Iterative Optimization Research Articles

Research on Chinese Traditional Architectural Culture and Inheritance Strategy: A Case Study of the Goulou Cluster of Yue Dialects in Guangxi

Traditional Chinese villages and architectural cultural resources are abundant. Against the backdrop of rapid development in contemporary socioeconomic and urbanization processes, rural construction is facing multiple challenges such as imbalanced urban–rural development, gradually fading cultural traditions, and disharmonious living environments. The cultural elements of rural architecture urgently need more systematic and effective protection, integration, and reuse. Therefore, the precise extraction of traditional architectural features and their translation applications in modern contexts are gradually becoming key issues in current research and practice fields. This study takes traditional architecture of the Goulou Cluster of Yue Dialects in Guangxi, China, as an example. Through field investigations and mathematical and GIS spatial analysis, architectural samples were identified and extracted typologically, and a database of traditional architecture was constructed, delineating architectural cultural zones and summarizing type characteristics to create a genealogy map. Based on the results of the architectural genealogy study, modern translation pathways for traditional architecture were proposed through spatial modeling, technical analysis, and iterative optimization. Modern translation experiments were conducted on selected typical villages and their traditional buildings, exploring the application model system of traditional architecture in modern contexts. This study not only deepens the scientific understanding of the genealogy zoning characteristics of traditional architecture in the Goulou Cluster of Yue Dialects in Guangxi but also provides a reference for the modern translation and optimization path of traditional architecture, providing important theoretical basis and application guidance for promoting the inheritance and innovation of rural culture, and realizing the protection and updating of rural architectural style.

A sensing system and solving method for dynamic detection of relative pose of hydraulic support group

The precise detection of the pose of hydraulic support groups is crucial for the construction of intelligent coal mines. Addressing current challenges in comprehensive position sensing of support groups, such as one-sided descriptions, missing information, and limited detection capabilities, this paper, based on the concept of digital twin, proposes a sensing system and solving method for dynamic detection of the relative pose of hydraulic support group. Initially, a relative pose detection model, based on the six-point localization principle, is proposed by combining existing sensor information. Then, a sensing system is designed, incorporating a photoelectric detection device for monitoring key position parameters and virtual sensors for determining pose information. Consequently, a method for dynamically deriving relative positions, driven by the fusion of real-virtual iterative solving, real-virtual error feedback, and iterative condition optimization, is established. Finally, a relative pose dynamic detection system for a hydraulic support prototype is constructed in a laboratory environment. Experimental results demonstrate that the sensor system and the relative position detection method designed in this paper achieve a relative position accuracy of over 95.32 % for the hydraulic support, with a dynamic reconstruction time of less than 0.2 s. This verifies the rationality of the sensor system and the feasibility and accuracy of the dynamic deduction method. To sum up, this work provides a theoretical foundation and technical support for the autonomous perception of hydraulic support group, autonomous frame adjustment between frames, and overall straightness adjustment. It also lays the groundwork for further research and the advancement of information-physical systems in the fully-mechanized mining face.

Systematic optimization and evaluation of a Dutch sexual health intervention: Role model stories for chlamydia prevention, testing, and treatment.

The rapidly evolving nature of eHealth necessitates regular optimization and subsequent evaluation. Within the Dutch sexual health intervention Sense.info, we utilized a mixed-methods cyclic evaluation process to assess and optimize the potential impact of the chlamydia page. This paper reports on the page's optimization through the development of role model stories for chlamydia prevention and the subsequent evaluation of these stories. The experiences of 10 young individuals served as the basis of role model stories using the behavior change principle modeling based on social cognitive theory. These stories aimed to motivate young individuals to undergo sexually transmitted infection testing, use condoms, and notify sexual partners. Once the stories were posted online, we tracked use data between July and September 2022 and investigated end-user perspectives through a think-aloud study combined with semistructured interviews (N = 20, M age = 19.7, SDage = 2.65). Template analyses were used for the analysis of the think-aloud study. Use data revealed that all stories were accessed by website visitors, yet other page elements on the chlamydia page interacted with more. The exploration of end-user perspectives indicated a positive impact of the personal stories on normalization, self-efficacy, and skills related to chlamydia preventive behaviors. Mixed results were found regarding some conditions for the effectiveness of the behavior change principle modeling. This study provided valuable insights into the cyclic evaluation process for evaluating and optimizing web-based public health interventions, as well as the potential impact of role model stories on sexual health prevention. Also, aspects of the stories that could be optimized in future optimization rounds were identified. Overall, this research contributes to enhancing the impact of eHealth interventions through iterative evaluation and optimization processes.

