Antonio Liotta

Mario Di Mauro, Giovanni Galatro, Fabio Postiglione et al.

Predicting the behavior of real-time traffic (e.g., VoIP) in mobility scenarios could help the operators to better plan their network infrastructures and to optimize the allocation of resources. Accordingly, in this work the authors propose a forecasting analysis of crucial QoS/QoE descriptors (some of which neglected in the technical literature) of VoIP traffic in a real mobile environment. The problem is formulated in terms of a multivariate time series analysis. Such a formalization allows to discover and model the temporal relationships among various descriptors and to forecast their behaviors for future periods. Techniques such as Vector Autoregressive models and machine learning (deep-based and tree-based) approaches are employed and compared in terms of performance and time complexity, by reframing the multivariate time series problem into a supervised learning one. Moreover, a series of auxiliary analyses (stationarity, orthogonal impulse responses, etc.) are performed to discover the analytical structure of the time series and to provide deep insights about their relationships. The whole theoretical analysis has an experimental counterpart since a set of trials across a real-world LTE-Advanced environment has been performed to collect, post-process and analyze about 600,000 voice packets, organized per flow and differentiated per codec.

Yuxuan Lin, Yang Chang, Xuan Tong et al.

In the advancement of industrial informatization, unsupervised anomaly detection technology effectively overcomes the scarcity of abnormal samples and significantly enhances the automation and reliability of smart manufacturing. As an important branch, industrial image anomaly detection focuses on automatically identifying visual anomalies in industrial scenarios (such as product surface defects, assembly errors, and equipment appearance anomalies) through computer vision techniques. With the rapid development of Unsupervised industrial Image Anomaly Detection (UIAD), excellent detection performance has been achieved not only in RGB setting but also in 3D and multimodal (RGB and 3D) settings. However, existing surveys primarily focus on UIAD tasks in RGB setting, with little discussion in 3D and multimodal settings. To address this gap, this artical provides a comprehensive review of UIAD tasks in the three modal settings. Specifically, we first introduce the task concept and process of UIAD. We then overview the research on UIAD in three modal settings (RGB, 3D, and multimodal), including datasets and methods, and review multimodal feature fusion strategies in multimodal setting. Finally, we summarize the main challenges faced by UIAD tasks in the three modal settings, and offer insights into future development directions, aiming to provide researchers with a comprehensive reference and offer new perspectives for the advancement of industrial informatization. Corresponding resources are available at https://github.com/Sunny5250/Awesome-Multi-Setting-UIAD.

Yan Wang, Wei Song, Giancarlo Fortino et al.

Underwater images play a key role in ocean exploration, but often suffer from severe quality degradation due to light absorption and scattering in water medium. Although major breakthroughs have been made recently in the general area of image enhancement and restoration, the applicability of new methods for improving the quality of underwater images has not specifically been captured. In this paper, we review the image enhancement and restoration methods that tackle typical underwater image impairments, including some extreme degradations and distortions. Firstly, we introduce the key causes of quality reduction in underwater images, in terms of the underwater image formation model (IFM). Then, we review underwater restoration methods, considering both the IFM-free and the IFM-based approaches. Next, we present an experimental-based comparative evaluation of state-of-the-art IFM-free and IFM-based methods, considering also the prior-based parameter estimation algorithms of the IFM-based methods, using both subjective and objective analysis (the used code is freely available at https://github.com/wangyanckxx/Single-Underwater-Image-Enhancement-and-Color-Restoration). Starting from this study, we pinpoint the key shortcomings of existing methods, drawing recommendations for future research in this area. Our review of underwater image enhancement and restoration provides researchers with the necessary background to appreciate challenges and opportunities in this important field.

Diaeddin Rimawi, Antonio Liotta, Marco Todescato et al.

