Convolutional neural network model based on radiological images to support COVID-19 diagnosis: Evaluating database biases

As SARS-CoV-2 has spread quickly throughout the world, the scientific community has spent major efforts on better understanding the characteristics of the virus and possible means to prevent, diagnose, and treat COVID-19. A valid approach presented in the literature is to develop an image-based method to support COVID-19 diagnosis using convolutional neural networks (CNN). Because the availability of radiological data is rather limited due to the novelty of COVID-19, several methodologies consider reduced datasets, which may be inadequate, biasing the model. Here, we performed an analysis combining six different databases using chest X-ray images from open datasets to distinguish images of infected patients while differentiating COVID-19 and pneumonia from 'no-findings' images. In addition, the performance of models created from fewer databases, which may imperceptibly overestimate their results, is discussed. Two CNN-based architectures were created to process images of different sizes (512 × 512, 768 × 768, 1024 × 1024, and 1536 × 1536). Our best model achieved a balanced accuracy (BA) of 87.7% in predicting one of the three classes ('no-findings', 'COVID-19', and 'pneumonia') and a specific balanced precision of 97.0% for 'COVID-19' class. We also provided binary classification with a precision of 91.0% for detection of sick patients (i.e., with COVID-19 or pneumonia) and 98.4% for COVID-19 detection (i.e., differentiating from 'no-findings' or 'pneumonia'). Indeed, despite we achieved an unrealistic 97.2% BA performance for one specific case, the proposed methodology of using multiple databases achieved better and less inflated results than from models with specific image datasets for training. Thus, this framework is promising for a low-cost, fast, and noninvasive means to support the diagnosis of COVID-19.

Public health in times of crisis: An overlooked variable in city management theories?

The volume of research that associates the theme of city management with crises resulting from emerging infectious disease is modest, even after the occurrences of Ebola and Severe Acute Respiratory Syndrome. Similarly, the Coronavirus disease (COVID-19) pandemic has thus far contributed only modestly to the expansion of attention to people's health, through city management, in times of crisis. This study, by means of a systematic literature review, analyzes the gap in research on urban theory on how epidemics are confronted. The term "cities" had 2,440,607 articles published and were identified 665 that presents the combination of the term "pandemic". After the development of content analysis were identified 11 articles prior to 2019 and 10 articles published between January and June 2020, adhering to the objective of this investigation. Prior to 2019 studies addressed topics related to the construction of an urban structure aimed at reducing people's vulnerability to infectious diseases, starting in 2020, the focus of researchers' attention is on the use of information and communication technologies used as tools for prevention and control. Theories of the management of cities indicate the need to extrapolate the urban perimeter, incorporating the relations of dependence in cities with the other actors within the surroundings, especially in times of crisis. Studies have emphasized that cities are not isolated islands; rather, they are parts of a complex system with multiple exchanges. This thematic field of study enhances research that presents urban planning solutions by using data-driven management to consider conduct, parameters, and protocols relating to public health in moments of crisis.

The Ouroboros Model, Proposal for Self-Organizing General Cognition Substantiated

The Ouroboros Model has been proposed as a biologically-inspired comprehensive cognitive architecture for general intelligence, comprising natural and artificial manifestations. The approach addresses very diverse fundamental desiderata of research in natural cognition and also artificial intelligence, AI. Here, it is described how the postulated structures have met with supportive evidence over recent years. The associated hypothesized processes could remedy pressing problems plaguing many, and even the most powerful current implementations of AI, including in particular deep neural networks. Some selected recent findings from very different fields are summoned, which illustrate the status and substantiate the proposal.

Use and Adaptations of Machine Learning in Big Data—Applications in Real Cases in Agriculture

The data generated in modern agricultural operations are provided by diverse elements, which allow a better understanding of the dynamic conditions of the crop, soil and climate, which indicates that these processes will be increasingly data-driven. Big Data and Machine Learning (ML) have emerged as high-performance computing technologies to create new opportunities to unravel, quantify and understand agricultural processes through data. However, there are many challenges to achieve the integration of these technologies. It implies making some adaptations to ML for using it with Big Data. These adaptations must consider the increasing volume of data, its variety and the transmission speed issues. This paper provides information on the use of Big Data and ML for agriculture, identifying challenges, adaptations and the design of architectures for these systems. We conducted a Systematic Literature Review (SLR), which allowed us to analyze 34 real cases applied in agriculture. This review may be of interest to computer or data scientists and electronic or software engineers. The results show that manipulating large volumes of data is no longer a challenge due to Cloud technologies. There are still challenges regarding (1) processing speed due to little control of the data in its different stages, raw, semi-processed and processed data (value data); (2) information visualization systems, which support technical data little understood by farmers.

