LSTM-based Forecasting using Policy Stringency and Time-varying Parameters of the SIR Model for COVID-19

Accurate forecasting of the number of infections is an important task that can allow health care decision makers to allocate medical resources efficiently during a pandemic. Two approaches have been combined, a stochastic model by Vega et al. for modelling infectious disease and Long Short-Term Memory using COVID-19 data and government's policies. In the proposed model, LSTM functions as a nonlinear adaptive filter to modify the outputs of the SIR model for more accurate forecasts one to four weeks in the future. Our model outperforms most models among the CDC models using the United States data. We also applied the model on the Canadian data from two provinces, Saskatchewan and Ontario where it performs with a low mean absolute percentage error. © 2023 IEEE.

UNet Deep Learning Architecture for Segmentation of Vascular and Non-Vascular Images: A Microscopic Look at UNet Components Buffered With Pruning, Explainable Artificial Intelligence, and Bias

Biomedical image segmentation (BIS) task is challenging due to the variations in organ types, position, shape, size, scale, orientation, and image contrast. Conventional methods lack accurate and automated designs. Artificial intelligence (AI)-based UNet has recently dominated BIS. This is the first review of its kind that microscopically addressed UNet types by complexity, stratification of UNet by its components, addressing UNet in vascular vs. non-vascular framework, the key to segmentation challenge vs. UNet-based architecture, and finally interfacing the three facets of AI, the pruning, the explainable AI (XAI), and the AI-bias. PRISMA was used to select 267 UNet-based studies. Five classes were identified and labeled as conventional UNet, superior UNet, attention-channel UNet, hybrid UNet, and ensemble UNet. We discovered 81 variations of UNet by considering six kinds of components, namely encoder, decoder, skip connection, bridge network, loss function, and their combination. Vascular vs. non-vascular UNet architecture was compared. AP(ai)Bias 2.0-UNet was identified in these UNet classes based on (i) attributes of UNet architecture and its performance, (ii) explainable AI (XAI), and, (iii) pruning (compression). Five bias methods such as (i) ranking, (ii) radial, (iii) regional area, (iv) PROBAST, and (v) ROBINS-I were applied and compared using a Venn diagram. Vascular and non-vascular UNet systems dominated with sUNet classes with attention. Most of the studies suffered from a low interest in XAI and pruning strategies. None of the UNet models qualified to be bias-free. There is a need to move from paper-to-practice paradigms for clinical evaluation and settings.

Evaluation of AI Techniques for Detecting Deceptive Reviews in Cyberspace: A Study of Pre- and Post-COVID-19 Trends

With cyberspace's continuous evolution, online reviews play a crucial role in determining business success in various sectors, ranging from restaurants and hotels to e-commerce applications. Typically, a favorable review for a specific product draws in more consumers and results in a significant boost in sales. Unfortunately, a few businesses are using deceptive methods to improve their online reputation by using fake reviews of competitors. As a result, detecting fake reviews has become a difficult and ever-changing research field. Verbal characteristics extracted from review text, as well as nonverbal features such as the reviewer's engagement metrics, the IP address of the device, and so on, play an important role in detecting fake reviews. This article examines and compares various machine learning techniques for detecting deceptive reviews on various online platforms such as e-commerce websites such as Amazon and online review websites such as Yelp, among others. © 2023 IEEE.

ACL 2022 - 60th Annual Meeting of the Association for Computational Linguistics, Proceedings of System Demonstrations

The proceedings contain 27 papers. The topics discussed include: UKP-SQUARE: an online platform for question answering research;ViLMedic: a framework for research at the intersection of vision and language in medical AI;TextPruner: a model pruning toolkit for pre-trained language models;AnnIE: an annotation platform for constructing complete open information extraction benchmark;AdapterHub playground: simple and flexible few-shot learning with adapters;QiuNiu: a Chinese lyrics generation system with passage-level input;automatic gloss dictionary for sign language learners;PromptSource: an integrated development environment and repository for natural language prompts;COVID-19 claim radar: a structured claim extraction and tracking system;TS-Anno: an annotation tool to build, annotate and evaluate text simplification corpora;and CogKGE: a knowledge graph embedding toolkit and benchmark for representing multi-source and heterogeneous knowledge.

