Alzheimer’s disease (AD) is characterized by complex alterations in brain connectivity, making the understanding of these patterns critical for early diagnosis and intervention. This study presents a motif-based analysis of functional brain connectivity utilizing synthetic adjacency matrices of virtual connectomics derived from Alzheimer’s Disease Neuroimaging Initiative (ADNI) data. Our approach involves first sparsifying the functional brain network to enhance the significance of the connections, followed by the construction of a directed network from bidirectional correlation-based edge weights between ROIs (Regions of Interest) to accurately capture the flow of information. By systematically searching for recurrent motifs within these networks, we aim to identify specific patterns of connectivity that may distinguish AD patients from healthy controls. Motifs are fundamental building blocks that provide insights into the functional organization of the brain and can reveal underlying mechanisms of neurodegeneration. This analysis not only contributes to the characterization of brain network alterations in AD but also demonstrates the utility of synthetic connectomes in neuroimaging research. Our findings have implications for developing network-based biomarkers and enhancing our understanding of the pathophysiology of Alzheimer’s disease, highlighting the importance of integrating advanced network analysis techniques to unravel the complexities of brain connectivity in neurodegenerative conditions.

In this paper, we focus on network robustness in complex networks by identifying those links within a network graph G whose attack/removal would cause a severe network damage. More specifically, we investigate the role of the effective resistance matrix in identifying an order of links more vulnerable to attacks. In our previous works, we have both evaluated a strategy of link removals based on the ranking provided by the Hadamard product matrix between the adjacency matrix of G and the effective resistance matrix, and a strategy of node removals based on the ranking of the diagonal elements of the pseudoinverse of the Laplacian matrix associated to G. Now, through a real-world networking scenario of an Internet backbone, we start considering the line graph L(G) of G (i.e. the dual graph in which the links of G are nodes). Then, we investigate if removing nodes in the line graph is the same as removing links in G. The relation between the Laplacian of the line graph and the graph itself is not obvious, which does not allow us to immediately map the performance of a node removal strategy to the performance of a link removal strategy. Carrying out our analysis on Erdős-Rényi, Watts-Strogatz and Bárabasi-Albert networks, we look for a relation, if existing, between (a) the node removal in the line graph of G and (b) the link removal in G. Results show that the two attack strategies show a notable degree of similarity mostly on the Bárabasi-Albert networks.

The COVID-19 pandemic generated extensive and far-reaching discussions on social media platforms, effectively becoming a primary source for people to access and disseminate information regarding the outbreak. These social media conversations possess the potential to shape public opinions, but they also carry the risk of spreading panic and misinformation during crises like the COVID-19 pandemic.

Medical staff can be considerably supported in patient healthcare delivery thanks to the adoption of machine learning and deep learning methods by enhancing clinicians decisions and analysis with targeted clinical knowledge, patient information, and other health data. This paper proposes a learning methodology that, on the basis of the current patient health status, clinical history, diagnostic and laboratory results, provides insights for clinicians in the diagnosis and therapy decision processes. The approach relies on the concept that patients with similar vital signs patterns are, in all probability, affected by the same or very similar health problems. Thus, they can have the same or very similar diagnoses. Patients physiological signals are modeled as time series and the similarity among them is exploited. The method is formulated as a classification problem in which an ad-hoc multi-label k-nearest neighbor approach is combined with similarity concepts based on word embedding. Experimental results on real-world clinical data have shown that the proposed approach allows detecting diagnoses with a precision up to about 75%.

Artificial Intelligence (AI), since the onset of the COVID-19 pandemic at the beginning of the last year, is playing an important role in supporting physicians and health authorities in different difficult tasks such as virus spreading, patient diagnosing and monitoring, contact tracing. In this paper, we provide an overview of the methods based on AI technologies proposed for COVID-19 forecasting. Summary statistics of the techniques adopted by researchers, categorized on the base of the underlying AI sub-area, are reported, along with publication venue of papers. The effectiveness of these approaches is investigated and their capabilities or weaknesses in providing reliable predictions are discussed. Future challenges are finally analyzed and research directions for improving current tools are suggested.

