Shyam Rajagopalan - Academia.edu (original) (raw)

Uploads

Papers by Shyam Rajagopalan

Detecting self-stimulatory behaviours for autism diagnosis

2014 IEEE International Conference on Image Processing (ICIP), 2014

Autism Spectrum Disorders (ASD), often referred to as autism, are neurological disorders characte... more Autism Spectrum Disorders (ASD), often referred to as autism, are neurological disorders characterised by deficits in cognitive skills, social and communicative behaviours. A common way of diagnosing ASD is by studying behavioural cues expressed by the children. We introduce a new publicly-available dataset of children videos exhibiting self-stimulatory (stimming) behaviours commonly used for autism diagnosis. These videos, posted by parents/caregivers in public domain websites, are collected and annotated for the stimming behaviours. These videos are extremely challenging for automatic behaviour analysis as they are recorded in uncontrolled natural settings. The dataset contains 75 videos with an average duration of 90 seconds per video, grouped under three categories of stimming behaviours: arm flapping, head banging and spinning. We also provide baseline results of tests conducted on this dataset using a standard bag of words approach for human action recognition. To the best of our knowledge, this is the first attempt in publicly making available a Self-Stimulatory Behaviour Dataset (SSBD) of children videos recorded in natural settings.

Automated faceted reporting for web analytics

Proceedings of the 4th international workshop on Web-scale knowledge representation retrieval and reasoning - Web-KR '13, 2013

ABSTRACT Traditionally, web analytics has focused on analysis and reporting of business metrics o... more ABSTRACT Traditionally, web analytics has focused on analysis and reporting of business metrics of interest to marketers, such as page views and revenue, by various dimensions of session characteristics, that can be obtained from user request. We introduce the notion of faceted reporting in the context of web analytics, where aggregated business metrics are reported grouped by a facet, a dimension along which a document could be represented. For example, in the case of e-Commerce sites, facets are typically various product attributes such as price, color, manufacturer, etc. For a typical website one could think of thousands of facets, but not all of them are equally important for the marketer in all reporting scenarios. In this work, we propose a business-metric driven scheme for automatic selection of facets for various reporting scenarios. The facet selection is done based on optimizing an objective function involving business metrics and we present our evaluation results based on multiple objective functions. We observe that, marketers' intuitive selection of useful facets is inaccurate. On the other hand automated methods proposed in this paper can highlight insights from the data.

The Journal of Foot and Ankle Surgery, 2007

Lipoma is one of the most common benign soft tissue tumors. The most common location of lipomas i... more Lipoma is one of the most common benign soft tissue tumors. The most common location of lipomas is in areas of abundant adipose tissue. Reports of a lipoma in the foot exist, but toe lipomas are rare. The case presented is one of a large, expanding lipoma engulfing the lateral aspect of the third toe and the whole of the third web space. It measured 10 cm in diameter. This was successfully removed surgically. To the best of our knowledge, the size of this lipoma is probably one of the largest ever reported in the toes of an adult.

Play with me — Measuring a child's engagement in a social interaction