Search Results (61)

Background: Three-dimensional cephalometric landmarking provides the spatial reference framework for computer-aided surgical simulation in craniomaxillofacial (CMF) surgery. Conventional workflows rely on two-dimensional computer interfaces (CIs), yet imaging data are inherently volumetric, and repeated CBCT imaging creates pressure to minimise patient radiation exposure. Immersive virtual reality (VR) offers a more intuitive environment for spatial tasks, yet the feasibility of ultra-low-dose (uLD) protocols for cephalometric landmarking in CI and VR remains unevaluated. This pilot study evaluated accuracy, reproducibility and workload across low-dose (LD) and uLD CBCT protocols in both environments. Methods: Four CMF radiologists placed ten 3D cephalometric landmarks on 20 CBCT datasets across three rounds. Round 1 used deep learning-predicted coordinates as ground truth. Rounds 2–3 assessed blind reproducibility. Workload was evaluated using the NASA Task Load Index. Results: Median Round 1 accuracy was 1.00 mm in both environments; mean CI accuracy was 1.05 mm and mean VR accuracy was 2.03 mm after outlier exclusion. Log analysis identified controller slips and software logging errors as a primary VR outlier source (22/793, 2.77%). Reproducibility was higher in CIs; VR medians remained clinically relevant. Dose level had no meaningful effect. The NASA-TLX showed decreasing VR workload across sessions, with AI-guided landmarking associated with the lowest mental demand. Conclusions: VR-based landmarking is feasible: its median accuracy was comparable to that of CIs and radiologists responded positively. Reproducibility was lower in VR, attributable to software constraints rather than the visualisation modality. The uLD protocol performed comparably to LD, supporting dose optimisation. Integration of AI assistance within VR represents the most promising direction for further development. Full article

In recent years, Additive Manufacturing (AM) has transformed the development of new products, enabling more efficient, sustainable, and creative solutions across multiple sectors. Accordingly, this research explores the integration of Selective Laser Melting (SLM) with advanced Computer-Aided (CAx) tools, specifically Generative Design (GD) and Topology Optimisation (TO), to rethink an everyday product. The developed concept, an SLM water tap, highlights the seamless synergy between design and product engineering. Reverse Engineering (RE) was applied to analyse the conventional internal mechanism, which was redesigned in accordance with Design for Additive Manufacturing (DfAM) principles. This approach enabled the integration of the internal cartridge architecture into the tap body as a single metal component, reducing system complexity and part count. TO was applied to key components, achieving a 35% mass reduction without compromising the simulated structural performance of the system. GD was employed to generate optimised internal flow channels, resulting in a numerically simulated flow rate of 4.69 L/min. Integrating CAx tools enabled a customisable product with varied surface textures. This work contributes to the deconstruction of traditional manufacturing paradigms and advances the understanding of AM for functionally relevant product design. Full article

The rapid advancement of machine learning and artificial intelligence (AI) has created new opportunities to enhance diagnostic accuracy in dermatology, particularly within primary care settings. Computer-aided diagnosis (CAD) systems have demonstrated potential to support General Practitioners (GPs) by enabling earlier and more consistent identification of skin diseases. This review critically examines the literature on explainable artificial intelligence (XAI) for skin disease classification, with a specific focus on the evolution of explainability frameworks and the methodological implications of dataset selection. A comprehensive review of studies published between 2020 and 2025 was conducted across multiple academic databases, encompassing research on skin lesion detection, classification, and monitoring. The analysis reveals that deep learning architectures, particularly those leveraging transfer learning with models such as EfficientNet, ResNet, and Xception, frequently report high classification accuracies—often exceeding 90% when evaluated on single benchmark datasets. However, studies employing multiple datasets consistently demonstrate more stable and generalisable performance, albeit with modest reductions in reported accuracy, highlighting a critical trade-off between performance optimisation and real-world robustness. The review further identifies a clear temporal progression in the adoption of XAI techniques. Early studies relied on a broader range of post hoc explainability while later work increasingly consolidated around Grad-CAM, SHAP, and related attribution techniques, followed by gradual diversification into more specialised frameworks such as TCAVs (Testing with Concept Activation Vectors) and Prototype-based Networks. Despite these advances, the lack of clinically grounded explanations, limited integration of ethical considerations, and reliance on non-clinical imagery continue to constrain clinical applicability which we have explored using a GRADE-style narrative. Notably, evidence suggests that CAD systems can improve GP diagnostic accuracy for conditions such as melanoma and seborrhoeic keratosis; however, sustained clinical adoption remains contingent on transparent, reliable, and context-aware explainability mechanisms. Full article

