Iterative Optimization Research Articles

Accelerable adaptive cepstrum and L2-Dual Net for acoustic emission-based quality monitoring in laser shock peening

Acoustic emission monitoring in laser shock peening facilitates real-time detection of potential quality issues arising from variations in industrial parameters, enabling iterative optimization of the manufacturing process through material behavior analysis. However, existing research still lacks a comprehensive understanding of the time-varying time-frequency characteristics in dynamic acoustic emission and efficient corresponding models. Therefore, this study proposes an innovative monitoring approach that integrates accelerable adaptive cepstrum (AAC) and L2-Dual Net. Specifically, AAC first employs variable frames and filters to map time-varying features in the signal, and then obtains representative frame length distributions and filter weights for different operating conditions based on statistical information. AAC not only unveils time-varying features in signals but also boasts an efficient computational process. L2-Dual Net is a novel quality assessment model with robust feature extraction and local spatial feature interactions. The incorporation of L2 norm equips the model with robust interference immunity, while the dual spatial attention mechanism helps the model to interact with spatial features exhibiting different time-frequencies. Variable process parameter experiments for aluminum alloy 7075 and titanium alloy TC4 were conducted to validate the reliability of the proposed method. Results demonstrate that AAC showcases optimal computational efficiency and higher feature resolution. When compared with state-of-the-art network architectures, L2-Dual Net exhibits superior information flow, along with higher recognition accuracy and robustness. Moreover, various variants of L2-Dual Net are explored and the code is accessible at https://github.com/Qinr1026/L2-Dual-Net. The proposed method holds promising potential for application in other areas of acoustic emission monitoring.

Active Vibration Control and Parameter Optimization of Genetic Algorithm for Partially Damped Composites Beams.

The paper partially covered Active Constrained Layer Damping (ACLD) cantilever beams' dynamic modeling, active vibration control, and parameter optimization techniques as the main topic of this research. The dynamic model of the viscoelastic sandwich beam is created by merging the finite element approach with the Golla Hughes McTavish (GHM) model. The governing equation is constructed based on Hamilton's principle. After the joint reduction of physical space and state space, the model is modified to comply with the demands of active control. The control parameters are optimized based on the Kalman filter and genetic algorithm. The effect of various ACLD coverage architectures and excitation signals on the system's vibration is investigated. According to the research, the genetic algorithm's optimization iteration can quickly find the best solution while achieving accurate model tracking, increasing the effectiveness and precision of active control. The Kalman filter can effectively suppress the impact of vibration and noise exposure to random excitation on the system.

Dynamic phase measurement based on two-step phase-shifting interferometry with geometric phase grating

Abstract This paper proposes a novel dynamic 2-step phase-shifting interferometry method with a geometric phase grating and direct aberration-free object phase recovery algorithm. By exploring the amplitude-phase modulation property of the geometric phase grating, two-step phase-shifting interferograms with π / 2 phase shift can be obtained in a single shot through two kinds of spatial-multiplexing arrangements. Then the restriction on the background uniformity of the 2-step phase-shifting algorithms and the system aberration can be avoided simultaneously, based on the presented direct and fast object phase demodulation strategy with an object-free state recorded in advance, so an accurate object measurement result can be guaranteed. Accordingly, a detailed analysis of the theoretical model of error sources is conducted by taking the depolarization error of geometric phase grating and phase measurement model error into consideration, with a Least Squares Iteration optimization strategy established to further improve the measurement accuracy. Experiments on various types of phase objects, such as a photo-etched quartz substrate, the spatial light modulator, and a silicon chip, validate the effectiveness and accuracy of our method when compared with the reference phase obtained from 4-step temporal phase-shifting method. The dynamic phase measurement capability is demonstrated by exhibiting the evaporation process of alcohol droplet.

