PQSCT: Pseudo-Siamese BERT for Concept Tagging With Both Questions and Solutions

The global outbreak of the new coronavirus epidemic has promoted the development of intelligent education and the utilization of online learning systems. In order to provide students with intelligent services such as cognitive diagnosis and personalized exercises recommendation, a fundamental task is the concept tagging for exercises, which extracts knowledge index structures and knowledge representations for exercises. Unfortunately, to the best of our knowledge, existing tagging approaches based on exercise content either ignore multiple components of exercises, or ignore that exercises may contain multiple concepts. To this end, in this paper, we present a study of concept tagging. First, we propose an improved pre-trained BERT for concept tagging with both questions and solutions (QSCT). Specifically, we design a question-solution prediction task and apply the BERT encoder to combine questions and solutions, ultimately obtaining the final exercise representation through feature augmentation. Then, to further explore the relationship between questions and solutions, we extend the QSCT to a pseudo-siamese BERT for concept tagging with both questions and solutions (PQSCT). We optimize the feature fusion strategy, which integrates five different vector features from local and global into the final exercise representation. Finally, we conduct extensive experiments on real-world datasets, which clearly demonstrate the effectiveness of our proposed models for concept tagging. IEEE

CCTwins: A Weakly-Supervised Transformer-based Crowd Counting Method with Adaptive Scene Consistency Attention

Recently, crowd counting has attracted significant attention, particularly in the context of the COVID-19 pandemic, due to its ability to automatically provide accurate crowd numbers in images. To address the challenges of location-level labeling, several transformer-based crowd counting methods have been proposed with only count-level supervision. However, these methods directly use the transformer as an encoder without considering the uneven crowd distribution. To address this issue, we propose CCTwins, a novel transformer-based crowd counting method with only count-level supervision. Specifically, we introduce an adaptive scene consistency attention mechanism to enhance the transformer-based model Twins-SVT-L for feature extraction in crowded scenes. Additionally, we design a multi-level weakly-supervised loss function that generates estimated crowd numbers in a coarse-to-fine manner, making it more appropriate for weakly-supervised settings. Moreover, intermediate features supervised by count-level labels are utilized to fuse multi-scale features. Experimental results on four public datasets demonstrate that our proposed method outperforms the state-of-the-art weakly-supervised methods, achieving up to a 16.6% improvement in MAE and up to a 13.8% improvement in RMSE across all evaluation settings. Moreover, the proposed CCTwins obtains competitive counting performance, even when compared to the state-of-the-art fully-supervised methods. IEEE

The Model of Organizational Performance Based on Employees' Dynamic Capabilities-Verification During Crisis Caused by Black Swan Event

The article concerns the potential influence of employees' dynamic capabilities on the performance of entire organization, which operates in crisis caused by Black Swan event. It is the expansion of job performance model based on employees' dynamic capabilities, proposing the possibility of translating the positive influence of those capabilities onto entire organization and underlining the importance of employees' dynamic capabilities during crisis within organization. Based on literature analysis, the shape of the amended model is proposed, in which employees' dynamic capabilities influence organizational performance through elements of the original model (person-job fit, work motivation, job satisfaction, work engagement and job performance), and additional ones: person-organization fit, person-supervisor fit. The proposed model is empirically verified based on the sample of 1160 organization operating in Poland, Italy and USA during an active wave of COVID-19 pandemic (which is an example of Black Swan event). The results obtained using path analysis confirmed that employees' dynamic capabilities indeed influence organizational performance of organizations operating in crisis caused by Black Swan event through elements proposed in the model.

