Enhance-Net: An Approach to Boost the Performance of Deep Learning Model Based on Real-Time Medical Images

Real-time medical image classification is a complex problem in the world. Using IoT technology in medical applications assures that the healthcare sectors improve the quality of treatment while lowering costs via automation and resource optimization. Deep learning is critical in categorizing medical images, which is accomplished by artificial intelligence. Deep learning algorithms allow radiologists and orthopaedic surgeons to make their life easier by providing them with quicker and more accurate findings in real time. Despite this, the classic deep learning technique has hit its performance limits. For these reasons, in this research, we examine alternative enhancement strategies to raise the performance of deep neural networks to provide an optimal solution known as Enhance-Net. It is possible to classify the experiment into six distinct stages. Champion-Net was chosen as a deep learning model from a pool of benchmark deep learning models (EfficientNet: B0, MobileNet, ResNet-18, and VGG-19). This stage helps choose the optimal model. In the second step, Champion-Net was tested with various resolutions. This stage helps conclude dataset resolution and improves Champion-Net performance. The next stage extracts green channel data. In the fourth step, Champion-Net combines with image enhancement algorithms CLAHE, HEF, and UM. This phase serves to improve Enhance-performance. The next stage compares the Enhance-Net findings to the lightness order error (LoE). In Enhance-Net models, the current study combines image enhancement and green channel with Champion-Net. In the final step, radiologists and orthopaedic surgeons use the trained model for real-time medical image prediction. The study effort uses the musculoskeletal radiograph-bone classification (MURA-BC) dataset. Classification accuracy of Enhance-Net was determined for the train and test datasets. These models obtained 98.02 percent, 94.79 percent, and 94.61 percent accuracy, respectively. The 96.74% accuracy was achieved during real-time testing with the unseen dataset.

The impact of governmental COVID‐19 measures on manufacturers' stock market valuations: The role of labor intensity and operational slack

This study investigates the impact of the Chinese government's Level I emergency response policy on manufacturers' stock market values. We empirically examine the roles of human resource dependence (labor intensity) and operational slack within the context of supply chain resilience. Through an event study of 1357 Chinese manufacturing companies, we find that the government's emergency response policy triggered statistically significant positive abnormal returns for manufacturers. However, we also find that there exists a negative impact on abnormal returns for manufacturers that are labor‐intensive, giving rise to arguments based in resource dependence theory. In addition, the results indicate the positive role played by operational slack (e.g., financial and inventory slack) in helping manufacturers maintain operations and business continuity, effectively mitigating risks and adding to the manufacturers' resilience. With these findings, we contribute to operations and supply chain management by calling attention to the importance of human resource redundancy while at the same time identifying financial slack and inventory as supply chain resilience strategies that were able to mitigate pandemic‐related risks.

Outdoor Localization for a Mobile Robot under Different Weather Conditions Using a Deep Learning Algorithm

A fundamental issue in robotics is the precise localization of mobile robots in uncertain environments. Due to changing environmental patterns and lighting, localization under difficult perceptual conditions remains problematic. This paper presents an approach for locating an outdoor mobile robot using deep learning algorithms merge with 3D Light Detection and Ranging LiDAR data and RGB-D image. This approach is divided into three levels. The first is the training level, which involves scanning the localization area with a 3D LiDAR sensor and then converting the data into a 2.5D image based on the Principal Component Analysis. The testing is the second level in the Intensity Hue Saturation process. Then, the RGB and Depth images are combined to create a 2.5D fusion image. These datasets are trained and tested using Convolution Neural Networks. The K-Nearest Neighbor algorithm is used in the third level is the classification. The results show that the proposed approach is better in terms of accuracy of 97.46% and the Mean error distance is 0.6 meters.

