Iterative Optimization Research Articles

Discovery of Ketal-Ester Ionizable Lipid Nanoparticle with Reduced Hepatotoxicity, Enhanced Spleen Tropism for mRNA Vaccine Delivery.

The safety and efficacy of the lipid nanoparticle (LNP) delivery system are crucial for the successful development of messenger RNA vaccines. We designed and synthesized a series of ketal ester lipids (KELs), featuring a biodegradable ketal moiety in the linker and ester segments in the tail. Through iterative optimization of the head and tail groups of KELs, we tuned the pKa and molecular shapes, and identified (4S)-KEL12 as a safe and efficient ionizable lipid for mRNA delivery. (4S)-KEL12 LNP showed significantly higher delivery efficacy and lower toxicity than the DLin-MC3-DMA LNP. In comparison to SM-102 LNP, (4S)-KEL12 LNP exhibited better spleen tropism, reduced liver tropism, and hepatotoxicity. Additionally, (4S)-KEL12 demonstrated good biodegradability following intramuscular or intravenous injection. Notably, (4S)-KEL12 LNP encapsulated with a therapeutic mRNA cancer vaccine elicited robust cellular immune responses leading to substantial tumor regression along with prolonged survival in tumor-bearing mice. Our results suggest that (4S)-KEL12 LNP holds great promise for mRNA vaccine delivery. The comprehensive analysis of the structure-activity relationship, toxicity, biodegradability, distribution, expression, efficacy, and stereochemistry of these LNPs will greatly contribute to the rational design and discovery of novel lipid-based delivery systems.

An iteratively optimized downscaling method for city-scale air quality forecast emission inventory establishment

Air quality models (AQMs) are pivotal in forecasting air quality and shaping pollution control strategies. Nonetheless, the effectiveness of AQMs is often compromised in many cities due to the absence of accurate local emission inventories. To address this gap, this study presents a novel AQM-ready emission inventory generation technique with iterative optimization ability for city-scale applications in China. An efficient emission processing tool was introduced in this study, which utilizes the High-Resolution Multi-resolution Emission Inventory for China (HR-MEIC) as input. Using environmental observations and a region map, the tool can justify emissions of different regions iteratively. With the iterative optimization method, the model performance can be notably improved even without local emissions. The optimization was realized by splitting model-ready emissions into different regions and adjusting the emissions using scale factors calculated with the modeling results and the observations of each region. This methodology was applied to the Eight Cities in the Chengdu Plain (CP8C), located in the western margin of Sichuan Basin with complex topography and meteorological conditions, southwestern China, monthly throughout 2023. Air quality modeling was carried out using Weather Forecast and Research Model (WRF) and the Community Multiscale Air Quality Model (CMAQ). The results showed that the optimization acquired a good performance after five cycles for PM2.5 and NO2, with correlation coefficients (R values) surging from 0.62 and 0.37 to 0.77 and 0.73, respectively, while their normalized mean bias (NMB) substantially decreased from 22.8 % and 100.4 % to 3.6 % and 3.3 %. The underestimation on O3 concentration was also improved by the optimization, although enhancements in O3 modeling remained modest. This technique provides an easy-to-copy method to generate reasonable AQM-ready emission files with open emission data and observation data, which would be beneficial for the cities' air quality forecast in cities without local emission inventories.

Online extrinsic parameters calibration of on-board stereo cameras based on certifiable optimization

The extrinsic parameters of on-board stereo cameras can be slightly altered due to temperature fluctuations, vibrations, and accidental impacts during automobile driving, leading to significant performance loss in dense stereo matching. In this paper, we propose an online calibration method based on certifiable optimization to address this issue. Initially, sparse feature points are collected based on plane distribution and disparity. A robust optimization model is then developed to minimize the epipolar error, utilizing iterative local optimization to eliminate outliers and determine the 5DOF extrinsic parameters. Subsequently, a relaxation problem is constructed using inliers, and global optimization is performed to certify that the locally optimal results are indeed globally optimal. Comparative experimental results demonstrate that the proposed method offers high accuracy and reliability. Additionally, the quality of the disparity map generated by our calibration method is comparable to that achieved through offline calibration.