Hand drill shape optimization using Open CASCADE library and the steepest descent method

In this article, compliance optimization with the steepest descent method of the hand drill bits shapes for metal drilling is presented. The analysis of stress, displacements and compliance of the solid with random shape can be performed using the finite element method. In the case of a high number of optimization iterations, each analysis needs automatic modifications of geometry, mesh and boundary conditions. The Open CASCADE library can be used in the fast and automatic construction of modified models. It allows for fast reanalysis for each derivative of the objective function in the optimization process. The motivation of this research is to fill the gap in the literature on drilling technology. Most of the contemporary research is devoted to the oil and gas industry, while optimization of the hand drill bits used in metal drilling is rare. Compliance optimization allows us to find the shape which guarantees a greater stiffness for the specified loading conditions and a given amount of material. Although the obtained compliance was low, further experimental research would be needed to apply new solutions in drilling practice. This will involve the construction of the drill bit tips and the development of a heat treatment process

Development and experimental validation of computational methods for human antibody affinity enhancement.

High affinity is crucial for the efficacy and specificity of antibody. Due to involving high-throughput screens, biological experiments for antibody affinity maturation are time-consuming and have a low success rate. Precise computational-assisted antibody design promises to accelerate this process, but there is still a lack of effective computational methods capable of pinpointing beneficial mutations within the complementarity-determining region (CDR) of antibodies. Moreover, random mutations often lead to challenges in antibody expression and immunogenicity. In this study, to enhance the affinity of a human antibody against avian influenza virus, a CDR library was constructed and evolutionary information was acquired through sequence alignment to restrict the mutation positions and types. Concurrently, a statistical potential methodology was developed based on amino acid interactions between antibodies and antigens to calculate potential affinity-enhanced antibodies, which were further subjected to molecular dynamics simulations. Subsequently, experimental validation confirmed that a point mutation enhancing 2.5-fold affinity was obtained from 10 designs, resulting in the antibody affinity of 2nM. A predictive model for antibody-antigen interactions based on the binding interface was also developed, achieving an Area Under the Curve (AUC) of 0.83 and a precision of 0.89 on the test set. Lastly, a novel approach involving combinations of affinity-enhancing mutations and an iterative mutation optimization scheme similar to the Monte Carlo method were proposed. This study presents computational methods that rapidly and accurately enhance antibody affinity, addressing issues related to antibody expression and immunogenicity.

Machine Learning-Driven GCC Loop Unrolling Optimization: Compiler Performance Enhancement Strategy Based on XGBoost

In contemporary compilers, the determination of the loop unrolling factor is traditionally based on manually crafted heuristic rules. This approach heavily relies on human intuition, which limits its ability to achieve optimized performance across diverse architectures and can sometimes even lead to performance declines. Additionally, developers face challenges in achieving cross-platform compatibility, often necessitating extensive redesign efforts. In response, this study introduces a method leveraging the XGBoost algorithm to predict the optimal loop unrolling factor for compiler optimization, thereby aiming to replace human thinking with machine learning methods and standardize development processes. Initially, the study gathers data on the loop unrolling factors as determined by profile guided optimization technology, analyzes program-specific loop feature vectors and employs cross-validation, including the Pearson correlation coefficient and feature importance ranking, to construct a dataset. Subsequent use of XGBoost to train this dataset models the decision-making process for selecting the most effective loop unrolling factor. The final step involves integrating XGBoost’s trained decision tree model into GCC to calculate the optimal loop unrolling factor during actual compilation. Empirical results on the RISC-V platform indicate that this new method, when tested against the SPEC CPU 2006 benchmark suite, offers up to 6.18% improvement in performance over the existing heuristic approach. It provides a new method for loop unrolling in compilers, and provides an innovative guide for the application of machine learning in compilers.

