Search

With the rapid growth of the scale of social media information, it is getting more and more difficult for social media to detect fake news by using manual review. The spread of fake news may misguide the public, cause social panic, and even lead to violence, which could be avoided by using early detection technology to timely identify fake news on social media. Since fake news is often deliberately designed to attract attention, it is difficult for mongers to provide pictures that match the fabricated stories. However, most of existing multi-modal solutions only use the information of images and text, but do not take into account the correlation between them, which limits the effect of model detection effect. In this paper, we proposed a novel Fake News Detection Framework (FNDF) in Sina Weibo based on hybrid feature fusion method. Specifically, a total of 16 features from text, images and users are extracted to distinguish fake news. Moreover, we extract image-text correlation between text and images. Then, a new deep neural network model called Fake News Net (FNN) is built to implement the detection of fake news, which makes use of a pre-training model named Enhanced Representation through Knowledge Integration (ERNIE), a convolution network named Visual Geometry Group (VGG-19), and a Back Propagation (BP) neural network. We validated it on a publicly available dataset, which shows that the F1-score of the FNN model reaches 95.90%, outperforming the state-of-the-art methods by 3.08%. The ablation experiment also proves that the correlation between images and texts increased the F1-score of the model by 3.15%. And the data balancing experiments show that our model still keeps outstanding detection performance when there is less fake news compared to real news, which is closer to the real-world scenario. The research in this paper provides theoretical methods and research ideas for the detection of fake news on social networks. • A framework FNDF extracts a total of 16 features from text, images and users respectively. • The semantic features of text in images are deeply mined. • Based on SiameseNet, this paper proposes a feature of image-text correlation. • A novel deep neural network called FNN is built for hybrid feature fusion. • The results demonstrate that our method outperforms the state-of-the-art models. [ABSTRACT FROM AUTHOR]

In this paper, we show a deep learning model for bot detection, named as DeBot, for industrial network traffic. DeBot uses a novel Cascade Forward Back Propagation Neural Network (CFBPNN) model with a subset of features using the Correlation-based Feature Selection (CFS) technique. A time series-based Nonlinear Auto-regressive Network with eXogenous inputs (NARX) technique analyzes the factors having a higher impact on the target variable and predict the behavioral pattern. To the best of our knowledge, we pioneer the use of optimal feature selection and integration with the cascading model of deep learning in bot detection of IIoTs. We conduct a thorough set of experiments on five popular bot datasets: NF-UNSW-NB15, NF-ToN-IoT, NF-BoT-IoT, NF-CSE-CIC-IDS2018, and ToN-IoT-Windows. We compare CFBPNN with other existing neural network models. We observe that CFBPNN in DeBot shows 100% accuracy in all the datasets with subset evaluation and obtains optimum F1-score and zero precision. [Display omitted] • We address the multi-layered network model with IIoT features to enable bot attack detection. • Our DeBot model evaluates the subset with optimal features with high impact on attack class and predict the risk factor. • We pioneer the implementation of time series-based Nonlinear Auto-Regressive eXogenous (NARX) model to predict the risk in the specified time gap. • We introduce a new cascading model with recurrent feature to preserve the relationship between input and output variables. [ABSTRACT FROM AUTHOR]

Over the last decade, the ever increasing world-wide demand for early detection of breast cancer at many screening sites and hospitals has resulted in the need of new research avenues. According to the World Health Organization (WHO), an early detection of cancer greatly increases the chances of taking the right decision on a successful treatment plan. The Computer-Aided Diagnosis (CAD) systems are applied widely in the detection and differential diagnosis of many different kinds of abnormalities. Therefore, improving the accuracy of a CAD system has become one of the major research areas. In this paper, a CAD scheme for detection of breast cancer has been developed using deep belief network unsupervised path followed by back propagation supervised path. The construction is back-propagation neural network with Liebenberg Marquardt learning function while weights are initialized from the deep belief network path (DBN-NN). Our technique was tested on the Wisconsin Breast Cancer Dataset (WBCD). The classifier complex gives an accuracy of 99.68% indicating promising results over previously-published studies. The proposed system provides an effective classification model for breast cancer. In addition, we examined the architecture at several train-test partitions. [ABSTRACT FROM AUTHOR]

• Improve speed of learning process. • Decreases the computational time. • To reduce the complexity of a model and makes it simple and easier to interpret. • To improve the accuracy of a model and reduce over fitting. The Neural Network has a significant impact in developing predictive models in a wide range of applications. In this paper, a neuro-fuzzy prediction model is developed depending on improving the performance of the traditional artificial neural networks using Adaptive Momentum Optimizer. This optimizer simulates the behavior of the International Trade Analysis in the agriculture industry, and this method is used to determine the optimal parameters of artificial neural networks. The proposed model is compared with the existing models such as Support Vector Machine, Random Forest, Decision Tree and traditional Artificial Neural Network models. To examine the forecasting performance of the proposed approach, agriculture datasets is used. The performance of the models was assessed using different performance evaluation criteria and the empirical results show that the back propagation neural network with Adam optimizer attains favorable prediction accuracy of 96.78%, and a better convergence rate. Compared to other benchmark algorithms, the proposed algorithm performs better, and the result validates the effectiveness of the back propagation with Adam optimizer for Natural Language Processing. Image, graphical abstract [ABSTRACT FROM AUTHOR]

Diabetic retinopathy (DR) is the most common cause of blindness in middle-age subjects and low DR screening rates demonstrates the need for an automated image assessment system, which can benefit from the development of deep learning techniques. Therefore, the effective classification performance is significant in favor of the referable DR identification task. In this paper, we propose a new strategy, which applies multiple weighted paths into convolutional neural network, called the WP-CNN, motivated by the ensemble learning. In WP-CNN, multiple path weight coefficients are optimized by back propagation, and the output features are averaged for redundancy reduction and fast convergence. The experiment results show that with the efficient training convergence rate WP-CNN achieves an accuracy of 94.23% with sensitivity of 90.94%, specificity of 95.74%, an area under the receiver operating curve of 0.9823 and F1-score of 0.9087. By taking full advantage of the multipath mechanism, the proposed WP-CNN is shown to be accurate and effective for referable DR identification compared to the state-of-art algorithms. [ABSTRACT FROM AUTHOR]