GraphTS: Graph-represented time series for subsequence anomaly detection.

Automatic detection of subsequence anomalies (i.e., an abnormal waveform denoted by a sequence of data points) in time series is critical in a wide variety of domains. However, most existing methods for subsequence anomaly detection often require knowing the length and the total number of anomalies in time series. Some methods fail to capture recurrent subsequence anomalies due to using only local or neighborhood information for anomaly detection. To address these limitations, in this paper, we propose a novel graph-represented time series (GraphTS) method for discovering subsequence anomalies. In GraphTS, we provide a new concept of time series graph representation model, which represents both recurrent and rare patterns in a time series. Particularly, in GraphTS, we develop a new 2D time series visualization (2Dviz) method, which compacts all 1D time series patterns into a 2D spatial temporal space. The 2Dviz method transfers time series patterns into a higher-resolution plot for easier sequence anomaly recognition (or detecting subsequence anomalies). Then, a Graph is constructed based on the 2D spatial temporal space of time series to capture recurrent and rare subsequence patterns effectively. The represented Graph also can be used to discover single and recurrent subsequence anomalies with arbitrary lengths. Experimental results demonstrate that the proposed method outperforms the state-of-the-art methods in terms of accuracy and efficiency.

Strain-Insensitive Elastic Surface Electromyographic (sEMG) Electrode for Efficient Recognition of Exercise Intensities.

Surface electromyography (sEMG) sensors are widely used in the fields of ergonomics, sports science, and medical research. However, current sEMG sensors cannot recognize the various exercise intensities efficiently because of the strain interference, low conductivity, and poor skin-conformability of their electrodes. Here, we present a highly conductive, strain-insensitive, and low electrode-skin impedance elastic sEMG electrode, which consists of a three-layered structure (polydimethylsiloxane/galinstan + polydimethylsiloxane/silver-coated nickel + polydimethylsiloxane). The bottom layer of the electrode consists of vertically conductive magnetic particle paths, which are insensitive to stretching strain, collect sEMG charge from human skin, and finally transfer it to processing circuits via an intermediate layer. Our skin-friendly electrode exhibits high conductivity (0.237 and 1.635 mΩ.cm resistivities in transverse and longitudinal directions, respectively), low electrode-skin impedance (47.23 kΩ at 150 Hz), excellent strain-insensitivity (10% change of electrode-skin impedance within the 0%-25% strain range), high fatigue resistance (>1500 cycles), and good conformability with skin. During various exercise intensities, the signal-to-noise ratio (SNR) of our electrode increased by 22.53 dB, which is 206% and 330% more than that of traditional Ag/AgCl and copper electrode, respectively. The ability of our electrode to efficiently recognize various exercise intensities confirms its great application potential for the field of sports health.

Exploring Douglas-Peucker Algorithm in the Detection of Epileptic Seizure from Multicategory EEG Signals.

Discovering the concealed patterns of Electroencephalogram (EEG) signals is a crucial part in efficient detection of epileptic seizures. This study develops a new scheme based on Douglas-Peucker algorithm (DP) and principal component analysis (PCA) for extraction of representative and discriminatory information from epileptic EEG data. As the multichannel EEG signals are highly correlated and are in large volumes, the DP algorithm is applied to extract the most representative samples from EEG data. The PCA is utilised to produce uncorrelated variables and to reduce the dimensionality of the DP samples for better recognition. To verify the robustness of the proposed method, four machine learning techniques, random forest classifier (RF), k-nearest neighbour algorithm (k-NN), support vector machine (SVM), and decision tree classifier (DT), are employed on the obtained features. Furthermore, we assess the performance of the proposed methods by comparing it with some recently reported algorithms. The experimental results show that the DP technique effectively extracts the representative samples from EEG signals compressing up to over 47% sample points of EEG signals. The results also indicate that the proposed feature method with the RF classifier achieves the best performance and yields 99.85% of the overall classification accuracy (OCA). The proposed method outperforms the most recently reported methods in terms of OCA in the same epileptic EEG database.

A PCA aided cross-covariance scheme for discriminative feature extraction from EEG signals.

BACKGROUND AND OBJECTIVES: Feature extraction of EEG signals plays a significant role in Brain-computer interface (BCI) as it can significantly affect the performance and the computational time of the system. The main aim of the current work is to introduce an innovative algorithm for acquiring reliable discriminating features from EEG signals to improve classification performances and to reduce the time complexity. METHODS: This study develops a robust feature extraction method combining the principal component analysis (PCA) and the cross-covariance technique (CCOV) for the extraction of discriminatory information from the mental states based on EEG signals in BCI applications. We apply the correlation based variable selection method with the best first search on the extracted features to identify the best feature set for characterizing the distribution of mental state signals. To verify the robustness of the proposed feature extraction method, three machine learning techniques: multilayer perceptron neural networks (MLP), least square support vector machine (LS-SVM), and logistic regression (LR) are employed on the obtained features. The proposed methods are evaluated on two publicly available datasets. Furthermore, we evaluate the performance of the proposed methods by comparing it with some recently reported algorithms. RESULTS: The experimental results show that all three classifiers achieve high performance (above 99% overall classification accuracy) for the proposed feature set. Among these classifiers, the MLP and LS-SVM methods yield the best performance for the obtained feature. The average sensitivity, specificity and classification accuracy for these two classifiers are same, which are 99.32%, 100%, and 99.66%, respectively for the BCI competition dataset IVa and 100%, 100%, and 100%, for the BCI competition dataset IVb. The results also indicate the proposed methods outperform the most recently reported methods by at least 0.25% average accuracy improvement in dataset IVa. The execution time results show that the proposed method has less time complexity after feature selection. CONCLUSIONS: The proposed feature extraction method is very effective for getting representatives information from mental states EEG signals in BCI applications and reducing the computational complexity of classifiers by reducing the number of extracted features.

Wireless sensor networks for heritage object deformation detection and tracking algorithm.

Deformation is the direct cause of heritage object collapse. It is significant to monitor and signal the early warnings of the deformation of heritage objects. However, traditional heritage object monitoring methods only roughly monitor a simple-shaped heritage object as a whole, but cannot monitor complicated heritage objects, which may have a large number of surfaces inside and outside. Wireless sensor networks, comprising many small-sized, low-cost, low-power intelligent sensor nodes, are more useful to detect the deformation of every small part of the heritage objects. Wireless sensor networks need an effective mechanism to reduce both the communication costs and energy consumption in order to monitor the heritage objects in real time. In this paper, we provide an effective heritage object deformation detection and tracking method using wireless sensor networks (EffeHDDT). In EffeHDDT, we discover a connected core set of sensor nodes to reduce the communication cost for transmitting and collecting the data of the sensor networks. Particularly, we propose a heritage object boundary detecting and tracking mechanism. Both theoretical analysis and experimental results demonstrate that our EffeHDDT method outperforms the existing methods in terms of network traffic and the precision of the deformation detection.