Pre-gating and contextual attention gate - A new fusion method for multi-modal data tasks.

Multi-modal representation learning has received significant attention across diverse research domains due to its ability to model a scenario comprehensively. Learning the cross-modal interactions is essential to combining multi-modal data into a joint representation. However, conventional cross-attention mechanisms can produce noisy and non-meaningful values in the absence of useful cross-modal interactions among input features, thereby introducing uncertainty into the feature representation. These factors have the potential to degrade the performance of downstream tasks. This paper introduces a novel Pre-gating and Contextual Attention Gate (PCAG) module for multi-modal learning comprising two gating mechanisms that operate at distinct information processing levels within the deep learning model. The first gate filters out interactions that lack informativeness for the downstream task, while the second gate reduces the uncertainty introduced by the cross-attention module. Experimental results on eight multi-modal classification tasks spanning various domains show that the multi-modal fusion model with PCAG outperforms state-of-the-art multi-modal fusion models. Additionally, we elucidate how PCAG effectively processes cross-modality interactions.

A review on modelling of thermochemical processing of biomass for biofuels and prospects of artificial intelligence-enhanced approaches.

Biofuels from lignocellulosic biomass converted via thermochemical technologies can be renewable and sustainable, which makes them promising as alternatives to conventional fossil fuels. Prior to building industrial-scale thermochemical conversion plants, computational models are used to simulate process flows and conditions, conduct feasibility studies, and analyse process and business risk. This paper aims to provide an overview of the current state of the art in modelling thermochemical conversion of lignocellulosic biomass. Emphasis is given to the recent advances in artificial intelligence (AI)-based modelling that plays an increasingly important role in enhancing the performance of the models. This review shows that AI-based models offer prominent accuracy compared to thermodynamic equilibrium modelling implemented in some models. It is also evident that gasification and pyrolysis models are more matured than thermal liquefaction for lignocelluloses. Additionally, the knowledge gained and future directions in the applications of simulation and AI in process modelling are explored.

Explainability of the COVID-19 epidemiological model with nonnegative tensor factorization.

The world is witnessing the devastating effects of the COVID-19 pandemic. Each country responded to contain the spread of the virus in the early stages through diverse response measures. Interpreting these responses and their patterns globally is essential to inform future responses to COVID-19 variants and future pandemics. A stochastic epidemiological model (SEM) is a well-established mathematical tool that helps to analyse the spread of infectious diseases through communities and the effects of various response measures. However, interpreting the outcome of these models is complex and often requires manual effort. In this paper, we propose a novel method to provide the explainability of an epidemiological model. We represent the output of SEM as a tensor model. We then apply nonnegative tensor factorization (NTF) to identify patterns of global response behaviours of countries and cluster the countries based on these patterns. We interpret the patterns and clusters to understand the global response behaviour of countries in the early stages of the pandemic. Our experimental results demonstrate the advantage of clustering using NTF and provide useful insights into the characteristics of country clusters.

Deep learning based topic and sentiment analysis: COVID19 information seeking on social media.

Social media platforms have become a common place for information exchange among their users. People leave traces of their emotions via text expressions. A systematic collection, analysis, and interpretation of social media data across time and space can give insights into local outbreaks, mental health, and social issues. Such timely insights can help in developing strategies and resources with an appropriate and efficient response. This study analysed a large Spatio-temporal tweet dataset of the Australian sphere related to COVID19. The methodology included a volume analysis, topic modelling, sentiment detection, and semantic brand score to obtain an insight into the COVID19 pandemic outbreak and public discussion in different states and cities of Australia over time. The obtained insights are compared with independently observed phenomena such as government-reported instances.

An observational analysis of the trope "A p-value of < 0.05 was considered statistically significant" and other cut-and-paste statistical methods.

Appropriate descriptions of statistical methods are essential for evaluating research quality and reproducibility. Despite continued efforts to improve reporting in publications, inadequate descriptions of statistical methods persist. At times, reading statistical methods sections can conjure feelings of dèjá vu, with content resembling cut-and-pasted or "boilerplate text" from already published work. Instances of boilerplate text suggest a mechanistic approach to statistical analysis, where the same default methods are being used and described using standardized text. To investigate the extent of this practice, we analyzed text extracted from published statistical methods sections from PLOS ONE and the Australian and New Zealand Clinical Trials Registry (ANZCTR). Topic modeling was applied to analyze data from 111,731 papers published in PLOS ONE and 9,523 studies registered with the ANZCTR. PLOS ONE topics emphasized definitions of statistical significance, software and descriptive statistics. One in three PLOS ONE papers contained at least 1 sentence that was a direct copy from another paper. 12,675 papers (11%) closely matched to the sentence "a p-value < 0.05 was considered statistically significant". Common topics across ANZCTR studies differentiated between study designs and analysis methods, with matching text found in approximately 3% of sections. Our findings quantify a serious problem affecting the reporting of statistical methods and shed light on perceptions about the communication of statistics as part of the scientific process. Results further emphasize the importance of rigorous statistical review to ensure that adequate descriptions of methods are prioritized over relatively minor details such as p-values and software when reporting research outcomes.

