Search Results (9)

Accurate urban land cover information is crucial for effective urban planning and management. While convolutional neural networks (CNNs) demonstrate superior feature learning and prediction capabilities using image-level annotations, the inherent mixed-category nature of input image patches leads to classification errors along object boundaries. Fully convolutional neural networks (FCNs) excel at pixel-wise fine segmentation, making them less susceptible to heterogeneous content, but they require fully annotated dense image patches, which may not be readily available in real-world scenarios. This paper proposes an object-based semi-supervised spatial attention residual UNet (OS-ARU) model. First, multiscale segmentation is performed to obtain segments from a remote sensing image, and segments containing sample points are assigned the categories of the corresponding points, which are used to train the model. Then, the trained model predicts class probabilities for all segments. Each unlabeled segment’s probability distribution is compared against those of labeled segments for similarity matching under a threshold constraint. Through label propagation, pseudo-labels are assigned to unlabeled segments exhibiting high similarity to labeled ones. Finally, the model is retrained using the augmented training set incorporating the pseudo-labeled segments. Comprehensive experiments on aerial image benchmarks for Vaihingen and Potsdam demonstrate that the proposed OS-ARU achieves higher classification accuracy than state-of-the-art models, including OCNN, 2OCNN, and standard OS-U, reaching an overall accuracy (OA) of 87.83% and 86.71%, respectively. The performance improvements over the baseline methods are statistically significant according to the Wilcoxon Signed-Rank Test. Despite using significantly fewer sparse annotations, this semi-supervised approach still achieves comparable accuracy to the same model under full supervision. The proposed method thus makes a step forward in substantially alleviating the heavy sampling burden of FCNs (densely sampled deep learning models) to effectively handle the complex issue of land cover information identification and classification. Full article

Imbalance classification is common in scenarios like fault diagnosis, intrusion detection, and medical diagnosis, where obtaining abnormal data is difficult. This article addresses a one-class problem, implementing and refining the One-Class Nearest-Neighbor (OCNN) algorithm. The original inter-quartile range mechanism is replaced with the K-means with outlier removal (KMOR) algorithm for efficient outlier identification in the target class. Parameters are optimized by treating these outliers as non-target-class samples. A new algorithm, the Location-based Nearest-Neighbor (LBNN) algorithm, clusters one-class training data using KMOR and calculates the farthest distance and percentile for each test data point to determine if it belongs to the target class. Experiments cover parameter studies, validation on eight standard imbalanced datasets from KEEL, and three applications on real medical imbalanced datasets. Results show superior performance in precision, recall, and G-means compared to traditional classification models, making it effective for handling imbalanced data challenges. Full article

Accurate classification of forest stand is crucial for protection and management needs. However, forest stand classification remains a great challenge because of the high spectral and textural similarity of different tree species. Although existing studies have used multiple remote sensing data for forest identification, the effects of different spatial resolutions and combining multi-source remote sensing data for automatic complex forest stand identification using deep learning methods still require further exploration. Therefore, this study proposed an object-oriented convolutional neural network (OCNN) classification method, leveraging data from Sentinel-2, RapidEye, and LiDAR to explore classification accuracy of using OCNN to identify complex forest stands. The two red edge bands of Sentinel-2 were fused with RapidEye, and canopy height information provided by LiDAR point cloud was added. The results showed that increasing the red edge bands and canopy height information were effective in improving forest stand classification accuracy, and OCNN performed better in feature extraction than traditional object-oriented classification methods, including SVM, DTC, MLC, and KNN. The evaluation indicators show that ResNet_18 convolutional neural network model in the OCNN performed the best, with a forest stand classification accuracy of up to 85.68%. Full article

