Search

The world of information technology is more than ever being flooded with huge amounts of data, nearly 2.5 quintillion bytes every day. This large stream of data is called big data, and the amount is increasing each day. This research uses a technique called sampling, which selects a representative subset of the data points, manipulates and analyzes this subset to identify patterns and trends in the larger dataset being examined, and finally, creates models. Sampling uses a small proportion of the original data for analysis and model training, so that it is relatively faster while maintaining data integrity and achieving accurate results. Two deep neural networks, AlexNet and DenseNet, were used in this research to test two sampling techniques, namely sampling with replacement and reservoir sampling. The dataset used for this research was divided into three classes: acceptable, flagged as easy, and flagged as hard. The base models were trained with the whole dataset, whereas the other models were trained on 50% of the original dataset. There were four combinations of model and sampling technique. The F-measure for the AlexNet model was 0.807 while that for the DenseNet model was 0.808. Combination 1 was the AlexNet model and sampling with replacement, achieving an average F-measure of 0.8852. Combination 3 was the AlexNet model and reservoir sampling. It had an average F-measure of 0.8545. Combination 2 was the DenseNet model and sampling with replacement, achieving an average F-measure of 0.8017. Finally, combination 4 was the DenseNet model and reservoir sampling. It had an average F-measure of 0.8111. Overall, we conclude that both models trained on a sampled dataset gave equal or better results compared to the base models, which used the whole dataset. [ABSTRACT FROM AUTHOR]

Corona Virus (COVID-19) is a novel virus that crossed an animalhuman barrier and emerged in Wuhan, China. Until now it has affected more than 119 million people. Detection of COVID-19 is a critical task and due to a large number of patients, a shortage of doctors has occurred for its detection. In this paper, a model has been suggested that not only detects the COVID-19 using X-ray and CT-Scan images but also shows the affected areas. Three classes have been defined; COVID-19, normal, and Pneumonia for X-ray images. For CT-Scan images, 2 classes have been defined COVID-19 and non-COVID-19. For classification purposes, pre-trained models like ResNet50, VGG-16, and VGG19 have been used with some tuning. For detecting the affected areas Gradient-weighted Class Activation Mapping (GradCam) has been used. As the X-rays and ct images are taken at different intensities, so the contrast limited adaptive histogram equalization (CLAHE) has been applied to see the effect on the training of the models. As a result of these experiments, we achieved a maximum validation accuracy of 88.10% with a training accuracy of 88.48% for CT-Scan images using the ResNet50 model. While for X-ray images we achieved a maximum validation accuracy of 97.31% with a training accuracy of 95.64% using the VGG16 model. [ABSTRACT FROM AUTHOR]

While the internet has a lot of positive impact on society, there are negative components. Accessible to everyone through online platforms, pornography is, inducing psychological and health related issues among people of all ages. While a difficult task, detecting pornography can be the important step in determining the porn and adult content in a video. In this paper, an architecture is proposed which yielded high scores for both training and testing. This dataset was produced from 190 videos, yielding more than 19 h of videos. The main sources for the content were from YouTube, movies, torrent, and websites that hosts both pornographic and non-pornographic contents. The videos were from different ethnicities and skin color which ensures the models can detect any kind of video. A VGG16, Inception V3 and Resnet 50 models were initially trained to detect these pornographic images but failed to achieve a high testing accuracy with accuracies of 0.49, 0.49 and 0.78 respectively. Finally, utilizing transfer learning, a convolutional neural network was designed and yielded an accuracy of 0.98. [ABSTRACT FROM AUTHOR]

• A taxonomy discussing application execution strategies in fog computing. • A comprehensive discussion about components of application execution in fog computing. • Critical analysis providing in detail information about key aspects of application execution strategies. • Identifying research gaps and highlight new research directions which needs to be addressed in the future. With tremendous advancements in smart phone industry and IoT devices, edge computing has emerged to provide computational services at edge of the network. As a result, applications can be executed in a distributive manner to meet the latency requirements of applications. Despite these advancements, these devices are still considered to have limited energy, memory and computational resources compared to stationary standalone devices. Mobile edge computing extends mobile cloud computing close to end-users, decreasing latency and bandwidth utilisation by offloading tasks to edge servers. Fog computing places nodes between cloud and edge servers. A challenging approach in these paradigms is establishing offloading decision to edge/fog server, and distributed application execution at run time for heterogeneous devices. This paper reviews execution of resource-intensive tasks on mobile devices in distributed frameworks. The objective is to identify research gaps and highlight new research directions that can be pursued in future. Application execution involves application partitioning, task allocation, task execution and task resumption. In this paper, we propose a separate taxonomy for each step in application execution, reviews state-of-the-art techniques, and analyses critical aspects of application execution in a distributed manner. It further investigates similarities and differences among these techniques based on each step of application execution. [ABSTRACT FROM AUTHOR]

