Search

Arbovirus is a vital, life-threatening disease worldwide and continues to be a significant problem while the world is dealing with the major coronavirus (COVID-19) pandemic. Vectors, mostly mosquitoes and ticks, transmit this disease. Dengue fever, chikungunya, and Zika viruses are the major threats because of their high incidence, public health burden, and clinically significant disease spectrum. These vector-borne disease causes one-fourth of annual deaths, leading to various infectious diseases. The arbovirus represents eight different families and 14 genera; most viruses belong to the family Bunyaviridae, and some also belong to Togaviridae, Reoviridae, and Flaviviridae. The arbovirus disease was isolated first in tropical and subtropical regions of South America and Africa and has high significance because of suitable environmental conditions for virus transmission and vector expansion. Its transmission cycle ranges from simple to highly complex. DENV is the most prevalent, results in febrile illness, and has transmission in 128 different countries. CHIKV causes infection in asymptomatic people, and the problems include nephritis, arthritis, myelitis, and acute encephalopathy. ZIKV-infected 80% of people are asymptomatic and may cause rashes, myalgia, fever, headache, and conjunctivitis. Vaccines for DENV are not clinically available; it is a primary arboviral infection in the world nowadays. The exposure of arbovirus diseases continues to be a global health problem regardless of continuing efforts. This review article will overview major arbovirus diseases and their diagnosis, treatment, and prevention strategies., Comment: 4 Figure, 1 table

As large-scale graphs become more widespread, more and more computational challenges with extracting, processing, and interpreting large graph data are being exposed. It is therefore natural to search for ways to summarize these expansive graphs while preserving their key characteristics. In the past, most graph summarization techniques sought to capture the most important part of a graph statistically. However, today, the high dimensionality and complexity of modern graph data are making deep learning techniques more popular. Hence, this paper presents a comprehensive survey of progress in deep learning summarization techniques that rely on graph neural networks (GNNs). Our investigation includes a review of the current state-of-the-art approaches, including recurrent GNNs, convolutional GNNs, graph autoencoders, and graph attention networks. A new burgeoning line of research is also discussed where graph reinforcement learning is being used to evaluate and improve the quality of graph summaries. Additionally, the survey provides details of benchmark datasets, evaluation metrics, and open-source tools that are often employed in experimentation settings, along with a detailed comparison, discussion, and takeaways for the research community focused on graph summarization. Finally, the survey concludes with a number of open research challenges to motivate further study in this area., Comment: 21 pages, 4 figures, 9 tables, Journal of IEEE Transactions on Artificial Intelligence

Artificial intelligence (AI) enables machines to learn from human experience, adjust to new inputs, and perform human-like tasks. AI is progressing rapidly and is transforming the way businesses operate, from process automation to cognitive augmentation of tasks and intelligent process/data analytics. However, the main challenge for human users would be to understand and appropriately trust the result of AI algorithms and methods. In this paper, to address this challenge, we study and analyze the recent work done in Explainable Artificial Intelligence (XAI) methods and tools. We introduce a novel XAI process, which facilitates producing explainable models while maintaining a high level of learning performance. We present an interactive evidence-based approach to assist human users in comprehending and trusting the results and output created by AI-enabled algorithms. We adopt a typical scenario in the Banking domain for analyzing customer transactions. We develop a digital dashboard to facilitate interacting with the algorithm results and discuss how the proposed XAI method can significantly improve the confidence of data scientists in understanding the result of AI-enabled algorithms.

We compute partition functions of the deformed multiple M5-branes theory on $K3\times T^2$ using the refined topological vertex formalism and the Borcherds lift. The deformation is related to the mass deformation in the corresponding four dimensional $N=4$ $SU(N)$ gauge theory on $K3$. The seed of the Borcherd-lift is calculated by taking the universal part of the type IIb little string free energy of the CY3-fold $X_{N,1}$. We provide explicit modular covariant expressions, as expansions in the mass parameter $m$, of the genus two Siegel modular forms produced by the Borcherds lift of the first few seed functions. We also discuss the relation between genus-one free energy and Ray-Singer Torsion, and the automorphic properties of the latter., Comment: 20 pages+appendices, one figure

In this paper we study certain degenerations of the mirror curves, associated with Calabi-Yau threefolds $X_{N,M}$, and the effect of these degenerations on the topological string partition function of $X_{N,M}$. We show that when the mirror curve degenerates and become the union of the lower genus curves the corresponding partition function factorizes into pieces corresponding to the components of the degenerate mirror curve. Moreoever we show that using degeneration of a generalised mirror curve it is possible to obtain the partition function corresponding to $X_{N,M-1}$ from $X_{N,M}$., Comment: modification of the title,some explanations and references added,Introduction and Discussion sections re-arranged

