Iterative Optimization Approach Research Articles

An Iterative Optimization Approach for Fuzzy Predictive Control

This paper proposes an iterative approach in fuzzy model predictive control. When the prediction model is nonlinear or uncertain, non-convex optimization is often encountered which has to be solved by iterative approximation. An alternative is to convert the original issue into a min-max robust MPC problem, where the knowledge of the predictive membership function is not utilized. In this paper, based on the robust MPC approach, we further enhance the model prediction by iteratively applying the optimal control move and state sequences in order to improve the performance. A numerical example is provided to illustrate the effectiveness of the proposed approach.

Interval combination iterative optimization approach coupled with SIMPLS (ICIOA-SIMPLS) for quantitative analysis of surface-enhanced Raman scattering (SERS) spectra.

Quantitative analysis of surface-enhanced Raman scattering (SERS) spectra has been a critical step in trace level analysis. In this study, a novel variable selection method called interval combination iterative optimization approach coupled with SIMPLS (ICIOA-SIMPLS) was proposed for simultaneously predicting the volume ratios of various pesticides by quantitative analysis of the SERS spectra of the compounds. Four strategies, including interval selection, model population analysis (MPA), weighted bootstrap sampling (WBS) and soft shrinkage were combined in the current designed ICIOA-SIMPLS approach. Firstly, the SERS spectra were split into a series of equal-width spectral intervals. Secondly, WBS, as a random sampling method was applied based on the initial weights of spectral intervals to generate random combinations of spectral intervals, namely sub-datasets. On this basis, multivariate calibration sub-models were developed by applying SIMPLS followed by MPA to statistically analyze the outputs of sub-models and update the weights of spectral intervals. Finally, using an iterative optimization procedure the optimal spectral interval combination with the lowest root mean squares error of cross-validation (RMSECV) was searched in a soft shrinkage manner. For the sake of investigating the performance of ICIOA-SIMPLS, four methods including SIMPLS, VCPA-SIMPLS, VISSA-SIMPLS and ICIOA-SIMPLS were tested on two groups of SERS spectra for comparison. The findings revealed that the best prediction performance was obtained with ICIOA-SIMPLS. Hence, this proposed method offers a robust and effective variable selection strategy for quantitative analysis of spectroscopic datasets.

GrIP-PCA: Grassmann Iterative P-Norm Principal Component Analysis

Principal component analysis is one of the most commonly used methods for dimensionality reduction in signal processing. However, the most commonly used PCA formulation is based on the $L_2$ -norm, which can be highly influenced by outlier data. In recent years, there has been growing interest in the development of more robust PCA methods. Recent works explore alternative norms, such as the $L_1$ -norm or the more general $L_p$ -norms, which significantly improve robustness over the $L_2$ -norm. In this work, we present the Grassmann Iterative P-norm PCA (GrIP-PCA) method, which uses an iterative Grassmann manifold optimization approach to find the solution to the highly non-convex $L_p$ -norm PCA problem. The increased flexibility of this iterative optimization approach allows for the first ever direct comparison between the projection maximization and reprojection minimization objective functions for general $L_p$ -PCA. Our results demonstrate that the underutilized reprojection formulation leads to improved robustness of PCA in multiple experiments.

Spectral Adversarial Feature Learning for Anomaly Detection in Hyperspectral Imagery

Theoretically, hyperspectral images (HSIs) are capable of providing subtle spectral differences between different materials, but in fact, it is difficult to distinguish between background and anomalies because the samples of anomalous pixels in HSIs are limited and susceptible to background and noise. To explore the discriminant features, a spectral adversarial feature learning (SAFL) architecture is specially designed for hyperspectral anomaly detection in this article. In addition to reconstruction loss, SAFL also introduces spectral constraint loss and adversarial loss in the network with batch normalization to extract the intrinsic spectral features in deep latent space. To further reduce the false alarm rate, we present an iterative optimization approach by a weighted suppression function that depends on the contribution rate of each feature to the detection. In particular, the structure tensor matrix is adopted to adaptively calculate the contribution rate of each feature. Benefiting from these improvements, the proposed method is superior to the typical and state-of-the-art methods either in detection probability or false alarm rate.

