Abstract

Coronavirus 2019, called COVID-19, is a transmissible disease caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). It earlier impacted the citizens of China alone. However, it has rapidly spread all over the world. The COVID-19 supply chain system aims to facilitate access to several critical items, such as personal protective equipment (PPE), biomedical equipment, diagnostics supplies, and vaccines. In this article, we discuss a robust security framework for vaccine distribution and tracking in an Internet of Medical Things (IoMT)-based cloud-assisted COVID-19 environment by considering both intra-country and inter-country scenarios. Various transactions related to vaccine requests, orders, distribution, and tracking are put into the blockchain in the form of blocks. Since blockchain technology offers immutability, transparency, and decentralization, the security of the proposed framework has been improved significantly. The proposed framework also supports artificial intelligence(AI)-based big data analytics on the information stored into the blocks in the blockchain. Furthermore, a practical demonstration of the proposed framework has been done through a blockchain simulation study.

Abstract

—In an Internet of Things (IoT) enabled e-health system, smart health devices sense the health data continuously and share the collected data with the neighboring controller device (i.e., personal server) via some wireless communication mechanism (i.e., bluetooth and zigbee), and finally the data is stored on some health server (i.e., a server over the cloud). The health data is then accessible to healthcare service providers (for example, doctors, nursing staff, relatives of patient) for tracking and monitoring of health conditions of the patients for their better treatment at the earliest. In an IoT enabled health system, the smart healthcare devices communicate over public channel, which causes various types of threats and attacks on the ongoing communication. Therefore, we need a powerful privacypreserving security mechanism to secure the communication happens in an IoT enabled e-health system as the health data is strictly private and confidential. In this paper, we propose a new privacy-preserving access control and key management scheme for the secure communication of IoT enabled e-health system (SPCS-IoTEH). We also conduct informal security analysis of the proposed SPCS-IoTEH to show its robustness against various types of active and passive attacks. The performance of SPCSIoTEH is also shown to be better than other existing competing schemes.

Abstract

— The effect of adjusting damping factor α and tolerance τ on iterations needed for PageRank computation is studied here. Relative performance of PageRank computation with L1, L2, and L∞ norms used as convergence check, are also compared with six possible mean ratios. It is observed that increasing the damping factor α linearly increases the iterations needed almost exponentially. On the other hand, decreasing the tolerance τ exponentially decreases the iterations needed almost exponentially. On average, PageRank with L∞ norm as convergence check is the fastest, quickly followed by L2 norm, and then L1 norm. For large graphs, above certain tolerance τ values, convergence can occur in a single iteration. On the contrary, below certain tolerance τ values, sensitivity issues can begin to appear, causing computation to halt at maximum iteration limit without convergence. The six mean ratios for relative performance comparison are based on arithmetic, geometric, and harmonic mean, as well as the order of ratio calculation. Among them GM-RATIO, geometric mean followed by ratio calculation, is found to be most stable, followed by AM-RATIO.

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

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

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 study aims to first formulate a tool to identify an individual’s natural affinity towards appreciation of music vs lyrics and identify personality traits (including empathic and emotional traits) associated with the same.

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.