Area A (Curriculum 1: Computer Science)
The Phd candidate will exploit text processing techniques to discover temporal and spatial relations in large semi-structured data (e.g. Wikipedia). These relations will be used to build a storyline capturing the interactions between prominent people (writers, artists, scientists, politicians, etc), their cultural influence and their legacy in the evolution of the culture. The project will involve two research groups in FBK, Digital Humanities (DH) and Mobile and Social Computing Lab (MobS) and will be conducted also in collaboration with the MIT MacroConnections group at MIT Media Lab, lead by Prof. Cesar Hidalgo.
Contact: firstname.lastname@example.org / email@example.com
Nowadays, human translation and machine translation are no longer antithetical opposites. Rather, the two worlds are getting closer and started to complement each other. On one side, the evolution of translation industry is witnessing a clear trend towards the adoption of Machine Translation (MT) as a primary support to professional translators. On the other side, the variety of data that can be collected from human feedback provides to MT research an unprecedented wealth of knowledge about the dynamics (practical and cognitive) of the translation process. The future is a symbiotic scenario where humans are assisted by reliable MT technology that, at the same time, continuously evolves by learning from translators activity. This grant aim to transform this vision into reality. The candidate will team up a world-class research effort developing novel MT technology capable to integrate information obtained unobtrusively from real professional translation workflows. Relevant topics include: i) neural machine translation ii) deep learning from human feedback iii) language independent continuous space representations, and much more. No specific knowledge of languages nor linguistics is required, while strong programming skills are a must. Students will have access to a state of the art cluster with 1520 CPUs and 12 last generation GPUs. Machine translation is a very active field, both in academia and industry, and offers great opportunities for internships and job placements.
More information at: hlt-mt.fbk.eu
The PhD research project aims at carrying out research activity on machine learning methodologies for brain connectivity data analysis. The main goal is to design and to deploy machine learning algorithms for open challenges such as the detection of the main structural and functional pathways of the brain white matter, the characterization of the differences with respect to altered brain connections, the inter-individuals analysis of brain connectivity structures.
Area B (Curriculum 1: Computer Science)
Department of Information Engineering and Computer Science
netCommons  is a three-year research project that focuses on Community Networks (CNs), large bottom-up communication infrastructures that are blooming in many European and non-European countries.
The PhD candidate will work on mainly three themes:
Studying and collecting information about the existent CNs, their network properties and their social organization in order to produce mixed techno-social monitoring metrics that the communities can use to have the “pulse” of the network and the community. These metrics will help the community in shaping decisions about the growth, the ownership and the management of the network.
Continuing the work done in the ANS lab  about the optimization of routing functions for large mesh network based on topology metrics.
Developing the PeerStreamer peer-to-peer streaming application  in order to be easily deployable in CNs. This involves porting it to dedicated hardware and improving the network-awareness of the application with specific optimization for CNs.
Cooperative driving is the new frontier beyond self driving cars. Vehicles use DSRC (Dedicated Short Range Communications) to coordinate maneuvers, form platoons, avoid accidents (road casualties have a worldwide toll comparable to a war!). Coordination with pedestrians and bikers is the next step to improve Urban mobility and make smarter transportation in cities. The ideal candidate has a strong background in Computer Science, Networking, Simulation and Stochastic system, as well as an open mind-set to acquire novel competences in fields like automotive technology, electronics and human computer interaction.
Safety critical systems are becoming increasingly complex.
Effective analysis tools are required to detect flaws in the early design stages, to prove the compliance with requirements, and to ensure the required levels of reliability.
The activity will aim at the development of formal techniques for model-based verification and safety assessment of critical systems, including model checking and temporal logics for finnite- and infinite-state systems, Fault Tree Analysis (FTA), Failure Model and Effects Analysis (FMEA), Fault Detection, Identification and Recovery (FDIR).
The studies will be carried out within the Embedded Systems Unit at Fondazione Bruno Kessler. The Unit has a long experience in the application of formal methods in sectors of hardware design, railways, avionics, space, and will be part of projects funded by the European Union, the European Space Agency, and major industrial players.
More information at: http://es.fbk.eu
Area C (Curriculum 1: Computer Science)
Department of Information Engineering and Computer Science
The challenge of the project is to lay the scientific foundations of a global science of (cyber) security and cyber risk for Digital Finance, a domain whose characteristics are a myriad of small, invisible, lucrative and potentially unlawful activities (e.g. considering the effect of a minor glitch on the initial public offering on NASDAQ) that can be used by strategic adversaries.
Email contact below is only for further information. Interested students should anyhow formally apply through the general application process and mark grant C1 as well as C
This Phd Topic is about how to best represent knowledge in order to enable digital humanities, for instance in the context of a better fruition of a book.
The purpose of this research is the definition and implementation of software architectures to enable real time anomaly detection on Big Data real time streams . The identified solution(s) should enable for example the identification and the characterization of event in a city (as well as the prediction of the event) , in order to evaluate its real impact.