Gradient descent optimization of acoustic holograms for transcranial focused ultrasound

Acoustic holographic lenses, also known as acoustic holograms, can change the phase of a transmitted wavefront in order to shape and construct complex ultrasound pressure fields, often for focusing the acoustic energy on a target region. These lenses have been proposed for transcranial focused ultrasound (tFUS) to create diffraction-limited focal zones that target specific brain regions while compensating for skull aberration. Holograms are currently designed using time-reversal approaches in full-wave time-domain numerical simulations. Such simulations need time-consuming computations, which severely limits the adoption of iterative optimization strategies. In the time-reversal method, the number and distribution of virtual sources can significantly influence the final sound field. Because of the computational constraints, predicting these effects and determining the optimal arrangement is challenging. This study introduces an efficient method for designing acoustic holograms using a volumetric holographic technique to generate focused fields inside the skull. The proposed method combines a modified mixed-domain method for ultrasonic propagation with a gradient descent iterative optimization algorithm. The findings are further validated in underwater experiments with a realistic 3D-printed skull phantom. This approach enables substantially faster holographic computation than previously reported techniques. The iterative process uses explicitly defined loss functions to bias the ultrasound field’s optimization parameters to specific desired characteristics, such as axial resolution, transversal resolution, coverage, and focal region uniformity, while eliminating the uncertainty associated with virtual sources in time-reversal techniques. The proposed techniques enable more rapid hologram computation and more flexibility in tailoring ultrasound fields for specific therapeutic requirements.

Optimisation of synchronisation control parameters for enhanced bilateral teleoperation system

Abstract Bilateral teleoperation systems encounter challenges in achieving synchronisation between master and slave robots due to communication time delays. This paper addresses the instability caused by these delays and proposes a solution through advanced control algorithms. Nonlinear optimisation algorithms might only sometimes deliver solutions in the allotted time, particularly when handling complicated, high-dimensional issues or when optimisation iterations are extensive. The study first develops a comprehensive mathematical model encompassing the dynamics and communication intricacies of both master and slave sides in teleoperation. By recognising the limitations of existing proportional-derivative controllers in compensating for communication errors, a sequential quadratic programming-proportional-integral-derivative (SQP-PID) controller is introduced. This controller accumulates and rectifies synchronisation delay errors, ensuring precise control without steady-state deviations. The proposed SQP-PID controller stands out for its ability to handle steady-state errors effectively, offering swift response and maintaining stability. Leveraging the SQP optimisation algorithm, it intelligently tunes the parameters, minimising synchronisation errors. The approach capitalises on the simplicity, performance, and robustness of the SQP-PID controller, providing a promising avenue for enhancing bilateral teleoperation systems’ accuracy and stability, maintaining initial discrepancy with a best fitness value of 0.98 % in varied operating conditions.

Data-driven room acoustic modeling via differentiable feedback delay networks with learnable delay lines

Over the past few decades, extensive research has been devoted to the design of artificial reverberation algorithms aimed at emulating the room acoustics of physical environments. Despite significant advancements, automatic parameter tuning of delay-network models remains an open challenge. We introduce a novel method for finding the parameters of a feedback delay network (FDN) such that its output renders target attributes of a measured room impulse response. The proposed approach involves the implementation of a differentiable FDN with trainable delay lines, which, for the first time, allows us to simultaneously learn each and every delay-network parameter via backpropagation. The iterative optimization process seeks to minimize a perceptually motivated time-domain loss function incorporating differentiable terms accounting for energy decay and echo density. Through experimental validation, we show that the proposed method yields time-invariant frequency-independent FDNs capable of closely matching the desired acoustical characteristics and outperforms existing methods based on genetic algorithms and analytical FDN design.