Deep learning-based important weights-only transfer learning approach for COVID-19 CT-scan classification.

COVID-19 has become a pandemic for the entire world, and it has significantly affected the world economy. The importance of early detection and treatment of the infection cannot be overstated. The traditional diagnosis techniques take more time in detecting the infection. Although, numerous deep learning-based automated solutions have recently been developed in this regard, nevertheless, the limitation of computational and battery power in resource-constrained devices makes it difficult to deploy trained models for real-time inference. In this paper, to detect the presence of COVID-19 in CT-scan images, an important weights-only transfer learning method has been proposed for devices with limited runt-time resources. In the proposed method, the pre-trained models are made point-of-care devices friendly by pruning less important weight parameters of the model. The experiments were performed on two popular VGG16 and ResNet34 models and the empirical results showed that pruned ResNet34 model achieved 95.47% accuracy, 0.9216 sensitivity, 0.9567 F-score, and 0.9942 specificity with 41.96% fewer FLOPs and 20.64% fewer weight parameters on the SARS-CoV-2 CT-scan dataset. The results of our experiments showed that the proposed method significantly reduces the run-time resource requirements of the computationally intensive models and makes them ready to be utilized on the point-of-care devices.

SARS-CoV-2 Spike protein induces TLR4-mediated long-term cognitive dysfunction recapitulating post-COVID-19 syndrome in mice.

Cognitive dysfunction is often reported in patients with post-coronavirus disease 2019 (COVID-19) syndrome, but its underlying mechanisms are not completely understood. Evidence suggests that severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2) Spike protein or its fragments are released from cells during infection, reaching different tissues, including the CNS, irrespective of the presence of the viral RNA. Here, we demonstrate that brain infusion of Spike protein in mice has a late impact on cognitive function, recapitulating post-COVID-19 syndrome. We also show that neuroinflammation and hippocampal microgliosis mediate Spike-induced memory dysfunction via complement-dependent engulfment of synapses. Genetic or pharmacological blockage of Toll-like receptor 4 (TLR4) signaling protects animals against synapse elimination and memory dysfunction induced by Spike brain infusion. Accordingly, in a cohort of 86 patients who recovered from mild COVID-19, the genotype GG TLR4-2604G>A (rs10759931) is associated with poor cognitive outcome. These results identify TLR4 as a key target to investigate the long-term cognitive dysfunction after COVID-19 infection in humans and rodents.

A lightweight network for COVID-19 detection in X-ray images.

The Novel Coronavirus 2019 (COVID-19) is a global pandemic which has a devastating impact. Due to its quick transmission, a prominent challenge in confronting this pandemic is the rapid diagnosis. Currently, the commonly-used diagnosis is the specific molecular tests aided with the medical imaging modalities such as chest X-ray (CXR). However, with the large demand, the diagnoses of CXR are time-consuming and laborious. Deep learning is promising for automatically diagnosing COVID-19 to ease the burden on medical systems. At present, the most applied neural networks are large, which hardly satisfy the rapid yet inexpensive requirements of COVID-19 detection. To reduce huge computation and memory demands, in this paper, we focus on implementing lightweight networks for COVID-19 detection in CXR. Concretely, we first augment data based on clinical visual features of CXR from expertise. Then, according to the fact that all the input data are CXR, we design a targeted four-layer network with either 11×11 or 3×3 kernels to recognize regional features and detail features. A pruning criterion based on the weights importance is also proposed to further prune the network. Experiments on a public COVID-19 dataset validate the effectiveness and efficiency of the proposed method.