COVID-19 pandemic is affecting the lives of the citizens worldwide. Epidemiologists, policy makers and clinicians need to understand public concerns and sentiment to make informed decisions and adopt preventive and corrective measures to avoid critical situations. In the last few years, social media become a tool for spreading the news, discussing ideas and comments on world events. In this context, social media plays a key role since represents one of the main source to extract insight into public opinion and sentiment. In particular, Twitter has been already recognized as an important source of health-related information, given the amount of news, opinions and information that is shared by both citizens and official sources. However, it is a challenging issue identifying interesting and useful content from large and noisy text-streams. The study proposed in the paper aims to extract insight from Twitter by detecting the most discussed topics regarding COVID-19. The proposed approach combines peak detection and clustering techniques. Tweets features are first modeled as time series. After that, peaks are detected from the time series, and peaks of textual features are clustered based on the co-occurrence in the tweets. Results, performed over real-world datasets of tweets related to COVID-19 in US, show that the proposed approach is able to accurately detect several relevant topics of interest, spanning from health status and symptoms, to government policy, economic crisis, COVID-19-related updates, prevention, vaccines and treatments.

The fast expansion during the recent years of online social networks, such as Twitter, Facebook, or Foursquare, is making available an enormous and continuous stream of user-generated contents including information on human mobility within urban context. In particular, online social networks allows for the collection of geo-tagged data obtained through the GPS readings of phones through which users have the possibility to tag posts, photos and videos with geographical coordinates. In this context, recommending the future position of a mobile object is key for the implementations of several applications aiming at improving mobility within urban areas. The paper proposes a location recommendation approach that exploits geo-tagged data on social networks. The approach integrates user preference, sequential mobility and geographic constraints. The recommendation task is formulated as a similarity problem among the visiting and mobility profiles of users, accounting the mobility sequentiality in the patterns. Two ranking metrics are introduced to predict places the user could like. The metrics are then combined into an overall recommendation ranking function. The candidate locations are then ranked according to the two similarity measures. The experimental results obtained by using a real-world dataset of tweets show that the proposed method is effective in recommending unseen locations, outperforming representative state-of-the-art approaches.

On line social networks (e.g., Facebook, Twitter) allow users to tag their posts with geographical coordinates collected through the GPS interface of smart phones. The time- and geo-coordinates associated with a sequence of tweets manifest the spatial-temporal movements of people in real life. The paper presents an approach to recommend travel routes to social media users exploiting historic mobility data, social features of users and geographic characteristics of locations. Travel routes recommendation is formulated as a ranking problem aiming at minimg the top interesting locations and travel sequences among them, and exploit such information to recommend the most suitable travel routes to a target user.

Detecting diseases at early stage can help to overcome and treat them accurately. Identifying the appropriate treatment depends on the method that is used in diagnosing the diseases. A Clinical Decision Support System (CDS) can greatly help in identifying diseases and methods of treatment. In this paper we propose a CDS framework that can integrate heterogeneous health data from different sources, such as laboratory test results, basic information of patients, and health records. Using the electronic health medical data so collected, innovative machine learning and deep learning approaches are employed to implement a set of services to recommend a list of diseases and thus assist physicians in diagnosing or treating their patients health issues more efficiently.

Social media are playing an increasingly important role in reporting major events happening in the world. However, detecting events and topics of interest from social media is a challenging task due to the huge magnitude of the data and the complex semantics of the language being processed. The paper proposes an online algorithm to discover topics that incrementally groups short text by incorporating the textual content with latent feature vector representations of words appearing in the text, trained on very large corpora to improve the check-in topic mapping learnt on a smaller corpus. Experimental results show that by using information from the external corpora, the approach obtains significant improvements with respect to classical topic detection methods.

Social media, in recent years, have become an invaluable source of information for both public and private organizations to enhance the comprehension of people interests and the onset of new events. Twitter, especially, allows a fast spread of news and events happening real time that can contribute to situation awareness during emergency situations, but also to understand trending topics of a period. The article proposes an online algorithm that incrementally groups tweet streams into clusters. The approach summarizes the examined tweets into the cluster centroid by maintaining a number of textual and temporal features that allow the method to effectively discover groups of interest on particular themes. Experiments on messages posted by users addressing different issues, and a comparison with state-of-the-art approaches show that the method is capable to detect discussions regarding topics of interest, but also to distinguish bursty events revealed by a sudden spreading of attention on messages published by users.

