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

Telepresence for surgical assistance and training using eXtended reality during and after pandemic periods.

Existing challenges in surgical education (See one, do one, teach one) as well as the COVID-19 pandemic make it necessary to develop new ways for surgical training. Therefore, this work describes the implementation of a scalable remote solution called "TeleSTAR" using immersive, interactive and augmented reality elements which enhances surgical training in the operating room. The system uses a full digital surgical microscope in the context of Ear-Nose-Throat surgery. The microscope is equipped with a modular software augmented reality interface consisting an interactive annotation mode to mark anatomical landmarks using a touch device, an experimental intraoperative image-based stereo-spectral algorithm unit to measure anatomical details and highlight tissue characteristics. The new educational tool was evaluated and tested during the broadcast of three live XR-based three-dimensional cochlear implant surgeries. The system was able to scale to five different remote locations in parallel with low latency and offering a separate two-dimensional YouTube stream with a higher latency. In total more than 150 persons were trained including healthcare professionals, biomedical engineers and medical students.

Synthetic data accelerates the development of generalizable learning-based algorithms for X-ray image analysis

Artificial intelligence (AI) now enables automated interpretation of medical images. However, AI's potential use for interventional image analysis remains largely untapped. This is because the post hoc analysis of data collected during live procedures has fundamental and practical limitations, including ethical considerations, expense, scalability, data integrity and a lack of ground truth. Here we demonstrate that creating realistic simulated images from human models is a viable alternative and complement to large-scale in situ data collection. We show that training AI image analysis models on realistically synthesized data, combined with contemporary domain generalization techniques, results in machine learning models that on real data perform comparably to models trained on a precisely matched real data training set. We find that our model transfer paradigm for X-ray image analysis, which we refer to as SyntheX, can even outperform real-data-trained models due to the effectiveness of training on a larger dataset. SyntheX provides an opportunity to markedly accelerate the conception, design and evaluation of X-ray-based intelligent systems. In addition, SyntheX provides the opportunity to test novel instrumentation, design complementary surgical approaches, and envision novel techniques that improve outcomes, save time or mitigate human error, free from the ethical and practical considerations of live human data collection.Simulated data is an alternative to real data for medical applications where interventional data are needed to train AI-based systems. Gao and colleagues develop a model transfer paradigm to train deep networks on synthetic X-ray data and corresponding labels generated using simulation techniques from CT scans. The approach establishes synthetic data as a viable resource for developing machine learning models that apply to real clinical data.

Spatial Identification, Prevention and Control of Epidemics in High-Rise Residential Areas Based on Wind Environments

The wind environment in residential areas can exert a direct or indirect influence on the spread of epidemics, with some scholars paying particular attention to the epidemic prevention and control of residential areas from the perspective of wind environments. As a result, it is urgent to re-examine the epidemic prevention response of residential spaces. Taking high-rise residential areas in Xi'an as an example, the article defines the air flow field area based on on-site wind environment measurements, crowd behavior annotation, and CFD simulation. Using the double-effect superposition of crowd behavior and risk space, the paper undertook a multiple identification strategy of epidemic prevention space. The identification methods and management and control strategies of epidemic prevention in high-rise residential areas are proposed. Additionally, the living environment of residential areas is optimized, and a healthy residential space is created. The transformation from concept and calls for action to space implementation is made to provide a reference for improving the space management and control capabilities in high-rise residential areas in China. The results of this study can be used as a guideline for future residential planning and design from the perspective of preventing airborne diseases.