Contact: firstname.lastname@example.org / email@example.com
The almost universal adoption of mobile phones, the exponential increase in the use of Internet services, social media platforms, and credit cards, and the proliferation of wearable devices and connected objects (Internet of Things) have resulted in a massive production of human behavioral data that characterize many aspects of daily life with extremely fine temporal and spatial granularities. This scenario, however, raises unprecedented privacy challenges and concerns derived from the collection, storage and usage of vast amounts of personal data.
As people become increasingly sensitive about the collection and use of their personal data, there is a need for trusted infrastructures that allow citizens to manage their personal data with security mechanisms (e.g. cryptographic techniques) regarding their privacy. In this thesis the student will explore secure and decentralized (e.g. blockchain based) platforms for enabling personal data sharing and markets. A possible case study will be the application of these platforms to financial and insurance data driven services (e.g. new credit scoring models).
Contact: firstname.lastname@example.org / email@example.com / firstname.lastname@example.org
The aim of this Ph.D. thesis is the development of a predictive analytics approach based on machine learning to model the association between mobility and human activity. In particular, this research will focus on novel methods for geomarketing based on the integration of deep learning with geospatial technologies over high frequency telecommunications data (CDR - Call Detail Records). Geomarketing functions such as dwell time, catchment area analytics, movement directions, visitor density, origin and trajectory analysis will be derived in a predictive framework, to enable informed decisions in applications of ethical and economic interest. As a challenge, the research will address the application to real-time analytics of high frequency retail or public service data, enabling to create a dynamic characterization of city and territories at diverse temporal, geospatial, and social scales. The work will require a highly multidisciplinary approach, leading to improvements in extracting patterns from mobile phone data, automatic synthesis of features in machine learning, and actionable graphics within dashboards, with expected impact on fields such as marketing science and urban science. This project has also clear business applications, which will be explored on retail data streams in the pharma domain and other areas to demonstrate the approach. The grant is funded by Telecom Italia; the thesis project will be developed in internship at FBK in its Complex Data Analytics research line, with the support of experts in Predictive Models for Big Data, GIS, and Mobile and Social Computing.
Contact: email@example.com / firstname.lastname@example.org / email@example.com
Area D (Curriculum 2: Telecommunications)
Department of Information Engineering and Computer Science
The research activity that will be developed is related to the development of advanced methods for the analysis of remote sensing images. The methods should be able to automatically extract information from the satellite images and will be devoted to feature extaction and classification/decision fusion based on machine learning. The target data are both single and multitemporal SAR images as well as optical multispectral images. The techniques will be tested and validated on the problem of cryosphere monitoring and on the hydrologiccal parameter estimation.
The activity will be developed at the Remote Sensing Laboratory (RSLab) of the University of Trento
D2 / D3 - Definition, design, implementation and validation of acquisition strategies and data analysis methodologies for the Radar for Icy Moon Exploration (RIME) in the framework of the JUpiter ICy moon Explorer (JUICE) (2 grants)
The research activity that will be developed is related to the Radar for Icy moon Exploration (RIME) in the framework of the JUpiter ICy moon Explorer (JUICE) mission of the European Space Agency. RIME is developed under the leadership of the University of Trento in cooperation with Italian Industry and the Jet Propulsion Laboratory (JPL) in US with the funding of Italian Space Agency and NASA. RIME has an international Science Team that includes scientists from many different institutions in Europe and US.
RIME is a radar sounder (ground penetrating radar from satellite platform) defined to study the geology, the geophysics and the possible presence of water in the subsurface (up to 9 km) of the Jupiter icy moons, i.e., Ganymede, Europa and Callisto
The research activitities related to the two PhD positions will befocused on the definition, design, implementation and validation of acquisition strategies and data analysis methodologies for RIME. The PhD student will work at the Remote Sensing Laboratory of the Univeristy of Trento and will cooperate with the international RIME Science Team. The specific acitvities will be focused on radar sounding, radar performance simulation, radar signal processing, radar acquisition strategies and data analysis methods for addressing the geophysics and geological challenges of the study of the Jupiter Icy Moons (Europa, Ganymede, and Callisto)
Remote sensing sensors for Earth and planetary observation are experiencing a fast technological development. Images with enhanced features are available showing better trade-off in terms of spectral, spatial, and temporal resolution. Information extraction and retrieval from such data requires the design, implementation and validation of novel methodologies and algorithms based on pattern recognition, image/signal processing, machine learning and/or data fusion.
In the above context the Remote Sensing for Digital Earth Unit at Fondazione Bruno Kessler is looking for a Ph.D. student candidate. Besides the general requirements established by the rules of the ICT school, preferential characteristics for candidates for this scholarship are:
• master degree in fields like Electrical Engineering, Communication Engineering, Computer Science, Mathematics or equivalents;
• knowledge in pattern recognition, image/signal processing, statistic and/or remote sensing;
• good knowledge of written and spoken English;
• expertise in programming languages like C or Matlab.
More information at: http://rsde.fbk.eu/