Network anomaly detection using Deep Autoencoder and parallel Artificial Bee Colony algorithm-trained neural network

Cyberattacks are increasingly becoming more complex, which makes intrusion detection extremely difficult. Several intrusion detection approaches have been developed in the literature and utilized to tackle computer security intrusions. Implementing machine learning and deep learning models for network intrusion detection has been a topic of active research in cybersecurity. In this study, artificial neural networks (ANNs), a type of machine learning algorithm, are employed to determine optimal network weight sets during the training phase. Conventional training algorithms, such as back-propagation, may encounter challenges in optimization due to being entrapped within local minima during the iterative optimization process; global search strategies can be slow at locating global minima, and they may suffer from a low detection rate. In the ANN training, the Artificial Bee Colony (ABC) algorithm enables the avoidance of local minimum solutions by conducting a high-performance search in the solution space but it needs some modifications. To address these challenges, this work suggests a Deep Autoencoder (DAE)-based, vectorized, and parallelized ABC algorithm for training feed-forward artificial neural networks, which is tested on the UNSW-NB15 and NF-UNSW-NB15-v2 datasets. Our experimental results demonstrate that the proposed DAE-based parallel ABC-ANN outperforms existing metaheuristics, showing notable improvements in network intrusion detection. The experimental results reveal a notable improvement in network intrusion detection through this proposed approach, exhibiting an increase in detection rate (DR) by 0.76 to 0.81 and a reduction in false alarm rate (FAR) by 0.016 to 0.005 compared to the ANN-BP algorithm on the UNSW-NB15 dataset. Furthermore, there is a reduction in FAR by 0.006 to 0.0003 compared to the ANN-BP algorithm on the NF-UNSW-NB15-v2 dataset. These findings underscore the effectiveness of our proposed approach in enhancing network security against network intrusions.

Enhancing Planning for Autonomous Driving via an Iterative Optimization Framework Incorporating Safety-Critical Trajectory Generation

Ensuring the safety of autonomous vehicles (AVs) in complex and high-risk traffic scenarios remains a critical unresolved challenge. Current AV planning methods exhibit limitations in generating robust driving trajectories that effectively avoid collisions, highlighting the urgent need for improved planning strategies to address these issues. This paper introduces a novel iterative optimization framework that incorporates safety-critical trajectory generation to enhance AV planning. The use of the HighD dataset, which is collected using the wide-area remote sensing capabilities of unmanned aerial vehicles (UAVs), is fundamental to the framework. Remote sensing enables large-scale real-time observation of traffic conditions, providing precise data on vehicle dynamics, road structures, and surrounding environments. To generate safety-critical trajectories, the decoder within the conditional variational auto-encoder (CVAE) is innovatively designed through a data-mechanism integration method, ensuring that these trajectories strictly adhere to vehicle kinematic constraints. Furthermore, two parallel CVAEs (Dual-CVAE) are trained collaboratively by a shared objective function to implicitly model the multi-vehicle interactions. Inspired by the concept of “learning to collide”, adversarial optimization is integrated into the Dual-CVAE (Adv. Dual-CVAE), facilitating efficient generation from normal to safety-critical trajectories. Building upon this, these generated trajectories are then incorporated into an iterative optimization framework, significantly enhancing the AV’s planning ability to avoid collisions. This framework decomposes the optimization process into stages, initially addressing normal trajectories and progressively tackling more safety-critical and collision trajectories. Finally, comparative case studies of enhancing AV planning are conducted and the simulation results demonstrate that the proposed method can efficiently enhance AV planning by generating safety-critical trajectories.

A novel optimal fourth-order iteration scheme for solving nonlinear problems in applied sciences

A novel optimal fourth-order iteration scheme for solving nonlinear problems in applied sciences

NVH multiobjective and robust optimization of electric motor design, including power losses

As part of electric motor design, compromises between NVH considerations, electrotechnical design and performance targets must be made. Electromagnetic excitation within the airgap results in structure-borne and airborne noise transmission to the vehicle. High-frequency tones are characteristic of this noise. Efficient computation methods exist to estimate these vibration and noise levels. From the early design stage, NVH performance can be diagnosed and optimized. The focus on NVH can no longer be separated from efficiency optimization. Simulation workflows and optimization loops, developed for NVH-related targets, are updated to consider copper and iron losses. The modification of the geometrical design must be addressed to reduce both dynamic excitation and energy loss, or at least offer compromises. Electric motor design optimization requires the handling of multiple objectives and constraints from multiple physics. In addition, design robustness must be ensured as part of the industrial process: manufacturing tolerances have to be considered to define a robust optimized design.

