Early polyp detection is vital in avoiding colorectal cancer, a top contributor to cancer-related deaths globally.Automated polyp detection has been greatly improved by deep learning, but extensive deployment tends to be hamperedby patient data privacy fears. For this purpose, we suggest a federated learning (FL) paradigm that enables decentralizedmodel training without sharing raw patient data while having high diagnostic accuracy. We first performed an extensiveevaluation using DL models on a polyp dataset that we gathered. MobileNetV2 was the best performing model as perimportant metrics like accuracy, precision, recall, and F1 score. In order to further expand its representational power, weincorporated a transformer module into MobileNetV2 so that the model can better capture long-range dependencies andcontext information. Our new Transformer-Enhanced MobileNetV2 model was then implemented on several simulatedclients in a federated learning scenario. This configuration enabled training over decentralized clinical data withoutviolating patient privacy. We utilized standard FL algorithms for model averaging and evaluated the system in accuracy,precision, recall, F1 score, and convergence time. The devised approach performed extremely well with an accuracy of98.37% and an F1 score of 0.971 while converging effectively in 27-33 rounds. These findings imply that a promisingpath for safe and effective medical image analysis is to combine transformer designs with lightweight models in afederated condition.
It is still hard to accurately find bone fractures and figure out how bad osteoarthritis (OA) is from X-raypictures because of the complicated anatomical differences and the lack of contextual modelling in standard deeplearning methods. This research presents XrayBoneNet, a hybrid deep learning system that combines ConvolutionalNeural Networks (CNNs), Transformer-based global feature modelling, and attention mechanisms for concurrentfracture identification, OA grading, and localization. The model has two heads: one for binary fracture classification andone for multi-class OA staging. It also has a bounding box regression head for accurate localization. To improve trainingefficiency and performance, a hybrid optimization technique that uses Bighorn Sheep Optimization (BSO) for globalexploration and Logarithmic Mean Optimization (LMO) for fine-tuning is developed. The Bone Fracture Multi-RegionX-ray dataset shows that XrayBoneNet works better than state-of-the-art models like ResNet50, DenseNet121, andVision Transformer. It has 96.8% accuracy in fracture detection, 94.5% accuracy in OA classification, and an Intersection-over-Union (IoU) of 0.87 for localization. The suggested system offers an effective and comprehensiblealternative for automated radiological diagnosis.
Skin diseases range from mild conditions to severe threats, such as melanoma highlighting the critical importance of early and accurate evaluation for effective treatment. Traditional diagnostic methods that depend heavily on visual inspection and biopsy are often prone to delays and susceptible to human error underscoring the need for more efficient and reliable approaches. This study introduced a computerized system for detecting skin diseases using deep learning techniques and classification, with a focus on enhancing diagnostic efficiency and accuracy. The approach begins with the comprehensive preprocessing of skin images including illumination adjustment, elimination of artifacts via morphology closing and edge improvement using an unsharp filter. These steps improve the image clarity and prepare the data for accurate analysis. To address variations in lesion size and boundary irregularities a Fuzzy k-means clustering technique segments the affected skin regions, ensuring adaptable detection across diverse skin conditions. The classifier Deep-MobileNet integrates the lightweight MobileNet architecture with Squeeze-and-Excitation (SE) blocks enabling it to effectively differentiate between healthy and diseased skin. SE blocks enhance the model’s ability to capture spatial dependencies thereby improving classification precision. To further optimize the classifier’s performance hyperparameters are tuned using the adaptive deer hunting optimization (ADHO) algorithm, which accelerates convergence and boosts model efficiency. By providing an automated efficient solution this approach has the potential to assist healthcare providers in diagnosing skin diseases quickly and reliably thereby supporting timely and effective treatment interventions. The efficiency of the suggested method is evaluated based on accuracy, sensitivity, specificity and F1-Score. The experimental outcome showed that recommended approach attained a maximum accuracy of 91.96%.
