Haider Raza

EWMA model based shift-detection methods for detecting covariate shifts in non-stationary environments

Dataset shift is a very common issue wherein the input data distribution shifts over time in non-stationary environments. A broad range of real-world systems face the challenge of dataset shift. In such systems, continuous monitoring of the process behavior and tracking the state of shift are required in order to decide about initiating adaptive corrections in a timely manner. This paper presents novel methods for covariate shift-detection tests based on a two-stage structure for both univariate and multivariate time-series. The first stage works in an online mode and it uses an exponentially weighted moving average (EWMA) model based control chart to detect the covariate shift-point in non-stationary time-series. The second stage validates the shift-detected by first stage using the Kolmogorov-Smirnov statistical hypothesis test (K-S test) in the case of univariate time-series and the Hotelling T-Squared multivariate statistical hypothesis test in the case of multivariate time-series. Additionally, several orthogonal transformations and blind source separation algorithms are investigated to counteract the adverse effect of cross-correlation in multivariate time-series on shift-detection performance. The proposed methods are suitable to be run in real-time. Their performance is evaluated through experiments using several synthetic and real-world datasets. Results show that all the covariate shifts are detected with much reduced false-alarms compared to other methods. The main focus is on the covariate shift-detection tests based on EWMA.In univariate shift-detection test, getting the excessive false-alarms is an issue.The issue of false-alarms has been handled by a novel two-stage structure test.A multivariate formulation for the covariate shift-detection is also presented.The proposed methods are superior in accuracy and reducing the false-alarms.

Dataset Shift Detection in Non-stationary Environments Using EWMA Charts

Dataset shift is a major challenge in the non-stationary environments wherein the input data distribution may change over time. Detecting the dataset shift point in the time-series data, where the distribution of time-series changes its properties, is of utmost interest. Dataset shift exists in a broad range of real-world systems. In such systems, there is a need for continuous monitoring of the process behavior and tracking the state of the shift so as to decide about initiating adaptive corrections in a timely manner. This paper presents an algorithm to detect the shift-point in a non-stationary time-series data. The proposed method detects the shift-point based on an exponentially weighted moving average (EWMA) control chart for auto-correlated observations. This algorithm is suitable to be run in real-time and monitors the data to detect the dataset shift. Its performance is evaluated through experiments using synthetic and real-world datasets. Results show that all the dataset-shifts are detected without the delay.

Adaptive learning with covariate shift-detection for motor imagery-based brain---computer interface

A common assumption in traditional supervised learning is the similar probability distribution of data between the training phase and the testing/operating phase. When transitioning from the training to testing phase, a shift in the probability distribution of input data is known as a covariate shift. Covariate shifts commonly arise in a wide range of real-world systems such as electroencephalogram-based brain–computer interfaces (BCIs). In such systems, there is a necessity for continuous monitoring of the process behavior, and tracking the state of the covariate shifts to decide about initiating adaptation in a timely manner. This paper presents a covariate shift-detection and -adaptation methodology, and its application to motor imagery-based BCIs. A covariate shift-detection test based on an exponential weighted moving average model is used to detect the covariate shift in the features extracted from motor imagery-based brain responses. Following the covariate shift-detection test, the methodology initiates an adaptation by updating the classifier during the testing/operating phase. The usefulness of the proposed method is evaluated using real-world BCI datasets (i.e. BCI competition IV dataset 2A and 2B). The results show a statistically significant improvement in the classification accuracy of the BCI system over traditional learning and semi-supervised learning methods.

Optimising frequency band selection with forward-addition and backward-elimination algorithms in EEG-based brain-computer interfaces

A major problem in a brain-computer interface (BCI) based on electroencephalogram (EEG) recordings is the varying statistical properties of the signals during inter- or intra-session transfers that often lead to deteriorated BCI performances. A filter bank CSP (FBCSP) algorithm typically uses all the features from all the bands to extract and select robust features. In this paper, we evaluate the performance of four methods for frequency band selection applied to binary motor imagery classification: forward-addition (FA), backward-elimination (BE), the intersection and the union of the FA and BE. These methods automatically select and learn the best discriminative sets of frequency bands, and their corresponding CSP features. The performances of the proposed methods are evaluated on binary motor imagery classification using a publicly available real-world dataset (BCI competition 2008 dataset 2A). It is found that the BE method provides the best improvement resulting in an average classification accuracy increase of the BCI system over the FBCSP algorithm, from 77.06% to 79.09%.

EWMA based two-stage dataset shift-detection in non-stationary environments

Dataset shift is a major challenge in the non-stationary environments wherein the input data distribution may change over time. In a time-series data, detecting the dataset shift point, where the distribution changes its properties is of utmost interest. Dataset shift exists in a broad range of real-world systems. In such systems, there is a need for continuous monitoring of the process behavior and tracking the state of the shift so as to decide about initiating adaptive corrections in a timely manner. This paper presents a novel method to detect the shift-point based on a two-stage structure involving Exponentially Weighted Moving Average (EWMA) chart and Kolmogorov-Smirnov test, which substantially reduces type-I error rate. The algorithm is suitable to be run in real-time. Its performance is evaluated through experiments using synthetic and real-world datasets. Results show effectiveness of the proposed approach in terms of decreased type-I error and tolerable increase in detection time delay.

