Search Results (28)

Background/Objectives: Artificial intelligence (AI) models for glaucoma screening using colour fundus photography have shown strong internal performance; however, their external validity and calibration reliability remain uncertain. This study developed a controlled four-dataset benchmark to evaluate six glaucoma-screening models across RIM-ONE, DRISHTI-GS, the Hillel Yaffe Glaucoma Dataset, and ORIGA. Methods: The evaluated models included a hybrid deep-handcrafted random forest (RF), transfer-learning and semi-supervised VGG16 models, and a compact convolutional neural network (CNN). Performance was assessed in within-dataset and cross-dataset settings using discrimination metrics, including accuracy, area under the receiver operating characteristic curve (AUC), balanced accuracy, and Matthews correlation coefficient (MCC), as well as calibration metrics, including Brier score and expected calibration error (ECE). Threshold stability, preprocessing ablation, and repeated-seed analyses were also performed. Results: Within-dataset evaluation showed strong discrimination, with the complete hybrid CNN + histogram of oriented gradients (HOG) + local binary patterns (LBP) + minimum redundancy maximum relevance (mRMR) + RF pipeline achieving a mean accuracy of 0.8697 and an AUC of 0.8972. However, cross-dataset performance was poor, with a mean accuracy of 0.5685 and an AUC of 0.5798. The denoising autoencoder-enhanced transfer-learning model showed improved probability calibration in transfer settings. Preprocessing effects were dataset-dependent, with raw images, region of interest (ROI) cropping, and Retinex normalisation producing different external performance patterns. Conclusions: High internal accuracy did not translate into reliable cross-domain generalisation. None of the evaluated models were suitable for zero-shot deployment without site-specific validation or recalibration. Full article

Multi-modal sentiment analysis integrates linguistic, acoustic, and visual evidence, yet the reliability of these streams varies across samples because of missing observations, masking, measurement noise, and feature corruption. This paper presents a trainable reliability-aware evidential fusion framework that estimates not only sentiment predictions but also modality-specific evidence, predictive uncertainty, observable input quality, cross-modal disagreement, and normalized sample-dependent fusion weights. Each available modality is independently encoded and processed by an evidential classification head and a quality estimation head. Availability masks enforce exact exclusion of missing streams, while estimated quality, Dirichlet uncertainty, and Jensen–Shannon disagreement jointly regulate the contribution of each observed stream. The model is optimized end-to-end using fused classification, evidential regularization, clean–corrupted consistency, reliability-calibrated cross-modal alignment, and quality regression objectives. Experiments are conducted on both CMU-MOSI and CMU-MOSEI using their official speaker-independent splits. Binary classification follows the standard non-zero protocol, in which samples with sentiment score zero are excluded from Acc-2 and binary F1 evaluation; all labeled samples are retained for seven-class accuracy, mean absolute error, and correlation. The evaluation covers complete-input, every single- and double-modality missing pattern, graded and unseen corruption, combined missing-plus-corrupted conditions, calibration, selective prediction, statistical testing, and computational efficiency. All comparative values in the main tables are identified as local controlled adaptations under the common pipeline, while selected published reference values are reported separately to prevent provenance mixing. Across both datasets, the empirical results show that the proposed method preserves competitive complete-input performance while providing larger and more consistent gains as modality availability or integrity deteriorates. Full article

