Search Results (2,986)

Background/Objectives: In the modern healthcare landscape, breast cancer remains one of the most prevalent malignancies and a leading cause of mortality among women worldwide. Early and accurate prediction of breast cancer plays a pivotal role in effective diagnosis, treatment planning, and improving survival outcomes. However, due to the complexity and heterogeneity of medical data, achieving high predictive accuracy remains a significant challenge. This study proposes an intelligent hybrid system that integrates traditional machine learning (ML), deep learning (DL), and ensemble learning approaches for enhanced breast cancer prediction using the Wisconsin Breast Cancer Dataset. Methods: The proposed system employs a multistage framework comprising three main phases: (1) data preprocessing and balancing, which involves normalization using the min–max technique and application of the Synthetic Minority Over-sampling Technique (SMOTE) to mitigate class imbalance; (2) model development, where multiple ML algorithms, DL architectures, and a novel ensemble model are applied to the preprocessed data; and (3) model evaluation and validation, performed under three distinct training–testing scenarios to ensure robustness and generalizability. Model performance was assessed using six statistical evaluation metrics—accuracy, precision, recall, F1-score, specificity, and AUC—alongside graphical analyses and rigorous statistical tests to evaluate predictive consistency. Results: The findings demonstrate that the proposed ensemble model significantly outperforms individual machine learning and deep learning models in terms of predictive accuracy, stability, and reliability. A comparative analysis also reveals that the ensemble system surpasses several state-of-the-art methods reported in the literature. Conclusions: The proposed intelligent hybrid system offers a promising, multidisciplinary approach for improving diagnostic decision support in breast cancer prediction. By integrating advanced data preprocessing, machine learning, and deep learning paradigms within a unified ensemble framework, this study contributes to the broader goals of precision oncology and AI-driven healthcare, aligning with global efforts to enhance early cancer detection and personalized medical care. Full article

Background: Iron ore tailings (IOTs) are a mine waste product used as road materials and suffer from a lack of sufficient strength, which should be improved through stabilization. Unconfined compressive strength (UCS) is a crucial parameter for determining the quality and mix design of stabilized soils, which is time-consuming, requires specialized equipment and professional operators, and is not affordable. Methods: In this study, six ensemble learning techniques, five-fold cross-validation, and the Fennec Fox Optimization metaheuristic algorithm were utilized to predict UCS. For this purpose, cement content, curing time, compaction energy, and moisture content were selected as independent variables. Results: The results suggested that XGBoost-FFO was the most accurate model, R² = 0.9505, MAE = 0.257, MSE = 0.118, and RMSE = 338. Two interpretation methods were employed to evaluate the model’s performance, and the results indicated that the most significant parameter was compaction energy. Conclusions: Moreover, to facilitate practical engineering applications, a graphical user interface (GUI) was also designed to predict the UCS of cement-stabilized IOTs. Full article

Conventional sensing expends energy at three stages: powering dedicated sensors, transmitting measurements, and executing computationally intensive inference. Wireless sensing re-purposes WiFi channel state information (CSI) inherent in every packet, eliminating extra sensors and uplink traffic, though reliance on deep neural networks (DNNs) often trained and run on graphics processing units (GPUs) can negate these gains. This review highlights two core energy efficiency levers in CSI-based wireless sensing. First ambient CSI harvesting cuts power use by an order of magnitude compared to radar and active Internet of Things (IoT) sensors. Second, integrated sensing and communication (ISAC) embeds sensing functionality into existing WiFi links, thereby reducing device count, battery waste, and carbon impact. We review conventional handcrafted and accuracy-first methods to set the stage for surveying green learning strategies and lightweight learning techniques, including compact hybrid neural architectures, pruning, knowledge distillation, quantisation, and semi-supervised training that preserve accuracy while reducing model size and memory footprint. We also discuss hardware co-design from low-power microcontrollers to edge application-specific integrated circuits (ASICs) and WiFi firmware extensions that align computation with platform constraints. Finally, we identify open challenges in domain-robust compression, multi-antenna calibration, energy-proportionate model scaling, and standardised joules per inference metrics. Our aim is a practical battery-friendly wireless sensing stack ready for smart home and 6G era deployments. Full article

Hwang developed inventory models with amelioration items and applied the graphical method to locate the optimal solution. In this study, we derive an analytical method to find two local maximum points and one local minimum point. Our maximum profit is greatly superior to that of Hwang, because his maximum profit is about 0.246% of ours. The local maximum point near the starting point (denoted as $3\times {10}^{-7}$) is almost impossible to discoverby the numerical method, illustrating the effectiveness of our analytical method. Full article