Enhancing unsupervised learning in medical image registration through scale-aware context aggregation.

Deformable image registration (DIR) is essential for medical image analysis, facilitating the establishment of dense correspondences between images to analyze complex deformations. Traditional registration algorithms often require significant computational resources due to iterative optimization, while deep learning approaches face challenges in managing diverse deformation complexities and task requirements. We introduce ScaMorph, an unsupervised learning model for DIR that employs scale-aware context aggregation, integrating multiscale mixed convolution with lightweight multiscale context fusion. This model effectively combines convolutional networks and vision transformers, addressing various registration tasks. We also present diffeomorphic variants of ScaMorph to maintain topological deformations. Extensive experiments on 3D medical images across five applications-atlas-to-patient and inter-patient brain magnetic resonance imaging (MRI) registration, inter-modal brain MRI registration, inter-patient liver computed tomography (CT) registration as well as inter-modal abdomen MRI-CT registration-demonstrate that our model significantly outperforms existing methods, highlighting its effectiveness and broader implications for enhancing medical image registration techniques.

Fuzzy Weighted Principal Component Analysis for Anomaly Detection

Principal Component Analysis (PCA) is one of the most famous unsupervised dimensionality reduction algorithms and has been widely used in many fields. However, it is very sensitive to outliers, which reduces the robustness of the algorithm.. In recent years, many studies have tried to employ \(\ell_{1}\) -norm to improve the robustness of PCA, but they all lack rotation invariance or the solution is expensive. In this paper, we propose a novel robust principal component analysis, namely, Fuzzy Weighted Principal Component Analysis (FWPCA), which still uses squared \(\ell_{2}\) -norm to minimize reconstruction error and maintains rotation invariance of PCA. The biggest bright spot is that the contribution of data is restricted by fuzzy weights, so that the contribution of normal samples are much greater than noise or abnormal data, and realizes anomaly detection. Besides, a more reasonable data center can be obtained by solving the optimal mean to make projection matrix more accurate. Subsequently, an effective iterative optimization algorithm is developed to solve this problem, and its convergence is strictly proved. Extensive experimental results on face datasets and RGB anomaly detection datasets show the superiority of our proposed method.

Absolute modal wavefront reconstruction in a rotational shearing interferometer by iterative optimization.

We propose an iterative optimization approach for wavefront reconstruction in a rotational shearing interferometer based on Zernike polynomials. Two incorrect shearing amounts are optimized simultaneously, enabling the absolute reconstruction of wavefronts with high uniformity in the root mean square (RMS). Simulations under noisy conditions show that the reconstruction error, in terms of peak-to-valley (PV) and RMS, remains within the μλ range. The approach was experimentally validated by identifying asymmetric aberrations in an imperfectly collimated light source, showing strong agreement with the wavefront obtained from a Shack-Hartmann sensor.

FPGA Implementation of PRNGs Based on Chaotic Systems Optimized by DE, GWO, and PSO

ABSTRACTThe optimization of chaotic systems remains a challenge because the search space of the design parameters can have several orders of magnitude, causing that the corresponding eigenvalues can be very sparse, thus producing unnecessary long simulation times. This imposes the need of estimating the step‐size of the numerical method that discretizes the ordinary differential equations. In this manner, the proposed work shows the optimization of chaotic systems, by applying differential evolution (DE), grey wolf optimization (GWO), and particle swarm optimization (PSO) algorithms. Within the optimization loop, is estimated taking into account the inverse of the highest eigenvalue, and the total time simulation is estimated by taking the inverse of the lowest eigenvalue. The constraints consider that a chaotic system is simulated only if there exist two complex eigenvalues and if the Fourier transform of the chaotic time series has a spectrum area in a certain threshold. A single‐objective function is associated to maximize the Kaplan–Yorke dimension , and then PSO, DE, and GWO are executed with the same number of runs, generations, and population individuals. Their performances are compared by Wilcoxon and Levene tests. The best solutions obtained for each optimization algorithm and for each chaotic system are used to implement pseudo‐random number generators (PRNG). Finally, the PRNGs that passed NIST and TestU01 tests are implemented into a field‐programmable gate array.

