Performance comparison of machine learning driven approaches for classification of complex noises in quick response code images.

Quick response codes (QRCs) are found on many consumer products and often encode security information. However, information retrieval at receiving end may become challenging due to the degraded clarity of QRC images. This degradation may occur because of the transmission of digital images over noise channels or limited printing technology. Although the ability to reduce noises is critical, it is just as important to define the type and quantity of noises present in QRC images. Therefore, this study proposed a simple deep learning-based architecture to segregate the image as either an original (normal) QRC or a noisy QRC and identifies the noise type present in the image. For this, the study is divided into two stages. Firstly, it generated a QRC image dataset of 80,000 images by introducing seven different noises (speckle, salt & pepper, Poisson, pepper, localvar, salt, and Gaussian) to the original QRC images. Secondly, the generated dataset is fed to train the proposed convolutional neural network (CNN)-based model, seventeen pre-trained deep learning models, and two classical machine learning algorithms (Naïve Bayes (NB) and Decision Tree (DT)). XceptionNet attained the highest accuracy (87.48%) and kappa (85.7%). However, it is worth noting that the proposed CNN network with few layers competes with the state-of-the-art models and attained near to best accuracy (86.75%). Furthermore, detailed analysis shows that all models failed to classify images having Gaussian and Localvar noises correctly.

An Intelligent Anomaly Detection Approach for Accurate and Reliable Weather Forecasting at IoT Edges: A Case Study.

Industrialization and rapid urbanization in almost every country adversely affect many of our environmental values, such as our core ecosystem, regional climate differences and global diversity. The difficulties we encounter as a result of the rapid change we experience cause us to encounter many problems in our daily lives. The background of these problems is rapid digitalization and the lack of sufficient infrastructure to process and analyze very large volumes of data. Inaccurate, incomplete or irrelevant data produced in the IoT detection layer causes weather forecast reports to drift away from the concepts of accuracy and reliability, and as a result, activities based on weather forecasting are disrupted. A sophisticated and difficult talent, weather forecasting needs the observation and processing of enormous volumes of data. In addition, rapid urbanization, abrupt climate changes and mass digitization make it more difficult for the forecasts to be accurate and reliable. Increasing data density and rapid urbanization and digitalization make it difficult for the forecasts to be accurate and reliable. This situation prevents people from taking precautions against bad weather conditions in cities and rural areas and turns into a vital problem. In this study, an intelligent anomaly detection approach is presented to minimize the weather forecasting problems that arise as a result of rapid urbanization and mass digitalization. The proposed solutions cover data processing at the edge of the IoT and include filtering out the missing, unnecessary or anomaly data that prevent the predictions from being more accurate and reliable from the data obtained through the sensors. Anomaly detection metrics of five different machine learning (ML) algorithms, including support vector classifier (SVC), Adaboost, logistic regression (LR), naive Bayes (NB) and random forest (RF), were also compared in the study. These algorithms were used to create a data stream using the time, temperature, pressure, humidity and other sensor-generated information.

Sand cat swarm optimization-based feedback controller design for nonlinear systems.

The control of the open loop unstable systems with nonlinear structure is challenging work. In this paper, for the first time, we present a sand cat swarm optimization (SCSO) algorithm-based state feedback controller design for open-loop unstable systems. The SCSO algorithm is a newly proposed metaheuristic algorithm with an easy-to-implement structure that can efficiently find the optimal solution for optimization problems. The proposed SCSO-based state feedback controller can successfully optimize the control parameters with efficient convergence curve speed. In order to show the performance of the proposed method, three different nonlinear control systems such as an Inverted pendulum, a Furuta pendulum, and an Acrobat robot arm are considered. The control and optimization performances of the proposed SCSO algorithm are compared with well-known metaheuristic algorithms. The simulation results show that the proposed control method can either outperform the compared metaheuristic-based algorithms or have competitive results.

A Conceptual Multi-Layer Framework for the Detection of Nighttime Pedestrian in Autonomous Vehicles Using Deep Reinforcement Learning.