Hyperdimensional computing (HDC) provides a highly efficient alternative to neural networks for intracranial electroencephalography (iEEG) seizure detection on edge devices with strict resource limits. While sparse HDC can significantly reduce energy use, current hardware fails to capitalize on this for two reasons. First, existing designs do not optimize the encoding architecture specifically for sparse execution, leaving potential energy savings on the table. Second, researchers often ignore the “area” problem, the large physical space high-dimensional vectors take up on a chip, which must be solved to make these devices small enough for practical edge use. This work presents a sparse HDC accelerator that bridges these gaps through three key contributions. First, we streamline the sparse encoding architecture to improve energy and area efficiency by integrating a compressed item memory (CompIM) and simplified spatial bundling. Second, to address the area bottleneck and enable true edge deployment, we systematically explore area trade-offs via sequentialization techniques, evaluating both channel folding (CF) and vector folding (VF). Third, we push efficiency even further by proposing an item-memory-free (IM-free) architecture. By replacing the baseline segmented shift binding with a standard shift binding scheme, and gracefully utilizing raw local binary pattern (LBP) codes directly as shift amounts, we completely bypass the CompIM for simultaneous area and energy savings. However, this optimization incurs a drop in detection accuracy; hence, we ultimately present two tailored configurations. First, our energy-optimized IM-free design achieves a 5.55× area and 3.08× energy improvement over the sparse HDC baseline, alongside 8.20× and 13.37× improvements over the dense baseline. Second, to prioritize clinical performance, our balanced streamlined design utilizes a channel folding factor (CFF) of 4 to preserve higher accuracy. This balanced approach achieves a 5.97× area and a 4.66× energy improvement over the dense baseline, with a 4× latency increase. Full article

Texture feature extraction plays a crucial role in land-use and land-cover (LULC) classification for the remotely sensed images. However, when these images are quantized to a limited number of gray levels to reduce data volume or noise, conventional texture descriptors often lose discriminative power. This study investigates singular values of the gray-level co-occurrence matrix (GLCM) as novel texture features for image classification, with local binary pattern (LBP), complete LBP (CLBP) statistics, and original GLCM features proposed by Haralick et al. for comparison. Under coarse quantization, texture descriptors of LBP and its variants, which encode micro-texture, lose detail, whereas GLCM, which encodes macro-texture, retains structural co-occurrence patterns. This study thus proposes a new feature set, namely the Singular Values of the gray-level co-occurrence matrix (SVGM), for texture discrimination. Experimental analysis indicates SVGM achieves higher class separability by preserving dominant spatial structure while suppressing noise and redundancy. Quantitative evaluation using classical SVMs with multiple kernels, quantum learning models with different kernels, and neural baselines (ANN and 1D-CNN) further shows that SVGM consistently improves classification performance. Within our tested models, quantum kernel SVMs are competitive and achieve the best results on some datasets, while classical models perform best on others. Full article

The contemporary challenge in remote sensing lies in the precise retrieval of increasingly abundant and high-resolution remotely sensed images (RS image) stored in expansive data warehouses. The heightened spatial and spectral resolutions, coupled with accelerated image acquisition rates, necessitate advanced tools for effective data management, retrieval, and exploitation. The classification of large-sized images at the pixel level generates substantial data, escalating the workload and search space for similarity measurement. Semantic-based image retrieval remains an open problem due to limitations in current artificial intelligence techniques. Furthermore, on-board storage constraints compel the application of numerous compression algorithms to reduce storage space, intensifying the difficulty of retrieving substantial, sensitive, and target-specific data. This research proposes an innovative hybrid approach to enhance the retrieval of remotely sensed images. The approach leverages multilevel classification and multiscale feature extraction strategies to enhance performance. The retrieval system comprises two primary phases: database building and retrieval. Initially, the proposed Multiscale Multiangle Mean-shift with Breaking Ties (MSMA-MSBT) algorithm selects informative unlabeled samples for hyperspectral and synthetic aperture radar images through an active learning strategy. Addressing the scaling and rotation variations in image capture, a flexible and dynamic algorithm, modified Deep Image Registration using Dynamic Inlier (IRDI), is introduced for image registration. Given the complexity of remote sensing images, feature extraction occurs at two levels. Low-level features are extracted using the modified Multiscale Multiangle Completed Local Binary Pattern (MSMA-CLBP) algorithm to capture local contexture features, while high-level features are obtained through a hybrid CNN structure combining pretrained networks (Alexnet, Caffenet, VGG-S, VGG-M, VGG-F, VGG-VDD-16, VGG-VDD-19) and a fully connected dense network. Fusion of low- and high-level features facilitates final class distinction, with soft thresholding mitigating misclassification issues. A region-based similarity measurement enhances matching percentages. Results, evaluated on high-resolution remote sensing datasets, demonstrate the effectiveness of the proposed method, outperforming traditional algorithms with an average accuracy of 86.66%. The hybrid retrieval system exhibits substantial improvements in classification accuracy, similarity measurement, and computational efficiency compared to state-of-the-art scene classification and retrieval methods. Full article