Image fusion is the method of combining the features of different images into one to get a more informativeor high-quality image. Among its various types, multi-modal image fusion is a crucial one where images obtained usingsensors receptive to different light radiation are integrated into one final image. Infrared (IR) and Visible (VIS) ImageFusion (IVIF) is one such popular fusion technology. In IVIF, visible sensor produces clean texture and structureinformation, while it is sensitive to illumination and occlusion. IR sensor, though vulnerable to noise, captures salienttargets that emit thermal radiation. The contrasting properties of the two images can be exploited by producing a fusedimage that both highlights the prominent target as well manifests detailed information. First, the acquired IR and VISsource images are each decomposed using the Gaussian blur filter into base (low-frequency) and detail (high-frequency)components. As opposed to the conventional way of concatenating the respective base and detailed components of thesource images, a new technique of combinative concatenation has been performed providing a comprehensive set of 6unique features to perform fusion. The proposed combinative concatenation is mathematically formulated, illustratinghow cross-modal feature generation improves the retention of information and enhances modal complementarity.Weighted Sum (WS), Principal Component Analysis (PCA) and Laplacian Pyramid (LP) have been used for the fusionprocess. The 6 unique features extracted are fused in 20 different ways considering all combinations to provide fusedresults with different properties. Finally, a set of 4 statistical analysis methods are applied to identify the best fusionstrategy. As a highlight, this paper has assessed these fusion strategies over live images captured using a Near-Infrared(NIR) and VIS camera depicting different illumination conditions (bright, dim and dark), and its effects over the fusionperformance are assessed in comparison to fusion of similar images from an existing dataset.
The rapid growth of motor vehicles in urban areas has led to an increasing demand for parking facilities andrequires tariff policies that are more adaptive to real field conditions. This study aims to develop a parking revenuepotential classification model to support the formulation of progressive parking tariff policies using a data-driven andspatial analysis approach. The dataset includes vehicle attributes, parking volume, and temporal parking usage patterns.Parking revenue potential is categorized into low, medium, and high classes using a quantile-based approach. Unlikemost previous studies that focus on parking occupancy prediction, this study proposes a revenue-orientedspatiotemporal classification model integrating spatial coordinates and temporal parking patterns to support adaptivetariff policy formulation. The Random Forest algorithm is applied to classify parking revenue potential into low,medium, and high categories, achieving an accuracy of 90.24% for two-wheeled vehicles and 89.02% for four-wheeledvehicles. The classification results are integrated into an interactive Streamlit-based dashboard that visualizes the spatialdistribution of parking revenue potential and enables simulations of progressive tariff adjustments based on spatialzones and temporal conditions. The proposed system functions as a decision support tool for parking management,aiming to improve operational efficiency and sustainably increase regional parking retribution revenue.
Nephrolithiasis (kidney stone disease) is a common urological disease that has a high clinical and economic impact. The early diagnosis is needed to avoid complications like obstruction of the ureter, infection, impaired kidney functioning. Traditional imaging modalities, such as ultrasonography, kidney-ureter-bladder radiography, and non-contrast computed tomography, are common but have a number of limitations, specifically their operator dependence, radiation, and low sensitivity to small or radiolucent stones. This review follows a PRISMA-based methodology to conduct a systematic review of studies published between 2015 and 2025 on the topic of computational intelligence methods such as artificial intelligence, machine learning, and deep learning to detect kidney stones based on medical images. Major scientific databases were considered in studies according to imaging modality, preprocessing method, model architecture and performance measures. Deep learning models, especially, Convolutional Neural Networks and U-Net-based frameworks, are highly effective in detection and segmentation tasks and have been reported to have accuracy of 86 to 99.9 percent, Dice coefficients over 0.85 and AUC of up to 0.99 in controlled data. Hybridization to combine ML classifiers, including Support Vector Machines, further improves the performance of classification. Yet, these outcomes are commonly limited through small datasets, class imbalance, external validation, and overfitting, which have an impact on real-life generalization. The use of computational intelligence has greatly improved the detection of kidney stones by enhancing automation, precision, and reproducibility. However, there are still major issues, such as the standardization of the dataset, interpretability of the models, and limitations to the clinical implementation. Explainable AI, federated learning, and 3D volumetric analysis should be prioritized in future research to create diagnostic systems.