FedUSC: Collaborative Unsupervised Representation Learning from Decentralized Data for Internet of Things

Federated Learning (FL) lately has shown much promise in improving the shared model and preserving data privacy. However, these existing methods are only of limited utility in the Internet of Things (IoT) scenarios, as they either heavily depend on high-quality labeled data or only perform well under idealized conditions, which typically cannot be found in practical applications. In this paper, we propose a novel federated unsupervised learning method for image classification without the use of any ground truth annotations. In IoT scenarios, a big challenge is that decentralized data among multiple clients is normally non-IID, leading to performance degradation. To address this issue, we further propose a dynamic update mechanism that can decide how to update the local model based on weights divergence. Extensive experiments show that our method outperforms all baseline methods by large margins, including +6.67% on CIFAR-10, +5.15% on STL-10, and +8.44% on SVHN in terms of classification accuracy. In particular, we obtain promising results on Mini-ImageNet and COVID-19 datasets and outperform several federated unsupervised learning methods under non-IID settings. IEEE

Assessing the Impact of Contextual Information in Hate Speech Detection

Social networks and other digital media deal with huge amounts of user-generated contents where hate speech has become a problematic more and more relevant. A great effort has been made to develop automatic tools for its analysis and moderation, at least in its most threatening forms, such as in violent acts against people and groups protected by law. One limitation of current approaches to automatic hate speech detection is the lack of context. The spotlight on isolated messages, without considering any type of conversational context or even the topic being discussed, severely restricts the available information to determine whether a post on a social network should be tagged as hateful or not. In this work, we assess the impact of adding contextual information to the hate speech detection task. We specifically study a subdomain of Twitter data consisting of replies to digital newspapers posts, which provides a natural environment for contextualized hate speech detection. We built a new corpus in Spanish (Rioplatense variant) focused on hate speech associated to the COVID-19 pandemic, annotated using guidelines carefully designed by our interdisciplinary team. Our classification experiments using state-of-the-art transformer-based machine learning techniques show evidence that adding contextual information improves the performance of hate speech detection for two proposed tasks: binary and multi-label prediction, increasing their Macro F1 by 4.2 and 5.5 points, respectively. These results highlight the importance of using contextual information in hate speech detection. Our code, models, and corpus has been made available for further research. © 2013 IEEE.

A Prompt-Based Topic-Modeling Method for Depression Detection on Low-Resource Data

Depression has a large impact on one’s personal life, especially during the COVID-19 pandemic. People have been trying to develop reliable methods for the depression detection task. Recently, methods based on deep learning have attracted much attention from the research community. However, they still face the challenge that data collection and annotation are difficult and expensive. In many real-world applications, only a small number of or even no training data are available. In this context, we propose a Prompt-based Topic-modeling method for Depression Detection (PTDD) on low-resource data, aiming to establish an effective way of depression detection under the above challenging situation. Instead of learning discriminating features from a small amount of labeled data, the proposed framework turns to leverage the generalization power of pretrained language models. Specifically, based on the question-and-answer routine during the interview, we first reorganize the text data according to the predefined topics for each interviewee. Via the prompt-based framework, we then predict whether the next-sentence prompt is emotionally positive or not. Finally, the depression detection task can be achieved based on the obtained topicwise predictions through a simple voting process. In the experiments, we validate the effectiveness of our model under several low-resource data settings. The results and analysis demonstrate that our PTDD achieves acceptable performance when only a few training samples or even no training samples are available. IEEE

Examining the Influence of Trustworthiness, Financial Rewards, and Admiration for Crowdsourcing in the Post COVID-19 Period

Over the past two decades, crowdsourcing activities have expanded considerably. More recently, the COVID-19 pandemic has radically changed the way people live and work, and the way organizations do business. So far, not many studies have analyzed if and to what extent trustworthiness can influence the admiration to practice crowdsourcing and could reward financial benefits in the COVID-19 period. Against this background, in this article, the aim is to investigate the influence of crowdfunding trustworthiness and financial rewards on the success of crowdsourcing activities. The analysis is made more complete by including technology leadership support as a moderator. With the help of the existing literature and theories, a research model has been developed conceptually, which was later validated using the partial least square-structural equation modeling technique on a sample of 319 responses from participants based in Europe and Asia. The study found that lucidity, gamification, exposure, and coordination along with financial rewards positively influence admiration for crowdsourcing, which, in turn, positively impacts successful crowdsourcing practices in the COVID-19 period. The study also shows that there is a significant moderating impact of technological leadership support on successful crowdsourcing practices in the COVID-19 period. IEEE