Recognition of Bengali handwritten digits has several unique challenges, including the variation in writing styles, the different shapes and sizes of digits, the varying levels of noise, and the distortion in the images. Despite significant improvements, there is still room for further improvement in the recognition rate. By building datasets and developing models, researchers can advance state-of-the-art support, which can have important implications for various domains. In this paper, we introduce a new dataset of 5440 handwritten Bengali digit images acquired from a Bangladeshi University that is now publicly available. Both conventional machine learning and CNN models were used to evaluate the task. To begin, we scrutinized the results of the ML model used after integrating three image feature descriptors, namely Binary Pattern (LBP), Complete Local Binary Pattern (CLBP), and Histogram of Oriented Gradients (HOG), using principal component analysis (PCA), which explained 95% of the variation in these descriptors. Then, via a fine-tuning approach, we designed three customized CNN models and their stack to recognize Bengali handwritten digits. On handcrafted image features, the XGBoost classifier achieved the best accuracy at 85.29%, an ROC AUC score of 98.67%, and precision, recall, and F1 scores ranging from 85.08% to 85.18%, indicating that there was still room for improvement. On our own data, the proposed customized CNN models and their stack model surpassed all other models, reaching a 99.66% training accuracy and a 97.57% testing accuracy. In addition, to robustify our proposed CNN model, we used another dataset of Bengali handwritten digits obtained from the Kaggle repository. Our stack CNN model provided remarkable performance. It obtained a training accuracy of 99.26% and an almost equally remarkable testing accuracy of 96.14%. Without any rigorous image preprocessing, fewer epochs, and less computation time, our proposed CNN model performed the best and proved the most resilient throughout all of the datasets, which solidified its position at the forefront of the field. Full article

The deep learning method has achieved great success in hyperspectral image classification, but the lack of labeled training samples still restricts the development and application of deep learning methods. In order to deal with the problem of small samples in hyperspectral image classification, a novel small sample classification method based on rotation-invariant uniform local binary pattern (RULBP) features and a graph-based masked autoencoder is proposed in this paper. Firstly, the RULBP features of hyperspectral images are extracted, and then the k-nearest neighbor method is utilized to construct the graph. Furthermore, self-supervised learning is conducted on the constructed graph so that the model can learn to extract features more suitable for small sample classification. Since the self-supervised training mainly adopts the masked autoencoder method, only unlabeled samples are needed to complete the training. After training, only a small number of samples are used to fine-tune the graph convolutional network, so as to complete the classification of all nodes in the graph. A large number of classification experiments on three commonly used hyperspectral image datasets show that the proposed method could achieve higher classification accuracy with fewer labeled samples. Full article

In the paper, we introduce a new model that addresses the generation of quantum droplets (QDs) in the binary Bose–Einstein condensate (BEC) mixture with mutually symmetric spinor components loaded in multi-color optical lattices (MOLs) of commensurate wavelengths and tunable intensities. The considered MOL confinement is the combination of the four-color optical lattice with an exponential periodic trap, which includes the complete set of the Fourier harmonics. Employing the one-dimensional (1D) extended Gross–Pitäevskii equation (eGPE), we calculate the exact analytical form of the wavefunction, MF/BMF nonlinearities, and MOL trap parameters. Utilizing the exact solutions, the formation of supersolid-like spatially periodic matter-wave droplet lattices and superlattices is illustrated under the space-periodic nonlinearity management. The precise positioning of the density maxima/minima of the droplet patterns at the center of the trap and tunable Anderson-like localization are observed by tuning the symmetry and amplitude of the considered MOL trap. The stability of the obtained solution is confirmed using the Vakhitov–Kolokolov (VK) criterion. Full article

