International Journal of Neural Systems

Network intrusion detection is becoming a challenging task with cyberattacks that are becoming more and more sophisticated. Failing the prevention or detection of such intrusions might have serious consequences. Machine learning approaches try to recognize network connection patterns to classify unseen and known intrusions but also require periodic re-training to keep the performances at a high level. In this paper, a novel continuous learning intrusion detection system, called Soft-Forgetting Self-Organizing Incremental Neural Network (SF-SOINN), is introduced. SF-SOINN, besides providing continuous learning capabilities, is able to perform fast classification, is robust to noise, and it obtains good performances with respect to the existing approaches. The main characteristic of SF-SOINN is the ability to remove nodes from the neural network based on their utility estimate. SF-SOINN has been validated on the well-known NSL-KDD and CIC-IDS-2017 intrusion detection datasets as well as on some artificial data to show the classification capability on more general tasks.

Echo state networks (ESNs), belonging to the family of recurrent neural networks (RNNs), are suitable for addressing complex nonlinear tasks due to their rich dynamic characteristics and easy implementation. The reservoir of the ESN is composed of a large number of sparsely connected neurons with randomly generated weight matrices. How to set the structural parameters of the ESN becomes a difficult problem in practical applications. Traditionally, the design of the parameters of the ESN structure is performed manually. The manual adjustment of the ESN parameters is not convenient since it is an extremely challenging and time-consuming task. This paper proposes an ensemble of five particle swarm optimization (PSO) strategies to design the structure of ESN and then reduce the manual intervention in the design process. An adaptive selection mechanism is used for each particle in the evolution to select a strategy from the strategy candidate pool for evolution. In addition, leaky integration neurons are used as reservoir internal neurons, which are added within the adaptive mechanism for optimization. The root mean squared error (RMSE) is adopted as the evaluation criterion. The experimental results on Mackey–Glass time series benchmark dataset show that the proposed method outperforms other traditional evolutionary methods. Furthermore, experimental results on electrocardiogram dataset show that the proposed method on the ensemble of PSO displays an excellent performance on real-world problems.

Conventional rehabilitation strategies for stroke survivors become difficult when voluntary movements are severely disturbed. Combining passive limb mobilization, robotic devices and EEG-based brain-computer interfaces (BCI) systems might improve treatment and clinical follow-up of these patients, but detailed knowledge of neurophysiological mechanisms involved in functional recovery, which might help for tailoring stroke treatment strategies, is lacking. Movement-related EEG changes (EEG event-related desynchronization (ERD) in $beta$ and $alpha$ bands, an indicator of motor cortex activation traditionally used for BCI systems), were evaluated in a group of 23 paralyzed chronic stroke patients in two unilateral motor tasks alternating paretic and healthy hands ((i) passive movement, using a hand exoskeleton, and (ii) voluntary movement), and compared to nine healthy subjects. In tasks using unaffected hand, we observed an increase of contralesional hemisphere activation for stroke patients group. Unexpectedly, when using paralyzed hand, motor cortex activation was reduced or absent in severely affected group of patients, while patients with moderate motor deficit showed an activation greater than control group. Cortical activation was reduced or absent in damaged hemisphere of all the patients in both tasks. Significant differences related to severity of motor deficit were found in the time course of $alpha$-$beta$ bands power ratio in EEG of contralesional hemisphere while moving affected hand. These findings suggest the presence of different compensation mechanisms in contralesional hemisphere of stroke patients related to the grade of motor disability, that might turn quantitative EEG during a movement task, obtained from a BCI system controlling a robotic device included in a rehabilitation task, into a valuable tool for monitoring clinical progression, evaluating recovery, and tailoring treatment of stroke patients.

Decoding brain intention from noninvasively measured neural signals has recently been a hot topic in brain-computer interface (BCI). The motor commands about the movements of fine parts can increase the degrees of freedom under control and be applied to external equipment without stimulus. In the decoding process, the classifier is one of the key factors, and the graph information of the EEG was ignored by most researchers. In this paper, a graph convolutional network (GCN) based on functional connectivity was proposed to decode the motor intention of four fine parts movements (shoulder, elbow, wrist, hand). First, event-related desynchronization was analyzed to reveal the differences between the four classes. Second, functional connectivity was constructed by using synchronization likelihood (SL), phase-locking value (PLV), H index (H), mutual information (MI), and weighted phase-lag index (WPLI) to acquire the electrode pairs with a difference. Subsequently, a GCN and convolutional neural networks (CNN) were performed based on functional topological structures and time points, respectively. The results demonstrated that the proposed method achieved a decoding accuracy of up to 92.81% in the four-class task. Besides, the combination of GCN and functional connectivity can promote the development of BCI.

This research presents a new method for detecting obsessive–compulsive disorder (OCD) based on time–frequency analysis of multi-channel electroencephalogram (EEG) signals using the multi-variate synchrosqueezing transform (MSST). With the evolution of multi-channel sensor implementations, the employment of multi-channel techniques for the extraction of features arising from multi-channel dependency and mono-channel characteristics has become common. MSST has recently been proposed as a method for modeling the combined oscillatory mechanisms of multi-channel signals. It makes use of the concepts of instantaneous frequency (IF) and bandwidth. Electrophysiological data, like other nonstationary signals, necessitates both joint time–frequency analysis and independent time and frequency domain studies. The usefulness and effectiveness of a multi-variate, wavelet-based synchrosqueezing algorithm paired with a band extraction method are tested using electroencephalography data obtained from OCD patients and control groups in this research. The proposed methodology yields substantial results when analyzing differences between patient and control groups.

Humans obtain characteristic information such as texture and weight of external objects, relying on the brain’s integration and classification of tactile information; however, the decoding mechanism of multi-level tactile information is relatively elusive from the temporal sequence. In this paper, nonvariant frequency, along with the variant pulse width of electrotactile stimulus, was performed to generate multi-level pressure sensation. Event-related potentials (ERPs) were measured to investigate the mechanism of whole temporal tactile processing. Five ERP components, containing P100–N140–P200–N200–P300, were observed. By establishing the relationship between stimulation parameters and ERP component amplitudes, we found the following: (1) P200 is the most significant component for distinguishing multi-level tactile sensations; (2) P300 is correlated well with the subjective judgment of tactile sensation. The temporal sequence of brain topographies was implemented to clarify the spatiotemporal characteristics of the tactile process, which conformed to the serial processing model in neurophysiology and cortical network response area described by fMRI. Our results can help further clarify the mechanism of tactile sequential processing, which can be applied to improve the tactile BCI performance, sensory enhancement, and clinical diagnosis for doctors to evaluate the tactile process disorders by examining the temporal ERP components.