Hyperspectral imaging (HSI) has proven to be a powerful tool for capturing detailed spectral and spatial information across diverse applications. Despite the advancements in deep learning (DL) and Transformer architectures for HSI classification, challenges such as computational efficiency and the need for extensive labeled data persist. This letter introduces WaveMamba, a novel approach that integrates wavelet transformation with the spatial-spectral Mamba (SSMamba) architecture to enhance HSI classification. WaveMamba captures both local texture patterns and global contextual relationships in an end-to-end trainable model. The Wavelet-based enhanced features are then processed through the state-space architecture to model spatial-spectral relationships and temporal dependencies. The experimental results indicate that WaveMamba surpasses existing models, achieving an accuracy improvement of 4.5% on the University of Houston dataset and a 2.0% increase on the Pavia University dataset.

Hyperspectral imaging provides rich spectral-spatial information essential for fine-grained land cover classification. However, high dimensionality, spectral redundancy, and noise sensitivity significantly hinder classification accuracy. To overcome these issues, this work propose DIFF-SE, a novel differential transformer framework enhanced with a dual-path squeeze-and-excitation (E-SE) module tailored for hyperspectral image (HSI) classification (HSIC). The proposed multi-head differential attention mechanism contrasts paired attention maps to amplify discriminative spectral-spatial cues while suppressing redundancy and noise. Simultaneously, the E-SE module performs concurrent spectral and spatial recalibration, dynamically emphasizing informative bands and salient regions. Extensive experiments on three benchmark datasets, Pavia University (PU), WHU-Hi-HanChuan (HC), and OHID-1, demonstrate that DIFF-SE consistently achieves superior overall accuracies of 99.34%, 99.31%, and 94.99%, respectively, outperforming several recent state-of-the-art methods. The source code will be publicly released at https://github.com/mahmad000.

Hyperspectral images (HSIs) capture detailed spectral–spatial information across hundreds of contiguous bands, enabling precise material identification in domains such as environmental monitoring, agriculture, and urban analysis. However, the high dimensionality and spectral variability inherent to HSIs present significant challenges for effective feature extraction and classification. This letter introduces EnergyFormer (EF), a transformer-based framework designed to overcome these limitations through three key innovations: 1) multihead energy attention (MHEA), which formulates an energy optimization mechanism to selectively enhance discriminative spectral–spatial features; 2) Fourier positional embedding (FoPE), which adaptively models long-range spectral and spatial dependencies; and 3) enhanced convolutional block attention module (ECBAM), which emphasizes informative wavelength bands and spatial structures for robust representation learning. Extensive experiments on the WHU-Hi-HanChuan, Salinas, and Pavia University datasets demonstrate that EF achieves superior classification performance with overall accuracies of 99.28%, 98.63%, and 98.72%, respectively, outperforming leading CNN-, transformer-, and Mamba-based models.

Hyperspectral image classification (HSIC) is a challenging task due to the high dimensionality of hyperspectral data, the complex interplay of spatial and spectral features, and the scarcity of annotated samples. Existing approaches, mainly based on tokenization-based feature extraction, introduce artificial segmentation, increasing computational cost, and may lead to information loss. To address these issues, a novel framework, Byte Latent Mamba with Knowledge Distillation (BLM-KD), overcoming explicit tokenization by directly learning byte-level spectral-spatial representations from raw hyperspectral data, is proposed. The Byte Latent Mamba architecture learns compact and expressive byte-level features through an end-to-end convolutional encoder, preserving spectral continuity and spatial structure. A structured State Space Model (SSM) is integrated to model long-range spatial-spectral dependencies efficiently via learned dynamic state transitions. Additionally, an adaptive knowledge distillation (KD) strategy is adopted, where a high-capacity teacher model selectively transfers salient features to a lightweight student model, driven by a temperature-controlled weighting schedule. This ensures robust generalization with reduced model complexity. A patch-based preprocessing scheme also excludes irrelevant zero-labeled samples, refining the training process. Extensive experiments conducted on multiple real-world hyperspectral benchmarks demonstrate that BLM-KD outperforms existing state-of-the-art methods in both classification accuracy and computational efficiency.