Currently, image compression algorithms are an integral part of modern information systems in variousindustries and spheres of human activity, including telecommunications, medicine, artificial intelligence, and defensetechnologies. This paper deals with a novel image compression method based on nonlinear multiscale decompositionwith fractional-rational approximation, providing a compact representation of image components while preservingreconstruction quality. The proposed algorithm consists of five steps, including image preprocessing, discretization,nonlinear multiscale decomposition, quantization, and arithmetic compression. The method was evaluated using 1000test images and demonstrated an average compression ratio of 13.2, with reconstructed image quality of 41.5 dB, outperforming classical wavelet-based approaches under comparable conditions (approximately by 8-10% in average).The computational complexity of the proposed algorithm remains suitable for practical implementation, making it apromising solution for efficient image compression in modern digital systems.
Addressing crowd control and safety at large-scale events is the central focus of this study. The proposed methodology is tested on ShanghaiTechA, ShanghaiTechB and UCF CC50 datasets. Apart from VGG-16 referred as the baseline model, the study utilizes a Convolutional Neural Network (CNN) model like VGG with dilatable layers and Atrous Spatial Pyramid Pooling (ASPP) layers on these datasets to identify every individual in the crowd by their heads. Furthermore, optical flow analysis identifies fast-moving pixels, facilitating the detection of rapid movements within the crowd. YOLO tracking is additionally employed to monitor the direction of object movement within the crowd. By integrating these methodologies, the study aims to enhance overall safety and security of individuals in the crowd. VGG with dilatable layers gives the least Mean Absolute Error for ShanghaiTechA and ShanghaiTechB datasets. The ASPP approach demonstrates approximately 15% higher accuracy on average compared to the baseline model for the ShanghaiTechA and UCF CC 50 datasets.
Satellite imagery is always used to study spatial geographies to find water, residential, farmland, and forest lands; which can be further used for township development and planning, landscape detection etc. Semantic segmentation and image classification are the two crucial procedures in determining the spatial geographies. In order to improve the generalization ability of semantic segmentation algorithms, a combined model of UNet_ResNet is used in this paper. The engineered model is a type of Convolutional Neural Networks using GeoGANs which detects semantic patches in neural networks with smaller sizes and regional characteristics within a certain spatial and pixel scale. However, it faces a semantic segmentation challenge of identifying roadways in metropolitan areas. The model shows an accuracy score from 93% to 97.3% for image classification and segmentation purposes which fares better than the implementation of various existing architectures.
Image denoising remains a fundamental challenge in image processing, particularly when dealing with additive white gaussian noise (AWGN) that degrades visual quality and information content. This paper introduces a novel multi-stage denoising framework that uniquely combines Contourlet transform, radial basis function neural networks (RBFNN), and kalman filtering to effectively preserve important image features while removing noise. The contourlet transform first decomposes images into multi-resolution, directional subbands, providing a sparse representation that better captures geometric structures compared to traditional wavelet approaches. We then employ an RBFNN trained through back-propagation to adaptively threshold the contourlet coefficients based on local image characteristics and noise levels. Finally, kalman filtering is applied as a post-processing step to further suppress residual noise artifacts. Comprehensive experiments conducted on standard benchmark datasets demonstrate that our approach outperforms several state-of-the-art methods, including BM3D and recent deep learning-based techniques, particularly at moderate to high noise levels (σ ≥ 15). Quantitative evaluations show our method achieves superior PSNR improvements of up to 2.4dB and SSIM improvements of 0.12 compared to recent competing approaches, while qualitative results confirm better preservation of edges and textural details. The proposed framework offers an effective balance between computational efficiency and denoising performance, making it suitable for various practical applications.
This paper establishes a new process of surface defect detection of steel products with both integrated image processing and image vision capabilities. The approach which incorporates Multi-Scale Local Binary Pattern (MSLBP), Dual-Tree Complex Wavelet Transform (DTCWT), and Gabor Wavelet in extracting features, whilst the Neighborhood Component Analysis (NCA) approach is in selecting the features. Ensemble AdaBoost is employed as a comparative baseline classifier and the final defect detection performance is presented in the Enhanced Snake Optimized Support Vector Machines (ESO-SVM) model. The suggested approach is superior to the classical methods, as the results of the experiments show 98.8 percent accuracy and 98.5 percent F1-score at the process of detecting fine and irregular defects under different production conditions. The system improves reliability and scalability of automatic defect detection thus increasing the quality of steel products and decreasing wastes.