A Collaborative Artificial Intelligence System (CAIS) works with humans in a shared environment to achieve a common goal. To recover from a disruptive event that degrades its performance and ensures its resilience, a CAIS may then need to perform a set of actions either by the system, by the humans, or collaboratively together. As for any other system, recovery actions may cause energy adverse effects due to the additional required energy. Therefore, it is of paramount importance to understand which of the above actions can better trade-off between resilience and greenness. In this in-progress work, we propose an approach to automatically evaluate CAIS recovery actions for their ability to trade-off between the resilience and greenness of the system. We have also designed an experiment protocol and its application to a real CAIS demonstrator. Our approach aims to attack the problem from two perspectives: as a one-agent decision problem through optimization, which takes the decision based on the score of resilience and greenness, and as a two-agent decision problem through game theory, which takes the decision based on the payoff computed for resilience and greenness as two players of a cooperative game.

Edoardo Bianchi, Antonio Liotta

Estimating how well a person performs an action, rather than which action is performed, is central to coaching, rehabilitation, and talent identification. This task is challenging because proficiency is encoded in subtle differences in timing, balance, body mechanics, and execution, often distributed across multiple views and short temporal events. We discuss three recent contributions to multi-view proficiency estimation on Ego-Exo4D. SkillFormer introduces a parameter-efficient discriminative architecture for selective multi-view fusion; PATS improves temporal sampling by preserving locally dense excerpts of fundamental movements; and ProfVLM reformulates proficiency estimation as conditional language generation, producing both a proficiency label and expert-style feedback through a gated cross-view projector and a compact language backbone. Together, these methods achieve state-of-the-art accuracy on Ego-Exo4D with up to 20x fewer trainable parameters and up to 3x fewer training epochs than video-transformer baselines, while moving from closed-set classification toward interpretable feedback generation. These results highlight a shift toward efficient, multi-view systems that combine selective fusion, proficiency-aware sampling, and actionable generative feedback.

Edoardo Bianchi, Antonio Liotta

Automated sports skill assessment requires capturing fundamental movement patterns that distinguish expert from novice performance, yet current video sampling methods disrupt the temporal continuity essential for proficiency evaluation. To this end, we introduce Proficiency-Aware Temporal Sampling (PATS), a novel sampling strategy that preserves complete fundamental movements within continuous temporal segments for multi-view skill assessment. PATS adaptively segments videos to ensure each analyzed portion contains full execution of critical performance components, repeating this process across multiple segments to maximize information coverage while maintaining temporal coherence. Evaluated on the EgoExo4D benchmark with SkillFormer, PATS surpasses the state-of-the-art accuracy across all viewing configurations (+0.65% to +3.05%) and delivers substantial gains in challenging domains (+26.22% bouldering, +2.39% music, +1.13% basketball). Systematic analysis reveals that PATS successfully adapts to diverse activity characteristics-from high-frequency sampling for dynamic sports to fine-grained segmentation for sequential skills-demonstrating its effectiveness as an adaptive approach to temporal sampling that advances automated skill assessment for real-world applications. Visit our project page at https://edowhite.github.io/PATS

Edoardo Bianchi, Antonio Liotta

Assessing human skill levels in complex activities is a challenging problem with applications in sports, rehabilitation, and training. In this work, we present SkillFormer, a parameter-efficient architecture for unified multi-view proficiency estimation from egocentric and exocentric videos. Building on the TimeSformer backbone, SkillFormer introduces a CrossViewFusion module that fuses view-specific features using multi-head cross-attention, learnable gating, and adaptive self-calibration. We leverage Low-Rank Adaptation to fine-tune only a small subset of parameters, significantly reducing training costs. In fact, when evaluated on the EgoExo4D dataset, SkillFormer achieves state-of-the-art accuracy in multi-view settings while demonstrating remarkable computational efficiency, using 4.5x fewer parameters and requiring 3.75x fewer training epochs than prior baselines. It excels in multiple structured tasks, confirming the value of multi-view integration for fine-grained skill assessment. Project page at https://edowhite.github.io/SkillFormer

Diaeddin Rimawi, Antonio Liotta, Marco Todescato et al.

