Andrea Pinna

Matteo Vaccargiu, Riccardo Lai, Maria Ilaria Lunesu et al.

We study how bots contribute to open-source discussions in the Ethereum ecosystem and whether they influence developers' emotional tone. Our dataset covers 36,875 accounts across ten repositories with 105 validated bots (0.28%). Human participation follows a U-shaped pattern, while bots engage in uniform (pull requests) or late-stage (issues) activity. Bots respond faster than humans in pull requests but play slower maintenance roles in issues. Using a model trained on 27 emotion categories, we find bots are more neutral, yet their interventions are followed by reduced neutrality in human comments, with shifts toward gratitude, admiration, and optimism and away from confusion. These findings indicate that even a small number of bots are associated with changes in both timing and emotional dynamics of developer communication.

Kamil Jeziorek, Andrea Pinna, Tomasz Kryjak

Recent advances in event camera research emphasize processing data in its original sparse form, which allows the use of its unique features such as high temporal resolution, high dynamic range, low latency, and resistance to image blur. One promising approach for analyzing event data is through graph convolutional networks (GCNs). However, current research in this domain primarily focuses on optimizing computational costs, neglecting the associated memory costs. In this paper, we consider both factors together in order to achieve satisfying results and relatively low model complexity. For this purpose, we performed a comparative analysis of different graph convolution operations, considering factors such as execution time, the number of trainable model parameters, data format requirements, and training outcomes. Our results show a 450-fold reduction in the number of parameters for the feature extraction module and a 4.5-fold reduction in the size of the data representation while maintaining a classification accuracy of 52.3%, which is 6.3% higher compared to the operation used in state-of-the-art approaches. To further evaluate performance, we implemented the object detection architecture and evaluated its performance on the N-Caltech101 dataset. The results showed an accuracy of 53.7 % mAP@0.5 and reached an execution rate of 82 graphs per second.

Kamil Jeziorek, Piotr Wzorek, Krzysztof Blachut et al.

The utilisation of event cameras represents an important and swiftly evolving trend aimed at addressing the constraints of traditional video systems. Particularly within the automotive domain, these cameras find significant relevance for their integration into embedded real-time systems due to lower latency and energy consumption. One effective approach to ensure the necessary throughput and latency for event processing is through the utilisation of graph convolutional networks (GCNs). In this study, we introduce a custom EFGCN (Event-based FPGA-accelerated Graph Convolutional Network) designed with a series of hardware-aware optimisations tailored for PointNetConv, a graph convolution designed for point cloud processing. The proposed techniques result in up to 100-fold reduction in model size compared to Asynchronous Event-based GNN (AEGNN), one of the most recent works in the field, with a relatively small decrease in accuracy (2.9% for the N-Caltech101 classification task, 2.2% for the N-Cars classification task), thus following the TinyML trend. We implemented EFGCN on a ZCU104 SoC FPGA platform without any external memory resources, achieving a throughput of 13.3 million events per second (MEPS) and real-time partially asynchronous processing with low latency. Our approach achieves state-of-the-art performance across multiple event-based classification benchmarks while remaining highly scalable, customisable and resource-efficient. We publish both software and hardware source code in an open repository: https://github.com/vision-agh/gcnn-dvs-fpga

Matteo Vaccargiu, Andrea Pinna, Maria Ilaria Lunesu et al.

Smart contract vulnerabilities have caused billions in financial losses, raising questions about whether programming language paradigms can reduce security overhead. While imperative languages like Solidity require developers to manually implement security checks, resource-oriented languages like Move encode safety guarantees in type systems. We present a preliminary mixed-methods study analyzing 12 functionally-equivalent contract pairs implemented in both Solidity and Move by the same development team, complemented by a survey of 11 developers experienced in both languages. Quantitative analysis reveals that Move reduces explicit security overhead by 60\% (security check density: 6.7% vs. 16.8%, p=0.002, Cohen's d=-1.75) at the cost of 47% larger code size (p=0.002, d=1.90), while maintaining identical cyclomatic complexity. Developer surveys show moderate learning difficulty but higher safety confidence in Move (Median=6/7, 10 of 11 above neutral), with 55% preferring Move for security-critical applications despite ecosystem maturity gaps. These preliminary findings suggest resource-oriented paradigms shift security from runtime validation to compile-time guarantees, though adoption requires investment in learning and tooling. The controlled comparison provides initial evidence for paradigm effects on smart contract development, informing language selection decisions and identifying opportunities for improved developer resources.

Kamil Jeziorek, Piotr Wzorek, Krzysztof Blachut et al.