Multi-objective optimization of the heating oil circuit inside the calendering roller for the lithium battery pole piece

The heating oil circuit plays an essential role in the heating calendering roller for the lithium battery pole piece. To achieve the optimization of the heating oil circuit, a fluid-thermal-structural coupling method and a multi-objective optimization procedure are proposed to obtain the optimal solution. A fluid–thermal–structural coupling flowchart based on the numerical modeling for the calendering roller temperature distribution is created to automate the analysis processes in the optimization iteration. In the multi-objective optimization procedure, an integrated optimization framework is established by the prebuilt CAD module and the FEM module in the commercial software. Then, the improved NSGA-II algorithm is selected to execute the optimization loop. The methodology was successfully implemented in a redesigned case of a lithium battery rolling equipment company in China. After redesigning the heating oil circuit inside a calendering roller, both the maximum surface temperature non-uniformity and the maximum surface radial thermal deformation of the roller are reduced remarkably by 29.8% and 13.2%, respectively. The results indicate that the proposed method is feasible and makes designing the heating oil circuit easier. The case illustrates that this method can be extended to practical cases of heating oil circuit design for the lithium battery calendering roller.

Collaborative Sensing-Aware Task Offloading and Resource Allocation for Integrated Sensing-Communication- and Computation-Enabled Internet of Vehicles (IoV)

Integrated Sensing, Communication, and Computation (ISCC) has become a key technology driving the development of the Internet of Vehicles (IoV) by enabling real-time environmental sensing, low-latency communication, and collaborative computing. However, the increasing sensing data within the IoV leads to demands of fast data transmission in the context of limited communication resources. To address this issue, we propose a Collaborative Sensing-Aware Task Offloading (CSTO) mechanism for ISCC to reduce the sensing tasks transmission delay. We formulate a joint task offloading and communication resource allocation optimization problem to minimize the total processing delay of all vehicular sensing tasks. To solve this mixed-integer nonlinear programming (MINLP) problem, we design a two-stage iterative optimization algorithm that decomposes the original optimization problem into a task offloading subproblem and a resource allocation subproblem, which are solved iteratively. In the first stage, a Deep Reinforcement Learning algorithm is used to determine task offloading decisions based on the initial setting. In the second stage, a convex optimization algorithm is employed to allocate communication bandwidth according to the current task offloading decisions. We conduct simulation experiments by varying different crucial parameters, and the results demonstrate the superiority of our scheme over other benchmark schemes.

A novel framework for online decision-making and feedback optimization of complex products process parameter based on edge-cloud collaboration

Background Intelligent manufacturing is perceived as a manufacturing mode with powerful learning and cognitive capabilities empowered by information technologies such as the internet of things, edge computing, and cloud computing. The mode can be used to address the problems of low intelligence and poor timeliness of traditional process planning. Methods The framework includes the multi-objective process planning method based on real-time data, and the process closed-loop optimization mechanism of “cloud-based theoretical process planning plus edge MEC side online simulation verification and real-time feedback adjustment”, which realizes online process planning and iterative optimization in mass customization. Results The feasibility of the online analysis method for thin-walled part milling deformation is verified by taking the finishing process of aerospace thin-walled parts as an example. The experimental results show that the simulation time on the single analysis step is reduced from 6s to 1s, and the accuracy rate is 86.9%. Conclusions A new intelligent process planning theoretical framework integrating with online process planning and autonomous collaborative control, namely, digital twin and multi-access edge computing process planning (DT-MEC-PP) is proposed in this paper.