Machine learning-based modeling in food processing applications: State of the art.

Food processing is a complex, multifaceted problem that requires substantial human interaction to optimize the various process parameters to minimize energy consumption and ensure better-quality products. The development of a machine learning (ML)-based approach to food processing applications is an exciting and innovative idea for optimizing process parameters and process kinetics to reduce energy consumption, processing time, and ensure better-quality products; however, developing such a novel approach requires significant scientific effort. This paper presents and evaluates ML-based approaches to various food processing operations such as drying, frying, baking, canning, extrusion, encapsulation, and fermentation to predict process kinetics. A step-by-step procedure to develop an ML-based model and its practical implementation is presented. The key challenges of neural network training and testing algorithms and their limitations are discussed to assist readers in selecting algorithms for solving problems specific to food processing. In addition, this paper presents the potential and challenges of applying ML-based techniques to hybrid food processing operations. The potential of physics-informed ML modeling techniques for food processing applications and their strategies is also discussed. It is expected that the potential information of this paper will be valuable in advancing the ML-based technology for food processing applications.

Progressive domain adaptation for detecting hate speech on social media with small training set and its application to COVID-19 concerned posts.

In this world of information and experience era, microblogging sites have been commonly used to express people feelings including fear, panic, hate and abuse. Monitoring and control of abuse on social media, especially during pandemics such as COVID-19, can help in keeping the public sentiment and morale positive. Developing the fear and hate detection methods based on machine learning requires labelled data. However, obtaining the labelled data in suddenly changed circumstances as a pandemic is expensive and acquiring them in a short time is impractical. Related labelled hate data from other domains or previous incidents may be available. However, the predictive accuracy of these hate detection models decreases significantly if the data distribution of the target domain, where the prediction will be applied, is different. To address this problem, we propose a novel concept of unsupervised progressive domain adaptation based on a deep-learning language model generated through multiple text datasets. We showcase the efficacy of the proposed method in hate speech and fear detection on the tweets collection during COVID-19 where the labelled information is unavailable.

Identifying Covid-19 misinformation tweets and learning their spatio-temporal topic dynamics using Nonnegative Coupled Matrix Tensor Factorization.

Social media platforms like Twitter have become an easy portal for billions of people to connect and exchange their thoughts. Unfortunately, people commonly use these platforms to share misinformation which can influence other people adversely. The spread of misinformation is unavoidable in an extraordinary situation like Covid-19, and the consequences can be dreadful. This paper proposes a two-step ranking-based misinformation detection (RMiD) technique. Firstly, a novel ranking-based approach leveraging the scalable information retrieval infrastructure is applied to detect misinformation from a huge collection of unlabelled tweets based on a related but very small labelled misinformation data set. Secondly, the identified misinformation tweets are represented as a coupled matrix tensor model and Nonnegative Coupled Matrix Tensor Factorization is applied to learn their spatio-temporal topic dynamics. The experimental analysis shows that RMiD is capable of detecting misinformation with better coverage and less noise in comparison with existing techniques. Moreover, the coupled matrix tensor representation has improved the quality of topics discovered from unlabelled data up to 4% by leveraging the semantic similarity of terms in labelled data. SUPPLEMENTARY INFORMATION: The online version supplementary material available at 10.1007/s13278-021-00767-7.

Injury narrative text classification using factorization model.

Narrative text is a useful way of identifying injury circumstances from the routine emergency department data collections. Automatically classifying narratives based on machine learning techniques is a promising technique, which can consequently reduce the tedious manual classification process. Existing works focus on using Naive Bayes which does not always offer the best performance. This paper proposes the Matrix Factorization approaches along with a learning enhancement process for this task. The results are compared with the performance of various other classification approaches. The impact on the classification results from the parameters setting during the classification of a medical text dataset is discussed. With the selection of right dimension k, Non Negative Matrix Factorization-model method achieves 10 CV accuracy of 0.93.

Generating rules with predicates, terms and variables from the pruned neural networks.

Artificial neural networks (ANN) have demonstrated good predictive performance in a wide range of applications. They are, however, not considered sufficient for knowledge representation because of their inability to represent the reasoning process succinctly. This paper proposes a novel methodology Gyan that represents the knowledge of a trained network in the form of restricted first-order predicate rules. The empirical results demonstrate that an equivalent symbolic interpretation in the form of rules with predicates, terms and variables can be derived describing the overall behaviour of the trained ANN with improved comprehensibility while maintaining the accuracy and fidelity of the propositional rules.