In the present scenario, cancerous tumours are common in humans due to major changes in nearby environments. Skin cancer is a considerable disease detected among people. This cancer is the uncontrolled evolution of atypical skin cells. It occurs when DNA injury to skin cells, or a genetic defect, leads to an increase quickly and establishes malignant tumors. However, in rare instances, many types of skin cancer occur from DNA changes tempted by infrared light affecting skin cells. This disease is a worldwide health problem, so an accurate and appropriate diagnosis is needed for efficient treatment. Current developments in medical technology, like smart recognition and analysis utilizing machine learning (ML) and deep learning (DL) techniques, have transformed the analysis and treatment of these conditions. These approaches will be highly effective for the recognition of skin cancer utilizing biomedical imaging. This study develops a Multi-scale Feature Fusion of Deep Convolutional Neural Networks on Cancerous Tumor Detection and Classification (MFFDCNN-CTDC) model. The main aim of the MFFDCNN-CTDC model is to detect and classify cancerous tumours using biomedical imaging. To eliminate unwanted noise, the MFFDCNN-CTDC method initially utilizes a sobel filter (SF) for the image preprocessing stage. For the segmentation process, Unet3+ is employed, providing precise localization of tumour regions. Next, the MFFDCNN-CTDC model incorporates multi-scale feature fusion by combining ResNet50 and EfficientNet architectures, capitalizing on their complementary strengths in feature extraction from varying depths and scales of the input images. The convolutional autoencoder (CAE) model is utilized for the classification method. Finally, the parameter tuning process is performed through a hybrid fireworks whale optimization algorithm (FWWOA) to enhance the classification performance of the CAE model. A wide range of experiments is performed to authorize the performance of the MFFDCNN-CTDC approach. The experimental validation of the MFFDCNN-CTDC approach exhibited a superior accuracy value of 98.78% and 99.02% over existing techniques under ISIC 2017 and HAM10000 datasets.
skin cancer detectionskin lesion classificationmulti-scale feature fusionconvolutional neural networks
The recent approval of the nasal spray combination of mometasone (MOM) and olopatadine (OLO) presents a significant analytical challenge, as only a single reported method exists for its determination, deviating from eco-friendly practices. This study addresses this critical gap by pioneering the application of machine learning techniques to develop robust UV spectrophotometric approach for the simultaneous quantification of MOM and OLO, along with two genotoxic impurities: 4-dimethylamino pyridine (DAP) and methyl para-toluene sulfonate (MTS). By simultaneously determining these highly concerning genotoxic impurities and active pharmaceutical ingredients, this method underscores its paramount significance in upholding rigorous pharmaceutical quality standards and safeguarding patient safety. Applying the multilevel-multifactor experimental design, the calibration set was meticulously chosen at five different concentrations, yielding 25 calibration mixtures with central levels of 4, 46.5, 2.5, and 3 µg/mL for MOM, OLA, MTS, and DAP, respectively. The key innovation lies in the strategic implementation of the Kennard-Stone Clustering Algorithm to create a robust validation set of thirteen mixtures, resolving the limitations of reported chemometric methods' random data splitting. This approach ensures unbiased evaluation across the full concentration space, improving the method's reliability and sustainability. The robustness of this approach was rigorously tested using five distinct chemometric models: principal component regression, classical least squares, partial least squares, genetic algorithm-partial least squares, and multivariate curve resolution-alternating least squares, demonstrating its broad applicability across diverse modeling techniques. All models successfully determined all components with excellent recovery, low bias-corrected prediction, and adequate limits of detection. The Greenness Index Spider Charts and the Green Solvents Selection Tool were used to choose environmentally conscious solvents. A comprehensive sustainability assessment employed six state-of-the-art tools, including the national environmental method index, complementary green analytical procedure index, analytical greenness metric, blue applicability grade index, carbon footprint analysis, and the red-green-blue 12 metrics. Favorable results across all metrics affirmed the method's eco-friendliness, real-world applicability, and cost-effectiveness, supporting sustainable development goals in pharmaceutical quality control processes.