In this paper, an algorithm based on local binary pattern (LBP) is proposed to obtain clear remote sensing images under the premise of unknown causes of blurring. We find that LBP can completely record the texture features of the images, which will not change widely due to the generation of blur. Therefore, LBP prior is proposed, which can filter out the pixels containing important textures in the blurry image through the mapping relationship. The corresponding processing methods are adopted for different types of pixels to cope with the challenges brought by the rich texture and details of remote sensing images and prevent over-sharpening. However, the existence of LBP prior increases the difficulty of solving the model. To solve the model, we construct the projected alternating minimization (PAM) algorithm that involves the construction of the mapping matrix, the fast iterative shrinkage-thresholding algorithm (FISTA) and the half-quadratic splitting method. Experiments with the AID dataset show that the proposed method can achieve highly competitive processing results for remote sensing images. Full article

Glaucoma is one of the eye diseases stimulated by the fluid pressure that increases in the eyes, damaging the optic nerves and causing partial or complete vision loss. As Glaucoma appears in later stages and it is a slow disease, detailed screening and detection of the retinal images is required to avoid vision forfeiture. This study aims to detect glaucoma at early stages with the help of deep learning-based feature extraction. Retinal fundus images are utilized for the training and testing of our proposed model. In the first step, images are pre-processed, before the region of interest (ROI) is extracted employing segmentation. Then, features of the optic disc (OD) are extracted from the images containing optic cup (OC) utilizing the hybrid features descriptors, i.e., convolutional neural network (CNN), local binary patterns (LBP), histogram of oriented gradients (HOG), and speeded up robust features (SURF). Moreover, low-level features are extracted using HOG, whereas texture features are extracted using the LBP and SURF descriptors. Furthermore, high-level features are computed using CNN. Additionally, we have employed a feature selection and ranking technique, i.e., the MR-MR method, to select the most representative features. In the end, multi-class classifiers, i.e., support vector machine (SVM), random forest (RF), and K-nearest neighbor (KNN), are employed for the classification of fundus images as healthy or diseased. To assess the performance of the proposed system, various experiments have been performed using combinations of the aforementioned algorithms that show the proposed model based on the RF algorithm with HOG, CNN, LBP, and SURF feature descriptors, providing ≤99% accuracy on benchmark datasets and 98.8% on k-fold cross-validation for the early detection of glaucoma. Full article

Renewable Energy Sources provide a viable solution to the problem of ever-increasing climate change. For this reason, several countries focus on electricity production using alternative sources. In this paper, the optimal positioning of the installation of wave energy converters is examined taking into account geospatial and technical limitations. Geospatial constraints depend on Land Use classes and seagrass of the coastal areas, while technical limitations include meteorological conditions and the morphology of the seabed. Suitable installation areas are selected after the exclusion of points that do not meet the aforementioned restrictions. We implemented a Deep Neural Network that operates based on heterogeneous data fusion, in this case satellite images and time series of meteorological data. This fact implies the definition of a two-branches architecture. The branch that is trained with image data provides for the localization of dynamic geospatial classes in the potential installation area, whereas the second one is responsible for the classification of the region according to the potential wave energy using wave height and period time series. In making the final decision on the suitability of the potential area, a large number of static land use data play an important role. These data are combined with neural network predictions for the optimizing positioning of the Wave Energy Converters. For the sake of completeness and flexibility, a Multi-Task Neural Network is developed. This model, in addition to predicting the suitability of an area depending on seagrass patterns and wave energy, also predicts land use classes through Multi-Label classification process. The proposed methodology is applied in the marine area of the city of Sines, Portugal. The first neural network achieves 98.7% Binary Classification accuracy, while the Multi-Task Neural Network 97.5% in the same metric and 93.5% in the F1 score of the Multi-Label classification output. Full article

