Search Step Research Articles

Multiple source tracking and identifications in urban regions with unstable wind flows: Particle swarm optimization methodologies and their benchmark solutions

The prompt and accurate identification of transient pollution sources in urban regions is imperative for effective pollutant control and the mitigation to public health risks. Depending on sparse concentration distributions, multiple pollution sources identification is inherently complex and difficult, particularly when the pollutant sources exhibit time-varying release rates and are located in urban environments subject to dynamic wind flows. In this research, two niche-based Particle Swarm Optimization (PSO) algorithms, Niche-DPSO (niche pso for dynamic systems) and RSNM-DPSO (ranged subgroup pso with nelder mead for dynamic systems), were simultaneously proposed, aiming to localize multiple pollution sources under the background of unsteady wind flow fields. The MUST experiment, characterized by its complex layout replete with densely arranged obstacles, was adopted as the application scenario. Computational Fluid Dynamics (CFD) was employed to simulate the release of pollutant concentration at (−25.8 m, 0 m, 1.6 m) and (24.2 m, 41.6 m, 1.6 m), with flow velocities ranges from 1.8 to 7.6 m/s. Representative performance-influencing factors, including niche radius, population size, sensor response time, and sensor errors, were systematically evaluated. The results suggested that both Niche-DPSO and RSNM-DPSO algorithms were generally effective in positioning multiple pollution sources. Comparative analysis revealed that Niche-DPSO consistently outperformed RSNM-DPSO in terms of localization success rates, achieving a peak performance of approximately 98 %. Furthermore, Niche-DPSO could maintain its robust performance even under time-spatial-varying environmental and operational conditions, albeit at the expense of requiring more search steps and longer CPU processing time.

An adaptive artificial bee colony for hybrid flow shop scheduling with batch processing machines in casting process

Hybrid flow shop scheduling problem (HFSP) with real-life constraints has been extensively considered; however, HFSP with batch processing machines (BPM) at a middle stage is seldom investigated. In this study, HFSP with BPM at a middle stage in hot & cold casting process is considered and an adaptive artificial bee colony (AABC) is proposed to minimise makespan. To produce high quality solutions, an adaptive search process with employed bee phase and adaptive search step is implemented. Adaptive search step, which may be onlooker bee phase or cooperation or empty, is decided by evolution quality and an adaptive threshold. Cooperation is performed between the improved solutions of one employed bee swarm and the unimproved solutions of another swarm. Six search operators are constructed and search operator is adaptively adjusted. A new scout phase is also given. A lower bound is provided and proved. Extensive experiments are conducted. The computational results validate that new strategies such as cooperation are effective and efficient and AABC can obtain better results than methods from existing literature on the considered problem.

Toward Data Center Digital Twins via Knowledge-based Model Calibration and Reduction

Computational fluid dynamics (CFD) models have been widely used for prototyping data centers. Evolving them into high-fidelity and real-time digital twins is desirable for the online operations of data centers. However, CFD models often have unsatisfactory accuracy and high computation overhead. Manually calibrating the CFD model parameters is tedious and labor-intensive. Existing automatic calibration approaches apply heuristics to search the model configurations. However, each search step requires a long-lasting process of repeatedly solving the CFD model, rendering them impractical, especially for complex CFD models. This article presents Kalibre , a knowledge-based neural surrogate approach that calibrates a CFD model by iterating four steps of (i) training a neural surrogate model, (ii) finding the optimal parameters through neural surrogate retraining, (iii) configuring the found parameters back to the CFD model, and (iv) validating the CFD model using sensor-measured data. Thus, the parameter search is offloaded to the lightweight neural surrogate. To speed up Kalibre’s convergence, we incorporate prior knowledge in training data initialization and surrogate architecture design. With about ten hours of computation on a 64-core processor, Kalibre achieves mean absolute errors (MAEs) of 0.57°C and 0.88°C in calibrating the CFD models of two production data halls hosting thousands of servers. To accelerate CFD-based simulation, we further propose Kalibreduce that incorporates the energy balance principle to reduce the order of the calibrated CFD model. Evaluation shows the model reduction only introduces 0.1°C to 0.27°C extra errors while accelerating the CFD-based simulations by thousand times.

