The Crow Search Algorithm, or CSA, belongs to a broad family of swarm-based metaheuristics that translate animal behavior into mathematical search procedures. The original inspiration is the habit of crows to follow one another to find hidden food caches. In the computational version, each candidate solution is treated as a crow moving through a multidimensional search space, and the algorithm alternates between two complementary modes. Exploration spreads the crows widely across the space to discover promising regions, while exploitation concentrates the search around the best positions found so far to refine them. The balance between these two phases largely determines whether an optimizer succeeds on a given problem.

Despite its intuitive appeal and strong space-search capabilities, the standard CSA has a well-documented structural flaw. During exploration it relies on randomly selected individuals and random probabilities to decide where crows move next, and its search mode remains fundamentally simple. On rugged, high-dimensional landscapes studded with local optima, this randomness can cause the swarm to wander without direction, missing the global best solution entirely. The authors of the new study set out to correct precisely this deficiency by replacing the algorithm’s weakest components with more disciplined, strategy-driven mechanisms borrowed and adapted from other successful optimizers.

The resulting MSD-CSA introduces a hybrid updating strategy for the exploration phase that combines the guiding strategy of the Jellyfish Search Optimizer with a technique known as refraction-based learning. The jellyfish-inspired component steers crows toward high-quality regions of the search space rather than letting them drift at random, while refraction-based learning acts as a corrective lens, repositioning solutions so that promising areas are examined from new angles. Together, these mechanisms give the exploration phase a sense of purpose: instead of scattering blindly, the swarm is systematically directed toward regions likely to contain the global optimum.

Refinement of the exploitation phase comes from a spiral-based motion strategy. Spiral trajectories, popularized by the Whale Optimization Algorithm, allow candidate solutions to circle inward around the best-known position, tightening the search progressively rather than jumping chaotically around a promising basin. In MSD-CSA this spiral mechanism enhances the efficacy of the exploitation phase, ensuring that once the swarm identifies a fertile region, it extracts the best possible solution from it. The interplay between directed exploration and spiral-guided exploitation is what the authors identify as the key to the algorithm’s improved balance between global and local search.

Validating a new metaheuristic requires exhaustive comparison, and the researchers staged an unusually thorough evaluation. MSD-CSA was tested against the original CSA, six established algorithms — Particle Swarm Optimization (PSO), Grey Wolf Optimizer (GWO), Moth-Flame Optimization (MFO), Whale Optimization Algorithm (WOA), Multi-Verse Optimizer (MVO), and Teaching-Learning-Based Optimization (TLBO) — and three improved competitors, eKGSA, EJAYA, and CCSA. The battleground consisted of eleven well-known unimodal benchmark functions, which have a single optimum and test convergence speed, and nine multimodal functions, which contain many local optima and test the ability to escape premature convergence. Across this suite, MSD-CSA achieved the best results on 63 percent of the unimodal functions and 89 percent of the multimodal functions, a margin the authors interpret as evidence that their multi-strategy design pays off most where classical algorithms struggle most.

Statistical rigor underpinned these comparisons. The team performed a series of statistical tests on the benchmark results and analyzed convergence curves to characterize how the algorithm behaves on problems with different features. They also probed robustness by running the tests at various problem dimensions, checking whether performance degrades as the search space grows. This dimension-scaling analysis matters for practical applications, where the number of variables in an engineering model can range from a handful to hundreds, and an optimizer that collapses at high dimension is of limited use. The reported results indicate that MSD-CSA maintains its advantage across these dimensional variations.

Benchmarks alone rarely convince engineers, so the authors turned to four real-world design problems: gear train design, the multi-disk clutch brake design problem, gas transmission system design, and reactor network design. Each of these problems involves nonlinear constraints and discrete or continuous variables, and each has served for years as a proving ground for optimization algorithms. MSD-CSA was pitted against other optimization methods on all four, and the experimental results showed its superiority, delivering the best designs among the compared methods. For engineers, the message is that the algorithm’s benchmark dominance translates into tangible improvements on problems with direct industrial relevance, from mechanical drivetrains to chemical process networks.

Perhaps the most striking demonstration came from control engineering. The team designed a robust control model for quadcopter altitude control based on MSD-CSA, using the optimizer to tune the controller that governs a drone’s vertical motion. In the analyses, the MSD-CSA-based controller reached the reference altitude in a short time, achieved an overshoot of just 0.0489, and recorded an error rate of 6.05e-04. For a flying vehicle, low overshoot means the drone does not lurch past its target height before settling, and a small steady-state error means it holds that height accurately. These figures suggest that metaheuristic-tuned controllers can meet the demanding stability requirements of aerial robotics, where every millisecond of response and every centimeter of altitude deviation counts.