A cascaded FAS-UNet+ framework with iterative optimization strategy for segmentation of organs at risk.

Segmentation of organs at risks (OARs) in the thorax plays a critical role in radiation therapy for lung and esophageal cancer. Although automatic segmentation of OARs has been extensively studied, it remains challenging due to the varying sizes and shapes of organs, as well as the low contrast between the target and background. This paper proposes a cascaded FAS-UNet+ framework, which integrates convolutional neural networks and nonlinear multi-grid theory to solve a modified Mumford-shah model for segmenting OARs. This framework is equipped with an enhanced iteration block, a coarse-to-fine multiscale architecture, an iterative optimization strategy, and a model ensemble technique. The enhanced iteration block aims to extract multiscale features, while the cascade module is used to refine coarse segmentation predictions. The iterative optimization strategy improves the network parameters to avoid unfavorable local minima. An efficient data augmentation method is also developed to train the network, which significantly improves its performance. During the prediction stage, a weighted ensemble technique combines predictions from multiple models to refine the final segmentation. The proposed cascaded FAS-UNet+ framework was evaluated on the SegTHOR dataset, and the results demonstrate significant improvements in Dice score and Hausdorff Distance (HD). The Dice scores were 95.22%, 95.68%, and HD values were 0.1024, and 0.1194 for the segmentations of the aorta and heart in the official unlabeled dataset, respectively. Our code and trained models are available at https://github.com/zhuhui100/C-FASUNet-plus .

An enhanced proportional topology optimization method with new density filtering weight function for the minimum compliance problem

This article proposes an enhanced proportional topology optimization (EPTO) method to solve the structural topology optimization problem of minimizing compliance under material volume constraints. In the proposed method, a new filtering weight function based on the improved Heaviside threshold function is adopted to filter element density during the optimization process. The optimization process of the EPTO method consists of an inner loop and an outer loop. In the inner loop, density distribution is modified in combination with a new filtering weight function. By locally averaging the weighted element compliance, an improved density distribution function in the inner loop is put forward to make the topology configuration of the optimized structure more reasonable. In addition, the projection method is used to reduce the number of intermediate density elements, thereby obtaining optimization results with clear boundaries. In the outer loop, a new termination criterion is adopted, which terminates the optimization process by determining that the relative error of the objective function in several consecutive iterations is less than the specified value. The effectiveness and efficiency of the proposed method are demonstrated through several numerical examples involving two-dimensional (2D) and three-dimensional (3D) topology optimization problems. The results of numerical examples show that the proposed method can not only accelerate the convergence of optimization iterations, but also obtain optimized structures with smaller objective function values and better topology configurations. HIGHLIGHTS A new density filtering weight function is proposed based on an improved Heaviside threshold function. An improved inner loop density distribution formula is proposed by combining a new filtering weight function. Using projection based methods to suppress the appearance of intermediate density elements. Verify the effectiveness of the proposed algorithm by comparing the optimization results with existing algorithms such as top88 and PTO.

Regionalized multiple-point statistical simulation for calibrating process-based geologic models to seismic data

Calibrating process-based geologic models to seismic data is critical and has been challenging for decades. The traditional approach to data calibration involves tuning the model input parameters by trial-and-error or through an automated inverse procedure. This can improve the model calibration to data but can hardly reach a fully satisfactory result. We adopt a multiple-point statistics (MPS) approach where a process-based geologic model is used as a training image for statistical pattern recognition. First, we define a rock-physics model from the process-based geologic model and derive its seismic attributes through seismic forward modeling. Then, we use the process-based model and its seismic attributes as coupled training images for geologic pattern recognition and regeneration under seismic data constraints. The method differs from the conventional MPS method in several ways: (1) the training image is a process-based geologic model of the reservoir of interest, thus defined on the same grid of the reservoir model; (2) the training image is generally nonstationary but there is no need to partition the nonstationary training image into pseudostationary ones; (3) the geologic facies and seismic constraint are related through seismic forward modeling instead of statistical inference, thus there is no need to convert seismic data to facies proportion or probability; (4) multiple-point statistics are based on Bayes’ law and Gaussian kernel approximation of conditional probability instead of a somehow arbitrary probability combination scheme or a heuristic rule; and (5) the method does not involve an iterative optimization procedure. Therefore, it also differs from the neural-network-based machine-learning approach, where the data conditioning is achieved through an iterative optimization procedure. These differences make our method advantageous for calibrating process-based geologic models. The two examples with synthetic data illustrate the effectiveness of the method. The first one is derived from a satellite image of a river delta, and the second one from the Stanford VI reservoir model.

