Search Results (1,248)

Background: This article provides a comprehensive overview of recent advancements in artificial intelligence (AI) and deep-learning technologies for breast cancer (BC) diagnosis across various imaging modalities. Methods: A systematic review was conducted in strict adherence to the PRISMA guidelines, incorporating a comparative analysis of 65 peer-reviewed studies published between 2018 and 2024. The evaluation focused on diagnostic performance, architectural developments, and clinical integration strategies. Results: The review synthesizes primary findings on convolutional neural networks (CNNs), emerging architectures including graph neural networks, and hybrid models, with diagnostic accuracy, risk prediction, and personalized screening strategies identified as the leading research domains. Notable achievements include CNNs attaining up to 98.5% accuracy in mammography and Vision Transformers reaching 96% in histopathological analysis. Furthermore, the implementation of explainable AI methodologies, such as SHAP, LIME, and Grad-CAM, is emphasized for maintaining transparency, trust, and accountability in clinical decision-making. Conclusions: AI constitutes a pivotal factor in facilitating early BC diagnosis and optimizing treatment outcomes. Nevertheless, significant challenges persist, including dataset heterogeneity, model generalizability, standardization of imaging protocols, computational resource limitations, and the seamless integration of these technologies into established clinical workflows. Future research must prioritize robust multi-dataset validation and standardized implementation frameworks to overcome existing limitations and advance successful BC diagnostic practices. Full article

Influence Maximization (IM) is a fundamental problem in social network analysis that aims to identify a set of k seed nodes that maximizes influence spread under a given propagation model. Despite its importance in applications such as viral marketing and epidemic control, the IM problem is NP-hard, making exact solutions computationally infeasible for large-scale networks. Existing approximation methods typically rely either on static centrality heuristics, which often ignore global network structure, or on metaheuristic algorithms, which may suffer from slow convergence due to random initialization. This paper proposes a novel approach, termed Advanced Centrality-Driven Discrete Particle Swarm Optimization (DPSO), which integrates a weighted hybrid centrality score combining Degree, PageRank, and Betweenness centrality to guide the stochastic search process. In addition, a systematic grid search methodology is employed to determine the optimal weight configuration of the hybrid score. Experiments conducted on three real-world datasets (Twitter, ego-Facebook, and ca-HepTh) demonstrate that the optimal seeding strategy is strongly dependent on network topology. The results show that dense social networks favor popularity-based metrics such as Degree and PageRank, whereas sparse collaboration networks benefit significantly from bridge-oriented metrics such as Betweenness centrality. Overall, the proposed method achieves consistent improvements in influence spread across different network types, with the largest gains (up to 70%) observed in sparse network settings. Full article

Industrial maintenance and predictive diagnostics constitute fundamental pillars of modern manufacturing that prevent equipment failures, minimize operational downtime, and optimize maintenance costs across diverse industrial environments. Vibration-based fault classification plays an important role in industrial operations, necessitating highly sophisticated diagnostic methodologies. This research addresses these industrial imperatives through a comprehensive investigation of novel hybrid deep learning architectures for vibration-based fault classification. This study introduces a strategic integration of Quadratic Neural Networks (QNNs), which demonstrate superior non-linear feature extraction capabilities on a vibration signal compared to traditional convolutional approaches. A systematic evaluation of seven sophisticated architectures establishes a clear performance hierarchy, with QuCNN-LSTM-Transformer emerging as the optimal model achieving 99.26% average accuracy. All proposed models demonstrate excellence, with test accuracies consistently surpassing 95% across all evaluated scenarios. The data analyzed is emprical utilizing sensor data collected from an experimental rig and shows exceptional performance consistency on CWRU and HUST datasets. This investigation establishes a new paradigm in intelligent diagnostics, offering functional guidance and definitive analysis of hybrid architectures that advance industrial fault classification applications. Full article