The study, supported by the Scientific Research Projects unit of Fırat University under grant TEKF.21.12, arrives amid a wave of multi-strategy enhancements to nature-inspired optimizers, including boosted variants of whale, sparrow, dung beetle, and marine predators algorithms. What distinguishes the MSD-CSA work is the completeness of its validation pipeline, spanning statistical testing, dimensional robustness checks, constrained engineering design, and dynamic control of a physical system. By grafting the guiding intelligence of jellyfish search and the corrective power of refraction learning onto the crow’s exploratory flight, and by adding spiral motion for precision refinement, the researchers have produced an optimizer that balances exploration and exploitation with unusual effectiveness. As optimization problems in cloud computing, robotics, and engineering design grow ever more complex, hybrid algorithms of this kind may become the default tools for finding the best possible answers in vast and treacherous search spaces.

Subject of Research: A multi-strategy enhanced Crow Search Algorithm for global optimization and engineering design applications

Article Title: Multi-strategy driven crow search algorithm for global optimization and engineering problems

Article References: Koca, G. O., Olmez, Y., & Kurnaz, M. K. (2026). Multi-strategy driven crow search algorithm for global optimization and engineering problems. Cluster Computing, 29(13), Article 751. https://doi.org/10.1007/s10586-026-06543-6

Image Credits: AI Generated

DOI: 10.1007/s10586-026-06543-6

Keywords: Crow Search Algorithm, metaheuristics, swarm intelligence, global optimization, Jellyfish Search Optimizer, refraction-based learning, spiral-based strategy, engineering design optimization, quadcopter altitude control, benchmark functions, exploration and exploitation, Cluster Computing

The problem the team set out to solve is one that anyone working with cone-beam CT (CBCT) knows intimately. CBCT, originally developed for dental diagnostics, has become a workhorse of image-guided radiation therapy, interventional radiology and surgical navigation because it delivers high-resolution 3D images directly in the treatment room at lower radiation doses and faster scan times than conventional CT. But the traditional reconstruction method, the Feldkamp-Davis-Kress (FDK) algorithm, demands a large number of X-ray projections. When clinicians cut the number of projections to reduce dose — a critical safety goal — FDK produces noisy, artifact-riddled images.

Iterative reconstruction methods offer a way out. Instead of applying a single filtering step, they repeatedly refine an image estimate: the current guess is forward-projected to simulate what the scanner would measure, the simulated projections are compared with the actual measured data, and the difference is back-projected to update the image. Regularization terms, often based on the total variation (TV) norm, stabilize the solution by encouraging smooth tissue regions while preserving sharp anatomical edges. Algorithms such as ASD-POCS and its adaptive-weighted variant AwPCCS can produce strikingly good images from sparse, low-dose data — but only if their hyperparameters are set just right.

That is the catch. ASD-POCS alone carries eight tunable parameters, including the maximum number of iterations, the number of TV minimization steps, a data inconsistency tolerance, and several step-size and reduction factors spanning value ranges from a thousand candidate settings down to just ten. Even tiny deviations from the optimal combination can visibly degrade image quality. Manual tuning is tedious, time-consuming, and prone to observer variability, and any change in machine, organ, or radiation protocol typically forces clinicians to start over. Prior automated approaches have mostly optimized a single parameter, most often the regularization weight, and nearly all have relied on reference-based objective functions that assume a ground-truth reconstruction exists — an assumption that collapses in real clinical scenarios.

The new framework, called Search Space Aware Crow Search Algorithm (SSA-CSA), attacks both gaps at once. It is built on the crow search algorithm (CSA), a bio-inspired metaheuristic that models how crows hide food and follow flockmates to steal their caches. In the original CSA, each crow’s position encodes a candidate solution; here, each crow carries a vector of hyperparameter values, one per tunable parameter, allowing the entire parameter set of a reconstruction algorithm to be optimized simultaneously. The researchers reformulated all five core components of a metaheuristic — population initialization, exploitation, exploration, the balance between local and global search, and the fitness function — into a unified, reference-free pipeline.