Speech enhancement plays a vital role in improving the perceptual quality and intelligibility of speech signals degraded by environmental noise, particularly in modern network-based and signal processing systems. Traditional U-Net architectures capture local spectral details effectively but struggle to model long-range dependencies and may propagate residual noise through skip connections. Transformer-based models provide strong global context modeling but often fail to retain fine-grained spectral cues. To overcome these limitations, this paper presents a Nested U-Net–based network-oriented speech enhancement framework that incorporates Multi-Scale Feature Extraction, Feature Calibration, and a Dual-Path Higher-Order Information Interaction with Time-Frequency Attention module. The Multi-Scale Feature Extraction blocks in both encoder and decoder extract multi-resolution spectral patterns, while the nested topology strengthens hierarchical feature reuse. At the bottleneck, a stack of four Dual-Path Higher-Order Information Interaction with Time-Frequency Attention modules captures long-range temporal and spectral dependencies, and feature calibration adaptively filters encoder features to reduce noise transfer. Extensive experiments on Common Voice and LibriSpeech datasets demonstrate that the proposed model achieves superior perceptual evaluation of speech quality, short-time objective intelligibility, and signal-to-distortion ratio scores, particularly under moderate (0dB) signal-to-noise ratio conditions. The results confirm that the framework provides robust enhancement performance and consistently outperforms several recent state-of-the-art methods in terms of speech quality, intelligibility, and noise suppression.
Melanoma skin disease is a major concern for skin cancer-related deaths worldwide. Early diagnosis and detection are crucial for improving patient outcomes. However, existing detection methods often result in false alarms, highlighting the need for more accurate and reliable approaches. This paper proposes a Dual-Stream Semi-Supervised Melanoma Network (DS-MelNet) for melanoma detection. The DS-MelNet utilizes a semi-supervised learning framework to incorporate both labeled and unlabeled data, enhancing detection accuracy. The model's performance is evaluated on the SIIM-ISIC Melanoma Classification Challenge dataset. The dataset undergoes hair detection and removal from skin lesion images using three algorithms proposed in literature viz. Modified Dull Razor, Modified E-shaver and Adaptive principle curvature with Modified dull razor fusion. Performance of the proposed models is assessed through commonly used metrics that include Accuracy, Recall, Precision, and F1-score. Comparative analysis of the DS-MelNet is performed against two benchmarks: Simple Convolutional Neural Network (SCNN) and a Fine-tuned VGG-16 model proposed in this paper. The results clearly indicate that the DS-MelNet demonstrates superior performance, achieving an accuracy of 86% and outperforming both SCNN (76%) and VGG-16 (82%) models. This exceptional performance underscores the potential of the DS-MelNet for effective melanoma classification. The study highlights the promise of semi-supervised learning frameworks and sophisticated neural networks in enhancing melanoma diagnostics. The ability of the proposed model to learn from a small set of labeled data makes it highly suitable for real-world applications where annotated datasets are limited.
Classifying and predicting banana shelf life is vital for optimizing storage and distribution in agriculture. Traditional methods, relying on subjective visual inspection, are inconsistent and time-intensive. This study presents a new, non-destructive approach combining thermal imaging, and machine learning to classify naturally ripened and artificially ripened bananas and forecast their shelf life. Preprocessed thermal images are flattened, segmented into fixed-size patches, and then linearly projected into feature tokens. Position embeddings are incorporated to retain spatial information, and the sequence is processed by a Vision Transformer (ViT) encoder, which leverages self-attention mechanisms to model relationships between patches. The [CLS] token output is subsequently processed through fully connected layers for final classification, achieving 97.59% accuracy. Validation using t-SNE visualization demonstrated clear class separability, and receiver operating characteristic (ROC) curves confirmed robust performance. With an MSE of 0.10, MAE of 0.18, and R2 score of 0.85, the random forest algorithm performed exceptionally well at predicting the shelf life of artificially ripened bananas. This approach offers significant advantages, including improved accuracy, reduced subjectivity, and efficiency in data processing. By integrating thermal imaging with advanced models, the proposed method enhances agricultural supply chain management and promotes precision in ripening classification and shelf life prediction.
