Giuseppe D’Aniello

A new DSS based on situation awareness for smart commerce environments

Real time adaptation of marketing strategies and actions in smart commerce environments, such as shops and malls, is an open challenge with a tremendous impact for the survival of traditional retailers. A main issue of traditional retailers, in comparison with e-commerce shops, is that they usually rely on analysis of point-of-sales data after purchase and/or focus groups and self-reports where customers are asked about what they like or want. This techniques, even if solid grounded to marketing and consumer research, do not allow analysis of data and decision making in real time, i.e., when consumers are inside a shop. In this paper we present our results on the definition and validation of a decision support system for real time decision making on discount and promotion actions. The system makes decision on the basis of recognition and assessment of situations of interest for the consumers, modelled with heuristics related to behavioural economics results. We validated our solution in a virtual shop simulated with V-REP, demonstrating its capabilities to adapt with regards to the changes in the environments, in terms of sensors, people, products, and different situations.

Sustaining self-regulation processes in seamless learning scenarios by situation awareness

This paper faces the problem of increasing the awareness of learners, with respect to their whole learning processes, in order to sustain their capabilities to adapt such processes. The idea is to exploit models and approaches for Situation Awareness, previously adopted in other fields, also in the human learning domain by defining a framework that can be instantiated in a wide range of seamless learning scenarios. Being aware of the learning situations in which they are, learners can make decisions to adapt their behaviours and self-regulate their processes. More specifically, the approach is able to identify learning path types by exploiting the metaphor of bubbles, which represent sets of concepts already acquired by learners. It is possible to identify the situations in which learners are involved by taking into account the way in which such bubbles arise, grow and join together. Lastly, this work also provides a description and an early evaluation of the developed software prototype.

Resilient Semantic Sensor Middleware

Resilience is the capability of a system to absorb and mitigate unexpected faults and risks. This paper describes the definition of a resilient middleware for sensor network management in dynamic environments for supporting Situation Awareness processes in security scenarios.

A City-Scale Situation-Aware Adaptive Learning System

The concept of Seamless Learning is becoming more and more effective because the newer technologies are able to meet the personal needs of the people and really support them in their learning processes. Thus, the learning experience is a moment in the everyday life strongly related with the situation each person is dealing with. The main idea of this work is to define a flexible seamless learning environment able to identify the context where a learner is deepened in and to apply an adaptation by respecting her learning goals. The proposed approach leverages on three main aspects: situation awareness, adaptive learning and semantic technologies.

An AmI-Based Software Architecture Enabling Evolutionary Computation in Blended Commerce: The Shopping Plan Application

This work describes an approach to synergistically exploit ambient intelligence technologies, mobile devices, and evolutionary computation in order to support blended commerce or ubiquitous commerce scenarios. The work proposes a software architecture consisting of three main components: linked data for e-commerce, cloud-based services, and mobile apps. The three components implement a scenario where a shopping mall is presented as an intelligent environment in which customers use NFC capabilities of their smartphones in order to handle e-coupons produced, suggested, and consumed by the abovesaid environment. The main function of the intelligent environment is to help customers define shopping plans, which minimize the overall shopping cost by looking for best prices, discounts, and coupons. The paper proposes a genetic algorithm to find suboptimal solutions for the shopping plan problem in a highly dynamic context, where the final cost of a product for an individual customer is dependent on his previous purchases. In particular, the work provides details on the Shopping Plan software prototype and some experimentation results showing the overall performance of the genetic algorithm.

An approach based on semantic stream reasoning to support decision processes in smart cities

Abstract This paper discusses the use of stream reasoning models and techniques to provide a stream reasoning-based architecture to represent, manage and process data streams produced in the Smart City context, to extract useful knowledge for a better understanding of city phenomena and to support the decision making processes in both the city governance and the citizens. The proposed architecture, taking into account the need for processing heterogeneous data/information across several and different domains, is able to sustain decision-making processes deployed at operational, tactical and strategical levels. Such architecture is distributed and adopts a meet-in-the-middle configuration logic that is really effective and scalable in a complex environment like a (smart) city. The applicability of semantic technologies to implement all the aforementioned features is demonstrated by means of a complex case study realized by using a dataset, related to the city of Aarhus, provided by the CityPulse EU Project.

Adaptive Goal Selection for improving Situation Awareness: the Fleet Management case study

Abstract: Lack of Situation Awareness (SA) when dealing with complex dynamic environments is recognized as one of the main causes of human errors, leading to serious and critical incidents. One of the main issues is the attentional tunneling manifested, for instance, by human operators (in Decision Support Systems) focusing their attention on a single goal and loosing the awareness of the global picture of the monitored environments. A further issue is represented by stimuli, coming from such environments, which may divert the attention of the operators from the most important aspects and cause erroneous decisions. Thus, the need to define systems helping human operators to improve SA with respect to the two aforementioned drawbacks emerges. These systems should help operators in focusing their attention on active goals and, when really needed, switching it on new goals, in a sort of continuous adaptation. In this work an adaptive goal selection approach exploiting both goal-driven and data-driven information processing is proposed. The approach has been defined and injected in an existing multi-agent framework for Situation Awareness and applied in a Fleet Management System. The approach has been evaluated by means of the SAGAT methodology.

Fuzzy Consensus Model in Collective Knowledge Systems: An Application for Fighting Food Frauds

Food fraud is related to different illicit conducts which aim at gaining economic benefit from counterfeiting food and ignoring the damage they cause to public economy and health. Consumers use the new technologies, like social networks, in order to share their worries about food frauds and to stay informed about them. But, in such a complex and dynamic context, it is important to ensure the reliability of news about food frauds in order to avoid misinformation and general panic phenomena. In this context, we propose an extension of a Collective Knowledge System aiming at verifying the reliability of news about food frauds and to decide whether to publish and spread information on the food frauds in the society. A Fuzzy Consensus Model has been proposed for helping the experts in achieving a shared decision about the reliability of each news and about its publication and diffusion. An illustrative example demonstrates the feasibility and the usefulness of the proposed approach.

Kernel of a DSS for the Evaluation of the Founding Team of a University—Based Spin Off

This work focuses on a University-based Spin Off (USO) with consequent review of the traditional university mission on the need/opportunity to give more to Knowledge. Europe, Italian government and other institutions fund spin-offs through announcements, in which the evaluation method for merits still shows limitations, due to a light presence of Italian excellence. The work, starting from the Service Science Management Engineering and Design (SSMD+D), proposes a review of the literature about demographic factors in the founding team, but more generally of human capital in spin-offs in order to create value. According to Visintin and Pittino (see Visintin and Pittino in Technovation 34: 31–43, 2014), the paper aims to design a kernel of a fuzzy logic based DSS to evaluate ex-ante the likely success of the founding team of a USO. Academic spin-offs of the University of Salerno are useful to test the DSS.