Multi-objective optimization for a composite pressure vessel with unequal polar openings

Multi-objective parametric optimization problem is presented for overwrapped composite pressure vessels under internal pressure for storage and heating water. It is solved using the developed iterative optimization algorithm. Optimal values of design parameters for the vessel are obtained by varying the set of parameters for composite layers, such as the thickness of layers and radii of polar openings, which influence the distribution of fiber angles along the vessel. The suggested optimization methodology is based on the mechanical solution for composite vessels and the satisfaction of the main failure criteria. An innovative approach lies in the possibility of using the developed optimization methodology for designing vessels with non-symmetrical filament winding, which have unequal polar openings on the domes. This became possible due to the development of a special numerical mechanical finite element model of a composite vessel. A specific Python program provides the creation of a model and controls the exchange of data between the modules of the iterative optimization process. The numerical model includes the determination of the distribution of fiber angles on the domes and cylindrical part of the vessel as well as changes in layer thicknesses. The optimization problem solution is provided using a Multi-Island Genetic Algorithm, this type of method showed its efficiency for such applications, by allowing to avoid local solutions. Thus, optimal parameters of a composite vessel were found by minimizing composite mass and thickness and maximizing the strain energy. Test solutions using the developed methodology are presented for three types of composite materials to evaluate their possibility for integration into the vessel design model.

An automatically recursive feature elimination method based on threshold decision in random forest classification

ABSTRACT The rich feature information contained in the diverse remote sensing data has also exhibited growing potential in the field of image classification. However, the processing of multi-feature data still grapples with the challenges posed by the “curse of dimensionality” and the high computational costs. This paper proposes a remote sensing feature parameter selection method. This method is based on the Gini index of a Random Forest (RF) classifier and employs a 10% threshold decision to identify the optimal combination of remote sensing feature parameters. First, spectral features, texture features, temperature features, elevation features, and principal component features are selected to create a stack of remote sensing images. Second, multiple sets of decision trees are established to cross-validate the contributions of various feature parameters. The feature rankings are determined based on the normalized mean of feature importance. Subsequently, a threshold isset to filter out remote sensing feature parameters that meet the criteria. Finally, an iterative parameter optimization process is carried out to obtain the optimal combination of remote sensing feature parameters. The Landsat 8 image covering Hangzhou Bay in eastern China and the Sentinel-2 remote sensing image of Yancheng Nature Reserve in Jiangsu, China were selected for experiments. The results show that the feature parameters of the remote sensing image screened by the method in this paper are representative, and the proposed method demonstrates strong adaptability and generalization performance in complex environments. The study has important guiding significance for regional spatial planning and sustainable development.

Layer-wise normalized deep incomplete multiview nonnegative matrix factorization

Deep (semi-)nonnegative matrix factorization based models have demonstrated promising performance in the multiview clustering tasks. However, they are all developed upon the assumption that the multiview datasets are complete in all views, and need to be pre-trained layer-by-layer to get reasonable results. Addressing these issues, an algorithm named layer-wise normalized deep incomplete multiview nonnegative matrix factorization (LWNdimNMF) is presented in this paper to tackle the multiview clustering problem with arbitrary missing views. Specifically, a novel layer-wise normalization strategy is developed to constrain the value distribution of the factor matrix in each layer to ensure the numerical stability of the model and make it robust to the initialization. Another benefit of this strategy is that it can effectively depress the objective function value and make the model fit data well. An instance selection alignment is adopted to fuse the incomplete multiple views by aligning the paired instances. To discover the high-order geometrical information in each incomplete view, a hypergraph regularization is incorporated into the proposed model. An effective iterative optimization algorithm based on the multiplicative updating rules is designed to solve the minimizing problem. Extensive experiments are conducted to evaluate the effectiveness of the proposed model by comparing with several state-of-the-art (SOTA) incomplete multiview clustering (IMC) methods on ten real-world multiview datasets. The source code is available at: https://github.com/GuoshengCui/LWNdimNMF.

Enhancing Digital Health Awareness and mHealth Competencies in Medical Education: Proof-of-Concept Study and Summative Process Evaluation of a Quality Improvement Project.