Event-based vision is an emerging research field involving processing data generated by Dynamic Vision Sensors (neuromorphic cameras). One of the latest proposals in this area are Graph Convolutional Networks (GCNs), which allow to process events in its original sparse form while maintaining high detection and classification performance. In this paper, we present the hardware implementation of a~graph generation process from an event camera data stream, taking into account both the advantages and limitations of FPGAs. We propose various ways to simplify the graph representation and use scaling and quantisation of values. We consider both undirected and directed graphs that enable the use of PointNet convolution. The results obtained show that by appropriately modifying the graph representation, it is possible to create a~hardware module for graph generation. Moreover, the proposed modifications have no significant impact on object detection performance, only 0.08% mAP less for the base model and the N-Caltech data set.Finally, we describe the proposed hardware architecture of the graph generation module.

Piotr Wzorek, Kamil Jeziorek, Tomasz Kryjak et al.

Event cameras are becoming increasingly popular as an alternative to traditional frame-based vision sensors, especially in mobile robotics. Taking full advantage of their high temporal resolution, high dynamic range, low power consumption and sparsity of event data, which only reflects changes in the observed scene, requires both an efficient algorithm and a specialised hardware platform. A recent trend involves using Graph Convolutional Neural Networks (GCNNs) implemented on a heterogeneous SoC FPGA. In this paper we focus on optimising hardware modules for graph convolution to allow flexible selection of the FPGA resource (BlockRAM, DSP and LUT) for their implementation. We propose a ''two-step convolution'' approach that utilises additional BRAM buffers in order to reduce up to 94% of LUT usage for multiplications. This method significantly improves the scalability of GCNNs, enabling the deployment of models with more layers, larger graphs sizes and their application for more dynamic scenarios.

Fabio Caddeo, Andrea Pinna

The tourism industry is increasingly influenced by the evolution of information and communication technologies (ICT), which are revolutionizing the way people travel. In this work we want to nvestigate the use of innovative IT technologies by DMOs (Destination Management Organizations), focusing on blockchain technology, both from the point of view of research in the field, and in the study of the most relevant software projects. In particular, we intend to verify the benefits offered by these IT tools in the management and monitoring of a destination, without forgetting the implications for the other stakeholders involved. These technologies, in fact, can offer a wide range of services that can be useful throughout the life cycle of the destination.

Andrea Pinna, Simona Ibba

Temporary work is an employment situation useful and suitable in all occasions in which business needs to adjust more easily and quickly to workload fluctuations or maintain staffing flexibility. Temporary workers play therefore an important role in many companies, but this kind of activity is subject to a special form of legal protections and many aspects and risks must be taken into account both employers and employees. In this work we propose a blockchain-based system that aims to ensure respect for the rights for all actors involved in a temporary employment, in order to provide employees with the fair and legal remuneration (including taxes) of work performances and a protection in the case employer becomes insolvent. At the same time, our system wants to assist the employer in processing contracts with a fully automated and fast procedure. To resolve these problems we propose the D-ES (Decentralized Employment System). We first model the employment relationship as a state system. Then we describe the enabling technology that makes us able to realize the D-ES. In facts, we propose the implementation of a DLT (Decentralized Ledger Technology) based system, consisting in a blockchain system and of a web-based environment. Thanks the decentralized application platforms that makes us able to develop smart contracts, we define a discrete event control system that works inside the blockchain. In addition, we discuss the temporary work in agriculture as a interesting case of study.

Andrea Pinna, Roberto Tonelli, Matteo Orrú et al.

A Blockchain is a global shared infrastructure where cryptocurrency transactions among addresses are recorded, validated and made publicly available in a peer- to-peer network. To date the best known and important cryptocurrency is the bitcoin. In this paper we focus on this cryptocurrency and in particular on the modeling of the Bitcoin Blockchain by using the Petri Nets formalism. The proposed model allows us to quickly collect information about identities owning Bitcoin addresses and to recover measures and statistics on the Bitcoin network. By exploiting algebraic formalism, we reconstructed an Entities network associated to Blockchain transactions gathering together Bitcoin addresses into the single entity holding permits to manage Bitcoins held by those addresses. The model allows also to identify a set of behaviours typical of Bitcoin owners, like that of using an address only once, and to reconstruct chains for this behaviour together with the rate of firing. Our model is highly flexible and can easily be adapted to include different features of the Bitcoin crypto-currency system.

Simone Porru, Andrea Pinna, Michele Marchesi et al.

The Blockchain technology is reshaping finance, economy, money to the extent that its disruptive power is compared to that of the Internet and the Web in their early days. As a result, all the software development revolving around the Blockchain technology is growing at a staggering rate. In this paper, we acknowledge the need for software engineers to devise specialized tools and techniques for blockchain-oriented software development. From current challenges concerning the definition of new professional roles, demanding testing activities and novel tools for software architecture, we take a step forward by proposing new directions on the basis of a curate corpus of blockchain-oriented software repositories, detected by exploiting the information enclosed in the 2016 Moody's Blockchain Report and teh market capitalization of cryptocurrencies. Ensuring effective testing activities, enhancing collaboration in large teams, and facilitating the development of smart contracts all appear as key factors in the future of blockchain-oriented software development.