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

Radiium systemic radiotherapy - 223 patients with mCRPC. Experience of the Republic of Bashkortostan

Introduction & Objectives: The incidence of prostate cancer, both in the world and in the Russian Federation, tends to increase. In the Republic of Bashkortostan in 2021, 699 patients with this diagnosis were registered. 19.6% of patients had stage IV disease at the time of diagnosis. 5818 patients were registered, of which 361 died within a year. The effectiveness of hormonal treatment of common prostate cancer has time limitations, after which there is a development of resistance to castration and progression of the disease. To date, drugs such as kabazitaxel, sipuleucel-T vaccine, abiraterone, enzalutamide and radium-223 have been approved for use in metastatic CRPC. The purpose of the work: analysis of the experience of systemic radiotherapyand Radium - 223 patients with mCRPC in the Republic of Bashkortostan in 2021. Material(s) and Method(s): Analysis of patients who received systemic radiotherapy Radium - 223 in the Republic of Bashkortostan according to medical documentation and research data. In 2021, Radiy-223 radiotherapy was performed on 7 patients diagnosed with mCRPC. Median age 63.14 years. All patients met the criteria for treatment, i.e. had castration-resistant prostate cancer with bone metastases, without visceral metastases. All patients had concomitant pathology from the cardiovascular system, respiratory tract, endocrine system. According to the previous surgical treatment, patients were distributed as follows: orchidectomy - 4, prostatectomy - 1 and 2 patients underwent tumor biopsy. By morphology: Glisson 6 - 2 patients, Glisson 7 - 1, Glisson 8 - 3, Glisson 10 - 1. 4 patients were referred to Xofigo for radiologically confirmed progression, 3 patients were progressingin height at PSA levels. Result(s): 1 patient previously received 1 line of systemic therapy, 5 patients received 2 lines, 1 patient received 3 lines of therapy. 6 patients received all 6 courses of radiotherapy, 1 patient did not complete treatment due to COVID 19. He is expected to complete therapy. All patients are currently alive with no signs of disease progression. Serious side effects were not registered. Conclusion(s): The "therapeutic window" for the prescription of radium-223 is the period before the appearance of visceral metastases and decline of the somatic status. To achieve the maximum benefit from the appointment of radium-223, it is necessary to conduct >=5 cycles of therapy, which is possible in 1-2 treatment lines. It is necessary to select patients carefully for radiotherapy - Radium 223.Copyright © 2022 European Association of Urology. Published by Elsevier B.V.

Successful Application of Foamed Cement Slurry in an Ultradeepwater Well of 11,900-ft Water Depth (Claiming World Record)

Foamed cement was successfully used in the riserless section of an ultradeepwater well located in 11,900ft water depth. Foamed cement was selected to minimize operating costs and provide flexibility to adjust slurry density on a short notice. The seawater column exerted 5,319.1-psi hydrostatic pressure on the annulus. Consequently, nitrogen (N2) density could no longer be neglected. This paper presents simulations performed in preparation for the job, operational considerations, and post-job evaluation. The lead slurry needed a density of 1.25 SG and develops a compressive strength of at least 300 psi within 48 hr. Considering the cost and challenges associated with outsourcing resources under current Covid-19 pandemic restrictions, the foamed cement system was preferred over chemical-or particle-extended cement or blend systems. The N2 ratio for the foamed cement slurry system was 700 scf/bbl. With a base slurry pumping rate of 5 bbl/min, the required N2 pumping rate was 3,500 scf/min, which was greater than the capability of a single N2 pump (3,000-scf/min rate). Because the rig deck space could not accommodate three N2 pumps, one pump would serve as backup;thus, the final plan consisted of using two N2 pumps simultaneously. Two parallel foamed slurry treating lines were rigged up to reduce the fluid velocity in a single line. All laboratory testing was conducted locally. Additives used in the foamed slurry were environmentally friendly. A proprietary process-control system was used during the cementing operation and automatically synchronized the N2 pumps and foam pump rates with the base slurry rate. The cementing crew consisted of 11 individuals, including 2 client representatives. The entire pumping operation was completed in 10 hr. A total base slurry volume of 1016.2 bbl was continuously mixed and pumped at the density of 13.35 lbm/ gal (1.60 SG). The resulting foamed slurry volume was 1387.0 bbl with an average foam quality of 27.8% and foamed slurry density of 10.5 lbm/gal (1.26 SG). A total of 119 metric tonne of class G cement and 30,711 L of N2 were consumed during the pumping operation. The lead slurry was followed by 603.9 bbl of 15.86 lbm/gal (1.90 SG) class G cement tail slurry and 349.7 bbl of seawater for displacement. The final surface pressure was 594.6 psi. The lead slurry reached the seabed and the float shoe check was positive. No casing subsidence was observed. neglected when high-hydrostatic pressure is involved. © 2023, Offshore Technology Conference.