Synthesis of Low-Sidelobe 4-D Heterogeneous Antenna Arrays Including Mutual Coupling Using Iterative Convex Optimization

A novel iterative convex optimization approach is proposed for the synthesis of low-sidelobe 4-D heterogeneous arrays in the presence of mutual coupling effect. To realize wide bandwidth and wide-angle scanning, a tightly coupled dipole element (TCDE) is selected as the basic element. Due to the strong coupling between antenna elements, the active element pattern (AEP) and active reflection coefficient (ARC) are included in the proposed approach in order to evaluate the overall mutual coupling and port matching. Specifically, a nonconvex programming problem in terms of the given maximum sidelobe level (SLL), the ARC or reflected power at the center frequency, and the given maximum sideband level (SBL) at sidebands is established. After the application of some mathematical transformations, the nonconvex programming problem is decomposed into a convex optimization problem at the center frequency and an iterative convex problem (ICP) at sidebands. Owing to the efficiency of the convex optimization, the two problems can be efficiently solved. The proposed approach is applied to synthesize low-sidelobe patterns while minimizing the SBL in a 32-element cone-shaped 4-D heterogeneous array. The simulated and measured results verify the effectiveness of the proposed approach and show the advantages (improved gain) of the heterogeneous array.

Optimization of Silicone 3D Printing with Hierarchical Machine Learning

Additive manufacturing of soft materials requires optimization of printable inks, formulations of these feedstocks, and complex printing processes that must balance a large number of disparate but highly correlated variables. Here, hierarchical machine learning (HML) is applied to 3D printing of silicone elastomer via freeform reversible embedding (FRE), which is challenging because it involves depositing a Newtonian prepolymer liquid phase within a Bingham plastic support bath. The advantage of the HML algorithm is that it can predict the behavior of complex physical systems using sparse data sets through integration of physical modeling in a framework of statistical learning. Here, it is shown that this algorithm can be used to simultaneously optimize material, formulation, and processing variables. The FRE method for 3D printing silicone parts was optimized based on a training set with 38 trial runs. Compared with the previous results from iterative optimization approaches using design-of-experiment and steepest-ascent methods, HML increased printing speed by up to 2.5 × while retaining print fidelity and also identified a unique silicone formulation and printing parameters that had not been found previously through trial-and-error approaches. These results indicate that HML is an effective tool with the potential for broad application for planning and optimizing in additive manufacturing of soft materials via the FRE method.

Caching mechanism for mobile edge computing in V2I networks

AbstractThe caching‐enabled mobile edge computing (MEC) system becomes increasingly crucial to the future long‐term evolution vehicle‐to‐infrastructure (LTE‐V2I) network, especially for fast delivery of popular content of delay‐sensitive applications in the backhaul capacity–limited vehicular networks. Most related studies mainly focus on computation offloading strategy design and coding caching, while the deployment strategy design of caching capacities for high‐speed vehicles has been overlooked. In this paper, we investigate the deployment problem in LTE‐V2I networks with particular consideration on high‐speed vehicles. First, in a one‐way scenario, a joint optimization framework is formulated to minimize the cache size of the MEC system, meanwhile maximizing the average downloading percentage, where the MEC system's backhaul capacities, vehicle speeds, content popularity distributions, and sides of the highway are taken into account. The impacts of LTE‐V2I system parameters, eg, vehicle speed, on the objective function are revealed through the one‐way optimization. Then, the two‐way optimization is formulated and solved by developing an iterative optimization approach based on the aforementioned one‐way scenario. Particularly, the optimal caching allocation between two ways is derived. Simulation results validate the effectiveness of the proposed approaches even with low backhaul capacities and high vehicle speed.

Iterative Optimization of the Cyclic Peptide SFTI-1 Yields Potent Inhibitors of Neutrophil Proteinase 3.

Neutrophils produce at least four serine proteases that are packaged within azurophilic granules. These enzymes contribute to antimicrobial defense and inflammation but can be destructive if their activities are not properly regulated. Accordingly, they represent therapeutic targets for several diseases, including chronic obstructive pulmonary disease, cystic fibrosis, and rheumatoid arthritis. In this study, we focused on proteinase 3 (PR3), a neutrophil protease with elastase-like specificity, and engineered potent PR3 inhibitors based on the cyclic peptide sunflower trypsin inhibitor-1 (SFTI-1). We used an iterative optimization approach to screen targeted substitutions at the P1, P2, P2', and P4 positions of SFTI-1, and generated several new inhibitors with K i values in the low nanomolar range. These SFTI-variants show high stability in human serum and are attractive leads for further optimization.

Extended reduced‐rank joint estimation of direction of arrival with mutual coupling for coherent signals

AbstractThis paper proposes an extended method for direction‐of‐arrival (DOA) estimation with unknown mutual coupling for coherent signals. The proposed method employs the forward/backward spatial smoothing to decorrelate the coherent signals in the process of rank reduction with the joint iterative subspace optimization approach. Then, the autocalibration of mutual coupling is performed based on the Capon's minimum variance criterion. Performance of the proposed method is compared with the state of the art algorithms in terms of DOA root‐mean‐square error and in terms of probability of successful estimation, where successful estimation is the case when the average of absolute DOA estimation error is within 2.5°. It is shown that the proposed method has a similar performance as the state of the art autocalibration methods while offering a lower computational complexity.