A Static Machine Learning Based Evaluation Method for Usability and Security Analysis in E-Commerce website

Measurement of e-commerce usability based on static quantities variable is state-of-the-art because of the adoption of sequential tracing of the next phase in the categorical data. An offline static model is trained. A static model is trained offline. In other words, we train the model once and then use it for a set period of time. The global COVID-19 outbreak has completely disrupted society and drastically altered daily life. The concept refers to an electronic commerce network that appears with thorough, understandable conviction, demand, and rapid confirmation as a replacement for the economic market’s "brick-and-mortar" model, which replaces how we do everything, including business strategy, and provides a better understanding with the interpretation of e-commerce features. This study was supervised to analyses usability assessments using statistical methods, as well as security assessments using online e-commerce security scanner tools, in order to investigate e-business standards that take into account the caliber of e-services in e-commerce websites across Asian nations. The method was developed to optimize complex systems based on multiple criteria. The initial (supplied) weights are used to determine the compromise ranking list and compromise solution. This paper examines the usability of e-commerce in rural areas using a new data set from the Jharkhand region. On the e-commerce websites of Jharkhand, India, usability is commonly considered in conjunction with learnability, memorability, effectiveness, engagement, efficiency, and completeness. Using a user-oriented questionnaire testing method, this survey attempts to close the gaps mentioned above. Then, across each column, divide each value by the column-wise sum that is created using their corresponding value, whichever produces a new matrix B. Finally, determine the row-wise sum of matrix B that represents the (3 X 1) matrix. Using model trees and bagging, this study addresses classification-related issues. This regression technique is useful for problems involving classification. The model is trained using secondary data from the MBTI 16 personality factors affecting personality category. Author

1000 days of COVID-19: A gender-based long-term investigation into attitudes with regards to vaccination

The coronavirus pandemic has undoubtedly been one of the major recent events that have affected our society at the global level. During this period, unprecedented measures have been imposed worldwide by authorities in an effort to contain the spread of the disease. These measures have led to a worldwide debate among the public, occurring not least within the forum of social media, tapping into pre-existing trends of skepticism, such as vaccine hesitancy. At the same time, it has become apparent that the pandemic affected women and men differently. With these two themes in view, the paper aims to analyze using a data-driven approach the evolution of opinions with regards to vaccination against COVID-19 throughout the entire duration of the pandemic from the point of view of gender. For this analysis, approximately 1,500,000 short user-contributed texts have been retrieved from the popular microblogging platform Twitter, posted between 30 January 2020 and 30 November 2022. Using a machine learning approach, several classifiers have been trained to identify the likely gender (female or male) of the author, as well as the stance of the specific post towards the COVID-19 vaccines (neutral, in favor, or against), achieving 85.69% and 93.64% weighted accuracy measures for each problem, respectively. Based on this analysis, it can be observed that most tweets exhibit a neutral stance, while the number of tweets in favor of vaccination is greater than the number of tweets opposing vaccination, with the distribution varying across time in response to specific events. The subject matter of the tweets varied more between stances than between genders, suggesting that there is no significant difference between the contents of tweets posted by females and males. We also find that while the overall engagement on Twitter with the topic of vaccination against COVID-19 is on the wane, there has been a rise in the number of against tweets continuing into the present. Author

Crowd-Resourcing in Response to the COVID-19 Pandemic: A Resource Transformation Perspective

Driven by recent calls for more research that examines forms of crowdsourcing used to address social challenges, in this article, we contribute to the broader literature on open innovation and crowdsourcing by investigating how crowdsourcing platforms enable the transformation of crowd-based resources. We have focused on initiatives with broader social purposes, rather than those that are for-profit and single firm-driven, where the resulting resources are usually solely controlled by a specific organization. By analyzing 19 crowd-based initiatives with a similar context—responding to the coronavirus disease pandemic—we studied a variety of initiatives and identified three distinct types of crowdsourcing platforms that enable resource transformation: resource pooling;resource cocreation;and resource enabling beyond the platform boundaries. We depict how access to and control of resources vary across initiatives. We have framed our contribution as crowd-resourcing, providing a reference model for the design of platforms based on the type of involvement and expected degree of resource transformation. IEEE