This study proposes a robust hybrid framework for iris segmentation in covert biometric systems, specifically addressing the challenge of non-ideal images featuring fully or nearly closed eyes. To overcome the limitations of traditional geometric methods, this study implements a SqueezeNet-based Deep Convolutional Neural Network (DCNN) for rapid eye-state classification. Comparative analysis with various pretrained DCNN models indicates that SqueezeNet provides an optimal balance of accuracy and efficiency, requiring only 1.24 million parameters and a minimal memory footprint of 5.2 MB. For iris contour demarcation, the proposed algorithm combines the Circular Hough Transform (CHT) with global gray-level statistics and anatomical constraints to facilitate reliable iris localization. Utilizing image decimation, percentile-based thresholding, and Canny edge detection, it systematically delineates the limbic and pupillary boundaries. This improved search methodology ensures precise contour delineation, even under sub-optimal imaging circumstances. The proposed algorithm was validated on a novel dataset encompassing challenging conditions such as specular reflections, blur, non-uniform illumination, and varying degrees of occlusion, including nearly or fully closed eyes. Experimental results demonstrate superior segmentation accuracy and significant computational efficiency, underscoring the model’s potential for real-time biometric applications in unconstrained environments. Full article

This study introduces a novel Quantum-Inspired Hybrid Bald Eagle-Ukari Algorithm with Reinforcement Learning (QI-HBEUA-RL) for comprehensive optimization of conical solar distillers equipped with sand-filled copper conical fins. The proposed algorithm synergistically combines quantum computing principles (superposition and entanglement), bio-inspired metaheuristics (Bald Eagle Search and Ukari Algorithm), and reinforcement learning mechanisms to achieve unprecedented optimization performance in complex thermal-hydraulic systems. The QI-HBEUA-RL framework employs quantum-encoded population representation, enabling simultaneous exploration of multiple solution states, while reinforcement learning dynamically adjusts algorithmic parameters based on search landscape characteristics and historical performance data. Experimental validation tested seven distiller configurations in El-Oued, Algeria, under controlled conditions (7.85 kWh/m²/day solar radiation, 42.2 °C ambient temperature). The optimal configuration of copper conical fins with 14 g sand at 0 cm spacing achieved: daily productivity of 7.75 L/m²/day (+61.46% improvement over conventional design), thermal efficiency of 61.9%, exergy efficiency of 4.02%, and economic payback period of 5.8 days. Comprehensive algorithm comparison against six state-of-the-art multi-objective optimizers (NSGA-II, MOEA/D, MOPSO, MOGWO, MOHHO) across 30 independent runs demonstrated statistically significant superiority (p < 0.001, Wilcoxon test). QI-HBEUA-RL achieved 7.42% improvement in hypervolume indicator, 29.35% reduction in inverted generational distance, and 19.49% better solution spacing. Generalization validation on seven benchmark problems (ZDT1-6, DTLZ2, DTLZ7) and three renewable energy applications confirmed algorithm robustness across diverse problem types. Three real-world case studies, remote village water supply (238:1 benefit–cost), industrial facility (100% energy reduction), and emergency relief (740× cost savings) validate practical implementation viability. This research advances solar thermal desalination technology and multi-objective optimization methodologies, providing validated solutions for sustainable freshwater production in water-scarce regions. Full article

Efficient design of desalination and brine management systems, which are central to a water circular economy, requires accurate thermodynamic data such as the osmotic coefficient. This property is key to understanding salt behavior in aqueous solutions, directly impacting the energy efficiency and sustainability of treatment processes. This study presents a predictive framework that combines machine learning with the Gazelle Optimization Algorithm (GOA) to accurately estimate osmotic coefficients for various inorganic salt solutions. The GOA was employed to automatically tune the hyperparameters of two models: Decision Tree (DT) and Gradient Boosting Machine (GBM). Using a comprehensive dataset of 893 samples with 27 salt-specific parameters, the GOA-GBM hybrid model delivered the highest predictive accuracy, achieving an R² of 0.9734 on test data. The GOA-DT model also performed robustly (R² = 0.9260), providing a more interpretable alternative. By creating a reliable tool for predicting osmotic coefficients, this methodology enables more precise process simulation and optimization. This directly supports the development of energy-efficient desalination technologies and informed decision-making for water reuse and resource recovery. The integration of advanced digital tools like GOA with machine learning offers a powerful approach to enhancing process efficiency and environmental safety, contributing directly to the design of sustainable, circular economy-based water treatment solutions for industrial and municipal applications. Full article