Using a 3D ResNet for Detecting the Presence and Severity of COVID-19 from CT Scans

Deep learning has been used to assist in the analysis of medical imaging. One use is the classification of Computed Tomography (CT) scans for detecting COVID-19 in subjects. This paper presents Cov3d, a three dimensional convolutional neural network for detecting the presence and severity of COVID-19 from chest CT scans. Trained on the COV19-CT-DB dataset with human expert annotations, it achieves a macro f1 score of 87.87 on the test set for the task of detecting the presence of COVID-19. This was the ‘runner-up' for this task in the ‘AI-enabled Medical Image Analysis Workshop and Covid-19 Diagnosis Competition' (MIA-COV19D). It achieved a macro f1 score of 46.00 for the task of classifying the severity of COVID-19 and was ranked in fourth place. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

CODA-19: Using a non-expert crowd to annotate research aspects on 10,000+ abstracts in the COVID-19 open research dataset

This paper introduces CODA-19, a human-annotated dataset that codes the Background, Purpose, Method, Finding/Contribution, and Other sections of 10,966 English s in the COVID-19 Open Research Dataset. CODA-19 was created by 248 crowd workers from Amazon Mechanical Turk within 10 days, and achieved labeling quality comparable to that of experts. Each was annotated by nine different workers, and the final labels were acquired by majority vote. The inter-annotator agreement (Cohen's kappa) between the crowd and the biomedical expert (0.741) is comparable to inter-expert agreement (0.788). CODA-19's labels have an accuracy of 82.2% when compared to the biomedical expert's labels, while the accuracy between experts was 85.0%. Reliable human annotations help scientists access and integrate the rapidly accelerating coronavirus literature, and also serve as the battery of AI/NLP research, but obtaining expert annotations can be slow. We demonstrated that a non-expert crowd can be rapidly employed at scale to join the fight against COVID-19. © ACL 2020.All right reserved.

Spanish Corpora of tweets about COVID-19 vaccination for automatic stance detection

The paper presents new annotated corpora for performing stance detection on Spanish Twitter data, most notably Health-related tweets. The objectives of this research are threefold: (1) to develop a manually annotated benchmark corpus for emotion recognition taking into account different variants of Spanish in social posts;(2) to evaluate the efficiency of semi-supervised models for extending such corpus with unlabelled posts;and (3) to describe such short text corpora via specialised topic modelling. A corpus of 2,801 tweets about COVID-19 vaccination was annotated by three native speakers to be in favour (904), against (674) or neither (1,223) with a 0.725 Fleiss' kappa score. Results show that the self-training method with SVM base estimator can alleviate annotation work while ensuring high model performance. The self-training model outperformed the other approaches and produced a corpus of 11,204 tweets with a macro averaged f1 score of 0.94. The combination of sentence-level deep learning embeddings and density-based clustering was applied to explore the contents of both corpora. Topic quality was measured in terms of the trustworthiness and the validation index. © 2023 The Author(s)

Quantification Annotation in ISO 24617-12, Second Draft

This paper describes the continuation of a project that aims at establishing an interoperable annotation scheme for quantification phenomena as part of the ISO suite of standards for semantic annotation, known as the Semantic Annotation Framework. After a break, caused by the Covid-19 pandemic, the project was relaunched in early 2022 with a second working draft, which deals with certain issues in the annotation of quantification in a more satisfactory way than the original first working draft. © European Language Resources Association (ELRA), licensed under CC-BY-NC-4.0.

Making Italian Parliamentary Records Machine-Actionable: The Construction of the ParlaMint-IT Corpus

This paper describes the process of acquisition, cleaning, interpretation, coding and linguistic annotation of a collection of parliamentary debates from the Senate of the Italian Republic covering the COVID-19 pandemic emergency period and a former period for reference and comparison according to the CLARIN ParlaMint prescriptions. The corpus contains 1199 sessions and 79,373 speeches for a total of about 31 million words, and was encoded according to the ParlaCLARIN TEI XML format. It includes extensive metadata about the speakers, sessions, political parties and parliamentary groups. As required by the ParlaMint initiative, the corpus was also linguistically annotated for sentences, tokens, POS tags, lemmas and dependency syntax according to the universal dependencies guidelines. Named entity annotation and classification is also included. All linguistic annotation was performed automatically using state-of-the-art NLP technology with no manual revision. The Italian dataset is freely available as part of the larger ParlaMint 2.1 corpus deposited and archived in CLARIN repository together with all other national corpora. It is also available for direct analysis and inspection via various CLARIN services and has already been used both for research and educational purposes. © European Language Resources Association (ELRA).