Multihead self-attention and cross-attention mechanisms often suffer from computational inefficiencies, limited scalability, and suboptimal contextual understanding, particularly in hyperspectral image (HSI) classification. These mechanisms struggle to effectively capture long-range dependencies while maintaining computational feasibility due to the quadratic complexity of self-attention. To address these challenges, this work proposes PolicyMamba, a spectral-spatial mamba model enhanced with a localized policy attention mechanism. This mechanism reduces computational overhead by restricting attention to nonoverlapping localized regions and enforcing sparsity constraints, ensuring that only the most informative interactions are retained. A hierarchical aggregation strategy further integrates patch-wise attention outputs, preserving spectral-spatial correlations across scales. In addition, a sliding window patch process enhances local feature continuity while mitigating information loss. The PolicyMamba framework integrates spectral-spatial token generation, token enhancement, localized attention, and state transition modules, significantly improving HSI feature representation. Extensive experiments demonstrate that PolicyMamba achieves superior classification accuracy, outperforming conventional and state-of-the-art methods in land cover classification (LCC) by efficiently modeling intricate dependencies in HSI data.

Conventional active learning approaches for hyperspectral image classification (HSIC) have limitations such as incrementally growing training sets without considering class structure and heterogeneity within existing and new samples. Additionally, there is limited research leveraging both spectral and spatial information jointly, and stopping criteria are not well established. This study presents a novel fuzzybased spatial-spectral Within and Between method (FLG) for preserving local and global class discriminative information. The method first explores spatial fuzziness to identify misclassified samples. It then computes total within-class and between-class information locally and globally. This information is integrated into a discriminative objective function to selectively query heterogeneous samples, mitigating randomness among training data. Experimental results on benchmark Hyperspectral datasets demonstrate the FLG improves classification accuracy across generative, extreme learning machine, and sparse multinomial logistic regression models by jointly exploiting spectral and spatial information to expand labeled training sets strategically.

Transformers have proven effective for Hyperspectral Image Classification (HSIC) but often incorporate average pooling that results in information loss. This paper presents WaveFormer, a novel transformer-based approach that leverages wavelet transforms for invertible downsampling. This preserves data integrity while enabling attention learning. Specifically, WaveFormer unifies downsampling with wavelet transforms to decompress feature maps without loss. This provides an efficient tradeoff between performance and computation. Furthermore, the wavelet decomposition enhances the interaction between structural and shape information in image patches and channel maps. To evaluate WaveFormer, we conducted extensive experiments on two benchmark hyperspectral datasets. Our results demonstrate that WaveFormer achieves state-of-the-art classification accuracy, obtaining overall accuracies of 95.66% and 96.54% on the Pavia University and the University of Houston datasets, respectively. By integrating wavelet transforms, WaveFormer presents a new transformer architecture for hyperspectral imagery that achieves superior classification without information loss from average pooling.

Hyperspectral image classification (HSIC) faces challenges in preserving high-frequency features during downsampling and hierarchical filtering in the CNN architecture. To overcome this, we propose sharpened cosine similarity (SCS) as an alternative to convolutions within a neural network for HSIC. SCSNet emphasizes parameter efficiency by bypassing nonlinear activation layers, normalization steps, and dropout post the SCS layer. Additionally, MaxAbsPool is implemented instead of MaxPool for superior performance. Experimental results on public HSI datasets demonstrate SCS’s comparable accuracy, achieving 99% for both Indian Pines and Salinas datasets.

In Transformer-based hyperspectral image classification (HSIC), predefined positional encodings (PEs) are crucial for capturing the order of each input token. However, their typical representation as fixed-dimensional learnable vectors makes it challenging to adapt to variable-length input sequences, thereby limiting the broader application of Transformers for HSIC. To address this issue, this study introduces an implicit conditional PEs (CPEs) scheme in a Transformer for HSIC, conditioned on the input token’s local neighborhood. The proposed spatial–spectral Transformer (SSFormer) integrates spatial–spectral information and enhances classification performance by incorporating a CPE mechanism, thereby increasing the Transformer layers’ capacity to preserve contextual relationships within the HSI data. Moreover, SSFormer ensembles the cross attention between patches and proposed learnable embeddings. This enables the model to capture global and local features simultaneously while addressing the constraint of limited training samples in a computationally efficient manner. Extensive experiments on publicly available HSI benchmarking datasets were conducted to validate the effectiveness of the proposed SSFormer model. The results demonstrated remarkable performance, achieving the classification accuracies of 97.7% on the Indian Pines dataset and 96.08% on the University of Houston dataset.

