Search

Methods to measure work stress generally rely on subjective measures from questionnaires or require dedicated sensors that are cumbersome to wear and interfere with the task. To address this problem, we propose a method to detect stress unobtrusively using commodity devices (keyboards, mice) instrumented with pressure sensors. We propose a minimalist design that can be easily replicated by other researchers using off-the-shelf and low-cost hardware. We validate the design in a laboratory experiment that simulates office tasks and mild stressors while avoiding methodological limitations of previous studies. We compare stress-detection performance when using conventional features reported in the literature (keystroke dynamics, mouse trajectories) augmented with information from pressure sensors. Our results indicate that pressure provides additional information for stress discrimination; adding pressure information to keystroke dynamics and mouse trajectories improves classification performance by 6% and 3%, respectively. These results show how devices that are already part of the modern workplace may be used and enhanced to automatically and unobtrusively detect stress.

Cranes play an important role in the industry sectors worldwide, such as construction, transport, shipping and cargo industry. For the safety of loading and unloading materials there are definitely ongoing improvements in the crane industry. However, there still remains issues related to the crane operation and control measures given by the pendulum swing while the crane is moving. To solve this problem a vision-based movement control of a 3 degrees of freedom (3 DOF) crane system, using both an analytical and experimental models based on displacements and adaptive optimization algorithms was proposed. The framework consists of three steps, more precise recognition, detection and tracking a set of targets within the image to compute the payload displacement. A prepossessing process was applied in order to enhance the image improving both the color information and the edge extraction task. Then, a set of targets within the image were detected to estimate the displacement. Then to solve the problem given by the displacement, a tracking task was implemented using a second order filter. This paper introduces a new strategy to determine the relationship between the movement of the spin in the jib and position of the markers within the image. Regression analysis was carried out to take into account the motion of the cart and the payload. In Results Section is shown a set of real-time experiment, obtaining euclidean errors of 1.41 pixel, 2 pixels and 3.16 pixels for Cart, Jib and Hoist, respectively.

Foreign accent conversion (FAC) is the problem of generating a synthetic voice that has the voice identity of a second-language (L2) learner and the pronunciation patterns of a native (L1) speaker. This synthetic voice has been referred to as a “golden-speaker” in the pronunciation-training literature. FAC is generally achieved by building a voice-conversion model that maps utterances from a source (L1) speaker onto the target (L2) speaker. As such, FAC requires that a reference utterance from the L1 speaker be available at synthesis time. This greatly restricts the application scope of the FAC system. In this work, we propose a “reference-free” FAC system that eliminates the need for reference L1 utterances at synthesis time, and transforms L2 utterances directly. The system is trained in two steps. First, a conventional FAC procedure is used to create a golden-speaker using utterances from a reference L1 speaker (which are then discarded) and the L2 speaker. Second, a pronunciation-correction model is trained to convert L2 utterances to match the golden-speaker utterances obtained in the first step. At synthesis time, the pronunciation-correction model directly transforms a novel L2 utterance into its golden-speaker counterpart. Our results show that the system reduces foreign accents in novel L2 utterances, achieving a 20.5% relative reduction in word-error-rate of an American English automatic speech recognizer and a 19% reduction in perceptual ratings of foreign accentedness obtained through listening tests. Over 73% of the listeners also rated golden-speaker utterances as having the same voice identity as the original L2 utterances.

This paper investigates the effect of reinforcement schedules on biofeedback games for stress self-regulation. In particular, it examines whether partial reinforcement can improve resistance to extinction of relaxation behaviors, i.e., once biofeedback is removed. Namely, we compare two types of reinforcement schedules (partial and continuous) in a mobile biofeedback game that encourages players to slow their breathing during gameplay. The game uses a negative-reinforcement instrumental conditioning paradigm, removing an aversive stimulus (random actions in the game) if players slows down their breathing. We conducted an experimental trial with 24 participants to compare the two reinforcement schedules against a control condition. Our results indicate that partial reinforcement improves resistance to extinction, as measured by breathing rate and skin conductance post-treatment. In addition, based on linear regression and correlation analysis we found that participants in the partial reinforcement learned to slow their breathing at the same pace as those under continuous reinforcement. The article discusses the implications of these results and directions for future work.