Recently, many methods discover effective evidence from reliable sources by appropriate neural networks for explainable claim verification, which has been widely recognized. However, in these methods, the discovery process of evidence is nontransparent and unexplained. Simultaneously, the discovered evidence only roughly aims at the interpretability of the whole sequence of claims but insufficient to focus on the false parts of claims. In this paper, we propose a Decision Tree-based Co-Attention model (DTCA) to discover evidence for explainable claim verification. Specifically, we first construct Decision Tree-based Evidence model (DTE) to select comments with high credibility as evidence in a transparent and interpretable way. Then we design Co-attention Self-attention networks (CaSa) to make the selected evidence interact with claims, which is for 1) training DTE to determine the optimal decision thresholds and obtain more powerful evidence; and 2) utilizing the evidence to find the false parts in the claim. Experiments on two public datasets, RumourEval and PHEME, demonstrate that DTCA not only provides explanations for the results of claim verification but also achieves the state-of-the-art performance, boosting the F1-score by 3.11%, 2.41%, respectively., Comment: ACL 2020

With the course of progress in the field of medicine, most of the patients lives can be saved. The only thing required is the proper attention at the proper time. Our wearable solution tries to solve this issue by taking the patients vitals and transmitting them to the server for live monitoring using the mobile app along with the patients current location. In case of an emergency, that is if any vitals show any abnormalities, an SMS is sent to the caregiver of the patient with the patients location so that he can reach there on time., Comment: Published in the Proceedings of the International Conference on Computational Science and Engineering (Beliaghata, Kolkata, India, 4-6 October 2016)

A series of deep learning approaches extract a large number of credibility features to detect fake news on the Internet. However, these extracted features still suffer from many irrelevant and noisy features that restrict severely the performance of the approaches. In this paper, we propose a novel model based on Adversarial Networks and inspirited by the Shared-Private model (ANSP), which aims at reducing common, irrelevant features from the extracted features for information credibility evaluation. Specifically, ANSP involves two tasks: one is to prevent the binary classification of true and false information for capturing common features relying on adversarial networks guided by reinforcement learning. Another extracts credibility features (henceforth, private features) from multiple types of credibility information and compares with the common features through two strategies, i.e., orthogonality constraints and KL-divergence for making the private features more differential. Experiments first on two six-label LIAR and Weibo datasets demonstrate that ANSP achieves the state-of-the-art performance, boosting the accuracy by 2.1%, 3.1%, respectively and then on four-label Twitter16 validate the robustness of the model with 1.8% performance improvements., Comment: Information Sciences

Recently, neural networks based on multi-task learning have achieved promising performance on fake news detection, which focus on learning shared features among tasks as complementary features to serve different tasks. However, in most of the existing approaches, the shared features are completely assigned to different tasks without selection, which may lead to some useless and even adverse features integrated into specific tasks. In this paper, we design a sifted multi-task learning method with a selected sharing layer for fake news detection. The selected sharing layer adopts gate mechanism and attention mechanism to filter and select shared feature flows between tasks. Experiments on two public and widely used competition datasets, i.e. RumourEval and PHEME, demonstrate that our proposed method achieves the state-of-the-art performance and boosts the F1-score by more than 0.87%, 1.31%, respectively., Comment: 10 pages, 5 figures, EMNLP 2019

In a contemporary world, people become dependent on electronic devices. Technologies help to clarification and structure life in many ways to meet the need of the children oriented requirements. The children suffering from disabilities (e.g. autism) has desperate needs for elucidation and structures their life. MumIES is a research based system facilitates to support and manage their living. This paper works on MumIES system to evaluate usability of the system in extraordinary environment for extraordinary people. The paper shows from the survey observation users need supporting tools to access the children's potential and challenges and to give the full support to overcome disabilities. Usability evaluation has been considered one of the key challenges to MumIES system. The paper represents analysis, design of usability studies for the extraordinary user in environment.

We study BPS bound states of little strings in a limit where they realise monopole strings in five dimensional gauge theories. The latter have gauge group $U(M)^N$ and arise from compactification of $(1,0)$ little string theories of type $A_{M-1} \times A_{N-1}$. We find evidence that the partition function of a certain subclass of monopole strings of charge $(k,\ldots,k)$ ($k\geq 1$) is expressible as the partition function of a symmetric orbifold sigma model, whose target space is precisely the symmetric product of the moduli space of monopoles with charge $(1, \ldots, 1)$.