Computer-aided COVID-19 diagnosis and a comparison of deep learners using augmented CXRs

Background: Coronavirus Disease 2019 (COVID-19) is contagious, producing respiratory tract infection, caused by a newly discovered coronavirus. Its death toll is too high, and early diagnosis is the main problem nowadays. Infected people show a variety of symptoms such as fatigue, fever, tastelessness, dry cough, etc. Some other symptoms may also be manifested by radiographic visual identification. Therefore, Chest X-Rays (CXR) play a key role in the diagnosis of COVID-19. Methods: In this study, we use Chest X-Rays images to develop a computer-aided diagnosis (CAD) of the disease. These images are used to train two deep networks, the Convolution Neural Network (CNN), and the Long Short-Term Memory Network (LSTM) which is an artificial Recurrent Neural Network (RNN). The proposed study involves three phases. First, the CNN model is trained on raw CXR images. Next, it is trained on pre-processed CXR images and finally enhanced CXR images are used for deep network CNN training. Geometric transformations, color transformations, image enhancement, and noise injection techniques are used for augmentation. From augmentation, we get 3,220 augmented CXRs as training datasets. In the final phase, CNN is used to extract the features of CXR imagery that are fed to the LSTM model. The performance of the four trained models is evaluated by the evaluation techniques of different models, including accuracy, specificity, sensitivity, false-positive rate, and receiver operating characteristic (ROC) curve. Results: We compare our results with other benchmark CNN models. Our proposed CNN-LSTM model gives superior accuracy (99.02%) than the other state-of-the-art models. Our method to get improved input, helped the CNN model to produce a very high true positive rate (TPR 1) and no false-negative result whereas false negative was a major problem while using Raw CXR images. Conclusions: We conclude after performing different experiments that some image pre-processing and augmentation, remarkably improves the results of CNN-based models. It will help a better early detection of the disease that will eventually reduce the mortality rate of COVID.

PF : Website Fingerprinting Attack Using Probabilistic Topic Model

Website fingerprinting (WFP) attack enables identifying the websites a user is browsing even under the protection of privacy-enhancing technologies (PETs). Previous studies demonstrate that most machine-learning attacks need multiple types of features as input, thus inducing tremendous feature engineering work. However, we show the other alternative. That is, we present Probabilistic Fingerprinting (PF), a new website fingerprinting attack that merely leverages one type of features. They are produced by using a mathematical model PWFP that combines a probabilistic topic model with WFP for the first time, due to a finding that a plain text and the sequence file generated from a traffic instance are essentially the same. Experimental results show that the proposed new features are more distinguishing than the existing features. In a closed-world setting, PF attains a better accuracy performance (99.79% at most) than prior attacks on various datasets gathered in the scenarios of Shadowsocks, SSH, and TLS, respectively. Besides, even when the number of training instances drops to as few as 4, PF still reaches an accuracy of above 90%. In the more realistic open-world setting, PF attains a high true positive rate (TPR) and Bayes detection rate (BDR), and a low false positive rate (FPR) in all evaluations, which outperforms the other attacks. These results highlight that it is meaningful and possible to explore new features to improve the accuracy of WFP attacks.

Support Vector Machine with Information Gain Based Classification for Credit Card Fraud Detection System

In the credit card industry, fraud is one of the major issues to handle as sometimes the genuine credit card customers may get misclassified as fraudulent and vice-versa. Several detection systems have been developed but the complexity of these systems along with accuracy and precision limits its usefulness in fraud detection applications. In this paper, a new methodology Support Vector Machine with Information Gain (SVMIG) to improve the accuracy of identifying the fraudulent transactions with high true positive rate for the detection of frauds in credit card is proposed. In SVMIG, the min-max normalization is used to normalize the attributes and the feature set of the attributes are reduced by using information gain based attribute selection. Further, the Apriori algorithm is used to select the frequent attribute set and to reduce the candidate’s itemset size while detecting fraud. The experimental results suggest that the proposed algorithm achieves 94.102% higher accuracy on the standard dataset compared to the existing Bayesian and random forest based approaches for a large sample size in dealing with legal and fraudulent transactions

Evaluating GAN-Based Image Augmentation for Threat Detection in Large-Scale Xray Security Images