In the rapidly evolving landscape of medical diagnostics, efficient and accurate tools for disease identification are crucial. This study analyzes three convolutional neural network (CNN) architectures—IRV2, ResNet50, and DenseNet121—pre-trained on ImageNet and RadImageNet datasets for respiratory disease diagnosis using chest radiographs. We used over 10,000 chest X-ray images, including COVID-19, pneumonia, and control cases, to train and evaluate these models. RadImageNet-trained models, particularly ResNet50, achieved superior performance with 94.49% accuracy, 93.92% sensitivity, and 95.59% precision compared to ImageNet-trained counterparts, though the improvement was not statistically significant in most cases. To enhance interpretability, we developed a counterfactual-based method generating visual explanations of critical areas influencing diagnostic outcomes. This approach, not requiring access to training data or model internals, identifies image parts that could change the predicted diagnosis if altered. It aids in understanding model reasoning and can correct misclassifications, successfully reclassifying up to 40.91% of previously misclassified images through our masking method. By providing clear, independent visual explanations, our method aims to foster trust in AI-assisted diagnoses among medical professionals. While preliminary results are promising, further validation with medical experts will help confirm the clinical relevance of the highlighted regions. This will strengthen the transparency and interpretability of AI decision-making in healthcare. The visual nature of these explanations offers a valuable tool for interpreting complex medical image classification models and may enhance the synergy between AI systems and human expertise in diagnostic processes.
Emergencies of natural, technological, and military origin require rapid and accurate assessment of victims' conditions to support effective rescue and medical response. Traditional visual examination methods are often limited by stress, time pressure, and incomplete information, leading to delayed or inaccurate decisions. This study proposes a multimodal deep learning approach for automated identification of human resource lesions in emergency scenarios. The developed framework integrates visual, audio, and text/sensory data using convolutional neural networks, Transformer-based models, and a Transformer Cross-Attention fusion mechanism. The proposed architecture enables effective extraction and integration of heterogeneous features for lesion classification, severity estimation, and automated medical triage. Experimental evaluation was conducted on multimodal datasets containing injury images, audio recordings, and symptom descriptions. The model was trained using a combined loss function and evaluated with classification, regression, and triage metrics. The results demonstrate high system performance, achieving a macro-F1 score of 0.87, validation accuracy of 86–87%, and triage accuracy above 90%, including 95% for the RED category. The regression model for severity prediction achieved an R² value of 0.92, while modality importance analysis confirmed the dominant contribution of visual information. The experiments also showed stable model convergence and strong generalisation ability without significant overfitting. The proposed multimodal framework confirms the effectiveness of deep learning and cross-attention mechanisms for automated lesion identification and emergency medical triage. The developed approach can be applied in decision-support systems for rescue operations, emergency medicine, and intelligent VR/AR training simulators.
This research outlines a comprehensive dual-modality speech recognition system designed specifically to support hearing-impaired students in understanding spoken Kannada through synchronized processing of auditory signals and visual articulatory cues. The approach capitalizes on deep learning capabilities to improve performance to extract speech-related features from spectrograms and Mel-Frequency Cepstral Coefficients (MFCC) for audio, and lip movement discriminative features via CNNs and Temporal Convolutional Networks (TCNs) for visual input. A hybrid architecture, KanAVNet (Kannada Audio-Visual Network), based on a CNN–BiLSTM framework is integrated with a Connectionist Temporal Classification (CTC) loss function to enable robust sequence-to-sequence mapping while addressing temporal alignment challenges in audio-visual speech recognition. The system is fitted on a custom-developed Kannada audiovisual dataset, addressing the scarcity of regional-language AVSR resources. Empirical evidence shows that the model performs with a high degree of accuracy of 93.2%, a Word Error Rate (WER) of 9.8%, and an F1 score of 91.2%, outperforming baseline unimodal and existing multimodal models. This research highlights the effectiveness of multimodal fusion strategies in noisy environments and showcases the potential of AI-driven tools in promoting accessible and inclusive education for students with auditory impairments.