In this paper, a multi-objective optimisation method based on the Non-dominated sorting genetic algorithm II (NSGA-II) is proposed, which proves to be effective in solving the computer-aided molecular design (CAMD) problem in the design of solvents for cooling crystallisation. A multi-objective optimisation model has been developed for the CAMD problem of solvents in the crystallisation process with the toxicity, solubility parameters, and potential recovery of the solvents as objective functions and the feasibility of the molecular structure as constraints. The properties involved are to be calculated by the group contribution method, and the solubility parameters of the solute in the solvent are calculated based on the Universal Quasichemical Functional-group Activity Coefficients (UNIFAC) model. Based on this method, cooling crystallisation solvents for 2-mercaptobenzothiazole (MBT) and sebacic acid were designed. The results indicate that the proposed multi-objective CAMD framework exhibits a certain degree of generality. Even when the optimisation parameters and methods differ from those of other existing frameworks, it does not overlook the optimal solutions under specific design conditions. Furthermore, clustering of the Pareto front for MBT revealed that, since multi-objective optimisation does not aim to obtain a single optimal solution, it can identify multiple candidate solvents that balance potential yield and toxicity. This approach avoids the issue of single-objective optimisation, which tends to overemphasise potential yield at the expense of toxicity. Full article

Maxillofacial defects impair facial aesthetics and oral function, arising from trauma, tumor resection, or congenital anomalies; however, reconstruction using Computer-Aided Design (CAD) and autologous grafts remains complex and time-intensive, and is associated with donor-site morbidity. Although deep learning (DL) has advanced automated reconstruction, existing models often address isolated tasks, lack integrated multi-scale feature learning, and rely on small datasets. This study proposes the Maxillofacial Implant-generation Network (MaxI-Net), a fast, resource-efficient three-dimensional DL framework for end-to-end maxillofacial defect reconstruction and patient-specific implant generation, with a completion step of cavity filling within the assembly. The model employs a 3D encoder–bottleneck-decoder architecture integrating hybrid dilated convolutions, residual connections, squeeze-and-excitation (SE) blocks, and 3D Convolutional Block Attention Modules (CBAM) with multi-scale feature fusion. It was trained on 921 Cone Beam-Computed Tomography (CBCT) scans, augmented to 11,973 maxillary defect pairs, using Dice loss and Adam optimisation with Automatic Mixed Precision, and benchmarked against UNet, UNETR, SegResNet, and SwinUNETR. MaxI-Net achieved the following: superior Dice Similarity Coefficient (DSC) = 0.778; 95th percentile Hausdorff Distance (HD95) = 3.453 mm; DSC Standard Deviation (SD) = 0.094; 95% confidence interval (CI) for mean DSC: 0.775–0.782). It was statistically validated against all competing architectures via pairwise Wilcoxon signed-rank tests, with significant DSC improvements confirmed across all comparators (p < 0.001) and rank-biserial effect sizes ranging from r = 0.250 against the closest competitor SegResNet* with high efficiency (0.06 s/volume; 9.6 min/epoch). Internal cavity filling of the generated implants was performed as a brief manual post-processing step in Autodesk Fusion 360 prior to biomechanical validation. Biomechanical validation using a finite element analysis (FEA) of polyether–ether–ketone (PEEK) implants (~26.53 g) showed 41% stress reduction under physiological loads (100–400 N), predicting a ~9.2-year lifespan. Full article

The optimisation design of agricultural machinery is shifting from offline, experience-driven engineering towards adaptive, data-driven, and closed-loop intelligent optimisation. Conventional approaches based on computer-aided engineering (CAE), empirical testing, mathematical modelling, and static multi-objective optimisation have provided an important engineering foundation, but they remain limited under unstructured field conditions involving soil heterogeneity, crop variability, climatic disturbance, and nonlinear machinery–environment interactions. This review systematically examines the evolution of intelligent optimisation design for agricultural machinery from conventional simulation-based methods to artificial intelligence (AI)- and digital twin (DT)-enabled paradigms. First, mathematical modelling, response surface methodology, discrete element method (DEM), computational fluid dynamics (CFD), multi-body dynamics (MBD), heuristic algorithms, and early AI-assisted surrogate optimisation are reviewed to clarify their contributions and limitations. Second, frontier enabling technologies are analysed, including agriculture-specific large models, generative AI, lightweight edge intelligence, deep reinforcement learning (DRL), embodied AI, federated learning (FL), and privacy-preserving computing. Third, system-level applications integrating DT and AI are discussed, with emphasis on full-lifecycle machinery optimisation, device–edge–cloud collaborative control, multi-agent fleet coordination, predictive maintenance, and Agriculture 5.0-oriented intelligent equipment systems. Key deployment bottlenecks are further identified, including sim-to-real inconsistency, virtual–physical mismatch in DTs, edge-side trade-offs among accuracy, latency, energy consumption, and cost, insufficient validation standards, and economic adoption barriers. Finally, a 2025–2030 roadmap is proposed, highlighting large-model–DT closed loops, control biomimetics, green low-carbon optimisation, and trustworthy human–machine symbiosis for sustainable Agriculture 5.0. Full article