SOM-LWL method for identification of COVID-19 on chest X-rays

The outbreak of coronavirus disease 2019 (COVID-19) has had an immense impact on world health and daily life in many countries. Sturdy observing of the initial site of infection in patients is crucial to gain control in the struggle with COVID-19. The early automated detection of the recent coronavirus disease (COVID-19) will help to limit its dissemination worldwide. Many initial studies have focused on the identification of the genetic material of coronavirus and have a poor detection rate for long-term surgery. The first imaging procedure that played an important role in COVID-19 treatment was the chest X-ray. Radiological imaging is often used as a method that emphasizes the performance of chest X-rays. Recent findings indicate the presence of COVID-19 in patients with irregular findings on chest X-rays. There are many reports on this topic that include machine learning strategies for the identification of COVID-19 using chest X-rays. Other current studies have used non-public datasets and complex artificial intelligence (AI) systems. In our research, we suggested a new COVID-19 identification technique based on the locality-weighted learning and self-organization map (LWL-SOM) strategy for detecting and capturing COVID-19 cases. We first grouped images from chest X-ray datasets based on their similar features in different clusters using the SOM strategy in order to discriminate between the COVID-19 and non-COVID-19 cases. Then, we built our intelligent learning model based on the LWL algorithm to diagnose and detect COVID-19 cases. The proposed SOM-LWL model improved the correlation coefficient performance results between the Covid19, no-finding, and pneumonia cases; pneumonia and no-finding cases; Covid19 and pneumonia cases; and Covid19 and no-finding cases from 0.9613 to 0.9788, 0.6113 to 1 0.8783 to 0.9999, and 0.8894 to 1, respectively. The proposed LWL-SOM had better results for discriminating COVID-19 and non-COVID-19 patients than the current machine learning-based solutions using AI evaluation measures.

An Exploration of Ethical Decision Making with Intelligence Augmentation

In recent years, the use of Artificial Intelligence agents to augment and enhance the operational decision making of human agents has increased. This has delivered real benefits in terms of improved service quality, delivery of more personalised services, reduction in processing time, and more efficient allocation of resources, amongst others. However, it has also raised issues which have real-world ethical implications such as recommending different credit outcomes for individuals who have an identical financial profile but different characteristics (e.g., gender, race). The popular press has highlighted several high-profile cases of algorithmic discrimination and the issue has gained traction. While both the fields of ethical decision making and Explainable AI (XAI) have been extensively researched, as yet we are not aware of any studies which have examined the process of ethical decision making with Intelligence augmentation (IA). We aim to address that gap with this study. We amalgamate the literature in both fields of research and propose, but not attempt to validate empirically, propositions and belief statements based on the synthesis of the existing literature, observation, logic, and empirical analogy. We aim to test these propositions in future studies.

Deep convolutional neural networks for multiplanar lung nodule detection: Improvement in small nodule identification

PURPOSE

Early detection of lung cancer is of importance since it can increase patients' chances of survival. To detect nodules accurately during screening, radiologists would commonly take the axial, coronal, and sagittal planes into account, rather than solely the axial plane in clinical evaluation. Inspired by clinical work, the paper aims to develop an accurate deep learning framework for nodule detection by a combination of multiple planes.

METHODS

The nodule detection system is designed in two stages, multiplanar nodule candidate detection, multiscale false positive (FP) reduction. At the first stage, a deeply supervised encoder-decoder network is trained by axial, coronal, and sagittal slices for the candidate detection task. All possible nodule candidates from the three different planes are merged. To further refine results, a three-dimensional multiscale dense convolutional neural network that extracts multiscale contextual information is applied to remove non-nodules. In the public LIDC-IDRI dataset, 888 computed tomography scans with 1186 nodules accepted by at least three of four radiologists are selected to train and evaluate our proposed system via a tenfold cross-validation scheme. The free-response receiver operating characteristic curve is used for performance assessment.

RESULTS

The proposed system achieves a sensitivity of 94.2% with 1.0 FP/scan and a sensitivity of 96.0% with 2.0 FPs/scan. Although it is difficult to detect small nodules (i.e., <6 mm), our designed CAD system reaches a sensitivity of 93.4% (95.0%) of these small nodules at an overall FP rate of 1.0 (2.0) FPs/scan. At the nodule candidate detection stage, results show that the system with a multiplanar method is capable to detect more nodules compared to using a single plane.

CONCLUSION

Our approach achieves good performance not only for small nodules but also for large lesions on this dataset. This demonstrates the effectiveness of our developed CAD system for lung nodule detection.

A Generic Encapsulation to Unravel Social Spreading of a Pandemic: An Underlying Architecture

Cases of a new emergent infectious disease caused by mutations in the coronavirus family, called “COVID-19,” have spiked recently, affecting millions of people, and this has been classified as a global pandemic due to the wide spread of the virus. Epidemiologically, humans are the targeted hosts of COVID-19, whereby indirect/direct transmission pathways are mitigated by social/spatial distancing. People naturally exist in dynamically cascading networks of social/spatial interactions. Their rational actions and interactions have huge uncertainties in regard to common social contagions with rapid network proliferations on a daily basis. Different parameters play big roles in minimizing such uncertainties by shaping the understanding of such contagions to include cultures, beliefs, norms, values, ethics, etc. Thus, this work is directed toward investigating and predicting the viral spread of the current wave of COVID-19 based on human socio-behavioral analyses in various community settings with unknown structural patterns. We examine the spreading and social contagions in unstructured networks by proposing a model that should be able to (1) reorganize and synthesize infected clusters of any networked agents, (2) clarify any noteworthy members of the population through a series of analyses of their behavioral and cognitive capabilities, (3) predict where the direction is heading with any possible outcomes, and (4) propose applicable intervention tactics that can be helpful in creating strategies to mitigate the spread. Such properties are essential in managing the rate of spread of viral infections. Furthermore, a novel spectra-based methodology that leverages configuration models as a reference network is proposed to quantify spreading in a given candidate network. We derive mathematical formulations to demonstrate the viral spread in the network structures.

