Secure Convolutional Neural Network-based Internet-of-Healthcare Applications

Convolutional neural networks (CNNs) have gained popularity for Internet-of-Healthcare (IoH) applications such as medical diagnostics. However, new research shows that adversarial attacks with slight imperceptible changes can undermine deep neural network techniques in healthcare. This raises questions regarding the safety of deploying these IoH devices in clinical situations. In this paper, we review the techniques used in fighting against cyber-attacks. Then, we propose to study the robustness of some well-known CNN architectures’belonging to sequential, parallel, and residual families, such as LeNet5, MobileNetV1, VGG16, ResNet50, and InceptionV3 against fast gradient sign method (FGSM) and projected gradient descent (PGD) attacks, in the context of classification of chest radiographs (X-rays) based on the IoH application. Finally, we propose to improve the security of these CNN structures by studying standard and adversarial training. The results show that, among these models, smaller models with lower computational complexity are more secure against hostile threats than larger models that are frequently used in IoH applications. In contrast, we reveal that when these networks are learned adversarially, they can outperform standard trained networks. The experimental results demonstrate that the model performance breakpoint is represented by γ= 0.3 with a maximum loss of accuracy tolerated at 2%. Author

A New Approach for Forecasting Crude Oil Prices Based on Stochastic and Deterministic Influences of LMD Using ARIMA and LSTM Models

Crude oil is one of the non-renewable power sources and is the lifeblood of the contemporary industry. Every significant change in the price of crude oil (CO) will have an effect on how the global economy, including COVID-19, develops. This study developed a novel hybrid prediction technique that depends on local mean decomposition, Autoregressive Integrated Moving Average (ARIMA), and Long Short-term Memory (LSTM) models to increase crude oil price prediction accuracy. The original data is decomposed by local mean decomposition (LMD), and the decomposed components are reconstructed into stochastic and deterministic (SD) components by average mutual information to reduce the computation cost and enhance forecasting accuracy, predict each individual reconstructed component by ARIMA, and integrate the residuals with LSTM to capture the nonlinearity in residuals and help to find the final prediction result. The new hybrid model LMD-SD-ARIMA-LSTM has reduced the volatility and solved the issue of the overfitting problem of neural networks. The proposed hybrid technique is validated using publicly accessible data from the West Texas Intermediate (WTI), and forecast accuracy are compared using accuracy measures. The value of Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) for ARIMA, LSTM, LMD-ARIMA, LMD-SD-ARIMA, LMD-ARIMA-LSTM, LMD-SD-ARIMA-LSTM, and Naïve are 1.00, 1.539, 5.289, 0.873, 0.359, 0.106, 4.014 and 2.165, 1.832, 9.165, 1.359, 1.139, 1.124 and 3.821 respectively. From these results, it is concluded that the proposed model LMD-SD-ARIMA-LSTM has minimum values for MAE and MAPE which assured the superiority of the proposed model in One-step ahead forecasting. Moreover, forecasting performance is also compared up to five steps ahead. The findings demonstrate that the suggested approach is a helpful tool for predicting CO prices both in the short and long term. Furthermore, the current study reduces labor costs by combing the stationary and non-stationary Product Functions (PFs) into stochastic and deterministic components with improved accuracy. Meanwhile, the traditional econometric model can strengthen the prediction behavior of CO prices after decomposition and reconstruction, and the new hybrid forecasting method has better performance in medium and long-term forecasting of the CO price. Moreover, accurate predictions can provide reasonable advice for relevant departments to make correct decisions. © 2013 IEEE.

