Abstract

Increasing demands of wearable health monitoring seek dedicated spectrum for short range wireless communication of biosignals, for which frequency band near 400 MHz has been utilized recently. While using the dedicated spectrum, biosignal communication must not cause any out of band radiations and interference, for which there is a strong need to develop spurfree, low phase noise and energy efficient wireless transmitters (TX). In this research, for the first time we present design and implementation of a reference-spur-free, low phase noise, sub-mW dual modulation mode (frequency shift keying (FSK) and on-off keying (OOK)) 400 MHz TX for wearable health monitoring, where RF synthesis depends solely on an extremely low phase noise oscillator, which uses a 400 MHz surface acoustic wave resonator and does not include any power hungry, spurgenerating frequency multiplier or phase/frequency lock loop. The proposed TX has been designed and fabricated in 180 nm CMOS technology. Measurement results show that the energy efficiencies of the proposed TX in FSK and OOK mode are 1.8 nJ/bit at 250 kb/s and 0.23 nJ/bit at 2 Mb/s, respectively. To prove the utility of the proposed TX, biosignal communication is also demonstrated with the help of a commercial receiver in actual operating scenarios, where the measured bit error rate in FSK mode was < 10−5 for range of 2 m. Index Terms—Health-monitoring, wearable, spur-free, transmitter, FSK, OOK, 400 MHz, MedRadio

Abstract

Estimation of basic material properties of masonry and understanding its compressive behaviour is the initial crucial steps in analyzing the performance of masonry buildings. Masonry being a complex and inelastic material has a large variation in mechanical properties such as compressive strength and modulus of elasticity. The variation for Indian masonry is even higher, as most of the manufacturing and construction process is performed manually. Mechanical characterization of solid clay bricks, mortar cubes (1:4 cement-sand proportion) and masonry prisms are performed using laboratory tests to determine the compressive properties. The non-linear stress strain behaviour of masonry and its constituents is also presented. Based on the results of the present study and past literature, variation in mechanical properties of Indian masonry & its constituents is studied based on two different mortar grades (1:4 and 1:6). It is observed that these properties have a large portion of aleatory variability, due to variations in constituent materials and workmanship. The relationship between the compressive strength and elastic modulus of brick, mortar and masonry is also presented. Further, the relative performance of different empirical models in predicting the properties of masonry is compared and their efficacy is examined using the statistical and error-assessment parameters. Results showed that the compressive strength of the Indian masonry can be determined using most of the empirical relations available worldwide, with reasonable accuracy; however, the elastic modulus of masonry cannot be estimated with the same level of confidence.

Abstract

No Results Found

Abstract

No Results Found

Abstract

The localization of acoustic sources is a parameter estimation problem where the parameters of interest are the direction of arrivals (DOAs). The DOA estimation problem can be formulated as a sparse parameter estimation problem and solved using compressive sensing (CS) methods. In this paper, the CS method of sparse Bayesian learning (SBL) is used to find the DOAs. We specifically use multi-frequency SBL leading to a non-convex optimization problem, which is solved using fixed-point iterations. We evaluate SBL along with traditional DOA estimation methods of conventional beamforming (CBF) and multiple signal classification (MUSIC) on various source localization tasks from the open access LOCATA dataset. The comparative study shows that SBL significantly outperforms CBF and MUSIC on all the considered tasks.

Abstract

The evolution of social media platforms have empowered everyone to access information easily. Social media users can easily share information with the rest of the world. This may sometimes encourage spread of fake news, which can result in undesirable consequences. In this work, we train models which can identify health news related to COVID-19 pandemic as real or fake. Our models achieve a high F1-score of 98.64%. Our models achieve second place on the leaderboard, tailing the first position with a very narrow margin 0.05% points.

Abstract

We propose a knowledge-based approach for extraction of Cause-Effect (CE) relations from biomedical text. Our approach is a combination of an unsupervised machine learning technique to discover causal triggers and a set of high-precision linguistic rules to identify cause/effect arguments of these causal triggers. We evaluate our approach using a corpus of 58,761 Leukaemia-related PubMed abstracts consisting of 568,528 sentences. We could extract 152,655 CE triplets from this corpus where each triplet consists of a cause phrase, an effect phrase and a causal trigger. As compared to the existing knowledge base - SemMedDB (Kilicoglu et al., 2012), the number of extractions are almost twice. Moreover, the proposed approach outperformed the existing technique SemRep (Rindflesch and Fiszman, 2003) on a dataset of 500 sentences.

Abstract

Every year publicly listed companies file financial reports to give insights about their activities. These reports are meant for shareholders or general public to evaluate the company’s health and decide whether to buy or sell stakes in the company. However, these annual financial reports tend to be long, and it is time-consuming to go through the reports for each company. We propose a Goal Guided Summarization technique through which the summary is extracted. The goal, in our case, is the decision to buy or sell company’s shares. We use hierarchical neural models for achieving this goal while extracting summaries. By the means of intrinsic and extrinsic evaluation we observe that the summaries extracted by our approach can model the decision of buying and selling shares better compared to summaries extracted by other summarization techniques as well as the complete document itself. We also observe that the summary extractor model can be used to construct stock portfolios which give better returns compared to major stock index.

Abstract

Sexism, an injustice that subjects women and girls to enormous suffering, manifests in blatant as well as subtle ways. In the wake of growing documentation of experiences of sexism on the web, the automatic categorization of accounts of sexism has the potential to assist social scientists and policymakers in studying and thereby countering sexism. The existing work on sexism classification has certain limitations in terms of the categories of sexism used and/or whether they can co-occur. To the best of our knowledge, this is the first work on the multi-label classification of sexism of any kind(s).1 We also consider the related task of misogyny classification. While sexism classification is performed on textual accounts describing sexism suffered or observed, misogyny classification is carried out on tweets perpetrating misogyny. We devise a novel neural framework for classifying sexism and misogyny that can combine text representations obtained using models such as Bidirectional Encoder Representations from Transformers with distributional and linguistic word embeddings using a flexible architecture involving recurrent components and optional convolutional ones. Further, we leverage unlabeled accounts of sexism to infuse domain-specific elements into our framework. To evaluate the versatility of our neural approach for tasks pertaining to sexism and misogyny, we experiment with adapting it for misogyny identification. For categorizing sexism, we investigate multiple loss functions and problem transformation techniques to address the multi-label problem formulation. We develop an ensemble approach using a proposed multi-label classification model with potentially overlapping subsets of the category set. Proposed methods outperform several deep-learning as well as traditional machine learning baselines for all three tasks.

Abstract

Hateful and Toxic content has become a significant concern in today's world due to an exponential rise in social media. The increase in hate speech and harmful content motivated researchers to dedicate substantial efforts to the challenging direction of hateful content identification. In this task, we propose an approach to automatically classify hate speech and offensive content. We have used the datasets obtained from FIRE 2019 and 2020 shared tasks. We perform experiments by taking advantage of transfer learning models. We observed that the pre-trained BERT model and the multilingual-BERT model gave the best results. The code is made publically available at https://github.com/suman101112/hasoc-fire-2020.