Yann Laurillau

EMG feature evaluation for improving myoelectric pattern recognition robustness

In pattern recognition-based myoelectric control, high accuracy for multiple discriminated motions is presented in most of related literature. However, there is a gap between the classification accuracy and the usability of practical applications of myoelectric control, especially the effect of long-term usage. This paper proposes and investigates the behavior of fifty time-domain and frequency-domain features to classify ten upper limb motions using electromyographic data recorded during 21days. The most stable single feature and multiple feature sets are presented with the optimum configuration of myoelectric control, i.e. data segmentation and classifier. The result shows that sample entropy (SampEn) outperforms other features when compared using linear discriminant analysis (LDA), a robust classifier. The averaged test classification accuracy is 93.37%, when trained in only initial first day. It brings only 2.45% decrease compared with retraining schemes. Increasing number of features to four, which consists of SampEn, the fourth order cepstrum coefficients, root mean square and waveform length, increase the classification accuracy to 98.87%. The proposed techniques achieve to maintain the high accuracy without the retraining scheme. Additionally, this continuous classification allows the real-time operation.

Clover architecture for groupware

In this paper we present the Clover architectural model, a new conceptual architectural model for groupware. Our model results from the combination of the layer approach of Dewans generic architecture with the functional decomposition of the Clover design model. The Clover design model defines three classes of services that a groupware application may support, namely, production, communication and coordination services. The three classes of services can be found in each functional layer of our model. Our model is illustrated with a working system, the CoVitesse system, its software being organized according to our Clover architectural model.

Feature extraction of the first difference of EMG time series for EMG pattern recognition

This paper demonstrates the utility of a differencing technique to transform surface EMG signals measured during both static and dynamic contractions such that they become more stationary. The technique was evaluated by three stationarity tests consisting of the variation of two statistical properties, i.e., mean and standard deviation, and the reverse arrangements test. As a result of the proposed technique, the first difference of EMG time series became more stationary compared to the original measured signal. Based on this finding, the performance of time-domain features extracted from raw and transformed EMG was investigated via an EMG classification problem (i.e., eight dynamic motions and four EMG channels) on data from 18 subjects. The results show that the classification accuracies of all features extracted from the transformed signals were higher than features extracted from the original signals for six different classifiers including quadratic discriminant analysis. On average, the proposed differencing technique improved classification accuracies by 2-8%.

COMM notation for specifying collaborative and multimodal interactive systems

Multi-user multimodal interactive systems involve multiple users that can use multiple interaction modalities. Although multi-user multimodal systems are becoming more prevalent (especially multimodal systems involving multitouch surfaces), their design is still ad-hoc without properly keeping track of the design process. Addressing this issue of lack of design tools for multi-user multimodal systems, we present the COMM (Collaborative and MultiModal) notation and its on-line editor for specifying multi-user multimodal interactive systems. Extending the CTT notation, the salient features of the COMM notation include the concepts of interactive role and modal task as well as a refinement of the temporal operators applied to tasks using the Allen relationships. A multimodal military command post for the control of unmanned aerial vehicles (UAV) by two operators is used to illustrate the discussion.

EMG amplitude estimators based on probability distribution for muscle-computer interface

To develop an advanced muscle–computer interface (MCI) based on surface electromyography (EMG) signal, the amplitude estimations of muscle activities, i.e., root mean square (RMS) and mean absolute value (MAV) are widely used as a convenient and accurate input for a recognition system. Their classification performance is comparable to advanced and high computational time-scale methods, i.e., the wavelet transform. However, the signal-to-noise-ratio (SNR) performance of RMS and MAV depends on a probability density function (PDF) of EMG signals, i.e., Gaussian or Laplacian. The PDF of upper-limb motions associated with EMG signals is still not clear, especially for dynamic muscle contraction. In this paper, the EMG PDF is investigated based on surface EMG recorded during finger, hand, wrist and forearm motions. The results show that on average the experimental EMG PDF is closer to a Laplacian density, particularly for male subject and flexor muscle. For the amplitude estimation, MAV has a higher SNR, defined as the mean feature divided by its fluctuation, than RMS. Due to a same discrimination of RMS and MAV in feature space, MAV is recommended to be used as a suitable EMG amplitude estimator for EMG-based MCIs.