Bone scintigraphy is a widely available and cost-effective modality for detecting skeletal metastases in prostate cancer, yet visual interpretation can be challenging due to heterogeneous uptake patterns, benign mimickers, and a high reporting workload, motivating robust computer-aided decision support. In this study, we present an experimental evaluation of fourteen convolutional neural network (CNN) architectures for binary metastasis classification in planar bone scintigraphy using a unified protocol. Fourteen models, CNN (baseline), AlexNet, VGG16, VGG19, ResNet18, ResNet34, ResNet50, ResNet50-attention, DenseNet121, DenseNet169, DenseNet121-attention, WideResNet50_2, EfficientNet-B0, and ConvNeXt-Tiny, were trained and tested on 600 scan images (300 normal, 300 metastatic) from the Jordanian Royal Medical Services under identical preprocessing and augmentation with stratified five-fold cross-validation. We report mean ± SD for AUC-ROC, accuracy, precision, sensitivity (recall), F1-score, specificity, and Cohen’s κ, alongside calibration via the Brier score and deployment indicators (parameters, FLOPs, model size, and inference time). DenseNet121 achieved the best overall balance of diagnostic performance and reliability, reaching AUC-ROC 96.0 ± 1.2, accuracy 89.2 ± 2.2, sensitivity 83.7 ± 3.4, specificity 94.7 ± 2.2, F1-score 88.5 ± 2.5, κ = 0.783 ± 0.045, and the strongest calibration (Brier 0.080 ± 0.013), with stable fold-to-fold behaviour. DenseNet121-attention produced the highest AUC-ROC (96.3 ± 1.1) but exhibited greater variability in specificity, indicating less consistent false-alarm control. Complexity analysis supported DenseNet121 as deployable (~7.0 M parameters, ~26.9 MB, ~92 ms/image), whereas heavier models yielded only limited additional clinical value. These results support DenseNet121 as a reliable backbone for automated metastasis detection in planar scintigraphy, with future work focusing on external validation, threshold optimisation, interpretability, and model compression for clinical adoption. Full article

The early stages of structural design increasingly make use of computational tools that support rapid exploration, performance-informed decision-making, and closer interaction between design and engineering. This systematic mapping study examines how Algorithm-Aided Design (AAD) and the Finite Element Method (FEM) are applied and combined in conceptual design workflows. Based on a structured search across three academic databases and a coding scheme applied to 87 publications, the literature is mapped according to algorithmic strategies, FEM applications, element types, disciplinary domains, and levels of integration. The results show that algorithmic and predictive approaches are reported with increasing frequency after 2020, alongside growing use of surrogate models and optimisation routines. Linear-elastic analyses and shell- or beam-based models are frequently reported, particularly in civil engineering contexts, while nonlinear, dynamic, and solid-element analyses appear more prominently in mechanical domains. More tightly coupled AAD–FEM workflows become increasingly visible after 2021, reflecting a growing interest in real-time or near-real-time simulation feedback during early design exploration. At the same time, the literature highlights persistent challenges related to computational cost, fragmented toolchains, limited interoperability, and the relatively limited use of multiscale or advanced material models in conceptual design. Taken together, the findings suggest that continued progress toward more integrated AAD–FEM workflows is closely tied to advances in computational efficiency, improved data exchange and interoperability, and the development of more accessible design–analysis environments across disciplinary boundaries. Full article