Currently, there is a need to optimize knowledge on digital transformation in mental health care, including digital therapeutics (eg, prescription apps), in medical education. However, in Germany, digital health has not yet been systematically integrated into medical curricula and is taught in a relatively small number of electives. Challenges for lecturers include the dynamic field as well as lacking guidance on how to efficiently apply innovative teaching formats for these new digital competencies. Quality improvement projects provide options to pilot-test novel educational offerings, as little is known about the acceptability of participatory approaches in conventional medical education. This quality improvement project addressed the gap in medical school electives on digital health literacy by introducing and evaluating an elective scoping study on the systematic development of different health app concepts designed by students to cultivate essential skills for future health care professionals (ie, mobile health [mHealth] competencies). This proof-of-concept study describes the development, optimization, implementation, and evaluation of a web-based elective on digital (mental) health competencies in medical education. Implemented as part of a quality improvement project, the elective aimed to guide medical students in developing app concepts applying a design thinking approach at a German medical school from January 2021 to January 2024. Topics included defining digital (mental) health, quality criteria for health apps, user perspective, persuasive design, and critical reflection on digitization in medical practice. The elective was offered 6 times within 36 months, with continuous evaluation and iterative optimization using both process and outcome measures, such as web-based questionnaires. We present examples of app concepts designed by students and summarize the quantitative and qualitative evaluation results. In total, 60 students completed the elective and developed 25 health app concepts, most commonly targeting stress management and depression. In addition, disease management and prevention apps were designed for various somatic conditions such as diabetes and chronic pain. The results indicated high overall satisfaction across the 6 courses according to the evaluation questionnaire, with lower scores indicating higher satisfaction on a scale ranging from 1 to 6 (mean 1.70, SD 0.68). Students particularly valued the content, flexibility, support, and structure. While improvements in group work, submissions, and information transfer were suggested, the results underscore the usefulness of the web-based elective. This quality improvement project provides insights into relevant features for the successful user-centered and creative integration of mHealth competencies into medical education. Key factors for the satisfaction of students involved the participatory mindset, focus on competencies, discussions with app providers, and flexibility. Future efforts should define important learning objectives for digital health literacy and provide recommendations for integration rather than debating the need for digital health integration.

Innovative Approaches to Expansion Loop Design for Enhanced Piping System Durability

Expansion loops are critical components in piping systems, designed to manage stress caused by thermal expansion and contraction, thereby ensuring the system's durability and safety. This study investigates innovative approaches to optimizing expansion loop design, focusing on improving the performance and reliability of piping systems under various operational conditions. The research examines multiple configurations, including alterations in loop length, shape modifications, and the incorporation of additional loops, to assess their impact on stress distribution within the system. While the primary focus of this study is on static stress analysis, transient operational factors, such as water hammer, were also considered in the analysis to provide a more comprehensive understanding of the loop configurations' performance under various conditions. The findings demonstrate that while increasing the loop length can effectively reduce stress, alternative designs, such as double loops or modified shapes, offer superior stress management, particularly in space-constrained environments. The study concludes that optimal expansion loop design should accommodate thermal expansion and provide robustness against potential transient effects, contributing to a more reliable piping system. These insights provide valuable guidelines for the design and optimization of piping systems across various industrial applications.

Hazard-consistent scenario selection for long-term storm surge risk assessment over extended coastal regions

The recent destructive hurricane seasons and concerns related to the future influence of climate change have increased the relevance of coastal storm hazards and, in particular, of storm surge hazard estimation when discussing the resilience of coastal communities. This hazard is generally represented as surge inundation probabilities over a large number of individual locations in the geographic domain of interest, and is typically assessed utilizing an ensemble of storm scenarios (i.e., storm events) that are representative of the regional climatology. This paper investigates the storm ensemble selection within this setting, with the objective of identifying a small number of storm scenarios that are consistent with some chosen hazard descriptions over a large geographic region. Beyond the storm events, the occurrence rates (i.e., weights) are also updated. Following past works, a two-stage optimization is adopted for the storm selection. The inner-loop identifies the occurrence rates for a given storm subset, formulating the problem as a linear programming optimization for the sum of absolute deviation for the predicted hazard. The outer-loop searches for the best subset with the desired number of storms, adopting a genetic algorithm integer optimization for minimizing the aforementioned deviation. This work extends this implementation to extended coastal regions, with many locations of interest. In this case, it is computationally intractable to consider all the locations in the domain within the linear programming formulation, and for this reason, a subset of representative locations is chosen through cluster analysis. The hazard description for only these locations is used in the storm ensemble selection. For clustering, different strategies using correlation between locations based on geospatial information, surge response, or a combination of both are examined. Additionally, the correlation in the hazard description is better integrated into the storm selection by establishing a modification of the objective function adopted for the outer optimization loop. Applications to different North Atlantic coastal domains are presented as case studies.