Strengthening supply chain resilience during COVID‐19: A case study of JD.com

The coronavirus/SARS‐CoV‐2 (COVID‐19) outbreak has caused severe supply chain disruptions in practically all industries worldwide. Online e‐commerce platforms, which interact directly with various industries and service numerous consumers, have become remarkable interfaces to observe the impacts of the pandemic on supply chains. Using quantitative operational data obtained from JD.com https://www.jd.com., this study analyzes the impact of the pandemic on supply chain resilience, summarizes the challenging scenarios that retailing supply chains experienced in China, and presents the practical response of JD.com throughout the pandemic. To summarize, the pandemic caused exceptional demand and severe logistical disruptions in China, and JD.com has handled well its supply chain management in response based on its integrated supply chain structure and comprehensive intelligent platforms. In particular, the existing intelligent platforms and the delivery procedures were modified slightly but promptly to deal with specific disruptions. Moreover, the entire market scenario in China was effectively controlled through the joint efforts of multiple firms, the government, and the entire Chinese society. Our study provides an example of using practical operational indicators to analyze supply chain resilience, and suggests firms pay attention to operational flexibility and collaboration beyond supply chains to deal with a large‐scale supply chain disruption, such as the COVID‐19 outbreak.

Developing supply chain resilience through integration: An empirical study on an e‐commerce platform

The outbreak of the COVID‐19 pandemic has disrupted supply chains and increased the uncertainties faced by firms. While firms are struggling to survive and recover from the pandemic, Chinese e‐commerce platforms have demonstrated resilient supply chains. We develop a framework that investigates the impacts of integration between an e‐commerce platform and suppliers on supply chain resilience and the moderating effect of the suppliers' product flexibility. An analysis of data from a Chinese e‐commerce platform using operational indicators finds that integration between the e‐commerce platform and suppliers in terms of information sharing, joint planning and logistics cooperation has positive impacts on supply chain resilience, while procurement automation has the opposite effect. Furthermore, product flexibility positively moderates the impacts of information sharing, joint planning and logistics cooperation. The results enhance current understandings of the factors that contribute to the development of supply chain resilience and reveal that the relationship between integration and resilience should be examined within a contingency framework. The findings also provide guidelines for managers taking measures to mitigate the negative influences of supply chain disruptions.

Realizing supply chain agility under time pressure: Ad hoc supply chains during the COVID‐19 pandemic

When the COVID‐19 pandemic began in 2020, the medical product industry faced an unusual demand shock for personal protective equipment (PPE), including face masks, face shields, disinfectants, and gowns. Companies from various industries responded to the urgent need for these potentially life‐saving products by adopting ad hoc supply chains in an exceptionally short time: They found new suppliers, developed the products, ramped‐up production, and distributed to new customers within weeks or even days. We define these supply chains as ad hoc supply chains that are built for a specific need, an immediate need, and a time‐limited need. By leveraging a unique sampling, we examined how companies realize supply chain agility when building ad hoc supply chains. We develop an emergent theoretical model that proposes dynamic capabilities to enable companies building ad hoc supply chains in response to a specific need, moderated by an entrepreneurial orientation allowing firms to leverage dynamic capabilities at short notice and a temporary orientation that increases a company's focus on exploiting the short‐term opportunity of ad hoc supply chains.

Breaking out of the pandemic: How can firms match internal competence with external resources to shape operational resilience?

This study explores how firms sought to effectively match their internal competence with external resources from the supply chain network to improve operational resilience (OR) during the COVID‐19 pandemic. Drawing upon matching theory, this study provides an internal–external matching perspective based on flexibility–stability features of OR to explain the operational mechanisms underlying the different matchings between internal flexibility (i.e., product diversity)/stability (i.e., operational efficiency) and external flexibility (i.e., structural holes)/stability (i.e., network centrality). We find that more heterogeneous matchings between internal (external) flexibility and external (internal) stability have a complementary effect that enhances OR, whereas more homogeneous matchings between internal flexibility (or stability) and external flexibility (or stability) have a substitutive effect that reduces OR. This study provides valuable contributions to research focusing on the supply chain, organizational resilience, and operations management.

Working from home and firm resilience to the COVID‐19 pandemic

The COVID‐19 pandemic has disrupted firms' operations. To cope with the crisis, many firms have allowed their employees to work from home (WFH). We examine whether a firm's WFH capacity has increased its resilience during the pandemic. We test the hypotheses using a unique data set that combines listed firms' financial statements, supply chain partners, and job postings on a leading online platform that provides hiring services. We find that imposing COVID‐19 anti‐contagion policies on firms and their suppliers or customers significantly increases their operating revenue volatility, slows their recovery, and has repercussions on their supply chains. WFH enhances firms' resistance capacity by reducing the effect of COVID‐19 on their operating revenue volatility and disruptions to their supply chain partners;however, it also decreases their recovery capacity by extending the time taken to return to normal. Firm attributes, along with workers' occupations, education, and experience, have an impact on the effect of WFH on firm resilience. This study enhances our understanding of shock transmission across supply chains and WFH as a source of firm resilience.