Deep Reinforcement Learning-Based Approach for Efficient and Reliable Droplet Routing on MEDA Biochips

The micro-electrode-dot-array (MEDA) architecture provides precise droplet control and real-time sensing in digital microfluidic biochips. Previous work has shown that trapped charge under microelectrodes (MCs) leads to droplets being stuck and failures in fluidic operations. A recent approach utilizes real-time sensing of MC health status, and attempts to avoid degraded electrodes during droplet routing. However, the problem with this solution is that the computational complexity is unacceptable for MEDA biochips of realistic size. Consequently, in this work, we introduce a deep reinforcement learning (DRL)-based approach to bypass degraded electrodes and enhance the reliability of routing. The DRL model utilizes the information of health sensing in real time to proactively reduce the likelihood of charge trapping and avoid using degraded MCs. Simulation results show that our approach provides effective routing strategies for COVID-19 testing protocols. We also validate our DRL-based approach using fabricated prototype biochips. Experimental results show that the developed DRL model completed the routing tasks using a fewer number of clock cycles and shorter total execution time, compared with a baseline routing method. Moreover, our DRL-based approach provides reliable routing strategies even in the presence of degraded electrodes. Our experimental results show that the proposed DRL-based routing is robust to occurrences of electrode faults, as well as increases the lifetime and usability of microfluidic biochips compared to existing strategies.

Post-Pandemic Follow-Up Audit of Security Checkpoints

This paper provides a follow-up audit of security checkpoints (or simply checkpoints) for mass transportation hubs such as airports and seaports aiming at the post-pandemic R&D adjustments. The goal of our study is to determine biometric-enabled resources of checkpoints for a counter-epidemic response. To achieve the follow-up audit goals, we embedded the checkpoint into the Emergency Management Cycle (EMC) –the core of any doctrine that challenges disaster. This embedding helps to identify the technology-societal gaps between contemporary and post-pandemic checkpoints. Our study advocates a conceptual exploration of the problem using EMC profiling and formulates new tasks for checkpoints based on the COVID-19 pandemic lessons learned. In order to increase practical value, we chose a case study of face biometrics for an experimental post-pandemic follow-up audit. Author

Improving Effectiveness of Simulation-Based Inference in the Massively Parallel Regime

Simulation-based Inference (SBI) is a widely used set of algorithms to learn the parameters of complex scientific simulation models. While primarily run on CPUs in High-Performance Compute clusters, these algorithms have been shown to scale in performance when developed to be run on massively parallel architectures such as GPUs. While parallelizing existing SBI algorithms provides us with performance gains, this might not be the most efficient way to utilize the achieved parallelism. This work proposes a new parallelism-aware adaptation of an existing SBI method, namely approximate Bayesian computation with Sequential Monte Carlo(ABC-SMC). This new adaptation is designed to utilize the parallelism not only for performance gain, but also toward qualitative benefits in the learnt parameters. The key idea is to replace the notion of a single ‘step-size’hyperparameter, which governs how the state space of parameters is explored during learning, with step-sizes sampled from a tuned Beta distribution. This allows this new ABC-SMC algorithm to more efficiently explore the state-space of the parameters being learned. We test the effectiveness of the proposed algorithm to learn parameters for an epidemiology model running on a Tesla T4 GPU. Compared to the parallelized state-of-the-art SBI algorithm, we get similar quality results in <inline-formula><tex-math notation="LaTeX">$\sim 100 \times$</tex-math></inline-formula> fewer simulations and observe <inline-formula><tex-math notation="LaTeX">$\sim 80 \times$</tex-math></inline-formula> lower run-to-run variance across 10 independent trials. IEEE

Chinese Named Entity Recognition of Epidemiological Investigation of Information on COVID-19 Based on BERT

The named entity recognition based on the epidemiological investigation of information on COVID-19 can help analyze the source and route of transmission of the epidemic to control the spread of the epidemic better. Therefore, this paper proposes a Chinese named entity recognition model BERT-BiLSTM-IDCNN-ELU-CRF (BBIEC) based on the epidemiological investigation of information on COVID-19 of the BERT pre-training model. The model first processes the unlabeled epidemiological investigation of information on COVID-19 into the character-level corpus and annotates it with artificial entities according to the BIOES character-level labeling system and then uses the BERT pre-training model to obtain the word vector with position information;then, through the bidirectional long-short term memory neural network (BiLSTM) and the improved iterated dilated convolutional neural network (IDCNN) extract global context and local features from the generated word vectors and concatenate them serially;output all possible label sequences to the conditional random field (CRF);finally pass the condition random The airport decodes and generates the entity tag sequence. The experimental results show that the model is better than other traditional models in recognizing the entity of the epidemiological investigation of information on COVID-19.