Traffic flow prediction is a key component of Intelligent Transportation Systems (ITS), crucial for alleviating urban congestion, optimizing traffic management, and improving the overall efficiency of road networks. With the rapid growth in vehicle numbers and the increasing complexity of urban traffic patterns, accurate short-term traffic flow prediction has become increasingly important. This paper comprehensively reviews the latest advancements in traffic flow prediction methods, focusing on graph neural network (GNN)-based approaches and hybrid deep learning frameworks. First, we introduce the fundamental theoretical foundations, including graph neural networks, deep learning algorithms, heuristic optimization methods, and attention mechanisms. Subsequently, we summarize GNN-based prediction methods into four paradigms: (1) federated learning and privacy-preserving methods, enabling cross-regional collaboration while protecting sensitive data; (2) dynamically adaptive graph structure methods, capturing time-varying spatial dependencies; (3) multi-graph fusion and attention mechanism methods, enhancing feature representations from multiple perspectives; and (4) cross-domain technology integration methods, fusing novel architectures and interdisciplinary technologies. Furthermore, we investigate hybrid methods combining signal decomposition, heuristic optimization, and attention mechanisms with LSTM networks to address challenges related to non-stationarity and model optimization. For each category, we analyzed representative works and summarized their core innovations, strengths, and limitations using a systematic comparative table. Finally, we discussed current challenges, including computational complexity, model interpretability, and generalization ability, and outlined future research directions such as lightweight model design, uncertainty quantification, multimodal data fusion, and integration with traffic control systems. This review provides researchers and practitioners with a systematic understanding of the latest advances in traffic flow prediction and offers guidance for methodological selection and future research. Full article

Urban micro-tidal canals frequently suffer from severe hypoxia due to restricted hydrodynamic exchange and untreated discharges. Field monitoring during a 2022 mass fish mortality event at the Dongsam tidal canal revealed that during the ‘tidal window gap’—a hydraulic stagnation period required for passive tidal flushing—bottom-layer dissolved oxygen (DO) plummeted to a lethal 0.44 mg/L. To address the limitations of passive tidal exchange, this study proposes a conceptual hybrid water purification framework integrating active ecological interventions: wall-mounted spiral flow aeration for continuous oxygenation and vertical bio-curtains for pollutant interception. By synergizing fluid mechanics with ecological engineering, core design parameters were systematically derived: an effective mixing width (W_eff = 2.2 h), longitudinal spacing (L_s = 13.6 × W_eff ), an optimal root immersion ratio (D_r/h = 0.6), and climate-adaptive planting densities (ρ_p ≈ 2–32 plants/m²). Additionally, a corrosion-resistant FRP guide rail system was incorporated to facilitate autonomous adaptation to tidal fluctuations. The framework was conceptualized through a prototype design for the Dongsam canal and subsequently scaled to 15 international micro-tidal canals across diverse climatic zones. The optimized bilateral staggered configuration established a continuous 528 m² ecological refuge, ensuring DO levels recover above the critical 3 mg/L threshold. Ultimately, this research presents a comprehensive methodological framework and a flexible engineering toolkit to guide water quality and ecological resilience enhancements in shallow urban waterways worldwide. Full article

Aerospace vehicles operate across a wide flight envelope, traversing dense atmospheric layers from near-space to low Earth orbit. Trajectory planning and optimization in a large spatial domain and wide speed range present severe challenges to traditional methods, including computational efficiency, model accuracy, and constraint adaptability. Artificial intelligence provides an effective pathway to overcome these limitations and has become a key driver for advancing trajectory planning and optimization of aerospace vehicles. This paper presents a systematic review of the core characteristics of aerospace trajectory planning, including environment coupling, multi-constraint compliance, propulsion integration, and aerodynamic nonlinearity, as well as the limitations of traditional methods. The study focuses on the application of intelligent algorithms in both the ascent and reentry phases. For the ascent phase, three key issues are addressed: multistage hybrid optimization with continuous and discrete variables, propulsion multimodal–trajectory coupling, and trajectory reconfiguration under engine failure. For the reentry phase, discussions are focused on such technical difficulties as multi-constraint trajectory generation, no-fly zone avoidance, and multi-mission requirement optimization. Finally, future research directions in intelligent trajectory planning and optimization are discussed, providing theoretical support and methodological guidance for the autonomous and intelligent development of aerospace vehicle trajectory planning. Full article