Adversarial Machine Learning Protection Using the Example of Evasion Attacks on Medical Images

This work considers evasion attacks on machine learning (ML) systems that use medical images in their analysis. Their systematization and a practical assessment of feasibility are carried out. Existing protection techniques against ML evasion attacks are presented and analyzed. The features of medical images are given and the formulation of the problem of evasion attack protection for these images based on several protective methods is provided. The authors have identified, implemented, and tested the most relevant protection methods on practical examples: an analysis of images of patients with COVID-19.

Conceptual design and simulation study of an autonomous indoor medical waste collection robot

Solid waste management is one of the critical challenges seen everywhere, and the coronavirus disease (COVID-19) pandemic has only worsened the problems in the safe disposal of infectious waste. This paper outlines a design for a mobile robot that will intelligently identify, grasp, and collect a group of medical waste items using a six-degree of freedom (DoF) arm, You Only Look Once (YOLO) neural network, and a grasping algorithm. Various designs are generated before running simulations on the selected virtual model using Robot Operating System (ROS) and Gazebo simulator. A lidar sensor is also used to map the robot's surroundings and navigate autonomously. The robot has good scope for waste collection in medical facilities, where it can help create a safer environment.

The use and significance of machine learning to screen COVID-19

Coronavirus disease 2019 (COVID-19) virus was first seen in 2019 December in China and rapidly spread all over the world and millions of people are infected with this virus. This disease has sited the entire world in dangerous circumstances. At the start of this virus, it was a very serious matter in China but now it is being observed all over the world. The virus is life-threatening, and other public who are affected by previous diseases or those people whose age is more than 60 are more affected by this virus. The healthcare and drug industries have tried to find a treatment. While machine learning algorithms are largely applied in other areas, at this time every health care unit has to want to use machine learning techniques to find, predict, track, and screen the spread of COVID-19, and try to find the treatment of it. we show what is the journey of machine learning to find and track COVID-19 and also observing it from a screening and detecting the COVID-19. We show how much research has been done yet to detection of COVID-19 and which algorithm of machine learning is best for the detection and screening of the COVID-19.

Conceptual design and simulation study of an autonomous indoor medical waste collection robot

Solid waste management is one of the critical challenges seen everywhere, and the coronavirus disease (COVID-19) pandemic has only worsened the problems in the safe disposal of infectious waste. This paper outlines a design for a mobile robot that will intelligently identify, grasp, and collect a group of medical waste items using a six-degree of freedom (DoF) arm, You Only Look Once (YOLO) neural network, and a grasping algorithm. Various designs are generated before running simulations on the selected virtual model using Robot Operating System (ROS) and Gazebo simulator. A lidar sensor is also used to map the robot's surroundings and navigate autonomously. The robot has good scope for waste collection in medical facilities, where it can help create a safer environment.

Mathematical modelling for prediction of spread of corona virus and artificial intelligence/machine learning-based technique to detect COVID-19 via smartphone sensors

COVID-19 is a novel corona virus which is infectious and communicable disease and it is originated from Wuhan, China. As the virus is mutating, the world is suffering from its spread again and again. However, the spread of communicable diseases can be predicted in advance so the proper preventive measures can be taken before it become life-taking. In this paper, mathematical model (SEIR) for the prediction of infectious diseases, which is modification of conventional SIR model is described and modelled which can be used to predict the cases in advance. A novel framework to detect COVID-19 from home is also proposed using artificial intelligence, machine learning and smartphone embedded sensors. The various smartphone embedded sensors such as proximity sensor, light sensor, accelerometer, gyroscope and fingerprint sensors are used to read the symptoms or activity and scan the CT images, and can be used to detect COVID-19.