Abstract Efficient word representation techniques (word embeddings) with modern machine learning models have shown reasonable improvement on automatic text classification tasks. However, the effectiveness of such techniques has not been evaluated yet in terms of insufficient word vector representation for training. Convolutional Neural Network has achieved significant results in pattern recognition, image analysis, and text classification. This study investigates the application of the CNN model on text classification problems by experimentation and analysis. We trained our classification model with a prominent word embedding generation model, Fast Text on publically available datasets, six benchmark datasets including Ag News, Amazon Full and Polarity, Yahoo Question Answer, Yelp Full, and Polarity. Furthermore, the proposed model has been tested on the Twitter US airlines non-benchmark dataset as well. The analysis indicates that using Fast Text as word embedding is a very promising approach.

In forensic sciences, blood is a shred of essential evidence for reconstructing crime scenes. Blood identification and classification may help to confirm a suspect, although several chemical processes are used to recreate the crime scene. However, these approaches can have an impact on DNA analysis. A potential application of bloodstain identification and classification using Hyperspectral Imaging (HSI) can be used as substance clas-sification in forensic science for crime scene analysis. Therefore, this work proposes the use of a fast and compact Hybrid CNN to process HSI data for bloodstain identification and classification. For experimental and validation purposes, we perform exper-iments on a publicly available Hyperspectral-based Bloodstain dataset. This dataset has different types of substances i.e., blood and blood-like compounds, for instance, ketchup, artificial blood, beetroot juice, poster paint, tomato concentrate, acrylic paint, uncertain blood. We compare the results with state-of-the-art 3D CNN model and examine the results in detail and present a discussion of each tested architecture with limited availability of the training samples (e.g., only 5 % (792 samples) of the data samples are used to train the model, and validated on 5 % (792 samples) data samples and finally blindly tested on 90 % (14260 samples) of the data samples). The source code can be access on https://github.com/MHassaanButt/FCHCNN-for-HSIC

Glioblastoma (GB) is a malignant brain tumor and requires surgical resection. Although complete resection of GB improves prognosis, supratotal resection may cause neurological abnormalities. Therefore, intraoperative tissue classification techniques are needed to delineate infected tumor regions to remove reoccurrences. To delineate the affected regions, surgeons mostly rely on traditional magnetic resonance imaging (MRI) which often lacks accuracy and precision due to the brain-shift phenomenon. Hyperspectral Imaging (HSI) is a noninvasive advanced optical technique and has the potential to classify tissue cells accurately. However, HSI tumor classification is challenging due to overlapping regions, high interclass similarity, and homogeneous information. Additionally, HSI models using 2D Convolutional Neural Network (CNN) models works with spectral information eliminating spatial features and 3D followed by 2D hybrid model lacks abstract level spatial information. Therefore, in this study, we have used a minimal layer 3D CNN model to classify the GB tumor region from normal tissues using an intraoperative VivoHSI dataset. The HSI data have normal tissue (NT), tumor tissue (TT), hypervascularized tissue or blood vessels (BV), and background (BG) tissue cells. The proposed 3D CNN model consists of only two 3D layers using limited training samples (20%), which are further divided into 50% for training and 50% for validation and blind tested (80%) on the rest of the data. This study outperformed then state-of-the-art hybrid architecture by achieving an overall accuracy of 99.99%.

Cross-modal retrieval has attracted great attention due to the increasing demand for tremendous amounts of multimodal data in recent years. These retrievals could either be text-to-image or image-to-text. To address the problem of inappropriate information included between images and texts, we propose two cross-modal recovery techniques established on a dual-branch neural network defined on a common subspace and the hashing learning method. First, a cross-modal recovery technique established on a multilabel information deep ranking model (MIDRM) is provided. In this method, we introduce a triplet-loss function into the dual-branch neural network model. This function takes advantage of the semantic information of the bimodal components, focusing on not only the similarities between similar images and text features but also the distances between dissimilar images and texts. Second, we establish a new cross-modal hashing technique said to be the deep regularized hashing constraint (DRHC). In this method, the regularized function is used to replace the binary constraint, and the discrete value is constrained to a certain numerical range so that the network can achieve end-to-end training. Overall, the time complexity is greatly improved, and the occupied storage space is also greatly reduced. Different experiments on our proposed MIDRM and DRHC models demonstrate their superior performance to those of the state-of-the-art methods on two widely used data sets. The experimental results show that our approach also increases the mean average precision of cross-modal recovery.