Coral reefs are the sub-aqueous calcium carbonate structures collected by the invertebrates known as corals. The charm and beauty of coral reefs attract tourists, and they play a vital role in preserving biodiversity, ceasing coastal erosion, and promoting business trade. However, they are declining because of over-exploitation, damaging fishery, marine pollution, and global climate changes. Also, coral reefs help treat human immune-deficiency virus (HIV), heart disease, and coastal erosion. The corals of Australia’s great barrier reef have started bleaching due to the ocean acidification, and global warming, which is an alarming threat to the earth’s ecosystem. Many techniques have been developed to address such issues. However, each method has a limitation due to the low resolution of images, diverse weather conditions, etc. In this paper, we propose a bag of features (BoF) based approach that can detect and localize the bleached corals before the safety measures are applied. The dataset contains images of bleached and unbleached corals, and various kernels are used to support the vector machine so that extracted features can be classified. The accuracy of handcrafted descriptors and deep convolutional neural networks is analyzed and provided in detail with comparison to the current method. Various handcrafted descriptors like local binary pattern, a histogram of an oriented gradient, locally encoded transform feature histogram, gray level co-occurrence matrix, and completed joint scale local binary pattern are used for feature extraction. Specific deep convolutional neural networks such as AlexNet, GoogLeNet, VGG-19, ResNet-50, Inception v3, and CoralNet are being used for feature extraction. From experimental analysis and results, the proposed technique outperforms in comparison to the current state-of-the-art methods. The proposed technique achieves 99.08% accuracy with a classification error of 0.92%. A novel bleached coral positioning algorithm is also proposed to locate bleached corals in the coral reef images. Full article

While there has been a massive increase in research into face recognition, it remains a challenging problem due to conditions present in real life. This paper focuses on the inherently present issue of partial occlusion distortions in real face recognition applications. We propose an approach to tackle this problem. First, face images are divided into multiple patches before local descriptors of Local Binary Patterns and Histograms of Oriented Gradients are applied on each patch. Next, the resulting histograms are concatenated, and their dimensionality is then reduced using Kernel Principle Component Analysis. Once completed, patches are randomly selected using the concept of random sampling to finally construct several sub-Support Vector Machine classifiers. The results obtained from these sub-classifiers are combined to generate the final recognition outcome. Experimental results based on the AR face database and the Extended Yale B database show the effectiveness of our proposed technique. Full article

A shoeprint is a valuable clue found at a crime scene and plays a significant role in forensic investigations. In this paper, in order to maintain the local features of a shoeprint image and place a pattern in a block, a novel automatic method was proposed, referred to as Modified Multi-Block Local Binary Pattern (MMB-LBP). In this method, shoeprint images are divided into blocks according to two different models. The histograms of all blocks of the first and second models are separately measured and stored in the first and second feature matrices, respectively. The performance evaluations of the proposed method were carried out by comparing with state-of-the-art methods. The evaluation criteria are the successful retrieval rates obtained using the best match score at rank one and cumulative match score for the first five matches. The comparison results indicated that the proposed method performs better than other methods, in terms of retrieval of complete and incomplete shoeprints. That is, the proposed method was able to retrieve 97.63% of complete shoeprints, 96.5% of incomplete toe shoeprints, and 91.18% of incomplete heel shoeprints. Moreover, the experiments showed that the proposed method is significantly resistant to the rotation, salt and pepper noise, and Gaussian white noise distortions in comparison with the other methods. Full article

Urban vegetation can regulate ecological balance, reduce the influence of urban heat islands, and improve human beings’ mental state. Accordingly, classification of urban vegetation types plays a significant role in urban vegetation research. This paper presents various window sizes of completed local binary pattern (CLBP) texture features classifying urban vegetation based on high spatial-resolution WorldView-2 images in areas of Shanghai (China) and Lianyungang (Jiangsu province, China). To demonstrate the stability and universality of different CLBP window textures, two study areas were selected. Using spectral information alone and spectral information combined with texture information, imagery is classified using random forest (RF) method based on vegetation type, showing that use of spectral information with CLBP window textures can achieve 7.28% greater accuracy than use of only spectral information for urban vegetation type classification, with accuracy greater for single vegetation types than for mixed ones. Optimal window sizes of CLBP textures for grass, shrub, arbor, shrub-grass, arbor-grass, and arbor-shrub-grass are 3 × 3, 3 × 3, 11 × 11, 9 × 9, 9 × 9, 7 × 7 for urban vegetation type classification. Furthermore, optimal CLBP window size is determined by the roughness of vegetation texture. Full article