Adaptive learning with covariate shift-detection for non-stationary environments

Learning with dataset shift is a major challenge in non-stationary environments wherein the input data distribution may shift over time. Detecting the dataset shift point in the time-series data, where the distribution of time-series shifts its properties, is of utmost interest. Dataset shift exists in a broad range of real-world systems. In such systems, there is a need for continuous monitoring of the process behavior and tracking the state of the shift so as to decide about initiating adaptation in a timely manner. This paper presents an adaptive learning algorithm with dataset shift-detection using an exponential weighted moving average (EWMA) model based test in a non-stationary environment. The proposed method initiates the adaptation by reconfiguring the knowledge-base of the classifier. This algorithm is suitable for real-time learning in non-stationary environments. Its performance is evaluated through experiments using synthetic datasets. Results show that it reacts well to different covariate shifts.

Exploring gaze-motor imagery hybrid brain-computer interface design

Non-invasive Brain-Computer Interface (BCI) has appeared as a new hope for a large population of disabled people, who were waiting for a new communication means that would translate some brain responses into actions. After several decades of research in fields such as neuroscience and machine learning, the performance remains too low due to the low signal to noise ratio of the EEG signal, and the time that has to be dedicated to the recording of the brain responses. Hybrid BCIs consider the combination of several modalities, including brain responses, for new communication systems. The creation of a Hybrid BCI requires particular care as it possesses the constraints from several modalities. We propose to investigate the performance that could be achieved in a paradigm, where gaze control is used for the selection of an item on a computer screen and motor imagery is used to enable the selected item on the screen. Based on the results obtained from gaze detection with an eye tracker, and motor imagery detection with non-invasive EEG recording, we show that the performance of a parallel Hybrid BCI is only beneficial if the accuracy of each modality reaches a particular limit, and if the number of commands from each modality is carefully chosen.

Covariate shift-adaptation using a transductive learning model for handling non-stationarity in EEG based brain-computer interfaces

A major challenge to devising robust brain-computer interfaces (BCIs) based on electroencephalogram (EEG) data is the immanent non-stationary characteristics of EEG signals. Statistical properties of the signals may shift during inter-or-intra session transfers that often leads to deteriorated BCI performance. The shift in the input data distribution from training to testing phase is called a covariate shift. It can be caused by various reasons such as different electrode placements, varying impedances and other ongoing brain activities. We propose an algorithm to handle this issue by adapting to the covariate shifts in the EEG data using a transductive learning approach. The performance of the proposed method is evaluated on the BCI competition 2008-Graz dataset B. The results show an improvement in classification accuracy of the BCI system over a traditional learning method. The obtained results support the conclusion that covariate-shift-adaptation using transductive learning is helpful to realize adaptive BCI systems.

Selection of cluster-head using PSO in CGSR protocol

Routing protocol for Ad Hoc Wireless Networks are categorised on the basis of routing information update mechanism, use of temporal information for routing, topolgy information organization and miscellaneous classification based on ultization of specific resources. The CGSR lies under table driven or proactive protocol based on routing information update mechanism. CGSR is a hierarchical routing scheme which enables partial cooridnation between nodes by electing cluster-heads. The main disadvantage of CGSR is increase in path length and instabilty in the system at high mobility when the rate of change of cluster-heads is high. The power consumption at the cluster-head node is also a matter of concern because the battery-draining rate at the cluster-head is higher than the normal node. This could lead to frequent change in cluster-head which may result in mulitple path breaks. In order to deal with this problem we have used PSO for choosing cluster-head in CGSR. The results obtained are good as compared to Least Cluster Change(LCC) algorithm and Genetic Algorithm (GA). This experiment is performed on MATLAB.

A combination of transductive and inductive learning for handling non-stationarities in motor imagery classification

A major issue for bringing brain-computer interface (BCI) based on electroencephalogram (EEG) recordings outside of laboratories is the non-stationarities of EEG signals. Varying statistical properties of the signals during inter- or intra-session transfers can lead to deteriorated BCI performances over time. These variations may cause the input data distribution to shift when transitioning from the training phase (calibration session) to the testing/operating phase resulting in a covariate shift. We propose to handle this issue using a novel hybrid learning method based on two classifiers, wherein the first classifier allows including new information in the training dataset, and the second classifier performs an overall classification. The proposed method is motivated by the smoothness assumption, i.e., the points that are closest to each other are more likely to share the same label, and may be added online to enrich the training dataset. The method is evaluated on two real-world datasets corresponding to motor imagery detection (BCI competition 2008 dataset 2A and 2B). The results support the conclusion that an improvement in the classification accuracy over traditional inductive learning and semi-supervised learning methods can be obtained.