Salvatore Distefano

Muhammad Ahmad, Muhammad Hassaan Farooq Butt, Adil Mehmood Khan et al.

Recent advancements in transformers, specifically self-attention mechanisms, have significantly improved hyperspectral image (HSI) classification. However, these models often suffer from inefficiencies, as their computational complexity scales quadratically with sequence length. To address these challenges, we propose the morphological spatial mamba (SMM) and morphological spatial-spectral Mamba (SSMM) model (MorpMamba), which combines the strengths of morphological operations and the state space model framework, offering a more computationally efficient alternative to transformers. In MorpMamba, a novel token generation module first converts HSI patches into spatial-spectral tokens. These tokens are then processed through morphological operations such as erosion and dilation, utilizing depthwise separable convolutions to capture structural and shape information. A token enhancement module refines these features by dynamically adjusting the spatial and spectral tokens based on central HSI regions, ensuring effective feature fusion within each block. Subsequently, multi-head self-attention is applied to further enrich the feature representations, allowing the model to capture complex relationships and dependencies within the data. Finally, the enhanced tokens are fed into a state space module, which efficiently models the temporal evolution of the features for classification. Experimental results on widely used HSI datasets demonstrate that MorpMamba achieves superior parametric efficiency compared to traditional CNN and transformer models while maintaining high accuracy. The code will be made publicly available at \url{https://github.com/mahmad000/MorpMamba}.

Muhammad Ahmad, Muhammad Hassaan Farooq Butt, Muhammad Usama et al.

Spatial-Spectral Mamba (SSM) improves computational efficiency and captures long-range dependencies, addressing Transformer limitations. However, traditional Mamba models overlook rich spectral information in HSIs and struggle with high dimensionality and sequential data. To address these issues, we propose the SSM with multi-head self-attention and token enhancement (MHSSMamba). This model integrates spectral and spatial information by enhancing spectral tokens and using multi-head attention to capture complex relationships between spectral bands and spatial locations. It also manages long-range dependencies and the sequential nature of HSI data, preserving contextual information across spectral bands. MHSSMamba achieved remarkable classification accuracies of 97.62\% on Pavia University, 96.92\% on the University of Houston, 96.85\% on Salinas, and 99.49\% on Wuhan-longKou datasets. The source code is available at \href{https://github.com/MHassaanButt/MHA\_SS\_Mamba}{GitHub}.

Muhammad Ahmad, Muhammad Usama, Manuel Mazzara et al.

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 paper introduces WaveMamba, a novel approach that integrates wavelet transformation with the spatial-spectral Mamba 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.

Muhammad Ahmad, Manuel Mazzara, Salvatore Distefano et al.

Hyperspectral image classification (HSIC) has gained significant attention because of its potential in analyzing high-dimensional data with rich spectral and spatial information. In this work, we propose the Differential Spatial-Spectral Transformer (DiffFormer), a novel framework designed to address the inherent challenges of HSIC, such as spectral redundancy and spatial discontinuity. The DiffFormer leverages a Differential Multi-Head Self-Attention (DMHSA) mechanism, which enhances local feature discrimination by introducing differential attention to accentuate subtle variations across neighboring spectral-spatial patches. The architecture integrates Spectral-Spatial Tokenization through three-dimensional (3D) convolution-based patch embeddings, positional encoding, and a stack of transformer layers equipped with the SWiGLU activation function for efficient feature extraction (SwiGLU is a variant of the Gated Linear Unit (GLU) activation function). A token-based classification head further ensures robust representation learning, enabling precise labeling of hyperspectral pixels. Extensive experiments on benchmark hyperspectral datasets demonstrate the superiority of DiffFormer in terms of classification accuracy, computational efficiency, and generalizability, compared to existing state-of-the-art (SOTA) methods. In addition, this work provides a detailed analysis of computational complexity, showcasing the scalability of the model for large-scale remote sensing applications. The source code will be made available at \url{https://github.com/mahmad000/DiffFormer} after the first round of revision.

Muhammad Ahmad, Francesco Mauro, Manuel Mazzara et al.

Hyperspectral image (HSI) classification presents inherent challenges due to high spectral dimensionality, significant domain shifts, and limited availability of labeled data. To address these issues, we propose a novel Active Transfer Learning (ATL) framework built upon a Spatial-Spectral Transformer (SST) backbone. The framework integrates multistage transfer learning with an uncertainty-diversity-driven active learning mechanism that strategically selects highly informative and diverse samples for annotation, thereby significantly reducing labeling costs and mitigating sample redundancy. A dynamic layer freezing strategy is introduced to enhance transferability and computational efficiency, enabling selective adaptation of model layers based on domain shift characteristics. Furthermore, we incorporate a self-calibrated attention mechanism that dynamically refines spatial and spectral weights during adaptation, guided by uncertainty-aware feedback. A diversity-promoting sampling strategy ensures broad spectral coverage among selected samples, preventing overfitting to specific classes. Extensive experiments on benchmark cross-domain HSI datasets demonstrate that the proposed SST-ATL framework achieves superior classification performance compared to conventional approaches. The source code is publicly available at https://github.com/mahmad000/ATL-SST.

