Route planning is a fundamental function for autonomous vehicles (AVs) tasked with navigating complex road networks. Traditional formulations of the route planning problem typically assume a single destination, where the solution is defined as the optimal path from the starting point to the designated goal. In this paper, we introduce a two-stage hierarchical route planning algorithm designed to determine a feasible and optimal route that sequentially connects multiple target points within a road network. Our approach employs a graph-based representation of the road network and systematically integrates global and local search strategies to guarantee both the feasibility and minimality of the resulting route. The proposed approach also introduces a semantic representation of the planned route, providing natural language indications and specifying the planned behaviour of the car. This is accomplished by classifying the discrete points that define the planned route. The validity of the proposed approach was tested experimentally on a 1:10 scale autonomous vehicle.

Alzheimer's Disease (AD) is the most common neurodegenerative disease. Its first stage, namely prodromal or Mild Cognitive Impairment (MCI), is characterized by slightly structural changes in the subcortical structures of the temporal lobe. Brain Magnetic Resonance (MR) is the most utilized neu-roimaging modality for the diagnosis of AD. Although an early therapeutic intervention during the initial stages of AD appears to have a positive impact on the progression of symptoms, its accurate diagnosis is still very difficult. Deep Learning (DL)-based decision-support systems hold great potential in generalizing even under subtle anatomical changes of the brain, like the ones caused by AD at its onset. To our knowledge, we were the first to develop a Convolutional Long Short-Term Memory (ConvLSTM)-based decision-support system and an improved version of it for the automatic diagnosis of AD from 3D brain MR. The research presented in this paper aims to extend their applicability to MCI for effectiveness verification through the development of CLAUDIA, a new on-cloud decision-support system for the automatic diagnosis of Alzheimer's prodromal stage and disease from 3D brain MR. To this aim, we selected 438 unenhanced scans from the ADNI-1 dataset, preprocessed them, and injected the preprocessed scans to the ConvLSTM-based neural network for automatic feature extraction and binary/multiclass classification. On test data, CLAUDIA achieved very encouraging results that highlight the superiority of the multiclass classifier in comparison to the two binary classifiers. On the basis of the achieved outcomes, we demonstrated that CLAUDIA, being the first to extend the applicability of a ConvLSTM-based neural network to MCI for effectiveness verification, represents a promising scan-, DL-based decision-support system for the automatic diagnosis of Alzheimer's prodromal stage and disease from 3D brain MR. Moreover, its cloud thus machine-independent nature ensures a full reproducibility of the implementation while guaranteeing cost saving and sustainability.

This paper focuses on the study and development of learning algorithms oriented to wear classification and predictive maintenance (PdM) of the cutting tool (CT) of a clamping machine for producing structural steel bars. While several works dedicated to CTs for turning and milling operations, or in general for metal removal operations, also known as subtractive manufacturing processes, can be found in the literature, the phenomena related to cutting with a cutting knife have not been widely treated in the literature. This article intends to focus on the analysis of the latter problem. The objective is to estimate the wear of the CT, a critical component of the steel bar cutting machine. The SVM classifiers were therefore used to classify the wear. For the predictive maintenance purpose, two algorithms were implemented for the prediction of the remaining service life, based on the Degradation Model and the Similarity Model respectively; in the first method, a prediction and state update function were used, while in the second method, a Long Short-Term Memory (LSTM) Neural Network (NN) was used.

Alzheimer's Disease (AD) is the most prevailing form of dementia, killing more people than prostate and breast cancers combined. Structural Magnetic Resonance Imaging (sMRI) is widely used for the analysis of progressive brain aggravation and its clinical utility in discriminating AD is well established. Even if an effective cure does not exist yet, early detection is fundamental for slowing down the worsening of symptoms. Thus, the aim of the present work is to propose an end-to-end 3D Convolutional Long Short-Term Memory (ConvLSTM)-based framework for early diagnosis of AD from full-resolution whole-brain sMRI scans. The proposed framework was applied to 427 full-resolution whole-brain sMRI scans belonging to both OASIS and ADNI databases in order to provide a less dataset-specific approach. Results show that our framework is performing well in discriminating AD from Cognitively Normal (CN) patients, reaching a classification accuracy of 86%, sensitivity of 96%, f1-score of 88% and AUC of 93% on the test data. The tests were performed on a scalable GPU cloud service and are publicly available to guarantee reproducibility. Since the proposed framework performs well without domain-specific knowledge from AD as well as computationally-costly processes such as segmentation, it can be applied to other mental disorders using whole-brain sMRI scans as input data.