Industrial automation systems are undergoing a revolutionary change with the use of Internet-connected operating equipment and the adoption of cutting-edge advanced technology such as AI, IoT, cloud computing, and deep learning within business organizations. These innovative and additional solutions are facilitating Industry 4.0. However, the emergence of these technological advances and the quality solutions that they enable will also introduce unique security challenges whose consequence needs to be identified. This research presents a hybrid intrusion detection model (HIDM) that uses OCNN-LSTM and transfer learning (TL) for Industry 4.0. The proposed model utilizes an optimized CNN by using enhanced parameters of the CNN via the grey wolf optimizer (GWO) method, which fine-tunes the CNN parameters and helps to improve the model’s prediction accuracy. The transfer learning model helps to train the model, and it transfers the knowledge to the OCNN-LSTM model. The TL method enhances the training process, acquiring the necessary knowledge from the OCNN-LSTM model and utilizing it in each next cycle, which helps to improve detection accuracy. To measure the performance of the proposed model, we conducted a multi-class classification analysis on various online industrial IDS datasets, i.e., ToN-IoT and UNW-NB15. We have conducted two experiments for these two datasets, and various performance-measuring parameters, i.e., precision, F-measure, recall, accuracy, and detection rate, were calculated for the OCNN-LSTM model with and without TL and also for the CNN and LSTM models. For the ToN-IoT dataset, the OCNN-LSTM with TL model achieved a precision of 92.7%; for the UNW-NB15 dataset, the precision was 94.25%, which is higher than OCNN-LSTM without TL. Full article

In recent years, deep learning-based image classification has become widespread, especially in remote sensing applications, due to its automatic and strong feature extraction capability. However, as deep learning methods operate on rectangular-shaped image patches, they cannot accurately extract objects’ boundaries, especially in complex urban settings. As a result, combining deep learning and object-based image analysis (OBIA) has become a new avenue in remote sensing studies. This paper presents a novel approach for combining convolutional neural networks (CNN) with OBIA based on joint optimization of segmentation parameters and deep feature extraction. A Bayesian technique was used to find the best parameters for the multiresolution segmentation (MRS) algorithm while the CNN model learns the image features at different layers, achieving joint optimization. The proposed classification model achieved the best accuracy, with 0.96 OA, 0.95 Kappa, and 0.96 mIoU in the training area and 0.97 OA, 0.96 Kappa, and 0.97 mIoU in the test area, outperforming several benchmark methods including Patch CNN, Center OCNN, Random OCNN, and Decision Fusion. The analysis of CNN variants within the proposed classification workflow showed that the HybridSN model achieved the best results compared to 2D and 3D CNNs. The 3D CNN layers and combining 3D and 2D CNN layers (HybridSN) yielded slightly better accuracies than the 2D CNN layers regarding geometric fidelity, object boundary extraction, and separation of adjacent objects. The Bayesian optimization could find comparable optimal MRS parameters for the training and test areas, with excellent quality measured by AFI (0.046, −0.037) and QR (0.945, 0.932). In the proposed model, higher accuracies could be obtained with larger patch sizes (e.g., 9 × 9 compared to 3 × 3). Moreover, the proposed model is computationally efficient, with the longest training being fewer than 25 s considering all the subprocesses and a single training epoch. As a result, the proposed model can be used for urban and environmental applications that rely on VHR satellite images and require information about land use. Full article

Chronic kidney disease (CKD) is one of the most life-threatening disorders. To improve survivability, early discovery and good management are encouraged. In this paper, CKD was diagnosed using multiple optimized neural networks against traditional neural networks on the UCI machine learning dataset, to identify the most efficient model for the task. The study works on the binary classification of CKD from 24 attributes. For classification, optimized CNN (OCNN), ANN (OANN), and LSTM (OLSTM) models were used as well as traditional CNN, ANN, and LSTM models. With various performance matrixes, error measures, loss values, AUC values, and compilation time, the implemented models are compared to identify the most competent model for the classification of CKD. It is observed that, overall, the optimized models have better performance compared to the traditional models. The highest validation accuracy among the tradition models were achieved from CNN with 92.71%, whereas OCNN, OANN, and OLSTM have higher accuracies of 98.75%, 96.25%, and 98.5%, respectively. Additionally, OCNN has the highest AUC score of 0.99 and the lowest compilation time for classification with 0.00447 s, making it the most efficient model for the diagnosis of CKD. Full article