Hyperspectral images (HSIs) are used in a large number of real-world applications. HSI classification (HSIC) is a challenging task due to high interclass similarity, high intraclass variability, overlapping, and nested regions. The 2-D convolutional neural network (CNN) is a viable classification approach since HSIC depends on both spectral–spatial information. The 3-D CNN is a good alternative for improving the accuracy of HSIC, but it can be computationally intensive due to the volume and spectral dimensions of HSI. Furthermore, these models may fail to extract quality feature maps and underperform over the regions having similar textures. This work proposes a 3-D CNN model that utilizes both spatial–spectral feature maps to improve the performance of HSIC. For this purpose, the HSI cube is first divided into small overlapping 3-D patches, which are processed to generate 3-D feature maps using a 3-D kernel function over multiple contiguous bands of the spectral information in a computationally efficient way. In brief, our end-to-end trained model requires fewer parameters to significantly reduce the convergence time while providing better accuracy than existing models. The results are further compared with several state-of-the-art 2-D/3-D CNN models, demonstrating remarkable performance both in terms of accuracy and computational time.

Convolutional Neural Networks (CNNs) have been extensively studied for Hyperspectral Image Classification (HSIC). However, CNNs are critically attributed to a large number of labeled training samples, which outlays high costs in terms of time and resources. Moreover, CNNs are trained on some samples and have been tested on the entire HSI. Perhaps, the entire HSI is taken into account at test time to appropriately generate the ground truth maps. In order to obtain a higher accuracy while considering the limited availability of training samples and disjoint validation and test samples, this work proposes a fast and compact 3D CNN-based Active Learning (AL) for HSIC that integrates both deep transfer learning and AL into a unified framework. In the proposed methodology, a 3D CNN model is trained with very few training samples (i.e., 5%, only) and in the next phase, the most informative and heterogeneous samples are queried from the validation set (candidate set) based on the fuzziness, mutual information and breaking ties of the trained model. The 3D CNN model is later fine-tuned (rather retraining from scratch) with the new training samples (i.e., 200 samples are selected in each iteration) to reduce the computational cost. The proposed method has been compared with the state-of-the-art traditional and deep models proposed for HSIC. Experimental results proved the superiority of our proposed method on several benchmark HSI datasets with significantly fewer labeled samples. Matlab demo can be accessed on GitHub: github.com/mahmad00.

Convolutional Neural Networks (CNNs) have been extensively utilized for Hyperspectral (HSI) as well as Light Detection and Ranging (LiDAR) data Classification. However, CNNs have not been much explored for joint HSI and LiDAR image classification. Therefore, this article proposes a joint feature learning (HSI and LiDAR) and fusion mechanism using CNN and Spatial Morphological blocks which generates highly accurate land-cover maps. The CNN model comprises three Conv3D layers and is directly applied to the HSIs for extracting discriminative spectral-spatial feature representation. On the contrary, the spatial morphological block is able to capture the information relevant to the height or shape of the different land-cover regions from LiDAR data. The LiDAR features are extracted using morphological dilation and erosion layers which increase the robustness of the proposed model by considering elevation information as an additional feature. Finally, both the obtained features from CNNs and spatial morphological blocks are combined using an additive operation prior to the classification. Extensive experiments are shown with widely used HSIs and LiDAR datasets, i.e., University of Houston (UH), Trento, and MUUFL Gulfport scene. The reported results show that the proposed model significantly outperforms traditional methods and other state-of-the-art deep learning models. The source code for the proposed model will be made available publicly at https://github.com/AnkurDeria/HSI+LiDAR.

The Internet of Things (IoT) devices, networks, and applications have become an integral part of modern societies. Despite their social, economic, and industrial benefits, these devices and networks are frequently targeted by cybercriminals. Hence, IoT applications and networks demand lightweight, fast, and flexible security solutions to overcome these challenges. In this regard, artificial-intelligence-based solutions with Big Data analytics can produce promising results in the field of cybersecurity. This article proposes a lightweight dense random neural network (DnRaNN) for intrusion detection in the IoT. The proposed scheme is well suited for implementation in resource-constrained IoT networks due to its inherent improved generalization capabilities and distributed nature. The suggested model was evaluated by conducting extensive experiments on a new generation IoT security dataset ToN_IoT. All the experiments were conducted under different hyperparameters and the efficiency of the proposed DnRaNN was evaluated through multiple performance metrics. The findings of the proposed study provide recommendations and insights in binary class and multiclass scenarios. The proposed DnRaNN model attained attack detection accuracy of 99.14% and 99.05% for binary class and multiclass classifications, respectively.

