Bayesian Linear Discriminant Analysis Research Articles

Exploring different classification-dependent QSAR modelling strategies for HDAC3 inhibitors in search of meaningful structural contributors.

Histone deacetylase 3 (HDAC3), a Zn2+-dependent class I HDACs, contributes to numerous disorders such as neurodegenerative disorders, diabetes, cardiovascular disease, kidney disease and several types of cancers. Therefore, the development of novel and selective HDAC3 inhibitors might be promising to combat such diseases. Here, different classification-based molecular modelling studies such as Bayesian classification, recursive partitioning (RP), SARpy and linear discriminant analysis (LDA) were conducted on a set of HDAC3 inhibitors to pinpoint essential structural requirements contributing to HDAC3 inhibition followed by molecular docking study and molecular dynamics (MD) simulation analyses. The current study revealed the importance of hydroxamate function for Zn2+ chelation as well as hydrogen bonding interaction with Tyr298 residue. The importance of hydroxamate function for higher HDAC3 inhibition was noticed in the case of Bayesian classification, recursive partitioning and SARpy models. Also, the importance of substituted thiazole ring was revealed, whereas the presence of linear alkyl groups with carboxylic acid function, any type of ester function, benzodiazepine moiety and methoxy group in the molecular structure can be detrimental to HDAC3 inhibition. Therefore, this study can aid in the design and discovery of effective novel HDAC3 inhibitors in the future.

Automatic identification of schizophrenia employing EEG records analyzed with deep learning algorithms.

Electroencephalography is a method of detecting and analyzing electrical activity in the brain. This electrical activity can be recorded and processed to aid in the clinical diagnosis of mental disorders. In this study, a novel system for classifying schizophrenia patients from EEG recordings is presented. The developed algorithm decomposes the EEG signals into a system of radial basis functions using the method of fuzzy means. This decomposition helps to obtain the information from the various electrodes of the EEG and allows separating between healthy controls and patients with schizophrenia. The proposed method has been compared with classical machine learning algorithms, such as, K-Nearest Neighbor, Adaboost, Support Vector Machine, and Bayesian Linear Discriminant Analysis. The results show that the proposed method obtains the highest values in terms of balanced accuracy, recall, precision and F1 score, close to 93% in all cases. The model developed in this study can be implemented in brain activity analysis systems that help in the prediction of patients with schizophrenia.

Inter-Hospital Advanced and Mild Alzheimer's Disease Classification Based on Electroencephalogram Measurements via Classical Machine Learning Algorithms.

In pursuit of diagnostic tools capable of targeting distinct stages of Alzheimer's disease (AD), this study explores the potential of electroencephalography (EEG) combined with machine learning (ML) algorithms to identify patients with mild or moderate AD (ADM) and advanced AD (ADA). This study aims to assess the classification accuracy of six classical ML algorithms using a dataset of 668 patients from multiple hospitals. The dataset comprised measurements obtained from 668 patients, distributed among control, ADM, and ADA groups, collected from five distinct hospitals between 2011 and 2022. For classification purposes, six classical ML algorithms were employed: support vector machine, Bayesian linear discriminant analysis, decision tree, Gaussian Naïve Bayes, K-nearest neighbor and random forest. The RF algorithm exhibited outstanding performance, achieving a remarkable balanced accuracy of 93.55% for ADA classification and 93.25% for ADM classification. The consistent reliability in distinguishing ADA and ADM patients underscores the potential of the EEG-based approach for AD diagnosis. By leveraging a dataset sourced from multiple hospitals and encompassing a substantial patient cohort, coupled with the straightforwardness of the implemented models, it is feasible to attain notably robust results in AD classification.

SKDCPM algorithm can improve the single-trial decoding performance of very similar error-related potentials.

