An Enhanced Semi-Supervised Support Vector Machine Algorithm for Spectral-Spatial Hyperspectral Image Classification

Effective urban planning and management rely on accurate land cover mapping, which can be achieved through the combination of remote sensing data and machine learning algorithms. This study aimed to explore and demonstrate the potential benefits of integrating Sentinel-1 SAR and Sentinel-2 MSI satellite imagery for urban land cover classification in Gondar city, Ethiopia. Synthetic Aperture Radar (SAR) data from Sentinel-1A and Multispectral Instrument (MSI) data from Sentinel-2B for the year 2023 were utilized for this research work. Support Vector Machine (SVM) and Random Forest (RF) machine learning algorithms were utilized for the classification process. Google Earth Engine (GEE) was used for the processing, classification, and validation of the remote sensing data. The findings of the research provided valuable insights into the performance evaluation of the Support Vector Machine (SVM) and Random Forest (RF) algorithms for image classification using different datasets, namely Sentinel 2B Multispectral Instrument (MSI) and Sentinel 1A Synthetic Aperture Radar (SAR) data. When applied to the Sentinel 2B MSI dataset, both SVM and RF achieved an overall accuracy (OA) of 0.69, with a moderate level of agreement indicated by the Kappa score of 0.357. For the Sentinel 1A SAR data, SVM maintained the same OA of 0.69 but showed an improved Kappa score of 0.67, indicating its suitability for SAR image classification. In contrast, RF achieved a slightly lower OA of 0.66 with Sentinel 1A SAR data. However, when the datasets of Sentinel 2B MSI and Sentinel 1A SAR were combined, SVM achieved an impressive OA of 0.91 with a high Kappa score of 0.80, while RF achieved an OA of 0.81 with a Kappa score of 0.809. These findings highlight the potential of fusing satellite data from multiple sources to enhance the accuracy and effectiveness of image classification algorithms, making them valuable tools for various applications, including land use mapping and environmental monitoring.

The support vector machine (SVM) has been a dominant machine-learning technique in the last decade and has demonstrated its efficiency in many applications. Research on classification of hyperspectral images have shown the efficiency of this method to overcome the Hughes phenomenon for classification of such images. A major drawback of classification by SVM is that this classifier was originally developed to solve binary problems, and the algorithms for multiclass problems usually have a high-computational load. In this article, a new and fast method for multiclass problems is proposed. This method has two stages. In the first stage, samples are classified by a maximum likelihood (ML) classifier, and in the second stage, SVM selects the final label of a sample among high-probability classes for that sample by a tree structure. So, for each sample, only some classes must be searched by SVM to find its label. The uncertainty of ML classification for a sample is obtained by the entropy of probabilities, and the number of classes that must be searched by SVM for a sample is obtained based on the uncertainty of that sample in the primary ML classification. This approach is compared with two widely used multiclass algorithms: one-against-one (OAO) and directed acyclic graph (DAGSVM). The obtained results on real data from the Airborne Visible/Infrared Imaging Spectrometer (AVIRIS) revealed less computational time and better accuracy compared to these multiclass algorithms.

This paper presents a simulation method of hyper-spectral dynamic scene and image sequence for hyper-spectral equipment evaluation and target detection algorithm. Because of high spectral resolution, strong band continuity, anti-interference and other advantages, in recent years, hyper-spectral imaging technology has been rapidly developed and is widely used in many areas such as optoelectronic target detection, military defense and remote sensing systems. Digital imaging simulation, as a crucial part of hardware in loop simulation, can be applied to testing and evaluation hyper-spectral imaging equipment with lower development cost and shorter development period. Meanwhile, visual simulation can produce a lot of original image data under various conditions for hyper-spectral image feature extraction and classification algorithm. Based on radiation physic model and material characteristic parameters this paper proposes a generation method of digital scene. By building multiple sensor models under different bands and different bandwidths, hyper-spectral scenes in visible, MWIR, LWIR band, with spectral resolution 0.01μm, 0.05μm and 0.1μm have been simulated in this paper. The final dynamic scenes have high real-time and realistic, with frequency up to 100 HZ. By means of saving all the scene gray data in the same viewpoint image sequence is obtained. The analysis results show whether in the infrared band or the visible band, the grayscale variations of simulated hyper-spectral images are consistent with the theoretical analysis results.