Data available in software engineering for many applications contains variability and it is not possible to say which variable helps in the process of the prediction. Most of the work present in software defect prediction is focused on the selection of best prediction techniques. For this purpose, deep learning and ensemble models have shown promising results. In contrast, there are very few researches that deals with cleaning the training data and selection of best parameter values from the data. Sometimes data available for training the models have high variability and this variability may cause a decrease in model accuracy. To deal with this problem we used the Akaike information criterion (AIC) and the Bayesian information criterion (BIC) for selection of the best variables to train the model. A simple ANN model with one input, one output and two hidden layers was used for the training instead of a very deep and complex model. AIC and BIC values are calculated and combination for minimum AIC and BIC values to be selected for the best model. At first, variables were narrowed down to a smaller number using correlation values. Then subsets for all the possible variable combinations were formed. In the end, an artificial neural network (ANN) model was trained for each subset and the best model was selected on the basis of the smallest AIC and BIC value. It was found that combination of only two variables' ns and entropy are best for software defect prediction as it gives minimum AIC and BIC values. While, nm and npt is the worst combination and gives maximum AIC and BIC values. [ABSTRACT FROM AUTHOR]

High-speed networks are utilized to satisfy user demands by using cloud and edge services. Due to the heterogeneous nature of these networks, security, trust, and privacy are the significant challenges for these networks. These networks are vulnerable to various security threats, lack of trustworthy devices, and user privacy concerns due to architectural complexities, diversity of protocols, and dynamic network topologies. This Systematic Literature Review (SLR) explores these networks in terms of technologies, edge and cloud services, security, trust and privacy concerns. Torress-Carrion methodology is used as a guideline to conduct this review to find the recent security, trust and privacy concerns. The attacks related to each area and their solutions are discussed to evaluate their strengths and weaknesses. The various existing technologies explore like Blockchain, encryption, hashing, and fuzzy logic. In addition, the trust evaluation and user privacy provision techniques are also discuss. This SLR also explores the methods designed for different communication layers against the various multilingual passive/active attacks like Sybil, Denial of Service (DoS), Distributed Denial of Service (DDoS), and Man in the Middle (MITM). This SLR will provide a direction to new researchers in the field of security, trust, and privacy to design more efficient and effective solutions to deal with new security challenges. [ABSTRACT FROM AUTHOR]

The 2019 novel coronavirus (COVID-19) originating from China, has spread rapidly among people living in other countries. According to the World Health Organization (WHO), by the end of January, more than 104 million people have been affected by COVID-19, including more than 2 million deaths. The number of COVID-19 test kits available in hospitals is reduced due to the increase in regular cases. Therefore, an automatic detection system should be introduced as a fast, alternative diagnostic to prevent COVID-19 from spreading among humans. For this purpose, three different BiT models: DenseNet, InceptionV3, and Inception-ResNetV4 have been proposed in this analysis for the diagnosis of patients infected with coronavirus pneumonia using X-ray radiographs in the chest. These three models give and examine Receiver Operating Characteristic (ROC) analyses and uncertainty matrices, using 5-fold cross-validation. We have performed the simulations which have visualized that the pre-trained DenseNet model has the best classification efficiency with 92% among two other models proposed (83.47% accuracy for inception V3 and 85.57% accuracy for Inception-ResNetV4). • COVID-19 prediction using chest X-ray images. • The manual method i.e. PCR is time-consuming and high costs. • A novel automated image-based technique DenseNet and BiTModels like R101x1, which segment and identify Covid-19 patient x-ray. • Covid-19 normal and affected patient data is used. • Comparing with other models, training and testing accuracy, the R101x1 has an average accuracy, i.e., 91% in the Covid-19 class Prediction. [ABSTRACT FROM AUTHOR]

Background: COVID-19 has spread very rapidly, and it is important to build a system that can detect it in order to help an overwhelmed health care system. Many research studies on chest diseases rely on the strengths of deep learning techniques. Although some of these studies used state-of-the-art techniques and were able to deliver promising results, these techniques are not very useful if they can detect only one type of disease without detecting the others. Objective: The main objective of this study was to achieve a fast and more accurate diagnosis of COVID-19. This study proposes a diagnostic technique that classifies COVID-19 x-ray images from normal x-ray images and those specific to 14 other chest diseases. Methods: In this paper, we propose a novel, multilevel pipeline, based on deep learning models, to detect COVID-19 along with other chest diseases based on x-ray images. This pipeline reduces the burden of a single network to classify a large number of classes. The deep learning models used in this study were pretrained on the ImageNet dataset, and transfer learning was used for fast training. The lungs and heart were segmented from the whole x-ray images and passed onto the first classifier that checks whether the x-ray is normal, COVID-19 affected, or characteristic of another chest disease. If it is neither a COVID-19 x-ray image nor a normal one, then the second classifier comes into action and classifies the image as one of the other 14 diseases. Results: We show how our model uses state-of-the-art deep neural networks to achieve classification accuracy for COVID-19 along with 14 other chest diseases and normal cases based on x-ray images, which is competitive with currently used state-of-the-art models. Due to the lack of data in some classes such as COVID-19, we applied 10-fold cross-validation through the ResNet50 model. Our classification technique thus achieved an average training accuracy of 96.04% and test accuracy of 92.52% for the first level of classification (ie, 3 classes). For the second level of classification (ie, 14 classes), our technique achieved a maximum training accuracy of 88.52% and test accuracy of 66.634% by using ResNet50. We also found that when all the 16 classes were classified at once, the overall accuracy for COVID-19 detection decreased, which in the case of ResNet50 was 88.92% for training data and 71.905% for test data. Conclusions: Our proposed pipeline can detect COVID-19 with a higher accuracy along with detecting 14 other chest diseases based on x-ray images. This is achieved by dividing the classification task into multiple steps rather than classifying them collectively. [ABSTRACT FROM AUTHOR]