SD-GAN: A Style Distribution Transfer Generative Adversarial Network for Covid-19 Detection through X-ray Images

The Covid-19 pandemic is a prevalent health concern around the world in recent times. Therefore, it is essential to screen the infected patients at the primary stage to prevent secondary infections from person to person. The reverse transcription polymerase chain reaction (RT-PCR) test is commonly performed for Covid-19 diagnosis, while it requires significant effort from health professionals. Automated Covid-19 diagnosis using chest X-ray images is one of the promising directions to screen infected patients quickly and effectively. Automatic diagnostic approaches are used with the assumption that data originating from different sources have the same feature distributions. However, the X-ray images generated in different laboratories using different devices experience style variations e.g., intensity and contrast which contradict the above assumption. The prediction performance of deep models trained on such heterogeneous images of different distributions with different noises is affected. To address this issue, we have designed an automatic end-to-end adaptive normalization-based model called style distribution transfer generative adversarial network (SD-GAN). The designed model is equipped with the generative adversarial network (GAN) and task-specific classifier to transform the style distribution of images between different datasets belonging to different race people and carried out Covid-19 detection effectively. Evaluated results on four different X-ray datasets show the superiority of the proposed model to state-of-the-art methods in terms of the visual quality of style transferred images and the accuracy of Covid-19 infected patient detection. SD-GAN is publicly available at: https://github.com/tasleem-hello/SD-GAN/tree/SD-GAN. Author

Removing Zero Variance Units of Deep Models for COVID-19 Detection

Deep Learning has been used for several applications including the analysis of medical images. Some transfer learning works show that an improvement in performance is obtained if a pre-trained model on ImageNet is transferred to a new task. Taking into account this, we propose a method that uses a pre-trained model on ImageNet to fine-tune it for Covid-19 detection. After the fine-tuning process, the units that produce a variance equal to zero are removed from the model. Finally, we test the features of the penultimate layer in different classifiers removing those that are less important according to the f-test. The results produce models with fewer units than the transferred model. Also, we study the attention of the neural network for classification. Noise and metadata printed in medical images can bias the performance of the neural network and it obtains poor performance when the model is tested on new data. We study the bias of medical images when raw and masked images are used for training deep models using a transfer learning strategy. Additionally, we test the performance on novel data in both models: raw and masked data. Author

JDSR-GAN: Constructing An Efficient Joint Learning Network for Masked Face Super-Resolution

With the growing importance of preventing the COVID-19 virus in cyber-manufacturing security, face images obtained in most video surveillance scenarios are usually low resolution together with mask occlusion. However, most of the previous face super-resolution solutions can not efficiently handle both tasks in one model. In this work, we consider both tasks simultaneously and construct an efficient joint learning network, called JDSR-GAN, for masked face super-resolution tasks. Given a low-quality face image with mask as input, the role of the generator composed of a denoising module and super-resolution module is to acquire a high-quality high-resolution face image. The discriminator utilizes some carefully designed loss functions to ensure the quality of the recovered face images. Moreover, we incorporate the identity information and attention mechanism into our network for feasible correlated feature expression and informative feature learning. By jointly performing denoising and face super-resolution, the two tasks can complement each other and attain promising performance. Extensive qualitative and quantitative results show the superiority of our proposed JDSR-GAN over some competitive methods. IEEE

Robust Task Scheduling for Heterogeneous Robot Teams Under Capability Uncertainty