Sugarcane Yield Mapping Using High-Resolution Imagery Data and Machine Learning Technique

Yield maps provide essential information to guide precision agriculture (PA) practices. Yet, on-board yield monitoring for sugarcane can be challenging. At the same time, orbital images have been widely used for indirect crop yield estimation for many crops like wheat, corn, and rice, but not for sugarcane. Due to this, the objective of this study is to explore the potential of multi-temporal imagery data as an alternative for sugarcane yield mapping. The study was based on developing predictive sugarcane yield models integrating time-series orbital imaging and a machine learning technique. A commercial sugarcane site was selected, and Sentinel-2 images were acquired from the beginning of the ratoon sprouting until harvesting of two consecutive cropping seasons. The predictive yield models RF (Random forest) and MLR (Multiple Linear Regression) were developed using orbital images and yield maps generated by a commercial sensor-system on harvesting. Original yield data were filtered and interpolated with the same spatial resolution of the orbital images. The entire dataset was divided into training and testing datasets. Spectral bands, especially the near-infrared at tillering crop stage showed greater contribution to predicting sugarcane yield than the use of derived spectral vegetation indices. The Root Mean Squared Error (RMSE) obtained for the RF regression based on multiple spectral bands was 4.63 Mg ha−1 with an R2 of 0.70 for the testing dataset. Overall, the RF regression had better performance than the MLR to predict sugarcane yield.

An Accuracy vs. Complexity Comparison of Deep Learning Architectures for the Detection of COVID-19 Disease

In parallel with the vast medical research on clinical treatment of COVID-19, an important action to have the disease completely under control is to carefully monitor the patients. What the detection of COVID-19 relies on most is the viral tests, however, the study of X-rays is helpful due to the ease of availability. There are various studies that employ Deep Learning (DL) paradigms, aiming at reinforcing the radiography-based recognition of lung infection by COVID-19. In this regard, we make a comparison of the noteworthy approaches devoted to the binary classification of infected images by using DL techniques, then we also propose a variant of a convolutional neural network (CNN) with optimized parameters, which performs very well on a recent dataset of COVID-19. The proposed model’s effectiveness is demonstrated to be of considerable importance due to its uncomplicated design, in contrast to other presented models. In our approach, we randomly put several images of the utilized dataset aside as a hold out set; the model detects most of the COVID-19 X-rays correctly, with an excellent overall accuracy of 99.8%. In addition, the significance of the results obtained by testing different datasets of diverse characteristics (which, more specifically, are not used in the training process) demonstrates the effectiveness of the proposed approach in terms of an accuracy up to 93%.

Applications of artificial intelligence in battling against covid-19: A literature review

Colloquially known as coronavirus, the Severe Acute Respiratory Syndrome CoronaVirus 2 (SARS-CoV-2), that causes CoronaVirus Disease 2019 (COVID-19), has become a matter of grave concern for every country around the world. The rapid growth of the pandemic has wreaked havoc and prompted the need for immediate reactions to curb the effects. To manage the problems, many research in a variety of area of science have started studying the issue. Artificial Intelligence is among the area of science that has found great applications in tackling the problem in many aspects. Here, we perform an overview on the applications of AI in a variety of fields including diagnosis of the disease via different types of tests and symptoms, monitoring patients, identifying severity of a patient, processing covid-19 related imaging tests, epidemiology, pharmaceutical studies, etc. The aim of this paper is to perform a comprehensive survey on the applications of AI in battling against the difficulties the outbreak has caused. Thus we cover every way that AI approaches have been employed and to cover all the research until the writing of this paper. We try organize the works in a way that overall picture is comprehensible. Such a picture, although full of details, is very helpful in understand where AI sits in current pandemonium. We also tried to conclude the paper with ideas on how the problems can be tackled in a better way and provide some suggestions for future works.

Methodology and tools for creating training samples for artificial intelligence systems for recognizing lung cancer on CT images

Introduction. Medical imaging techniques can diagnose many diseases at the early stages of their development, improving the patient survival. Artificial intelligence (AI) systems, requiring the high-quality annotated and marked-up sets of medical images, are a suitable and promising means of improving the diagnostics’ quality. The purpose of the study was to develop a methodology and software for creating AIS training sets. Material and methods. We compared the main annotation methods’ performance and accuracy and based the information system on the most efficient method in both domains to develop an optimal approach. To markup objects of interest, we used the cluster model of lesions localization previously developed by the authors. We used C++ and Kotlin programming languages for software development. Results. A structured annotation template with delivered a glossary of terms became the basis of the information system. The latter consists of three interacting modules, two of which are executed on a remote server’s capacities and one on a personal computer or mobile device of the end-user. The first module is a web service responsible for the workflow logic. The second module, a web server, is responsible for interacting with client applications. Its role is to identify users and manage the database and Picture Archiving and Communication System (PACS) connections. The front-end module is a web application with a graphical interface that assists the end-user in images’ markup and annotation. Conclusions. An algorithmic basis and a software package have been created for annotation and markup of CT images. The resulting information system was used in a large-scale lung cancer screening project for the creation of medical imaging datasets.

