LightAnomalyNet: A Lightweight Framework for Efficient Abnormal Behavior Detection

The continuous development of intelligent video surveillance systems has increased the demand for enhanced vision-based methods of automated detection of anomalies within various behaviors found in video scenes. Several methods have appeared in the literature that detect different anomalies by using the details of motion features associated with different actions. To enable the efficient detection of anomalies, alongside characterizing the specificities involved in features related to each behavior, the model complexity leading to computational expense must be reduced. This paper provides a lightweight framework (LightAnomalyNet) comprising a convolutional neural network (CNN) that is trained using input frames obtained by a computationally cost-effective method. The proposed framework effectively represents and differentiates between normal and abnormal events. In particular, this work defines human falls, some kinds of suspicious behavior, and violent acts as abnormal activities, and discriminates them from other (normal) activities in surveillance videos. Experiments on public datasets show that LightAnomalyNet yields better performance comparative to the existing methods in terms of classification accuracy and input frames generation.

A Lightweight Framework for Intelligent Fault Diagnosis Acceleration in Complex Industrial Systems

<p>With the acquisition of massive condition monitoring data, how to realize real-time and efficient intelligent fault diagnosis is the focus of current research. Inspired by the ideas of compressed sensing (CS) and deep extreme learning machines (DELM), a data-driven lightweight framework is proposed to accelerate intelligent fault diagnosis. The integrated framework contains two modules: data sampling and fault diagnosis. Data sampling module projects the intensive original monitoring data into lightweight compressed sampling data non-linearly, which can effectively reduce the pressure of transmission, storage and calculation. Fault diagnosis module digs deeply into the inner connection between the compressed sampled signal and the fault types to realize accurate fault diagnosis. This work has three meaningful points. First, we believe that the bearing vibration signal is not strictly sparse in the transform domain. Second, we verified that the sparse signal after compressed sampling can be directly used for fault diagnosis without being reconstructed. Third, adding a kernel function to the DELM can perfectly map the low-dimensional inseparable features after compressed sampling to the high-dimensional space non-linearly to make it linearly separable and thus improve the classification accuracy</p>

A Lightweight Framework for Intelligent Fault Diagnosis Acceleration in Complex Industrial Systems

<p>With the acquisition of massive condition monitoring data, how to realize real-time and efficient intelligent fault diagnosis is the focus of current research. Inspired by the ideas of compressed sensing (CS) and deep extreme learning machines (DELM), a data-driven lightweight framework is proposed to accelerate intelligent fault diagnosis. The integrated framework contains two modules: data sampling and fault diagnosis. Data sampling module projects the intensive original monitoring data into lightweight compressed sampling data non-linearly, which can effectively reduce the pressure of transmission, storage and calculation. Fault diagnosis module digs deeply into the inner connection between the compressed sampled signal and the fault types to realize accurate fault diagnosis. This work has three meaningful points. First, we believe that the bearing vibration signal is not strictly sparse in the transform domain. Second, we verified that the sparse signal after compressed sampling can be directly used for fault diagnosis without being reconstructed. Third, adding a kernel function to the DELM can perfectly map the low-dimensional inseparable features after compressed sampling to the high-dimensional space non-linearly to make it linearly separable and thus improve the classification accuracy</p>

A Novel EMG-Based Hand Gesture Recognition Framework Based on Multivariate Variational Mode Decomposition

Surface electromyography (sEMG) is a kind of biological signal that records muscle activity noninvasively, which is of great significance in advanced human-computer interaction, prosthetic control, clinical therapy, and biomechanics. However, the number of hand gestures that can be recognized is limited and the recognition accuracy needs to be further improved. These factors lead to the fact that sEMG products are not widely used in practice. The main contributions of this paper are as follows. Firstly, considering the increasing number of gestures to be recognized and the complexity of gestures, an extensible two-stage machine learning lightweight framework was innovatively proposed for multi-gesture task recognition. Secondly, the multivariate variational mode decomposition (MVMD) is applied to extract the spatial–temporal features from the multiple channels to the EMG signals, and the separable convolutional neural network is used for modelling. In this work, the experimental results for 52 hand gestures recognition task show that the average accuracy on each stage is about 90%. The potential movement information is mainly contained in the low-frequency oscillator of the sEMG signal, and the model performs better with the low-frequency oscillation from the MVMD algorithm on the second stage classification than that of other decomposition methods.