AN ASSESSMENT OF SPATIAL VARIATION OF LAND SURFACE CHARACTERISTICS OF MINNA, NIGER STATE NIGERIA FOR SUSTAINABLE URBANIZATION USING GEOSPATIAL TECHNIQUES

Image classification is critical in computer vision, with numerous applications ranging from e-commerce to medical imaging. This study provides a comprehensive evaluation of traditional machine learning algorithms for image classification, implementing and analysing novel fault tolerance mechanisms amongst these algorithms. The authors compared the performance of K-Nearest Neighbors (KNN), Decision Trees, Random Forest, and XGBoost on both Fashion MNIST and CIFAR-10 datasets. The comparison was extended to include Support Vector Machine (SVM), Logistic Regression, and Naive Bayes classifiers in order to expand the evaluation of these models on the indicated datasets. Key findings demonstrated the superiority of ensemble methods, particularly XGBoost, which achieved 89.31% of accuracy on Fashion MNIST and 54.93% on CIFAR-10, consistently outperforming other models across various configurations. Random Forest exhibited robust performance as the secondbest model, reaching 87.42% and 51.64% of accuracy on the respective datasets. The significant performance gap between datasets demonstrated the challenges that traditional machine learning models face with complex image data. Implementing the fault tolerance framework in this study has also shown a remarkable effectiveness, achieved a 94.6% recovery rate while maintaining model accuracy within 0.1% of standard implementations. This was achieved with minimal computational overhead (2.3% of training time and 1.8% of memory usage), making it highly practical for production deployments. The system significantly reduced operational failures, decreasing crashes from 5.2 to 0.3 per day and increasing average uptime from 4.3 to 12.0 hours. The study also reveals important insights regarding model scalability and resource requirements, with memory usage varying significantly across models (325MB to 8,923MB). These findings provide valuable guidance for practitioners in selecting and implementing machine learning models for image classification tasks, particularly in scenarios where both performance and system reliability are critical. This research contributes to the field by demonstrating the feasibility of implementing robust fault tolerance in machine learning systems without compromising accuracy while also providing comprehensive performance comparisons across different model architectures and dataset complexities. The developed framework serves as a foundation for building more reliable machine-learning systems for real-world applications.

In this research, a new method for spectral-spatial classification of hyperspectral images based on hierarchical segmentation algorithm is introduced. Among the various spectral-spatial classification algorithms, the marker-based hierarchical segmentation algorithm has so far achieved the best results in combination with the support vector machine (SVM) classification algorithm. In the proposed method adopted in this research, the dimensions of the hyperspectral image were reduced via the minimum noise fraction (MNF) algorithm. Then, five spatial/texture features of wavelet transform, Gabor transform, mean, entropy, and contrast were extracted from the obtained bands. Later on, the multi-layer perceptron (MLP) neural network and SVM classification algorithms were applied to the obtained spectral and texture features, and their results were combined. The resulting map was then used to select the markers and to combine them with the marker-based hierarchical segmentation algorithm using the majority voting rule. The proposed method was applied to three hyperspectral images, Pavia, Telops, and Washington DC Mall. The results of the experiments demonstrate the superiority of the proposed method over the initial marker-based hierarchical algorithm. Quantitatively, it was better by 8, 12, and 9% for the Pavia, Telops, and Washington DC Mall datasets regarding the Kappa coefficient parameter, respectively.

Diabetic Retinopathy (DR) is a microangiopathic complication of diabetes mellitus that can cause visual impairment to permanent blindness. Early detection of DR is essential to prevent disease progression, but conventional methods require time, cost, and expertise that are not always available. This study aims to compare the performance of the Random Forest (RF) and Support Vector Machine (SVM) algorithms in DR classification based on texture features extracted from retinal fundus images. The dataset used consists of 3,000 retinal fundus images obtained from the Kaggle platform, divided into 2,400 training data and 600 test data. Image preprocessing includes conversion to grayscale, resizing to a resolution of 128×128 pixels, and normalization. Feature extraction is performed using a combination of Local Binary Pattern (LBP) and Gray Level Co-occurrence Matrix (GLCM) to produce a 14-dimensional feature vector. Performance evaluation uses accuracy, precision, recall, F1-score, ROC curve, and 5-fold cross-validation metrics. The results showed that Random Forest significantly outperformed SVM with an accuracy of 96% compared to 64%, an AUC value of 0.99 compared to 0.72, and an average cross-validation accuracy of 94.5% compared to 63.42%. Random Forest also showed balanced performance in both classes with precision, recall, and F1-score of 0.96, while SVM experienced classification imbalance especially in the disease class. This study proves that Random Forest is a more optimal algorithm for an automatic DR detection system based on fundus image texture features and can support increasing the accessibility of DR screening in areas with limited specialist medical personnel.