Nikolay Buldakov, Timur Khalilev, Salvatore Distefano et al.

This paper discusses an open source solution to smart-parking in highly urbanized areas. Interviews have been conducted with domain experts, user stories defined and a system architecture has been proposed with a case study. Our solution allows independent owners of parking space to be integrated into one unified system, that facilitates the parking situation in a smart city. The utilization of such a system raises the issues of trust and transparency among several actors of the parking process. In order to tackle those, we propose a smart contract-based solution, that brings in trust by encapsulating sensitive relations and processes into transparent and distributed smart contracts.

Saad Sohail, Muhammad Usama, Usman Ghous et al.

Hyperspectral imaging (HSI) provides rich spectral-spatial information across hundreds of contiguous bands, enabling precise material discrimination in applications such as environmental monitoring, agriculture, and urban analysis. However, the high dimensionality and spectral variability of HSI data pose significant challenges for feature extraction and classification. This paper presents EnergyFormer, a transformer-based framework designed to address these challenges through three key innovations: (1) Multi-Head Energy Attention (MHEA), which optimizes an energy function to selectively enhance critical spectral-spatial features, improving feature discrimination; (2) Fourier Position Embedding (FoPE), which adaptively encodes spectral and spatial dependencies to reinforce long-range interactions; and (3) Enhanced Convolutional Block Attention Module (ECBAM), which selectively amplifies informative wavelength bands and spatial structures, enhancing representation learning. Extensive experiments on the WHU-Hi-HanChuan, Salinas, and Pavia University datasets demonstrate that EnergyFormer achieves exceptional overall accuracies of 99.28\%, 98.63\%, and 98.72\%, respectively, outperforming state-of-the-art CNN, transformer, and Mamba-based models. The source code will be made available at https://github.com/mahmad000.

Muhammad Ahmad, Manuel Mazzara, Salvatore Distefano et al.

Hyperspectral image (HSI) classification remains a challenging task due to the intricate spatial-spectral correlations. Existing transformer models excel in capturing long-range dependencies but often suffer from information redundancy and attention inefficiencies, limiting their ability to model fine-grained relationships crucial for HSI classification. To overcome these limitations, this work proposes MemFormer, a lightweight and memory-enhanced transformer. MemFormer introduces a memory-enhanced multi-head attention mechanism that iteratively refines a dynamic memory module, enhancing feature extraction while reducing redundancy across layers. Additionally, a dynamic memory enrichment strategy progressively captures complex spatial and spectral dependencies, leading to more expressive feature representations. To further improve structural consistency, we incorporate a spatial-spectral positional encoding (SSPE) tailored for HSI data, ensuring continuity without the computational burden of convolution-based approaches. Extensive experiments on benchmark datasets demonstrate that MemFormer achieves superior classification accuracy, outperforming state-of-the-art methods.

Muhammad Ahmad, Muhammad Hassaan Farooq Butt, Muhammad Usama et al.

Hyperspectral image (HSI) classification plays a pivotal role in domains such as environmental monitoring, agriculture, and urban planning. However, it faces significant challenges due to the high-dimensional nature of the data and the complex spectral-spatial relationships inherent in HSI. Traditional methods, including conventional machine learning and convolutional neural networks (CNNs), often struggle to effectively capture these intricate spectral-spatial features and global contextual information. Transformer-based models, while powerful in capturing long-range dependencies, often demand substantial computational resources, posing challenges in scenarios where labeled datasets are limited, as is commonly seen in HSI applications. To overcome these challenges, this work proposes GraphMamba, a hybrid model that combines spectral-spatial token generation, graph-based token prioritization, and cross-attention mechanisms. The model introduces a novel hybridization of state-space modeling and Gated Recurrent Units (GRU), capturing both linear and nonlinear spatial-spectral dynamics. GraphMamba enhances the ability to model complex spatial-spectral relationships while maintaining scalability and computational efficiency across diverse HSI datasets. Through comprehensive experiments, we demonstrate that GraphMamba outperforms existing state-of-the-art models, offering a scalable and robust solution for complex HSI classification tasks.

Muhammad Ahmad, Adil Mehmood Khan, Manuel Mazzara et al.

