Detection of Hypoglycemia and Hyperglycemia Using Noninvasive Wearable Sensors: Electrocardiograms and Accelerometry

BACKGROUND

Monitoring glucose excursions is important in diabetes management. This can be achieved using continuous glucose monitors (CGMs). However, CGMs are expensive and invasive. Thus, alternative low-cost noninvasive wearable sensors capable of predicting glycemic excursions could be a game changer to manage diabetes.

METHODS

In this article, we explore two noninvasive sensor modalities, electrocardiograms (ECGs) and accelerometers, collected on five healthy participants over two weeks, to predict both hypoglycemic and hyperglycemic excursions. We extract 29 features encompassing heart rate variability features from the ECG, and time- and frequency-domain features from the accelerometer. We evaluated two machine learning approaches to predict glycemic excursions: a classification model and a regression model.

RESULTS

The best model for both hypoglycemia and hyperglycemia detection was the regression model based on ECG and accelerometer data, yielding 76% sensitivity and specificity for hypoglycemia and 79% sensitivity and specificity for hyperglycemia. This had an improvement of 5% in sensitivity and specificity for both hypoglycemia and hyperglycemia when compared with using ECG data alone.

CONCLUSIONS

Electrocardiogram is a promising alternative not only to detect hypoglycemia but also to predict hyperglycemia. Supplementing ECG data with contextual information from accelerometer data can improve glucose prediction.

A Review of Digital Innovations for Diet Monitoring and Precision Nutrition

This article provides an up-to-date review of technological advances in 3 key areas related to diet monitoring and precision nutrition. First, we review developments in mobile applications, with a focus on food photography and artificial intelligence to facilitate the process of diet monitoring. Second, we review advances in 2 types of wearable and handheld sensors that can potentially be used to fully automate certain aspects of diet logging: physical sensors to detect moments of dietary intake, and chemical sensors to estimate the composition of diets and meals. Finally, we review new programs that can generate personalized/precision nutrition recommendations based on measurements of gut microbiota and continuous glucose monitors with artificial intelligence. The article concludes with a discussion of potential pitfalls of some of these technologies.

Modeling Individual Differences in Food Metabolism through Alternating Least Squares

Understanding how macronutrients (e.g., carbohydrates, protein, fat) affect blood glucose is of broad interest in health and dietary research. The general effects are well known, e.g., adding protein and fat to a carbohydrate-based meal tend to reduce blood glucose. However, there are large individual differences in food metabolism, to where the same meal can lead to different glucose responses across individuals. To address this problem, we present a technique that can be used to simultaneously (1) model macronutrients' effects on glucose levels over time and (2) capture inter-individual differences in sensitivity to macronutrients. The model assumes that each macronutrient adds a basis function to the differences in macronutrient metabolism. The technique performs a linear decomposition of glucose responses, alternating between estimating the macronutrients' effect over time and capturing an individual's sensitivity to macronutrients. On an experimental dataset containing glucose responses to a variety of mixed meals, the technique is able to extract basis functions for the macronutrients that are consistent with their hypothesized effects on PPGRs, and also characterize how macronutrients affect individuals differently.

Evaluating the Role of Breathing Guidance on Game-Based Interventions for Relaxation Training