Error related potential (ErrP) is an effective control signal for the brain-computer interface (BCI). Current ErrP decoding methods can only distinguish right and wrong mental states. However, in real scenarios, error conditions often contain more detailed information, such as the degree of error, which would induce very similar ErrPs. Distinguishing such ErrPs effectively is of vital importance to provide more detailed information for optimizing BCIs. Hereto, a major challenge is the EEG differences of very similar ErrPs are very small. Thus, it is necessary to develop new efficient method for decoding very similar ErrPs. This study newly proposed an algorithm named shrinkage discriminant canonical pattern matching (SKDCPM), and compared its decoding results with the linear discriminant analysis (LDA), shrinkage LDA (SKLDA), stepwise LDA (SWLDA), Bayesian LDA (BLDA) and the DCPM, which were algorithms commonly used for ErrP decoding. A data set of 18 subjects was built, it had four conditions, i.e., right (0°), errors with varying degrees, i.e., 45°, 90°, 180° deviation from the predicted direction. As a result, the SKDCPM had high balanced accuracy (BACC) in right-wrong classification (0° vs. others). More importantly, it achieved a grand averaged BACC of 69.54% with the highest up to 74.25%, which outperformed all the other algorithms in very similar ErrPs decoding (45° vs. 90° vs. 180°) significantly. This study could provide new decoding methods for developing the ErrP-based BCI system.

Improving Intention Detection in Single-Trial Classification Through Fusion of EEG and Eye-Tracker Data

Intention decoding is an indispensable procedure in hands-free human–computer interaction (HCI). A conventional eye-tracker system using a single-model fixation duration may issue commands that ignore users' real expectations. Here, an eye-brain hybrid brain–computer interface (BCI) interaction system was introduced for intention detection through the fusion of multimodal eye-tracker and event-related potential (ERP) [a measurement derived from electroencephalography (EEG)] features. Eye-tracking and EEG data were recorded from 64 healthy participants as they performed a 40-min customized free search task of a fixed target icon among 25 icons. The corresponding fixation duration of eye tracking and ERP were extracted. Five previously-validated linear discriminant analysis (LDA)-based classifiers [including regularized LDA, stepwise LDA, Bayesian LDA, shrinkage linear discriminant analysis (SKLDA), and spatial-temporal discriminant analysis] and the widely-used convolutional neural network (CNN) method were adopted to verify the efficacy of feature fusion from both offline and pseudo-online analysis, and the optimal approach was evaluated by modulating the training set and system response duration. Our study demonstrated that the input of multimodal eye tracking and ERP features achieved a superior performance of intention detection in the single-trial classification of active search tasks. Compared with the single-model ERP feature, this new strategy also induced congruent accuracy across classifiers. Moreover, in comparison with other classification methods, we found that SKLDA exhibited a superior performance when fusing features in offline tests (ACC = 0.8783, AUC = 0.9004) and online simulations with various sample amounts and duration lengths. In summary, this study revealed a novel and effective approach for intention classification using an eye-brain hybrid BCI and further supported the real-life application of hands-free HCI in a more precise and stable manner.

Accurate neural network classification model for schizophrenia disease based on electroencephalogram data

Electroencephalogram is a useful interface system that translates the human electrical brain activity into voltage signals. By these means, the recorded brain waves can be employed to characterize, classify, or diagnose mental disorders. A novel neural network model to classify patients with schizophrenia based on electroencephalograms is presented. The proposed model decomposes the multichannel electroencephalogram records into a group of multivariate novel radial basis functions using a fuzzy means algorithm. The decomposition permits to extract different electroencephalogram channel information and distinguish between two sort of classes i.e., schizophrenic patients and healthy controls. Results show improved accuracy compared to classical algorithms reported in the literature i.e., Support Vector Machine, Bayesian Linear Discriminant Analysis, Decision Tree, Gaussian Naive Bayes, Random Forest, K-Nearest Neighbour, Convolutional Neuronal Network, or Adaboost. As a result, the method presented in this paper achieves the highest balanced accuracy, recall, precision and F1 score values, close to 93% in all cases. The model presented in this paper may be integrated in real time tools involved during the diagnostic of schizophrenia.