Biofeedback games are an attractive alternative to standard techniques for learning short-term relaxation skills. In this paper, we present the design, implementation, and evaluation of three respiratory biofeedback games. To validate these games, we compared breathing rate across 100 male participants (23 years ± 3.2 years) playing biofeedback and audio pacing versions of these games as well as a paced breathing app. The games were placed between repeat runs of a cognitively stressful Stroop-based task and the impact of the games on breathing and cognitive performance in the task also assessed. Our results showed that 1) differences in gameplay did not impact player performance; 2) biofeedback not only led to better breath control during play but also during the subsequent cognitively stressful task; and 3) biofeedback led to better attentional-cognitive performance in the subsequent task. Our multi-game experiments show that using respiratory biofeedback in video games is an effective strategy to learn paced breathing—on par with the standalone technique of paced breathing—and to self-regulate stress levels in later stressful scenarios. Furthermore, owing to its entertainment value, our relaxation solution has the potential to be more engaging and accessible than standalone paced breathing, for use over longer durations.

Sparse-coding techniques for voice conversion assume that an utterance can be decomposed into a sparse code that only carries linguistic contents, and a dictionary of atoms that captures the speakers’ characteristics. However, conventional dictionary-construction and sparse-coding algorithms rarely meet this assumption. The result is that the sparse code is no longer speaker-independent, which leads to lower voice-conversion performance. In this paper, we propose a Cluster-Structured Sparse Representation (CSSR) that improves the speaker independence of the representations. CSSR consists of two complementary components: a Cluster-Structured Dictionary Learning module that groups atoms in the dictionary into clusters, and a Cluster-Selective Objective Function that encourages each speech frame to be represented by atoms from a small number of clusters. We conducted four experiments on the CMU ARCTIC corpus to evaluate the proposed method. In a first ablation study, results show that each of the two CSSR components enhances speaker independence, and that combining both components leads to further improvements. In a second experiment, we find that CSSR uses increasingly larger dictionaries more efficiently than phoneme-based representations by allowing finer-grained decompositions of speech sounds. In a third experiment, results from objective and subjective measurements show that CSSR outperforms prior voice-conversion methods, improving the acoustic quality of the synthesized speech while retaining the target speaker's voice identity. Finally, we show that the CSSR captures latent (i.e., phonetic) information in the speech signal.

Accent conversion AC aims to transform non-native utterances to sound as if the speaker had a native accent. This can be achieved by mapping source speech spectra from a native speaker into the acoustic space of the target non-native speaker. In prior work, we proposed an AC approach that matches frames between the two speakers based on their acoustic similarity after compensating for differences in vocal tract length. In this paper, we propose a new approach that matches frames between the two speakers based on their phonetic rather than acoustic similarity. Namely, we map frames from the two speakers into a phonetic posteriorgram using speaker-independent acoustic models trained on native speech. We thoroughly evaluate the approach on a speech corpus containing multiple native and non-native speakers. The proposed algorithm outperforms the prior approach, improving ratings of acoustic quality 22% increase in mean opinion score and native accent 69% preference while retaining the voice quality of the non-native speaker. Furthermore, we show that the approach can be used in the reverse conversion direction, i.e., generating speech with a native speaker's voice quality and a non-native accent. Finally, we show that this approach can be applied to non-parallel training data, achieving the same accent conversion performance.

This paper compares the effectiveness of two biofeedback mechanisms to promote acquisition and transfer of deep-breathing skills using a casual videogame. The first biofeedback mechanism, game adaptation, delivers respiratory information by altering an internal parameter of the game; the second, visual biofeedback, displays respiratory information explicitly without altering the game. We conduct a user study that examines visual biofeedback and game adaptation as independent variables with electrodermal activity, heart rate variability, and respiration as dependent variables. In particular, we evaluate these forms of biofeedback by their ability to facilitate acquisition of relaxation skills and promote skill transfer to subsequent stressful tasks. Our results indicate that game adaptation promotes skill acquisition and transfer more effectively than visual biofeedback, but that a combination of the two outperforms either in isolation. Combining visual and game biofeedback also results in faster learning of deep-breathing skills than either channel alone. Our study suggests that the two forms of biofeedback play different roles, with game adaptation being more effective in encouraging deep breathing, and visual channels helping players maintain the target breathing rate.