The global increase in dementia cases, which is predicted to exceed 152 million by 2050, poses substantial challenges to healthcare systems and caregiving structures. Concurrently, the expansion of mobile health (mHealth) technologies offers scalable, cost-effective opportunities for dementia care. This study systematically reviews 100 publicly available dementia-related mobile applications on the Apple App Store (iOS) and the Google Play Store (Android), categorised using the Mobile App Rating Scale (MARS), as well as the targeted end-users, Internet of Things (IoT) integration, data protection, and cost burden. Applications were evaluated for their utility in cognitive training, memory support, carer education, clinical decision-making, and emotional well-being. Findings indicate a predominance of carer resources and support tools, while clinically integrated platforms, cognitive assessments, and adaptive memory aids remain underrepresented. Most apps lack empirical validation, inclusive design, and integration with electronic health records, raising ethical concerns around data privacy, transparency, and informed consent. In parallel, the study identifies promising pathways for energy-optimised IoT systems, Artificial Intelligence (AI), and Ambient Assisted Living (AAL) technologies in fostering dementia-friendly, sustainable environments. Key gaps include limited use of low-power wearables, energy-efficient sensors, and smart infrastructure tailored to therapeutic needs. Application domains such as cognitive training (19 apps) and carer resources (28 apps) show early potential, while emerging innovations in neuroadaptive architecture and emotional computing remain underexplored. The findings emphasize the need for co-designed, evidence-based digital solutions that align with the evolving needs of people with dementia, carers, and clinicians. Future innovations must integrate sustainability principles, promote interoperability, and support global aging populations through ecologically responsible, person-centred dementia care ecosystems. Full article

Injection moulding of liquid silicone rubber (LSR) requires reliable computer-aided engineering simulations to support process optimisation, which in turn depend on accurate material data. In this study, thermo-physical and kinetic properties of a highly filled injection moulding (IM) grade of LSR were systematically characterised using complementary experimental approaches, and their impact on simulation fidelity was critically assessed. Specific heat capacity was measured using both modulated DSC and the standard sapphire method, revealing temperature dependence but no intrinsic change during curing, with sapphire-based data incorporating enthalpic effects more realistically for process prediction. Thermal conductivity was found to be nearly constant across the processing temperature range. Curing kinetics were investigated by calorimetry and rheology, with the former supporting an autocatalytic mechanism and the latter suggesting an $n^{th}$-order model, reflecting differences in detection sensitivity and onset characterisation. When implemented into injection moulding simulations, viscosity primarily affected injection pressures, while differences in specific heat capacity and curing kinetics strongly influenced predicted curing profiles and cycle times. These results emphasise that dataset choice, particularly for curing-related parameters, is critical to achieving predictive accuracy in LSR injection moulding simulations. Unlike previous studies on LSR injection moulding, which typically adapt thermoplastic-inspired characterisation methods without systematically addressing their limitations, this work introduces an organised and comparative methodology to evaluate how different material characterisation techniques influence simulation outcomes. The proposed approach establishes a methodological framework that can guide future research and improve the reliability of process simulations for LSR and other polymeric systems. Full article

Structural Topology Optimisation (STO) plays a critical role in computational engineering, enabling the creation of material-efficient, performance-driven structures. However, dynamic STO workflows, particularly those involving time-varying or seismic excitations, are often inaccessible to architects and engineers due to their reliance on standalone solvers, large-scale data handling, and advanced programming skills. This paper introduces a Computer-Aided Design (CAD)-embedded, time-dependent STO framework built upon a modular, adjoint-based optimisation core integrated into a Visual Programming Language (VPL) interface. Implemented within a parametric CAD environment through a custom C# component, the framework embeds a MATLAB-based solver to support geometry definition, boundary condition control, and dynamic finite element analysis under harmonic and seismic loading. The resulting Graphical User Interface (GUI) lowers technical barriers by enabling users to iteratively configure STO parameters, manage meshing, and visualise real-time results. Case studies on tall building façades under earthquake excitation validate the framework’s ability to minimise displacement at targeted Degrees of Freedom (DOFs), dynamically adapt material distributions, and enhance structural resilience. By bridging high-fidelity computational methods with accessible visual workflows, the proposed system advances the integration of dynamic STO into both architectural and engineering practice. Full article