Scaffolding practices for modelling instruction in STEM-related contexts: insights from expert and novice teachers

AbstractMathematical modelling (MM) plays a pivotal role in the integration of Science, Technology, Engineering and Mathematics (STEM) into school studies. This current empirical study suggests using a four-step solution plan as a scaffolding tool during the instruction of MM tasks in a STEM context in formal school mathematics. The study goals are twofold; first to recognise MM-oriented scaffolding practices of teachers during observations of their instruction of MM tasks. Second, to explore the differences in type and quantity of the recognised scaffolding practices, while comparing MM task instruction in a STEM context of expert and novice teachers. Using a multiple case study design, we conducted an in-depth study of MM scaffolding practices implemented during instruction of three MM tasks in a STEM context (the ‘Mobileye’, ‘Gamma correction’, and ‘GPS’ MM tasks) taught by three expert teachers and five novice teachers, in a total of five lessons for each group. Findings revealed three types of practices to support a particular solution plan step, enact the transition between solution plan steps, and motivate students' MM learning. A similar distribution of practices between expert and novice teachers was revealed, while support in each step of the solution plan was evident to all, especially during the mathematical search step. The study provides a perspective on the necessary practices that may take place in modelling instruction in a STEM context.

Experience of having a sibling with autism spectrum disorder: a systematic review protocol.

This qualitative systematic review aims to understand the experiences of neurotypical siblings of a person with autism spectrum disorder. Autism spectrum disorder influences communication and social interaction with other people and has a significant impact on family relationships. The experiences of siblings range from the positive, such as development of increased empathy and ability to cope with challenges, to experiences that are more negative, such as a higher risk of bullying. In many countries, neurotypical siblings are marginalized and don't receive adequate support to cope with the increased challenges. This review will consider qualitative studies exploring the experiences of siblings of a person with autism spectrum disorder. There will be no limitations regarding age, gender, sex, or length of relationship with the sibling. We will consider studies from all countries and contexts. This study will be conducted according to the JBI methodology for qualitative reviews. A 3-step search strategy will be used to find published and unpublished studies from the following sources: MEDLINE, CINAHL, APA PsycINFO, Scopus, SocINDEX, Web of Science, Embase, ERIC, ProQuest Dissertations and Theses, Open Dissertations, and Google Scholar (first 100 records). There will be no search limitations on the publication period or language, but only studies with an English-language abstract/title will be considered for inclusion. Screening, data extraction, and data synthesis will be conducted by 2 independent reviewers.

An Enhanced Hunger Games Search Optimization with Application to Constrained Engineering Optimization Problems.

The Hunger Games Search (HGS) is an innovative optimizer that operates without relying on gradients and utilizes a population-based approach. It draws inspiration from the collaborative foraging activities observed in social animals in their natural habitats. However, despite its notable strengths, HGS is subject to limitations, including inadequate diversity, premature convergence, and susceptibility to local optima. To overcome these challenges, this study introduces two adjusted strategies to enhance the original HGS algorithm. The first adaptive strategy combines the Logarithmic Spiral (LS) technique with Opposition-based Learning (OBL), resulting in the LS-OBL approach. This strategy plays a pivotal role in reducing the search space and maintaining population diversity within HGS, effectively augmenting the algorithm's exploration capabilities. The second adaptive strategy, the dynamic Rosenbrock Method (RM), contributes to HGS by adjusting the search direction and step size. This adjustment enables HGS to escape from suboptimal solutions and enhances its convergence accuracy. Combined, these two strategies form the improved algorithm proposed in this study, referred to as RLHGS. To assess the efficacy of the introduced strategies, specific experiments are designed to evaluate the impact of LS-OBL and RM on enhancing HGS performance. The experimental results unequivocally demonstrate that integrating these two strategies significantly enhances the capabilities of HGS. Furthermore, RLHGS is compared against eight state-of-the-art algorithms using 23 well-established benchmark functions and the CEC2020 test suite. The experimental results consistently indicate that RLHGS outperforms the other algorithms, securing the top rank in both test suites. This compelling evidence substantiates the superior functionality and performance of RLHGS compared to its counterparts. Moreover, RLHGS is applied to address four constrained real-world engineering optimization problems. The final results underscore the effectiveness of RLHGS in tackling such problems, further supporting its value as an efficient optimization method.