The of the quality of odors emitted from automobile cabin interiors is an important element for the design of vehicles that meet prospective customers' expectations. Extending our previous work on machine-versus-human odor assessment for intact automobile cabin interiors, in this paper, we evaluated odors generated from individual interior parts using a human panel and field asymmetric ion mobility spectrometry (FAIMS). We used image processing techniques to extract geometric features from FAIMS dispersion fields, and built the predictive models for three odor assessment parameters (intensity, irritation, and pleasantness) by means of partial least squares regression. The best feature set was chosen by backward sequential feature selection. Using k -fold cross validation, we achieved statistically significant correlation 0.95 between human panel measured and machine olfaction predicted odor assessment scores with a sample set of 48 interior automobile parts. These results, generated using the geometric image processing methods demonstrated herein, further support the feasibility of replacing a human panel by machine olfaction for the assessment of odor quality of interior automobile parts.

Training stress-prediction models is challenging due to the difficulty in reliably eliciting stress and relaxation responses in participants. For example, a task intended to elicit a relaxation response (e.g., deep breathing) can have the opposite effect depending on the participant's appraisal of and familiarity with the exercise. Including such instances in a training set undermines the accuracy of the resulting prediction model. This paper presents a technique, ReBreathe , to identify such instances based on respiratory patterns and determine their accurate stress/relax labels. We compared this relabeling approach against two labeling techniques: 1) nominal labels obtained from the experimental protocol and 2) labels obtained from subjective assessments. We then trained generalized estimating equation regression models to predict the resulting stress/relax labels from measures of heart rate variability and electrodermal activity. Training the model using protocol labels achieved a classification rate of 0.53 on participants not included in the training set. Relabeling the exercises based on each participant's subjective ratings increased classification rates but only marginally (0.61). In contrast, relabeling the exercises based on respiratory patterns increased classification rates to 0.88, or a four-fold reduction in error rates. These results illustrate the unreliability of protocol and subjective labels during stress/relax exercises and the potential benefits of ReBreathe .

This paper presents an active-sensing framework for concentration-independent identification of volatile chemicals using a tunable infrared interferometer. The framework operates in real time to generate a sequence of absorption lines that can best discriminate among a given set of chemicals. The active-sensing algorithm was previously developed to optimize temperature programs for metal-oxide chemosensors. Here, we adapt it to tune a nondispersive infrared spectroscope on the basis of a Fabry-Perot interferometer (FPI). We also extend this framework to allow the identification of chemical samples irrespective of their concentrations. Therefore, we use nonnegative matrix factorization to create concentration-independent absorption profiles of different chemicals, and then employ linear least squares to fit sensor observations to the response profiles. We tested the framework on a simulated classification problem with 27 chemicals and compared against a passive sensing approach; the active-sensing consistently outperformed the passive sensing in terms of classification performance for various sensing budgets and at various levels of sensor noise. We also validated the approach experimentally using a commercial FPI sensor and a database of eight household chemicals. Our results show that the method can predict the sample identity irrespective of concentration.

We propose a concatenative synthesis approach to the problem of foreign accent conversion. The approach consists of replacing the most accented portions of nonnative speech with alternative segments from a corpus of the speaker's own speech based on their similarity to those from a reference native speaker. We propose and compare two approaches for selecting units, one based on acoustic similarity [e.g., mel frequency cepstral coefficients (MFCCs)] and a second one based on articulatory similarity, as measured through electromagnetic articulography (EMA). Our hypothesis is that articulatory features provide a better metric for linguistic similarity across speakers than acoustic features. To test this hypothesis, we recorded an articulatory-acoustic corpus from a native and a nonnative speaker, and evaluated the two speech representations (acoustic versus articulatory) through a series of perceptual experiments. Formal listening tests indicate that the approach can achieve a 20% reduction in perceived accent, but also reveal a strong coupling between accent and speaker identity. To address this issue, we disguised original and resynthesized utterances by altering their average pitch and normalizing vocal tract length. An additional listening experiment supports the hypothesis that articulatory features are less speaker dependent than acoustic features.