A Collaborative Artificial Intelligence System (CAIS) performs actions in collaboration with the human to achieve a common goal. CAISs can use a trained AI model to control human-system interaction, or they can use human interaction to dynamically learn from humans in an online fashion. In online learning with human feedback, the AI model evolves by monitoring human interaction through the system sensors in the learning state, and actuates the autonomous components of the CAIS based on the learning in the operational state. Therefore, any disruptive event affecting these sensors may affect the AI model's ability to make accurate decisions and degrade the CAIS performance. Consequently, it is of paramount importance for CAIS managers to be able to automatically track the system performance to understand the resilience of the CAIS upon such disruptive events. In this paper, we provide a new framework to model CAIS performance when the system experiences a disruptive event. With our framework, we introduce a model of performance evolution of CAIS. The model is equipped with a set of measures that aim to support CAIS managers in the decision process to achieve the required resilience of the system. We tested our framework on a real-world case study of a robot collaborating online with the human, when the system is experiencing a disruptive event. The case study shows that our framework can be adopted in CAIS and integrated into the online execution of the CAIS activities.

Davide Domini, Laura Erhan, Gianluca Aguzzi et al.

Federated Learning offers privacy-preserving collaborative intelligence but struggles to meet the sustainability demands of emerging IoT ecosystems necessary for Society 5.0-a human-centered technological future balancing social advancement with environmental responsibility. The excessive communication bandwidth and computational resources required by traditional FL approaches make them environmentally unsustainable at scale, creating a fundamental conflict with green AI principles as billions of resource-constrained devices attempt to participate. To this end, we introduce Sparse Proximity-based Self-Federated Learning (SParSeFuL), a resource-aware approach that bridges this gap by combining aggregate computing for self-organization with neural network sparsification to reduce energy and bandwidth consumption.

Edoardo Bianchi, Jacopo Staiano, Antonio Liotta

Existing approaches to skill proficiency estimation often rely on black-box video classifiers, ignoring multi-view context and lacking explainability. We present ProfVLM, a compact vision-language model that reformulates this task as generative reasoning: it jointly predicts skill level and generates expert-like feedback from egocentric and exocentric videos. Central to our method is an AttentiveGatedProjector that dynamically fuses multi-view features, projected from a frozen TimeSformer backbone into a language model tuned for feedback generation. Trained on EgoExo4D with expert commentaries, ProfVLM surpasses state-of-the-art methods while using up to 20x fewer parameters and reducing training time by up to 60%. Our approach not only achieves superior accuracy across diverse activities, but also outputs natural language critiques aligned with performance, offering transparent reasoning. These results highlight generative vision-language modeling as a powerful new direction for skill assessment.

Muhammad Usman Yaseen, Ashiq Anjum, Giancarlo Fortino et al.

Object recognition from live video streams comes with numerous challenges such as the variation in illumination conditions and poses. Convolutional neural networks (CNNs) have been widely used to perform intelligent visual object recognition. Yet, CNNs still suffer from severe accuracy degradation, particularly on illumination-variant datasets. To address this problem, we propose a new CNN method based on orientation fusion for visual object recognition. The proposed cloud-based video analytics system pioneers the use of bi-dimensional empirical mode decomposition to split a video frame into intrinsic mode functions (IMFs). We further propose these IMFs to endure Reisz transform to produce monogenic object components, which are in turn used for the training of CNNs. Past works have demonstrated how the object orientation component may be used to pursue accuracy levels as high as 93\%. Herein we demonstrate how a feature-fusion strategy of the orientation components leads to further improving visual recognition accuracy to 97\%. We also assess the scalability of our method, looking at both the number and the size of the video streams under scrutiny. We carry out extensive experimentation on the publicly available Yale dataset, including also a self generated video datasets, finding significant improvements (both in accuracy and scale), in comparison to AlexNet, LeNet and SE-ResNeXt, which are the three most commonly used deep learning models for visual object recognition and classification.

Mario Di Mauro, Giovanni Galatro, Giancarlo Fortino et al.