In Building Information Modeling (BIM) of bridge piers, persistent limitations have been observed in the modeling of spiral hoop rebar with variable pitch and diameter. Taking Revit as an example, its built-in family files can only generate spirals with constant geometry. When dealing with non-uniform rebar, designers often have to rely on segmented modeling or manual operations, which is not only time-consuming but also prone to deviations. To solve this problem, this paper proposes a parameterized modeling method based on the secondary development of Revit. By combining the Revit API with the C# programming language, the spiral equation is embedded into the Non-Uniform Rational B-Spline (NURBS) curve reconstruction framework, realizing the continuous modeling of spiral hoop rebar in a unified model. This method also allows users to flexibly input parameters such as cover thickness, rebar diameter, and segment length through a graphical user interface. Through comparative experiments, the proposed method and the traditional family file modeling method were verified respectively in the modeling of a single column and an entire bridge pier. The results indicate that the proposed method reduces the average modeling time of a single bridge pier by 66.5% and that of the entire project by 48.7%. While maintaining high geometric accuracy, this method significantly shortens modeling time and reduces workload, especially demonstrating higher consistency in pitch transition sections and conical sections. Beyond technical performance, this study also demonstrates that the secondary development of Revit provides a practical and feasible solution for the efficient, precise, and generalizable modeling of complex reinforcing bar components in terms of expanding BIM functions, which holds significant practical implications. Full article

This study aims to enhance the security of unmanned aerial vehicles (UAVs) within the Internet of Drones (IoD) ecosystem by detecting and preventing Denial-of-Service (DoS) attacks. We introduce DroneDefender, a web-based intrusion detection system (IDS) that employs machine learning (ML) techniques to identify anomalous network traffic patterns associated with DoS attacks. The system is evaluated using the CIC-IDS 2018 dataset and utilizes the Random Forest algorithm, optimized with the SMOTEENN technique to tackle dataset imbalance. Our results demonstrate that DroneDefender significantly outperforms traditional IDS solutions, achieving an impressive detection accuracy of 99.93%. Key improvements include reduced latency, enhanced scalability, and a user-friendly graphical interface for network administrators. The innovative aspect of this research lies in the development of an ML-driven, web-based IDS specifically designed for IoD environments. This system provides a reliable, adaptable, and highly accurate method for safeguarding drone operations against evolving cyber threats, thereby bolstering the security and resilience of UAV applications in critical sectors such as emergency services, delivery, and surveillance. Full article

The digital and ecological transition of the industrial sector requires methodological tools that integrate information modelling, performance simulation, and operational decision support. In this context, the present study introduces and tests a semi-automatic BIM-to-BEM framework to optimise human–machine interaction and support critical data interpretation through Graphical User Interfaces. The objective is to propose and validate a BIM-to-BEM workflow for an existing industrial facility to enable comparative evaluation of energy retrofit scenarios. The information model, developed through an interdisciplinary federated approach and calibrated using parametric procedures, was exported in the gbXML format to generate a dynamic, interoperable energy model. Six simulation scenarios were defined incrementally, including interventions on the building envelope, Heating, Ventilation and Air Conditioning (HVAC) systems, photovoltaic production, and relamping. Results are made accessible through dashboards developed with Business Intelligence tools, allowing direct comparison of different design configurations in terms of thermal loads and indoor environmental stability, highlighting the effectiveness of integrated solutions. For example, the combined interventions reduced heating demand by up to 32% without compromising thermal comfort, while in the relamping scenario alone, the building could achieve an estimated 300 MWh reduction in annual electricity consumption. The proposed workflow serves as a technical foundation for developing an operational and evolving Digital Twin, oriented toward the sustainable governance of building–system interactions. The method proves to be replicable and scalable, offering a practical reference model to support the energy transition of existing industrial environments. Full article