A return mapping algorithm based on the hyper dual step derivative approximation for elastoplastic models

Accurately evaluating derivatives poses a key challenge when numerically implementing complex constitutive models. This work presents an implicit stress update algorithm that utilizes the hyper dual step derivative approximation to address derivative evaluations in elastoplastic problems. Initially, the performance of various numerical differentiation methods is discussed and compared by examining their numerical errors in the representative example. Subsequently, the hyper dual step derivative approximation, without truncation and subtractive cancellation errors, is employed to compute the Jacobian matrix and consistent tangent operator, ensuring quadratic convergence in both local and global computations. The size of the Newton search step is optimized by the line search technique, thereby enhancing the convergence in solving nonlinear stress integral equations. Finally, the proposed stress update algorithm is used to implement the non-associated Mohr–Coulomb plastic model in the ABAQUS software using the UMAT subroutine. The stress update algorithm’s performance and its practical application in geotechnical engineering problems are demonstrated using five boundary value problems.

Nursing interventions for pediatric patients with cancer and their families: a scoping review protocol.

This scoping review will identify and map available nursing interventions provided by pediatric oncology hospital services to pediatric patients with cancer and/or their family members. The aim is to develop a comprehensive overview of the characteristics of nursing interventions and to identify potential knowledge gaps. Clinical nursing care is an essential part of pediatric oncology. In pediatric oncology nursing research, a shift from explanatory studies to intervention studies is recommended. The body of research on interventions for pediatric oncology patients and their families has grown in recent years. However, there are no reviews on nursing interventions currently available for pediatric oncology. Studies will be considered for inclusion if they refer to pediatric patients with cancer, and/or family members of a pediatric patient with cancer, who have received non-pharmacological and non-procedural nursing interventions provided by a pediatric oncology hospital service. Studies must also be peer-reviewed, published from the year 2000 onward, and written in English, Danish, Norwegian, or Swedish. The review will be conducted in accordance with the JBI guidelines for scoping reviews. A 3-step search strategy will be followed using the PCC mnemonic (Population, Content, Context). The databases to be searched will include Scopus, PubMed, CINAHL, PsyclNFO, and Embase. The identified studies will be screened based on title and abstract, as well as full text, by 2 independent reviewers. Data will be extracted and managed in Covidence. A summary of the results will be presented as a narrative description, supported by tables.

Influence of parameterization method and optimization algorithm on airfoil optimization

In this study, the impact of parameterization methods and optimization algorithms on the optimization results of the RAE2822 airfoil is examined. Specifically, how variations in the number of design variables, spacing of control points, the scaling scale of the objective function, and line search step of different FFD parameterization methods affect the resistance convergence process are investigated. The results indicate that the number of design variables and the spacing of control points play a significant role in the speed and minimum value of resistance convergence. In contrast, the scaling scale of the objective function and the line search step has a relatively minor impact on resistance optimization.

A Real-Time Path Planning Method for Urban Low-Altitude Logistics UAVs.

To solve the problem of poor real-time performance in path planning algorithms for unmanned aerial vehicles (UAVs) in low-altitude urban logistics, a path planning method combining modified Beetle Antennae Search (BAS) with the Simulated Annealing (SA) algorithm is proposed. Firstly, based on the requirements of task execution and constraints of UAV flight, a fitness function for real-time search of waypoints is designed while ensuring the safety and obstacle avoidance of the UAV. Then, to improve the search accuracy and real-time performance, determining the initial search direction in the BAS algorithm is improved, while the search step size and antennae sensing length are updated in real-time according to the distance between the UAV and the obstacle. Finally, the SA algorithm is combined with the BAS algorithm to update the waypoints, expanding the search range of each waypoint, avoiding the process of updating the waypoints from becoming trapped in the local optimal waypoints. Meanwhile, the effectiveness of the next waypoint is evaluated based on the Metropolis criterion. This paper generates a virtual urban logistics distribution environment based on the density and distribution of urban buildings, and compares the performance of algorithms in obstacle-sparse, obstacle-moderate, and obstacle-dense environments. The simulation results demonstrate that the improved method in this paper has a more significant capacity for environmental adaptation. In terms of the path length, waypoints, safety obstacle avoidance, and smoothness, the planned path outperforms the original BAS method. It satisfies the needs of real-time path planning for UAVs involved in urban low-altitude logistics.