Convolutional Neural Networks (CNN) are more suitable, indeed. However, fixed kernel sizes make traditional CNN too specific, neither flexible nor conducive to feature learning, thus impacting on the classification accuracy. The convolution of different kernel size networks may overcome this problem by capturing more discriminating and relevant information. In light of this, the proposed solution aims at combining the core idea of 3D and 2D Inception net with the Attention mechanism to boost the HSIC CNN performance in a hybrid scenario. The resulting \textit{attention-fused hybrid network} (AfNet) is based on three attention-fused parallel hybrid sub-nets with different kernels in each block repeatedly using high-level features to enhance the final ground-truth maps. In short, AfNet is able to selectively filter out the discriminative features critical for classification. Several tests on HSI datasets provided competitive results for AfNet compared to state-of-the-art models. The proposed pipeline achieved, indeed, an overall accuracy of 97\% for the Indian Pines, 100\% for Botswana, 99\% for Pavia University, Pavia Center, and Salinas datasets.

Muhammad Ahmad, Manuel Mazzara, Salvatore Distefano

Convolutional Neural Networks (CNN) have been rigorously studied for Hyperspectral Image Classification (HSIC) and are known to be effective in exploiting joint spatial-spectral information with the expense of lower generalization performance and learning speed due to the hard labels and non-uniform distribution over labels. Several regularization techniques have been used to overcome the aforesaid issues. However, sometimes models learn to predict the samples extremely confidently which is not good from a generalization point of view. Therefore, this paper proposed an idea to enhance the generalization performance of a hybrid CNN for HSIC using soft labels that are a weighted average of the hard labels and uniform distribution over ground labels. The proposed method helps to prevent CNN from becoming over-confident. We empirically show that in improving generalization performance, label smoothing also improves model calibration which significantly improves beam-search. Several publicly available Hyperspectral datasets are used to validate the experimental evaluation which reveals improved generalization performance, statistical significance, and computational complexity as compared to the state-of-the-art models. The code will be made available at https://github.com/mahmad00.

Muhammad Ahmad, Sidrah Shabbir, Rana Aamir Raza et al.

Convolutional Neural Networks (CNN) has been extensively studied for Hyperspectral Image Classification (HSIC) more specifically, 2D and 3D CNN models have proved highly efficient in exploiting the spatial and spectral information of Hyperspectral Images. However, 2D CNN only considers the spatial information and ignores the spectral information whereas 3D CNN jointly exploits spatial-spectral information at a high computational cost. Therefore, this work proposed a lightweight CNN (3D followed by 2D-CNN) model which significantly reduces the computational cost by distributing spatial-spectral feature extraction across a lighter model alongside a preprocessing that has been carried out to improve the classification results. Five benchmark Hyperspectral datasets (i.e., SalinasA, Salinas, Indian Pines, Pavia University, Pavia Center, and Botswana) are used for experimental evaluation. The experimental results show that the proposed pipeline outperformed in terms of generalization performance, statistical significance, and computational complexity, as compared to the state-of-the-art 2D/3D CNN models except commonly used computationally expensive design choices.

Muhammad Ahmad, Sidrah Shabbir, Swalpa Kumar Roy et al.

Hyperspectral Imaging (HSI) has been extensively utilized in many real-life applications because it benefits from the detailed spectral information contained in each pixel. Notably, the complex characteristics i.e., the nonlinear relation among the captured spectral information and the corresponding object of HSI data make accurate classification challenging for traditional methods. In the last few years, Deep Learning (DL) has been substantiated as a powerful feature extractor that effectively addresses the nonlinear problems that appeared in a number of computer vision tasks. This prompts the deployment of DL for HSI classification (HSIC) which revealed good performance. This survey enlists a systematic overview of DL for HSIC and compared state-of-the-art strategies on the said topic. Primarily, we will encapsulate the main challenges of traditional machine learning for HSIC and then we will acquaint the superiority of DL to address these problems. This survey breakdown the state-of-the-art DL frameworks into spectral features, spatial features, and together spatial-spectral features to systematically analyze the achievements (future research directions as well) of these frameworks for HSIC. Moreover, we will consider the fact that DL requires a large number of labeled training examples whereas acquiring such a number for HSIC is challenging in terms of time and cost. Therefore, this survey discusses some strategies to improve the generalization performance of DL strategies which can provide some future guidelines.

Antonio Capizzi, Salvatore Distefano, Manuel Mazzara

DevOps is a quite effective approach for managing software development and operation, as confirmed by plenty of success stories in real applications and case studies. DevOps is now becoming the main-stream solution adopted by the software industry in development, able to reduce the time to market and costs while improving quality and ensuring evolvability and adaptability of the resulting software architecture. Among the aspects to take into account in a DevOps process, data is assuming strategic importance, since it allows to gain insights from the operation directly into the development, the main objective of a DevOps approach. Data can be therefore considered as the fuel of the DevOps process, requiring proper solutions for its management. Based on the amount of data generated, its variety, velocity, variability, value and other relevant features, DevOps data management can be mainly framed into the BigData category. This allows exploiting BigData solutions for the management of DevOps data generated throughout the process, including artefacts, code, documentation, logs and so on. This paper aims at investigating data management in DevOps processes, identifying related issues, challenges and potential solutions taken from the BigData world as well as from new trends adopting and adapting DevOps approaches in data management, i.e. DataOps.