A convenient and efficient 4-(diethylamino)-butylamine-labeled polarity-response-homodispersed strategy for absolute quantification of carboxyl submetabolome: Monitoring the whole progressive course of hepatocellular carcinoma

Recent studies have shown that dysregulation of carboxyl submetabolome homeostasis is closely related to the occurrence and development of hepatocellular carcinoma (HCC). However, it is still a challenge to quantify carboxyl metabolites with high efficiency by conventional methods due to their species diversity and nature differences. Moreover, there are few studies on carboxyl submetabolome profiling during the whole progression of HCC. In this study, a convenient and efficient workflow for absolute quantification of carboxyl submetabolome was established based on the 4-(diethylamino)-butylamine (DEABA)-labeled polarity-response-homodispersed strategy. After optimizing derivation conditions with response surface methodology (RSM), the reaction only needed 1 min at room temperature, which radically simplified the labeling process. Compared with nonderivatization, the gaps of polarities and responses of the analytes were narrowed by DEABA labeling, realizing the polarity-response-homodispersion. Then resolution and sensitivity in HPLC-MS/MS were improved significantly. Ultimately, the workflow was applied to monitor carboxyl metabolic profile in human plasma of the whole progressive course of hepatocellular carcinoma. Combined with analysis of variance (ANOVA), orthogonal partial least squares discrimination analysis (OPLS-DA), Bayesian linear discriminant analysis (BLDA) and other data mining methods, the biomarkers of “health-hepatitis-cirrhosis-HCC” were screened out, and the diagnostic model was established. Furthermore, the relevancy between carboxyl submetabolome disorders and the pathogenesis of HCC was investigated. The developed method has the characteristics of high sensitivity, high coverage and high practicability, which is suitable for the study of biomarkers of carboxyl submetabolome in the whole progression of HCC.

High-Precise Bipolar Disorder Detection by Using Radial Basis Functions Based Neural Network

Presently, several million people suffer from major depressive and bipolar disorders. Thus, the modelling, characterization, classification, diagnosis, and analysis of such mental disorders bears great significance in medical research. Electroencephalogram records provide important information to improve clinical diagnosis and are very useful in the scientific community. In this work, electroencephalogram records and patient data from the Hospital Virgen de la Luz in Cuenca (Spain) were processed for a correct classification of bipolar disorders. This work implemented an innovative radial basis function-based neural network employing a fuzzy means algorithm. The results show that the proposed method is an effective approach for discrimination of two kinds of classes, i.e., bipolar disorder patients and healthy persons. The proposed algorithm achieved the best performance compared with other machine learning techniques such as Bayesian linear discriminant analysis, Gaussian naive Bayes, decision trees, K-nearest neighbour, or support vector machine, showing a very high accuracy close to 97%. Therefore, the neural network technique presented could be used as a new tool for the diagnosis of bipolar disorder, considering the possibility of integrating this method into medical software.

Evaluation of color modulation in visual P300-speller using new stimulus patterns.

Objective The stimulus color of P300-BCI systems has been successfully modified. However, the effects of different color combinations have not been widely investigated. In this study, we designed new stimulus patterns to evaluate the influence of color modulation on the BCI performance and waveforms of the evoked related potential (ERP).Methods Comparison was performed for three new stimulus patterns consisting of red face and colored block-shape, namely, red face with a white rectangle (RFW), red face with a blue rectangle (RFB), and red face with a red rectangle (RFR). Bayesian linear discriminant analysis (BLDA) was used to construct the individual classifier model. Repeated-measures ANOVA and Bonferroni correction were applied for statistical analysis. Results The RFW pattern obtained the highest average online accuracy with 96.94%, and those of RFR and RFB patterns were 93.61% and of 92.22% respectively. Significant differences in online accuracy and information transfer rate (ITR) were found between RFW and RFR patterns (p < 0.05). Conclusion Compared with RFR and RFB patterns, RFW yielded the best performance in P300-BCI. These new stimulus patterns with different color combinations have considerable importance to BCI applications and user-friendliness.

The Automatic Detection of Seizure Based on Tensor Distance And Bayesian Linear Discriminant Analysis.