CS2 : A Controllable and Simultaneous Synthesizer of Images and Annotations with Minimal Human Intervention

The destitution of image data and corresponding expert annotations limit the training capacities of AI diagnostic models and potentially inhibit their performance. To address such a problem of data and label scarcity, generative models have been developed to augment the training datasets. Previously proposed generative models usually require manually adjusted annotations (e.g., segmentation masks) or need pre-labeling. However, studies have found that these pre-labeling based methods can induce hallucinating artifacts, which might mislead the downstream clinical tasks, while manual adjustment could be onerous and subjective. To avoid manual adjustment and pre-labeling, we propose a novel controllable and simultaneous synthesizer (dubbed CS$$

Data Models for Annotating Biomedical Scholarly Publications: the Case of CORD-19

Semantic text annotations have been a key factor for supporting computer applications ranging from knowledge graph construction to biomedical question answering. In this systematic review, we provide an analysis of the data models that have been applied to semantic annotation projects for the scholarly publications available in the CORD-19 dataset, an open database of the full texts of scholarly publications about COVID-19. Based on Google Scholar and the screening of specific research venues, we retrieve seventeen publications on the topic mostly from the United States of America. Subsequently, we outline and explain the inline semantic annotation models currently applied on the full texts of biomedical scholarly publications. Then, we discuss the data models currently used with reference to semantic annotation projects on the CORD-19 dataset to provide interesting directions for the development of semantic annotation models and projects. © 2022 ACM.

Hoaxes and Hidden agendas: A Twitter Conspiracy Theory Dataset

Hoaxes and hidden agendas make for compelling conspiracy theories. While many of these theories are ultimately innocuous, others have the potential to do real harm, instigating real-world support or disapproval of the theories. This is further fueled by social media which provides a platform for conspiracy theories to spread at unprecedented rates. Thus, there is a need for the development of automated models to detect conspiracy theories from the social media space in order to quickly and effectively identify the topics of the season and the prevailing stance. To support this development, we create ground truth data through human annotation. In this work, we collect and manually annotate a dataset from Twitter, comprising of four conspiracy theories. Each Tweet is annotated with one of the four topics {climate change, COVID-19 origin, COVID-19 vaccine, Epstein-Maxwell trial}, and its stance towards the conspiracy theory {support, neutral, against}. We perform experiments on this multi-topic dataset to demonstrate its usage in conspiracy-detection, stance-detection and topic-detection. © 2022 Owner/Author.

Annotating Protein Structures for Understanding SARS-CoV-2 Interactome

Protein Contact Network (PCN) is an emerging paradigm for modelling protein structure. A common approach to interpreting such data is through network-based analyses. It has been shown that clustering analysis may discover allostery in PCN. Nevertheless Network Embedding has shown good performances in discovering hidden communities and structures in network. SARS-CoV-2 proteins, and in particular S protein, have a modular structure that need to be annotated to understand complex mechanism of infections. Such annotations, and in particular the highlighting of regions participating in the binding of human ACE2 and TMPRSS, may help the design of tailored strategy for preventing and blocking infection. In this work, we compare some approaches for graph embedding with respect to some classical clustering approaches for annotating protein structures. Results shows that embedding may reveal interesting structure that constitute the starting point for further analysis. © 2022 CEUR-WS. All rights reserved.

TBR-NER: Research on COVID-19 Text Information Extraction Based on Joint Learning of Topic Recognition and Named Entity Recognition

There is a centralization of the core content in the text information of the new crown epidemic notification. This paper proposes a joint learning text information extraction method: TBR-NER (topic-based recognition named entity recognition) based on topic recognition and named entity recognition to predict the labeled risk areas and epidemic trajectory information in text information. Transfer learning and data augmentation are used to solve the problem of data scarcity caused by the initial local outbreak of the epidemic, and mutual understanding is achieved by topic self-labeling without introducing additional labeled data. Taking the epidemic cases in Hebei and Jilin provinces as examples, the reliability and effectiveness of the method are verified by five types of topic recognition and 15 types of entity information extraction. The experimental results show that, compared with the four existing NER methods, this method can achieve optimality faster through the mutual learning of each task at the early stage of training. The optimal accuracy in the independent test set can be improved by more than 20%, and the minimum loss value is significantly reduced. This also proves that the joint learning algorithm (TBR-NER) mentioned in this paper performs better in such tasks. The TBR-NER model has specific sociality and applicability and can help in epidemic prediction, prevention, and control.