This article develops a stochastic programming framework for multiagent systems, where task decomposition, assignment, and scheduling problems are simultaneously optimized. The framework can be applied to heterogeneous mobile robot teams with distributed subtasks. Examples include pandemic robotic service coordination, explore and rescue, and delivery systems with heterogeneous vehicles. Owing to their inherent flexibility and robustness, multiagent systems are applied in a growing range of real-world problems that involve heterogeneous tasks and uncertain information. Most previous works assume one fixed way to decompose a task into roles that can later be assigned to the agents. This assumption is not valid for a complex task where the roles can vary and multiple decomposition structures exist. Meanwhile, it is unclear how uncertainties in task requirements and agent capabilities can be systematically quantified and optimized under a multiagent system setting. A representation for complex tasks is proposed: agent capabilities are represented as a vector of random distributions, and task requirements are verified by a generalizable binary function. The conditional value at risk is chosen as a metric in the objective function to generate robust plans. An efficient algorithm is described to solve the model, and the whole framework is evaluated in two different practical test cases: capture-the-flag and robotic service coordination during a pandemic (e.g., COVID-19). Results demonstrate that the framework is generalizable, is scalable up to 140 agents and 40 tasks for the example test cases, and provides low-cost plans that ensure a high probability of success.

Foreign Bodies Detector Based on DETR for High-Resolution X-Ray Images of Textiles

Foreign bodies (FBs) detection for X-ray images of textiles is a novel and challenging task. To solve the problem of poor performance of anchor-based detectors for FBs detection, we propose a feature-enhanced object detection framework with transformer (FE-DETR). Based on the split-attention of residual split-attention network (ResNeSt), we add convolutional block attention module (CBAM) between residual blocks and replace the $3\times $ 3 convolutional layer of the last residual block with deformable convolution network (DCN) to adapt FBs with different scales. Then, we propose a multiscale feature encoding (MSFE) module to solve the feature dispersion caused by deep convolution. Meanwhile, the transformer module is selected as the prediction head of the detector. During training, several heuristic strategies are used to further optimize the performance of FE-DETR. In addition, we construct a benchmark dataset for the textile FBs detection task. With end-to-end training, FE-DETR achieves higher performance than the baseline and mainstream state-of-the-art methods, with mean average precision (mAP) = 0.74, average precision (AP) = 0.992, average recall (AR) = 0.971, and $F1$ -score = 0.987. This article has been applied to the production line of medical protective clothing during the Corona Virus Disease 2019 (COVID-19) period and has yielded impressive results in actual production. © 1963-2012 IEEE.

A Blockchain-Based Crowdsourcing Loan Platform for Funding Higher Education in Developing Countries

In developing countries, funding is a significant obstacle to receiving higher education. Brilliant but needy students cannot complete their studies since their parents are unemployed and their countries' economies are poor. As a result, the students' talents are not harnessed to their full potential. In order to help students obtain higher education and harness their full potential, governments provide student loans to students in higher education. The government provides loans to students through the ministry of education. The students pay back the loan with interest when they start working. Governments have been the sole funders of student loans. The emergence of COVID-19 and the Russia-Ukraine war have resulted in a global economic crisis. Because of the global economic crisis, the government's spending has increased. In order to help reduce the burden of government and thereby reduce spending, we intend to revolutionize the student loan program through blockchain and crowdsourcing. This work presents a blockchain-based crowdsourcing decentralized loan platform where investors will be brought on board to provide funds for students in higher education. The platform will allow students to apply for loans from investors through registered financial institutions. The students will pay back the loans with interest when they enter the workforce. The proposed platform will allow students to fund their education, investors will get interest on the money they invest, and governments can channel the money they put into student loan programs into other avenues. We perform a thorough security analysis and back the efficiency of our work with numerical results. © 2013 IEEE.