Context: In numerous low- and middle-income nations, malaria remains a significant issue due to the challenges associated with diagnosing it through thin blood smears. The appearance of images can vary significantly depending on the microscope type, magnification, lighting conditions, slide preparation methods, and staining techniques. Due to the delicate morphology of parasites, false negatives might adversely affect patient care. Objective: To achieve optimal outcomes from validation, it is essential to construct a robust and easily replicable process. This pipeline should integrate the optimal elements of classical machine learning and end-to-end deep learning, enhance reliability by pairwise ensembling, and select ensemble weights in a logical, data-driven manner. Method: To achieve our objective, we propose two tracks. The initial track encompasses real-time augmentation, convolution-based feature extraction, and the training of calibrated classical classifiers. The second module focuses on training many convolutional networks from inception to completion. Subsequently, we construct paired ensembles and employ a hybrid methodology to select convex weights for combining the findings. This method initially evaluates a set of candidate weights and then refines them to maximise validation accuracy. Results: The precision of the two-track architecture consistently improves, transitioning from conventional baselines to end-to-end models. Optimal and consistent enhancements are achieved through weighted ensembling. Utilising optimised fusion reduces the incidence of false negatives for subtle parasites and false positives caused by staining artefacts. This yields an accuracy of 96.35% on the reserved data and reduced variance across folds. Conclusions: The integration of augmentation, multiple modelling tracks, and optimal pairwise ensembling yields the highest accuracy in categorising malaria smears. It facilitates further enhancements by incorporating supplementary models, multi-class extensions, and operating-point calibration. Full article

The adoption of disruptive technologies has become increasingly critical for organizations, particularly following the global shifts prompted by the COVID-19 pandemic. Despite the potential benefits, many organizations, including those in the Fast-Moving Consumer Goods (FMCG) industry, face significant hurdles in this transition. Consequently, this study aims to understand the primary challenges and enabling factors influencing the adoption of disruptive technologies for sustainable digital transformation within the South African FMCG sector. A quantitative methodology was employed, utilizing a questionnaire for data collection. Data from 102 respondents were analyzed using SPSS version 28, involving descriptive statistics (mean item score) to rank factors and exploratory factor analysis (EFA) to identify underlying constructs, and a reliability test was carried out with a score of 0.7. Key challenges identified include high initial costs and poor collaboration. Prominent enabling factors include top management commitment and operational cost reduction. The EFA revealed significant underlying challenge dimensions such as “Infrastructural and Resources Constraints” and “Human Factors Constraints,” and enabling dimensions including “Organizational Commitment and Strategy” and “Leadership.” The study concludes with key implications for promoting successful adoption. The adoption of disruptive technologies has become a strategic imperative for sustainable digital transformation (SDT), particularly in emerging markets such as South Africa’s FMCG sector. This study investigates the key challenges and enabling factors shaping technology adoption within this context. A quantitative methodology was employed, using a structured questionnaire distributed to 102 professionals across FMCG organizations in Gauteng. Exploratory factor analysis (EFA) revealed latent dimensions within both challenges and enablers, which were then interpreted through the lens of Rogers’ Diffusion of Innovation (DOI) theory. To enhance analytical clarity, a matrix model was developed linking factor dimensions to DOI attributes such as relative advantage, complexity, compatibility, trialability, and observability. The study found that high initial costs, poor collaboration, and human capability gaps significantly impede adoption, while strong leadership, strategic alignment, and operational cost savings facilitate it. The findings underscore the need for systemic interventions that address not only technical readiness but also leadership, organizational culture, and structural alignment. Practical implications are outlined for both policy and management, particularly in leveraging DOI attributes to accelerate digital transformation, as well optimize innovation diffusion within resource-constrained environments. For the future, the study proposed a hybrid methodology incorporating qualitative interviews to enhance depth and suggests longitudinal tracking to capture temporal shifts in transformation maturity. Full article