Hybridization of existing fractal aggregate construction methods has been used to obtain new fractal-like structures, with different properties and fractal dimensions to aggregates obtained using the hybridized methods alone. In this paper we propose the hybridization of the Diffusion-Limited Aggregation (DLA) approach with other methods for constructing fractal-like aggregates, such as Iterated Function Systems (IFSs), Lindenmayer systems (L-Systems), Strange Attractors (SAs) or Percolation-based fractal construction approaches. The proposed approach is a variation of the seeded DLA algorithm used previously in the literature, which consists of considering existing fractal aggregates as condensation nuclei before the DLA simulation. In this case, we revisit the seeded DLA scheme and test different existing fractals as nuclei, such as Strange Attractors or different IFS fractals. We also introduce a simple algorithm for simulating the diffusion of particle aggregate structures, based on concentration gradient diffusion. We show how different fractal aggregates diffuse using this model, and how the diffused versions of the fractal aggregates can then be used themselves as condensation nuclei for the seeded DLA algorithm, obtaining new fractal aggregates. We characterize the new fractal-like aggregates constructed by means of their fractal dimensions, calculated by using the box-counting approach. The obtained fractal-like aggregates have potential applications in computer graphics and multi-media art, due to their esthetic and visually attractive structures based on particles. Applications of the aggregates in statistical and material physics, as well as the modeling of new aggregate types using condensation nuclei and their applications in the development of algorithms, mathematical operators or antenna design, are also reported. Full article

Background: Short tandem repeats (STRs) are highly variable sequences present along the human genome, including the Y-chromosome. Y-STRs are exclusive to males, and the haplotypes they define are informative. Objectives: Twenty-six Y-STR loci were genotyped in 252 males from Northern Portugal to characterise Y-chromosome genetic variation using the Investigator Argus Y28 QS Kit. Methods: The kit mentioned was used to amplify male DNA samples, and capillary electrophoresis was used to analyze the fragments. Forensic parameters and haplotype diversity were computed, and samples’ haplogroups were predicted. A multidimensional scaling (MDS) plot was used to graphically represent the R_ST genetic distances, including reference populations. Results: A total of 250 different haplotypes were observed, including 248 unique ones, yielding a very high haplotype diversity (HD = 0.999) and discriminatory power (DP = 0.992). Haplogroup analysis indicated a predominance of R1b (58.7%), followed by E1b1b, I and J, pointing to a population history shaped by Mediterranean and North African gene flow. Comparative analysis between Portugal and 5 other populations showed greater genetic affinity with Spain and Italy, while revealing marked differentiation from Greece, Morocco, and former Portuguese colonies. Conclusions: The results confirm that the Northern Portuguese Population exhibits high Y-STR variability and robust forensic resolution. The dataset was submitted to the YHRD database, enhancing the representation of the Portuguese population and underscoring the value of the 26 locus panel for applications in forensic science, genealogy, and population genetics. Full article

Geophysical forward modeling serves as a fundamental theoretical approach for characterizing subsurface structures and material properties, essentially involving the computation of gravity responses at surface or spatial observation points based on a predefined density distribution. With the rapid development of data-driven techniques such as deep learning in geophysical inversion, forward algorithms are facing increasing demands in terms of computational scale, observable types, and efficiency. To address these challenges, this study develops an efficient forward modeling method based on voxel discretization, the enabling rapid calculation of gravity anomalies and radial gravity gradients on multiple observational surfaces. Leveraging the parallel computing capabilities of graphics processing units (GPU), together with tensor acceleration, Compute Unified Device Architecture (CUDA) execution, and Just-in-time (JIT) compilation strategies, the method achieves high efficiency and automation in the forward computation process. Numerical experiments conducted on several typical theoretical models demonstrate the convergence and stability of the calculated results, indicating that the proposed method significantly reduces computation time while maintaining accuracy, thus being well-suited for large-scale 3D modeling and fast batch simulation tasks. This research can efficiently generate forward datasets with multi-view and multi-metric characteristics, providing solid data support and a scalable computational platform for deep-learning-based geophysical inversion studies. Full article

Background/Objectives: The purpose of this umbrella review was to assess the risk of bias and the methodological and reporting quality of systematic reviews that evaluated the effects of thoracic spine manipulation (TSM) on individuals with mechanical neck pain. Methods: To be included, publications needed to be systematic reviews including studies with participants with neck pain >18 years old; at least two groups where the experimental intervention was TSM; assessed pain and/or function; and were published in English. Reviews limited to narrative, scoping, or retrospective studies, or those with cervical radiculopathy, were excluded. An electronic search was conducted in May 2025 using PubMed, CINAHL (EBSCO Host), and the Cochrane Library to identify relevant articles from inception to May 2025. Quality and risk of bias were assessed using A Measurement Tool to Assess Systematic Reviews 2 (AMSTAR 2), Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA 2020), and Risk of Bias in Systematic Reviews (ROBIS). Findings were summarized narratively and graphically. Results: Seven reviews (27 unique studies; 1394 participants, aged 18–62 years) met the inclusion criteria. Some evidence supported TSM for short-term improvement in neck pain, but confidence in results was low to critically low based on the AMSTAR 2 results. Four reviews had a high overall risk of bias, and three had a low risk. Reporting compliance varied widely (0–100%). Conclusions: While all the included systematic reviews suggested that TSM is a viable short-term option for individuals with neck pain, the overall confidence in these results ranged from low to critically low, making it difficult to draw firm conclusions about the true benefit of TSM in clinical practice. Registered prospectively in PROSPERO (CRD420251034330). Full article