Electroencephalogram (EEG) plays an important role in recording brain activity to diagnose epilepsy. However, it is not only laborious, but also not very cost effective for medical experts to manually identify the features on EEG. Therefore, automatic seizure detection in accordance with the EEG recordings is significant for the diagnosis and treatment of epilepsy. Here, a new method for detecting seizures using tensor distance (TD) is proposed. First, the time-frequency characteristics of EEG signals are obtained by wavelet transformation, and the tensor representation of EEG signals is then obtained. Tucker decomposition is used to obtain the principal components of the EEG tensor. After, the distances between different categories of EEG tensors are calculated as the EEG features. Finally, the TD features are classified through the Bayesian Linear Discriminant Analysis (Bayesian LDA) classifier. The performance of this method is measured by the sensitivity, specificity, and recognition accuracy. Results indicate 95.12% sensitivity, 97.60% specificity, 97.60% recognition accuracy, and a false detection rate of 0.76 per hour in the invasive EEG dataset, which included 566.57[Formula: see text]h of EEG recording data from 21 patients. Taken together, the results show that TD has a good detection effect for seizure classification and that this method has high computational speed and great potential for real-time diagnosis.

A P300-Based BCI System Using Stereoelectroencephalography and Its Application in a Brain Mechanistic Study.

Stereoelectroencephalography (SEEG) signals can be obtained by implanting deep intracranial electrodes. SEEG depth electrodes can record brain activity from the shallow cortical layer and deep brain structures, which is not achievable through other recording techniques. Moreover, SEEG has the advantage of a high signal-to-noise ratio (SNR). Therefore, it provides a potential way to establish a highly efficient brain-computer interface (BCI) and aid in understanding human brain activity. In this study, we implemented a P300-based BCI using SEEG signals. A single-character oddball paradigm was applied to elicit P300. To predict target characters, we fed the feature vectors extracted from the signals collected by five SEEG contacts into a Bayesian linear discriminant analysis (BLDA) classifier. Thirteen epileptic patients implanted with SEEG electrodes participated in the experiment and achieved an average online spelling accuracy of 93.85%. Moreover, through single-contact decoding analysis and simulated online analysis, we found that the SEEG-based BCI system achieved a high performance even when using a single signal channel. Furthermore, contacts with high decoding accuracies were mainly distributed in the visual ventral pathway, especially the fusiform gyrus (FG) and lingual gyrus (LG), which played an important role in building P300-based SEEG BCIs. These results might provide new insights into P300 mechanistic studies and the corresponding BCIs.

Riemann-Based Algorithms Assessment for Single- and Multiple-Trial P300 Classification in Non-Optimal Environments.

The P300 wave is commonly used in Brain-Computer Interface technology due to its higher bit rates when compared to other BCI paradigms. P300 classification pipelines based on Riemannian Geometry provide accuracies on par with state-of-the-art pipelines, without having the need for spatial filters, and also possess the ability to be calibrated with little data. In this study, five different P300 detection pipelines are compared, with three of them using Riemannian Geometry as either feature extraction or classification algorithms. The goal of this study is to assess the viability of Riemannian Geometry-based methods in non-optimal environments with sudden background noise changes, rather than maximizing classification accuracy values. For fifteen subjects, the average single-trial accuracy obtained for each pipeline was: 56.06% for Linear Discriminant Analysis (LDA), 72.13% for Bayesian Linear Discriminant Analysis (BLDA), 63.56% for Riemannian Minimum Distance to Mean (MDM), 69.22% for Riemannian Tangent Space with Logistic Regression (TS-LogR), and 63.30% for Riemannian Tangent Space with Support Vector Machine (TS-SVM). The results are higher for the pipelines based on BLDA and TS-LogR, suggesting that they could be viable methods for the detection of the P300 component when maximizing the bit rate is needed. For multiple-trial classification, the BLDA pipeline converged faster towards higher average values, closely followed by the TS-LogR pipeline. The two remaining Riemannian methods' accuracy also increases with the number of trials, but towards a lower value compared to the aforementioned ones. Single-stimulus detection metrics revealed that the TS-LogR pipeline can be a viable classification method, as its results are only slightly lower than those obtained with BLDA. P300 waveforms were also analyzed to check for evidence of the component being elicited. Finally, a questionnaire was used to retrieve the most intuitive focusing methods employed by the subjects.