Towards Specifying Multimodal Collaborative User Interfaces: A Comparison of Collaboration Notations

Interactive systems including multiple interaction devices and surfaces for supporting the collaboration of a group of co-located users are increasingly common in various domains. Nevertheless few collaborative and multimodal interface specification notations are proposed. As a first step towards a notation for specifying a design solution prior to its software design and development, we adopt an empirical approach. We applied and compared four existing notations for collaborative systems by considering a case study, namely, a system for supporting informal co-located collaboration in hospital work. This paper reports the conclusions from this empirical comparison.

Probability Density Functions of Stationary Surface EMG Signals in Noisy Environments

The probability density function (pdf) of an electromyography (EMG) signal provides useful information for choosing an appropriate feature extraction technique. The pdf is influenced by many factors, including the level of contraction force, muscle type, and noise. In this paper, we investigated the pdfs of noisy EMG signals artificially contaminated with five different noise types: 1) Electrocardiography (ECG) interference; 2) many spurious background spikes; 3) white Gaussian noise; 4) motion artifact; and 5) power line interference at various levels of signal-to-noise ratio (SNR). In addition, we evaluated a set of statistical descriptors for identifying a noisy EMG signal from its pdf, specifically kurtosis, negentropy, L-kurtosis, and robust measures of kurtosis (KR1 and KR2). The results show that at low SNR (<;5 dB), all noise types affect the statistical descriptors for the pdf of a noisy EMG signal. In addition, KR2 performs the best among these descriptors in identifying a noisy EMG signal from its pdf, because it is computed based on the quantiles of the data. As a result, it can avoid the effects of outliers resulting in the correct identification of pdf shape of noisy EMGs with all contamination types and all levels of SNR.

Single user multitouch on the DiamondTouch: from 2 x 1D to 2D

The DiamondTouch is a widely used multi-touch surface that offers high quality touch detection and user identification. But its underlying detection mechanism relies on two 1D projections (x and y) of the 2D surface. This creates ambiguous responses when a single user exercises multiple contacts on the surface and limits the ability of the DiamondTouch to provide full support of common multi-touch interactions such as the unconstrained translation, rotation and scaling of objects with two fingers. This paper presents our solution to reduce this limitation. Our approach is based on a precise modeling, using mixtures of Gaussians, of the touch responses on each array of antennas. This greatly reduces the shadowing of the touch locations when two or more fingers align with each other. We use these accurate touch detections to implement two 1D touch trackers and a global 2D tracker. The evaluation of our system shows that, in many situations, it can provide the complete 2D locations of at least two contacts points from the same user.

SEPIA, a support for engineering persuasive interactive applications: properties and functions

Design and creativity call for a large exploration of the design space for getting the design right and the right design [6]. Creativity support tools aim at speeding up this exploration for either saving time or exploring more design alternatives. This paper addresses the design of persuasive interactive systems. It provides designers and developers with a conceptual tool for structuring the exploration of the design space. In the vain of the IFIP properties [1] that are largely used in engineering HCI (e.g., observability), SEPIA (Support for Engineering Persuasive Interactive Applications) elicits a set of properties and functions to be considered when engineering persuasive interactive systems. SEPIA is expected to foster creativity and thereby to make people go beyond the classical monitoring feature.

Innovative key features for mastering model complexity: flexilab, a multimodel editor illustrated on task modeling

Modeling Human Computer Interaction (HCI) is nowadays practiced by IT companies. However, it remains a straightforward task that requires some advanced User Interface (UI) modeling tools to ease the design of large-scale models. This includes tackling massive UI models, multiplicity of models, multiplicity of stakeholders and collaborative editing. This paper presents a UI multimodel editor for HCI, illustrated on task modeling. We present innovative key features (genericity, creativity, model conformity, reusability, etc.) to facilitate UI model design and to ease interaction.