GalaxyRefine2: simultaneous refinement of inaccurate local regions and overall protein structure.

The 3D structure of a protein can be predicted from its amino acid sequence with high accuracy for a large fraction of cases because of the availability of large quantities of experimental data and the advance of computational algorithms. Recently, deep learning methods exploiting the coevolution information obtained by comparing related protein sequences have been successfully used to generate highly accurate model structures even in the absence of template structure information. However, structures predicted based on either template structures or related sequences require further improvement in regions for which information is missing. Refining a predicted protein structure with insufficient information on certain regions is critical because these regions may be connected to functional specificity that is not conserved among related proteins. The GalaxyRefine2 web server, freely available via http://galaxy.seoklab.org/refine2, is an upgraded version of the GalaxyRefine protein structure refinement server and reflects recent developments successfully tested through CASP blind prediction experiments. This method adopts an iterative optimization approach involving various structure move sets to refine both local and global structures. The estimation of local error and hybridization of available homolog structures are also employed for effective conformation search.

Flexible automation with compact NMR spectroscopy for continuous production of pharmaceuticals

Modular plants using intensified continuous processes represent an appealing concept for the production of pharmaceuticals. It can improve quality, safety, sustainability, and profitability compared to batch processes; besides, it enables plug-and-produce reconfiguration for fast product changes. To facilitate this flexibility by real-time quality control, we developed a solution that can be adapted quickly to new processes and is based on a compact nuclear magnetic resonance (NMR) spectrometer. The NMR sensor is a benchtop device enhanced to the requirements of automated chemical production including robust evaluation of sensor data. Beyond monitoring the product quality, online NMR data was used in a new iterative optimization approach to maximize the plant profit and served as a reliable reference for the calibration of a near-infrared (NIR) spectrometer. The overall approach was demonstrated on a commercial-scale pilot plant using a metal-organic reaction with pharmaceutical relevance.Graphical abstract

Learning-Assisted Optimization for Energy-Efficient Scheduling in Deadline-Aware NOMA Systems

In this paper, we study a class of minimum-energy scheduling problems in non-orthogonal multiple access (NOMA) systems. NOMA is adopted to enable efficient channel utilization and interference mitigation, such that base stations can consume minimal energy to empty their queued data in presence of transmission deadlines, and each user can obtain all the requested data timely. Due to the high computational complexity in resource scheduling and the stringent execution-time constraints in practical systems, providing a time-efficient and high-quality solution to 5G real-time systems is challenging. The conventional iterative optimization approaches may exhibit their limitations in supporting online optimization. We herein explore a viable alternative and develop a learning-assisted optimization framework to improve the computational efficiency while retaining competitive energy-saving performance. The idea is to use deep-learning-based predictions to accelerate the optimization process in conventional optimization methods for tackling the NOMA resource scheduling problems. In numerical studies, the proposed optimization framework demonstrates high computational efficiency. Its computational time is insensitive to the input size. The framework is able to provide optimal solutions as long as the learning-based predictions satisfy a derived optimality condition. For the general cases with imperfect predictions, the algorithmic solution is error-tolerable and performance scaleable, leading the energy-saving performance close to the global optimum.

Constrained density functional theory calculation with iterative optimization

An iterative optimization approach that simultaneously minimizes the energy and optimizes the Lagrange multipliers enforcing desired constraints is presented. The method is tested on previously established benchmark systems and it is proved to be efficient and accurate. The approach can also be efficiently used when the constraint is not a scalar quantity but a spatially varying function like the charge density distribution.

Active Perturbation in Modifier Adaptation for Real Time Optimization to Cope with Measurement Delays

Iterative optimization is a technique where the model-based optimization problem is iteratively updated to drive the plant to its optimal operating point in the presence of plant-model mismatch. Modifier adaptation (MA) is a state-of-the-art iterative optimization approach which can be used in the presence of both structural and parametric plant-model mismatch. Availability of plant measurements is key for the successful application of MA. In the process industries, analytical sensors cannot always be installed directly at the location of interest. A remote positioning of a measurement device leads to a significant delay in receiving the measurements, since the transportation of the sample to the sensor requires additional time. This leads to a waiting time between two successive iterations during which the standard iterative optimization techniques remain idle. In this contribution, the issue of a pure time delay caused by the remote positioning of a sensor is addressed. We propose an active perturbation strategy to obtain more information by perturbing the plant during the waiting time to improve the estimation of the plant gradient, which reduces the time to reach the plant-optimum. The performance of the proposed strategy is analyzed based on the simulation results from a chemical engineering case study.

Robust Object Tracking by Nonlinear Learning.

