Methods for integrating machine learning and constrained optimization

In the framework of industrial problems, the application of Constrained Optimization is known to have overall very good modeling capability and performance and stands as one of the most powerful, explored, and exploited tool to address prescriptive tasks. The number of applications is huge, ranging from logistics to transportation, packing, production, telecommunication, scheduling, and much more. The main reason behind this success is to be found in the remarkable effort put in the last decades by the OR community to develop realistic models and devise exact or approximate methods to solve the largest variety of constrained or combinatorial optimization problems, together with the spread of computational power and easily accessible OR software and resources. On the other hand, the technological advancements lead to a data wealth never seen before and increasingly push towards methods able to extract useful knowledge from them; among the data-driven methods, Machine Learning techniques appear to be one of the most promising, thanks to its successes in domains like Image Recognition, Natural Language Processes and playing games, but also the amount of research involved. The purpose of the present research is to study how Machine Learning and Constrained Optimization can be used together to achieve systems able to leverage the strengths of both methods: this would open the way to exploiting decades of research on resolution techniques for COPs and constructing models able to adapt and learn from available data. In the first part of this work, we survey the existing techniques and classify them according to the type, method, or scope of the integration; subsequently, we introduce a novel and general algorithm devised to inject knowledge into learning models through constraints, Moving Target. In the last part of the thesis, two applications stemming from real-world projects and done in collaboration with Optit will be presented.

Support infrastructures for multimedia services with guaranteed continuity and QoS

Advances in wireless networking and content delivery systems are enabling new challenging provisioning scenarios where a growing number of users access multimedia services, e.g., audio/video streaming, while moving among different points of attachment to the Internet, possibly with different connectivity technologies, e.g., Wi-Fi, Bluetooth, and cellular 3G. That calls for novel middlewares capable of dynamically personalizing service provisioning to the characteristics of client environments, in particular to discontinuities in wireless resource availability due to handoffs. This dissertation proposes a novel middleware solution, called MUM, that performs effective and context-aware handoff management to transparently avoid service interruptions during both horizontal and vertical handoffs. To achieve the goal, MUM exploits the full visibility of wireless connections available in client localities and their handoff implementations (handoff awareness), of service quality requirements and handoff-related quality degradations (QoS awareness), and of network topology and resources available in current/future localities (location awareness). The design and implementation of the all main MUM components along with extensive on the field trials of the realized middleware architecture confirmed the validity of the proposed full context-aware handoff management approach. In particular, the reported experimental results demonstrate that MUM can effectively maintain service continuity for a wide range of different multimedia services by exploiting handoff prediction mechanisms, adaptive buffering and pre-fetching techniques, and proactive re-addressing/re-binding.

Bridging innovation, nature and tradition: assessment of strategies for rural tourism development in Maramureş (Romania)

In the frame of EU rural policy, always more oriented towards environmental concerns and green livelihoods, Romania stands out for the predominance of rural areas and high nature value farming. The country has to face the challenge of joining the modernization process of rural farming systems with the valorization of local assets. Tourism has emerged as one of the main drivers of change and contributors for a sustainable exploitation of local resources. Rural tourism (RT) can foster the enhancement of the territorial capital (TC), the preservation of public goods (PGs) and the promotion of a more environmental oriented livelihood. The research focuses on a case study area, two valleys from Maramureş, where environmental approaches as diversification strategies are partially explored. The work investigates the role of tourism initiatives for the promotion of green oriented practices. The first part of the work is based on a literature review and interdisciplinary analysis of secondary data to identify the key issues: from rural development policy, to the concept of TC, of PGs and RT. The Romanian development programmes and related strategies are investigated; afterwards the characteristics of the County and the role of RT as diversification and valorisation policies is considered. The second part is based on the collection of primary data through interviews to different local stakeholders (farmers owners of rural guesthouses, local administrators, networks and artisans). The main frequencies are analyzed, a cluster analysis is computed to evaluate the similarities within the most representative groups and a comparative analysis is carried out between the two Valleys. The frame of the analysis is based on a set of indicators following the dimensions of the TC, to assess the characteristics of the local stakeholders and to outline the perception about the local PGs and on the adopted strategies to manage the territory. Final considerations are elaborated and few scenarios are outlined, giving relevance to the importance of improving awareness and creating embeddedness among public-private local stakeholders and resources as a tool for a socio-economic and environmental development of the area.

Statistical analysis of the error associated with the simplification of the stratigraphy in geotechnical models

The uncertainties in the determination of the stratigraphic profile of natural soils is one of the main problems in geotechnics, in particular for landslide characterization and modeling. The study deals with a new approach in geotechnical modeling which relays on a stochastic generation of different soil layers distributions, following a boolean logic – the method has been thus called BoSG (Boolean Stochastic Generation). In this way, it is possible to randomize the presence of a specific material interdigitated in a uniform matrix. In the building of a geotechnical model it is generally common to discard some stratigraphic data in order to simplify the model itself, assuming that the significance of the results of the modeling procedure would not be affected. With the proposed technique it is possible to quantify the error associated with this simplification. Moreover, it could be used to determine the most significant zones where eventual further investigations and surveys would be more effective to build the geotechnical model of the slope. The commercial software FLAC was used for the 2D and 3D geotechnical model. The distribution of the materials was randomized through a specifically coded MatLab program that automatically generates text files, each of them representing a specific soil configuration. Besides, a routine was designed to automate the computation of FLAC with the different data files in order to maximize the sample number. The methodology is applied with reference to a simplified slope in 2D, a simplified slope in 3D and an actual landslide, namely the Mortisa mudslide (Cortina d’Ampezzo, BL, Italy). However, it could be extended to numerous different cases, especially for hydrogeological analysis and landslide stability assessment, in different geological and geomorphological contexts.

Development and characterization of innovative graphene-based composites

Over the last decade, graphene and related materials (GRM) have drawn significant interest and resources for their development into the next generation of composite materials. This is because these nanoparticles have the ability to operate as reinforcing additives capable of imparting considerable mechanical property increases while also embedding multi-functional advantages on the host matrix. Because graphene and 2D materials are still in their early stages, the relative maturity of different types of composite systems varies. As a result, certain nanocomposite systems are currently commercially accessible, while others are not yet sufficiently developed to enter the market. A substantial emphasis has been placed on developing thermoplastic and thermosetting materials that combine a variety of mechanical and functional qualities. These include higher strength and stiffness, increased thermal and electrical conductivity, improved barrier properties, fire retardancy, and others, with the ultimate goal of providing multifunctionality to already employed composites. The work presented in this thesis investigates the use and benefits that GRM could bring to composites for a variety of applications, with the goal of realizing multifunctional components with improved properties that leads to lightweight and, as a result, energy and cost savings and pollution reduction in the environment. In particular, we worked on the following topics: • Benchmarking of commercial GRM-based master batches; • GRM-coatings for water uptake reduction; • GRM as thermo-electrical anti-icing /de-icing system; • GRM for Out of Oven curing of composites.