Working in a fast-paced environment can lead to shallow breathing, which can exacerbate stress and anxiety. To address this issue, this study aimed to develop micro-interventions that can promote deep breathing in the presence of stressors. First, we examined two types of breathing guides to help individuals learn deep breathing: providing their breathing rate as a biofeedback signal, and providing a pacing signal to which they can synchronize their breathing. Second, we examined the extent to which these two breathing guides can be integrated into a casual game, to increase enjoyment and skill transfer. We used a 2 × 2 factorial design, with breathing guide (biofeedback vs. pacing) and gaming (game vs. no game) as independent factors. This led to four experimental groups: biofeedback alone, biofeedback integrated into a game, pacing alone, and pacing integrated into a game. In a first experiment, we evaluated the four experimental treatments in a laboratory setting, where 30 healthy participants completed a stressful task before and after performing one of the four treatments (or a control condition) while wearing a chest strap that measured their breathing rate. Two-way ANOVA of breathing rates, with treatment (5 groups) and time (pre-test, post-test) as independent factors shows a significant effect for time [F(4, 50) = 18.49, p < 0.001, η t i m e 2 = 0 . 27 ] and treatment [F(4, 50) = 2.54, p = 0.05, η² = 0.17], but no interaction effects. Post-hoc t-tests between pre and post-test breathing rates shows statistical significance for the game with biofeedback group [t(5) = 5.94, p = 0.001, d = 2.68], but not for the other four groups, indicating that only game with biofeedback led to skill transfer at post-test. Further, two-way ANOVA of self-reported enjoyment scores on the four experimental treatments, with breathing guide and game as independent factors, found a main effect for game [ F ( 1 , 20 ) = 24 . 49 , p < 0 . 001 ,   η g a m e 2 = 0 . 55 ], indicating that the game-based interventions were more enjoyable than the non-game interventions. In a second experiment, conducted in an ambulatory setting, 36 healthy participants practiced one of the four experimental treatments as they saw fit over the course of a day. We found that the game-based interventions were practiced more often than the non-game interventions [t (34) = 1.99, p = 0.027, d = 0.67]. However, we also found that participants in the game-based interventions could only achieve deep breathing 50% of the times, whereas participants in the non-game groups succeeded 85% of the times, which indicated that the former need adequate training time to be effective. Finally, participant feedback indicated that the non-game interventions were better at promoting in-the-moment relaxation, whereas the game-based interventions were more successful at promoting deep breathing during stressful tasks.

Predicting the macronutrient composition of mixed meals from dietary biomarkers in blood

Diet monitoring is an essential intervention component for a number of diseases, from type 2 diabetes to cardiovascular diseases. However, current methods for diet monitoring are burdensome and often inaccurate. In prior work, we showed that continuous glucose monitors (CGMs) may be used to predict the macronutrients in a meal (e.g., carbohydrates, protein, and fat) by analyzing the shape of the post-prandial glucose response. The objective of this study was to examine a number of additional dietary biomarkers in blood by their ability to improve the prediction of meal macronutrients, compared to using CGMs alone. As our experimental method, we conducted a nutritional study where (n=10) participants consumed nine different mixed meals with varied but known macronutrient amounts, and we analyzed the concentration of 33 dietary biomarkers (including amino acids and their combinations, insulin, triglycerides, and 3 independent measures of glucose) at various times post-prandially. As our computational method, we built machine learning models to predict the macronutrient amounts from (1) individual biomarkers and (2) their combinations. The major result from this work is that the additional blood biomarkers provide complementary information, and more importantly, achieve higher prediction performance for the three macronutrients in terms of normalized root mean squared error (carbohydrates: 22.9%; protein: 23.4%; fat: 32.3%) than CGMs alone (carbohydrates: 28.2%, p = 0.08; protein: 42.9%, p<0.001; fat: 41.4%, p<0.05}). Our main conclusion is that augmenting CGMs to measure these additional dietary biomarkers improves macronutrient prediction performance, and may ultimately lead to the development of automated methods to monitor monitor nutritional intake. This work is significant to biomedical research as it provides a potential solution to the long-standing problem of diet monitoring, facilitating new interventions for a number of diseases.

Postprandial concentration of circulating branched chain amino acids are able to predict the carbohydrate content of the ingested mixed meal

BACKGROUND

The amount of the macronutrients protein and carbohydrate (CHO) in a mixed meal is known to affect each other's digestion, absorption, and subsequent metabolism. While the effect of the amount of dietary protein and fat on the glycemic response is well studied, the ability of postprandial plasma amino acid patterns to predict the meal composition is unknown.

OBJECTIVE

To study the postprandial plasma amino acid patterns in relation to the protein, CHO, and fat content of different mixed meals and to investigate if these patterns can predict the macronutrient meal composition.