A novel self-adaptive multi-strategy artificial bee colony algorithm for coverage optimization in wireless sensor networks

Wireless sensor node coverage optimization is a critical issue in wireless sensor networks (WSN), which is a commonly typical NP-hard problem. To enhance the coverage of wireless sensor networks, coverage optimization refers to the prudent placement of resource-constrained wireless sensor nodes. Current coverage optimization techniques frequently result in local optimums and have poor optimization performance. Based on the excellent optimization performance of artificial bee colony (ABC) algorithm, this paper presents a novel self-adaptive multi-strategy artificial bee colony (SaMABC) algorithm, which designs an appropriate strategy pool and a fine-grained adaptive selection mechanism according to the coverage optimization problem. Furthermore, the algorithm is improved through using simulated annealing approach and the dynamic search step to enhance its ability to jump out of the local optimum. Compared with the state-of-the-art optimization algorithms, the evaluation results carried out in several scenarios show that SaMABC obtains the best performance in terms of coverage optimization. Specifically, the coverage of wireless sensor networks in SaMABC achieves around 99.1% and outperforms the initial coverage by up to 14.1%.

Physical therapists' use of telehealth in older adults within the home health setting: a scoping review protocol.

The objective of this scoping review is to summarize the available information on types of telehealth services provided to older adults when physical therapy is involved in their delivery of care. Methods of clinical assessment and outcomes will also be identified. Information on telerehabilitation interventions for older adults is lacking, yet older individuals can greatly benefit from person-centered care within a home setting. Hence, it is important to synthesize the literature pertaining to telehealth and physical therapy to identify gaps and key implications. This review will consider studies that include adults who are 65 years of age or older, who receive telehealth services within their home, and have a physical therapist involved. Quantitative, qualitative, and gray literature will be included in this review. There will be no language limits. A 3-step search strategy will be followed, in line with the JBI methodology for scoping reviews. Databases to be searched will include JBI Evidence Synthesis , Cochrane Database of Systematic Reviews, MEDLINE (Ovid), CINAHL (EBSCOhost), PRIMO, PubMed Central, PsycINFO (Ovid), LWW Nursing/Medical Journals (Ovid), and OpenGrey. Data will be extracted by 2 independent reviewers. The results will be synthesized, charted, and mapped and the findings will be presented in a peer-reviewed journal. Open Science Framework https://osf.io/9kyus/.

Compared with CT/MRI LI-RADS, whether CEUS LI-RADS is worth popularizing in diagnosis of hepatocellular carcinoma?-a direct head-to-head meta-analysis.

Until now, there has been no systematic review or meta-analysis of direct head-to-head studies that compare two liver imaging reporting and data system (LI-RADS) algorithms, contrast-enhanced ultrasound (CEUS) LI-RADS and contrast-enhanced computed tomography/magnetic resonance imaging (CT/MRI) LI-RADS, for the diagnostic efficacy of hepatocellular carcinoma. The purpose of this study was to identify and head-to-head compare the diagnostic performance of both LI-RADS algorithms for hepatocellular carcinoma. We searched the PubMed, EMBASE, Web of Science, and Cochrane Library databases from the inception of each database to April 26, 2022, to find the comparative study of both LI-RADS algorithms for hepatocellular carcinoma at risk of patients who underwent both LI-RADS algorithms. Eligibility criteria included only studies published in English, full reports published, both retrospective and prospective studies. Liver histology or imaging follow-up results served as the reference standard. We analyzed the sensitivity, specificity, positive likelihood ratio, negative likelihood ratio, diagnostic odds ratio, and summary receiver operating characteristic curve to determine summary estimates. The Quality Assessment of Diagnostic Accuracy Studies was utilized to assess the methodological quality. In 5 included studies (831 patients, 877 lesions), the pooled sensitivity and pooled specificity of CEUS LR-5 were 0.79, 0.81, and 0.78, 0.79 in CT/MRI LR-5, respectively. The pooled sensitivity and pooled specificity of CEUS LR-4/5 were 0.86, 0.70, and 0.93, 0.59 in CT/MRI LR-4/5, respectively. There was no obvious difference between the two LI-RADS algorithms for hepatocellular carcinoma, and there was no significant statistical difference between two LR-M algorithms for non-hepatocellular carcinoma malignancies. The results of our analysis demonstrated that CEUS LI-RADS has satisfactory diagnostic performance similar to that of CT/MRI LI-RADS, which provides a theoretical basis for the popularization of CEUS LI-RADS for diagnosing HCC. This work was supported by Sichuan Science and Technology Program (No. 2020YFS0211). We registered this study on the international prospective register of systematic reviews (PROSPERO, CRD42022328107) before the search step.