Reducing Leakage of Single-Qubit Gates for Superconducting Quantum Processors Using Analytical Control Pulse Envelopes

Improving the speed and fidelity of quantum logic gates is essential to reach quantum advantage with future quantum computers. However, fast logic gates lead to increased leakage errors in superconducting quantum processors based on qubits with low anharmonicity, such as transmons. To reduce leakage errors, we propose and experimentally demonstrate two new analytical methods, Fourier ansatz spectrum tuning derivative removal by adiabatic gate (FAST DRAG) and higher-derivative (HD) DRAG, both of which enable shaping single-qubit control pulses in the frequency domain to achieve stronger suppression of leakage transitions compared to previously demonstrated pulse shapes. Using the new methods to suppress the ef transition of a transmon qubit with an anharmonicity of −212 MHz, we implement RX(π/2) gates achieving a leakage error below 3.0×10−5 down to a gate duration of 6.25 ns without the need for iterative closed-loop optimization. The obtained leakage error represents a 20-fold reduction in leakage compared to a conventional cosine DRAG pulse. Employing the FAST DRAG method, we further achieve an error per gate of (1.56±0.07)×10−4 at a 7.9-ns gate duration, outperforming conventional pulse shapes both in terms of error and gate speed. Furthermore, we study error-amplifying measurements for the characterization of temporal microwave control-pulse distortions, and demonstrate that non-Markovian coherent errors caused by such distortions may be a significant source of error for sub-10-ns single-qubit gates unless corrected using predistortion. Published by the American Physical Society 2024

Development of piezo-actuated x-ray deformable mirror for vertical focusing of synchrotron radiation at Indus-2

Piezo-actuated x-ray deformable mirrors (PXDMs) can effectively control the surface profile with sub-nanometre accuracy for adaptive focusing and correct the wavefront distortion generated due to imperfections in optical components or other extraneous effects like heat load, minor misalignments of synchrotron radiation beamline. Generating and controlling the desired shape of PXDMs with sub-nanometre accuracy is very challenging due to the presence of a large number of actuators and constraints related to nonlinearity of piezoactuator, boundary conditions, fabrication related limitations and the requirement for ex-situ as well as in-situ characterization of PXDM. To accomplish this, a PXDM of zerodur with multiple electrodes on a piezoactuator has been developed for vertical focusing of synchrotron x-rays for the first time in India. The PXDM has been fabricated and characterized by in-house developed technologies. The iterative piezo response function-based optimization technique is used to optimize the electric fields of individual piezoactuators in order to achieve the desired parabolic shape of the PXDM. The ex-situ characterization showed that the PXDM can achieve the target parabolic profile with 42 nm root-mean-square error. Furthermore, in-situ characterization at a beamline, BL-12, of Indus-2 synchrotron radiation source using PXDM has confirmed the focusing of collimated x-ray beam in the vertical direction from FWHM 235 μm to FWHM 83 μm.

