The LION lab fosters research and development in intelligent optimization and reactive search techniques for solving relevant problems arising in different application areas, including intelligent transportation systems, computer networks and mobility, mobile services and ubiquitous computing, social networks, clustering and pattern recognition in bio-informatics.
These challenges require an integration of different theoretical and practical tools in a creative environment that eliminates the borders between disciplines. This is the spirit of the LION activities, which include advanced research and educational opportunities ranging from the basic Computer Science degree, to the Master Degree in Computer Science, to the international PhD program.
Reactive Search and Intelligent Optimization (http://reactive-search.org)
Reactive Search advocates the integration of sub-symbolic machine learning techniques into local search heuristics for solving complex optimization problems. The word reactive hints at a ready response to events during the search through an internal online feedback loop for the self-tuning of critical parameters. Methodologies of interest for Reactive Search include machine learning and statistics, in particular reinforcement learning, active or query learning, neural networks, and meta-heuristics (although the boundary signalled by the "meta" prefix is not always clear). Intelligent optimization, a superset of Reactive Search, refers to a more extended area of research, including online and offline schemes based on the use of memory, adaptation, incremental development of models, experimental algorithmics applied to optimization, intelligent tuning and design of heuristics.
Mobility and intelligent transportation
In the area of intelligent transportation systems we study the technology for the collection, elaboration, transmission and use of context information gathered through wireless and wired sensors. The focus is on the collection and elaboration of context information for location- and user-aware services. The research activities are in the framework of the DAMASCO joint Italy-USA project with UCLA and are centered on "Intelligent Transport Systems" (ITS). The internetworking and communication framework is based on solutions suitable for ad hoc (multi-hop or peer-to-peer) and sensor networks so that new solutions to monitor and collect context information can be easily deployed. These data are processed to provide services for: i) Accurate traffic and environment information; ii) Distributed monitoring of vehicles and roads; iii) Improvement of road safety; iv) Infotainment. The deployment of ITS services for car networking is limited to a small number of vehicles equipped with sufficient electronics to create a network node. Thus, in the initial phase of the project, an infrastructure will be used to provide services to networking cars.
The increasing availability of huge amounts of data in machine readable format from sources as diverse as databases of chemical compounds, DNA and protein sequences and structures, tagged bookmarks, digital libraries, images, web pages and blogs represent an unprecedented opportunity as well as a formidable challenge for machine learning systems. Such a complex body of information calls for the most recent advances in machine learning research in order to scale to large datasets, deal with complex structured data both in input and output, and jointly solve multiple related tasks, as well as learn models able to transfer knowledge among similar tasks. Models able to provide interpretable explanations for their decisions are especially appealing for the domain experts. Our research is mainly focused on kernel machine algorithms for structured data, multitask learning and statistical relational methods.
Machine learning and optimization for bioinformatics
Computational molecular biology is a hot research area and a continuous source of relevant and challenging problems for machine learning. Structural bioinformatics aims at predicting the three-dimensional structure of macromolecules such as proteins and RNA, given their sequence of residues or nucleotides. Given its intrinsic complexity, the problem has been addressed by tackling a number of related sub-tasks, such as secondary structure, contact map or disulphide bridge prediction. Being able to effectively solve such sub-tasks and combine their outputs into a reliable 3D structure predictor is one of the greatest challenges in bioinformatics. The activity of living cells involves a huge number of interactions between their components, which can be represented as regulatory, metabolic and interaction networks whose structure is mostly unknown. Machine learning techniques need to be able to combine heterogeneous and noisy sources of information from evolutionary, similarity and experimental data in order to contribute to discovering such relational structures.
The wide applicability of reactive search and intelligent optimization techniques lead to various research projects in areas ranging from computer networks, to location-aware services, social networks, autonomic communications. A list of recent research projects follows.
- Triton, Trentino Research and Innovation for Tunnel Monitoring
- Damasco, Data Acquisition and MAnagement in a Sensing and COmmunicating environment
- CASCADAS, Component-ware for Autonomic Situation-aware Communications, and Dynamically Adaptable Services
- BIONETS, BioNets - mating in the computer world AMICI, Amici del Parco
- GRID.it, An Italian National Research Council Project on Grid Computing
- WILMA, Wireless Internet and Location Management Architecture
- E-NEXT, EU FP6 Network of Excellence on Internet protocols and services
- QuaSAR, "Qualita' e Controllabilita' dei Servizi di Comunicazione su Reti Eterogenee"
- ADONIS, Algorithms for Dynamic Optical Networks based on Internet Solutions
|Roberto Battiti||Mauro Brunato||Andrea Passerini|
Further InformationResearch Program's Technical reports
Research Program's Published papers