Formal Modeling of IoT-Based Drone Network for Combating COVID-19 Pandemic

Coronavirus biologically named COVID-19 is a disease that is circulating throughout the world due to its viral nature. The interaction of people is a source of spreading of coronavirus. Millions of people have been affected by this virus, and most of them have lost their lives. At present, this viral disease has grown into a worldwide pandemic which is a troubling spot for the whole world. Few technologies are supporting to manage and solve the COVID-19 crisis. In this paper, unified modeling language (UML) will be used to describe requirements and behavior of the proposed system. Unmanned aerial vehicle (UAV) drones are flying mechanical devices without any human pilot that is efficient to reduce the spreading rate of COVID-19. In the proposed IoT-based model, a cluster-based drones’ network will be used to monitor and perform required actions to tackle the violations of standard operating procedures (SOPs). The drones will gather all data through embedded cameras and sensors and will communicate with the control room to operate the actions as required. In this model, a well-maintained and collision-free network of drones will be designed using graph theory. Drones’ network will observe the violation of SOPs in the targeted area and make decisions such as produce alarm sound to alert persons and through communications by sending people warning messages on their smartphones. Further, the persons having COVID symptoms such as high temperature and unbalance respiratory rates will be identified using wearable sensors that are deployed to the targeted area and will send information to the control room to perform required actions. Drones will be able to provide medical kits to the patients’ residences that are identified using wearable sensors to reduce interaction of people. The model will be specified using Vienna Development Method-Specification language (VDM-SL) and validated through the VDM-SL toolbox.

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.

Effective Preprocessing and Normalization Techniques for COVID-19 Twitter Streams with POS Tagging via Lightweight Hidden Markov Model

The major focus of this research work is to refine the basic preprocessing steps for the unstructured text content and retrieve the potential conceptual features for further enhancement processes such as semantic enrichment and named entity recognition. Although some of the preprocessing techniques such as text tokenization, normalization, and Part-of-Speech (POS) tagging work exceedingly well on formal text, it has not performed well when it is applied into informal text such as tweets and short messages. Hence, we have given the enhanced text normalization techniques to reduce the complexity persist over the twitter streams and eliminate the overfitting issues such as text anomalies and irregular boundaries while fixing the grammar of the text. The hidden Markov model (HMM) has been pervasively used to extract the core lexical features from the Twitter dataset and suitably adapt the external documents to supplement the extraction techniques to complement the tweet context. Using this Markov process, the POS tags are identified as states of the Markov process, and words are the desired results of the model. As this process is very crucial for the next stage of entity extraction and classification, the effective handling of informal text is considered to be important and therefore proposed the most effective hybrid approach to deal with the issues appropriately.

Prospective RFID Sensors for the IoT Healthcare System

The outbreak of COVID-19 has attracted people’s attention to our healthcare system, stimulating the advancement of next-generation health monitoring technologies. IoT attracts extensive attention in this advancement for its advantage in ubiquitous communication and sensing. RFID plays a key role in IoT to tackle the challenges in passive communication and identification and is now emerging as a sensing technology which has the ability to reduce the cost and complexity of data collection. It is advantageous to introduce RFID sensor technologies in health-related sensing and monitoring, as there are many sensors used in health monitoring systems with the potential to be integrated with RFID for smart sensing and monitoring. But due to the unique characteristics of the human body, there are challenges in developing effective RFID sensors for human health monitoring in terms of communication and sensing. For example, in a typical IoT health monitoring application, the main challenges are as follows: (1) energy issues, the efficiency of RF front-end energy harvesting and power conversion is measured;(2) communication issues, the basic technology of RFID sensors shows great heterogeneity in terms of antennas, integrated circuit functions, sensing elements, and data protocols;and (3) performance stability and sensitivity issues, the RFID sensors are mainly attached to the object to be measured to carry out identification and parameter sensing. However, in practical applications, these can also be affected by certain environmental factors. This paper presents the recent advancement in RFID sensor technologies and the challenges for the IoT healthcare system. The current sensors used in health monitoring are also reviewed with regard to integrating possibility with RFID and IoT. The future research direction is pointed out for the emergence of the next-generation healthcare and monitoring system.