This systematic review and meta-analysis investigates the impact of artificial intelligence (AI) tools, including ChatGPT 3.5 and GitHub Copilot, on learning outcomes in computer programming courses. A total of 35 controlled studies published between 2020 and 2024 were analysed to assess the effectiveness of AI-assisted learning. The results indicate that students using AI tools outperformed those without such aids. The meta-analysis findings revealed that AI-assisted learning significantly reduced task completion time (SMD = −0.69, 95% CI [−2.13, −0.74], I² = 95%, p = 0.34) and improved student performance scores (SMD = 0.86, 95% CI [0.36, 1.37], p = 0.0008, I² = 54%). However, AI tools did not provide a statistically significant advantage in learning success or ease of understanding (SMD = 0.16, 95% CI [−0.23, 0.55], p = 0.41, I² = 55%), with sensitivity analysis suggesting result variability. Student perceptions of AI tools were overwhelmingly positive, with a pooled estimate of 1.0 (95% CI [0.92, 1.00], I² = 0%). While AI tools enhance computer programming proficiency and efficiency, their effectiveness depends on factors such as tool functionality and course design. To maximise benefits and mitigate over-reliance, tailored pedagogical strategies are essential. This study underscores the transformative role of AI in computer programming education and provides evidence-based insights for optimising AI-assisted learning. Full article

Amid the COVID-19 pandemic, understanding airborne pathogen transmission within confined spaces became critically important. The release of infectious aerosols through activities such as breathing, speaking, and coughing poses significant health risks, especially in confined spaces like airplane cabins. This study addresses gaps in the research by evaluating the impact of air changes per hour (ACH) on pathogen transmission in an aircraft cabin using computational fluid dynamics (CFD) simulations. A detailed computer-aided design (CAD) model representing half of a four-row section of a Boeing 737 cabin was developed, utilising symmetry boundary conditions to optimise the computational resources while maintaining accuracy. Using ANSYS Fluent 2024, four scenarios were simulated at ACH rates of 15, 20, 25, and 30, with 4 µm pathogens injected into the cabin from a single infector. Airflow patterns and pathogen residence times were analysed for each case. The results indicate that ACH 15 presents the highest risk of pathogen transmission, while increasing the ACH to 20 significantly reduces this risk, with diminishing returns observed beyond ACH 20. Thus, this study underscores the importance of balancing ventilation efficiency, energy consumption, and passenger comfort. The findings provide valuable insights into optimising the ventilation systems to mitigate the airborne transmission in aircraft cabins. Future research should explore higher ACH rates, validate their impact, and conduct a comprehensive optimisation study to further improve the infection control measures. Full article

The latest phase of the industrial revolution (Industry 4.0 and Industry 5.0) involves a large number of key areas that are crucial to improving the performance of technical systems. Computer-aided design and computer-aided engineering are important in their development and the digital twin of systems is one of the key tools for optimising their properties. This research deals with the use of these tools in the development of a machine tool. Nowadays, these tools are usually used separately. The aim of this work was therefore to propose a widely applicable methodology that would suitably combine the previously mentioned tools and thus use their synergistic effect. The proposed methodology was used on a specific machine, namely, a multifunctional portal centre, where features of computer-aided engineering (modelling, topology optimisation, stiffness and stress analyses, modal analyses, and analytical calculations) were combined with tools using the digital twin. The advanced simulations and the creation of the digital twin were performed in the pre-production phase of the machine and are described in detail within this paper. The aforementioned methodology was used to obtain and verify the final dimensions of the developed machine centre, which were the expected results. The proposed dimensions were verified in this way in terms of the mechanical properties of the designed machine (stiffness, strength, and modal properties), in terms of the suitability for machining the specific part, and in terms of the moved masses and drive parameters. Full article

The use of computer simulation to imitate physical processes has proven to be a time-efficient and cost-effective way of performing scenario testing for process optimisation in different applications. The finite element analysis (FEA) is the dominant numerical simulation method for analysing sheet metal forming processes. It uses mathematical tools and computer-aided engineering software programmes to predict forming processes. To improve the quality of output from the simulation, accurate material characterisation data that correctly model the behaviour of the material when it undergoes deformation must be provided. This paper outlines the stages of conducting material characterisation experiments, such as tensile, hardness, and formability tests, using the aluminium alloy AA1050-O. Sample preparation, the machine setup, and testing procedures for the material characterisation tests are given. Subsequent data preparation methods for input into an FEA software programme are also outlined. Implications of the testing results to a deep drawing process are examined while considering the formation of a rectangular monolithic component measuring 2300 mm by 1400 mm with a drawing depth of approximately 150 mm. The results from the characterisation tests indicate that the forming process for the product can be achieved using cold forming at room temperatures as a 25% strain was recorded before necking against an anticipated uniaxial strain of 5.93%. The aluminium alloy AA1050-O demonstrated a negligible strain rate sensitivity in the forming region, thus eliminating tool velocity from the key process parameters that should be considered during FEA simulations. A 50% increase in hardness was recorded after strain hardening. Full article