Anomaly Identification during Polymerase Chain Reaction for Detecting SARS-CoV-2 Using Artificial Intelligence Trained from Simulated Data

Real-time reverse transcription (RT) PCR is the gold standard for detecting Severe Acute Respiratory Syndrome Coronavirus 2 (SARS-CoV-2), owing to its sensitivity and specificity, thereby meeting the demand for the rising number of cases. The scarcity of trained molecular biologists for analyzing PCR results makes data verification a challenge. Artificial intelligence (AI) was designed to ease verification, by detecting atypical profiles in PCR curves caused by contamination or artifacts. Four classes of simulated real-time RT-PCR curves were generated, namely, positive, early, no, and abnormal amplifications. Machine learning (ML) models were generated and tested using small amounts of data from each class. The best model was used for classifying the big data obtained by the Virology Laboratory of Simon Bolivar University from real-time RT-PCR curves for SARS-CoV-2, and the model was retrained and implemented in a software that correlated patient data with test and AI diagnoses. The best strategy for AI included a binary classification model, which was generated from simulated data, where data analyzed by the first model were classified as either positive or negative and abnormal. To differentiate between negative and abnormal, the data were reevaluated using the second model. In the first model, the data required preanalysis through a combination of prepossessing. The early amplification class was eliminated from the models because the numbers of cases in big data was negligible. ML models can be created from simulated data using minimum available information. During analysis, changes or variations can be incorporated by generating simulated data, avoiding the incorporation of large amounts of experimental data encompassing all possible changes. For diagnosing SARS-CoV-2, this type of AI is critical for optimizing PCR tests because it enables rapid diagnosis and reduces false positives. Our method can also be used for other types of molecular analyses.

Artificial Intelligence Analysis of the Gene Expression of Follicular Lymphoma Predicted the Overall Survival and Correlated with the Immune Microenvironment Response Signatures

Follicular lymphoma (FL) is the second most common lymphoma in Western countries. FL is characterized by being incurable, usually having an indolent clinical course with frequent relapses, and an eventual patient’s death or transformation to Diffuse Large B-cell Lymphoma. The immune response and the tumoral immune microenvironment, including FOXP3+Tregs, PD-1+TFH cells, TNFRSF14 (HVEM), and BTLA play a role in the pathogenesis. We aimed to analyze the gene expression of FL by Artificial Intelligence (machine learning, deep learning), to identify genes associated with the prognosis of the patients and with the microenvironment in terms of overall survival (OS). A series of 184 cases of the GSE16131 dataset was analyzed by multilayer perceptron (MLP) and radial basis function (RBF) neural networks. In the analysis, MLP and RBF had a synergistic effect. From an initial set of 22,215 genes probes, a final set of 43 genes was highlighted. These 43 genes predicted the OS and correlated with the immune microenvironment: in a multivariate Cox analysis, 18 genes were associated with a poor prognosis (namely, MED8, KRT19, CDC40, SLC24A2, PRB1, KIAA0100, EVA1B, KLK10, TMEM70, BTN2A3P, TRPM4, MED6, FRYL, CBFA2T2, RANBP9, BNIP2, PTP4A2 and ALDH1L1) and 25 genes were associated with a good prognosis of the patients. Gene set enrichment analysis (GSEA) confirmed these findings and showed a typical sinusoidal-like shape. Some of the most relevant genes for poor OS were EVA1B, KRT19, BTN2A3P, KLK10, TRPM4, TMEM70, and SLC24A2 (hazard risk = from 1.7 to 4.3, p < 0.005) and for good OS, these were TDRD12 and ZNF230 (HR = 0.34 and 0.28, p < 0.001). EVA1B, KRT19, BTN2AP3, KLK10, and TRPM4 also associated with M2-like macrophage markers including CD163, MRC1 (CD206), and IL10 in the core enrichment for dead OS outcome by GSEA and to poor OS by Kaplan–Meier with Log rank test. The scientific literature showed that some of these genes also play a role in other types of cancer. In conclusion, by Artificial Intelligence, we have identified new biomarkers with prognostic relevance in FL.

Opportunities and Challenges of Geospatial Analysis for Promoting Urban Livability in the Era of Big Data and Machine Learning

Urban systems involve a multitude of closely intertwined components, which are more measurable than before due to new sensors, data collection, and spatio-temporal analysis methods. Turning these data into knowledge to facilitate planning efforts in addressing current challenges of urban complex systems requires advanced interdisciplinary analysis methods, such as urban informatics or urban data science. Yet, by applying a purely data-driven approach, it is too easy to get lost in the ‘forest’ of data, and to miss the ‘trees’ of successful, livable cities that are the ultimate aim of urban planning. This paper assesses how geospatial data, and urban analysis, using a mixed methods approach, can help to better understand urban dynamics and human behavior, and how it can assist planning efforts to improve livability. Based on reviewing state-of-the-art research the paper goes one step further and also addresses the potential as well as limitations of new data sources in urban analytics to get a better overview of the whole ‘forest’ of these new data sources and analysis methods. The main discussion revolves around the reliability of using big data from social media platforms or sensors, and how information can be extracted from massive amounts of data through novel analysis methods, such as machine learning, for better-informed decision making aiming at urban livability improvement.

Social Media and E-mail Marketing Campaigns: Symmetry versus Convergence

Companies use social business intelligence (SBI) to identify and collect strategically significant information from a wide range of publicly available data sources, such as social media (SM). This study is an SBI-driven analysis of a company operating in the insurance sector. It underlines the contribution of SBI technology to sustainable profitability of a company by using an optimized marketing campaign on Facebook, in symmetry with a traditional e-mail campaign. Starting from a campaign on SM, the study identified a client portfolio, processed data, and applied a set of statistical methods, such as the index and the statistical significance (T-test), which later enabled the authors to validate research hypotheses (RH), and led to relevant business decisions. The study outlines the preferences of the selected group of companies for the manner in which they run a marketing campaign on SM in symmetry with an e-mail-run campaign. Although the study focused on the practical field of insurance, the suggested model can be used by any company of any industry proving that BI technologies is the nexus of collecting and interpreting results that are essential, globally applicable, and lead to sustainable development of companies operating in the age of globalization. The results of the study prove that symmetrical unfolding (time and opportunity symmetry) of SM marketing campaigns, and using email, could lead to better results compared to two separate marketing campaigns. Moreover, the outcomes of both campaigns showed convergence on SBI platforms, which led to higher efficiency of management of preferences of campaign beneficiaries in the insurance sector.