YOLO-Based Face Mask Detection on Low-End Devices Using Pruning and Quantization

Deploying Deep Learning (DL) based object detection (OD) models in low-end devices, such as single board computers, may lead to poor performance in terms of frames-per-second (FPS). Pruning and quantization are well-known compression techniques that can potentially lead to a reduction of the computational burden of a DL model, with a possible decrease of performance in terms of detection accuracy. Motivated by the widespread introduction of face mask mandates by many institutions during the Covid-19 pandemic, we aim at training and compressing an OD model based on YOLOv4 to recognize the presence of face masks, to be deployed on a Raspberry Pi 4. We investigate the capability of different kinds of pruning and quantization techniques of increasing the FPS with respect to the uncompressed model, while retaining the detection accuracy. We quantitatively assess the pruned and quantized models in terms of Mean Average Precision (mAP) and FPS, and show that with proper pruning and quantization, the FPS can be doubled with a moderate loss in mAP. The results provide guidelines for compression of other OD models based on YOLO. © 2022 Croatian Society MIPRO.

Topology optimization search of deep convolution neural networks for CT and X-ray image classification.

Covid-19 is a disease that can lead to pneumonia, respiratory syndrome, septic shock, multiple organ failure, and death. This pandemic is viewed as a critical component of the fight against an enormous threat to the human population. Deep convolutional neural networks have recently proved their ability to perform well in classification and dimension reduction tasks. Selecting hyper-parameters is critical for these networks. This is because the search space expands exponentially in size as the number of layers increases. All existing approaches utilize a pre-trained or designed architecture as an input. None of them takes design and pruning into account throughout the process. In fact, there exists a convolutional topology for any architecture, and each block of a CNN corresponds to an optimization problem with a large search space. However, there are no guidelines for designing a specific architecture for a specific purpose; thus, such design is highly subjective and heavily reliant on data scientists' knowledge and expertise. Motivated by this observation, we propose a topology optimization method for designing a convolutional neural network capable of classifying radiography images and detecting probable chest anomalies and infections, including COVID-19. Our method has been validated in a number of comparative studies against relevant state-of-the-art architectures.

Eight pruning deep learning models for low storage and high-speed COVID-19 computed tomography lung segmentation and heatmap-based lesion localization: A multicenter study using COVLIAS 2.0.

BACKGROUND: COVLIAS 1.0: an automated lung segmentation was designed for COVID-19 diagnosis. It has issues related to storage space and speed. This study shows that COVLIAS 2.0 uses pruned AI (PAI) networks for improving both storage and speed, wiliest high performance on lung segmentation and lesion localization. METHOD: ology: The proposed study uses multicenter ∼9,000 CT slices from two different nations, namely, CroMed from Croatia (80 patients, experimental data), and NovMed from Italy (72 patients, validation data). We hypothesize that by using pruning and evolutionary optimization algorithms, the size of the AI models can be reduced significantly, ensuring optimal performance. Eight different pruning techniques (i) differential evolution (DE), (ii) genetic algorithm (GA), (iii) particle swarm optimization algorithm (PSO), and (iv) whale optimization algorithm (WO) in two deep learning frameworks (i) Fully connected network (FCN) and (ii) SegNet were designed. COVLIAS 2.0 was validated using "Unseen NovMed" and benchmarked against MedSeg. Statistical tests for stability and reliability were also conducted. RESULTS: Pruning algorithms (i) FCN-DE, (ii) FCN-GA, (iii) FCN-PSO, and (iv) FCN-WO showed improvement in storage by 92.4%, 95.3%, 98.7%, and 99.8% respectively when compared against solo FCN, and (v) SegNet-DE, (vi) SegNet-GA, (vii) SegNet-PSO, and (viii) SegNet-WO showed improvement by 97.1%, 97.9%, 98.8%, and 99.2% respectively when compared against solo SegNet. AUC > 0.94 (p < 0.0001) on CroMed and > 0.86 (p < 0.0001) on NovMed data set for all eight EA model. PAI <0.25 s per image. DenseNet-121-based Grad-CAM heatmaps showed validation on glass ground opacity lesions. CONCLUSIONS: Eight PAI networks that were successfully validated are five times faster, storage efficient, and could be used in clinical settings.