Co-salient object detection with iterative purification and predictive optimization

BackgroundCo-salient object detection (Co-SOD) aims to identify and segment commonly salient objects in a set of related images. However, most current Co-SOD methods encounter issues with the inclusion of irrelevant information in the co-representation. These issues hamper their ability to locate co-salient objects and significantly restrict the accuracy of detection. MethodsTo address this issue, this study introduces a novel Co-SOD method with iterative purification and predictive optimization (IPPO) comprising a common salient purification module (CSPM), predictive optimizing module (POM), and diminishing mixed enhancement block (DMEB). ResultsThese components are designed to explore noise-free joint representations, assist the model in enhancing the quality of the final prediction results, and significantly improve the performance of the Co-SOD algorithm. Furthermore, through a comprehensive evaluation of IPPO and state-of-the-art algorithms focusing on the roles of CSPM, POM, and DMEB, our experiments confirmed that these components are pivotal in enhancing the performance of the model, substantiating the significant advancements of our method over existing benchmarks. Experiments on several challenging benchmark co-saliency datasets demonstrate that the proposed IPPO achieves state-of-the-art performance.

Diversity-driven Privacy Protection Masks Against Unauthorized Face Recognition

Face recognition (FR) technologies have enabled many life-enriching applications but have also opened doors for potential misuse. Governments, private companies, or even individuals can scrape the web, collect facial images, and build a face database to fuel the FR system to identify human faces without their consent. This paper introduces PMask to combat such a privacy threat against unauthorized FR. It provides a holistic approach to enable privacy-preserving sharing of facial images. PMask preprocesses the facial image and hides its unique facial signature through iterative optimization with dual goals: (i) minimizing the amount of noise to ensure high image quality and (ii) minimizing the perception loss between the privacy-protected face and the original face to ensure the face is recognizable to be the same person by humans. Extensive experiments are conducted on eight representative FR models to evaluate PMask against unauthorized FR. The results validate that PMask provides much stronger protection, introduces less perceptible changes to facial images, and runs faster than state-of-the-art methods to provide privacy protection with a better user experience.

A Machine Learning Approach for Mechanical Component Design Based on Topology Optimization Considering the Restrictions of Additive Manufacturing

Additive manufacturing (AM) and topology optimization (TO) emerge as vital processes in modern industries, with broad adoption driven by reduced expenses and the desire for lightweight and complex designs. However, iterative topology optimization can be inefficient and time-consuming for individual products with a large set of parameters. To address this shortcoming, machine learning (ML), primarily neural networks, is considered a viable tool to enhance topology optimization and streamline AM processes. In this work, a machine learning (ML) model that generates a parameterized optimized topology is presented, capable of eliminating the conventional iterative steps of TO, which shortens the development cycle and decreases overall development costs. The ML algorithm used, a conditional generative adversarial network (cGAN) known as Pix2Pix-GAN, is adopted to train using a variety of training data pairs consisting of color-coded images and is applied to an example of cantilever optimization, significantly enhancing model accuracy and operational efficiency. The analysis of training data numbers in relation to the model’s accuracy shows that as data volume increases, the accuracy of the model improves. Various ML models are developed and validated in this study; however, some artefacts are still present in the generated designs. Structures that are free from these artefacts achieve 91% reliability successfully. On the other hand, the images generated with artefacts may still serve as suitable design templates with minimal adjustments. Furthermore, this research also assesses compliance with two manufacturing constraints: the limitations on build space and passive elements (voids). Incorporating manufacturing constraints into model design ensures that the generated designs are not only optimized for performance but also feasible for production. By adhering to these constraints, the models can deliver superior performance in future use while maintaining practicality in real-world applications.