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.

The impact of long COVID on myocardial work performance

Background: Long COVID emerged as a new condition, following the acute episode of coronavirus disease 2019 (COVID-19),exerting a significant impact on patients' quality of life [1]. Several studies involving COVID- 19 survivors emphasized the presence of cardiac abnormalities following the acute infection. However, data on possible mechanisms associated to long COVID remain limited. Clinical applications of myocardial work (MW) analysis, assessed by transthoracic echocardiography (TTE) have expended recently, showing an additional value in detecting cardiac dysfunction compared to standard parameters such as left ventricle ejection fraction (LVEF) or global longitudinal strain (GLS) in various pathologies, including COVID-19 [2]. Nevertheless, its potential role in detecting subclinical cardiac dysfunction in long COVID remained unexplored. Purpose(s): We assessed the association between subclinical cardiac dysfunction evaluated by global work index (GWI) and global constructive work (GCW) and long COVID. Method(s): We included 310 COVID-19 patients hospitalized between March and April 2020. All patients were invited to a systematic one-year follow-up, including clinical evaluation, TTE with MW assessment, chestcomputed tomography and spirometry. 140 patients completed the followup. Normal values for GWI and GCW were defined as 1926+/-247 mmHg% and 2224+/-229 mmHg% [3]. The primary endpoint was long COVID, characterized by a cluster of symptoms such as fatigue or dyspnea more than 3 months after the acute infection, without any other explanation. Result(s): 140 patients (57.1+/-13.9 years, 90 (64.3%) males) had a mean follow-up of 337.1+/-34.5 days.The mean values of LVEF, GWI and GCW were 55.2+/-3.2%, 2105.9+/-403.3 mmHg% and 2377.8+/-446.2 mmHg%. 83 (61%) patients had long COVID. No significant differences in terms of comorbidities, clinical evaluation and COVID-19 severity were found between patients with and without long COVID. GCW (2276.7+/-410.3 vs 2516.5+/-458.6, p=0.006) and GWI (2008.5+/-358.9 vs 2242.2+/-427.0, p=0.003) were the only TTE parameters different between patients with and without long COVID. Multivariable regression analysis showed that GWI <1926 mmHg% (OR 6.095;CI: 2.024-18.355, p=0.001) and GCW <2224 mmHg% (OR 3.205;CI: 1.181-8.694, p=0.022) were the only MW parameters independently associated with long COVID, irrespective of age or the severity of the acute infection, at one year. In a subgroup analysis of 77 patients without previous cardiovascular diseases, long COVID was diagnosed in 45 (58.4%)patients. GWI <1926 mmHg% (OR 8.015;CI: 2.149-29.887, p=0.002) remained independently associated with long COVID at 1 year follow-up. Conclusion(s): Long COVID, frequently observed in recovered COVID-19 patients may indicate the presence of subclinical cardiac dysfunction, reflected by a decrease of the left ventricle performance, assessed by GWI and GCW.Long-term follow-up including cardiac screening should be performed in order to identify patients at risk who would benefit from cardiac rehabilitation programs.

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

AI-Based and Digital Mental Health Apps: Balancing Need and Risk

Mental health and well-being are increasingly important topics in discussions on public health [1]. The COVID-19 pandemic further revealed critical gaps in existing mental health services as factors such as job losses and corresponding financial issues, prolonged physical illness and death, and physical isolation led to a sharp rise in mental health conditions [2]. As such, there is increasing interest in the viability and desirability of digital mental health applications. While these dedicated applications vary widely, from platforms that connect users with healthcare professionals to diagnostic tools to self-assessments, this article specifically explores the implications of digital mental health applications in the form of chatbots [3]. Chatbots can be text based or voice enabled and may be rule based (i.e., linguistics based) or based on machine learning (ML). They can utilize the power of conversational agents well-suited to task-oriented interactions, like Apple's Siri, Amazon's Alexa, or Google Assistant. But increasingly, chatbot developers are leveraging conversational artificial intelligence (AI), which is the suite of tools and techniques that allow a computer program to seemingly carry out a conversational experience with a person or a group. © 1982-2012 IEEE.

