Search

In the past few years, with the development of information technology and the focus on information security, many studies have gradually been aimed at data hiding technology. The embedding and extraction algorithms are mainly used by the technology to hide the data that requires secret transmission into a multimedia carrier so that the data transmission cannot be realized to achieve secure communication. Among them, reversible data hiding (RDH) is a technology for the applications that demand the secret data extraction as well as the original carrier recovery without distortion, such as remote medical diagnosis or military secret transmission. In this work, we hypothesize that the RDH performance can be enhanced by a more accurate pixel value predictor. We propose a new RDH scheme of prediction-error expansion (PEE) based on a multilayer perceptron, which is an extensively used artificial neural network in plenty of applications. The scheme utilizes the correlation between image pixel values and their adjacent pixels to obtain a well-trained multilayer perceptron so that we are capable of achieving more accurate pixel prediction results. Our data mapping method based on the three-dimensional prediction-error histogram modification uses all eight octants in the three-dimensional space for secret data embedding. The experimental results of our RDH scheme show that the embedding capacity greatly increases and the image quality is still well maintained.

Financial time series are often considered to be difficult to model and unlikely to predict. In this study. we assume that financial time series are based on a stochastic series generated by a Markov decision process. Based on this assumption. we investigate two problems related to the identification of the price time series of financial instruments. We try to distinguish the real price-volume time series from the artificial one. First, we investigate whether there is any machine learning model that can distinguish between real price-volume time series and those with time horizon reversed. Then, we investigate whether there is any machine learning model that can distinguish the price-volume time series from the real one when they are subjected to random manipulations of different proportions. The data we use are the daily prices and trading volumes of six U,S. stocks and one crypto-currency BTOUSD. We apply Long-Short Term Memory (LSTM) as the main machine learning model for the binary classification due to its success in fitting time series data. Based on the experimental results. we give positive answers to the above two questions. Our results also partially support the conjecture that the dynamics of a financial time series are driven by an underlying Markov decision processes. [ABSTRACT FROM AUTHOR]

Background: Crop plants such as rice, maize and sorghum play economically-important roles as main sources of food, fuel, and animal feed. However, current genome annotations of crop plants still suffer false-positive predictions; a more comprehensive registry of alternative splicing (AS) events is also in demand. Comparative genomics of crop plants is largely unexplored. Results: We performed a large-scale comparative analysis (ExonFinder) of the expressed sequence tag (EST) library from nine grass plants against three crop genomes (rice, maize, and sorghum) and identified 2,879 previously-unannotated exons (i.e., novel exons) in the three crops. We validated 81% of the tested exons by RT-PCR-sequencing, supporting the effectiveness of our in silico strategy. Evolutionary analysis reveals that the novel exons, comparing with their flanking annotated ones, are generally under weaker selection pressure at the protein level, but under stronger pressure at the RNA level, suggesting that most of the novel exons also represent novel alternatively spliced variants (ASVs). However, we also observed the consistency of evolutionary rates between certain novel exons and their flanking exons, which provided further evidence of their co-occurrence in the transcripts, suggesting that previously-annotated isoforms might be subject to erroneous predictions. Our validation showed that 54% of the tested genes expressed the newly-identified isoforms that contained the novel exons, rather than the previously-annotated isoforms that excluded them. The consistent results were steadily observed across cultivated (Oryza sativa and O. glaberrima) and wild (O. rufipogon and O. nivara) rice species, asserting the necessity of our curation of the crop genome annotations. Our comparative analyses also inferred the common ancestral transcriptome of grass plants and gain- and loss-of-ASV events. Conclusions: We have reannotated the rice, maize, and sorghum genomes, and showed that evolutionary rates might serve as an indicator for determining whether the identified exons were alternatively spliced. This study not only presents an effective in silico strategy for the improvement of plant annotations, but also provides further insights into the role of AS events in the evolution and domestication of crop plants. ExonFinder and the novel exons/ASVs identified are publicly accessible at http://exonfinder.sourceforge.net/. [ABSTRACT FROM AUTHOR]