Machine Learning (ML) techniques are becoming an invaluable support for network intrusion detection, especially in revealing anomalous flows, which often hide cyber-threats. Typically, ML algorithms are exploited to classify/recognize data traffic on the basis of statistical features such as inter-arrival times, packets length distribution, mean number of flows, etc. Dealing with the vast diversity and number of features that typically characterize data traffic is a hard problem. This results in the following issues: i) the presence of so many features leads to lengthy training processes (particularly when features are highly correlated), while prediction accuracy does not proportionally improve; ii) some of the features may introduce bias during the classification process, particularly those that have scarce relation with the data traffic to be classified. To this end, by reducing the feature space and retaining only the most significant features, Feature Selection (FS) becomes a crucial pre-processing step in network management and, specifically, for the purposes of network intrusion detection. In this review paper, we complement other surveys in multiple ways: i) evaluating more recent datasets (updated w.r.t. obsolete KDD 99) by means of a designed-from-scratch Python-based procedure; ii) providing a synopsis of most credited FS approaches in the field of intrusion detection, including Multi-Objective Evolutionary techniques; iii) assessing various experimental analyses such as feature correlation, time complexity, and performance. Our comparisons offer useful guidelines to network/security managers who are considering the incorporation of ML concepts into network intrusion detection, where trade-offs between performance and resource consumption are crucial.

Mario Di Mauro, Giovanni Galatro, Antonio Liotta

The use of Machine Learning (ML) techniques in Intrusion Detection Systems (IDS) has taken a prominent role in the network security management field, due to the substantial number of sophisticated attacks that often pass undetected through classic IDSs. These are typically aimed at recognising attacks based on a specific signature, or at detecting anomalous events. However, deterministic, rule-based methods often fail to differentiate particular (rarer) network conditions (as in peak traffic during specific network situations) from actual cyber attacks. In this paper we provide an experimental-based review of neural-based methods applied to intrusion detection issues. Specifically, we i) offer a complete view of the most prominent neural-based techniques relevant to intrusion detection, including deep-based approaches or weightless neural networks, which feature surprising outcomes; ii) evaluate novel datasets (updated w.r.t. the obsolete KDD99 set) through a designed-from-scratch Python-based routine; iii) perform experimental analyses including time complexity and performance (accuracy and F-measure), considering both single-class and multi-class problems, and identifying trade-offs between resource consumption and performance. Our evaluation quantifies the value of neural networks, particularly when state-of-the-art datasets are used to train the models. This leads to interesting guidelines for security managers and computer network practitioners who are looking at the incorporation of neural-based ML into IDS.

Lucia Cavallaro, Annamaria Ficara, Pasquale De Meo et al.

Compared to other types of social networks, criminal networks present hard challenges, due to their strong resilience to disruption, which poses severe hurdles to law-enforcement agencies. Herein, we borrow methods and tools from Social Network Analysis to (i) unveil the structure of Sicilian Mafia gangs, based on two real-world datasets, and (ii) gain insights as to how to efficiently disrupt them. Mafia networks have peculiar features, due to the links distribution and strength, which makes them very different from other social networks, and extremely robust to exogenous perturbations. Analysts are also faced with the difficulty in collecting reliable datasets that accurately describe the gangs' internal structure and their relationships with the external world, which is why earlier studies are largely qualitative, elusive and incomplete. An added value of our work is the generation of two real-world datasets, based on raw data derived from juridical acts, relating to a Mafia organization that operated in Sicily during the first decade of 2000s. We created two different networks, capturing phone calls and physical meetings, respectively. Our network disruption analysis simulated different intervention procedures: (i) arresting one criminal at a time (sequential node removal); and (ii) police raids (node block removal). We measured the effectiveness of each approach through a number of network centrality metrics. We found Betweeness Centrality to be the most effective metric, showing how, by neutralizing only the 5% of the affiliates, network connectivity dropped by 70%. We also identified that, due the peculiar type of interactions in criminal networks (namely, the distribution of the interactions frequency) no significant differences exist between weighted and unweighted network analysis. Our work has significant practical applications for tackling criminal and terrorist networks.

