Brahim Hamadicharef

Learning EEG-based spectral-spatial patterns for attention level measurement

In our every day life, our brain is constantly processing information and paying attention, reacting accordingly, to all sorts of sensory inputs (auditory, visual, etc.). In some cases, there is a need to accurately measure a persons level of attention to monitor a sportsman performance, to detect Attention Deficit Hyperactivity Disorder (ADHD) in children, to evaluate the effectiveness of neuro-feedback treatment, etc.

Brain-Computer Interface (BCI) literature - a bibliometric study

Brain-Computer Interface (BCI) is a relatively young research field which has seen a growing interest with associated number of publications over the last two decades. In this study we present the first bibliometric analysis of the BCI literature (1990–2008) from the Thomson Reuterss Institute for Scientific Information (ISI) Web of Knowledge. Thus, the main objectives of this bibliometric study are: 1) to explore the growth of BCI literature, 2) to assess if it follows Lotkas law of scientific productivity, 3) to identify authors, groups and countries contributing the most to BCI, 4) to reveal the characteristic of citation for the BCI literature, and finally, 5) to determine the core journals that published substantial portions of the literature on BCI. Results indicate that BCI literature follows a power law growth, has an average author count of 3.9 and an average page count of 7.09. More than half (52.73%) of the BCI literature is never cited, and 14 papers have been cited more than 100 times. The 3 most productive authors are leading BCI research groups, in Austria, Germany and the USA.

Performance Evaluation and Fusion of Methods for Early Detection of Alzheimer Disease

The number of people that develop Alzheimers Disease (AD) is rapidly rising, while the initial diagnosis and care of AD patients typically falls on non-specialist and still taking up to 3-5 years before being referred to specialists. An urgent need thus exists to develop methods to extract accurate and robust biomarkers from low-cost and non intrusive modalities such as electroencephalograms (EEGs). Contributions of this paper are three-fold. First we review 8 promising methods for early diagnosis of AD and undertake a performance evaluation using ROC analysis. We find that fractal dimension (AUC = 0.989), zero crossing interval (AUC = 0.980) and spectrum analysis of power alpha/theta ratio (Pwralpha,thetas)(AUC = 0.975) perform best, with all three having sensitivity and specificity higher than 94%. We plot ROC curve with 95% confidence contours because of the small size of our data set (17 AD and 24 NOLD). Second, we investigate a fusion approach to combine these methods, using a logistic regression model, into one single more accurate biomarker (AUC = 1.0). Thirdly, to help support the distribution and use of these methods for early detection and care of AD, we developed them as web-services, integrated into online tools available from the BIOPATTERN project portal (www.biopattern.org).

Frequentist versus Bayesian approaches for AUC Confidence Intervals bounds

In this paper we first present two approaches, Frequentist and Bayesian, to calculate the Confidence Interval (CI) of Area Under the Curve (AUC). The goal of this study is to compare both approaches and find out if they reveal significant differences along the sample size.

Scientometric Study of the Journal NeuroImage 1992-2009

For young researchers starting in a specific field of work, it is not always easy to make an opinion of a journal which potential for publication apart from the basis of peers’ advices and indicators such as impact factor. In this paper we use web technologies to create a scientometric picture, using bibliometric analysis methods, of the journal NeuroImage from its creation in 1992 until 2009. The aim of this work is show how to provide a good account of the journal’s bibliometrics which will help to quickly identify the journal’s main features. Results indicated that the Neuro Image literature consists of a total of 11604 contributions. The five top 5 major contributors were identified to be Kark J. Friston, Jon Ash burner, Keith J. Worsley, Bruce R. Fischl and Thomas E. Nichols. The top 5 most cited papers achieve very high number of citations (from 1026 to 1888). From authors affiliation, we also found strong international collaboration between US and Europe including UK, Germany, Switzerland, France and Italy, and with Asian countries such as Japan and China, shown using a strength color-coded connection-wheel diagram. This study will help future web sites to provide more bibliometric information about scientific journals, authors and research fields. As these are evolving very rapidly after each publication issue (e.g. citation counts, new contributing authors, etc.), web tools should be developed to provide the most recent bibliometric updates.