Using Epidemic Modeling, Machine Learning and Control Feedback Strategy for Policy Management of COVID-19

Coronavirus disease (COVID-19) is one of the world's most challenging pandemics, affecting people around the world to a great extent. Previous studies investigating the COVID-19 pandemic forecast have either lacked generalization and scalability or lacked surveillance data. City administrators have also often relied heavily on open-loop, belief-based decision-making, preventing them from identifying and enforcing timely policies. In this paper, we conduct mathematical and numerical analyses based on closed-loop decisions for COVID-19. Combining epidemiological theories with machine learning models gives this study a more accurate prediction of COVID-19's growth, and suggests policies to regulate it. The Susceptible, Infectious, and Recovered (SIR) model was analyzed using a machine learning model to estimate the optimal constant parameters, which are the recovery and infection rates of the coupled nonlinear differential equations that govern the epidemic model. To modulate the optimized parameters that regulate pandemic suppression and mitigation, a systematically designed feedback-based strategy was implemented. We also used pulse width modulation to modify on-off signals in order to regulate policy enforcement according to established metrics, such as infection recovery ratios. It was possible to determine what type of policy should be implemented in the country, as well as how long it should be implemented. Using datasets from John Hopkins University for six countries, India, Iran, Italy, Germany, Japan, and the United States, we show that our 30-day prediction errors are almost less than 3%. Our model proposes a threshold mechanism for policy control that divides the policy implementation into seven states, for example, if Infection Recovery Ratio (IRR) >80, we suggest a complete lockdown, vs if 10 ¡IRR ¡20, we suggest encouraging people to stay at home and organizations to work at 50% capacity. All countries which implemented a policy control strategy at an early stage were accurately predicted by our model. Furthermore, it was determined that the implementation of closed-loop strategies during a pandemic at different times effectively controlled the pandemic.

Rethinking Entrepreneurial Education: The Role of Digital Technologies to Assess Entrepreneurial Self-Efficacy and Intention of STEM Students

The COVID-19 pandemic imposed restrictions and social distancing requirements that limited face-to-face education. However, the challenge of continuing studies, albeit in an online environment, promoted the redesign of teaching models, thanks to the availability of digital technologies such as MOOCs, gamification, and digital platforms. The aim of this study is to analyze if students' entrepreneurial self-efficacy and intention can be achieved through an online designed and delivered entrepreneurial course, as in face-to-face entrepreneurial education, and whether digital technologies are helpful in pursuing this goal. Data from a sample of 210 engineering students enrolled in an online entrepreneurship course having a duration of 16 weeks revealed a positive impact of digital technologies adoption on students' self-efficacy and intention in launching a novel entrepreneurial venture. Practical implications concern insights about entrepreneurship education programs' learning strategies that need to be redesigned, with the adoption of ad hoc digital tools to support projects and business plan development. Finally, the study proposes managerial and policy implications for improving the inclusion of digital tools for enhancing University students' entrepreneurship education in the digital era.

Machine Learning Models for Predicting Financially Vigilant Low-Income Households

The COVID-19 pandemic has adversely affected households’lives in terms of social and economic factors across the world. The Malaysian government has devised a number of stimulus packages to combat the pandemic’s effects. Stimulus packages would be insufficient to alleviate household financial burdens if they did not target those most affected by lockdowns. As a result, assessing household financial vigilance in the case of crisis like the COVID-19 pandemic is crucial. This study aimed to develop machine learning models for predicting and profiling financially vigilant households. The Special Survey on the Economic Effects of Covid-19 and Individual Round 1 provided secondary data for this study. As a research methodology, a cross-industry standard process for data mining is followed. Five machine learning algorithms were used to build predictive models. Among all, Gradient Boosted Tree was identified as the best predictive model based on F-score measure. The findings showed machine learning approach can provide a robust model to predict households’financial vigilances, and this information might be used to build appropriate and effective economic stimulus packages in the future. Researchers, academics and policymakers in the field of household finance can use these recommendations to help them leverage machine learning. Author

On-Demand Ride-Hailing Service Platforms With Hired Drivers During Coronavirus (COVID-19) Outbreak: Can Blockchain Help?

