Search

[Display omitted] • Micro-expressions are swift and often occur when humans suppress genuine emotions. • Automatically recognizing micro-expressions is challenging due to its subtleness. • A region based visual association process for spontaneous detection is developed. • A deep learning framework combining visual association and deep features is proposed. • Significant improvements in micro-expression recognition demonstrated via experiments. Facial micro-expressions play a significant role in revealing concealed emotions. However, the recognition of micro-expressions is challenging due to their fleeting nature. Moreover, the visual features of the face and the visual relationships between the facial sub-regions have a strong influence on the presence of micro-expressions. In this work, a novel end-to-end facial micro-expression detection framework, called Deep3DCANN , is proposed to integrate these components for effective micro-expression detection. The first component of our framework is a deep 3D convolutional neural network that learns useful spatiotemporal features from a sequence of facial images. In the second component, a deep artificial neural network is utilized to trace the useful visual associations between different sub-regions of the face. Furthermore, a carefully crafted fusion mechanism is built to combine the learned facial features and the semantic relationships between the regions to predict the micro-expressions. We also construct a new loss function to jointly optimize both modules of our proposed architecture. Our proposed method performs favourably on five benchmark spontaneous micro-expression databases compared to existing micro-expression recognition baselines on videos. In addition, through an extended experiment, we show that our proposed approach can effectively recognize the frame-wise micro-expression changes in a sequence of video frames. [ABSTRACT FROM AUTHOR]

Cyber-physical systems (CPS) are used increasingly in modern industrial systems. These systems currently encounter a significant threat of malicious activities created by malicious software intent on exploiting the fact that the software of such industrial systems is integrated with hardware and network systems. Malicious codes dynamically and continuously change their internal structure and attack patterns using obfuscation techniques, such as polymorphism and metamorphism, in order to bypass and hide from conventional malware detection engines. This requires continuously updating the database of the malware detection engine, which requires periodic effort from manual experts. This could limit the real-time protection of CPS. In addition, this also makes preserving the availability and integrity of the services provided by CPS against malicious code challenging because there is a demand for the development of specialized malware detection techniques for CPS. In this paper, we propose a semi-supervised approach that automatically integrates the knowledge about unknown malware from already available and cheap unlabeled data into the detection system. The novelty of the proposed approach is that it does not require expert effort to update the database of the detection engine. Instead, the dynamic changes in malware attack patterns are extracted by unsupervised clustering from already available unlabeled data. Then the extracted geometric information about the intrinsic attack characteristics of the clusters is integrated into the classification systems of the detection engine, which updates the detection system automatically. The proposed approach uses global K-means clustering with term-frequency (TF), inverse document frequency (IDF), and cosine similarity as a distance measure for extracting the cluster information and adding it to a support vector machine (SVM) classification system. The proposed approach has been tested extensively on a real malware data set for both static and dynamic malware features. The experiment results show that the proposed semi-supervised approach achieves higher accuracy over the existing supervised approaches for all classifiers. We note that the static feature-based semi-supervised approach can improve detection accuracy significantly. While applying the proposed semi-supervised approach with the run-time characteristics of dynamic feature analysis, the combined effect of dynamic analysis and the proposed approach further increases the detection accuracy of all classifiers by up to a 100% for the SVM and the random forest classifiers, thus exceeding the existing supervised approaches with similar features. [ABSTRACT FROM AUTHOR]

• We propose a method to assess neonatal stress by analysing heart rate variability (HRV). • We consider an extension of the traditional pNN50 statistic to other durations. • We use the Lempel-Ziv complexity to analyse series of exceedances of the pNNx statistic. • We use a dataset of 40 newborns in four experimental phases to highlight the efficiency of the method. Among the existing measures of heart rate variability (HRV), the pNN50 statistics is one of the most commonly reported. However, it is only a single member of a much larger family of HRV measures – the pNN x statistics. In this research pNN x was further extended, combining it with the Lempel-Ziv complexity (LZ76) in a controlled neonatal stress framework. Two different types of stress stimuli on forty healthy newborns – a routine heel stick blood sampling, and a dull heel pressure stimulation – were considered by recording time intervals between heartbeats. Instead of relying on a single value, the entire spectrum from pNN1 to pNN100 was calculated, along with LZ76 derived from binarized sequences for each NN. The results of this study show a downward shift of the pNN x curves when newborns are stressed, with reduced LZ76 complexity when stressed. When ROC curves were utilized for the pNN x statistics and LZ76, however, the highest AUC values were observed when both measures were combined, with the highest AUC values of 0.88 (0.80-0.94) and 0.85 (0.74-0.91) for discriminating resting states from stress phases. Combining the widely used pNN x statistics with LZ76 extends the existing HRV toolbox, and shows a promising application in recognizing acute neonatal stress. [ABSTRACT FROM AUTHOR]