Industry 5.0: Potential Applications in COVID-19

Industry 5.0, the fifth industrial revolution, consists of smart digital information and manufacturing technologies. This industrial revolution generates effective processes and makes rapid improvement in industries and healthcare. Solutions to challenges posed by COVID-19 pandemic can be identified with the deployment of Industry 5.0-based technologies. It helps to provide personalized therapy and treatment processes to the COVID-19 patients if a detailed patient’s information is available. The aim of Industry 5.0 technologies is to create a smart healthcare environment with real-time capabilities. During the COVID-19 pandemic, these technologies can provide a remote monitoring system in healthcare. This paper identifies and studies major technologies of Industry 5.0 helpful for the COVID-19 pandemic. The supportive features of Industry 5.0 for the COVID-19 pandemic are discussed diagrammatically. Finally, we identified and studied significant challenges faced in the context of Industry 5.0 technologies for the COVID-19 pandemic. The literature revealed that this technological innovation allows a high personalization level to fulfill personal specific demands of the patient and doctors. These technologies play a significant role in making the life of doctors better. Further, doctors can use this technology to focus on critically infected patients and provide proper appropriate information regarding their better treatment. Moreover, Industry 5.0 technologies can help doctors and medical students for required medical training during this COVID-19 outbreak.

A Review on Early Forest Fire Detection Systems Using Optical Remote Sensing

The environmental challenges the world faces nowadays have never been greater or more complex. Global areas covered by forests and urban woodlands are threatened by natural disasters that have increased dramatically during the last decades, in terms of both frequency and magnitude. Large-scale forest fires are one of the most harmful natural hazards affecting climate change and life around the world. Thus, to minimize their impacts on people and nature, the adoption of well-planned and closely coordinated effective prevention, early warning, and response approaches are necessary. This paper presents an overview of the optical remote sensing technologies used in early fire warning systems and provides an extensive survey on both flame and smoke detection algorithms employed by each technology. Three types of systems are identified, namely terrestrial, airborne, and spaceborne-based systems, while various models aiming to detect fire occurrences with high accuracy in challenging environments are studied. Finally, the strengths and weaknesses of fire detection systems based on optical remote sensing are discussed aiming to contribute to future research projects for the development of early warning fire systems.

Pre-Training Autoencoder for Lung Nodule Malignancy Assessment Using CT Images

Lung cancer late diagnosis has a large impact on the mortality rate numbers, leading to a very low five-year survival rate of 5%. This issue emphasises the importance of developing systems to support a diagnostic at earlier stages. Clinicians use Computed Tomography (CT) scans to assess the nodules and the likelihood of malignancy. Automatic solutions can help to make a faster and more accurate diagnosis, which is crucial for the early detection of lung cancer. Convolutional neural networks (CNN) based approaches have shown to provide a reliable feature extraction ability to detect the malignancy risk associated with pulmonary nodules. This type of approach requires a massive amount of data to model training, which usually represents a limitation in the biomedical field due to medical data privacy and security issues. Transfer learning (TL) methods have been widely explored in medical imaging applications, offering a solution to overcome problems related to the lack of training data publicly available. For the clinical annotations experts with a deep understanding of the complex physiological phenomena represented in the data are required, which represents a huge investment. In this direction, this work explored a TL method based on unsupervised learning achieved when training a Convolutional Autoencoder (CAE) using images in the same domain. For this, lung nodules from the Lung Image Database Consortium and Image Database Resource Initiative (LIDC-IDRI) were extracted and used to train a CAE. Then, the encoder part was transferred, and the malignancy risk was assessed in a binary classification—benign and malignant lung nodules, achieving an Area Under the Curve (AUC) value of 0.936. To evaluate the reliability of this TL approach, the same architecture was trained from scratch and achieved an AUC value of 0.928. The results reported in this comparison suggested that the feature learning achieved when reconstructing the input with an encoder-decoder based architecture can be considered an useful knowledge that might allow overcoming labelling constraints.

Sentiment Analysis of Children and Youth Literature: Is There a Pollyanna Effect?

If the words of natural human language possess a universal positivity bias, as assumed by Boucher and Osgood’s (1969) famous Pollyanna hypothesis and computationally confirmed for large text corpora in several languages (Dodds et al., 2015), then children and youth literature (CYL) should also show a Pollyanna effect. Here we tested this prediction applying an unsupervised vector space model-based sentiment analysis tool called SentiArt (Jacobs, 2019) to two CYL corpora, one in English (372 books) and one in German (500 books). Pitching our analysis at the sentence level, and assessing semantic as well as lexico-grammatical information, both corpora show the Pollyanna effect and thus add further evidence to the universality hypothesis. The results of our multivariate sentiment analyses provide interesting testable predictions for future scientific studies of literature.