The ADHD detector analyzes behavioral, cognitive, or physiological data (e.g., EEG, eye-tracking, or surveys) to identify patterns associated with ADHD symptoms. This work offers a more sophisticated method of detecting ADHD by overcoming the main drawbacks of existing approaches in terms of data processing, detection accuracy, and computational time. The work is inspired by the fact that Deep Learning (DL) frameworks could transform the existing detection systems of ADHD. In the proposed framework, there is a new NeuroDCT-ICA module for the preprocessing of raw EEG data, which guarantees the elimination of noise and extraction of informative features. Moreover, the method introduces a novel RhinoFish Optimization (RFO) algorithm for selecting optimal features, which enhance the data processing capacity and the stability of the system. As a core of the approach, there is the ADHD-AttentionNet - the deep learning-based model aimed at improving the accuracy and confidence of ADHD identification. The model is validated with the standard metrics, and the performance of the model is outstanding as it has high accuracy of 98.52%, F-score of 98.26% and specificity of 98.16%. These outcomes show that the proposed model yields better accuracy in detecting ADHD related patterns.
Reinforcement learning is a remarkable aspect of the artificial intelligence field with many applications. Reinforcement learning facilitates learning new tasks based on action and reward principles. Motion planning addresses the navigation problem for robots. Current motion planning approaches lack support for automated, timely responses to the environment. The problem becomes worse in a complex environment cluttered with obstacles. Reinforcement learning can increase the capacity of robotic systems due to the reward system's capability and feedback to the environment. This could help deal with a complex environment. Existing algorithms for path planning are slow, computationally expensive, and less responsive to the environment, which causes late convergence to a solution. Furthermore, they are less efficient for task learning due to post-processing requirements. Reinforcement learning can address these issues using its action feedback and reward policies. This research presents a novel Q-learning-based reinforcement algorithm with deep learning integration. The proposed approach is evaluated in a narrow and cluttered passage environment. Further, improvements in the convergence of reinforcement learning-based motion planning and collision avoidance are addressed. The proposed approach's agent converged in 210th episodes in a cluttered environment and 400th episodes in a narrow passage environment. A state-of-the-art comparison shows that the proposed approach outperformed existing approaches based on the number of turns and convergence of the path by the planner.
Congenital heart disease (CHD), impacting around 1 % of infants worldwide, constitutes a significant healthcare challenge. Early detection is crucial, however constrained by the intricacies of conventional diagnostic techniques such as auscultation and echocardiography. This research presents a tailored one-dimensional convolutional neural network (1D-CNN) for the classification of phonocardiogram (PCG) signals into normal or abnormal categories, providing an automated and efficient solution for congenital heart disease (CHD) diagnosis. The model was trained on a composite dataset consisting of local pediatric PCG signals and publicly accessible dataset. Preprocessing methods, such as low- and high-pass filtering (60-650 Hz), resampling, and noise reduction, were utilized to enhance signal quality. Data augmentation techniques, including chunking, padding, and pitch-shifting, were employed to rectify dataset imbalances and improve model efficacy. Experimental results indicate substantial enhancements, attaining an accuracy of 98.56 %, precision of 98.56 %, F1 score of 98.55 %, sensitivity of 0.98, and specificity of 0.99. The comparative analysis demonstrates the proposed approach's superiority over current methods regarding accuracy and reliability. The research highlights the promise of combining modern signal processing with deep learning for efficient CHD screening. The suggested model exhibits outstanding performance yet, issues like dataset variability and noise persist. Future endeavors involve extending to multiclass categorization and assessing performance across a wider range of medical problems. This study represents a significant advancement in accessible, automated CHD diagnoses, enhancing clinical competence to elevate pediatric treatment.
International Journal of Computational Intelligence Systems · مجلد 18 (1)
Artificial intelligence (AI) transforms multiple businesses, including medical research, where AI-driven developments bring significant advantages. The application of machine learning algorithms enables medical researchers to examine large amounts of data accurately, which leads to the development of precise and effective treatment approaches. Lung cancer leads the list of critical healthcare issues because it remains the world’s most lethal form of cancer thus demanding innovative diagnostic tools for faster and accurate identification. The proposed study introduces an innovative method called CTGAN-RF which uses conditional tabular generative adversarial networks (CTGAN) and random forest (RF) classifier to detect lung cancer through synthetic data generation. The proposed model demonstrated superior performance by achieving a 0.9893 score of accuracy and 0.99 value for precision, F1 score, and recall. Extensive experimental evaluation for this method included testing nine classification algorithms. The implementation of different classifiers employed data balancing methods including SMOTE and borderline-SMOTE along with SMOTE ENN and unbalanced data configurations. Comparative analysis showed that CTGAN-RF consistently performed significantly better than traditional classifiers in dealing with class imbalance and improving prediction accuracy. After testing with fivefold cross-validation, the reliability of the model was further validated. In comparison to cutting-edge approaches for lung cancer diagnosis, the proposed methodology outperformed in terms of classification metrics. This in-depth evaluation of synthetic data augmentation with machine learning in lung cancer detection has helped in the development of personalized treatment strategies in the fight against such a life-threatening disease.