The inherent imbalance in the data distribution of X-ray security images is one of the most challenging aspects of computer vision algorithms applied in this domain. Most of the prior studies in this field have ignored this aspect, limiting their application in the practical setting. This paper investigates the effect of employing Generative Adversarial Networks (GAN)-based image augmentation, or image synthesis, in improving the performance of computer vision algorithms on an imbalanced X-ray dataset. We used Deep Convolutional GAN (DCGAN) to generate new X-ray images of threat objects and Cycle-GAN to translate camera images of threat objects to X-ray images. We synthesized new X-ray security images by combining threat objects with background X-ray images, which are used to augment the dataset. Then, we trained various Faster (Region Based Convolutional Neural Network) R-CNN models using different augmentation approaches and evaluated their performance on a large-scale practical X-ray image dataset. Experiment results show that image synthesis is an effective approach to combating the imbalance problem by significantly reducing the false-positive rate (FPR) by up to 15.3%. The FPR is further improved by up to 19.9% by combining image synthesis and conventional image augmentation. Meanwhile, a relatively high true positive rate (TPR) of about 94% was maintained regardless of the augmentation method used.

Data Empowerment of Decision-Makers in an Era of a Pandemic: Intersection of “Classic” and Artificial Intelligence in the Service of Medicine (Preprint)

BACKGROUND The COVID-19 outbreak required prompt action by health authorities around the world in response to a novel threat. With enormous amounts of information originating in sources with uncertain degree of validation and accuracy, it is essential to provide executive-level decision-makers with the most actionable, pertinent, and updated data analysis to enable them to adapt their strategy swiftly and competently. OBJECTIVE We report here the origination of a COVID-19 dedicated response in the Israel Defense Forces with the assembly of an operational Data Center for the Campaign against Coronavirus. METHODS Spearheaded by directors with clinical, operational, and data analytics orientation, a multidisciplinary team utilized existing and newly developed platforms to collect and analyze large amounts of information on an individual level in the context of SARS-CoV-2 contraction and infection. RESULTS Nearly 300,000 responses to daily questionnaires were recorded and were merged with other data sets to form a unified data lake. By using basic as well as advanced analytic tools ranging from simple aggregation and display of trends to data science application, we provided commanders and clinicians with access to trusted, accurate, and personalized information and tools that were designed to foster operational changes and mitigate the propagation of the pandemic. The developed tools aided in the in the identification of high-risk individuals for severe disease and resulted in a 30% decline in their attendance to their units. Moreover, the queue for laboratory examination for COVID-19 was optimized using a predictive model and resulted in a high true-positive rate of 20%, which is more than twice as high as the baseline rate (2.28%, 95% CI 1.63%-3.19%). CONCLUSIONS In times of ambiguity and uncertainty, along with an unprecedented flux of information, health organizations may find multidisciplinary teams working to provide intelligence from diverse and rich data a key factor in providing executives relevant and actionable support for decision-making.

Cyber Situation Comprehension for IoT Systems based on APT Alerts and Logs Correlation

With the emergence of the Advanced Persistent Threat (APT) attacks, many Internet of Things (IoT) systems have faced large numbers of potential threats with the characteristics of concealment, permeability, and pertinence. However, existing methods and technologies cannot provide comprehensive and prompt recognition of latent APT attack activities in the IoT systems. To address this problem, we propose an APT Alerts and Logs Correlation Method, named APTALCM and a framework of deploying APTALCM on the IoT system, where an edge computing architecture was used to achieve cyber situation comprehension without too much data transmission cost. Specifically, we firstly present a cyber situation ontology for modeling the concepts and properties to formalize APT attack activities in the IoT systems. Then, we introduce a cyber situation instance similarity measurement method based on the SimRank mechanism for APT alerts and logs Correlation. Combining with instance similarity, we further propose an APT alert instances correlation method to reconstruct APT attack scenarios and an APT log instances correlation method to detect log instance communities. Through the coalescence of these methods, APTALCM can accomplish the cyber situation comprehension effectively by recognizing the APT attack intentions in the IoT systems. The exhaustive experimental results demonstrate that the two kernel modules, i.e., Alert Instance Correlation Module (AICM) and Log Instance Correlation Module (LICM) in our APTALCM, can achieve both high true-positive rate and low false-positive rate.