The vision encompassing Smart and Software-defined Buildings (SSDB) is becoming more popular and its implementation is now more accessible due to the widespread adoption of the Internet of Things (IoT) infrastructure. Some of the most important applications sustaining this vision are energy management, environmental comfort, safety and surveillance. This paper surveys IoT and SSB technologies and their cooperation towards the realization of smart spaces. We propose a four-layer reference architecture and we organize related concepts around it. This conceptual frame is useful to identify the current literature on the topic and to connect the dots into a coherent vision of the future of residential and commercial buildings.

The unprecedented advancements in mobile phone technology on one hand offer plethora of applications to consumers, but on the other hand cause serious risk to users' privacy. Among other modules, camera is one of the most pervasive modules in smart phone used for taking pictures and videos. Furthermore, many applications use camera as an image capturing device that is used for different purposes such as entertainment or identification and authentication (e.g. biometric face authentication). In this paper, we aim at Android camera module and try to find vulnerabilities that could be exploited for camera spoofing. Particularly we aim at different techniques such as modifying the requesting application and creating virtual device at kernel level to use it as a camera. Our experiments revealed that it is still possible to spoof Android camera. Furthermore, based on our findings, we also suggest recommendations to avoid such exploit in Android applications.

Classifying hyperspectral data within high dimensionality is a challenging task. To cope with this issue, this study implements a semi‐supervised multi‐kernel class consistency regulariser graph‐based spatial–spectral feature learning framework. For feature learning process, establishing the neighbouring relationship between the distinct samples from the high‐dimensional space is the key to a favourable outcome for classification. The proposed method implements two kernels and a class consistency regulariser. The first kernel constructs simple edges where every single vertex represents one particular sample and the edge weight encodes the initial similarity between distinct samples. Later the obtained relation is fed into the second kernel to obtain the final features for classification where the semi‐supervised learning is conducted to estimate the grouping relations among different samples according to their similarity, class, and spatial information. To validate the performance of proposed framework, the authors conduct several experiments on three publically available hyperspectral datasets. The proposed work equates favourably with state‐of‐the‐art works with an overall classification accuracy of 98.54, 97.83, and 98.38% for Pavia University, Salinas‐A, and Indian Pines datasets, respectively.

Smartphones have ubiquitously integrated into our home and work environments. It is now a common practice for people to store their sensitive and confidential information on their phones. This has made it extremely important to authenticate legitimate users of a phone and block imposters. In this paper, we demonstrate that the motion dynamics of smartphones, captured using their built in accelerometers, can be used for accurate user identification. We call this mechanism gait fingerprinting. To this end, we first collected the acceleration data from multiple users as they walked with a smartphone placed freely in their pants pockets. Next, we studied the application of different feature extraction, feature selection and classification techniques from the machine learning literature on these data. Through extensive experimentation, demonstrated is that simple time domain features extracted from these data, which are further optimized using stepwise linear discrimination analysis, can be used to train artificial neural networks to identify legitimate user and block imposter with an average accuracy of 95%.

The accuracy of control systems analysis is of paramount importance as even minor design flaws can lead to disastrous consequences in this domain. This paper provides a higher-order-logic theorem proving based framework for the formal analysis of steady state errors in feedback control systems. In particular, we present the formalization of control system foundations, like transfer functions, summing junctions, feedback loops and pickoff points, and steady state error models for the step, ramp and parabola cases. These foundations can be built upon to formally specify a wide range of feedback control systems in higher-order logic and reason about their steady state errors within the sound core of a theorem prover. The proposed formalization is based on the complex number theory of the HOL-Light theorem prover. For illustration purposes, we present the steady state error analysis of a solar tracking control system.

In this paper, we propose a Progressive Differential Thresholding (PDT) framework for coordinated network anomaly detection. Under the proposed framework, nodes present on a packet's path progressively encode their opinion (malicious or benign) inside a packet. Subsequent nodes on the path use the encoded opinion as side-information to adapt their anomaly detection thresholds and in turn improve their classification accuracies. Accuracy benefits of PDT are evaluated through experimental evaluations of multiple non-proprietary anomaly detectors on a publicly-available attack dataset. These evaluations indicate that, while being distributed and having negligible complexity and communication overheads, the proposed PDT framework provides considerable and consistent improvements in anomaly detection accuracy. We observe upto 54% improvements in ADS detection accuracy while upto 4 times reduction in the false alarm rates.