Specific emitter identification unaffected by time through adversarial domain adaptation and continual learning

Timely identifying the emitter of target signals is crucial for communication security in complex electromagnetic environments. Specific emitter identification (SEI) is a technique to identify emitters using the hardware fingerprints of emitters. In this paper, the impact of changes in hardware fingerprints over time on SEI is solved, which significantly deteriorates identification performance. This issue is addressed from two aspects: one is mitigating the impact of these changes, and the other is tracking and adapting to them. For the aspect of mitigating impact, an alternating adversarial domain adaptation (AADA) method is proposed to eliminate the time-varying component in hardware fingerprints. Subsequently, a feature map calculation method using weighted Euclidean distance is designed, preserving the main parameters of feature maps for each emitter. For the aspect of tracking and adapting to changes, a continual learning method was designed based on feature maps of each emitter. This approach incorporates the selective annotation of unlabeled new data with an iterative optimization training process. To validate the effectiveness of the proposed method, we independently collected comprehensive time-variant datasets as well as simpler datasets with varying receivers and environments. The proposed method was tested on these datasets and compared with existing conventional and advanced methods. The experimental results indicate that the proposed SEI method exhibits superior recognition performance. Compared to existing methods, it achieved an average recognition accuracy improvement of over 8% on the time-variant dataset, and demonstrated enhanced robustness against these three types of variations.

FADO: Floorplan-Aware Directive Optimization Based on Synthesis and Analytical Models for High-Level Synthesis Designs on Multi-Die FPGAs

Multi-die FPGAs are widely adopted for large-scale accelerators, but optimizing high-level synthesis designs on these FPGAs faces two challenges. First, the delay caused by die-crossing nets creates an NP-hard floorplanning problem. Second, traditional directive optimization cannot consider resource constraints on each die or the timing issue incurred by the die-crossings. Furthermore, the high algorithmic complexity and the large scale lead to extended runtime for legalizing the floorplan of HLS designs under different directive configurations. To co-optimize the directives and floorplan of HLS designs on multi-die FPGAs, we formulate the co-search based on bin-packing variants and present two iterative optimization flows. The first (FADO 1.0) relies on a pre-built QoR library. It involves a greedy, latency-bottleneck-guided directive search, and an incremental floorplan legalization. Compared with a global floorplanning solution, it takes 693X~4925X shorter search time and achieves 1.16X~8.78X better design performance, measured in workload execution time. To remove the time-consuming QoR library generation, the second flow (FADO 2.0) integrates an analytical QoR model and redesigns the directive search to accelerate convergence. Through experiments on mixed dataflow and non-dataflow designs, compared with 1.0, FADO 2.0 further yields a 1.40X better design performance on average after implementation on the Alveo U250 FPGA.

Optimizing indoor air models through k-means clustering of nanoparticle size distribution data

Sectional physics-based aerosol models imply a computational effort that hinders their use in building digital twins, real-time predictive control, and computer-based iterative optimization versus black-box approaches. The innovation of this paper lies in the proposal of a novel systematic methodology to optimize the number of size bins in sectional reduced-order models for particle concentration simulations. This allows its application in indoor air quality management and overcomes generalizability and data-dependency issues of black-box models. This method, based on k-means clustering, aims to ensure precision when tackling relatively fast fine and ultrafine particle simulations targeting the reduction of time and resource consumption from experimentally-determined aerosol size distribution time series. Consequently, three tests were carried out using combustion aerosols inside a custom-designed emission chamber to simulate emission hotspots in non-commercial and occupational settings. 2-, 3-, 4-, and 5-cluster classifications were evaluated for data coming from 13 particle size bins through silhouette analysis and the study of their temporal profiles. Results show that the 4-cluster classification summarizes the behavior of data in the 10–420 nm range, ensuing up to a 77 % improvement in the model's computational demand. Moreover, this method allows an accurate definition of the necessary size ranges to calculate nanoparticle concentrations inside the chamber and facilitates the interpretation of aerosol behavior and processes through the resulting clusters' temporal profiles.