The major challenge faced by autonomous vehicles today is driving through busy roads without getting into an accident, especially with a pedestrian. To avoid collision with pedestrians, the vehicle requires the ability to communicate with a pedestrian to understand their actions. The most challenging task in research on computer vision is to detect pedestrian activities, especially at nighttime. The Advanced Driver-Assistance Systems (ADAS) has been developed for driving and parking support for vehicles to visualize sense, send and receive information from the environment but it lacks to detect nighttime pedestrian actions. This article proposes a framework based on Deep Reinforcement Learning (DRL) using Scale Invariant Faster Region-based Convolutional Neural Networks (SIFRCNN) technologies to efficiently detect pedestrian operations through which the vehicle, as agents train themselves from the environment and are forced to maximize the reward. The SIFRCNN has reduced the running time of detecting pedestrian operations from road images by incorporating Region Proposal Network (RPN) computation. Furthermore, we have used Reinforcement Learning (RL) for optimizing the Q-values and training itself to maximize the reward after getting the state from the SIFRCNN. In addition, the latest incarnation of SIFRCNN achieves near-real-time object detection from road images. The proposed SIFRCNN has been tested on KAIST, City Person, and Caltech datasets. The experimental results show an average improvement of 2.3% miss rate of pedestrian detection at nighttime compared to the other CNN-based pedestrian detectors.

Screening Lung Diseases Using Cascaded Feature Generation and Selection Strategies.

The global pandemic COVID-19 is still a cause of a health emergency in several parts of the world. Apart from standard testing techniques to identify positive cases, auxiliary tools based on artificial intelligence can help with the identification and containment of the disease. The need for the development of alternative smart diagnostic tools to combat the COVID-19 pandemic has become more urgent. In this study, a smart auxiliary framework based on machine learning (ML) is proposed; it can help medical practitioners in the identification of COVID-19-affected patients, among others with pneumonia and healthy individuals, and can help in monitoring the status of COVID-19 cases using X-ray images. We investigated the application of transfer-learning (TL) networks and various feature-selection techniques for improving the classification accuracy of ML classifiers. Three different TL networks were tested to generate relevant features from images; these TL networks include AlexNet, ResNet101, and SqueezeNet. The generated relevant features were further refined by applying feature-selection methods that include iterative neighborhood component analysis (iNCA), iterative chi-square (iChi2), and iterative maximum relevance-minimum redundancy (iMRMR). Finally, classification was performed using convolutional neural network (CNN), linear discriminant analysis (LDA), and support vector machine (SVM) classifiers. Moreover, the study exploited stationary wavelet (SW) transform to handle the overfitting problem by decomposing each image in the training set up to three levels. Furthermore, it enhanced the dataset, using various operations as data-augmentation techniques, including random rotation, translation, and shear operations. The analysis revealed that the combination of AlexNet, ResNet101, SqueezeNet, iChi2, and SVM was very effective in the classification of X-ray images, producing a classification accuracy of 99.2%. Similarly, AlexNet, ResNet101, and SqueezeNet, along with iChi2 and the proposed CNN network, yielded 99.0% accuracy. The results showed that the cascaded feature generator and selection strategies significantly affected the performance accuracy of the classifier.

COVID-19 in the Age of Artificial Intelligence: A Comprehensive Review.

The recent COVID-19 pandemic, which broke at the end of the year 2019 in Wuhan, China, has infected more than 98.52 million people by today (January 23, 2021) with over 2.11 million deaths across the globe. To combat the growing pandemic on urgent basis, there is need to design effective solutions using new techniques that could exploit recent technology, such as machine learning, deep learning, big data, artificial intelligence, Internet of Things, for identification and tracking of COVID-19 cases in near real time. These technologies have offered inexpensive and rapid solution for proper screening, analyzing, prediction and tracking of COVID-19 positive cases. In this paper, a detailed review of the role of AI as a decisive tool for prognosis, analyze, and tracking the COVID-19 cases is performed. We searched various databases including Google Scholar, IEEE Library, Scopus and Web of Science using a combination of different keywords consisting of COVID-19 and AI. We have identified various applications, where AI can help healthcare practitioners in the process of identification and monitoring of COVID-19 cases. A compact summary of the corona virus cases are first highlighted, followed by the application of AI. Finally, we conclude the paper by highlighting new research directions and discuss the research challenges. Even though scientists and researchers have gathered and exchanged sufficient knowledge over last couple of months, but this structured review also examined technological perspectives while encompassing the medical aspect to help the healthcare practitioners, policymakers, decision makers, policymakers, AI scientists and virologists to quell this infectious COVID-19 pandemic outbreak.

A machine learning-based framework for diagnosis of COVID-19 from chest X-ray images.

