Abstract

The effect of adjusting damping factor α, from a small initial value α0 to the final desired αf value, upon then iterations needed for PageRank computation is observed. Adjustment of the damping factor is done in one or more steps. Results show no improvement in performance over a fixed damping factor based PageRank.

Abstract

In this paper, we investigate the design of a system that is both energy efficient and has low hardware complexity. A fully analog architecture is considered in the system model to reduce the hardware complexity. The low beamforming gain of a fully analog system is improved by using double phase shifters at each antenna element, and multi-user(MU) transmission is enabled by using non-orthogonal multiple access(NOMA) as the radio access technique. The problem is formulated as an appropriately constrained energy efficiency(EE) maximization problem. This formulation is non-convex because it is fractional. To simplify this into a convex problem, we propose to use a quadratic transform. We then present an iterative algorithm to obtain optimal beamformer and power allocation. Finally, we evaluate the proposed system model via simulations.

Abstract

In recent times, a few new low-cost sensors have been introduced to the global market for monitoring particulate matter (PM). In this paper, the performance of three such low-cost PM sensors, namely SDS011, Prana Air, and SPS30, for measuring PM2.5 and PM10 levels is evaluated against a standard reference Aeroqual Series-500. The test setup was exposed to PM concentrations ranging from 30 µg/cm3 to 600 µg/cm3 . The results were based on 1 min, 15 min, 30 min, and 1 hr average readings. The experiments were carried out in indoor as well as outdoor environments. The comparative evaluation was performed before and after calibration. The performance of these sensors is evaluated in terms of coefficient of determination (R 2 ), coefficient of variation (Cv) and root mean square error (RMSE). Evaluation results show that these low-cost sensors have good performance after calibration with a reference sensor.

Abstract

During the COVID-19 pandemic, India’s complete lockdown was implemented from March 24 to May 3 2020, to minimize the effects of community transfer and control the rapidly growing rate of the virus spread. In this paper, we focus on quantifying the change in air pollution due to Hyderabad’s lockdown, the capital of Telangana State. For this, two datasets are employed. The first dataset is from the Central Pollution Control Board (CPCB) stations in the city. In contrast, the second dataset is the dense IoT network of PM monitors deployed in the educational campus of IIITH in Gachibowli, Hyderabad. An analysis is done on the collected data to understand the effect of lockdown on PM values while considering the yearly and seasonal variations. It has been shown that while there has been a significant drop in PM values. However, through correlation analysis between the temperature and the PM values during the regular times, not all PM values decrease because of the lockdown

Abstract

Healthy-Unhealthy Music Scale (HUMS), a compact 13-item instrument was developed for assessing musical engagement that is indicative of adolescent well-being (Saarikallio et al, 2015, Child and Adolescent Mental Health). However, there have been no studies examining the validity of HUMS in a clinically depressed cohort (DC).

Abstract

Dementia is a syndrome chronic or progressive that usually affects the cognitive functioning of the subjects. Alzheimer’s, a neurodegenerative disorder, is the leading cause of dementia. One of the many symptoms of Alzheimer’s Dementia is the inability to speak and understand language clearly. The last decade has seen a surge in the research done in Alzheimer’s Dementia detection using Linguistics and acoustic features. This paper takes up the Alzheimer’s Dementia classification task of ADReSS INTERSPEECH-2020 challenge, "Alzheimer’s Dementia Recognition through Spontaneous Speech: The ADReSS Challenge". It uses eight different acoustic features to find the attributes in the human speech production system (vocal track and excitation source) affected by Alzheimer’s Dementia. In this study, the Alzheimer’s dementia classification is performed using five different Machine Learning models using ADReSS INTERSPEECH-2020 challenge dataset. Since most of the studies in the previous literature have used linguistic features successfully for Alzheimer’s dementia classification, the current study also demonstrates the performance of the BERT model for the dementia classification task. The maximum accuracy obtained by the acoustic feature is 64.5%, and the BERT Model provides a classification accuracy of 79.1% over the test dataset. Finally, the score-level fusion of the acoustic model with the BERT Model shows an improvement of 6.1% classification accuracy over the BERT Model, which indicates the complementary nature of acoustic features to linguistic features.

Abstract

The detection and removal of disfluencies from speech is an important task since the presence of disfluencies can adversely affect the performance of speech-based applications such as Automatic Speech Recognition (ASR) systems and speech-to-speech translation systems. From the perspective of Indian languages, there is a lack of studies pertaining to speech disfluencies, their types and frequency of occurrence. Also, the resources available to perform such studies in an Indian context are limited. Through this paper, we attempt to address this issue by introducing the IIITH-Indian English Disfluency (IIITH-IED) Dataset. This dataset consists of 10-hours of lecture mode speech in Indian English. Five types of disfluencies - filled pause, prolongation, word repetition, part-word repetition and phrase repetition were identified in the speech signal and annotated in the corresponding transcription to prepare this dataset. The IIITH-IED dataset was then used to develop framelevel automatic disfluency detection systems. Two sets of features were extracted from the speech signal and then used to train classifiers for the task of disfluency detection. Amongst all the systems employed, Random Forest with MFCC features resulted in the highest average accuracy of 89.61% and F1-score of 0.89.

Abstract

Financial reports filed by various companies discuss compliance, risks, and future plans, such as goals and new projects, which directly impact their stock price. Quick consumption of such information is critical for financial analysts and investors to make stock buy/sell decisions and for equity evaluations. Hence, we study the problem of extractive summarization of 10-K reports. Recently, Transformer-based summarization models have become very popular. However, lack of in-domain labeled summarization data is a major roadblock to train such finance-specific summarization models. We also show that zero-shot inference on such pretrained models is not as effective either. In this paper, we address this challenge by modeling 10-K report summarization using a goal-directed setting where we leverage summaries with labeled goal-related data for the stock buy/sell classification goal. Further, we provide improvements by considering a multi-task learning method with an industry classification auxiliary task. Intrinsic evaluation as well as extrinsic evaluation for the stock buy/sell classification and portfolio construction tasks shows that our proposed method significantly outperforms strong baselines.

Abstract

Coherence is an important aspect of text quality and is crucial for ensuring its readability. It is an essential desirable for outputs from text generation systems like summarization, question answering, machine translation, question generation, table-to-text, etc. An automated coherence scoring model is also helpful in essay scoring or providing writing feedback. A large body of previous work has leveraged entity-based methods, syntactic patterns, discourse relations and more recently traditional deep learning architectures for text coherence assessment. We hypothesize that coherence assessment is a cognitively complex task which requires deeper models and can benefit from other related tasks. Accordingly, in this paper, we propose four different Transformerbased architectures for the task: vanilla Transformer, hierarchical Transformer, multi-task learning-based model, and a model with factbased input representation. Our experiments with popular benchmark datasets across multiple domains on four different coherence assessment tasks demonstrate that our models achieve state-of-the-art results outperforming existing models by a good margin.

Abstract

This paper describes our approach (IIITH) for SemEval-2021 Task 5: HaHackathon: Detecting and Rating Humor and Offense. Our results focus on two major objectives: (i) Effect of task adaptive pretraining on the performance of transformer based models (ii) How does lexical and hurtlex features help in quantifying humour and offense. In this paper, we provide a detailed description of our approach along with comparisions mentioned above.