Several technical innovations make the enhanced algorithm work. For initialization, the team developed a Chaotic Diagonal Linear Uniform (CDLU) scheme that combines diagonal stratified sampling with a deterministic sine chaos map, ensuring the initial flock of crows covers the enormous search space evenly without the ordering problems of standard diagonal sampling. For local search, crows now follow members of a dynamically shrinking ‘superior set’ of top performers identified via Pareto dominance, and random step factors are replaced with chaotic values. For global search, the crows gain ‘search space awareness’: a weight map is progressively built up around the best-performing regions of each parameter dimension, and exploration is steered by weighted random sampling rather than blind uniform randomness. The balance between exploitation and exploration is likewise made fitness-aware, so high-quality crows exploit while weaker ones explore, with the threshold tightening as the run progresses.

Equally important is the fitness function that guides the whole search. Because no reference image exists, the team designed a multi-objective, no-reference score combining the Signal-to-Noise Ratio (SNR), which captures noise reduction, with the high-frequency energy ratio (HFER), a Fourier-domain measure of image sharpness. The two metrics inherently conflict — smoother images are less noisy but blurrier — so the framework seeks the best trade-off point via a weighted sum. Ablation experiments on the publicly available SophiaBeads microCT dataset showed that this SNR-plus-HFER fitness outperformed alternatives based on SNR alone, Laplacian variance, or HFER alone when judged by two state-of-the-art learning-based image quality models, CHILL@UK and RPI_AXIS, and correlated strongly with those models’ scores.

The evaluation was unusually thorough. The framework was tested on six datasets from four different imaging systems, including a Nikon Custom Bay CT scanner, a medPhoton ImagingRing m device, and Philips Allura and Azurion C-arms, spanning glass-bead phantoms, line-pair CatPhan tests, a 3D-printed anthropomorphic thorax, a brain phantom with an inserted metal screw, a reconfigurable ChaosCube phantom, and simulated projections from five real patient CT volumes in the LIDC-IDRI lung database. Across ASD-POCS, AwPCSD and the prior-image-based PICCS algorithm, SSA-CSA consistently beat both manual parameter setting and the original CSA, with average improvements of roughly 3.9 percent in fitness, 4.3 percent on CHILL@UK and 3.9 percent on RPI_AXIS. A blind reader study by an expert radiologist with twenty years of CT experience ranked the SSA-CSA reconstructions first and awarded them the highest quality scores, including a perfect 5 out of 5 for the PICCS brain reconstruction from only 20 percent of the full projection set.

Perhaps the most clinically significant finding concerns generalizability. When the optimal parameter set found for one lung CT volume was applied to other patients and to different dose levels — from 100 percent of projections down to a severely undersampled 25 percent — image quality remained consistently good, indicating that a single optimization run can serve an entire class of similar imaging tasks. The same held for six different configurations of the ChaosCube phantom. In benchmark tests against eleven other optimization algorithms across nine standard functions, SSA-CSA showed fast convergence, low run-to-run variability attributable to its deterministic initialization, and statistically significant superiority in most pairwise Wilcoxon comparisons, even under the deliberately constrained budget of 25 individuals and 30 iterations chosen to reflect real clinical hardware limits.

The authors are candid about limitations: like all metaheuristics, SSA-CSA cannot guarantee a global optimum, its fitness weights require some experimental tuning, and its search-space awareness adds computational overhead — though this is negligible next to the cost of the reconstructions themselves and is incurred only once, offline. Future work may replace the hand-crafted fitness with a learned model or swap the metaheuristic for deep reinforcement learning. For now, the framework offers something clinics have lacked: a practical, operator-independent way to squeeze the best possible image quality out of low-dose iterative reconstruction, no reference image required.

Subject of Research: Automatic hyperparameter optimization for iterative cone-beam CT image reconstruction using an enhanced crow search metaheuristic algorithm

Article Title: Reference-free framework for automatic parameter optimization in iterative reconstruction using a novel search-space-aware crow search algorithm

Article References: MohammadiNasab, P., Biguri, A., Steininger, P., Keuschnigg, P., Lamminger, L., Lach, A., Islam, S. M. R. S., Breger, A., Karner, C., Schönlieb, C.-B., Birkfellner, W., & Hatamikia, S. (2026). Reference-free framework for automatic parameter optimization in iterative reconstruction using a novel search-space-aware crow search algorithm. Results in Engineering, 32, Article 113147. https://doi.org/10.1016/j.rineng.2026.113147

Image Credits: AI Generated

DOI: 10.1016/j.rineng.2026.113147

Keywords: cone-beam CT, iterative reconstruction, crow search algorithm, metaheuristics, hyperparameter optimization, low-dose imaging, image quality assessment, total variation regularization, ASD-POCS, PICCS, medical imaging, radiation dose reduction