Wei Song, Yan Wang, Dongmei Huang et al.

Underwater images often have severe quality degradation and distortion due to light absorption and scattering in the water medium. A hazed image formation model is widely used to restore the image quality. It depends on two optical parameters: the background light and the transmission map. Underwater images can also be enhanced by color and contrast correction from the perspective of image processing. In this paper, we propose an effective underwater image enhancement method for underwater images in composition of underwater image restoration and color correction. Firstly, a manually annotated background lights (MABLs) database is developed. With reference to the relationship between MABLs and the histogram distributions of various underwater images, robust statistical models of BLs estimation are provided. Next, the TM of R channel is roughly estimated based on the new underwater dark channel prior via the statistic of clear and high resolution underwater images, then a scene depth map based on the underwater light attenuation prior and an adjusted reversed saturation map are applied to compensate and modify the coarse TM of R channel. Next, TMs of G-B channels are estimated based on the difference of attenuation ratios between R channel and G-B channels. Finally, to improve the color and contrast of the restored image with a natural appearance, a variation of white balance is introduced as post-processing. In order to guide the priority of underwater image enhancement, sufficient evaluations are conducted to discuss the impacts of the key parameters including BL and TM, and the importance of the color correction. Comparisons with other state-of-the-art methods demonstrate that our proposed underwater image enhancement method can achieve higher accuracy of estimated BLs, less computation time, more superior performance, and more valuable information retention.

Elena Mocanu, Decebal Constantin Mocanu, Phuong H. Nguyen et al.

Unprecedented high volumes of data are becoming available with the growth of the advanced metering infrastructure. These are expected to benefit planning and operation of the future power system, and to help the customers transition from a passive to an active role. In this paper, we explore for the first time in the smart grid context the benefits of using Deep Reinforcement Learning, a hybrid type of methods that combines Reinforcement Learning with Deep Learning, to perform on-line optimization of schedules for building energy management systems. The learning procedure was explored using two methods, Deep Q-learning and Deep Policy Gradient, both of them being extended to perform multiple actions simultaneously. The proposed approach was validated on the large-scale Pecan Street Inc. database. This highly-dimensional database includes information about photovoltaic power generation, electric vehicles as well as buildings appliances. Moreover, these on-line energy scheduling strategies could be used to provide real-time feedback to consumers to encourage more efficient use of electricity.

Decebal Constantin Mocanu, Elena Mocanu, Peter Stone et al.

Through the success of deep learning in various domains, artificial neural networks are currently among the most used artificial intelligence methods. Taking inspiration from the network properties of biological neural networks (e.g. sparsity, scale-freeness), we argue that (contrary to general practice) artificial neural networks, too, should not have fully-connected layers. Here we propose sparse evolutionary training of artificial neural networks, an algorithm which evolves an initial sparse topology (Erdős-Rényi random graph) of two consecutive layers of neurons into a scale-free topology, during learning. Our method replaces artificial neural networks fully-connected layers with sparse ones before training, reducing quadratically the number of parameters, with no decrease in accuracy. We demonstrate our claims on restricted Boltzmann machines, multi-layer perceptrons, and convolutional neural networks for unsupervised and supervised learning on 15 datasets. Our approach has the potential to enable artificial neural networks to scale up beyond what is currently possible.

Decebal Constantin Mocanu, Maria Torres Vega, Eric Eaton et al.

Conceived in the early 1990s, Experience Replay (ER) has been shown to be a successful mechanism to allow online learning algorithms to reuse past experiences. Traditionally, ER can be applied to all machine learning paradigms (i.e., unsupervised, supervised, and reinforcement learning). Recently, ER has contributed to improving the performance of deep reinforcement learning. Yet, its application to many practical settings is still limited by the memory requirements of ER, necessary to explicitly store previous observations. To remedy this issue, we explore a novel approach, Online Contrastive Divergence with Generative Replay (OCD_GR), which uses the generative capability of Restricted Boltzmann Machines (RBMs) instead of recorded past experiences. The RBM is trained online, and does not require the system to store any of the observed data points. We compare OCD_GR to ER on 9 real-world datasets, considering a worst-case scenario (data points arriving in sorted order) as well as a more realistic one (sequential random-order data points). Our results show that in 64.28% of the cases OCD_GR outperforms ER and in the remaining 35.72% it has an almost equal performance, while having a considerably reduced space complexity (i.e., memory usage) at a comparable time complexity.