Attention mechanism-based Hyperspectral Image (HSI) classification algorithms typically extract spectral and spatial features by spectral attention and spatial attention network respectively. However, these algorithms lack joint attention and ignore imbalanced samples, leading to insufficient information extraction. To address this problem, this paper proposes a novel HSI classification algorithm based on the pyramidal coordinate attention and weighted self-distillation (PCA-WSD). To perform the joint attention of spectral and spatial features, the proposed PCA mechanism uses spectral attention to cope with the diverse spatial features. The PCA mechanism consists of two components. First, the spatial pyramid coordinate squeeze (SPCS) is designed to aggregate spatial features with local and global information. Then, the tailored spatial pyramid coordinate excitation (SPCE) adaptively enhances their informative spectral features for the obtained spatial features, realizing the joint attention to spectral-spatial features. Further, considering the imbalance of samples, WSD is proposed. Specifically, weighted cross-entropy is integrated into WSD. Extensive experiments are evaluated on the four HSI benchmark datasets: Indian Pine (IP), Pavia University (UP), Kennedy Space Center (KSC), and Pavia Center (PC). Compared with the seven advanced algorithms, experimental results of the proposed algorithm <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">1</sup> . reveal superior classification performance, especially for the imbalanced samples.

A novel dynamic classifier ensemble (DSE) algorithm for hyperspectral image classification is proposed. In this method, both spatial and spectral information is used to determine a pixel's label once the remaining classified pixels' neighborhood meets the threshold. The experimental results show that the DSE-based classification algorithm can provide the better performance for hyperspectral image classification, and the integration of spectral information with textural features can improve the classification performance for hyperspectral images.

To overcome the difficulty of automating and intelligently classifying the ground features in remote-sensing hyperspectral images, machine learning methods are gradually introduced into the process of remote-sensing imaging. First, the PaviaU, Botswana, and Cuprite hyperspectral datasets are selected as research subjects in this study, and the objective is to process remote-sensing hyperspectral images via machine learning to realize the automatic and intelligent classification of features. Then, the basic principles of the support vector machine (SVM) and extreme learning machine (ELM) classification algorithms are introduced, and they are applied to the datasets. Next, by adjusting the parameter estimates using a restricted Boltzmann machine (RBM), a new terrain classification model of hyperspectral images that is based on a deep belief network (DBN) is constructed. Next, the SVM, ELM, and DBN classification algorithms for hyperspectral image terrain classification are analysed and compared in terms of accuracy and consistency. The results demonstrate that the average detection accuracies of ELM on the three datasets are 89.54%, 96.14%, and 96.28%, and the Kappa coefficient values are 0.832, 0.963, and 0.924; the average detection accuracies of SVM are 88.90%, 92.11%, and 91.68%, and the Kappa coefficient values are 0.768, 0.913, and 0.944; the average detection accuracies of the DBN classification model are 92.36%, 97.31%, and 98.84%, and the Kappa coefficient values are 0.883, 0.944, and 0.972. The results also demonstrate that the classification accuracy of the DBN algorithm exceeds those of the previous two methods because it fully utilizes the spatial and spectral information of hyperspectral remote-sensing images. In summary, the DBN algorithm that is proposed in this study has high application value in object classification for remote-sensing hyperspectral images.

Hyperspectral images captured by airborne sensors provide huge information about earth cover. Human eye can see reflectance from limited wavelengths whereas hyperspectral images contain more than 200 bands captured in visible and infrared region of light. Classification is one of the methods used to analyse this information for decision making. Several techniques are available in the literature for supervised, unsupervised, and semi-supervised classification of hyperspectral images. Training samples for supervised classification are generated by ground sample collection from the actual site captured in the image. These training samples play an important role in classification and can greatly influence classification accuracy. In recent research, for selecting training samples ‘pixel purity’ based new methods were developed. However, in some cases, it might not be possible to gather ground truth of selected pixel. This paper advocate for a novel method inspired by Ant Colony System for selection of a subset from already developed training samples to achieve better classification results. It is interesting to see that a small subset of existing training samples achieve equivalent or in some cases better accuracy when compared to the use of all available training samples.