Performance Evaluation of a Simple Strategy to Optimize Formula Constants for Zero Mean or Minimal Standard Deviation or Root-Mean-Squared Prediction Error in Intraocular Lens Power Calculation

PurposeTo investigate the performance of a simple prediction scheme for the formula constants optimized for a mean (MPE), standard deviation (SDPE) or root-mean-squared refractive prediction error (RMSPE). DesignRetrospective cross-sectional study. MethodsUsing IOLMaster 700 biometric data from 888 eyes treated with the Hoya Vivinex lens and 821 eyes treated with the Alcon SA60AT lens, plus the power of the implanted lens and postoperative spherical equivalent refraction, optimized constants for SRKT, Hoffer Q, Holladay 1, Haigis, and K6 formulae were calculated using an iterative nonlinear optimization for zero MPE and minimal SDPE and RMSPE. Start values were detuned by ±1.5 from the MPE optimized constants and formula constants generated using the simple prediction scheme were compared to the corresponding directly optimized constants. ResultsFor all 5 formulae under test and with both datasets, constants optimized using the simple scheme showed excellent agreement with those from the iterative method with either MPE or RMSPE used as the optimization metric, and good agreement with SDPE as the metric. Constants optimized for zero MPE or minimal RMSPE agreed within 0.05, whereas constants for minimal SDPE could be systematically off by up to 0.6 from the MPE values, making SDPE unsuitable as an optimization metric. ConclusionsThis simple formula constant optimization scheme performs excellently for 4 disclosed formulae and one nondisclosed formula in our 2 monocentric datasets with zero MPE or minimal RMSPE as metrics. Multicentric studies with other study populations and biometers are required to further investigate the clinical applicability.

Tensor-based unsupervised feature selection for error-robust handling of unbalanced incomplete multi-view data

Recent advancements in multi-view unsupervised feature selection (MUFS) have been notable, yet two primary challenges persist. First, real-world datasets frequently consist of unbalanced incomplete multi-view data, a scenario not adequately addressed by current MUFS methodologies. Second, the inherent complexity and heterogeneity of multi-view data often introduce significant noise, an aspect largely neglected by existing approaches, compromising their noise robustness. To tackle these issues, this paper introduces a Tensor-Based Error Robust Unbalanced Incomplete Multi-view Unsupervised Feature Selection (TERUIMUFS) strategy. The proposed MUFS framework specifically caters to unbalanced incomplete multi-view data, incorporating self-representation learning with a tensor low-rank constraint and sample diversity learning. This approach not only mitigates errors in the self-representation process but also corrects errors in the self-representation tensor, significantly enhancing the model’s resilience to noise. Furthermore, graph learning serves as a pivotal link between MUFS and self-representation learning. An innovative iterative optimization algorithm is developed for TERUIMUFS, complete with a thorough analysis of its convergence and computational complexity. Experimental results demonstrate TERUIMUFS’s effectiveness and competitiveness in addressing unbalanced incomplete multi-view unsupervised feature selection (UIMUFS), marking a significant advancement in the field.

Research on multi-heat source arrangement optimization based on equivalent heat source method and reconstructed variational autoencoder

The variational autoencoder (VAE) architecture has significant advantages in predictive image generation. This study proposes a novel RFCNN-βVAE model, which combines residual-connected fully connected neural networks with VAE to handle multi-heat source arrangements. By integrating analytical solutions, polynomial fitting, and temperature field superposition, we accurately simulated the temperature rise distribution of a single heat source. We further explored the use of multiple equivalent heat sources to replace adiabatic boundary conditions. This enables the analytical method to effectively solve the two-dimensional conjugate convective heat transfer problem, providing a reliable alternative to traditional numerical solutions. Our results show that the model achieved high predictive accuracy. By adjusting the β parameter, we balanced reconstruction accuracy and latent space generalization. During the stable phase of the multi-heat source optimization iteration, 73.4% of the results outperformed the dense dataset benchmark, indicating that the model successfully optimized heat source coordinates and minimized peak temperature rise. This validates the feasibility and effectiveness of deep learning in thermal management system design. This research lays the groundwork for optimizing complex thermal environments and contributes valuable perspectives on the effective design of systems with multiple thermal sources or for applications like multi-beam lighting equalization.