Maria Torres Vega, Decebal Constantin Mocanu, Antonio Liotta

Among the various means to evaluate the quality of video streams, No-Reference (NR) methods have low computation and may be executed on thin clients. Thus, NR algorithms would be perfect candidates in cases of real-time quality assessment, automated quality control and, particularly, in adaptive mobile streaming. Yet, existing NR approaches are often inaccurate, in comparison to Full-Reference (FR) algorithms, especially under lossy network conditions. In this work, we present an NR method that combines machine learning with simple NR metrics to achieve a quality index comparably as accurate as the Video Quality Metric (VQM) Full-Reference algorithm. Our method is tested in an extensive dataset (960 videos), under lossy network conditions and considering nine different machine learning algorithms. Overall, we achieve an over 97% correlation with VQM, while allowing real-time assessment of video quality of experience in realistic streaming scenarios.

Decebal Constantin Mocanu, Elena Mocanu, Phuong H. Nguyen et al.

Restricted Boltzmann Machines (RBMs) and models derived from them have been successfully used as basic building blocks in deep artificial neural networks for automatic features extraction, unsupervised weights initialization, but also as density estimators. Thus, their generative and discriminative capabilities, but also their computational time are instrumental to a wide range of applications. Our main contribution is to look at RBMs from a topological perspective, bringing insights from network science. Firstly, here we show that RBMs and Gaussian RBMs (GRBMs) are bipartite graphs which naturally have a small-world topology. Secondly, we demonstrate both on synthetic and real-world datasets that by constraining RBMs and GRBMs to a scale-free topology (while still considering local neighborhoods and data distribution), we reduce the number of weights that need to be computed by a few orders of magnitude, at virtually no loss in generative performance. Thirdly, we show that, for a fixed number of weights, our proposed sparse models (which by design have a higher number of hidden neurons) achieve better generative capabilities than standard fully connected RBMs and GRBMs (which by design have a smaller number of hidden neurons), at no additional computational costs.

Decebal Constantin Mocanu, Haitham Bou Ammar, Luis Puig et al.

Estimation, recognition, and near-future prediction of 3D trajectories based on their two dimensional projections available from one camera source is an exceptionally difficult problem due to uncertainty in the trajectories and environment, high dimensionality of the specific trajectory states, lack of enough labeled data and so on. In this article, we propose a solution to solve this problem based on a novel deep learning model dubbed Disjunctive Factored Four-Way Conditional Restricted Boltzmann Machine (DFFW-CRBM). Our method improves state-of-the-art deep learning techniques for high dimensional time-series modeling by introducing a novel tensor factorization capable of driving forth order Boltzmann machines to considerably lower energy levels, at no computational costs. DFFW-CRBMs are capable of accurately estimating, recognizing, and performing near-future prediction of three-dimensional trajectories from their 2D projections while requiring limited amount of labeled data. We evaluate our method on both simulated and real-world data, showing its effectiveness in predicting and classifying complex ball trajectories and human activities.

Aravind Kota Gopalakrishna, Tanir Ozcelebi, Antonio Liotta et al.

In machine learning, the choice of a learning algorithm that is suitable for the application domain is critical. The performance metric used to compare different algorithms must also reflect the concerns of users in the application domain under consideration. In this work, we propose a novel probability-based performance metric called Relevance Score for evaluating supervised learning algorithms. We evaluate the proposed metric through empirical analysis on a dataset gathered from an intelligent lighting pilot installation. In comparison to the commonly used Classification Accuracy metric, the Relevance Score proves to be more appropriate for a certain class of applications.