Medical image classification is an essential task in the fields of computer-aided diagnosis and medical image analysis. In recent years, researchers have made extensive work on medical image classification by computer vision techniques. However, most of the current work is based on deep learning methods, which still suffer from expensive hardware resources, long time consuming and a lot of parameters to be optimized. In this paper, a multi-granularity ensemble algorithm for medical image classification based on broad learning system is proposed, which is an end-to-end lightweight model. On the one hand, the proposed method is designed to address the problem of weak image feature learning ability of broad learning system. The convolution module with fixed weights based on transfer learning is introduced as a feature extractor to extract fusion features of medical images. On the other hand, the multi-granularity ensemble framework is proposed, which learn the fusion features of medical images from fine-grained to coarse-grained respectively, and the prediction results at different granularity levels are integrated by ensemble learning. In this way, the bottom local features can be sufficiently considered, while the global features can also be taken into account. The experimental results show that on the MedMNIST dataset (containing 10 sub-datasets), the proposed method can shorten the training time by tens of times while having similar accuracy to deep convolutional neural networks. On the ChestXRay2017 dataset, the proposed method can achieve an accuracy of 92.5%, and the training time is also significantly better than other methods.

Nowadays, the information processing capabilities and resource storage capabilities of computers have been greatly improved, which also provides support for the neural network technology. Convolutional neural networks have good characterization capabilities in computer vision tasks, such as image recognition technology. Aiming at the problem of high similarity image recognition and classification in a specific field, this paper proposes a high similarity image recognition and classification algorithm fused with convolutional neural networks. First, we extract the image texture features, train different types, and different resolution image sets and determine the optimal texture different parameter values. Second, we decompose the image into subimages according to the texture difference, extract the energy features of each subimage, and perform classification. Then, the input image feature vector is converted into a one-dimensional vector through the alternating 5-layer convolution and 3-layer pooling of convolutional neural networks. On this basis, different sizes of convolution kernels are used to extract different convolutions of the image features, and then use convolution to achieve the feature fusion of different dimensional convolutions. Finally, through the increase in the number of training and the increase in the amount of data, the network parameters are continuously optimized to improve the classification accuracy in the training set and in the test set. The actual accuracy of the weights is verified, and the convolutional neural network model with the highest classification accuracy is obtained. In the experiment, two image data sets of gems and apples are selected as the experimental data to classify and identify gems and determine the origin of apples. The experimental results show that the average identification accuracy of the algorithm is more than 90%.

Cassava cultivation is important to the nation because of the products and raw materials that are supplied to industries. However, Its cultivation is affected by diseases such as cassava brown leaf and cassava mosaic, which have been classified using a Support Vector Machine (SVM). SqueezeNet pretrained Convolutional Neural Network (SPCNN) is adjudged a very effective image detection and classification algorithm with limited usage areas. This research, therefore was used to detect and classify cassava leaf diseases using SPCNN and SPCNN with multiclass SVM. Performance evaluation of both techniques showed that SPCNN effectively detected and classified cassava leaf diseases with optimal accuracies of 92.22% and 98.89% for SPCNN and SPCNN-SVM, respectively. Keywords- SqueezeNet, SVM, Cassava diseases, Feature extraction, Transfer learning Arinola I. O., Oke O. A. &amp; Falohun A. S. (2026): Detection and Classification of Cassava Leaf Diseases using Squeezenet Pretrained Convolutional Neural Network and Support Vector Machine. Journal of Advances in Mathematical &amp; Computational Science. Vol. 14, No. 1. Pp 1-12 Available online at www.isteams.net/mathematics-computationaljournal. dx.doi.org/10.22624/AIMS/MATHS/V14N1P1

Adaptive training is critical for image classification by artificial neural networks (ANNS). While the machine learning community has been enthusiastic in developing various training algorithms, little research has been conducted to evaluate the performance of these algorithms in image classification by neural networks. We introduce and evaluate nine commonly-used training algorithms in terms of their performance in land-cover classification from remotely sensed data by the multi-layer-perceptron (MLP) neural networks. ALP has been considered as the most popular neural network architecture. The training algorithms we consider are Steepest Gradient Descent, Gradient Descent with Momentum, Resilient Propagation, Fletcher-Reeves, Polak-Ribiere, Powell-Beale, Scaled Conjugate Gradient, BFGS (Broyden, Fletcher, Goldfarb, and Shanno), and Levenberg-Marquardt. We use each algorithm to train the MLP networks multiple times using identical training samples, and then apply each of the resultant network models to derive land-cover information from a Landsat Enhanced Thematic Mapper Plus (ETM+) image. The training algorithms are further evaluated according to their training efficiency, capability of convergence, classification accuracy, and stability of the classification accuracy. It is found that the performance of these algorithms varies substantially and selecting an appropriate algorithm can lead to a fast and efficient training and an increase in land-cover classification accuracy by artificial neural networks.