Antonio Capizzi, Salvatore Distefano, Manuel Mazzara et al.

The tools employed in the DevOps Toolchain generates a large quantity of data that is typically ignored or inspected only in particular occasions, at most. However, the analysis of such data could enable the extraction of useful information about the status and evolution of the project. For example, metrics like the "lines of code added since the last release" or "failures detected in the staging environment" are good indicators for predicting potential risks in the incoming release. In order to prevent problems appearing in later stages of production, an anomaly detection system can operate in the staging environment to compare the current incoming release with previous ones according to predefined metrics. The analysis is conducted before going into production to identify anomalies which should be addressed by human operators that address false-positive and negatives that can appear. In this paper, we describe a prototypical implementation of the aforementioned idea in the form of a "proof of concept". The current study effectively demonstrates the feasibility of the approach for a set of implemented functionalities.

Ilya Afanasyev, Manuel Mazzara, Subham Chakraborty et al.

Internet of Things (IoT) and robotics cannot be considered two separate domains these days. Internet of Robotics Things (IoRT) is a concept that has been recently introduced to describe the integration of robotics technologies in IoT scenarios. As a consequence, these two research fields have started interacting, and thus linking research communities. In this paper we intend to make further steps in joining the two communities and broaden the discussion on the development of this interdisciplinary field. The paper provides an overview, analysis and challenges of possible solutions for the Internet of Robotic Things, discussing the issues of the IoRT architecture, the integration of smart spaces and robotic applications.

Manuel Mazzara, Ilya Afanasyev, Smruti R. Sarangi et al.

The vision encompassing Smart and Software-defined Buildings (SSDB) is becoming more and more popular and its implementation is now more accessible due to the widespread adoption of the 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.

Muhammad Ahmad, Ali Kashif Bashir, Adil Mehmood Khan et al.

Smartphones have ubiquitously integrated into our home and work environments, however, users normally rely on explicit but inefficient identification processes in a controlled environment. Therefore, when a device is stolen, a thief can have access to the owner's personal information and services against the stored passwords. As a result of this potential scenario, this work proposes an automatic legitimate user identification system based on gait biometrics extracted from user walking patterns captured by a smartphone. A set of preprocessing schemes is applied to calibrate noisy and invalid samples and augment the gait-induced time and frequency domain features, then further optimized using a non-linear unsupervised feature selection method. The selected features create an underlying gait biometric representation able to discriminate among individuals and identify them uniquely. Different classifiers (i.e. Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Bagging, and Extreme Learning Machine (ELM)) are adopted to achieve accurate legitimate user identification. Extensive experiments on a group of $16$ individuals in an indoor environment show the effectiveness of the proposed solution: with $5$ to $70$ samples per window, KNN and bagging classifiers achieve $87-99\%$ accuracy, $82-98\%$ for ELM, and $81-94\%$ for SVM. The proposed pipeline achieves a $100\%$ true positive and $0\%$ false-negative rate for almost all classifiers.

Michael W. Bridges, Salvatore Distefano, Manuel Mazzara et al.

This paper proposes a model which aim is providing a more coherent framework for agents design. We identify three closely related anthropo-centered domains working on separate functional levels. Abstracting from human physiology, psychology, and philosophy we create the $P^3$ model to be used as a multi-tier approach to deal with complex class of problems. The three layers identified in this model have been named PhysioComputing, MindComputing, and MetaComputing. Several instantiations of this model are finally presented related to different IT areas such as artificial intelligence, distributed computing, software and service engineering.

Jordi Vallverdú, Max Talanov, Salvatore Distefano et al.

In this paper we present a new neurobiologically-inspired affective cognitive architecture: NEUCOGAR (NEUromodulating COGnitive ARchitecture). The objective of NEUCOGAR is the identification of a mapping from the influence of serotonin, dopamine and noradrenaline to the computing processes based on Von Neuman's architecture, in order to implement affective phenomena which can operate on the Turing's machine model. As basis of the modeling we use and extend the Lövheim Cube of Emotion with parameters of the Von Neumann architecture. Validation is conducted via simulation on a computing system of dopamine neuromodulation and its effects on the Cortex. In the experimental phase of the project, the increase of computing power and storage redistribution due to emotion stimulus modulated by the dopamine system, confirmed the soundness of the model.