Improving the performance of P300 BCI system using different methods

A brain–computer interface (BCI) can be used for people with severe physical disabilities such as ALS, or amyotrophic lateral sclerosis. BCI can allow these individuals to communicate again by creating a new communication channel directly from the brain to an output device. BCI technology can allow paralyzed people to share their intent with others, and thereby demonstrate that direct communication from the brain to the external world is possible, and that it might serve useful functions. In this paper, we propose a system to exploit the P300 signal in the brain, a positive deflection in event-related potentials. The P300 signal can be incorporated into a spelling device. BCI systems include machine learning algorithms (MLA). Their performance depends on the feature extraction and classification techniques employed. This work discusses the performance of different machine learning algorithms. First, a preprocessing step is introduced to the subjects to extract the important features before applying the machine learning algorithms. The presented algorithms are linear discriminant analysis (LDA I and LDA II), support vector machine (SVM I, SVM II, SVM III, and SVM IV), linear regression (LREG), and Bayesian linear discriminant analysis (BLDA). It is found that BLDA and SVMIV classifiers yield the highest performance for both subjects considered in our study.

A 36-Class Bimodal ERP Brain-Computer Interface Using Location-Congruent Auditory-Tactile Stimuli.

To date, traditional visual-based event-related potential brain-computer interface (ERP-BCI) systems continue to dominate the mainstream BCI research. However, these conventional BCIs are unsuitable for the individuals who have partly or completely lost their vision. Considering the poor performance of gaze independent ERP-BCIs, it is necessary to study techniques to improve the performance of these BCI systems. In this paper, we developed a novel 36-class bimodal ERP-BCI system based on tactile and auditory stimuli, in which six-virtual-direction audio files produced via head related transfer functions (HRTF) were delivered through headphones and location-congruent electro-tactile stimuli were simultaneously delivered to the corresponding position using electrodes placed on the abdomen and waist. We selected the eight best channels, trained a Bayesian linear discriminant analysis (BLDA) classifier and acquired the optimal trial number for target selection in online process. The average online information transfer rate (ITR) of the bimodal ERP-BCI reached 11.66 bit/min, improvements of 35.11% and 36.69% compared to the auditory (8.63 bit/min) and tactile approaches (8.53 bit/min), respectively. The results demonstrate the performance of the bimodal system is superior to each unimodal system. These facts indicate that the proposed bimodal system has potential utility as a gaze-independent BCI in future real-world applications.

MULTIPLE CLASSIFICATION TECHNIQUES TOWARD A ROBUST AND RELIABLE P300 BCI SYSTEM

A brain–computer interface (BCI) can be used for people with severe physical disabilities such as ALS or amyotrophic lateral sclerosis. BCI can allow these individuals to communicate again by creating a new communication channel directly from the brain to an output device. BCI technology can allow paralyzed people to share their intent with others, and thereby demonstrate that direct communication from the brain to the external world is possible and that it might serve useful functions. BCI systems include machine learning algorithms (MLAs). Their performance depends on the feature extraction and classification techniques employed. In this paper, we propose a system to exploit the P300 signal in the brain, a positive deflection in event-related potentials. The P300 signal can be incorporated into a spelling device. There are two benefits behind this kind of research. First of all, this work presents the research status and the advantages of communication via a BCI system, especially the P300 BCI system for disordered people, and the related literature review is presented. Secondly, the paper discusses the performance of different machine learning algorithms. Two different datasets are presented: the first dataset 2004 and the second dataset 2019. A preprocessing step is introduced to the subjects in both datasets first to extract the important features before applying the proposed machine learning methods: linear discriminant analysis (LDA I and LDA II), support vector machine (SVM I, SVM II, SVM III, and SVM IV), linear regression (LREG), Bayesian linear discriminant analysis (BLDA), and twin support vector machine (TSVM). By comparing the performance of the different machine learning systems, in the first dataset it is found that BLDA and SVMIV classifiers yield the highest performance for both subjects “A” and “B”. BLDA yields 98% and 66% for 15th and 5th sequences, respectively, whereas SVMIV yields 98% and 54.4% for 15th and 5th sequences, respectively. While in the second dataset, it is obvious that BLDA classifier yields the highest performance for both subjects “1” and “2”, it achieves 90.115%. The paper summarizes the P300 BCI system for the two introduced datasets. It discusses the proposed system, compares the classification methods performances, and considers some aspects for the future work to be handled. The results show high accuracy and less computational time which makes the system more applicable for online applications.