Corona virus disease (COVID-19) acknowledged as a pandemic by the WHO and mankind all over the world is vulnerable to this virus. Alternative tools are needed that can help in diagnosis of the coronavirus. Researchers of this article investigated the potential of machine learning methods for automatic diagnosis of corona virus with high accuracy from X-ray images. Two most commonly used classifiers were selected: logistic regression (LR) and convolutional neural networks (CNN). The main reason was to make the system fast and efficient. Moreover, a dimensionality reduction approach was also investigated based on principal component analysis (PCA) to further speed up the learning process and improve the classification accuracy by selecting the highly discriminate features. The deep learning-based methods demand large amount of training samples compared to conventional approaches, yet adequate amount of labelled training samples was not available for COVID-19 X-ray images. Therefore, data augmentation technique using generative adversarial network (GAN) was employed to further increase the training samples and reduce the overfitting problem. We used the online available dataset and incorporated GAN to have 500 X-ray images in total for this study. Both CNN and LR showed encouraging results for COVID-19 patient identification. The LR and CNN models showed 95.2-97.6% overall accuracy without PCA and 97.6-100% with PCA for positive cases identification, respectively.

Presenting the characteristics, smoking versus diabetes, and outcome among patients hospitalized with COVID-19.

METHODS: We designed a cross-sectional, observational follow-up for 284 COVID-19 patients involving healthy patients, smokers, diabetics, and diabetic plus smokers recruited from May 1, 2020 to June 25, 2020. The clinical features, severity, duration, and outcome of the disease were analyzed. RESULTS: Of 284 COVID-19 patients, the median age was 48 years (range, 18-80), and 33.80% were female. Common symptoms included fever (85.56%), shortness of breath (49.65%), cough (45.42%), and headache (40.86%). Patients with more than one comorbidity (diabetes and smoking) presented as severe-critical cases compared to healthy patients, diabetics, and smokers. Smokers presented with a lower rate of death in comparison to diabetic patients and diabetic + smoking, furthermore, smoking was less risky than diabetes. Although the mortality rate was high in patients with smokers compared to healthy patients (4.22%, the hazard ratio [HR], 1.358; 95% confidence interval [CI], 1.542-1.100; p = .014), it was less than in diabetics (7.04%, HR 1.531, 95% CI: 1.668-1.337, p = .000), and diabetic plus smoker (10.00%, HR, 1.659; 95% CI, 1.763-1.510; p = .000). CONCLUSION: Multiple comorbidities are closely related to the severity of COVID-19 disease progression and the higher mortality rate. Smokers presented as mild cases compared to diabetic and diabetic + smoking patients, who presented as severe to critical cases. Although a higher death rate in smokers was seen compared with healthy patients, this was smaller when compared to diabetic and diabetic + smoking patients.

A survey on artificial intelligence approaches in supporting frontline workers and decision makers for the COVID-19 pandemic.

While the world has experience with many different types of infectious diseases, the current crisis related to the spread of COVID-19 has challenged epidemiologists and public health experts alike, leading to a rapid search for, and development of, new and innovative solutions to combat its spread. The transmission of this virus has infected more than 18.92 million people as of August 6, 2020, with over half a million deaths across the globe; the World Health Organization (WHO) has declared this a global pandemic. A multidisciplinary approach needs to be followed for diagnosis, treatment and tracking, especially between medical and computer sciences, so, a common ground is available to facilitate the research work at a faster pace. With this in mind, this survey paper aimed to explore and understand how and which different technological tools and techniques have been used within the context of COVID-19. The primary contribution of this paper is in its collation of the current state-of-the-art technological approaches applied to the context of COVID-19, and doing this in a holistic way, covering multiple disciplines and different perspectives. The analysis is widened by investigating Artificial Intelligence (AI) approaches for the diagnosis, anticipate infection and mortality rate by tracing contacts and targeted drug designing. Moreover, the impact of different kinds of medical data used in diagnosis, prognosis and pandemic analysis is also provided. This review paper covers both medical and technological perspectives to facilitate the virologists, AI researchers and policymakers while in combating the COVID-19 outbreak.

The prevalence of gastrointestinal symptoms among patients with COVID-19 and the effect on the severity of the disease.