The Sustainability of Artificial Intelligence: An Urbanistic Viewpoint from the Lens of Smart and Sustainable Cities

The popularity and application of artificial intelligence (AI) are increasing rapidly all around the world—where, in simple terms, AI is a technology which mimics the behaviors commonly associated with human intelligence. Today, various AI applications are being used in areas ranging from marketing to banking and finance, from agriculture to healthcare and security, from space exploration to robotics and transport, and from chatbots to artificial creativity and manufacturing. More recently, AI applications have also started to become an integral part of many urban services. Urban artificial intelligences manage the transport systems of cities, run restaurants and shops where every day urbanity is expressed, repair urban infrastructure, and govern multiple urban domains such as traffic, air quality monitoring, garbage collection, and energy. In the age of uncertainty and complexity that is upon us, the increasing adoption of AI is expected to continue, and so its impact on the sustainability of our cities. This viewpoint explores and questions the sustainability of AI from the lens of smart and sustainable cities, and generates insights into emerging urban artificial intelligences and the potential symbiosis between AI and a smart and sustainable urbanism. In terms of methodology, this viewpoint deploys a thorough review of the current status of AI and smart and sustainable cities literature, research, developments, trends, and applications. In so doing, it contributes to existing academic debates in the fields of smart and sustainable cities and AI. In addition, by shedding light on the uptake of AI in cities, the viewpoint seeks to help urban policymakers, planners, and citizens make informed decisions about a sustainable adoption of AI.

IoT in the Wake of COVID-19: A Survey on Contributions, Challenges and Evolution

The novel coronavirus (COVID-19), declared by the World Health Organization (WHO) as a global pandemic, has brought with it changes to the general way of life. Major sectors of the world industry and economy have been affected and the Internet of Things (IoT) management and framework is no exception in this regard. This article provides an up to date survey on how a global pandemic such as COVID-19 has affected the world of IoT technologies. It looks at the contributions that IoT and associated sensor technologies have made towards virus tracing, tracking and spread mitigation. The associated challenges of deployment of sensor hardware in the face of a rapidly spreading pandemic have been looked into as part of this review article. The effects of a global pandemic on the evolution of IoT architectures and management have also been addressed, leading to the likely outcomes on future IoT implementations. In general, this article provides an insight into the advancement of sensor-based E-health towards the management of global pandemics. It also answers the question of how a global virus pandemic has shaped the future of IoT networks.

Evaluating Deep Learning Algorithms in Pulmonary Nodule Detection

Lung cancer is considered the deadliest cancer worldwide. In order to detect it, radiologists need to inspect multiple Computed Tomography (CT) scans. This task is tedious and time consuming. In recent years, promising methods based on deep learning object detection algorithms were proposed for the automatic nodule detection and classification. With those techniques, Computed Aided Detection (CAD) software can be developed to alleviate radiologist's burden and help speed-up the screening process. However, among available object detection frameworks, there are just a limited number that have been used for this purpose. Moreover, it can be challenging to know which one to choose as a baseline for the development of a new application for this task. Hence, in this work we propose a benchmark of recent state-of-the-art deep learning detectors such as Faster-RCNN, YOLO, SSD, RetinaNet and EfficientDet in the challenging task of pulmonary nodule detection. Evaluation is done using automatically segmented 2D images extracted from volumetric chest CT scans.

Light-Weight Student LSTM for Real-Time Wildfire Smoke Detection

As the need for wildfire detection increases, research on wildfire smoke detection combining low-cost cameras and deep learning technology is increasing. Camera-based wildfire smoke detection is inexpensive, allowing for a quick detection, and allows a smoke to be checked by the naked eye. However, because a surveillance system must rely only on visual characteristics, it often erroneously detects fog and clouds as smoke. In this study, a combination of a You-Only-Look-Once detector and a long short-term memory (LSTM) classifier is applied to improve the performance of wildfire smoke detection by reflecting on the spatial and temporal characteristics of wildfire smoke. However, because it is necessary to lighten the heavy LSTM model for real-time smoke detection, in this paper, we propose a new method for applying the teacher–student framework to deep LSTM. Through this method, a shallow student LSTM is designed to reduce the number of layers and cells constituting the LSTM model while maintaining the original deep LSTM performance. As the experimental results indicate, our proposed method achieves up to an 8.4-fold decrease in the number of parameters and a faster processing time than the teacher LSTM while maintaining a similar detection performance as deep LSTM using several state-of-the-art methods on a wildfire benchmark dataset.

A Deep Learning Approach to Detect COVID-19 Patients from Chest X-ray Images

Deep Learning has improved multi-fold in recent years and it has been playing a great role in image classification which also includes medical imaging. Convolutional Neural Networks (CNNs) have been performing well in detecting many diseases including coronary artery disease, malaria, Alzheimer’s disease, different dental diseases, and Parkinson’s disease. Like other cases, CNN has a substantial prospect in detecting COVID-19 patients with medical images like chest X-rays and CTs. Coronavirus or COVID-19 has been declared a global pandemic by the World Health Organization (WHO). As of 8 August 2020, the total COVID-19 confirmed cases are 19.18 M and deaths are 0.716 M worldwide. Detecting Coronavirus positive patients is very important in preventing the spread of this virus. On this conquest, a CNN model is proposed to detect COVID-19 patients from chest X-ray images. Two more CNN models with different number of convolution layers and three other models based on pretrained ResNet50, VGG-16 and VGG-19 are evaluated with comparative analytical analysis. All six models are trained and validated with Dataset 1 and Dataset 2. Dataset 1 has 201 normal and 201 COVID-19 chest X-rays whereas Dataset 2 is comparatively larger with 659 normal and 295 COVID-19 chest X-ray images. The proposed model performs with an accuracy of 98.3% and a precision of 96.72% with Dataset 2. This model gives the Receiver Operating Characteristic (ROC) curve area of 0.983 and F1-score of 98.3 with Dataset 2. Moreover, this work shows a comparative analysis of how change in convolutional layers and increase in dataset affect classifying performances.