A functional source separation algorithm to enhance error-related potentials monitoring in noninvasive brain-computer interface

Background and objectivesAn Error related Potential (ErrP) can be noninvasively and directly measured from the scalp through electroencephalography (EEG), as response, when a person realizes they are making an error during a task (as a consequence of a cognitive error performed from the user). It has been shown that ErrPs can be automatically detected with time-discrete feedback tasks, which are widely applied in the Brain-Computer Interface (BCI) field for error correction or adaptation. In this work, a semi-supervised algorithm, namely the Functional Source Separation (FSS), is proposed to estimate a spatial filter for learning the ErrPs and to enhance the evoked potentials. MethodsEEG data recorded on six subjects were used to evaluate the proposed method based on FFS algorithm in comparison with the xDAWN algorithm. FSS- and xDAWN-based methods were compared also to the Cz and FCz single channel. Single-trial classification was considered to evaluate the performances of the approaches. (Both the approaches were evaluated on single-trial classification of EEGs.) ResultsThe results presented using the Bayesian Linear Discriminant Analysis (BLDA) classifier, show that FSS (accuracy 0.92, sensitivity 0.95, specificity 0.81, F1-score 0.95) overcomes the other methods (Cz - accuracy 0.72, sensitivity 0.74, specificity 0.63, F1-score 0.74; FCz - accuracy 0.72, sensitivity 0.75, specificity 0.61, F1-score 0.75; xDAWN - accuracy 0.75, sensitivity 0.79, specificity 0.61, F1-score 0.79) in terms of single-trial classification. ConclusionsThe proposed FSS-based method increases the single-trial detection accuracy of ErrPs with respect to both single channel (Cz, FCz) and xDAWN spatial filter.

Comparison of the ERP-Based BCI Performance Among Chromatic (RGB) Semitransparent Face Patterns.

ObjectivePrevious studies have shown that combing with color properties may be used as part of the display presented to BCI users in order to improve performance. Build on this, we explored the effects of combinations of face stimuli with three primary colors (RGB) on BCI performance which is assessed by classification accuracy and information transfer rate (ITR). Furthermore, we analyzed the waveforms of three patterns.MethodsWe compared three patterns in which semitransparent face is overlaid three primary colors as stimuli: red semitransparent face (RSF), green semitransparent face (GSF), and blue semitransparent face (BSF). Bayesian linear discriminant analysis (BLDA) was used to construct the individual classifier model. In addition, a Repeated-measures ANOVA (RM-ANOVA) and Bonferroni correction were chosen for statistical analysis.ResultsThe results indicated that the RSF pattern achieved the highest online averaged accuracy with 93.89%, followed by the GSF pattern with 87.78%, while the lowest performance was caused by the BSF pattern with an accuracy of 81.39%. Furthermore, significant differences in classification accuracy and ITR were found between RSF and GSF (p < 0.05) and between RSF and BSF patterns (p < 0.05).ConclusionThe semitransparent faces colored red (RSF) pattern yielded the best performance of the three patterns. The proposed patterns based on ERP-BCI system have a clinically significant impact by increasing communication speed and accuracy of the P300-speller for patients with severe motor impairment.