The security of programmable logic controllers (PLCs) that control industrial systems is becoming increasingly critical due to the ubiquity of the Internet of Things technologies and increasingly nefarious cyber-attack activity. Conventional techniques for safeguarding PLCs are difficult due to their unique architectures. This work proposes a one-class support vector machine, one-class neural network interconnected in a feed-forward manner, and isolation forest approaches for verifying PLC process integrity by monitoring PLC memory addresses. A comprehensive experiment is conducted using an open-source PLC subjected to multiple attack scenarios. A new histogram-based approach is introduced to visualize anomaly detection algorithm performance and prediction confidence. Comparative performance analyses of the proposed algorithms using decision scores and prediction confidence are presented. Results show that isolation forest outperforms one-class neural network, one-class support vector machine, and previous work, in terms of accuracy, precision, recall, and F1-score on seven attack scenarios considered. Statistical hypotheses tests involving analysis of variance and Tukey’s range test were used to validate the presented results. Full article

As demand for bicycles increases, bicycle-related accidents are on the rise. There are many items such as helmets and racing suits for bicycles, but many people do not wear helmets even if they are the most basic safety protection. To protect the rider from accidents, technology is needed to measure the rider’s motion condition in real time, determine whether an accident has occurred, and cope with the accident. This paper describes an artificial intelligence airbag. The artificial intelligence airbag is a system that measures real-time motion conditions of a bicycle rider using a six-axis sensor and judges accidents with artificial intelligence to prevent neck injuries. The MPU 6050 is used to understand changes in the rider’s movement in normal and accident conditions. The angle is determined by using the measured data and artificial intelligence to determine whether an accident happened or not by analyzing acceleration and angle. In this paper, similar methods of artificial intelligence (NN, PNN, CNN, PNN-CNN) to are compared to the orthogonal convolutional neural network (O-CNN) method in terms of the performance of judgment accuracy for accident situations. The artificial neural networks were applied to the airbag system and verified the reliability and judgment in advance. Full article

Accurate information on crop distribution is of great importance for a range of applications including crop yield estimation, greenhouse gas emission measurement and management policy formulation. Fine spatial resolution (FSR) remotely sensed imagery provides new opportunities for crop mapping at a detailed level. However, crop classification from FSR imagery is known to be challenging due to the great intra-class variability and low inter-class disparity in the data. In this research, a novel hybrid method (OSVM-OCNN) was proposed for crop classification from FSR imagery, which combines a shallow-structured object-based support vector machine (OSVM) with a deep-structured object-based convolutional neural network (OCNN). Unlike pixel-wise classification methods, the OSVM-OCNN method operates on objects as the basic units of analysis and, thus, classifies remotely sensed images at the object level. The proposed OSVM-OCNN harvests the complementary characteristics of the two sub-models, the OSVM with effective extraction of low-level within-object features and the OCNN with capture and utilization of high-level between-object information. By using a rule-based fusion strategy based primarily on the OCNN’s prediction probability, the two sub-models were fused in a concise and effective manner. We investigated the effectiveness of the proposed method over two test sites (i.e., S1 and S2) that have distinctive and heterogeneous patterns of different crops in the Sacramento Valley, California, using FSR Synthetic Aperture Radar (SAR) and FSR multispectral data, respectively. Experimental results illustrated that the new proposed OSVM-OCNN approach increased markedly the classification accuracy for most of crop types in S1 and all crop types in S2, and it consistently achieved the most accurate accuracy in comparison with its two object-based sub-models (OSVM and OCNN) as well as the pixel-wise SVM (PSVM) and CNN (PCNN) methods. Our findings, thus, suggest that the proposed method is as an effective and efficient approach to solve the challenging problem of crop classification using FSR imagery (including from different remotely sensed platforms). More importantly, the OSVM-OCNN method is readily generalisable to other landscape classes and, thus, should provide a general solution to solve the complex FSR image classification problem. Full article