Scientometric Study of the IEEE Transactions on Software Engineering 1980-2010

In this paper a scientometric study on the IEEE Transactions on Software Engineering 1980-2010 is presented. Using the full records from the Thomson Reuters (ISI) Web of Science (WoS), the journal’s bibliometric measures are examined in terms of growth of literature, authorship characteristics, country of origin, distribution of articles’ citations and references, and finally graph network of the research collaborations. A keyword occurrence analysis was carried out on the articles’ title and the results used to create TagClouds showing perceptually their research importance. Furthermore, these TagClouds were created for the full 3 decades, shorter 5-year periods and most recent years, providing insights into potential research trends and help to relate them to major historic contributions in software engineering.

Intelligent and perceptual-based approach to musical instruments sound design

A novel, generic framework for musical instrument sound design is proposed. The framework uses an intelligent and perceptual based approach to address the two main problems in sound design - optimization of synthesis parameters and assessment of sound quality. A fuzzy model is used to capture and exploit knowledge of sound design from audio experts. A robust methodology, based on the ITU Perceptual Evaluation of Audio Quality (PEAQ) algorithm, is used for objective prediction of sound synthesis quality and sound quality assessment. The new framework makes it possible to automate the optimization of synthesis parameters. It also allows the designer to evaluate objectively, the perceptual impact of individual parameters on the final sound quality which is useful for benchmarking sound synthesis methods. The framework is generic and can be used for sound design for a wide range of musical instruments. We illustrate the use of the framework in pipe organ sound design. Results from this show that the new approach provides an important and useful alternative to existing methods.

International collaborations in brain-computer interface (BCI) research

The strength and quality of a research field can be depicted from its literature. In this paper, the Brain-Computer Interface (BCI) research literature is examined for collaborations at the individual level (i.e. researchers) and international level (i.e. countries). Records from the Web of Science (WoS)(Thomson Reuters) are examined to form an updated picture of the BCI research worldwide and in particular its international collaboration. Results indicate strong collaboration between Germany, USA, Austria, and Italy. At the BCI researcher level, this is less prominent. Furthermore, a research quality proxy, based on both Impact Factor (IF) and Eigen Factor (EF), is also examined for journals publishing BCI research. These results, updated regularly, will be published online to help to improve the BCI research community visibility.

AUC confidence bounds for performance evaluation of Brain-Computer Interface

Currently most performance evaluation of Brain-Computer Interface (BCI) systems is simply reported in terms of accuracy. In this paper we propose a novel approach to evaluate the true performance of BCI systems based on Receiver Operating Characteristic (ROC) analysis, that removes the limitations of the accuracy performance measure. We demonstrate the need to provide, and particularly for small sample size, Confidence Interval (CI) bounds to indicate reliability of the BCI system performance. The ROC-based methodology makes it possible to calculate CI, shown as a contour at each any points of the ROC curve, with value of the lower bound of the Area Under the Curve (AUC). We illustrate the usefulness of the methodology using the results the BCI Competition IV data set 3, dealing with the classification of wrist movements from four directions recorded using magnetoencephalogram (MEG). Plotting the 95% CI contours overlayed on the ROC curves revealed some overlap with the chance level, thus revealing potential different interpretation from claims based on single accuracy value. The ROC-based methodology will also help to determine minimal sample size, an important requirement for future BCI studies and competitions.

A plea for AUC confidence intervals in diagnosis models used in gynecology

Over the last decade many studies in the gynecology literature have been investigating the performance of diagnosis models such as Univariate, Risk of Malignancy Index (RMI) and Logistic Regression (LR). Typical performance results are claimed in terms of sensitivity (SEN), specificity (SPE), accuracy (ACC), Positive Predictive Value (PPV), Negative Predictive Value (NPV), with some studies als including Receiver Operating Characteristic (ROC) curve and its Area Under the Curve (AUC). It remains, however, that all these measures do not reflect any sample size and thus making it sometimes difficult to assess with confidence the true performance of these diagnosis models, in particular for small sample size. In this paper, we propose to use systematically, a ROC-based methodology that makes possible to calculate the Confidence Interval (CI) at each ROC point. The methodology is generic and robust to sample size, and based on Probability Density Function (PDF) without any assumption on the distribution. We illustrate its use on 6 recent studies and show that results with the additional AUC 95% CI contour is more adequate to compare the performance of these diagnosis models, especially with studies using different sample size.