Genome Scale Phylogenetic Analysis Differentiates SARS-CoV-2 Strains in Pakistani and Indian COVID-19 Patients with and without Travel History

The COVID-19 virus spread around the globe very rapidly during early 2020. Identification of the evolution pattern, and genome scale mutations in SARS-CoV-2 is essential to study the dynamics of this disease. The genomic sequences of thousands of SARS-CoV-2 infected patients from different countries are publicly available for sequence based in-depth analysis. In this study, the DNA sequences of SARS-CoV-2 from the COVID-19 infected patients (having or lacking a travel history) from Pakistan and India, the two highest populous neighboring countries in South Asia, have been analyzed by using computational tools of phylogenetics. These analyses revealed that the SARS-CoV-2 strain in Pakistani traveler COVID-19 patients is closely related to Iranian strains, the strain in non-traveler patients is related to the strain of Wuhan, China. Likewise, in India, the SARS-CoV-2 strains in travelers and non-travelers are closely related to Italy, Germany, and Mexico. The selected approach has also been utilized to find out the identical genomic regions and similar strains around the world. Collectively, our study suggested distinct strains and routes of viral transmission in Pakistan and India. These differences may infer partially the reason for the decline phase in viral propagation in Pakistan two months after the peak COVID-19 load, and rapid viral propagation in India making it the second worst-hit country in the world after the USA.

Annotations of Lung Abnormalities in Shenzhen Chest X-ray Dataset for Computer-Aided Screening of Pulmonary Diseases.

Developments in deep learning techniques have led to significant advances in automated abnormality detection in radiological images and paved the way for their potential use in computer-aided diagnosis (CAD) systems. However, the development of CAD systems for pulmonary tuberculosis (TB) diagnosis is hampered by the lack of training data that is of good visual and diagnostic quality, of sufficient size, variety, and, where relevant, containing fine region annotations. This study presents a collection of annotations/segmentations of pulmonary radiological manifestations that are consistent with TB in the publicly available and widely used Shenzhen chest X-ray (CXR) dataset made available by the U.S. National Library of Medicine and obtained via a research collaboration with No. 3. People's Hospital Shenzhen, China. The goal of releasing these annotations is to advance the state-of-the-art for image segmentation methods toward improving the performance of fine-grained segmentation of TB-consistent findings in digital Chest X-ray images. The annotation collection comprises the following: 1) annotation files in JSON (JavaScript Object Notation) format that indicate locations and shapes of 19 lung pattern abnormalities for 336 TB patients; 2) mask files saved in PNG format for each abnormality per TB patient; 3) a CSV (comma-separated values) file that summarizes lung abnormality types and numbers per TB patient. To the best of our knowledge, this is the first collection of pixel-level annotations of TB-consistent findings in CXRs. Dataset: https://data.lhncbc.nlm.nih.gov/public/Tuberculosis-Chest-X-ray-Datasets/Shenzhen-Hospital-CXR-Set/Annotations/index.html.

Efficient and Explainable Deep Neural Networks for Airway Symptom Detection in Support of Wearable Health Technology

Mobile health wearables are often embedded with small processors for signal acquisition and analysis. These embedded wearable systems are, however, limited with low available memory and computational power. Advances in machine learning, especially deep neural networks (DNNs), have been adopted for efficient and intelligent applications to overcome constrained computational environments. Herein, evolutionary algorithms are used to find novel DNNs that are accurate in classifying airway symptoms while allowing wearable deployment. As opposed to typical microphone‐acoustic signals, mechano‐acoustic data signals, which did not contain identifiable speech information for better privacy protection, are acquired from laboratory‐generated and publicly available datasets. The optimized DNNs had a low model file size of less than 150 kB and predicted airway symptoms of interest with 81.49% accuracy on unseen data. By performing explainable AI techniques, namely occlusion experiments and class activation maps, mel‐frequency bands up to 8,000 Hz are found as the most important feature for the classification. It is further found that DNN decisions are consistently relying on these specific features, fostering trust and transparency of the proposed DNNs. The proposed efficient and explainable DNN is expected to support edge computing on mechano‐acoustic sensing wearables for remote, long‐term monitoring of airway symptoms.

