Determining the price movement of stocks is a challenging problem to solve because of factors such as industry performance, economic variables, investor sentiment, company news, company performance, and social media sentiment. People can predict the price movement of stocks by applying machine learning algorithms on information contained in historical data, stock candlestick-chart data, and social-media data. However, it is hard to predict stock movement based on a single classifier. In this study, we proposed a multichannel collaborative network by incorporating candlestick-chart and social-media data for stock trend predictions. We first extracted the social media sentiment features using the Natural Language Toolkit and sentiment analysis data from Twitter. We then transformed the stock’s historical time series data into a candlestick chart to elucidate patterns in the stock’s movement. Finally, we integrated the stock’s sentiment features and its candlestick chart to predict the stock price movement over 4-, 6-, 8-, and 10-day time periods. Our collaborative network consisted of two branches: the first branch contained a one-dimensional convolutional neural network (CNN) performing sentiment classification. The second branch included a two-dimensional (2D) CNN performing image classifications based on 2D candlestick chart data. We evaluated our model for five high-demand stocks (Apple, Tesla, IBM, Amazon, and Google) and determined that our collaborative network achieved promising results and compared favorably against single-network models using either sentiment data or candlestick charts alone. The proposed method obtained the most favorable performance with 75.38% accuracy for Apple stock. We also found that the stock price prediction achieved more favorable performance over longer periods of time compared with shorter periods of time.

S-sulfenylation (S-sulphenylation, or sulfenic acid), the covalent attachment of S-hydroxyl (–SOH) to cysteine thiol, plays a significant role in redox regulation of protein functions. Although sulfenic acid is transient and labile, most of its physiological activities occur under control of S-hydroxylation. Therefore, discriminating the substrate site of S-sulfenylated proteins is an essential task in computational biology for the furtherance of protein structures and functions. Research into S-sulfenylated protein is currently very limited, and no dedicated tools are available for the computational identification of SOH sites. Given a total of 1096 experimentally verified S-sulfenylated proteins from humans, this study carries out a bioinformatics investigation on SOH sites based on amino acid composition and solvent-accessible surface area. A TwoSampleLogo indicates that the positively and negatively charged amino acids flanking the SOH sites may impact the formulation of S-sulfenylation in closed three-dimensional environments. In addition, the substrate motifs of SOH sites are studied using the maximal dependence decomposition (MDD). Based on the concept of binary classification between SOH and non-SOH sites, Support vector machine (SVM) is applied to learn the predictive model from MDD-identified substrate motifs. According to the evaluation results of 5-fold cross-validation, the integrated SVM model learned from substrate motifs yields an average accuracy of 0.87, significantly improving the prediction of SOH sites. Furthermore, the integrated SVM model also effectively improves the predictive performance in an independent testing set. Finally, the integrated SVM model is applied to implement an effective web resource, named MDD-SOH, to identify SOH sites with their corresponding substrate motifs. Availability and implementation: The MDD-SOH is now freely available to all interested users at http://csb.cse.yzu.edu.tw/MDDSOH/. All of the data set used in this work is also available for download in the website. Supplementary information: Supplementary data are available at Bioinformatics online. Contact:francis@saturn.yzu.edu.tw

Generating a realistic human class image from a sketch is a unique and challenging problem considering that the human body has a complex structure that must be preserved. Additionally, input sketches often lack important details that are crucial in the generation process, hence making the problem more complicated. In this article, we present an effective method for synthesizing realistic images from human sketches. Our framework incorporates human poses corresponding to locations of key semantic components (e.g., arm, eyes, nose), seeing that its a strong prior for generating human class images. Our sketch-image synthesis framework consists of three stages: semantic keypoint extraction, coarse image generation, and image refinement. First, we extract the semantic keypoints using Part Affinity Fields (PAFs) and a convolutional autoencoder. Then, we integrate the sketch with semantic keypoints to generate a coarse image of a human. Finally, in the image refinement stage, the coarse image is enhanced by a Generative Adversarial Network (GAN) that adopts an architecture carefully designed to avoid checkerboard artifacts and to generate photo-realistic results. We evaluate our method on 6,300 sketch-image pairs and show that our proposed method generates realistic images and compares favorably against state-of-the-art image synthesis methods.

The JPEG-XR encoding process utilizes two types of transform operations: Photo Overlap Transform (POT) and Photo Core Transform (PCT). Using the Device Porting Kit (DPK) provided by Microsoft, we performed encoding and decoding processes on JPEG XR images. It was discovered that when the quantization parameter is >1-lossy compression conditions, the resulting image displays chequerboard block artefacts, border artefacts and corner artefacts. These artefacts are due to the nonlinearity of transforms used by JPEG-XR. Typically, it is not so visible; however, it can cause problems while copying and scanning applications, as it shows nonlinear transforms when the source and the target of the image have different configurations. Hence, it is important for document image processing pipelines to take such artefacts into account. Additionally, these artefacts are most problematic for high-quality settings and appear more visible at high compression ratios. In this paper, we analyse the cause of the above artefacts. It was found that the main problem lies in the step of POT and quantization. To solve this problem, the use of a “uniform matrix” is proposed. After POT (encoding) and before inverse POT (decoding), an extra step is added to multiply this uniform matrix. Results suggest that it is an easy and effective way to decrease chequerboard, border and corner artefacts, thereby improving the image quality of lossy encoding JPEG XR than the original DPK program with no increased calculation complexity or file size.

This paper introduces a novel unsupervised domain adaptation (UDA) method, MeTa Discriminative Class-Wise MMD (MCWMMD), which combines meta-learning with a Class-Wise Maximum Mean Discrepancy (MMD) approach to enhance domain adaptation. Traditional MMD methods align overall distributions but struggle with class-wise alignment, reducing feature distinguishability. MCWMMD incorporates a meta-module to dynamically learn a deep kernel for MMD, improving alignment accuracy and model adaptability. This meta-learning technique enhances the model’s ability to generalize across tasks by ensuring domain-invariant and class-discriminative feature representations. Despite the complexity of the method, including the need for meta-module training, it presents a significant advancement in UDA. Future work will explore scalability in diverse real-world scenarios and further optimize the meta-learning framework. MCWMMD offers a promising solution to the persistent challenge of domain adaptation, paving the way for more adaptable and generalizable deep learning models.