Dr. LARISSA SUZUKI

Academic/Scientific Career

My journey in engineering started at the age of 16. My professional academic career started at the age of 18 and it includes:

  • Scientific Initiation Fellow of University Centre Barao de Maua
  • Teaching Assistant of University of Sao Paulo
  • Lecturer at University Centre Barao de Maua
  • Member of the Coordination of Extension/Internship activities of University Centre Barao de Maua
  • Member of the Coordination of R&D projects of University Centre Barao de Maua
  • Visiting Lecturer in the MBA program of University of Parana
  • Teaching Assistant of Lancaster University
  • Teaching Assistant of UCL
  • Honorary Research Associate of UCL
  • Honorary Associate Professor of UCL

I’ve supervised/co-supervised over 20 BSc/MSc dissertations and projects, some of which were considered outstanding projects in software engineering (IoT, Smart Homes), and a project which became an embedded feature in the Microsoft Visual Studio. These projects were part of an alliance between UCL and organisations such as Microsoft, Satalia, Credit Suisse.

During my PhD was a member of the Software Engineering Group at UCL, Digital City Exchange at Imperial College Business School and at the Senseable City Lab at MIT.

I’ve published several research papers academic journals, books and conferences, am a frequent Keynote, conference and panel speaker (including TEDx). 

I have been a committee member of the Grace Hopper Conference since 2014, and I am an elected member of the Technical and Professional Networks Communities Committee of the Institution of Engineering and Technology (IET). I am also a judge and/or reviewer of the Association for Computing Machinery (ACM) Global Research Competition, Royal Academy of Engineering (RAEng) Impact Grants Project Applications awards; and journals / papers of the Institute of Electrical and Electronics Engineers (IEEE) and Springer journals. I also chair the Tech London Advocates Smart Cities, and the R&D category of the IET Innovation Awards.

 

PhD Thesis

The Thesis

The thesis provides a systematic framework to design of large and highly interconnected data infrastructures which are provided and supported by multiple stakeholders. A closed-loop supply chain model is designed and managed to explicitly consider the activities and processes that enables data and ML to be city-wide leveraged.

Sponsorship and Awards

This thesis was sponsored by the EPSRC, and received fellowships and awards from:

Impact

This thesis pioneered the concept of data as infrastructure for smart cities. It was used to design Urban platforms in the European Union (40+ cities), and the City Data Strategy of London Government. Chapters of this thesis have been published as a book to drive the industry on smart cities.

Teaching

  • Senior Teaching Assistant (2011, 2012, 2013) – Department of Computer Science, University College London 
    • MSc Modules: Software Engineering, Introductory Programming, MSIN2009 Software Engineering, 3001 Technology Management and Professional Issues,  M022/GS02 Advanced Analysis and Design, GC02 Design, INST1003 Information Systems.

 

  • Teaching Assistant (2010,2011) – Department of Management Science, Lancaster University 
    • MSc Modules: MSCI526 Data mining for Marketing, Sales and Finance, MSCI521 Forecasting

 

  • Visiting Lecturer (2008-2009) – Department of Management Science, University Federal of Parana, International joint program with the Université Paris-Dauphine (France) and Laval University (Canada).MBA in Management of Logistics Systems.
    • MBA Modules: Systems to support decision making process in supply chain

 

  • Lecturer (2009 – 2010) – Department of Computer Science, University Centre Barao de Maua
    • BSc Modules: Introduction to Design Web, Introduction to Web Programming, Extensible Language Marking, Informatics applied to Agribusiness, Computer Graphics, Computational Logics, Discrete Mathematics, Operational Research, Digital Image Processing.

 

  • Teaching Assistant (2008 – 2009) – Department of Electrical Engineering, University of Sao Paulo – EESC
    • BEng’s Modules: Introduction to Computer Vision

Reviewer of IEEE Computers

Reviewer of the Journal of Digital Image (Springer)

Reviewer of the IEEE Transactions of Signal Processing

Reviewer of the Journal of Biological Systems (World Scientific).

Scientific Journal Referee

Pioneering Research

  • Smart Cities: I have been pursuing research on the topic since the beginning of the Digital-to-Intelligent-to-Smart Cities movement. I have worked in this field at MIT, IBM, ARUP, and the Greater London Authority. My research has originated the “Data for London” City Data Strategy of the Mayor of London – the world’s first strategy designed to create an effective data ecosystem in London which has maximum impact on the creation of innovative and cost-effective smart city services capable of solving London’s urban challenges.
  • The Internet of Things: I worked leading the Internet of Things architecture of ARUP Digital. My work included extensive technology, market and HCI research, physical infrastructure and legacy systems integration, data infrastructures and pervasive technologies design. I have made substantial contributions to the development of architectures for IoT and Linked Data applications, and received a patent while working at IBM on Smart Buildings & Augmented Reality applications.
  • Biomedical Engineering: I have pioneered a novel form of signal/image processing techniques which allows the restoration of lost information in analogic/digital mammography images in order to increase the early detection of breast cancer in both young and old women. Breast cancer is the most common cancer among women and one of the major causes of women death all over the world. The possibility of cure can increase about 30% if it is detected still in its early stages, as late detection of tumors in advanced stage makes treatment more difficult. This technique and its models developed in my MPhil thesis can be applied to assist Intelligent Computer Aided Diagnosis Systems to improve the performance of breast cancer screening – increased detectability of features without increasing false-positive rates. In practice, a false negative could mean a case of breast cancer that was not detected and a false positive may refer to a patient doing unnecessary additional examination, such as a breast biopsy. This technique is expected to eliminate false negatives cases and also reduce false positives cases. My research paved the way for the development of new techniques that may reduce radiation exposure in cancer patients by 20-30%.
  • Nuclear Medicine: Self adaptive machine learning methods applied to SPECT neuroimaging for the early diagnosis of Alzheimer and Epilepsy, and to predict the prognosis of medical interventions.

Research Blog

Participation in Research Projects

  1. USP Nuclear Medicine – Self adaptive machine learning methods applied to SPECT neuroimaging for the early diagnosis of Alzheimer and Epilepsy (University of Sao Paulo Medical School)
  2. TfL & Microsoft – Pedestrian Simulation and visualisation models using mixed reality holograms
  3. IET – Data Integration Approaches for Smarter Operation of Large Commercial Buildings
  4. ARUP – Sensing Occupancy and Extracting Value from Occupancy Data
  5. Oracle – Data Science Development Toolkit
  6. USP – The Superiority of Tsallis Entropy over Traditional Cost Functions for Brain MRI and SPECT Registration, Department of Nuclear Medicine, University of Sao Paulo Medical School, Brazil
  7. ARUP– A Reference Architecture for the Internet of Things
  8. Imperial College London – Digital City Exchange Project
  9. Lancaster Centre for Forecasting – Meta-learning technique for forecasting model selection: supply chain application
  10. USP Nuclear Medicine – Technetium-99m-ECD prescription for ictal SPECT in an Epilepsy Monitoring Unit (University of Sao Paulo Medical School)
  11. USP/FAPESP – Computational System for automatic evaluation of control quality parameters in mammography units using CCD sensors. (University of São Paulo)
  12. CAPES – Mammography images restoration by quantum noise reduction and MTF filtering, School of Engineering, University of São Paulo, Brazil, Project funded by Brazilian Government