Classification and pattern extraction of incidents: a deep learning-based approach

Classifying or predicting occupational incidents using both structured and unstructured (text) data are an unexplored area of research. Unstructured texts, i.e., incident narratives are often unutilized or underutilized. Besides the explicit information, there exist a large amount of hidden information present in a dataset, which cannot be explored by the traditional machine learning (ML) algorithms. There is a scarcity of studies that reveal the use of deep neural networks (DNNs) in the domain of incident prediction, and its parameter optimization for achieving better prediction power. To address these issues, initially, key terms are extracted from the unstructured texts using LDA-based topic modeling. Then, these key terms are added with the predictor categories to form the feature vector, which is further processed for noise reduction and fed to the adaptive moment estimation (ADAM)-based DNN (i.e., ADNN) for classification, as ADAM is superior to GD, SGD, and RMSProp. To evaluate the effectiveness of our proposed method, a comparative study has been conducted using some state-of-the-arts on five benchmark datasets. Moreover, a case study of an integrated steel plant in India has been demonstrated for the validation of the proposed model. Experimental results reveal that ADNN produces superior performance than others in terms of accuracy. Therefore, the present study offers a robust methodological guide that enables us to handle the issues of unstructured data and hidden information for developing a predictive model.

Future Trends in Data Science

With progression in technology, an enormous magnitude of information being collected from digital users by various businesses and organizations, has resulted in formation of huge data repositories commonly known by the term Big data. Data mining is a tool used for extracting hidden information from these vast databases to identify unique patterns and rules. The present paper aims to provide a detailed description of the importance of big data in today’s times, its characteristics, how data mining plays an important role in big data, why it is a necessity in today’s times, the process of data mining and functionalities it performs, data mining techniques such as classification, clustering etc. that help in finding the patterns to decide upon the future trends in businesses and applications of the same in various fields. The paper also discusses the important role of data mining in Business Intelligence (BI) and various industries, to identify unique patterns and obtain results from the data along with the second half of the paper focusing on further exploring the challenges that are faced in big data and tools used, the applications and upcoming trends in data science and lastly, the scope and importance of data science in the future.

INDIRECT INFORMATION HIDING TECHNOLOGY ON A MULTIADIC BASIS

It is shown that the current direction of increasing the safety of information resources when transmitting information in info-communication systems is the use of methods of steganographic instruction in video imagery. The effectiveness of such methods is significantly increased when used in a complex of methods of concealment, which are based on the principles of inconsistent and cosmic communication. At the same time, existing methods of steganographic are used in the process of insertion of information mainly only laws, empty features of visual perception of video images. So, it is justified that the scientific and applied problem, which is to increase the density of embedded messages in the video container with a given level of their reliability, is relevant. The solution of this problem is based on the solution of the contradiction, which concerns the fact that increasing the density of embedded data leads to a decrease in the bit rate of the video container, steganalysis stability, reliability of special information, and video container. Therefore, the research aims to develop a methodology for the steganographic embedding of information, taking into account the regularities of the video container, which are generated by its structural and structural-statistical features. The solution to the posed problem of applying steganographic transformations is proposed to be realised by methods of indirectly embedding parts of the hidden message in certain conditions or functional relationships. The possibility of creating steganographic transformations regarding the indirect embedding and extraction of hidden information in a multiadic basis by modifying the underlying basis system within an admissible set is demonstrated. It is shown that the multiadic system, which is created in the spectral space of DCT transforms, has the potential to form a set of admissible modifications of basis systems.

A Riemannian Newton trust-region method for fitting Gaussian mixture models

Gaussian Mixture Models are a powerful tool in Data Science and Statistics that are mainly used for clustering and density approximation. The task of estimating the model parameters is in practice often solved by the expectation maximization (EM) algorithm which has its benefits in its simplicity and low per-iteration costs. However, the EM converges slowly if there is a large share of hidden information or overlapping clusters. Recent advances in Manifold Optimization for Gaussian Mixture Models have gained increasing interest. We introduce an explicit formula for the Riemannian Hessian for Gaussian Mixture Models. On top, we propose a new Riemannian Newton Trust-Region method which outperforms current approaches both in terms of runtime and number of iterations. We apply our method on clustering problems and density approximation tasks. Our method is very powerful for data with a large share of hidden information compared to existing methods.

Steganographic method based on hidden messages embedding into Bezier curves of SVG images

The description of the steganographic method for embedding the digital watermark into image vector files of the SVG format is given. Vector images in SVG format can include elements based on Bezier curves. The proposed steganographic method is based on the splitting of cubic Bezier curves. Embedding hidden information involves splitting cubic Bezier curves according to the digital watermark given as numerical sequence. Algorithms of direct and reverse steganographic transformation are considered for proving the authenticity and integrity of a digital vector image. The StegoSVG library has been developed to implement forward and reverse steganographic transformations. The developed desktop application that implements the method is briefly described.

Optimal Image Steganography Content Destruction Techniques

The paper presents two approaches for destroying steganogrphy content in an image. The first is the overwriting approach where a random data can be written again over steganographic images whereas the second approach is the denoising approach. With the second approach two kinds of destruction techniques have been adopted these are filtering and discrete wavelet techniques. These two approaches have been simulated and evaluated over two types of hiding techniques, Least Significant Bit LSB technique and Discrete Cosine Transform DCT technique. The results of the simulation show the capability of both approaches to destroy the hidden information without any alteration to the cover image except the denoising approach enhance the PSNR in any received image even without hidden information by an average of 4dB.

A Novel Technique for Image Steganalysis Based on Separable Convolution and Adversarial Mechanism

Image steganalysis is a technique for detecting the presence of hidden information in images, which has profound significance for maintaining cyberspace security. In recent years, various deep steganalysis networks have been proposed in academia, and have achieved good detection performance. Although convolutional neural networks (CNNs) can effectively extract the features describing the image content, the difficulty lies in extracting the subtle features that describe the existence of hidden information. Considering this concern, this paper introduces separable convolution and adversarial mechanism, and proposes a new network structure that effectively solves the problem. The separable convolution maximizes the residual information by utilizing its channel correlation. The adversarial mechanism makes the generator extract more content features to mislead the discriminator, thus separating more steganographic features. We conducted experiments on BOSSBase1.01 and BOWS2 to detect various adaptive steganography algorithms. The experimental results demonstrate that our method extracts the steganographic features effectively. The separable convolution increases the signal-to-noise ratio, maximizes the channel correlation of residuals, and improves efficiency. The adversarial mechanism can separate more steganographic features, effectively improving the performance. Compared with the traditional steganalysis methods based on deep learning, our method shows obvious improvements in both detection performance and training efficiency.