This paper confronts with a reflection about a deep problem in computational models for cyber-physical systems (CPS). The problem arises in the contact between digital computing and the physical realm, and affects heavily the design, modeling, and implementation of CPS. Problems are exacerbated by the introduction of artificial intelligence and autonomy in industrial applications that have to meet sustainability of solutions, both in technical and societal sense. After a brief review, a new perspective and position on the future of sustainable CPS is addressed, and a pragmatic research path is presented. The RMAS (Relational-model Multi-Agent System) architecture is proposed as a test framework for the deep integration of real-world semantics into the advancements brought about by the digital transformation wave.

Abstract Since its dawn as a discipline, Artificial Intelligence (AI) has focused on mimicking the human mental processes. As AI applications matured, the interest for employing them into real-world complex systems (i.e., coupling AI with Cyber-Physical Systems—CPS) kept increasing. In the last decades, the multi-agent systems (MAS) paradigm has been among the most relevant approaches fostering the development of intelligent systems. In numerous scenarios, MAS boosted distributed autonomous reasoning and behaviors. However, many real-world applications (e.g., CPS) demand the respect of strict timing constraints. Unfortunately, current AI/MAS theories and applications onlyreason“about time” and are incapable ofacting“in time” guaranteeing any timing predictability. This paper analyzes the MAS compliance with strict timing constraints (real-time compliance)—crucial for safety-critical applications such as healthcare, industry 4.0, and automotive. Moreover, it elicits the main reasons for the lack of real-time satisfiability in MAS (originated from current theories, standards, and implementations). In particular, traditional internal agent schedulers (general-purpose-like), communication middlewares, and negotiation protocols have been identified as co-factors inhibiting real-time compliance. To pave the road towards reliable and predictable MAS, this paper postulates a formal definition and mathematical model of real-time multi-agent systems (RT-MAS). Furthermore, this paper presents the results obtained by testing the dynamics characterizing the RT-MAS model within the simulator MAXIM-GPRT. Thus, it has been possible to analyze the deadline miss ratio between the algorithms employed in the most popular frameworks and the proposed ones. Finally, discussing the obtained results, the ongoing and future steps are outlined.

The following topics are dealt with: Internet; Internet of Things; health care; geriatrics; medical signal processing; brain-computer interfaces; electroencephalography; ubiquitous computing; optimisation; indoor radio.

Uncertainty is inevitable in ambient assisted living (AAL) environments as sensors may read inaccurate data or due to the existence of unobserved variables for privacy reasons. Furthermore, the dynamic nature of the home environment and vague human communications may result in ambiguous, incomplete and inconsistent contextual information, which ultimately lead the smart home system into uncertainty. This paper aims to tackle some of these challenges, in particular, uncertainty due to vague human communication and missing information in ambient environments. For this, we proposed a probabilistic multi-agent system architecture for reasoning in smart homes by utilizing the notion of multiagent systems (MAS) technologies and probabilistic logic programming techniques. Accordingly, this study shows how the probabilistic reasoning technique enables the agents to reason under uncertainty. Furthermore, it discusses how the intelligent agents enhance their decision-making process by exchanging information about missing data or unobservable variables using agent interaction protocols. In general, the study demonstrates that the combination of MAS technologies and probabilistic logic programming can help in building a reasoning system, which is capable of performing well under vague inhabitant commands and missing information in a partially observable environment.

Cyber Physical Systems (CPS) require a multitude of components interacting among themselves and with the users to perform automatic actions, usually under unpredictable or uncertain conditions. Multi-Agent Systems (MAS) have emerged over the years as one of the major technological paradigms regulating interactions and negotiations among autonomous entities running under heterogeneous conditions. As such, MAS have the potential to support CPS in implementing a highly reconfigurable distributed thinking. However, some gaps are still present between MAS’ features and the strict requirements of CPS. The most relevant is the lack of reliability, which is mainly due to specific features characterizing negotiation protocols. This paper presents a systematic literature review of MAS negotiation protocols aiming at providing a comprehensive overview of their strengths and limitations, examining both the assumptions and requirements set during their development. While this work confirms the potential of MAS in regulating the interactions among CPS components, the findings also highlight the absence of real-time compliance in current negotiation protocols. Strongly characterizing CPS, the capability to face strict time constraints could bridge the gap between MAS and CPS.

