Angshu Rai

ORCID: 0000-0002-3072-7652
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Complex Network Analysis Techniques
  • Web Data Mining and Analysis
  • Recommender Systems and Techniques
  • Hip and Femur Fractures
  • Bone health and osteoporosis research
  • Expert finding and Q&A systems
  • Advanced Text Analysis Techniques
  • Hip disorders and treatments
  • Topic Modeling
  • Data Management and Algorithms
  • Time Series Analysis and Forecasting
  • Context-Aware Activity Recognition Systems
  • Opinion Dynamics and Social Influence
  • Anomaly Detection Techniques and Applications
  • Chronic Disease Management Strategies
  • Medical Coding and Health Information

IBM Research - India
2011-2021

Amgen (United States)
2020

École Polytechnique Fédérale de Lausanne
2012

Indian Institute of Technology Madras
2009

Recent technological advances in mobile-based access to social networking platforms and facilities update information real{time (e.g. Facebook) have allowed an individual's online presence be as ephemeral dynamic nature, her very thoughts interests. In this context, micro-blogging has been widely adopted by users effective means capture disseminate their actions a larger audience on daily basis. Interestingly, chatters of user obtained from micro-blogs offer unique source analyze interpret...

10.1145/1645953.1646240 article EN 2009-11-02

Fractures as a result of osteoporosis and low bone mass are common give rise to significant clinical, personal, economic burden. Even after fracture occurs, high risk remains widely underdiagnosed undertreated. Common assessment tools utilize subset clinical factors for prediction, often require manual data entry. Furthermore, these predict over the long term do not explicitly provide short-term estimates necessary identify patients likely experience in next 1-2 years.The goal this study was...

10.2196/22550 article EN cc-by Journal of Medical Internet Research 2020-09-12

Micro-blog forums, such as Twitter, constitute a powerful medium today that people use to express their thoughts and intentions on daily, in many cases, hourly, basis. Extracting ‘Real-Time Intention’ (RTI) of user from short text updates is huge opportunity towards web personalization social net- working around dynamic context. In this paper, we explore the novel problem detecting classifying RTIs micro-blogs. We find employing heuristic based ensemble approach reduced dimension feature...

10.1609/icwsm.v6i1.14312 article EN Proceedings of the International AAAI Conference on Web and Social Media 2021-08-03

Complex activities are that a combination of many simple ones. Typically, daily living (ADLs) fall in this category. activity recognition is an active area interest amongst sensing and knowledge mining community today. A majority investigations along vein has happened controlled experimental settings, with multiple wearable object-interaction sensors. This provides rich observation data for mining. Recently, new challenging problem to investigate accuracy complex the wild using smartphone.

10.1145/2350182.2350187 article EN 2012-08-12

Social networks such as Facebook and Twitter offer a huge opportunity to tap the collective wisdom (both published yet be published) of all participating users in order address information needs individual highly contextualized fashion using rich user-specific information. Realizing this opportunity, however, requires addressing two key limitations current social networks: (a) difficulty discovering relevant content beyond immediate neighborhood, (b) lack support for filtering based on...

10.1145/1963192.1963230 article EN 2011-03-28

Abstract Fragility fractures due to osteoporosis are common and associated with significant clinical, personal, economic burden. Even after a fragility fracture, remains widely underdiagnosed undertreated. Common fracture risk assessment tools, such as FRAX1 Garvan,2 confer over the long term but do not provide short-term estimates necessary identify very high-risk patients likely in next 1–2 years. Furthermore, these tools utilize cross-sectional data representing subset of all available...

10.1210/jendso/bvaa046.018 article EN cc-by-nc-nd Journal of the Endocrine Society 2020-04-01

<sec> <title>BACKGROUND</title> Fractures as a result of osteoporosis and low bone mass are common give rise to significant clinical, personal, economic burden. Even after fracture occurs, high risk remains widely underdiagnosed undertreated. Common assessment tools utilize subset clinical factors for prediction, often require manual data entry. Furthermore, these predict over the long term do not explicitly provide short-term estimates necessary identify patients likely experience in next...

10.2196/preprints.22550 preprint EN 2020-07-15
Coming Soon ...