Multivariate time series (MTS) are prevalent but inherently complex, making them challenging to analyze due to strong temporal and inter-variable correlations. This complexity often results in the use of sophisticated and difficult-to-interpret machine learning models. In real-life scenarios where critical applications of these models are common, their acceptability is crucial. Counterfactual explanations have emerged as a valuable tool for understanding machine learning systems by providing post-hoc analyzes of classification models. We introduce CFE4MTS (CounterFactual Explanation for Multivariate Time Series), a conditional, generation-based, plausible counterfactual explanation method, specifically designed for multivariate time series classification. Our approach leverages advanced time series modeling techniques to generate interpretable counterfactuals that belong to a given target class distribution. To evaluate the effectiveness of our method, we apply it to various real datasets, demonstrating the superiority of our approach over the state of the art methods.

Towards conversational agents that are capable of handling more complex questions on contractual conditions, formalizing contract statements in a machine readable way is crucial. However, constructing a formal model which captures the full scope of a contract proves difficult due to the overall complexity its set of rules represent. Instead, this paper presents a top-down approach to the problem. After identifying the most relevant contract statements, we model their underlying rules in a novel knowledge engineering method. A user-friendly tool we developed for this purpose allows to do so easily and at scale. Then, we expose the statements as service so they can get smoothly integrated in any chatbot framework.

Best-performing WLAN monitoring systems must capture as much wireless traffic as possible. To achieve this aim, several monitors are employed to capture wireless exchanges in a target area. Monitors potentially generate large traces that are all merged together to have a more complete, global view of the network behavior. Traces are often more equal than complementary, leading to the underutilization of monitors and to a higher system complexity. In this paper, we propose a methodology to make an efficient use of monitors in order to increase scalability. Such a methodology, based on trace similarity and community detection in graphs, ranks traces to reveal how many and which ones must be merged. Traces at the bottom of the rank, which belong to under-used monitors, are candidates to be relocated somewhere else to extend the target area. We evaluate the proposed methodology in two real-case scenarios. Results show that we can remove up to half of the monitors in our scenarios and still keep the same level of coverage.

In this work we propose ParkMaster, a low-cost crowdsourcing architecture which exploits machine learning techniques and vision algorithms to evaluate parking availability in cities. While the user is normally driving ParkMaster enables off the shelf smartphones to collect information about the presence of parked vehicles by running image recognition techniques on the phones camera video streaming. The paper describes the design of ParkMaster's architecture and shows the feasibility of deploying such mobile sensor system in nowadays smartphones, in particular focusing on the practicability of running vision algorithms on phones.

Mobile data traffic is set to triple in three years from now according to Cisco. This trend is a real challenge for operators since wireless capacity is bounded.

Achieving efficient content dissemination in mobile opportunistic networks becomes a big challenge when content sizes are large and require more capacity than what contact opportunities between nodes may offer. Content fragmentation solves only part of the problem, as nodes still need to decide which fragment to send when a contact happens. To address this problem, we propose EPICS, a protocol designed to quickly exchange large contents in opportunistic networks. Using grey relational analysis, EPICS is able to balance the distribution of contents that have different sizes and creation times, providing fairer delay distribution and faster dissemination. We implemented and evaluated EPICS through real experimentation using Android devices. Results show that EPICS significantly reduces content dissemination delays when compared to classic approaches.