Adaptive Iterative Control Optimization ICP Algorithm for Robust Point Cloud Registration in Urban Environments

This paper puts forward an improved ICP algorithm to improve the robustness of point cloud registration in complex urban environment, and adopts adaptive iterative control to solve the limitations of traditional ICP algorithm such as premature convergence or over-fitting caused by static iteration. Sobel convolution enhances the response ability of the algorithm to the complexity of the environment, and dynamically adjusts the iteration limit according to the feature difference of the point cloud, thus improving the registration accuracy and calculation efficiency. According to a large number of experiments on KITTI dataset, compared with the traditional ICP method, the algorithm can effectively reduce the root mean square error and improve the registration accuracy. These results verify the effectiveness and robustness of the algorithm in autonomous driving, robot navigation and urban mapping.

Fast iterative position estimation method of permanent magnet synchronous linear motor

Abstract In this paper, a Fast Iterative Phase Estimation (FIPE) algorithm is proposed for robotic grinding force control devices using Permanent Magnet Synchronous Linear Motors (PMSLM), requiring high positional accuracy and response speed. FIPE obtains optimal phase estimates through iterative searching and exhibit excellent dynamic performance. The proposed method is optimized by iterative optimization algorithms, which significantly reduces the number of iterations and enhance the response speed of position estimation. In addition, the effects of harmonics, amplitude mismatch, noise and DC errors in the raw signal on the FIPE algorithm are discussed, and a shallow neural network is introduced to compensate the periodic errors. The experimental results show that the FIPE algorithm has higher calculation accuracy and dynamic performance than the traditional PLL such as SRF-PLL, ANF-PLL and LKF-PLL, and has faster iteration speed than the traditional position estimator such as FPS-PLL.

Bayesian optimization with Gaussian-process-based active machine learning for improvement of geometric accuracy in projection multi-photon 3D printing

Multi-photon polymerization is a well-established, yet actively developing, additive manufacturing technique for 3D printing on the micro/nanoscale. Like all additive manufacturing techniques, determining the process parameters necessary to achieve dimensional accuracy for a structure 3D printed using this method is not always straightforward and can require time-consuming experimentation. In this work, an active machine learning based framework is presented for determining optimal process parameters for the recently developed, high-speed, layer-by-layer continuous projection 3D printing process. The proposed active learning framework uses Bayesian optimization to inform optimal experimentation in order to adaptively collect the most informative data for effective training of a Gaussian-process-regression-based machine learning model. This model then serves as a surrogate for the manufacturing process: predicting optimal process parameters for achieving a target geometry, e.g., the 2D geometry of each printed layer. Three representative 2D shapes at three different scales are used as test cases. In each case, the active learning framework improves the geometric accuracy, with drastic reductions of the errors to within the measurement accuracy in just four iterations of the Bayesian optimization using only a few hundred of total training data. The case studies indicate that the active learning framework developed in this work can be broadly applied to other additive manufacturing processes to increase accuracy with significantly reduced experimental data collection effort for optimization.

Application of an improved LightGBM hybrid integration model combining gradient harmonization and Jacobian regularization for breast cancer diagnosis

Cancer, as a shocking disease, is one of the most common malignant tumors among women, posing a huge threat to the physical health and safety of women worldwide. With the continuous development of science and technology, more and more high and new technologies are involved in the diagnosis and prediction of breast cancer. In recent years, intelligent medical assistants supported by data mining and machine learning algorithms have provided necessary support for doctors’ diagnosis. This study proposes an improved LightGBM hybrid integration model. Introducing gradient harmonic loss and cross entropy loss to enhance the model’s attention to minority classes in the dataset and alleviate the impact of data imbalance on diagnostic results. Designing whale optimization algorithm to improve LightGBM to achieve iterative optimization of hyperparameters, and enhance the overall performance of the model. Proposing Jacobian regularization method to denoise LightGBM to solve the problem of model sensitivity to noise. Developing the LightGBM hybrid integration model to ensure the accuracy and stability of model diagnosis on diverse and imbalanced datasets. The effectiveness of the proposed method has been comprehensively compared and verified through the dataset in the UCI machine learning repository, and the results show that the proposed method has achieved good diagnostic performance in all indicators. The hybrid integration model proposed in this paper can provide effective auxiliary support for doctors to diagnose breast cancer.

