOS along with critical pressure and temperature. The proposed approach is then applied to the vapor-pressure measurements of nitrogen, argon, oxygen, methane, and ethane in pores ranging from 3.5 nm to 8.1 nm. The results show that the ACF in nanopores increases as the pore size decreases, and the degree of size dependency varies across different pure components. The results also demonstrate that the proposed approach enables EOS predictions to match the measurements with good accuracy. This study quantifies the effects of pore size on the ACF for the first time and presents simple correlations for estimating the ACF when the pore radius is smaller than or equal to 10 nm. The proposed approach simplifies the application of EOS in nanopores and unconventional hydrocarbon reservoirs.

Tunable underwater sound absorption via piezoelectric materials with local resonators

In recent years, piezoelectric composite materials have been widely used in the design of underwater anechoic coatings due to their adaptability to tuning parameters. However, there are also some shortcomings, such as a single dissipation mechanism, narrow bandwidth, and poor low-frequency sound absorption. This work proposes an acoustic composite structure combining piezoelectric composite materials with local resonance units, which effectively enhances the sound absorption performance of the structure through the coupling effect of the piezoelectric energy consumption mechanism and local resonance mechanism. Compared to conventional acoustic structures, the proposed acoustic composite structure not only has a strong low-frequency sound absorption effect but also enriches the mid-high frequency sound absorption modes by connecting shunt damping circuits. On this basis, the effect of piezoelectric parameters and resonator morphological properties on structural sound absorption performance is further investigated, and the results show that the designed structure has the characteristic of sound absorption performance that is tunable. In addition, key factors affecting the sound absorption performance of the structure have been optimized to achieve better broadband sound absorption performance. This work may provide valuable ideas for the development of low-frequency broadband adjustable underwater sound-absorbing coatings.