Construction of Disease-Symptom Knowledge Graph from Web-Board Documents

Featured ApplicationAuthors are encouraged to provide a concise description of the specific application or a potential application of the work. This section is not mandatory.The research aim is to construct a disease-symptom knowledge graph (DSKG) as a cause-effect knowledge graph containing disease-symptom relations as a cause-effect relation type determined from downloaded documents on medical web-board resources. Each disease-symptom relation connects a disease-name concept node (a causative-concept node) to a corresponding node having a group of correlated symptom-concept/effect-concept features as common symptom-concept/effect-concept features among some disease-name concepts. The DSKG benefits non-professionals in preliminary diagnosis through a recommender web-board. There are three main problems: how to determine symptom concepts from sentences without annotation on the documents having disease-name concepts as the documents’ topic-names;how to determine the disease-symptom relations from the documents with/without complications;and how to construct the DSKG involving high dimensional symptom-concept features after union of the correlated symptom-concept groups. Therefore, we apply a word co-occurrence pattern including medical-symptom expressions from Wikipedia including MeSH and the Lexitron Dictionary to determine the symptom concepts. The Cartesian product is applied for automatic-supervised machine learning to determine the disease-symptom relation. We propose using Principal Component Analysis for constructing the DSKG by dimensionality reduction in the symptom-concept features with minimized information loss. In contrast to previous works, the proposed approach enables the DSKG construction with precise and concise representation scores of 7.8 and 9, respectively.

In Vitro Kinase-to-Phosphosite Database (iKiP-DB) Predicts Kinase Activity in Phosphoproteomic Datasets.

Phosphoproteomics routinely quantifies changes in the levels of thousands of phosphorylation sites, but functional analysis of such data remains a major challenge. While databases like PhosphoSitePlus contain information about many phosphorylation sites, the vast majority of known sites is not assigned to any protein kinase. Assigning changes in the phosphoproteome to the activity of individual kinases therefore remains a key challenge. A recent large-scale study systematically identified in vitro substrates for most human protein kinases. Here, we reprocessed and filtered these data to generate an in vitro Kinase-to-Phosphosite database (iKiP-DB). We show that iKiP-DB can accurately predict changes in kinase activity in published phosphoproteomic data sets for both well-studied and poorly characterized kinases. We apply iKiP-DB to a newly generated phosphoproteomic analysis of SARS-CoV-2 infected human lung epithelial cells and provide evidence for coronavirus-induced changes in host cell kinase activity. In summary, we show that iKiP-DB is widely applicable to facilitate the functional analysis of phosphoproteomic data sets.

A Prototype Web Application to Support Human-Centered Audiovisual Content Authentication and Crowdsourcing

Media authentication relies on the detection of inconsistencies that may indicate malicious editing in audio and video files. Traditionally, authentication processes are performed by forensics professionals using dedicated tools. There is rich research on the automation of this procedure, but the results do not yet guarantee the feasibility of providing automated tools. In the current approach, a computer-supported toolbox is presented, providing online functionality for assisting technically inexperienced users (journalists or the public) to investigate visually the consistency of audio streams. Several algorithms based on previous research have been incorporated on the backend of the proposed system, including a novel CNN model that performs a Signal-to-Reverberation-Ratio (SRR) estimation with a mean square error of 2.9%. The user can access the web application online through a web browser. After providing an audio/video file or a YouTube link, the application returns as output a set of interactive visualizations that can allow the user to investigate the authenticity of the file. The visualizations are generated based on the outcomes of Digital Signal Processing and Machine Learning models. The files are stored in a database, along with their analysis results and annotation. Following a crowdsourcing methodology, users are allowed to contribute by annotating files from the dataset concerning their authenticity. The evaluation version of the web application is publicly available online.