A Low-Cost Computational Method for Characterizing Event-Related Potentials for BCI Applications and Beyond

Event-related potentials (ERPs) are important neurophysiological markers widely used in scientific, medical and engineering contexts. Proper ERP detection contributes to widening the scope of use and, in general, improving functionality. The morphology and latency of ERPs are variable among subject sessions, which complicates their detection. Although variability is an intrinsic feature of neuronal activity, it can be addressed with novel views on ERP detection techniques. In this paper, we propose an agile method for characterizing and thus detecting variable ERPs, which keeps track of their temporal and spatial information through the continuous measurement of the area under the curve in ERP components. We illustrate the usefulness of the proposed ERP characterization for electrode selection in brain-computer interfaces (BCIs) and compare the results with other standard methods. We assess ERP classification for BCI use with Bayesian linear discriminant analysis (BLDA) and cross-validation. We also evaluate performance with both the information transfer rate and BCI utility. The results of our validation tests show that this characterization helps to take advantage of the information on the evolution of positive and negative ERP components and, therefore, to efficiently select electrodes for optimized ERP detection. The proposed method improves the classification accuracy and bitrate of all sets of electrodes analyzed. Furthermore, the method is robust between different day sessions. Our work contributes to the efficient detection of ERPs, manages inter- and intrasubject variability, decreases the computational cost of classic detection methods and contributes to promoting low-cost personalized brain-computer interfaces.

A Pilot Study on Falling-Risk Detection Method Based on Postural Perturbation Evoked Potential Features.

In the human-robot hybrid system, due to the error recognition of the pattern recognition system, the robot may perform erroneous motor execution, which may lead to falling-risk. While, the human can clearly detect the existence of errors, which is manifested in the central nervous activity characteristics. To date, the majority of studies on falling-risk detection have focused primarily on computer vision and physical signals. There are no reports of falling-risk detection methods based on neural activity. In this study, we propose a novel method to monitor multi erroneous motion events using electroencephalogram (EEG) features. There were 15 subjects who participated in this study, who kept standing with an upper limb supported posture and received an unpredictable postural perturbation. EEG signal analysis revealed a high negative peak with a maximum averaged amplitude of −14.75 ± 5.99 μV, occurring at 62 ms after postural perturbation. The xDAWN algorithm was used to reduce the high-dimension of EEG signal features. And, Bayesian linear discriminant analysis (BLDA) was used to train a classifier. The detection rate of the falling-risk onset is 98.67%. And the detection latency is 334ms, when we set detection rate beyond 90% as the standard of dangerous event onset. Further analysis showed that the falling-risk detection method based on postural perturbation evoked potential features has a good generalization ability. The model based on typical event data achieved 94.2% detection rate for unlearned atypical perturbation events. This study demonstrated the feasibility of using neural response to detect dangerous fall events.

Unsupervised adaptation of PLDA models for broadcast diarization

We present a novel model adaptation approach to deal with data variability for speaker diarization in a broadcast environment. Expensive human annotated data can be used to mitigate the domain mismatch by means of supervised model adaptation approaches. By contrast, we propose an unsupervised adaptation method which does not need for in-domain labeled data but only the recording that we are diarizing. We rely on an inner adaptation block which combines Agglomerative Hierarchical Clustering (AHC) and Mean-Shift (MS) clustering techniques with a Fully Bayesian Probabilistic Linear Discriminant Analysis (PLDA) to produce pseudo-speaker labels suitable for model adaptation. We propose multiple adaptation approaches based on this basic block, including unsupervised and semi-supervised. Our proposed solutions, analyzed with the Multi-Genre Broadcast 2015 (MGB) dataset, reported significant improvements (16% relative improvement) with respect to the baseline, also outperforming a supervised adaptation proposal with low resources (9% relative improvement). Furthermore, our proposed unsupervised adaptation is totally compatible with a supervised one. The joint use of both adaptation techniques (supervised and unsupervised) shows a 13% relative improvement with respect to only considering the supervised adaptation.