During the recent COVID-19 (CoV) global outbreak, there is a sharp decline of revenue of on-demand ride-hailing (ODR) platforms because people have serious worries of infection in the shared vehicles. Blockchain, which supports cryptocurrency and creates full traceability of the service history of each car and driver, may come to rescue by allowing the platform to offer only the "safe cars" to consumers. Motivated by the real world challenges associated with the CoV outbreak for the ODR platform, we build game-theoretical models based on the M/M/n queuing system to explore if and how blockchain can help. In the basic model, the ODR platform decides the service price and special hygiene level. Comparing between the cases with and without blockchain, we find that blockchain implementation increases both the service price and hygiene level. In addition, when the consumers' inherent worry of infection is substantially large, implementing blockchain achieves all-win for the ODR platform, drivers and consumers. In the extended models, we first consider the case when the special hygiene level is determined by the drivers under a mixed-leadership game and then explore the case when customers are risk averse. The main findings about blockchain adoption remain valid in both cases. However, when the drivers take charge of the special hygiene level, both optimal decisions are lower in most cases. It is also important to make efforts to reduce consumers' feeling volatility toward service valuation for improving the value of blockchain adoption and related performances.

Nonsmooth Convex Optimization to Estimate the Covid-19 Reproduction Number Space-Time Evolution With Robustness Against Low Quality Data

Daily pandemic surveillance, often achieved through the estimation of the reproduction number, constitutes a critical challenge for national health authorities to design counter-measures. In an earlier work, we proposed to formulate the estimation of the reproduction number as an optimization problem, combining data-model fidelity and space-time regularity constraints, solved by nonsmooth convex proximal minimizations. Though promising, that first formulation significantly lacks robustness against the Covid-19 data low quality (irrelevant or missing counts, pseudo-seasonalities,...) stemming from the emergency and crisis context, which significantly impairs accurate pandemic evolution assessments. The present work aims to overcome these limitations by carefully crafting a functional permitting to estimate jointly, in a single step, the reproduction number and outliers defined to model low quality data. This functional also enforces epidemiology-driven regularity properties for the reproduction number estimates, while preserving convexity, thus permitting the design of efficient minimization algorithms, based on proximity operators that are derived analytically. The explicit convergence of the proposed algorithm is proven theoretically. Its relevance is quantified on real Covid-19 data, consisting of daily new infection counts for 200+ countries and for the 96 metropolitan France counties, publicly available at Johns Hopkins University and Santé-Publique-France. The procedure permits automated daily updates of these estimates, reported via animated and interactive maps. Open-source estimation procedures will be made publicly available. [ FROM AUTHOR] Copyright of IEEE Transactions on Signal Processing is the property of IEEE 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 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 . (Copyright applies to all s.)

DeCoP:Deep Learning for COVID-19 Prediction of Survival

The current ongoing COVID-19 pandemic caused by the SARS-CoV-2 virus, has severely affected our daily life routines and behavior patterns. According to the World Health Organization, there have been 93 million confirmed cases with more than 1.99 million confirmed death around 235 Countries, areas or territories until 15 January 2021, 11:00 GMT+11. People who are affected with COVID-19 have different symptoms from people to people. When large amounts of patients are affected with COVID-19, it is important to quickly identify the health conditions of patients based on the basic information and symptoms of patients. Then the hospital can arrange reasonable medical resources for different patients. However, existing work has a low recall of 15.7% for survival predictions based on the basic information of patients (i.e., false positive rate (FPR) with 84.3%, FPR: actually survival but predicted as died). There is much room for improvement when using machine learning-based techniques for COVID-19 prediction. In this paper, we propose DeCoP to train a classifier to predict the survival of COVID-19 patients with high recall and F1 score. DeCoP is a deep learning (DL)-based scheme of Bidirectional Long Short-Term Memory (BiLSTM) along with Fuzzy-based Information Decomposition (FID) to predict the survival of patients. First of all, we apply FID oversampling to redistribute the training data of the Open COVID-19 Data Working Group. Then, we employ BiLSTM to learn the high-level feature representations from the redistributed dataset. After that, the high-level feature vector will be used to train the prediction model. Experimental results show that our proposed scheme achieves outstanding performances. Precisely, the improvement achieves about 19% and 18% in terms of recall and F1-measure. IEEE