Detecting -Vertex Cuts in Sparse Networks via a Fast Local Search Approach

The k-vertex cut (k-VC) problem belongs to the family of the critical node detection problems, which aims to find a minimum subset of vertices whose removal decomposes a graph into at least k connected components. It is an important NP-hard problem with various real-world applications, e.g., vulnerability assessment, carbon emissions tracking, epidemic control, drug design, emergency response, network security, and social network analysis. In this article, we propose a fast local search (FLS) approach to solve it. It integrates a two-stage vertex exchange strategy based on neighborhood decomposition and cut vertex, and iteratively executes operations of addition and removal during the search. Extensive experiments on both intersection graphs of linear systems and coloring/DIMACS graphs are conducted to evaluate its performance. Empirical results show that it significantly outperforms the state-of-the-art (SOTA) algorithms in terms of both solution quality and computation time in most of the instances. To evaluate its generalization ability, we simply extend it to solve the weighted version of the k-VC problem. FLS also demonstrates its excellent performance. IEEE

Masked Face Recognition Dataset and Application

During COVID-19 coronavirus epidemic, almost everyone wears a mask to prevent the spread of virus. It raises a problem that the traditional face recognition model basically fails in the scene of face-based identity verification, such as security check, community visit check-in, etc. Therefore, it is imminent to boost the performance of masked face recognition. Most recent advanced face recognition methods are based on deep learning, which heavily depends on a large number of training samples. However, there are presently no publicly available masked face recognition datasets, especially real ones. To this end, this work proposes three types of masked face datasets, including Masked Face Detection Dataset (MFDD), Real-world Masked Face Recognition Dataset (RMFRD) and Synthetic Masked Face Recognition Dataset (SMFRD). Besides, we conduct benchmark experiments on these three datasets for reference. As far as we know, we are the first to publicly release large-scale masked face recognition datasets that can be downloaded for free at https://github.com/X-zhangyang/Real-World-Masked-Face-Dataset.. IEEE

Pediatric Primary Care Mental Health Specialist Examination: Job Task Analysis

Developmental, behavioral, and mental health (DBMH) conditions among pediatric populations have increased in prevalence in primary care. Approximately 1 in 5 children have mental health conditions, but only 20% receive care. In October 2021, a national emergency in children's mental health was declared. The Pediatric Nursing Certification Board offers a pediatric primary care mental health specialist (PMHS) examination that validates the knowledge, skills, and abilities of certified nurse practitioners caring for children, adolescents, and young adults with DBMH conditions. This review describes the methodology, data analysis, and results of the job task analysis that ensures examination quality measuring preparedness to practice as a certified PMHS.

Ad-Hoc Monitoring of COVID-19 Global Research Trends for Well-Informed Policy Making

The COVID-19 pandemic has affected millions of people worldwide with severe health, economic, social, and political implications. Healthcare Policy Makers (HPMs) and medical experts are at the core of responding to this continuously evolving pandemic situation and are working hard to contain the spread and severity of this relatively unknown virus. Biomedical researchers are continually discovering new information about this virus and communicating the findings through scientific articles. As such, it is crucial for HPMs and funding agencies to monitor the COVID-19 research trend globally on a regular basis. However, given the influx of biomedical research articles, monitoring COVID-19 research trends has become more challenging than ever, especially when HPMs want on-demand guided search techniques with a set of topics of interest in mind. Unfortunately, existing topic trend modeling techniques are unable to serve this purpose as (1) traditional topic models are unsupervised, and (2) HPMs in different regions may have different topics of interest that they want to track. To address this problem, we introduce a novel computational task in this article called Ad-Hoc Topic Tracking, which is essentially a combination of zero-shot topic categorization and the spatio-temporal analysis task. We then propose multiple zero-shot classification methods to solve this task by building on state-of-the-art language understanding techniques. Next, we picked the best-performing method based on its accuracy on a separate validation dataset and then applied it to a corpus of recent biomedical research articles to track COVID-19 research endeavors across the globe using a spatio-temporal analysis. A demo website has also been developed for HPMs to create custom spatio-temporal visualizations of COVID-19 research trends. The research outcomes demonstrate that the proposed zero-shot classification methods can potentially facilitate further research on this important subject matter. At the same time, the spatio-temporal visualization tool will greatly assist HPMs and funding agencies in making well-informed policy decisions for advancing scientific research efforts. [ABSTRACT FROM AUTHOR] Copyright of ACM Transactions on Intelligent Systems & Technology is the property of Association for Computing Machinery and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)