Improving seasonal influenza forecasting combining official data sources with web search and social media is a recent research topic which can enhance situational awareness of healthcare organizations when monitoring the outbreak of seasonal flu. In this paper, a prediction model based on autoregression that combines data coming from official influenza surveillance system, with data from web search and social media regarding influenza is proposed. The model is evaluated on the two influenza seasons 2016-2017 and 2017-2018, restricted to Italy. The results show that by using Web-based social data, like Google search queries and tweets, we can obtain accurate weekly influenza predictions up to four weeks in advance. The proposed approach improves real-time influenza forecast compared to traditional surveillance systems based on data from sentinel doctors: the prediction error is reduced up to 47%, while the Pearson's correlation is improved of about 24%.

Influenza surveillance through social media data is becoming an important research topic because it could enhance the capabilities of official surveillance systems in monitoring the outbreak of seasonal flu, by providing healthcare organization with improved situational awareness. In this paper, the two influenza seasons 2016-2017 and 2017-2018, restricted to Italy, are investigated by analyzing the tweets posted by users regarding influenza-like illness. Two types of analysis are performed. The first studies the correlation between the tweets containing the most frequent flu related words with the data provided by the Italian InfluNet surveillance system. The second one examines the sentiment of people on the medicines used to heal flu. We show that there is a strict correlation between the reports published on the InfluNet system, and the contents posted by Twitter users about their symptoms and health state. Moreover, we found that the sentiment expressed by people regarding the treatment, in terms of medicines, taken to heal seems rather negative.

On line social networks (e.g., Facebook, Twitter) allow users to tag their posts with geographical coordinates collected through the GPS interface of smart phones. The time- and geo-coordinates associated with a sequence of tweets manifest the spatial-temporal movements of people in real life. This paper aims to analyze such movements to predict the next location of an individual based on the observations of his mobility behavior over some period of time and the recent locations that he has visited. To this end, we defined a prediction methodology based on a set of spatio-temporal features characterizing locations and movements among them. We then combined the features in a supervised learning approach based on M5 model trees. The experimental results obtained by using a real-world dataset show that the supervised method is effective in predicting the users next places achieving a remarkable accuracy.

Social networking services like Twitter and Instagram are a valuable sources of information to find out what happened or what is happening in a geographic area. This paper presents a method to catch and understand relevant events and happenings from social geo-tagged data. The proposed method consists in two main phases: (i) extraction of space-time features from social data and their modelization as time series, (ii) peak detection from time series, for identifying deviation from user normal behavior. Results of the experimental evaluation, performed over a real-word dataset of tweets, show that the proposed approach is able to accurately detect several relevant events, bounded to a geographic location and of varying importance and character, like exhibitions, festivals, competitions, and terrorist attacks such as that done at the Charlie Hebdo offices.We achieve a space accuracy up to 90%, and a time accuracy up to 95%.

The pervasive availability of increasingly powerful mobile computing devices like PDAs, smartphones and wearable sensors, is widening their use in complex applications such as collaborative analysis, information sharing, and data mining in a mobile context. Energy characterization plays a critical role in determining the requirements of data-intensive applications that can be efficiently executed over mobile devices. This paper presents an experimental study of the energy consumption behaviour of representative data mining algorithms running on mobile devices. Our study reveals that, although data mining algorithms are compute- and memory-intensive, by appropriate tuning of a few parameters associated to data (e.g., data set size, number of attributes, size of produced results) those algorithms can be efficiently executed on mobile devices by saving energy and, thus, prolonging devices lifetime. Based on the outcome of this study we also proposed a machine learning approach to predict energy consumption of mobile data-intensive algorithms. Results show that a considerable accuracy is achieved when the predictor is trained with specific-algorithm features.

This paper presents a technique that builds a layer of virtual sensors over a sensor network. The virtual sensors are able to infer and provide data for the physical sensors that do not work. The key assumption of our approach is that the physical quantities sensed by the sensors are related. The relations among sensors are unknown, but during a learning phase the layer of virtual sensors infers an approximation of them by means of fuzzy rules. The inferred fuzzy rules capture these relations in a simple way even when the corresponding mathematical models are complex. The set of fuzzy rules inferred for a node can be used to obtain virtual values when the real ones are not available. In order to develop our technique we improved the Tree Routing Protocol in charge to deliver data from the nodes to the base station and used Snlog, a Datalog-like language that supports the implementation of distributed algorithms for Wireless Sensor Network in a declarative way. We developed a system prototype and performed preliminary experiments that prove the validity of our approach.

DHT-based structured P2P systems have been proposed to index and retrieve many types of contents, including distributed collections of XML documents. During the query processing, a DHT can be used to efficiently identify all nodes storing relevant documents.