A5031347836- Digital Platforms and Economics
- Auction Theory and Applications
- Blockchain Technology Applications and Security
- Big Data and Business Intelligence
- Multi-Agent Systems and Negotiation
- Consumer Market Behavior and Pricing
- COVID-19 diagnosis using AI
- Information Technology Governance and Strategy
- Business Process Modeling and Analysis
- ICT Impact and Policies
- Speech Recognition and Synthesis
- Dispute Resolution and Class Actions
- Advertising and Communication Studies
- Privacy, Security, and Data Protection
- Voice and Speech Disorders
- Sharing Economy and Platforms
- Banking stability, regulation, efficiency
- Innovative Human-Technology Interaction
- Context-Aware Activity Recognition Systems
- ERP Systems Implementation and Impact
- Speech and dialogue systems
- Emotion and Mood Recognition
- Technology Assessment and Management
- Digital Rights Management and Security
- Digital and Cyber Forensics
Massachusetts Institute of Technology
2003-2024
EADA Business School
2023
Harvard University
2020-2021
Harvard University Press
2003-2020
IIT@MIT
2005-2020
Universidad de Navarra
1999-2004
St Petersburg University
2000
We hypothesized that COVID-19 subjects, especially including asymptomatics, could be accurately discriminated only from a forced-cough cell phone recording using Artificial Intelligence. To train our MIT Open Voice model we built data collection pipeline of cough recordings through website (opensigma.mit.edu) between April and May 2020 created the largest audio balanced dataset reported to date with 5,320 subjects.
Just like your phone can detect what song is playing in crowded spaces, we show that Artificial Intelligence transfer learning algorithms trained on cough recordings results diagnostic tests for COVID-19. To gain adoption by the health care community, plan to validate our a clinical trial and three other venues Mexico, Spain USA . However, if had data from on-going trials volunteers, may do much more. For example, confirmed stay-at-home COVID-19 patients, longitudinal audio test could be...
We introduce a novel audio processing architecture, the Open Voice Brain Model (OVBM), improving detection accuracy for Alzheimer's (AD) longitudinal discrimination from spontaneous speech. also outline OVBM design methodology leading us to such which in general can incorporate multimodal biomarkers and target simultaneously several diseases other AI tasks. Key our is use of multiple complementing each other, when two them uniquely identify different subjects disease we say they are...
There has been a lot of research addressing the relationship between Information Technology (IT) investments and productivity. Most work based on firm-level metrics such as total IT investment. We present what we believe is one first attempts to create systematic methodology assess impact in business process performance metrics. Our approach builds MIT Process Handbook basis both guide analysis capture resulting knowledge for future use. will preliminary results how use analyze given...
Purpose The purpose of this paper is to use a blended learning environment introduce principals in small businesses the benefits electronic commerce, while avoiding many barriers identified recent research. Design/ methodology/approach reports results from field tests Virtual Product Development Workshop (VPDW) approach introducing leaders and practical issues involved adding e‐commerce capabilities their firms. Findings finds that smaller business are real. Even so, senior staff firms have...
This paper analyses how transactions related to the exchange of goods and services are being performed on Internet. The adoption electronic markets in an industry has a disintermediation potential because it can create direct link between producer consumer (without need for intermediation role distributors). Electronic lower searches cost allowing customers choose more providers. ultimately reduces both costs customer profits producer. In this is contended that Internet have opposite effect,...
Using a process modeling-based approach to address privacy and related legal issues arising in an RFID-based augmented reality shopping situation.
Abstract Background: We introduce a novel speech processing framework, the MIT CBMM Open Voice Brain Model (OVBM), combining implementations of 4 modules intelligence: The brain OS chunks and overlaps audio samples transfers CNN features from sensory stream cognitive core creating multi-modal graph neural network symbolic compositional models for target task.Methods: Our approach consists pre-training to extract acoustic selected biomarkers then leverage transfer learning combine biomarker...
Appears in: EDULEARN17 Proceedings Publication year: 2017Pages: 8908-8918ISBN: 978-84-697-3777-4ISSN: 2340-1117doi: 10.21125/edulearn.2017.0672Conference name: 9th International Conference on Education and New Learning TechnologiesDates: 3-5 July, 2017Location: Barcelona, Spain
In this paper we analyze how transactions related to the digital trade of intangible goods and services is being performed on Internet. The adoption electronic markets in an industry has a desintermediation potential because it can create direct link between producer consumer (without need for intermediation role distributors). Electronic lower search cost allowing customers choose among more providers (which ultimately reduces both costs customer profits producer). contend that Internet*...
Suggesting a Voice Name System (VNS) to talk any object in the world.
Frontotemporal Dementia (FTD) encompasses a diverse group of progressive neurodegenerative diseases that impact speech production and comprehension, higher-order cognition, behavior, motor control. Traditional acoustic markers have been extensively studied in FTD, as assessments capturing apathy impairments recognizing expressing emotion. This work leverages machine learning to track changes emotional content within the individuals with FTD healthy controls. The aim project is develop tools...