Pandemic stricken cities on lockdown. Where are our planning and design professionals [now, then and into the future]?

Chinese cities have been placed upon lockdown in early 2020 in an attempt to contain the novel coronavirus (COVID-19), as increasingly huge demands are being placed upon Chinese and international health professionals to address this pandemic. Surprisingly, planning and design professionals are absent in the discourses about existing and post-COVID-19 strategies and actions even though previous pandemics historically revealed major impacts on the urban fabric from social and economic perspectives. This paper is a call for action for international architectural and urban organisations to include pandemics and similar in their disaster management strategies. This need is very evident in their need to better design creative and relevant protocols in partnership with health discipine organisations, and so that their applied deployment in pandemic stricken cities can be effected integrated seamlessly within normal city environment planning activities and also in incident situations like containing the current COVID-19 pandemic.

Predictive Insights for Improving the Resilience of Global Food Security Using Artificial Intelligence

Unabated pressures on food systems affect food security on a global scale. A human-centric artificial intelligence-based probabilistic approach is used in this paper to perform a unified analysis of data from the Global Food Security Index (GFSI). The significance of this intuitive probabilistic reasoning approach for predictive forecasting lies in its simplicity and user-friendliness to people who may not be trained in classical computer science or in software programming. In this approach, predictive modeling using a counterfactual probabilistic reasoning analysis of the GFSI dataset can be utilized to reveal the interplay and tensions between the variables that underlie food affordability, food availability, food quality and safety, and the resilience of natural resources. Exemplars are provided in this paper to illustrate how computational simulations can be used to produce forecasts of good and bad conditions in food security using multi-variant optimizations. The forecast of these future scenarios is useful for informing policy makers and stakeholders across domain verticals, so they can make decisions that are favorable to global food security.

Industry 4.0 in Finance: The Impact of Artificial Intelligence (AI) on Digital Financial Inclusion

This study sought to investigate the impact of AI on digital financial inclusion. Digital financial inclusion is becoming central in the debate on how to ensure that people who are at the lower levels of the pyramid become financially active. Fintech companies are using AI and its various applications to ensure that the goal of digital financial inclusion is realized that is to ensure that low-income earners, the poor, women, youths, small businesses participate in the mainstream financial market. This study used conceptual and documentary analysis of peer-reviewed journals, reports and other authoritative documents on AI and digital financial inclusion to assess the impact of AI on digital financial inclusion. The present study discovered that AI has a strong influence on digital financial inclusion in areas related to risk detection, measurement and management, addressing the problem of information asymmetry, availing customer support and helpdesk through chatbots and fraud detection and cybersecurity. Therefore, it is recommended that financial institutions and non-financial institutions and governments across the world adopt and scale up the use of AI tools and applications as they present benefits in the quest to ensure that the vulnerable groups of people who are not financially active do participate in the formal financial market with minimum challenges and maximum benefits.

The Role of Health Technology and Informatics in a Global Public Health Emergency: Practices and Implications From the COVID-19 Pandemic

At present, the coronavirus disease (COVID-19) is spreading around the world. It is a critical and important task to take thorough efforts to prevent and control the pandemic. Compared with severe acute respiratory syndrome and Middle East Respiratory Syndrome, COVID-19 spreads more rapidly owing to increased globalization, a longer incubation period, and unobvious symptoms. As the coronavirus has the characteristics of strong transmission and weak lethality, and since the large-scale increase of infected people may overwhelm health care systems, efforts are needed to treat critical patients, track and manage the health status of residents, and isolate suspected patients. The application of emerging health technologies and digital practices in health care, such as artificial intelligence, telemedicine or telehealth, mobile health, big data, 5G, and the Internet of Things, have become powerful "weapons" to fight against the pandemic and provide strong support in pandemic prevention and control. Applications and evaluations of all of these technologies, practices, and health delivery services are highlighted in this study.

Inferring Visual Biases in UAV Videos from Eye Movements

Unmanned Aerial Vehicle (UAV) imagery is gaining a lot of momentum lately. Indeed, gathered information from a bird-point-of-view is particularly relevant for numerous applications, from agriculture to surveillance services. We herewith study visual saliency to verify whether there are tangible differences between this imagery and more conventional contents. We first describe typical and UAV contents based on their human saliency maps in a high-dimensional space, encompassing saliency map statistics, distribution characteristics, and other specifically designed features. Thanks to a large amount of eye tracking data collected on UAV, we stress the differences between typical and UAV videos, but more importantly within UAV sequences. We then designed a process to extract new visual attention biases in the UAV imagery, leading to the definition of a new dictionary of visual biases. We then conduct a benchmark on two different datasets, whose results confirm that the 20 defined biases are relevant as a low-complexity saliency prediction system.