lung cancer detectionsynthetic data augmentationCTGANrandom forest
Case Studies in Thermal Engineering · مجلد 76 · 107397-107397
This work provides a detailed evaluation of a novel biomass-fueled multigeneration system, conceived to contribute to the growing emphasis on sustainable energy solutions. The architecture comprises a biomass gasifier, an innovative cascaded organic Rankine cycle (CORC) incorporating a high-temperature mixture in the top cycle, a proton exchange membrane electrolyzer (PEME), a Brayton cycle, and waste heat utilization units, all operating together to deliver electricity, hydrogen (H 2 ), and thermal output. A comprehensive thermodynamic modeling framework is established to evaluate the system’s performance across various operational scenarios. The framework emphasizes critical metrics, including exergy efficiency, levelized total emissions (LTE), and payback period (PP). These indicators ensure a holistic assessment of energy, exergy, economic, and environmental considerations. Parametric studies demonstrate that enhancements in biomass mass flow rate and combustion chamber temperature significantly increase power output and H 2 production while reducing the payback period, underscoring the system’s flexibility and economic feasibility. Furthermore, the study employs sophisticated machine learning optimization methods, combining artificial neural networks (ANNs) with genetic algorithms (GA), to determine optimal operating conditions with minimal computational effort and maximum efficiency. When evaluated at nominal parameters, the system records an exergy efficiency of 23.72%, achieves a PP of 5.61 years, and yields an LTE value of 0.34 ton/GJ. However, under optimized conditions, these values improve to 35.01%, 3.78 years, and 0.241 ton/GJ, respectively.
In the rapidly evolving field of healthcare 5.0, the Internet of Medical Things (IoMT) is expected to be an enabler that allows smart medical devices to collaborate and communicate with healthcare networks to speed up procedures, enhance care, and improve disease management. However, one of the critical issues for these networks still remains the secure and energy-efficient transmission of sensitive patient data. Thus, a novel security framework is proposed in this work, in which a Public Key Infrastructure- Energy-Efficient Routing Protocol (PKI-EERP) with a Zebra Optimization Algorithm (ZOA) is incorporated in spiking neural networks. The method combines data security robustness of the spiking neural networks to detect anomalies and check for access control purposes, with the PKI encryption to provide safe encryption and key management. The ZOA optimizes energy consumption in WSNs, and as a result transmission energy is significantly reduced up to 35 % compared to other implementations, and the network lifetime is increased by about 30 % through effective load balancing. It enhances both the privacy and energy efficiency that are essential for the safe and reliable operation of IoMT systems in contemporary healthcare environments, thus improving patient outcomes as well as standards of operations.
Internet of Medical ThingsHealthcare 5.0public key infrastructurespiking neural networks
Diet, stress, genetics, and a sedentary lifestyle may all contribute to heart disease rates. Although recent studies propose comprehensive automated diagnostic systems, these systems tend to focus on one aspect, such as feature selection, prioritization, or predictive accuracy. A more complete approach that considers all of these factors can improve the efficiency of a cardiac prediction system. This study uses an appropriate strategy to overcome potential network design problems, design challenges, overfitting, and lack of robustness that can interfere with system performance. The research introduces an ideally designed deep trust network called ID-DTN to improve system performance. The Ruzzo-Tompa method is used to eliminate noncontributory features. The Seagull Optimization Algorithm (SOA) is introduced to optimize the trust depth network to achieve optimal network design. The study scrutinizes the deep trust network (ID-DTN) and the restricted Boltzmann machine (RBM) and sheds light on the system's operation. This proposal can optimize both network architecture and feature selection, which is the main novelty. The proposed method is analyzed using the below-mentioned metrics: Matthew's correlation coefficient, F1 score, accuracy, sensitivity, specificity, and accuracy. ID-DTN performs well compared to other state-of-the-art methods. The validation results confirm that the proposed method improves the prediction accuracy to 97.11% and provides reliable recommendations for patients with cardiovascular disease.