Red mud-based composites show great potential in industrial solid waste utilization in response to the growing demand for low-carbon building materials. However, red mud–coal metakaolin geopolymers (RCGs) exhibit high brittleness and poor crack resistance, which limit their application in practical engineering. In order to improve the strength and toughness of RCGs, this study proposes a hybrid reinforcement strategy combining basalt fiber (BF) and polypropylene fiber (PPF). Effects of fiber length and fiber content on the mechanical properties of RCG were systematically investigated by orthogonal experimental design and response surface methodology (RSM). The microstructural characteristics were also analyzed using SEM, EDS, and XRD. Results show that fiber incorporation effectively enhances the mechanical properties and toughness of RCG, and BF length is the key factor influencing the strength of RCG. The optimal fiber ratio (BF: 11 mm, 0.23%; PPF: 6 mm, 0.20%) increases 9.52% of 28-day compressive strengths and 18.93% of 28-day flexural strengths. Microstructural analysis shows fibers bridging, interfacial stress transfer, and pull-out, which inhibit crack propagation. However, excessive fiber content may reduce matrix continuity. This manuscript provides a theoretical basis for optimizing red mud-based geopolymer composites and promotes the resource utilization of industrial solid waste. Full article

Optimization has played a fundamental role in the evolution of chemical engineering, enabling systematic decision-making under technical, economic, and environmental constraints. This review presents a structured and comparative analysis of the historical development and current state of optimization methodologies applied to chemical engineering, covering the transition from early linear and nonlinear programming approaches to advanced data-driven and artificial intelligence-based frameworks. A systematic literature review was conducted following the PRISMA guidelines, through which a total of 101 articles were retained for analysis. The results indicate that mixed-integer programming and decomposition-based methods remain widely adopted for structured industrial problems, while metaheuristic and hybrid data-driven approaches have experienced significant growth in recent years. In particular, a clear trend toward the integration of machine learning and surrogate modeling techniques is observed, driven by the need to address large-scale, non-convex, and highly nonlinear systems. The analysis reveals a clear methodological shift from classical linear optimization frameworks toward hybrid optimization strategies capable of addressing large-scale, non-convex, and highly nonlinear problems. Finally, current challenges and future research directions are identified, emphasizing the need for robust hybrid approaches that combine mathematical programming and intelligent algorithms to effectively manage complexity in next-generation chemical systems. Full article

This study presents an integrated technological approach for improving the service life and operational stability of a P6 die used in the cold-forging production of automotive brake connectors. The work was conducted in an industrial environment characterized by high production volumes and recurrent premature die failure. A hybrid methodology combining Shainin’s dominant-variable methodology with controlled experimentation and finite element analysis (FEA) was implemented to identify and optimize the dominant process variables affecting die durability. The attack angle, chamfer length, and machine rotational speed were determined to be the primary factors influencing stress distribution and fatigue behavior. The optimized configuration (16° attack angle, 1.4 mm chamfer length, and 88 RPM) increased die service life by 416%, improving production throughput from approximately 60,000 to over 250,000 parts per cycle. Numerical simulations confirmed that the geometric redesign effectively reduced localized Von Mises stress concentrations, contributing to enhanced structural reliability. The results demonstrate that integrating empirical industrial methodologies with numerical modeling provides a practical and replicable framework for technological improvement in high-volume cold-forging operations. The proposed approach is transferable to similar tooling optimization challenges in the automotive manufacturing sector. Full article

This study presents a methodology for determining the optimal placement of seismic sensors along the height of buildings to minimize the uncertainty in reconstructing structural responses at non-instrumented floors. Due to the extensive benefits of instrumentation—from model validation to damage detection and structural health monitoring—the number of instrumented structures is steadily increasing. However, to keep installation and maintenance costs within a reasonable range, structures are often instrumented sparsely. The response at non-instrumented locations is typically estimated using deterministic or probabilistic model-based, data-driven, or hybrid methods. Specifically, the authors recently proposed a method that combines a deterministic beam model with Gaussian Process Regression (GPR) to estimate responses at non-instrumented floors of an instrumented building. The present paper proposes a methodology to determine optimal sensor locations that minimize the uncertainty associated with this response estimation. This work is a sequel to a previous study that was limited to stationary excitation and extends the method to seismic excitations. The methodology is first verified through a numerical example and then applied to two real instrumented buildings. The results demonstrate that an average 40% reduction in uncertainty is achievable when sensors are positioned according to the proposed optimization approach, in comparison with a random distribution of sensors. Between the two real-life cases studied in this paper, the level of reduction in the response uncertainty is around 10% for the 52-story building because the existing sensors are almost uniformly distributed, while it is around 80% for the 73-story building because the existing sensors are distributed to measure the localized behavior of the building. Full article