Machine Learning Classification Ensemble of Multitemporal Sentinel-2 Images: The Case of a Mixed Mediterranean Ecosystem

Land cover type classification still remains an active research topic while new sensors and methods become available. Applications such as environmental monitoring, natural resource management, and change detection require more accurate, detailed, and constantly updated land-cover type mapping. These needs are fulfilled by newer sensors with high spatial and spectral resolution along with modern data processing algorithms. Sentinel-2 sensor provides data with high spatial, spectral, and temporal resolution for the in classification of highly fragmented landscape. This study applies six traditional data classifiers and nine ensemble methods on multitemporal Sentinel-2 image datasets for identifying land cover types in the heterogeneous Mediterranean landscape of Lesvos Island, Greece. Support vector machine, random forest, artificial neural network, decision tree, linear discriminant analysis, and k-nearest neighbor classifiers are applied and compared with nine ensemble classifiers on the basis of different voting methods. kappa statistic, F1-score, and Matthews correlation coefficient metrics were used in the assembly of the voting methods. Support vector machine outperformed the base classifiers with kappa of 0.91. Support vector machine also outperformed the ensemble classifiers in an unseen dataset. Five voting methods performed better than the rest of the classifiers. A diversity study based on four different metrics revealed that an ensemble can be avoided if a base classifier shows an identifiable superiority. Therefore, ensemble approaches should include a careful selection of base-classifiers based on a diversity analysis.

Image Collection Summarization Method Based on Semantic Hierarchies

The size of internet image collections is increasing drastically. As a result, new techniques are required to facilitate users in browsing, navigation, and summarization of these large volume collections. Image collection summarization methods present users with a set of exemplar images as the most representative ones from the initial image collection. In this study, an image collection summarization technique was introduced according to semantic hierarchies among them. In the proposed approach, images were mapped to the nodes of a pre-defined domain ontology. In this way, a semantic hierarchical classifier was used, which finally mapped images to different nodes of the ontology. We made a compromise between the degree of freedom of the classifier and the goodness of the summarization method. The summarization was done using a group of high-level features that provided a semantic measurement of information in images. Experimental outcomes indicated that the introduced image collection summarization method outperformed the recent techniques for the summarization of image collections.

Artificial Intelligence-Enhanced Predictive Insights for Advancing Financial Inclusion: A Human-Centric AI-Thinking Approach

According to the World Bank, a key factor to poverty reduction and improving prosperity is financial inclusion. Financial service providers (FSPs) offering financially-inclusive solutions need to understand how to approach the underserved successfully. The application of artificial intelligence (AI) on legacy data can help FSPs to anticipate how prospective customers may respond when they are approached. However, it remains challenging for FSPs who are not well-versed in computer programming to implement AI projects. This paper proffers a no-coding human-centric AI-based approach to simulate the possible dynamics between the financial profiles of prospective customers collected from 45,211 contact encounters and predict their intentions toward the financial products being offered. This approach contributes to the literature by illustrating how AI for social good can also be accessible for people who are not well-versed in computer science. A rudimentary AI-based predictive modeling approach that does not require programming skills will be illustrated in this paper. In these AI-generated multi-criteria optimizations, analysts in FSPs can simulate scenarios to better understand their prospective customers. In conjunction with the usage of AI, this paper also suggests how AI-Thinking could be utilized as a cognitive scaffold for educing (drawing out) actionable insights to advance financial inclusion.

Underlining the Role of Data Science and Technology in Supporting Supply Chains, Political Stability and Health Networks During Pandemics

This concluding chapter explores how data science and technology has been key in fighting COVID-19 through early detection and in the devising of tools for containing the spread. Interestingly, two precedence constraints are seen to emerge. First, data-driven modeling is the leading policy at an urban and national level, and second, legislations, which are being passed at record speed, will remain as a legacy postvirus. It is expected that those will accelerate the digital transition of communities for decades to come and lead to a resurgence of the smart cities concept which peaked in 2015. This chapter thus outlines the increasing role of data science in health sciences, the need for more robust digital infrastructures, and the role of technology in supporting livability of communities and world order.

Hough Transform and Clustering for a 3-D Building Reconstruction with Tomographic SAR Point Clouds

Tomographic synthetic aperture radar (TomoSAR) produces 3-D point clouds with unavoidable noise or false targets that seriously deteriorate the quality of 3-D images and the building reconstruction over urban areas. In this paper, a Hough transform was adopted to detect the outline of a building; however, on one hand, the obtained outline of a building with Hough transform is broken, and on the other hand, some of these broken lines belong to the same segment of a building outline, but the parameters of these lines are slightly different. These problems will lead to that segment of a building outline being represented by multiple different parameters in the Hough transform. Therefore, an unsupervised clustering method was employed for clustering these line parameters. The lines gathered in the same cluster were considered to correspond to a same segment of a building outline. In this way, different line parameters corresponding to a segment of a building outline were integrated into one and then the continuous outline of the building in cloud points was obtained. Steps of the proposed data processing method were as follows. First, the Hough transform was made use of to detect the lines on the tomography plane in TomoSAR point clouds. These detected lines lay on the outline of the building, but they were broken due to the density variation of point clouds. Second, the lines detected using the Hough transform were grouped as a date set for training the building outline. Unsupervised clustering was utilized to classify the lines in several clusters. The cluster number was automatically determined via the unsupervised clustering algorithm, which meant the number of straight segments of the building edge was obtained. The lines in each cluster were considered to belong to the same straight segment of the building outline. Then, within each cluster, which represents a part or a segment of the building edge, a repaired straight line was constructed. Third, between each two clusters or each two segments of the building outline, the joint point was estimated by extending the two segments. Therefore, the building outline was obtained as completely as possible. Finally, taking the estimated building outline as the clustering center, supervised learning algorithm was used to classify the building cloud point and the noise (or false targets), then the building cloud point was refined. Then, our refined and unrefined data were fed into the neural network for building the 3-D construction. The comparison results show the correctness and the effectiveness of our improved method.