The incidence of suicide, self-harm, and mental crises among teenagers is rising, presenting significant global public health issues. Conventional clinical risk evaluations have inadequate predictive accuracy, often overlooking high-risk adolescents. Machine learning models employing electronic health records provide an innovative method for predicting mental health crises through the integration of intricate clinical data patterns. Hence, this review aims to comprehensively examine and synthesize information about machine learning models created using electronic health record data for predicting suicide attempts, self-harm, or mental hospitalization in teenagers. Adhering to Preferred Reporting Items for Systematic reviews and Meta-Analyses (PRISMA) principles, we executed an exhaustive search across six databases (2000-2025) for peer-reviewed research utilizing machine learning algorithms on electronic health record data to predict adolescent mental health crises. The inclusion criteria emphasized structured or unstructured electronic health record inputs, teenage cohorts (ages 10-20), and performance indicators like area under the curve (AUC), sensitivity, or specificity. The Prediction Model Risk of Bias Assessment Tool (PROBAST) was utilized to evaluate the risk of bias. Our search yielded five studies (2019-2024) that satisfied the inclusion criteria. All studies were retrospective cohorts conducted in high-income nations. Structured electronic health record data (e.g., diagnoses, prescriptions) were frequently utilized; two studies included natural language processing. Machine learning models demonstrated moderate to high discrimination (AUC 0.68-0.88), exhibiting optimal performance in short-term suicide prediction with hybrid data inputs. All investigations, however, exhibited a significant risk of bias in the analysis domain owing to insufficient external validation and absent calibration data. The positive predictive values consistently remained modest across all models. Overall, machine learning models demonstrate potential for enhancing adolescent suicide risk classification utilizing electronic health record data, surpassing numerous traditional instruments. Nonetheless, issues of generalizability, ethical constraints, and implementation obstacles remain. Thorough validation, calibration, and equity assessments are necessary prior to incorporation into clinical practice.
adolescent mental healthsuicide risk predictionself-harmelectronic health records
Epilepsy represents a widespread neurological disorder that causes unexpected seizure occurrences which produce significant obstacles for daily life activities in people worldwide. Real-time seizure detection accuracy stands vital for safeguarding patients while ensuring timely interventions and bettering their quality of life. The present seizure detection methods suffer from multiple limitations including poor applicability across different cases and excessive incorrect alerts and inefficient feature selection procedures. Traditional deep learning algorithms generally fail to detect EEG patterns with both temporal and spatial characteristics thereby producing subpar results in practical settings. This study proposes EpilepNet-LD integrated with federated learning (FL), a novel framework for decentralized EEG analysis that preserves patient privacy while enabling collaborative model training. The framework employs a hybrid harmony search and mutual information (HSA-MI) feature selection technique to identify optimal temporal, spectral, and spatial EEG features, reducing computational overhead. The EpilepNet-LD architecture combines long short-term memory (LSTM) networks to capture temporal dependencies with DenseNet-121 to extract hierarchical spatial features, improving seizure detection performance. Extensive experimental evaluations confirmed the proposed method achieves 99.41% extensive experiments demonstrate that the proposed method achieves 99.41% accuracy and 99.50% sensitivity, outperforming existing state-of-the-art approaches. The integrated FL and HSA-MI approach, coupled with the EpilepNet-LD classifier, enables robust, real-time, and high-precision seizure detection, offering a reliable solution for advanced epilepsy monitoring and management.
epilepsyseizure detectionfederated learningmutual information feature selection
The integration of digital twins (DTs) with mobile edge computing (MEC) offers transformative potential for computational energy efficiency in Industry 5.0-driven 6G networks. However, existing frameworks often lack proactive resource allocation using DTs, relying instead on reactive adjustments. This paper proposes a novel DT-MEC framework that uniquely employs virtual DT replicas of MEC servers to predict computational states (e.g., server workloads, latency trends) in real time, enabling dynamic optimization of task offloading for large-scale Industrial IoT (IIoT) networks. Unlike prior DT-MEC integrations that focus on static resource allocation, our approach leverages predictive DT modeling to preemptively adjust resources, addressing a critical gap in the literature. To maximize energy efficiency, we formulate a mixed-integer non-linear problem (MINLP) that jointly optimizes local computation, transmission power, DT-edge association, and task execution time. The problem is transformed into a tractable form using piecewise linearization to reduce computational complexity and solved via an adaptive iterative algorithm that alternates between resource allocation and DT state updates. This method ensures a balance between solution accuracy and computational overhead, a key innovation compared to conventional optimization techniques. Simulations demonstrate that our framework achieves 40% higher energy efficiency, 50% lower outage probability, and 95% task completion rates compared to state-of-the-art benchmarks. Specific improvements include a 6.63% gain over binary offloading and 150.08% over edge-only schemes, validating its practicality for Industry 5.0 deployments. These results highlight our contributions: (1) a proactive DT-driven resource allocation mechanism, (2) a linearization technique for non-convex MINLP problems, and (3) an adaptive iterative solver that outperforms existing approaches in dynamic IIoT environments.
