Data aggregation | EPFL Graph Search

Data aggregation is the compiling of information from databases with intent to prepare combined datasets for data processing. Description The United States Geological Survey explains that, “when data are well documented, you know how and where to look for information and the results you return will be what you expect.” The source information for data aggregation may originate from public records and criminal databases. The information is packaged into aggregate reports and then sold to businesses, as well as to local, state, and government agencies. This information can also be useful for marketing purposes. In the United States, many data brokers' activities fall under the Fair Credit Reporting Act (FCRA) which regulates consumer reporting agencies. The agencies then gather and package personal information into consumer reports that are sold to creditors, employers, insurers, and other businesses. Various reports of information are provided by database aggregators. Individu

Privacy - Preserving Data Exchange and Aggregation in Healthcare

Alevtina Dubovitskaya

Medical data are often scattered among multiple clinics, hospitals, insurance companies, pharmacies, and research institutions that store and process personal healthcare information. The use of information and communication technologies for health (eHealth) provides us with the means to share healthcare data between authorized parties in an efficient manner. In this thesis, we address some of the challenges of implementing eHealth in practice: to achieve interoperability between data sources, and to ensure privacy for patients. Achieving both of these guarantees is our goal but they seem conflictual, hence the challenge. Once interoperability is achieved and a patientâs data are shared, it becomes evenmore difficult to ensure the patientâs privacy i.e., to provide to a patient control over his data and to guarantee the data anonymity in medical research. We address the aforementioned challenges by studying requirements from medical and legal perspectives, and by developing algorithms and frameworks to support privacy-preserving dynamic data-sharing, exchange, and aggregation from multiple data sources. In the first part of the thesis, we address certain privacy challenges. We present a framework based on the blockchain technology for ensuring traceability and accountability when sharing, exchanging, and aggregating medical data. Our framework ensures privacy, security, availability, and fine-grained access control over highly sensitive patient-data. We also analyze the potential of applying blockchain technology in different eHealth settings: primary care, medical-data research, and connected health. Our second contribution is a framework for privacy-preserving data aggregation: an algorithm for constructing the anonymized database and a protocol that improves the utility of the anonymized database as the database grows. In the second part of the thesis, we focus on achieving interoperability. We design an interface specification that defines communication protocols andmessages supporting integration of a new software tool in clinical practice. Then, we develop a multi-agent system (MAS) for the dynamic aggregation of the data collected and generated by this software tool for the purpose of clinical research. This MAS takes into account the objectives of the research study, the availability of data, and could employ our proposed algorithm for privacy-preserving data aggregation. The negotiation protocol in the framework of theMAS achieves a precise definition of database characteristics, such as schema, content, and privacy parameters, therefore increasing the efficiency of data collection for medical research and ensuring the privacy of patients.

EPFL2018

Social GAN: Socially Acceptable Trajectories with Generative Adversarial Networks

Alexandre Massoud Alahi, Agrim Gupta

Understanding human motion behavior is critical for autonomous moving platforms (like self-driving cars and social robots) if they are to navigate human-centric environments. This is challenging because human motion is inherently multimodal: given a history of human motion paths, there are many socially plausible ways that people could move in the future. We tackle this problem by combining tools from sequence prediction and generative adversarial networks: a recurrent sequence-to-sequence model observes motion histories and predicts future behavior, using a novel pooling mechanism to aggregate information across people. We predict socially plausible futures by training adversarially against a recurrent discriminator, and encourage diverse predictions with a novel variety loss. Through experiments on several datasets we demonstrate that our approach outperforms prior work in terms of accuracy, variety, collision avoidance, and computational complexity.

2018

Privacy - Preserving Data Exchange and Aggregation in Healthcare

Alevtina Dubovitskaya

EPFL2018