Regression Based Machine Learning to Generate and Validate a Metric for Food Insecurity

With the increased cost of living, exacerbated by COVID-19, thousands in New Jersey lack secure access to nutritious food. Given the importance of the issue, this research aims to produce an accurate metric using accessible data to quantify food insecurity. 16 potential explanatory variables, such as median household income and homeless population, were chosen as their values were defined across all NJ counties from 2015-2019. Using multiple linear regression, 14 unique metrics were created after four different variable pruning methods. The leading metric, with an adj. R2 value of 0.932, demonstrates the correlation between food insecurity, population, median household income, total population with health insurance, and population with private health insurance. The implementation of this metric could serve as a tool in predicting areas of food insecurity, highlighting affiliated factors, and revealing connections between racial populations. © 2021 IEEE.

Pruning digital contact networks for meso-scale epidemic surveillance using foursquare data

With the recent advances in human sensing, the push to integrate human mobility tracking with epidemic modeling highlights the lack of groundwork at the mesoscale (e.g., city-level) for both contact tracing and transmission dynamics. Although GPS data has been used to study city-level outbreaks in the past, existing approaches fail to capture the path of infection at the individual level. Consequently, in this paper, we extend epidemics prediction from estimating the size of an outbreak at the population level to estimating the individuals who may likely get infected within a finite period of time. To this end, we propose a network science based method to first build and then prune the dynamic contact networks for recurring interactions;these networks can serve as the backbone topology for mechanistic epidemics modeling. We test our method using Foursquare's Points of Interest (POI) smart phone geolocation data from over 1.3 million devices to better approximate the COVID-19 infection curves for two major (yet very different) US cities, (i.e., Austin and New York City), while maintaining the granularity of individual transmissions and reducing model uncertainty. Our method provides a foundation for building a disease prediction framework at the mesoscale that can help both policy makers and individuals better understand their estimated state of health and help the pandemic mitigation efforts. © 2021 ACM.

Attention and Emotional States during Horticultural Activities of Adults in 20s Using Electroencephalography: A Pilot Study

Since indoor, sedentary lifestyles became prevalent in society, humans have lost a sustainable connection to nature. An intervention utilizing outdoor horticultural activities could address such a challenge, but their beneficial effects on the brain and emotions have not been characterized in a quantitative approach. We aimed to investigate brain activity and emotional changes in adults in their 20s during horticultural activity to confirm feasibility of horticultural activity to improve cognitive and emotional states. Sixty university students participated in 11 outdoor horticultural activities at 2-min intervals. We measured brain waves of participants’ prefrontal cortex using a wireless electroencephalography device while performing horticultural activities. Between activities, we evaluated emotional states of participants using questionnaires. Results showed that each horticultural activity showed promotion of brain activity and emotional changes at varying degrees. The participants during physically intensive horticultural activities—digging, raking, and pruning—showed the highest attention level. For emotional states, the participants showed the highest fatigue, tension, and vigor during digging and raking. Plant-based activities—harvesting and transplanting plants—made participants feel natural and relaxed the most. Therefore, this pilot study confirmed the possibility of horticultural activity as a short-term physical intervention to improve attention levels and emotional stability in adults.

Iteratively Pruned Deep Learning Ensembles for COVID-19 Detection in Chest X-rays.

We demonstrate use of iteratively pruned deep learning model ensembles for detecting pulmonary manifestation of COVID-19 with chest X-rays. This disease is caused by the novel Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2) virus, also known as the novel Coronavirus (2019-nCoV). A custom convolutional neural network and a selection of ImageNet pretrained models are trained and evaluated at patient-level on publicly available CXR collections to learn modality-specific feature representations. The learned knowledge is transferred and fine-tuned to improve performance and generalization in the related task of classifying CXRs as normal, showing bacterial pneumonia, or COVID-19-viral abnormalities. The best performing models are iteratively pruned to reduce complexity and improve memory efficiency. The predictions of the best-performing pruned models are combined through different ensemble strategies to improve classification performance. Empirical evaluations demonstrate that the weighted average of the best-performing pruned models significantly improves performance resulting in an accuracy of 99.01% and area under the curve of 0.9972 in detecting COVID-19 findings on CXRs. The combined use of modality-specific knowledge transfer, iterative model pruning, and ensemble learning resulted in improved predictions. We expect that this model can be quickly adopted for COVID-19 screening using chest radiographs.