Intelligent Search Strategy for Doppler Frequency Based on Fuzzy Logic in DSSS Signal Acquisition

This study focuses on Doppler frequency search strategy for signal acquisition in direct sequence spread spectrum (DSSS) systems. According to DSSS signal accumulation energy vibration characteristics, the whole two-dimension search region can be divided into non-vicinity region, transition region and vicinity region. If only one search strategy is used for the whole region, it is difficult to balance the frequency search times and the frequency estimation accuracy. To solve the above problem, this study proposes an intelligent Doppler frequency search (IDFS) strategy. A fuzzy logic (FL) controller with two sets of fuzzy parameters is utilized to adjust the frequency search step size in the non-vicinity region and vicinity region, respectively. In the non-vicinity region, by jointly considering signal amplitude and code phase to design the fuzzy parameters of the FL controller, the IDFS strategy can reduce the frequency search times while reducing frequency false detection caused by abnormal change of signal energy. In the vicinity region, the fuzzy parameters are designed based on our previous work which aims to achieve higher frequency estimation accuracy. The effectiveness of the IDFS strategy is evaluated through Monte Carlo simulations. Simulation results show that the proposed intelligent search strategy can reduce the frequency search times while ensuring frequency estimation accuracy compared to other existing search strategies. Moreover, the proposed search strategy can reduce false detection in the non-vicinity region.

SAR Image Reconstruction via Incremental Imaging With Compressive Sensing

For synthetic aperture radar (SAR) imaging, the irregular loss of received data and the non-uniformly under sampling yield the SAR azimuth ambiguity (SAA) resulting in the degradation in image quality. To address this issue, the incremental SAR imaging approach based on the estimation of sensing dictionary matrix in the pursuit of sparsity is presented in this paper. Several beneficial contributions are included in the proposed method. First, the SAA reduction achievable in the proposed method is considerably improved more than that of the conventional compressive sensing (CS) based approach in terms of the image quality and computational efficiency. Second, we established the signal parameterization scheme which is divided into coarse and fine search steps to estimate the sensing matrix for SAR image restoration via signal model reconstruction. Third, an incremental imaging approach is devised to overcome the drawback of the conventional CS-based approach which is not sufficiently good leading to limited SAA reduction performance under the non-sparse SAR image. These contributions are verified using numerical simulations and experimental results.

ATNAS: Automatic Termination for Neural Architecture Search

Neural architecture search (NAS) is a framework for automating the design process of a neural network structure. While the recent one-shot approaches have reduced the search cost, there still exists an inherent trade-off between cost and performance. It is important to appropriately stop the search and further reduce the high cost of NAS. Meanwhile, the differentiable architecture search (DARTS), a typical one-shot approach, is known to suffer from overfitting. Heuristic early-stopping strategies have been proposed to overcome such performance degradation. In this paper, we propose a more versatile and principled early-stopping criterion on the basis of the evaluation of a gap between expectation values of generalisation errors of the previous and current search steps with respect to the architecture parameters. The stopping threshold is automatically determined at each search epoch without cost. In numerical experiments, we demonstrate the effectiveness of the proposed method. We stop the one-shot NAS algorithms and evaluate the acquired architectures on the benchmark datasets: NAS-Bench-201 and NATS-Bench. Our algorithm is shown to reduce the cost of the search process while maintaining a high performance.

Semantic segmentation using Firefly Algorithm-based evolving ensemble deep neural networks

Automatic segmentation of salient objects in real-world images has gained increasing interests owing to its popularity in diverse real-world applications, such as autonomous driving, medical diagnosis, aviation security, and underwater surveillance. In this research, we propose Firefly Algorithm (FA)-enhanced evolving ensemble deep networks for semantic segmentation and visual saliency prediction. An improved FA model is proposed to optimize network hyper-parameters. Specifically, it employs mutation operators and a neighbouring search strategy with granular search steps to establish search intensification. It also emphasizes search diversification by adopting multiple dynamic hybrid leaders and diverse adaptive sine and cosine search trajectories in full and randomly selected sub-dimensions to overcome stagnation. Because of its competent segmentation performance, DeepLabV3+ is fine-tuned using transfer learning with FA-based hyper-parameter identification. We optimize the learning rate, momentum and weight decay of the transfer learning network. A number of optimized DeepLabV3+ networks with distinguishing learning configurations are yielded. An ensemble model is subsequently constructed by incorporating three optimized base networks to further strengthen segmentation performance. Evaluated using diverse challenging semantic segmentation and saliency prediction tasks using underwater and medical image data sets, our evolving ensemble deep network illustrates significant superiority over other state-of-the-art deep networks and existing studies. The proposed FA model also outperforms other search methods in solving diverse mathematical landscapes with statistical significance.