Conv-Wake: A Lightweight Framework for Aircraft Wake Recognition

The recognition of aircraft wake vortex can provide an indicator of early warning for civil aviation transportation safety. In this paper, several wake vortex recognition models based on deep learning and traditional machine learning were presented. Nonetheless, these models are not completely suitable owing to their dependence on the visualization of LiDAR data that yields the information loss of in reconstructing the behavior patterns of wake vortex. To tackle this problem, we proposed a lightweight deep learning framework to recognize aircraft wake vortex in the wind field of Shenzhen Baoan Airport’s arrival and departure routes. The nature of the introduced model is geared towards three aspects. First, the dilation patch embedding module is used as the input representation of the framework, attaining additional rich semantics information over long distances while maintaining parameters. Second, we combined a separable convolution module with a hybrid attention mechanism, increasing the model’s attention to the space position of wake vortex core. Third, environmental factors that affect the vortex behavior of the aircraft’s wake were encoded into the model. Experiments were conducted on a Doppler LiDAR acquisition dataset to validate the effectiveness of the proposed model. The results show that the proposed network has an accuracy of 0.9963 and a recognition speed at 100 frames per second was achieved on an experimental device with 0.51 M parameters.

Development of the TOA-Related Models for PM2.5 Prediction Pre- and Post-COVID-19 Outbreak over Yangtze River Delta Region of China

The lockdown and the strict regulation measures implemented by Chinese government due to the outbreak of the COVID-19 pandemic not only decelerated the spread of the virus but also brought a positive effect on the nationwide atmospheric quality. In this study, we extended our previous research on remotely sensed estimation of PM2.5 concentrations in Yangtze River Delta region (i.e., YRD) of China from 2019 to the strict regulation period of 2020 (i.e., 24 Jan, 2020-31 Aug, 2020). Unlike the method using aerosol optical depth (AOD) developed in previous studies, we validated the possibility of moderate resolution imaging spectroradiometer (MODIS) top-of-atmosphere (TOA) reflectance (i.e., MODIS TOA) at 21 bands in estimating the PM2.5 concentrations in YRD region. Two random forests (i.e., TOA-sig RF and TOA-all RF) incorporated with different MODIS TOA datasets were developed, and the results showed that the TOA-sig RF model performed better with R2 of 0.81 (RMSE=8.07 μg/m3) than TOA-all RF model with R2 of 0.79 (RMSE=9.13 μg/m3). The monthly averaged PM2.5 exhibited the highest value of 50.81 μg/m3 in YRD region in January 2020 and sharply decreased from February to August 2020. The annual mean PM2.5 concentrations derived by TOA-sig RF model were 47.74, 32.14, and 21.04 μg/m3 in winter, spring, and summer in YRD during the strict regulation period of 2020, respectively, showing much lower values than those in 2019. Our research demonstrated that the PM2.5 concentrations could be effectively estimated by using MODIS TOA reflectance at 21 bands and the random forest.

A Taxonomy on Smart Healthcare Technologies: Security Framework, Case Study, and Future Directions

There is a massive transformation in the traditional healthcare system from the specialist-centric approach to the patient-centric approach by adopting modern and intelligent healthcare solutions to build a smart healthcare system. It permits patients to directly share their medical data with the specialist for remote diagnosis without any human intervention. Furthermore, the remote monitoring of patients utilizing wearable sensors, Internet of Things (IoT) technologies, and artificial intelligence (AI) has made the treatment readily accessible and affordable. However, the advancement also brings several security and privacy concerns that poorly maneuvered the effective performance of the smart healthcare system. An attacker can exploit the IoT infrastructure, perform an adversarial attack on AI models, and proliferate resource starvation attacks in smart healthcare system. To overcome the aforementioned issues, in this survey, we extensively reviewed and created a comprehensive taxonomy of various smart healthcare technologies such as wearable devices, digital healthcare, and body area networks (BANs), along with their security aspects and solutions for the smart healthcare system. Moreover, we propose an AI-based architecture with the 6G network interface to secure the data exchange between patients and medical practitioners. We have examined our proposed architecture with the case study based on the COVID-19 pandemic by adopting unmanned aerial vehicles (UAVs) for data exchange. The performance of the proposed architecture is evaluated using various machine learning (ML) classification algorithms such as random forest (RF), naive Bayes (NB), logistic regression (LR), linear discriminant analysis (LDA), and perceptron. The RF classification algorithm outperforms the conventional algorithms in terms of accuracy, i.e., 98%. Finally, we present open issues and research challenges associated with smart healthcare technologies.