We propose a method that obtains a discriminative visual dictionary and a nonlinear classifier for visual tracking tasks in a sparse coding manner based on the globally linear approximation for a nonlinear learning theory. Traditional discriminative tracking methods based on sparse representation learn a dictionary in an unsupervised way and then train a classifier, which may not generate both descriptive and discriminative models for targets by treating dictionary learning and classifier learning separately. In contrast, the proposed tracking approach can construct a dictionary that fully reflects the intrinsic manifold structure of visual data and introduces more discriminative ability in a unified learning framework. Finally, an iterative optimization approach, which computes the optimal dictionary, the associated sparse coding, and a classifier, is introduced. Experiments on two benchmarks show that our tracker achieves a better performance compared with some popular tracking algorithms.

Image Restoration via Group l2,1 Norm-Based Structural Sparse Representation

Sparse representation has recently been extensively studied in the field of image restoration. Many sparsity-based approaches enforce sparse coding on patches with certain constraints. However, extracting structural information is a challenging task in the field image restoration. Motivated by the fact that structured sparse representation (SSR) method can capture the inner characteristics of image structures, which helps in finding sparse representations of nonlinear features or patterns, we propose the SSR approach for image restoration. Specifically, a generalized model is developed using structured restraint, namely, the group [Formula: see text]-norm of the coefficient matrix is introduced in the traditional sparse representation with respect to minimizing the differences within classes and maximizing the differences between classes for sparse representation, and its applications with image restoration are also explored. The sparse coefficients of SSR are obtained through iterative optimization approach. Experimental results have shown that the proposed SSR technique can significantly deliver the reconstructed images with high quality, which manifest the effectiveness of our approach in both peak signal-to-noise ratio performance and visual perception.

Investigation of the operability for four-product dividing wall column with two partition walls

Abstract For separating some specific four component mixtures into four products, the four-product dividing wall column (FPDWC) with two partition walls can provide the same utility consumption with the extended Petlyuk configuration, although with structure simplicity. However, the reluctance to implement this kind of four product dividing wall column industrially also consists in the two uncontrollable vapor splits associated with it. The vapor split ratios are set at the design stage and might not be the optimal value for changed feed composition, thus minimum energy consumption could not be ensured. In the present work, a sequential iterative optimization approach was initially employed to determine the parameters of cost-effective FPDWC. Then the effect of maintaining the vapor split ratios at their nominal value on the energy penalty was investigated for the FPDWC with two partition walls, in case of feed composition disturbance. The result shows that no more than + 2% above the optimal energy requirements could be ensured for 20% feed composition disturbances, which is encouraging for industrial implementation.

Throughput Enhancement via Iterative Optimization Approach and Modifying Max-SINR Algorithm for the MIMO Interference Network under Imperfect Channel State Information

Design of robust transceiver for data rate improvement in interference channel (IC), under imperfect channel state information (CSI), is an important research area. This paper, employs an iterative optimization approach to design algorithm for throughput enhancement in a multi-input multi-output (MIMO) IC. Nodes in the MIMO IC, work in a time division duplex mode, where half of them are equipped with M antennas while the others have N antennas. In the proposed scheme, each transceiver adjusts its associated filter based on the maximization of the signal-to-interference-plus-noise ratio (SINR). In the time division duplex working mode, the problem utilizes reciprocity of the wireless network. Furthermore, it is investigated how the algorithms proposed by Gomadam et al. can be modified to enhance throughput under CSI error. With the knowledge of error variance Max-SINR is modified. Simulation results present the throughput performances of the proposed algorithms.

On gradient‐based optimization strategies for inverse problems in metal forming

AbstractIn the context of metal forming, optimization issues typically lead to inverse problems with a least‐squares minimization as the objective. Due to the nonlinearities in forming simulations, iterative optimization approaches have to be considered. Gradient‐based solution strategies for two inverse problems are proposed and compared to each other. Firstly, the identification of elasto‐plastic material parameters is regarded. Secondly, a recently developed approach for the determination of an optimal workpiece design is investigated. As a special feature, both approaches can be coupled in a non‐invasive fashion to arbitrary external finite element software via subroutines.

FACADE SEGMENTATION WITH A STRUCTURED RANDOM FOREST

Abstract. In this paper we present a bottom-up approach for the semantic segmentation of building facades. Facades have a predefined topology, contain specific objects such as doors and windows and follow architectural rules. Our goal is to create homogeneous segments for facade objects. To this end, we have created a pixelwise labeling method using a Structured Random Forest. According to the evaluation of results for two datasets with the classifier we have achieved the above goal producing a nearly noise-free labeling image and perform on par or even slightly better than the classifier-only stages of state-of-the-art approaches. This is due to the encoding of the local topological structure of the facade objects in the Structured Random Forest. Additionally, we have employed an iterative optimization approach to select the best possible labeling.