Some recent trends in distributed intelligent systems rely extensively on agent-based approaches. The so-called Multi-Agent Systems (MAS) are taking over the management of sensitive data on behalf of their producers and users (e.g., medical records, financial investment, energy market). Therefore, trusted interactions are needed more than ever, while accountability and transparency among the agents seem crucial characteristics to be achieved. To do so, recent trends advocate the use of blockchain technologies (BCT) in MAS. The blockchain is a distributed ledger technology that can execute programmable transaction logic, and provides a shared, immutable, and transparent append-only register of all the actions happening in the network. Although a few theoretical approaches have already been proposed, the quest for such a system consolidating BCT and MAS to guarantee privacy, scalability, transparency, and efficiency continues. This paper presents a reconciling system including BCT within the dynamics of a MAS. Such a system aims at (i) building a solid ground for trusted interactions and (ii) enabling more characterizing feature-based and trustworthy ways of computing agent reputation. The system has been tested in four scenarios with different configurations (regular executions and involving down-agents or malicious behaviors). Finally, the paper summarizes and discusses the experience gained, argues about the strategic choice of binding MAS and BCT, and presents some future challenges.

The multi-agent framework is a well-known approach to realize distributed intelligent systems. Multi-agent systems (MAS) are increasingly employed in safety-and information-critical domains (e.g., eHealth, cyber-physical systems, financial services, and energy market). Therefore, these systems need to be equipped with mechanisms to ensure transparency and the trustworthiness of the behaviors of their components. Trust can be achieved by employing reputation-based mechanisms. Nevertheless, the existing methods are still unable to fully guarantee the desired accountability and transparency. Aligned with the recent trends, advocating the distribution of trust to avoid the risks of having a single point of failure of the system, this work extends existing efforts on combining blockchain technologies (BCT) and MAS. To attain a trusted environment, we provide the architecture and implementation of a system that allows the agents to interact with each other and enables tracking how their reputation changes after every interaction. Agents reputations are computed transparently using smart contracts. Immutable distributed ledger stores reputation values, as well as services and their evaluations to ensure trustworthy interactions between the agents. We also developed a graphical interface to test different scenarios of interactions between the agents. Finally, we summarize and discuss the experience gained and explain the strategic choices when binding MAS and BCT.

The complexity of cyber-physical systems (CPSs) poses new challenges in their design, model checking and maintenance. The hardware and software designers are in search, more than ever, for simple and interoperable approaches that render the complexity of CPSs a treatable matter. In this work, database language is suggested as an enabling technology and a lean technique to the purpose. An example with best available embedded database technology is conducted by means of a deployment test on tiny embedded electronics.

The healthcare domain is wide and characterized by system and data herogeneity. To achieve high quality and efficiency standards, interoperability between different information systems is strongly required.

There are different proposals to extend RDF model theory allowing a treatment of uncertainty within the language. This works proposes a unified approach for RDF graph and statement labeling. This approach is more general than fuzzy and temporal labels and can be used to label RDF graphs with membership degrees, timestamps, or with a combination of labelings. Starting from a definition of labeled sets and labeled logic, we define labeled RDF and labeled RDF Schema. A partial ordering among labels allows qualitative treatment of uncertainty.

We propose a Hybrid System for dynamic environments, where a “Multiple Neural Networks” system works with Bayes Rule. One or more neural nets may no longer be able to properly operate, due to partial changes in some of the characteristics of the individuals. We assume that each expert network has a reliability factor that can be dynamically re-evaluated on the ground of the global recognition operated by the overall group. Since the net's degree of reliability is defined as the probability that the net is giving the desired output, in case of conflicts between the outputs of the various nets the re-evaluation of their degrees of reliability can be simply performed on the basis of the Bayes Rule. The new vector of reliability will be used for making the final choice, by applying two algorithms, the “Inclusion based” and the “Weighted” one over all the maximally consistent subsets of the global outcome.

A system of Multiple Neural Networks has been proposed to solve the face recognition problem. Our idea is that a set of expert networks specialized to recognize specific parts of face are better than a single network. This is because a single network could no longer be able to correctly recognize the subject when some characteristics partially change. For this purpose we assume that each network has a reliability factor defined as the probability that the network is giving the desired output. In case of conflicts between the outputs of the networks the reliability factor can be dynamically re-evaluated on the base of the Bayes Rule. The new reliabilities will be used to establish who is the subject. Moreover the network disagreed with the group and specialized to recognize the changed characteristic of the subject will be retrained and then forced to correctly recognize the subject. Then the system is subjected to continuous learning.