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

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.

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

CSI-Based Joint Location and Activity Monitoring for COVID-19 Quarantine Environments

The recent SARS-COV-2 virus, also known as COVID-19, badly affected the world's healthcare system due to limited medical resources for a large number of infected human beings. Quarantine helps in breaking the spread of the virus for such communicable diseases. This work proposes a nonwearable/contactless system for human location and activity recognition using ubiquitous wireless signals. The proposed method utilizes the channel state information (CSI) of the wireless signals recorded through a low-cost device for estimating the location and activity of the person under quarantine. We propose to utilize a Siamese architecture with combined one-dimensional convolutional neural networks (1-D-CNNs) and bi-directional long short-term memory (Bi-LSTM) networks. The proposed method provides high accuracy for the joint task and is validated on two real-world testbeds, first, using the designed low-cost CSI recording hardware, and second, on a public dataset for joint activity and location estimation. The human activity recognition (HAR) results outperform state-of-the-art machine and deep learning methods, and localization results are comparable with the existing methods. © 2001-2012 IEEE.

TrajSGAN: A Semantic-Guiding Adversarial Network for Urban Trajectory Generation

Simulating human mobility contributes to city behavior discovery and decision-making. Although the sequence-based and image-based approaches have made impressive achievements, they still suffer from respective deficiencies such as omitting the depiction of spatial properties or ordinal dependency in trajectory. In this article, we take advantage of the above two paradigms and propose a semantic-guiding adversarial network (TrajSGAN) for generating human trajectories. Specifically, we first devise an attention-based generator to yield trajectory locations in a sequence-to-sequence manner. The encoded historical visits are queried with semantic knowledge (e.g., travel modes and trip purposes) and their important features are enhanced by the multihead attention mechanism. Then, we designate a rollout module to complete the unfinished trajectory sequence and transform it into an image that can depict its spatial structure. Finally, a convolutional neural network (CNN)-based discriminator signifies how “real”the trajectory image looks, and its output is regarded as a reward signal to update the generator by the policy gradient. Experimental results show that the proposed TrajSGAN model significantly outperforms the benchmarks under the MTL-Trajet mobility dataset, with the divergence of spatial-related metrics such as radius of gyration and travel distance reduced by 10%–27%. Furthermore, we apply the real and synthetic trajectories, respectively, to simulate the COVID-19 epidemic spreading under three preventive actions. The coefficient of determination metric between real and synthetic results achieves 91%–98%, indicating that the synthesized data from TrajSGAN can be leveraged to study the epidemic diffusion with an acceptable difference. All of these results verify the superiority and utility of our proposed method. IEEE

Exploring the Suitability of Using Virtual Reality and Augmented Reality for Anatomy Training

Research on alternative ways to provide anatomy learning and training has increased over the past few years, especially since the COVID-19 pandemic. Virtual reality (VR) and augmented reality (AR) represent two promising alternatives in this regard. For this reason, in this work, we analyze the suitability of applying VR and AR for anatomy training, comparing an optical-based AR setup and a semi-immersive setup based on a VR table, using the same anatomy training software and the same interaction system. The AR-based setup uses a Magic Leap One, whereas the VR table is configured through the use of stereoscopic TV displays and a motion-capture system. This experiment builds on a previous one (Vergel et al., 2020) on which we have improved the AR-based setup and increased the complexity of one of the two tasks. The goal of this new experiment is to confirm whether the changes made in the setups modify the previous conclusions. Our hypothesis is that the improved AR-based setup will be more suitable, for anatomy training, than the VR-based setup. For this reason, we conducted an experimental research with 45 participants, comparing the use of an anatomy training software. Objective and subjective data were collected. The results show that the AR-based setup is the preferred choice. The differences in measurable performance were small but also favorable to the AR setup. In addition, participants provided better subjective ratings for the AR-based setup, confirming our initial hypothesis. Nevertheless, both setups offer a similar overall performance and provide excellent results in the subjective measures, with both systems approaching the highest possible values. IEEE