Deep proximal gradient network for absorption coefficient recovery in photoacoustic tomography

Objective.The optical absorption properties of biological tissues in photoacoustic (PA) tomography are typically quantified by inverting acoustic measurements. Conventional approaches to solving the inverse problem of forward optical models often involve iterative optimization. However, these methods are hindered by several challenges, including high computational demands, the need for regularization, and sensitivity to both the accuracy of the forward model and the completeness of the measurement data. The aim of this study is to introduce a novel learned iterative method for recovering spatially varying optical absorption coefficients (OACs) from PA pressure measurements.Approach.The study introduces a deep learning-based approach that employs the proximal gradient descent mechanism to achieve optical inversion. The proposed framework consists of multiple cascaded structural units, which iteratively update the absorption coefficients through a learning process, unit by unit.Main results.The proposed method was validated through simulations, phantom experiments, andin vivostudies. Comparative analyses demonstrated that the proposed approach outperforms traditional nonlearning and learning-based methods, achieving at least 12.85% improvement in relative errors, 3.50% improvement in peak signal-to-noise ratios, and 3.53% improvement in structural similarity in reconstructing the OAC distribution.Significance.This method significantly improves the accuracy and efficiency of quantitative PA tomography. By addressing key challenges such as computational demand and sensitivity to the accuracy of the forward model and the completeness of the measurement data, the proposed framework offers a more reliable and efficient alternative to traditional methods, with potential applications in medical imaging and diagnostics.

Comprehensive benefits evaluation of low impact development using scenario analysis and fuzzy decision approach

The comprehensive benefit evaluation of LID based on multi-criteria decision-making methods faces technical issues such as the uncertainties and vagueness in hybrid information sources, which can affect the overall evaluation results and ranking of alternatives. This study introduces a multi-indicator fuzzy comprehensive benefit evaluation approach for the selection of LID measures, aiming to provide a robust and holistic framework for evaluating their benefits at the community level. The proposed methodology integrates quantitative environmental and economic indicators with qualitative social benefit indicators, combining the use of the Storm Water Management Model (SWMM) and ArcGIS for scenario-based analysis, and the use of hesitant fuzzy language sets and Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) for decision-making. The framework’s novelty lies in the integration of the hesitant fuzzy weighted average algorithm to handle subjective uncertainties in expert judgment and the incorporation of multi-return period scenarios to enhance the robustness of the evaluation. The comprehensive benefits of 26 LID configurations were conducted in Chenglong Road Subdistrict under five rainfall return period scenarios of 5, 10, 20, 50, and 100 years. The results show that LID measures, particularly combinations of sunken green spaces and permeable paving, offer significant reductions in runoff and peak flow, along with improved flood mitigation across multiple return periods. Additionally, this study identifies practical LID implementation priorities for local decision-makers. The relative closeness is influenced by the indicators and non-calibrated parameters. However, it overall does not affect the main trends and key insights derived. The robustness of the proposed approach is reinforced by four key aspects: the impact of the Thiessen polygon method in ArcGIS, the influence of composite runoff coefficient and iterative optimization in SWMM, the effect of hesitant fuzzy linguistic sets and TOPSIS on weight calculation, and the contribution of simulations under different return periods to stability analysis.

Integrated Sensing and Communication Target Detection Framework and Waveform Design Method Based on Information Theory.