A Multilevel Biosensor-Based Epidemic Simulation Model for COVID-19

In order to design effective public health policies to combat the COVID-19 pandemic, local governments and organizations must be able to forecast the expected number of cases in their area. Although researchers have developed individual models for predicting COVID-19 based on sensor data without requiring a test, less research has been conducted on how to leverage those individual predictions in forecasting virus spread for determining hierarchical predictions from the community level to the state level. The multilevel adaptive and dynamic biosensor epidemic model, or m-ADBio, is designed to improve on the traditional susceptible–exposed–infectious–recovered (SEIR) model used to forecast the spread of COVID-19. In this study, the predictive performance of m-ADBio is examined at the state, county, and community levels through numerical experimentation. We find that the model improves over SEIR at all levels, but especially at the community level, where the m-ADBio model with sensor-based initial values yielded no statistically significant difference between the forecasted cases and the true observed data meaning that the model was highly accurate. Therefore, the m-ADBio model is expected to provide a more timely and accurate forecast to help policymakers optimize the pandemic management strategy.

Predicting the Epidemics Trend of COVID-19 Using Epidemiological-Based Generative Adversarial Networks

The Coronavirus disease 2019 (COVID-19) is a respiratory illness that can spread from person to person. Since the COVID-19 pandemic is spreading rapidly over the world and its outbreak has affected different people in different ways, it is significant to study or predict the evolution of its epidemic trend. However, most of the studies focused solely on either classical epidemiological models or machine learning models for COVID-19 pandemic forecasting, which either suffer from the limitation of the generalization ability and scalability or the lack of surveillance data. In this work, we propose T-SIRGAN that integrates the strengths of the epidemiological theories and deep learning models to be able to represent complex epidemic processes and model the non-linear relationship for more accurate prediction of the growth of COVID-19. T-SIRGAN first adopts the Susceptible-Infectious-Recovered (SIR) model to generate epidemiological-based simulation data, which are then fed into a generative adversarial network (GAN) as adversarial examples for data augmentation. Then, Transformers are used to predict the future trends of COVID-19 based on the generated synthetic data. Extensive experiments on real-world datasets demonstrate the superiority of our method. We also discuss the effectiveness of vaccine based on the difference between the predicted and the reported number of COVID-19 cases.

Transportation and Location Planning During Epidemics/Pandemics: Emerging Problems and Solution Approaches

The sudden changes in human mobility, the immense increase in demand for logistics and delivery systems, governmental restrictions, and uncertainty of the spread dynamics have introduced several transportation and location-related decision problems during the COVID-19 pandemic. Hence, a variety of Operations Research (OR) tools and techniques have been applied to tackle these problems for mitigating the adverse effects of the spread. In this study, we first investigate the emerging decision problematics observed during epidemics/pandemics under four research clusters as: (i) effects of epidemics on transportation, (ii) effect of mobility on pandemic spread, (iii) logistics and delivery systems, and (iv) medical waste management and wastewater-based epidemiology. Next, we explore the OR tools implemented to solve the transportation and location-related decision problems in each cluster. IEEE

Predictive Shoulder Kinematics of Rehabilitation Exercises through Immersive Virtual Reality