Chronic stress is endemic to modern society. However, as it is unfeasible for physicians to continuously monitor stress levels, its diagnosis is nontrivial. Wireless body sensor networks offer opportunities to ubiquitously detect and monitor mental stress levels, enabling improved diagnosis, and early treatment. This article describes the development of a wearable sensor platform to monitor a number of physiological correlates of mental stress. We discuss tradeoffs in both system design and sensor selection to balance information content and wearability. Using experimental signals collected from the wearable sensor, we describe a selected number of physiological features that show good correlation with mental stress. In particular, we propose a new spectral feature that estimates the balance of the autonomic nervous system by combining information from the power spectral density of respiration and heart rate variability. We validate the effectiveness of our approach on a binary discrimination problem when subjects are placed under two psychophysiological conditions: mental stress and relaxation. When used in a logistic regression model, our feature set is able to discriminate between these two mental states with a success rate of 81% across subjects.

This paper addresses a major weakness of traditional heart-rate-variability (HRV) analysis for the purpose of monitoring stress: sensitivity to respiratory influences. To address this issue, a linear system-identification model of the cardiorespiratory system using commercial heart rate monitors and respiratory sensors was constructed. Subtraction of respiratory driven fluctuations in heart rate leads to a residual signal where the effects of mental stress become more salient. We experimentally validated the effectiveness of this method on a binary discrimination problem with two conditions: mental stress of subjects performing cognitive tasks and a relaxation condition. In the process, we also propose a normalization method that can be used to compensate for ventilation differences between paced and spontaneous breathing. Our results suggest that, by separating respiration influences, the residual HRV has more discrimination power than traditional HRV analysis for the purpose of monitoring mental stress/load.

Various methods have recently appeared to transform foreign-accented speech into its native-accented counterpart. Evaluation of these accent conversion methods requires extensive listening tests across a number of perceptual dimensions. This article presents three objective measures that may be used to assess the acoustic quality, degree of foreign accent, and speaker identity of accent-converted utterances. Accent conversion generates novel utterances: those of a foreign speaker with a native accent. Therefore, the acoustic quality in accent conversion cannot be evaluated with conventional measures of spectral distortion, which assume that a clean recording of the speech signal is available for comparison. Here we evaluate a single-ended measure of speech quality, ITU-T recommendation P.563 for narrow-band telephony. We also propose a measure of foreign accent that exploits a weakness of automatic speech recognizers: their sensitivity to foreign accents. Namely, we use phoneme-level match scores given by the HTK recognizer trained on a large number of English American speakers to obtain a measure of native accent. Finally, we propose a measure of speaker identity that projects acoustic vectors (e.g., Mel cepstral, F0) onto the linear discriminant that maximizes separability for a given pair of source and target speakers. The three measures are evaluated on a corpus of accent-converted utterances that had been previously rated through perceptual tests. Our results show that the three measures have a high degree of correlation with their corresponding subjective ratings, suggesting that they may be used to accelerate the development of foreign-accent conversion tools. Applications of these measures in the context of computer assisted pronunciation training and voice conversion are also discussed.

Modulating the operating temperature of metal-oxide (MOX) chemical sensors gives rise to gas-specific signatures that provide a wealth of analytical information. In most cases, the operating temperature is modulated according to a standard waveform (e.g., ramp, sine wave). A few studies have approached the optimization of temperature profiles systematically, but these optimizations are performed offline and cannot adapt to changes in the environment. Here, we present an ?active perception? strategy based on Partially Observable Markov Decision Processes (POMDP) that allows the temperature program to be optimized in real time, as the sensor reacts to its environment. We characterize the method on a ternary classification problem using a simulated sensor model subjected to additive Gaussian noise, and compare it against two ?passive? approaches, a nai?ve Bayes classifier and a nearest neighbor classifier. Finally, we validate the method in real time using a Taguchi sensor exposed to three volatile compounds. Our results show that the POMDP outperforms both passive approaches and provides a strategy to balance classification performance and sensing costs.