Target detection is a core function of integrated sensing and communication (ISAC) systems. The traditional likelihood ratio test (LRT) target detection algorithm performs inadequately under low signal-to-noise ratio (SNR) conditions, and the performance of mainstream orthogonal frequency division multiplexing (OFDM) waveforms declines sharply in high-speed scenarios. To address these issues, an information-theory-based orthogonal time frequency space (OTFS)-ISAC target detection processing framework is proposed. This framework adopts the OTFS waveform as its fundamental signal. The target detection is implemented through a relative entropy test (RET) comparing echo signals against target presence/absence hypotheses. Furthermore, to enhance the system's target detection capability, the iterative OTFS-ISAC waveform design (I-OTFS-WD) method which maximizes the relative entropy is proposed. This method utilizes the minorization-maximization (MM) algorithm framework and semidefinite relaxation (SDR) technique to transform the non-convex optimization problem into an iterative convex optimization problem for resolution. The simulation results demonstrate that, under sufficient sample conditions, the RET algorithm achieves a 9.12-fold performance improvement over LRT in low-SNR scenarios; additionally, the optimized waveform reduces the sample requirements of the RET algorithm by 40%, further enhancing the target detection capability of the OTFS-ISAC system.

A note on using random starting values in small sample SEM.

Model estimation for SEM analyses in commonly used software typically involves iterative optimization procedures, which can lead to nonconvergence issues. In this paper, we propose using random starting values as an alternative to the current default strategies. By drawing from uniform distributions within data-driven lower and upper bounds (see De Jonckere et al. (2022) Structural Equation Modeling: A Multidisciplinary Journal, 29(3), 412-427), random starting values are generated for each (free) parameter in the model. Through three small simulation studies, we demonstrate that incorporating such bounded random starting values significantly reduces the nonconvergence rate, resulting in increased convergence rates ranging between 87% and 96% in the first two studies. In essence, bounded random starting values seem to offer a promising alternative to the default starting values that are currently used in most software packages.

A Unified Design Methodology for Front-End RF/mmWave Receivers

In this work, a unified design methodology for front-end RF/mmWave receivers is presented, aiming to significantly accelerate the design procedure of the front-end RF blocks in complex RX/TX chain implementations. The proposed design methodology is based on optimization loops with well-defined cost functions so as to minimize the design iterations that may be encountered during specification tuning. As proof of concept, two essential RF blocks widely used in RF receivers, a low-noise amplifier (LNA) and a voltage-controlled oscillator (VCO), were designed using the proposed unified methodology with a 65 nm RF-CMOS processing node. Finally, the derived designs were compared to similar designs in the literature, proving that the proposed unified methodology is capable of synthesizing RF/mmWave LNAs and VCOs with industry-standard specifications within a significantly faster time frame.

Iterative optimization annotation pipeline and ALSS-YOLO-Seg for efficient banana plantation segmentation in UAV imagery.

Precise segmentation of unmanned aerial vehicle (UAV)-captured images plays a vital role in tasks such as crop yield estimation and plant health assessment in banana plantations. By identifying and classifying planted areas, crop areas can be calculated, which is indispensable for accurate yield predictions. However, segmenting banana plantation scenes requires a substantial amount of annotated data, and manual labeling of these images is both timeconsuming and labor-intensive, limiting the development of large-scale datasets. Furthermore, challenges such as changing target sizes, complex ground backgrounds, limited computational resources, and correct identification of crop categories make segmentation even more difficult. To address these issues, we propose a comprehensive solution. First, we designed an iterative optimization annotation pipeline leveraging SAM2's zero-shot capabilities to generate high-quality segmentation annotations, thereby reducing the cost and time associated with data annotation significantly. Second, we developed ALSS-YOLO-Seg, an efficient lightweight segmentation model optimized for UAV imagery. The model's backbone includes an Adaptive Lightweight Channel Splitting and Shuffling (ALSS) module to improve information exchange between channels and optimize feature extraction, aiding accurate crop identification. Additionally, a Multi-Scale Channel Attention (MSCA) module combines multi-scale feature extraction with channel attention to tackle challenges of varying target sizes and complex ground backgrounds. We evaluated the zero-shot segmentation performance of SAM2 on the ADE20K and Javeri datasets. Our iterative optimization annotation pipeline demonstrated a significant reduction in manual annotation effort while achieving high-quality segmentation labeling. Extensive experiments on our custom Banana Plantation segmentation dataset show that ALSS-YOLO-Seg achieves state-of-the-art performance. Our code is openly available at https://github.com/helloworlder8/computer_vision.