DESIGN

Ten older adults were given 9 meals with 3 different levels (low, medium, and high) of protein, CHO, and fat in different combinations, taking the medium content as that of a standardized western meal. We monitored the postprandial plasma response for amino acids, glucose, insulin, and triglycerides for 8 h and the areas under the curve (AUC) were subsequently calculated. Multiple regression analysis was performed to determine if amino acid patterns could predict the meal composition.

RESULTS

Increasing meal CHO content reduced the postprandial plasma response of several amino acids including all branched chain amino acids (BCAA) (leucine; q < 0.0001, isoleucine; q = 0.0035, valine; q = 0.0022). The plasma BCAA patterns after the meal significantly predicted the meal's CHO content (leucine; p < 0.0001, isoleucine; p = 0.0003, valine; p = 0.0008) along with aspartate (p < 0.0001), tyrosine (p < 0.0001), methionine (p = 0.0159) and phenylalanine (p = 0.0332). Plasma citrulline predicted best the fat content of the meal (p = 0.0024).

CONCLUSIONS

The postprandial plasma BCAA patterns are lower with increasing meal CHO content and are strong predictors of a mixed meal protein and CHO composition, as are plasma citrulline for the fat content. We hypothesize that postprandial plasma amino acid concentrations can be used to predict the meal's macronutrient composition.

A Longitudinal Evaluation of Tablet-Based Child Speech Therapy with Apraxia World

Digital games can make speech therapy exercises more enjoyable for children and increase their motivation during therapy. However, many such games developed to date have not been designed for long-term use. To address this issue, we developed Apraxia World, a speech therapy game specifically intended to be played over extended periods. In this study, we examined pronunciation improvements, child engagement over time, and caregiver and automated pronunciation evaluation accuracy while using our game over a multi-month period. Ten children played Apraxia World at home during two counterbalanced 4-week treatment blocks separated by a 2-week break. In one treatment phase, children received pronunciation feedback from caregivers and in the other treatment phase, utterances were evaluated with an automated framework built into the game. We found that children made therapeutically significant speech improvements while using Apraxia World, and that the game successfully increased engagement during speech therapy practice. Additionally, in offline mispronunciation detection tests, our automated pronunciation evaluation framework outperformed a traditional method based on goodness of pronunciation scoring. Our results suggest that this type of speech therapy game is a valid complement to traditional home practice.

The influence of type of feedback during tablet-based delivery of intensive treatment for childhood apraxia of speech

PURPOSE

One of the key principles of motor learning supports using knowledge of results feedback (KR, i.e., whether a response was correct / incorrect only) during high intensity motor practice, rather than knowledge of performance (KP, i.e., whether and how a response was correct/incorrect). In the future, mobile technology equipped with automatic speech recognition (ASR) could provide KR feedback, enabling this practice to move outside the clinic, supplementing speech pathology sessions and reducing burden on already stretched speech-language pathology resources. Here, we employ a randomized controlled trial design to test the impact of KR vs KP feedback on children's response to the Nuffield Dyspraxia Programme 3, delivered through an android tablet. At the time of testing, ASR was not feasible and so correctness of responses was decided by the treating clinician.

METHOD

Fourteen children with CAS, aged 4-10 years, participated in a parallel group design, matched for age and severity of CAS. Both groups attended a university clinic for 1-hr therapy sessions 4 days a week for 3 weeks. One group received high frequency feedback comprised of both KR and KP, in the style of traditional, face-to-face intensive intervention on all days. The other group received high frequency KR + KP feedback on 1 day per week and high frequency KR feedback on the other 3 days per week, simulating the service delivery model of one clinic session per week supported by tablet-based home practice.

RESULTS

Both groups had significantly improved speech outcomes at 4-months post-treatment. Post-hoc comparisons suggested that only the KP group showed a significant change from pre- to immediately post-treatment but the group difference had dissipated by 1-month post-treatment. Heterogeneity in response to intervention within the groups suggests that other factors, not measured here, may be having a substantive influence on response to intervention and feedback type.

CONCLUSION

Mobile technology has the potential to increase motivation and engagement with therapy and to mitigate barriers associated with distance and access to speech pathology services. Further research is needed to explore the influence of type and frequency of feedback on motor learning, optimal timing for transitioning from KP to KR feedback, and how these parameters interact with task, child and context-related factors.