The objective of this research is to develop a low-cost infrared absorption spectroscope based on linear variable filter technology for the automated detection of concentrated gases and vapors, and the semiautomated detection of liquids. This instrument represents an alternative to electronic-nose devices based on cross-selective gas sensor arrays. Instead, the proposed instrument uses the concept of computational ldquopseudosensors,rdquo whereby spectral lines in an analytical instrument are clustered into groups and used as independent variables. We characterize the system on a database of chemical mixtures, and evaluate it on two real-world applications in the foodstuffs domain: oil adulteration and trans-fatty acid detection. Our results show that the proposed system is a viable low-resolution, low-cost analytical technique for niche applications.

This paper presents a neuromorphic approach for sensor-based machine olfaction that combines a portable chemical detection system based on microbead array technology with a biologically inspired model of signal processing in the olfactory bulb. The sensor array contains hundreds of microbeads coated with solvatochromic dyes adsorbed in, or covalently attached on, the matrix of various microspheres. When exposed to odors, each bead sensor responds with corresponding intensity changes, spectral shifts, and time-dependent variations associated with the fluorescent sensors. The bead array responses are subsequently processed using a model of olfactory circuits that capture the following two functions: chemotopic convergence of receptor neurons and center on-off surround lateral interactions. The first circuit performs dimensionality reduction, transforming the high-dimensional microbead array response into an organized spatial pattern (i.e., an odor image). The second circuit enhances the contrast of these spatial patterns, improving the separability of odors. The model is validated on an experimental dataset containing the responses of a large array of microbead sensors to five different analytes. Our results indicate that the model is able to significantly improve the separability between odor patterns, compared to that available from the raw sensor response

This paper presents a computational model for chemical sensor arrays inspired by the first two stages in the olfactory pathway: distributed coding with olfactory receptor neurons and chemotopic convergence onto glomerular units. We propose a monotonic concentration-response model that maps conventional sensor-array inputs into a distributed activation pattern across a large population of neuroreceptors. Projection onto glomerular units in the olfactory bulb is then simulated with a self-organizing model of chemotopic convergence. The pattern recognition performance of the model is characterized using a database of odor patterns from an array of temperature modulated chemical sensors. The chemotopic code achieved by the proposed model is shown to improve the signal-to-noise ratio available at the sensor inputs while being consistent with results from neurobiology.

This work presents an integral system capable of generating animations with realistic dynamics, including the individualized nuances, of three-dimensional (3-D) human faces driven by speech acoustics. The system is capable of capturing short phenomena in the orofacial dynamics of a given speaker by tracking the 3-D location of various MPEG-4 facial points through stereovision. A perceptual transformation of the speech spectral envelope and prosodic cues are combined into an acoustic feature vector to predict 3-D orofacial dynamics by means of a nearest-neighbor algorithm. The Karhunen-Loe/spl acute/ve transformation is used to identify the principal components of orofacial motion, decoupling perceptually natural components from experimental noise. We also present a highly optimized MPEG-4 compliant player capable of generating audio-synchronized animations at 60 frames/s. The player is based on a pseudo-muscle model augmented with a nonpenetrable ellipsoidal structure to approximate the skull and the jaw. This structure adds a sense of volume that provides more realistic dynamics than existing simplified pseudo-muscle-based approaches, yet it is simple enough to work at the desired frame rate. Experimental results on an audiovisual database of compact TIMIT sentences are presented to illustrate the performance of the complete system.

This work represents the first attempt to develop a sensory system, specifically designed for the characterization of wines, which combines three sensory modalities: an array of gas sensors, an array of electrochemical liquid sensors, and an optical system to measure color by means of CIElab coordinates. This new analytical tool, that has been called "electronic panel," includes not only sensors, but also hardware (injection system and electronics) and the software necessary for fusing information from the three modules. Each of the three sensory modalities (volatiles, liquids, and color) has been designed, tested, and optimized separately. The discrimination capabilities of the system have been evaluated on a database consisting of six red Spanish wines prepared using the same variety of grape (tempranillo) but differing in their geographic origins and aging stages. Sensor signals from each module have been combined and analyzed using pattern recognition techniques. The results of this work show that the discrimination capabilities of the system are significantly improved when signals from each module are combined to form a multimodal feature vector.