Efficient Multitask Reinforcement Learning Without Performance Loss.

We propose an iterative sparse Bayesian policy optimization (ISBPO) scheme as an efficient multitask reinforcement learning (RL) method for industrial control applications that require both high performance and cost-effective implementation. Under continual learning scenarios in which multiple control tasks are sequentially learned, the proposed ISBPO scheme preserves the previously learned knowledge without performance loss (PL), enables efficient resource use, and improves the sample efficiency of learning new tasks. Specifically, the proposed ISBPO scheme continually adds new tasks to a single policy neural network while completely preserving the control performance of previously learned tasks through an iterative pruning method. To create a free-weight space for adding new tasks, each task is learned through a pruning-aware policy optimization method called the sparse Bayesian policy optimization (SBPO), which ensures efficient allocation of limited policy network resources for multiple tasks. Furthermore, the weights allocated to the previous tasks are shared and reused in new task learning, thereby improving sample efficiency and the performance of new task learning. Simulations and practical experiments demonstrate that the proposed ISBPO scheme is highly suitable for sequentially learning multiple tasks in terms of performance conservation, efficient resource use, and sample efficiency.

Prediction of interface morphology formed by the oblique gas jet impinging on a liquid surface

This study presents a theoretical analysis of the oblique gas jet impingement process on a liquid surface, elucidating the evolution of the flow field distribution and the influence of jet parameters on cavity shape dynamics. By integrating surface tension effects, the existing Blanks and Chandrasekhara model was refined to develop an advanced predictive model for cavity morphology. The theoretical framework was substantiated through numerical simulations and corroborated with experimental measurements of cavity dimensions, captured using state-of-the-art machine vision technology. The findings reveal a consistent trend in cavity dimension variations: an increase in the cavity surface width with the elevation of the impinging angle from the vertical and an escalation in gas jet velocity. Conversely, a reduction in the impinging angle coupled with an increase in jet velocity leads to a deeper cavity. To enhance the predictive accuracy, the model underwent iterative optimization, incorporating experimental data and accounting for jet parameters. The refined model demonstrated achieved a maximum error of 0.135 mm and a minimum error of 0.03 mm, providing reliable forecasts of cavity depth, which is pivotal for applications in fluid dynamics and related engineering fields.

Design, synthesis, and pharmacological characterization of sulfonylurea-based NLRP3 inhibitors: Towards an effective therapeutic strategy for Alzheimer's disease

Alzheimer's disease (AD) is a prevalent neurodegenerative disorder that severely diminishes the quality of life for millions. The NLRP3 inflammasome, a critical mediator of inflammation, has emerged as a promising therapeutic target for AD. In this study, we report the development and optimization of a novel series of sulfonylurea-based NLRP3 inhibitors, with a focus on compound MC1 for the treatment of AD. Utilizing the co-crystal structure of MCC950 in complex with NLRP3 as a guide, we employed a hybrid approach of computer-aided drug design and traditional medicinal chemistry to perform two iterative optimization cycles. This strategy led to the synthesis and evaluation of 40 sulfonylurea derivatives, culminating in the identification of MC1 as the lead candidate. MC1 exhibited enhanced NLRP3 inhibitory activity and demonstrated high binding affinity to NLRP3, effectively blocking NLRP3 activation induced by diverse stimuli such as ATP and Nigericin, without perturbing upstream processes like reactive oxygen species (ROS) generation. In vivo experiments in AD mouse models revealed that MC1 significantly ameliorated cognitive deficits, surpassing the performance of MCC950. Importantly, MC1 showed no signs of hepatotoxicity or adverse effects on the central nervous system. These findings suggest that MC1 holds strong potential as a lead compound for further development in AD therapy, providing a new scaffold for NLRP3 inhibition with improved safety and efficacy profiles.

Spectral Efficiency Maximization Oriented Joint Optimization for RIS-Aided mmWave IABN: An Alternating Iterative Optimization Based Approach

Spectral Efficiency Maximization Oriented Joint Optimization for RIS-Aided mmWave IABN: An Alternating Iterative Optimization Based Approach