Background/Objectives: Keratoconus, a condition in which the cornea becomes thinner and steeper, can cause visual problems, particularly when it is progressive. Early diagnosis is important for preserving visual acuity. Raw data, unlike preprocessed data, are unaffected by software modifications. They retain their native structure across versions, providing consistency for analytical purposes. The objective of this study was to design a deep learning-based graphical user interface for predicting the corneal ectasia score using raw optical coherence tomography data. Methods: The graphical user interface was developed using Tkinter, a Python library for building graphical user interfaces. The user is allowed to select raw data from the cornea/anterior segment optical coherence tomography Casia2, which is generated in the 3dv format, from the local system. To view the predicted corneal ectasia score, the user must determine whether the selected 3dv file corresponds to the left or right eye. Extracted optical coherence tomography images are cropped, resized to 224 × 224 pixels and processed by the modified EfficientNet-B0 convolutional neural network to predict the corneal ectasia score. The predicted corneal ectasia score value is displayed along with a diagnosis: ‘No detectable ectasia pattern’ or ‘Suspected ectasia’ or ‘Clinical ectasia’. Performance metric values were rounded to four decimal places, and the mean absolute error value was rounded to two decimal places. Results: The modified EfficientNet-B0 obtained a mean absolute error of 6.65 when evaluated on the test dataset. For the two-class classification, it achieved an accuracy of 87.96%, a sensitivity of 82.41%, a specificity of 96.69%, a PPV of 97.52% and an F1 score of 89.33%. For the three-class classification, it attained a weighted-average F1 score of 84.95% and an overall accuracy of 84.75%. Conclusions: The graphical user interface outputs numerical ectasia scores, which improves other categorical labels. The graphical user interface enables consistent diagnostics, regardless of software updates, by using raw data from the Casia2. The successful use of raw optical coherence tomography data indicates the potential for raw optical coherence tomography data to be used, rather than preprocessed optical coherence tomography data, for diagnosing keratoconus. Full article

Accurate determination of a vehicle’s centre of gravity (CoG) is fundamental to driving dynamics, safety, and engineering design. However, existing static CoG estimation methods often neglect tyre deflection and detailed wheel geometry, which can introduce significant errors, particularly in electric vehicles, where the low and concentrated mass of the battery pack increases the sensitivity of vertical CoG calculations. This study presents a refined static axle-load-based method for electric vehicles, in which the influence of tyre deformation and lifting height on the accuracy of the vertical centre of gravity coordinate is explicitly considered and quantitatively justified. To minimise human error and accelerate the evaluation process, a custom-developed Python (Python 3.13.2.) software tool automates all calculations, provides an intuitive graphical interface, and generates visual representations of the resulting CoG position. The methodology was validated on a Volkswagen e-Golf, demonstrating that the proposed approach provides reliable and repeatable results. Due to its accuracy, reduced measurement complexity, and minimal equipment requirements, the method is suitable for design, educational, and diagnostic applications. Moreover, it enables faster and more precise preparation of vehicle dynamics tests, such as rollover assessments, by ensuring that sensor placement does not interfere with vehicle behaviour. Full article

Fluid–structure coupling is a prominent and hot topic in computer graphics and virtual reality. The hybrid technique known as FLIP combines the benefits of grid-based and particle-based techniques. Nevertheless, a significant problem is figuring out how to accomplish fluid–structure coupling interaction based on the FLIP technique framework. We propose an immersed boundary approach to handle the problem of realistic fluid–structure coupling interaction under the FLIP framework. The benchmark test results demonstrate that, in addition to producing rich fluid–structure coupling interaction results, our novel technique also effectively reflects the effects of moving obstacle boundaries on the flow and pressure fields, thereby expanding the application area of the FLIP method. Full article