Advanced framework for enhancing ultrasound images through an optimized hybrid search algorithm and a novel motion compounding processing chain

Ultrasound imaging is a fast, widespread, and essential diagnostic technique for examining the body’s internal anatomy to find abnormal tissues or diseases. However, speckle noise in ultrasound imaging corrupts fine details and edges and degrades the image’s resolution and contrast, making diagnosing more difficult. In this work, a speckle reduction method using motion compounding is proposed. The objective of this work is ultrasound image enhancement keeping all the diagnostics details and edges. The proposed method uses the pre-locations frames that the sonographer generates before locating the required diagnostic frame. These frames are applied to the proposed optimized Modified Three-Step Search (O-MTSS) algorithm to enhance the final processed frame. The O-MTSS algorithm is a hybrid between the Three Step Search algorithm (TSS) and the New Diamond Search Algorithm (NDS). The method requires a scoring layer for storing additional frames to select optimal frames that will be used for enhancement. The proposed methodology is tested on synthetic and real ultrasound images. The outcomes produce considerable speckle reduction while maintaining the image edges with good computational time for real-time scanning. The result is evaluated by subjective physicians, radiologists, and image evaluation metrics. According to the percentages of the subjective analysis, there is a remarkable improvement in the processed image. The proposed algorithm result is compared with existing algorithms; It is observed that the improvement in terms of signal to noise ratio, peak signal to noise ratio, mean square error, root mean square error and structural similarity index values of the proposed method are 4.6%, 3.32%, 12.02%, 6.2% and 1.57% respectively over Non-Local Low-Rank (NLLR) method. According to qualitative and quantitative analysis, the suggested method outperforms existing speckle reduction techniques regarding edge and fine detail preservation.

Inverse kinematics solution of demolition manipulator based on global mapping

In solving the inverse kinematics of the redundant hydraulic manipulator of the demolition robot, there are problems of multiple solutions and the contradiction between the real-time and accuracy of the calculation. A series calculation strategy combining global mapping and local search was proposed. Firstly, the inverse kinematics solution was mapped from the global space to the local space of the working point by the global neural network model, and then the inverse solution results were obtained by the local search of the gravitational search algorithm. To avoid the GSA falling into the local minima and improve the search speed and accuracy, an improved gravitational particle adaptive step search strategy was proposed to balance the exploration and development stage of the population. The simulation and experimental results show that the global than local inverse solution algorithm can avoid the multi-solution problems and ensure the stability and accuracy of the solution on the basis of real-time inversion.

Solving the capacitated vehicle routing problem with time windows via graph convolutional network assisted tree search and quantum-inspired computing

Vehicle routing problems are a class of NP-hard combinatorial optimization problems which attract a lot of attention, as they have many practical applications. In recent years there have been new developments solving vehicle routing problems with the help of machine learning, since learning how to automatically solve optimization problems has the potential to provide a big leap in optimization technology. Prior work on solving vehicle routing problems using machine learning has mainly focused on auto-regressive models, which are connected to high computational costs when combined with classical exact search methods as the model has to be evaluated in every search step. This paper proposes a new method for approximately solving the capacitated vehicle routing problem with time windows (CVRPTW) via a supervised deep learning-based approach in a non-autoregressive manner. The model uses a deep neural network to assist finding solutions by providing a probability distribution which is used to guide a tree search, resulting in a machine learning assisted heuristic. The model is built upon a new neural network architecture, called graph convolutional network, which is particularly suited for deep learning tasks. Furthermore, a new formulation for the CVRPTW in form of a quadratic unconstrained binary optimization (QUBO) problem is presented and solved via quantum-inspired computing in cooperation with Fujitsu, where a learned problem reduction based upon the proposed neural network is applied to circumvent limitations concerning the usage of quantum computing for large problem instances. Computational results show that the proposed models perform very well on small and medium sized instances compared to state-of-the-art solution methods in terms of computational costs and solution quality, and outperform commercial solvers for large instances.