Papers by Arindam Ghosh
Detection of essential hypertension with physiological signals from wearable devices
2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2015
Early detection of essential hypertension can support the prevention of cardiovascular disease, a... more Early detection of essential hypertension can support the prevention of cardiovascular disease, a leading cause of death. The traditional method of identification of hypertension involves periodic blood pressure measurement using brachial cuff-based measurement devices. While these devices are non-invasive, they require manual setup for each measurement and they are not suitable for continuous monitoring. Research has shown that physiological signals such as Heart Rate Variability, which is a measure of the cardiac autonomic activity, is correlated with blood pressure. Wearable devices capable of measuring physiological signals such as Heart Rate, Galvanic Skin Response, Skin Temperature have recently become ubiquitous. However, these signals are not accurate and are prone to noise due to different artifacts. In this paper a) we present a data collection protocol for continuous non-invasive monitoring of physiological signals from wearable devices; b) we implement signal processing techniques for signal estimation; c) we explore how the continuous monitoring of these physiological signals can be used to identify hypertensive patients; d) We conduct a pilot study with a group of normotensive and hypertensive patients to test our techniques. We show that physiological signals extracted from wearable devices can distinguish between these two groups with high accuracy.
Annotation and prediction of stress and workload from physiological and inertial signals
2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), 2015
Continuous daily stress and high workload can have negative effects on individuals&am... more Continuous daily stress and high workload can have negative effects on individuals' physical and mental well-being. It has been shown that physiological signals may support the prediction of stress and workload. However, previous research is limited by the low diversity of signals concurring to such predictive tasks and controlled experimental design. In this paper we present 1) a pipeline for continuous and real-life acquisition of physiological and inertial signals 2) a mobile agent application for on-the-go event annotation and 3) an end-to-end signal processing and classification system for stress and workload from diverse signal streams. We study physiological signals such as Galvanic Skin Response (GSR), Skin Temperature (ST), Inter Beat Interval (IBI) and Blood Volume Pulse (BVP) collected using a non-invasive wearable device; and inertial signals collected from accelerometer and gyroscope sensors. We combine them with subjects' inputs (e.g. event tagging) acquired using the agent application, and their emotion regulation scores. In our experiments we explore signal combination and selection techniques for stress and workload prediction from subjects whose signals have been recorded continuously during their daily life. The end-to-end classification system is described for feature extraction, signal artifact removal, and classification. We show that a combination of physiological, inertial and user event signals provides accurate prediction of stress for real-life users and signals.
Language Resources and Evaluation
Modern data-driven spoken language systems (SLS) require manual semantic annotation for training ... more Modern data-driven spoken language systems (SLS) require manual semantic annotation for training spoken language understanding parsers. Multilingual porting of SLS demands significant manual effort and language resources, as this manual annotation has to be replicated. Crowdsourcing is an accessible and cost-effective alternative to traditional methods of collecting and annotating data. The application of crowdsourcing to simple tasks has been well investigated. However, complex tasks, like cross-language semantic annotation transfer, may generate low judgment agreement and/or poor performance. The most serious issue in cross-language porting is the absence of reference annotations in the target language; thus, crowd quality control and the evaluation of the collected annotations is difficult. In this paper we investigate targeted crowdsourcing for semantic annotation transfer that delegates to crowds a complex task such as segmenting and labeling of concepts taken from a domain ontology; and evaluation using source language annotation. To test the applicability and effectiveness of the crowdsourced annotation transfer we have considered the case of close and distant language pairs: Italian-Spanish and Italian-Greek. The corpora annotated via crowdsourcing are evaluated against source and target language expert annotations. We demonstrate that the two evaluation references (source and target) highly correlate with each other; thus, drastically reduce the need for the target language reference annotations.
In this paper, we address the issue of automatic prediction of readers' mood from newspaper artic... more In this paper, we address the issue of automatic prediction of readers' mood from newspaper articles and comments. As online newspapers are becoming more and more similar to social media platforms, users can provide affective feedback, such as mood and emotion. We exploited the self-reported annotation of mood categories obtained from the metadata of the Italian online newspaper corriere.it to design and evaluate a system for predicting five different mood categories from news articles and comments: indignation, disappointment, worry, satisfaction and amusement. The outcome of our experiments shows that overall, bag-of-word-ngrams performs better compared to all other feature sets, however, stylometric features perform better for the mood prediction of articles. Our study shows that such self-reported annotations can be used to design automatic systems.
