Search

Malicious web domains represent a serious threat to online users’ privacy and security, causing monetary loss, theft of private information, and malware attacks, among others. In recent years, machine learning methods have been widely used as prediction models to identify malicious web domains. In this study, we propose a Fuzzy-Weighted Least Squares Support Vector Machine (FW-LS-SVM) model for malicious web domain identification. In our proposed model, a fuzzy-weighted operation is applied to each data sample considering the fact that different samples may have different importance. This fuzzy-weighted operation is also able to alleviate the influence of noise data and improve the model’s robustness by assigning weights to error constraints. For comparison purposes, three commonly used single machine learning classifiers and three widely used ensemble models are included in our experiments, in order to assess the performance of our proposed FW-LS-SVM and its ensemble version. Hyperlink indicators and uniform resource locator-based features are used to train the prediction models. Experimental results show that our proposed approach is highly effective in identifying malicious web domains, outperforming the well-established single and ensemble models being compared.

Fraudulent online sellers often collude with reviewers to garner fake reviews for their products. This act undermines the trust of buyers in product reviews, and potentially reduces the effectiveness of online markets. Being able to accurately detect fake reviews is, therefore, critical. In this study, we investigate several preprocessing and textual-based featuring methods along with machine learning classifiers, including single and ensemble models, to build a fake review detection system. Given the nature of product review data, where the number of fake reviews is far less than that of genuine reviews, we look into the results of each class in detail in addition to the overall results. We recognise from our preliminary analysis that, owing to imbalanced data, there is a high imbalance between the accuracies for different classes (e.g., 1.3% for the fake review class and 99.7% for the genuine review class), despite the overall accuracy looking promising (around 89.7%). We propose two dynamic random sampling techniques that are possible for textual-based featuring methods to solve this class imbalance problem. Our results indicate that both sampling techniques can improve the accuracy of the fake review class—for balanced datasets, the accuracies can be improved to a maximum of 84.5% and 75.6% for random under and over-sampling, respectively. However, the accuracies for genuine reviews decrease to 75% and 58.8% for random under and over-sampling, respectively. We also discover that, for smaller datasets, the Adaptive Boosting ensemble model outperforms other single classifiers; whereas, for larger datasets, the performance improvement from ensemble models is insignificant compared to the best results obtained by single classifiers.

Online learning is the main implementation of distance education and adult education. A pertinence and timely online teaching intervention could determine the persistence and quality of online learning. However, the existing intervention mechanism is mainly determined by teachers and focus on offline intervention which cannot be compatible with the online learning system well. In this paper we propose a model of online intervention which based on the learning behavior features. After interveners selection, the adaptive intervention measures could be generated in the intervention strategy library and executed automated. We emphasis on the construction of the intervention strategy library which combines with historical intervention experiences in strategy forming and representation. Besides this, we take a decision-making algorithm to classify the strategies and make adaptive and accurate strategies to different kinds of interveners. Adaptive online intervention strategy library is the premise and basis of automated online intervention, which can reduce the gap between the large number of online learners and the limited number of teachers. It also can improve the awareness of learners and teachers, thus gain the better effect on online learning ultimately.

The financial impact of positive reviews has prompted some fraudulent sellers to generate fake product reviews for either promoting their products or discrediting competing products. Many e-commerce portals have implemented measures to detect such fake reviews, and these measures require excellent detectors to be effective. In this work, we propose 133 unique features from the combination of content and behaviour-based features to detect fake reviews using machine learning classifiers. Preliminary results show that these features can provide good results for all datasets tested. Detailed analysis of the results, however, reveals the existence of class imbalance issues for two of the bigger datasets - there is a high imbalance between the accuracies of different classes (e.g., 7.73% for the fake class and 99.3% for the genuine class using a Multilayer Perceptron classifier). We therefore introduce two sampling methods that can improve the accuracy of the fake review class on balanced datasets. The accuracies can be improved to a maximum of 89% for both random under and over-sampling on Convolutional Neural Networks. Additionally, we propose a parallel cross-validation method that can speed up the validation process in a parallel environment.

Intelligent vehicle is a complex system includes at least three parts of information, the vehicles themselves, driving surroundings and drivers which has different formats, different properties, and different collection methods. These differences bring difficulties to communication and knowledge sharing among vehicles and drivers, and also create barriers to vehicle safety research. To address these problems, we propose a novel intelligent vehicle knowledge framework to contain all of related information of intelligent vehicle with clear hierarchical architecture and unified SOEKS structure. Based on the framework the anomaly detection approach using past driving experience and the neural knowledge DNA (NK-DNA) is proposed. And then we introduce the Long Short-Term Memory (LSTM) neural network into the Networks of NK-DNA, to detect abnormal CAN packages. We examine our approach with real car data and simulated attack data. The simulation results shown our framework and detection method can share easily and found anomalies of CAN bus flow.

The prediction of emergency event occupies an important position in the network public opinion. In this paper, an improved algorithm for emergency event based on statistics of word frequency is presented, which takes BBS, blog, news sites with commentary function as investigated subjects. The experiment shows it can provide the useful ideas and exploration for analysis of public opinion and early warning of mass group incidents.