Objective: The adoption of telehealth rapidly accelerated due to the global COVID19 pandemic disrupting communities and in-person healthcare practices. While telehealth had initial benefits in enhancing accessibility for remote treatment, physical rehabilitation has been heavily limited due to the loss of hands-on evaluation tools. This paper presents an immersive virtual reality (iVR) pipeline for replicating physical therapy success metrics through applied machine learning of patient observation. Methods: We demonstrate a method of training gradient boosted decision-trees for kinematic estimation to replicate mobility and strength metrics with an off-the-shelf iVR system. During a two-month study, training data was collected while a group of users completed physical rehabilitation exercises in an iVR game. Utilizing this data, we trained on iVR based motion capture data and OpenSim biomechanical simulations. Results: Our final model indicates that upper-extremity kinematics from OpenSim can be accurately predicted using the HTC Vive head-mounted display system with a Mean Absolute Error less than 0.78 degrees for joint angles and less than 2.34 Nm for joint torques. Additionally, these predictions are viable for run-time estimation, with approximately a 0.74 ms rate of prediction during exercise sessions. Conclusion: These findings suggest that iVR paired with machine learning can serve as an effective medium for collecting evidence-based patient success metrics in telehealth. Significance: Our approach can help increase the accessibility of physical rehabilitation with off-the-shelf iVR head-mounted display systems by providing therapists with metrics needed for remote evaluation. Author

Advanced Muti-Mutation with Intervention Policies Pandemic Model

A pandemic is a threat to humanity with potentially millions of deaths worldwide. Epidemiological models can be used to better understand pandemic dynamics and assist policymakers in optimizing their Intervention Policies (IPs). Most existing epidemiological models assume, sometimes incorrectly, that a pandemic is caused by a single pathogen, ignoring pathogen mutations over time that result in different pathogen variants with different characteristics. In addition, the existing models do not incorporate the effect of IPs like vaccinations and lockdowns during the fitting phase. In this work, we introduce a new multi-mutation model called Suspected-Infected-Vaccinated-Recovered-reInfected (SIVRI). This model extends the SIRS model with adaptation to incorporate available knowledge related to the different pathogen mutations together with multiple IPs. In order to find the model parameters we propose a new fitting procedure that supports the complex social, epidemiological, and clinical dynamics that occur during a pandemic. We examine the suggested SIVRI model in comparison to the SIRS and XGboost models on the COVID-19 pandemic in Israel that includes four COVID-19 mutations, and the vaccination and lockdown IPs. We show that the proposed model can fit accurately to the historical data and outperform the existing models in predictions of basic reproduction number, mortality rate, and severely infected individuals rate. Author

Modeling the Impact of Social Distancing on the COVID-19 Pandemic in a Low Transmission Setting

According to the World Health Organization and the CDC, social distancing is currently one of the most effective ways to slow the transmission of COVID-19. However, most existing epidemic models do not consider the impact of social distancing on the COVID-19 pandemic. In this article, we propose a new method to deterministic modeling of the effects of social distancing on the COVID-19 pandemic in a low transmission setting. Our model dynamic is expressed by a single predictive variable that satisfies an integro-differential equation. Once the dynamic variable is calculated, the process of agents from the normal state, infection state to rehabilitation state, or death state can be explored. Besides, an important parameter is added to the model to measure the impact of social distancing on epidemic transmission. We performed qualitative and quantitative experiments on various scenarios, and the results showed that 2 m is a safe social distancing on the COVID-19 pandemic in a low transmission setting. IEEE

Duality Between Coronavirus Transmission and Air-Based Macroscopic Molecular Communication.

This contribution exploits the duality between a viral infection process and macroscopic air-based molecular communication. Airborne aerosol and droplet transmission through human respiratory processes is modeled as an instance of a multiuser molecular communication scenario employing respiratory-event-driven molecular variable-concentration shift keying. Modeling is aided by experiments that are motivated by a macroscopic air-based molecular communication testbed. In artificially induced coughs, a saturated aqueous solution containing a fluorescent dye mixed with saliva is released by an adult test person. The emitted particles are made visible by means of optical detection exploiting the fluorescent dye. The number of particles recorded is significantly higher in test series without mouth and nose protection than in those with a well-fitting medical mask. A simulation tool for macroscopic molecular communication processes is extended and used for estimating the transmission of infectious aerosols in different environments. Towards this goal, parameters obtained through self experiments are taken. The work is inspired by the recent outbreak of the coronavirus pandemic.