digital twinmobile edge computing6Gtask offloading
This work aims to promote early and accurate diagnosis of Temporal Lobe Epilepsy (TLE) by developing state-of-the-art deep learning techniques, with the goal of minimizing the consequences of epilepsy on individuals and society. Current approaches for TLE detection have drawbacks, including applicability to particular MRI sequences, moderate ability to determine the side of the onset zones, and weak cross-validation with different patient groups, which hampers their practical use. To overcome these difficulties, a new Hybrid Attention-Enhanced Transformer Network (HAETN) is introduced for early TLE diagnosis. This approach uses newly developed Fuzzy-AAL Segmentation Framework (FASF) which is a combination of Fuzzy Possibilistic C-Means (FPCM) algorithm for segmentation of tissue and AAL labelling for labelling of tissues. Furthermore, an effective feature selection method is proposed using the Dipper- grey wolf optimization (DGWO) algorithm to improve the performance of the proposed model. The performance of the proposed method is thoroughly assessed by accuracy, sensitivity, and F1-score. The performance of the suggested approach is evaluated on the Temporal Lobe Epilepsy-UNAM MRI Dataset, where it attains an accuracy of 98.61%, a sensitivity of 99.83%, and F1-score of 99.82%, indicating its efficiency and applicability in clinical practice.
temporal lobe epilepsymagnetic resonance imagingfuzzy segmentationgrey wolf optimizer
Journal of Pioneering Medical Science · مجلد 14 (09) · 103-107
Coronary Artery Disease (CAD) remains a leading cause of morbidity and mortality worldwide. To evaluate the diagnostic performance of AI models in the early detection and risk stratification of CAD using ECG and imaging data and to compare their accuracy with cardiologist interpretation. Methods: This cross-sectional analytical study was conducted in Saudia, included 185 patients with suspected CAD who underwent both ECG and imaging evaluation. AI-based models, including convolutional neural networks for ECG and deep learning algorithms for imaging, were applied to detect CAD and stratify patients into risk categories. Cardiologist-confirmed diagnosis served as the reference standard. Results: The AI-ECG model achieved a sensitivity of 88.5%, specificity of 82.0% and an AUC of 0.90 (95% CI: 0.86–0.94). When ECG and imaging data were combined, diagnostic accuracy improved, with sensitivity of 92.4%, specificity of 85.2% and an AUC of 0.93 (95% CI: 0.89–0.96). AI-based risk stratification categorized 54 patients (29.2%) as low risk, 78 (42.2%) as intermediate risk and 53 (28.6%) as high risk. Confirmed CAD prevalence correlated strongly with AI-predicted risk groups, with 22.2% in the low-risk group and 88.7% in the high-risk group. Conclusion: Artificial intelligence demonstrates high accuracy in the early detection and risk stratification of CAD using ECG and imaging data. AI models performed comparably to cardiologists and offered significant efficiency gains. Integration of AI into cardiovascular workflows may enable earlier intervention, optimized resource allocation and improved patient outcomes. Further validation across larger and more diverse populations is warranted.
In the digital age, images permeate every facet of our lives, often carrying critical information for organizations, institutions, and even nation-states. Ensuring their security against unauthorized access is paramount. This research introduces a novel image encryption algorithm designed to safeguard the integrity and confidentiality of sensitive gray-scale digital images. The algorithm leverages the theory of axis-aligned bounding boxes, translating the input image into a 3D representation. Within this 3D space, two identically sized boxes are generated and assessed for overlap. If the boxes do not overlap, the pixels within them are swapped. This pixel-swapping process, guided by random numbers generated from a 5D multi-wing hyper-chaotic map, is repeated numerous times to infuse confusion into the image. To further enhance security, diffusion effects are introduced by performing an XoR operation between the confused image and random numbers provided by the piece-wise linear chaotic map. This study employs private key cryptography and utilizes four gray-scale images to validate the feasibility and effectiveness of the proposed method. Simulation has been carried out in the Pythonic ecosystem. So, the algorithms presented in this study are designed to closely resemble Python code. Comprehensive validation metrics attest to the robustness of the cipher, achieving an information entropy of 7.99985 and a computational speed of 0.3987 seconds. These results underscore the potential of this encryption approach for practical, real-world applications. These applications span military, diplomacy & government, commerce, showbiz, industry, and social life etc.