We propose a ¿multiple neural networks¿ system for dynamic environments, where one or more neural nets may no longer be able to properly operate, due to sensible partial changes in the characteristics of the individuals. We assume that each expert network has a reliability factor that can be dynamically re-evaluated on the ground of the global recognition operated by the overall group. Since the net's ¿degree of reliability¿ is defined as ¿the probability that the net is giving the desired output¿, in case of conflicts between the outputs of the various nets the re-evaluation of their ¿degrees of reliability¿ can be simply performed on the basis of the Bayes Rule. The new vector of reliability will be used for making the final choice, by applying the ¿inclusion based¿ algorithm over all the maximally consistent subsets of the global outcome. Finally, the nets recognized as responsible for the conflicts will be automatically forced to learn about the changes in the individuals' characteristics and avoid to make the same error in the immediate future.

The main problem with iris biometric identification systems is the presence of noises in the image of the eye (eyelid, eyelashes, etc...). To remove it many authors apply appropriate preprocessing to the image, but unfortunately this yields losses of information. Our work aims at correctly recognizing the subject also in presence of high rates of noise. The basic idea is that of partitioning the image of iris into 8 not-interleaved segments of the same size. Each segment is given to an LVQ network which generates prototypes with a high resistance to noise. Notwithstanding this, the 8 LVQ nets may still disagree in identifying the subject. In this paper we apply a method developed by the "belief revision" community to identify conflicts and rearrange the degrees of reliability of each expert (the LVQ nets) through a Bayesian algorithm. This estimated ranking of reliability is useful to take the final decision.

We present the architecture of an Inquiry Support System whose aim is to help a detective or a judge in eliciting a maximally consistent set of beliefs as the most believable piece of knowledge to reason with. This is done by (1) finding incoherence inside and across the various depositions; (2) generating the alternate maximally consistent set of beliefs; (3) estimating the degree of reliability of the various informants; and (4) estimating the degree of credibility of the various evidences. The solution of the case is searched among the various possible plots compatible with the maximally consistent set of beliefs retained by the system as the most believable one.

In order to perform effective communication, agents must be able to foresee the effects of their utterances on the addressee's mental state. In this paper we study the consequences of an utterance on the mental state of a hearer. Given an agent communication language with a STRIPS‐like semantics, we propose a set of criteria that allow the binding of the speaker's mental state to its uttering of a certain sentence. On the basis of these criteria, we give an abductive procedure that the hearer can adopt to partially recognize the speaker's mental state that led to a specific utterance.

We propose a distributed architecture for knowledge revisionintegration, where each element is conceived as a knowledgebased system able to exchange information with the others.since nodes can be affected by some degree of incompetence, part of the information running through the network may be incorrect and might cause contradictions in the knowledge base of some nodes.To manage these contradictions, each node is equipped with a belief revision module which makes it able to discriminate among more or less credible information and more or less reliable information sources.Our aim is that of comparing on a simulation basis the performances and the characteristics of this distributed system vs. those of a centralised architecture.We report here the fmt results of our experiments. .' % , .

INTRODUCTION Much of the detectives' and magistrates' task can be regarded as "knowledge processing." They have, typically, to acquire knowledge chunks, find the contradictions inside and across the various depositions, link the consistent hypotheses in a causally connected lattice and judge the credibility of the information and the reliability of the witnesses. * Sometimes, the complexity of the case could justify the assistance of an appropriate Decision Support System (DSS); we call Inquiry Support System (ISS) this specialized DSS. A first task of an intelligent ISS could be that of generating stereotypical hypotheses about the case under consideration. However, the ultimate task of an ISS should be that of providing a most credible and coherent set of beliefs about the case. Part of these beliefs comes from investigations on the spot and verified facts, part from the depositions of the various witnesses, part from hypotheses introduced by the detective him

This paper outlines a distinction between distributed truth maintenance and distributed belief revision. The latter has a more complex conceptualization than the former and it needs the evaluation of special features as the relationship between the informant's reliability and the information's credibility. We point out some criteria to judge the qualities of a distributed belief revision strategy from a global perspective. However, the performances of such a strategy can be estimated only on a simulation basis. The general framework for assumption-based distributed belief revision that we present has been tested on our specific "CLUEDO" multi-agent simulation testbed. The model has been continuously improved during many cycles of modification of the model, simulation, and evaluation of the performances, till the results presented in this paper are achieved.>