The article describes the theoretical foundations and software tools for scaling digital images by adaptive and combined application of bilinear and bicubic interpolation algorithms. An analysis of modern algorithms and image scaling tools has been performed. The theoretical foundations of image scaling using interpolation algorithms are described. The root mean square error between the pixel values of the original and scaled images was used as the scaling error. The scaling of images was performed by a complex of two interpolation algorithms. The first algorithm reduces the image scale, after which the second algorithm increases the scale. Such image processing is performed, in particular, in telecommunication systems for transmitting images at reduced scales. A correlation was found between the values of the average spatial period of the image and the relative scaling error, which is equal to the ratio of the scaling errors for different interpolation algorithms. The spatial period of the image was calculated based on its energy spectrum. A regression analysis was performed to determine the dependence of the relative scaling error on the spatial period of the images. It is found that in most cases bicubic interpolation provides a smaller scaling error, but for some images with small spatial period, bilinear interpolation provides a smaller error. It is proposed to increase the scaling accuracy by adaptively selecting the image interpolation algorithm depending on its spatial period. A combined application of interpolation algorithms was performed, which consists of reducing the scale using the bilinear interpolation algorithm and increasing the scale using the bicubic interpolation algorithm. A statistical analysis of the results of image scaling was performed. It was found that the combined application of algorithms in most cases provides a smaller error than the separate application of the bicubic and bilinear interpolation algorithms.
The water distribution sector in Indonesia still faces challenges in detecting leaks early due to manual data checks that are time-consuming and labor-intensive. PDAM (Regional Water Company) Tirta Wijaya Cilacap, Indonesia, faces similar problems. This study aims to implement a spatial customer prediction model to detect customer water usage and support data-driven operational decision-making. K-Means clustering groups customers by consumption patterns and geographic location, achieving a Silhouette Score of 0.4473 and a Davies–Bouldin Index of 0.7658, which indicates reasonably well-separated clusters in real-world data. In addition, water consumption forecasting was carried out with Seasonal–Trend Decomposition using Loess–Long Short-Term Memory (STL–LSTM) to predict trends and seasonality of water usage for each Customer Connection ID (CCID). The forecasting performance varies across CCIDs; the best case achieves an R2 of up to 0.95, while low-performing cases are discussed to clarify conditions where STL–LSTM is less reliable. The forecasting and clustering outputs are presented through a spatial visualization (map) of water-consumption categories and model results to support identifying areas that may require closer inspection for potential leakage and waste. This research contributes to strengthening technology-based public infrastructure, in line with SDG 9: Industry, Innovation, and Infrastructure, to promote sustainable water management.
Brain tumor detection and classification from MRI images is a challenging task. Early and accurate diagnosis are essential for selecting appropriate treatment plans and improving patient outcomes. Despite significant advances in deep learning for medical image recognition, comprehensive comparative analyses of brain tumor classification models, particularly regarding ensemble optimization, remain limited. This paper uses four state-of-the-art deep learning frameworks, namely EfficientNetB4, MobileNetV3, MobileNetV2, and EfficientNetB0, to classify brain MRI images into four categories: Glioma, Meningioma, Pituitary tumor, and Normal. It employs a two-phase transfer learning approach, followed by 5-fold cross-validation on 875 MRI images. A unified experimental framework is employed, incorporating a two-phase transfer learning approach, consistent preprocessing, and a rigorous evaluation protocol with 5-fold cross-validation and an independent test set to prevent data leakage. Both full and selective ensemble strategies are examined to improve the robustness and stability. The models are evaluated using accuracy, precision, recall, F-1 score, confusion matrices, and accuracy curves, and statistical validation using McNemar’s test. MobileNetV3 achieves the highest test accuracy of 98.76%, followed by EfficientNetB4 (97.89%) and EfficientNetB0 (93.48%). MobileNetV2 performs significantly worse, with an accuracy of less than 80%. The selective ensemble technique (which uses the best models) attains the highest accuracy of 92.97%, compared to the full ensemble (84.40%), which improves prediction robustness but does not surpass the best individual model in peak accuracy. Overall, it can be concluded that MobileNetV3 is the most suitable architecture for brain tumor classification, delivering high accuracy with minimal computational complexity. The selective ensemble approach also enhances performance, maintaining computational efficiency, emphasizing the importance of informed model selection in neuro-oncological image analysis and clinical decision-support systems.