Background and Aim: COVID-19 is a new pandemic disease recognized by the World Health Organization. It mainly affects the respiratory system, but it can also affect other systems. The gastrointestinal system has been found to be affected in many patients. This study investigated the COVID-19-related gastrointestinal manifestations and the effect of gastrointestinal involvement on the course and outcome of the disease. Methods: This was a retrospective descriptive study conducted on 140 COVID-19 polymerase chain reaction-positive symptomatic individuals admitted to Al-Shafa Hospital - Medical City Complex in Baghdad, Iraq during the period 2 March 2020 to 12 May 2020. Demographic data and clinical presentation and laboratory data were extracted from the case sheets of the patients and were also obtained from direct communication with the patients, their families, and medical staff. Results: Gastrointestinal (GI) symptoms alone were detected in 23.6% of the patients; 44.3% of the patients presented with only respiratory symptoms, and 32.1% presented with both respiratory and GI symptoms. Patients with only GI symptoms had less severe disease compared with those who had both GI and respiratory symptoms, who had more severe disease with higher mortality. Overall mortality was 8.6%, with no mortality in the GI symptoms alone group. The highest severity and mortality were in patients with both GI and respiratory symptoms (48.39 and 13.33%, respectively). Conclusions: COVID-19-related gastrointestinal symptoms are common, and their presence alone carries a better prognosis, but their presence with respiratory symptoms is associated with higher morbidity and mortality.

The relationship between mean platelet volume and albuminuria in patients with type 2 diabetes mellitus.

BACKGROUND&AIM: Mean platelet volume (MPV) is suggested as a marker of platelet reactivity and tendency for thrombosis and microvascular complications like albuminuria in patients with type 2 DM. We aimed to measure the MPV in patients with type 2 DM and its correlation with albuminuria, body mass index (BMI), duration of DM, hypertension (HTN), stroke, ischemic heart disease (IHD), and HbA1c level. METHODS: A cross sectional study included 100 patients with type 2 DM ≥ 18 y of both genders who were randomly selected from the medical units of Baghdad Teaching Hospital. After taking verbal consents; MPV was measured&correlated with aimed variables. Diabetics with HbA1c ≤ 7% were considered as having adequate control while those with (HbA1c) > 7% as having poor control. Albumin creatinine ratio (ACR) in urine was measured and classified into normal, moderately and severely increased. Odds ratios with 95% CI were calculated and P ≤ 0.05 was considered as statistically significant. RESULTS: The mean MPV was 7.7 fl ±â€¯1.2. Regarding ACR, 42% had normal level, 37% with moderately increased and 21% had severely increased level. Regarding HbA1c, 68% were having poorly controlled DM. Mean platelets' count and MPV were higher in the uncontrolled group with a statistically significant association. There was a statistically significant positive correlation between MPV and albuminuria, duration of DM, HTN, IHD, Stroke, BMI, HbA1c, and platelets count. CONCLUSIONS: The mean MPV was statistically significantly higher in the uncontrolled DM group and there was a statistically significant positive correlation between MPV and albuminuria.

The value of venous blood gas analysis in the diagnosis of diabetic ketoacidosis.

BACKGROUND & AIM: Newer blood gas analyzers have the ability to report electrolyte values and glucose in addition to pH, so this diagnostic process could be condensed in diagnosing diabetic ketoacidosis (DKA). We aimed to assess the accuracy of the venous blood gas (VBG) analysis with electrolytes for diagnosing DKA. METHODS: This study prospectively identified a convenience sample of (60 patients) presented with DKA and tested their VBG and serum electrolytes. The diagnosis of DKA was made according to American Diabetes Association criteria. Serum chemistry electrolyte values were considered to be the criterion standard. Sensitivity and specificity of VBG electrolytes results were compared against this standard. In addition, correlation coefficients for individual electrolytes between VBG electrolytes and laboratory chemistry electrolytes were calculated. RESULTS: Paired VBG and serum chemistry panels were available for 60 patients, only 49 patients were included, In this study; 20% of cases were newly diagnosed diabetes mellitus. The total number of diabetic ketoacidosis was 14 patients (28.5%). The sensitivity and specificity of the VBG and electrolytes for diagnosing DKA was 92.9% (95% confidence interval [CI]=89% to 99%) and 97.1% (95% CI=92% to 100%), respectively. Correlation coefficients between VBG and serum chemistry were 0.91, 0.47, 0.61, 0.65, and 0.58 for blood sugar, sodium, potassium, chloride, and creatinine respectively. CONCLUSIONS: Findings of this study offer preliminary support for the possibility of using VBG sample rather than VBG sample and serum chemistry electrolytes together to rule out diabetic ketoacidosis.