Handwritten Annotation Spotting in Printed Documents Using Top-Down Visual Saliency Models

In this article, we address the problem of localizing text and symbolic annotations on the scanned image of a printed document. Previous approaches have considered the task of annotation extraction as binary classification into printed and handwritten text. In this work, we further subcategorize the annotations as underlines, encirclements, inline text, and marginal text. We have collected a new dataset of 300 documents constituting all classes of annotations marked around or in-between printed text. Using the dataset as a benchmark, we report the results of two saliency formulations—CRF Saliency and Discriminant Saliency, for predicting salient patches, which can correspond to different types of annotations. We also compare our work with recent semantic segmentation techniques using deep models. Our analysis shows that Discriminant Saliency can be considered as the preferred approach for fast localization of patches containing different types of annotations. The saliency models were learned on a small dataset, but still, give comparable performance to the deep networks for pixel-level semantic segmentation. We show that saliency-based methods give better outcomes with limited annotated data compared to more sophisticated segmentation techniques that require a large training set to learn the model.

Malware Classification Based on Multilayer Perception and Word2Vec for IoT Security

With the construction of smart cities, the number of Internet of Things (IoT) devices is growing rapidly, leading to an explosive growth of malware designed for IoT devices. These malware pose a serious threat to the security of IoT devices. The traditional malware classification methods mainly rely on feature engineering. To improve accuracy, a large number of different types of features will be extracted from malware files in these methods. That brings a high complexity to the classification. To solve these issues, a malware classification method based on Word2Vec and Multilayer Perception (MLP) is proposed in this article. First, for one malware sample, Word2Vec is used to calculate a word vector for all bytes of the binary file and all instructions in the assembly file. Second, we combine these vectors into a 256x256x2-dimensional matrix. Finally, we designed a deep learning network structure based on MLP to train the model. Then the model is used to classify the testing samples. The experimental results prove that the method has a high accuracy of 99.54%.

The Influences of Live Streaming Affordance in Cross-Border E-Commerce Platforms

Despite the promise of cross-border e-commerce, attracting consumers is still a worldwide challenge. Many cross-border e-commerce platforms have responded to the challenges by embracing innovative tools like live streaming. However, there has been limited understandings of the unique nature of live streaming and its empirical influence. Taking an affordance view of live streaming, this study defines affordance of live streaming as the capacities provided by live streaming and examines how affordance of live streaming affect consumer behavior in the cross-border e-commerce context based on information transparency perspective. Results show that although live streaming does not directly affect consumers’ cross-border purchase intention, it can increase consumers’ purchase intention through increasing perceived information transparency. In addition, affordance of live streaming can further moderate the relationship between different types of information transparency and consumers’ cross-border purchase intention. The findings provide a much-needed contribution to academia and business.

Personalized, Sequential, Attentive, Metric-Aware Product Search

The task of personalized product search aims at retrieving a ranked list of products given a user’s input query and his/her purchase history. To address this task, we propose the PSAM model, a Personalized, Sequential, Attentive and Metric-aware (PSAM) model, that learns the semantic representations of three different categories of entities, i.e., users, queries, and products, based on user sequential purchase historical data and the corresponding sequential queries. Specifically, a query-based attentive LSTM (QA-LSTM) model and an attention mechanism are designed to infer users dynamic embeddings, which is able to capture their short-term and long-term preferences. To obtain more fine-grained embeddings of the three categories of entities, a metric-aware objective is deployed in our model to force the inferred embeddings subject to the triangle inequality, which is a more realistic distance measurement for product search. Experiments conducted on four benchmark datasets show that our PSAM model significantly outperforms the state-of-the-art product search baselines in terms of effectiveness by up to 50.9% improvement under NDCG@20. Our visualization experiments further illustrate that the learned product embeddings are able to distinguish different types of products.

The Influences of Live Streaming Affordance in Cross-border E-commerce Platform

Despite the promise of cross-border e-commerce, attracting consumers is still a worldwide challenge. Many cross-border e-commerce platforms have responded to the challenges by embracing innovative tools like live streaming. However, there has been limited understandings of the unique nature of live streaming and its empirical influence. Taking an affordance view of live streaming, this study defines affordance of live streaming as the capacities provided by live streaming and examines how affordance of live streaming affect consumer behavior in the cross-border e-commerce context based on information transparency perspective. Results show that although live streaming does not directly affect consumers’ cross-border purchase intention, it can increase consumers’ purchase intention through increasing perceived information transparency. In addition, affordance of live streaming can further moderate the relationship between different types of information transparency and consumers’ cross-border purchase intention. The findings provide a much-needed contribution to academia and business.

Kalman filter applied to Thevenin’s modeling of a lead-acid battery

<span>This article determines the internal parameters of a battery analyzed from its circuit equivalent, reviewing important information that can help to identify the battery’s state of charge (SOC) and its state of health (SOH). Although models that allow the dynamics of different types of batteries to be identified have been developed, few have defined the lead-acid battery model from the analysis of a filtered signal by applying a Kalman filter, particularly taking into account the measurement of noise not just at signal output but also at its input (this is a novelty raised from the experimental). This study proposes a model for lead-acid batteries using tools such as MATLAB^® and Simulink^®. First, a method of filtering the input and output signal is presented, and then a method for identifying parameters from 29 charge states is used for a lead-acid battery. Different SOCs are related to different values of open circuit voltage (OCV). Ultimately, improvements in model estimation are shown using a filter that considers system and sensor noise since the modeled and filtered signal is closer to the original signal than the unfiltered modeled signal.</span>