This year is the 10th anniversary of the first special issue on machine olfaction of the IEEE SENSORS JOURNAL. During this past decade, the field has grown in a number of exciting directions, including spectroscopic and olfactory receptorbased sensing, computational models of olfactory processing, and mobile and distributed sensing. This second special issue provides a timely update on advances during the past decade (as well as a vantage point from which to evaluate the last 30 years) in the field and, more importantly, the challenges that still lie ahead. It includes invited papers based upon presentations give at the International Symposium on Olfaction and Chemical Sensing (ISOCS) that was held in New York Digital Object Identifier 10.1109/JSEN.2012.2215434 City in 2011 (see www.olfactionsociety.org). To provide a balanced view of the various advances in the field, the special issue is organized into six distinct topic areas: biological sensors, chemical sensors, sensor systems, data processing, and electronic nose applications. The topic area of biological sensors recognises the fact that considerable effort is being directed towards improving the capability of artificial olfactory sensors by exploring more closely the biological system and seeking to mimic it more closely.

Pattern analysis constitutes a critical building block in the development of gas sensor array instruments capable of detecting, identifying, and measuring volatile compounds, a technology that has been proposed as an artificial substitute for the human olfactory system. The successful design of a pattern analysis system for machine olfaction requires a careful consideration of the various issues involved in processing multivariate data: signal-preprocessing, feature extraction, feature selection, classification, regression, clustering, and validation. A considerable number of methods from statistical pattern recognition, neural networks, chemometrics, machine learning, and biological cybernetics have been used to process electronic nose data. The objective of this review paper is to provide a summary and guidelines for using the most widely used pattern analysis techniques, as well as to identify research directions that are at the frontier of sensor-based machine olfaction.

This paper describes a portable electronic nose based on embedded PC technology. The instrument combines a small footprint with the versatility offered by embedded technology in terms of software development and digital communications services. A summary of the proposed hardware and software solutions is provided with an emphasis on data processing. Data evaluation procedures available in the instrument include automatic feature selection by means of SFFS, feature extraction with linear discriminant analysis (LDA) and principal component analysis (PCA), multi-component analysis with partial least squares (PLS) and classification through k-NN and Gaussian mixture models. In terms of instrumentation, the instrument makes use of temperature modulation to improve the selectivity of commercial metal oxide gas sensors. Field applications of the instrument, including experimental results, are also presented.

The performance of a pattern recognition system is dependent on, among other things, an appropriate data-preprocessing technique, In this paper, we describe a method to evaluate the performance of a variety of these techniques for the problem of odour classification using an array of gas sensors, also referred to as an electronic nose. Four experimental odour databases with different complexities are used to score the data-preprocessing techniques. The performance measure used is the cross-validation estimate of the classification rate of a K nearest neighbor voting rule operating on Fisher's linear discriminant projection subspace.

Witnessing the swift advances in the electronic means of seeing and hearing, scientists and engineers scent a market for systems mimicking the human nose. Already commercial systems from several companies are targeting applications, present and potential, that range from quality assurance of food and drugs to medical diagnosis, environmental monitoring, safety and security and military use. Here, the authors outline the major transducer technologies-in one sense, the key component of an electronic nose.

This paper presents a probabilistic model of ultrasonic range sensors using backpropagation neural networks trained on experimental data. The sensor model provides the probability of detecting mapped obstacles in the environment, given their position and orientation relative to the transducer. The detection probability can be used to compute the location of an autonomous vehicle from those obstacles that are more likely to be detected. The neural network model is more accurate than other existing approaches, since it captures the typical multilobal detection pattern of ultrasonic transducers. Since the network size is kept small, implementation of the model on a mobile robot can be efficient for real-time navigation. An example that demonstrates how the credence could be incorporated into the extended Kalman filter (EKF) and the numerical values of the final neural network weights are provided in the appendices.