Photoplethysmography (PPG) is a simple, unobtrusive and low-cost technique for measuring blood vo... more Photoplethysmography (PPG) is a simple, unobtrusive and low-cost technique for measuring blood volume pulse (BVP) used in heart-rate (HR) estimation. However, PPG based heart-rate monitoring devices are often affected by motion artifacts in on-the-go scenarios, and can yield a noisy BVP signal reporting erroneous HR values. Recent studies have proposed spectral decomposition techniques (e.g. M-FOCUSS, Joint-Sparse-Spectrum) to reduce motion artifacts and increase estimation accuracy, but at the cost of high computational load. The singular-value-decomposition and recursive calculations present in these approaches are not feasible for the implementation in real-time continuous-monitoring scenarios. In this paper, we propose an efficient HR estimation method based on a combination of fast-ICA, RLS and BHW filter stages that avoids sparse signal reconstruction, while maintaining a high HR estimation accuracy. The proposed method outperforms the state-of-the-art systems on the publicly available TROIKA data set both in terms of HR estimation accuracy (2.25 ± 1.93 BPM absolute error) and computational requirements.
In this paper, we analyze the influence of Twitter users in sharing news articles that may affect... more In this paper, we analyze the influence of Twitter users in sharing news articles that may affect the readers' mood. We collected data of more than 2000 Twitter users who shared news articles from Corriere.it, a daily newspaper that provides mood metadata annotated by readers on a voluntary basis. We automatically annotated personality types and communication styles of Twitter users and analyzed the correlations between personality, communication style, Twit-ter metadata (such as followig and folllowers) and the type of mood associated to the articles they shared. We also run a feature selection task, to find the best predictors of positive and negative mood sharing, and a classification task. We automatically predicted positive and negative mood sharers with 61.7% F1-measure.
In this paper, we describe an Italian corpus of news blogs, including bloggers' emotion tags, and... more In this paper, we describe an Italian corpus of news blogs, including bloggers' emotion tags, and annotations of agreement relations amongst blogger-comment pairs. The main contributions of this work are: the formalization of the agreement relation, the design of guidelines for its annotation, the quantitative analysis of the annotators' agreement.
inproceedings by Arindam Ghosh
A widely used strategy in human and machine performance enhancement is achieved through feedback.... more A widely used strategy in human and machine performance enhancement is achieved through feedback. In this paper we investigate the effect of live motivational feedback on motivating crowds and improving the performance of the crowdsourcing computational model. The provided feedback allows workers to react in real-time and review past actions (e.g. word deletions); thus, to improve their performance on the current and future (sub) tasks. The feedback signal can be controlled via clean (e.g. expert) supervision or noisy supervision in order to trade-off between cost and target performance of the crowd-sourced task. The feedback signal is designed to enable crowd workers to improve their performance at the (sub) task level. The type and performance of feedback signal is evaluated in the context of a speech transcription task. Amazon Mechanical Turk (AMT) platform is used to transcribe speech utterances from different corpora. We show that in both clean (expert) and noisy (worker/turker) real-time feedback conditions the crowd workers are able to provide significantly more accurate transcriptions in a shorter time.
Crowdsourcing is an accessible and cost-effective alternative to traditional methods of collectin... more Crowdsourcing is an accessible and cost-effective alternative to traditional methods of collecting and annotating data. The application of crowdsourcing to simple tasks has been well investigated. However, complex tasks like semantic annotation transfer require workers to take simultaneous decisions on chunk segmentation and labeling while acquiring on-the-go domain-specific knowledge. The increased task complexity may generate low judgment agreement and/or poor performance. The goal of this paper is to cope with these crowdsourcing requirements with semantic priming and unsupervised quality control mechanisms. We aim at an automatic quality control that takes into account different levels of workers' expertise and annotation task performance. We investigate the judgment selection and aggre-gation techniques on the task of cross-language semantic annotation transfer. We propose stochastic modeling techniques to estimate the task performance of a worker on a particular judgment with respect to the whole worker group. These estimates are used for the selection of the best judgments as well as weighted consensus-based annotation aggregation. We demonstrate that the technique is useful for increasing the quality of collected annotations.
Uploads
Papers by Arindam Ghosh
inproceedings by Arindam Ghosh