All-nanoparticle layer-by-layer coatings for Mid-IR on-chip gas sensing

Functionalization of optical waveguides with submicron all-nanoparticle coatings significantly enhanced the detection of acetone. Such coatings were enabled via precise control of the substrate withdrawal speed using the layer-by-layer deposition.

Stress and productivity patterns of interrupted, synergistic, and antagonistic office activities

We describe a controlled experiment, aiming to study productivity and stress effects of email interruptions and activity interactions in the modern office. The measurement set includes multimodal data for n = 63 knowledge workers who volunteered for this experiment and were randomly assigned into four groups: (G1/G2) Batch email interruptions with/without exogenous stress. (G3/G4) Continual email interruptions with/without exogenous stress. To provide context, the experiment's email treatments were surrounded by typical office tasks. The captured variables include physiological indicators of stress, measures of report writing quality and keystroke dynamics, as well as psychometric scores and biographic information detailing participants' profiles. Investigations powered by this dataset are expected to lead to personalized recommendations for handling email interruptions and a deeper understanding of synergistic and antagonistic office activities. Given the centrality of email in the modern office, and the importance of office work to people's lives and the economy, the present data have a valuable role to play.

Tradeoffs in the Efficient Detection of Sign Language Content in Video Sharing Sites

Video sharing sites have become keepers of de-facto digital libraries of sign language content, being used to store videos including the experiences, knowledge, and opinions of many in the deaf or hard of hearing community. Due to limitations of term-based search over metadata, these videos can be difficult to find, reducing their value to the community. Another result is that community members frequently engage in a push-style delivery of content (e.g., emailing or posting links to videos for others in the sign language community) rather than having access be based on the information needs of community members. In prior work, we have shown the potential to detect sign language content using features derived from the video content rather than relying on metadata. Our prior technique was developed with a focus on accuracy of results and are quite computationally expensive, making it unrealistic to apply them on a corpus the size of YouTube or other large video sharing sites. Here, we describe and examine the performance of optimizations that reduce the cost of face detection and the length of video segments processed. We show that optimizations can reduce the computation time required by 96%, while losing only 1% in F1 score. Further, a keyframe-based approach is examined that removes the need to process continuous video. This approach achieves comparable recall but lower precision than the above techniques. Merging the advantages of the optimizations, we also present a staged classifier, where the keyframe approach is used to reduce the number of non-sign language videos fully processed. An analysis of the staged classifier shows a further reduction in average computation time per video while achieving similar quality of results.

Automated speech analysis tools for children's speech production: A systematic literature review

PURPOSE

A systematic search and review of published studies was conducted on the use of automated speech analysis (ASA) tools for analysing and modifying speech of typically-developing children learning a foreign language and children with speech sound disorders to determine (i) types, attributes, and purposes of ASA tools being used; (ii) accuracy against human judgment; and (iii) performance as therapeutic tools.

METHOD

Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines were applied. Across nine databases, 32 articles published between January 2007 and December 2016 met inclusion criteria: (i) focussed on children's speech; (ii) tools used for speech analysis or modification; and (iii) reporting quantitative data on accuracy.

RESULT

Eighteen ASA tools were identified. These met the clinical threshold of 80% agreement with human judgment when used as predictors of intelligibility, impairment severity, or error category. Tool accuracy was typically <80% accuracy for words containing mispronunciations. ASA tools have been used effectively to improve to children's foreign language pronunciation.

CONCLUSION

ASA tools show promise for automated analysis and modification of children's speech production within assessment and therapeutic applications. Further work is needed to train automated systems with larger samples of speech to increase accuracy for assessment and therapeutic feedback.

Speech-driven mobile games for speech therapy: User experiences and feasibility

Purpose: To assist in remote treatment, speech-language pathologists (SLPs) rely on mobile games, which though entertaining, lack feedback mechanisms. Games integrated with automatic speech recognition (ASR) offer a solution where speech productions control gameplay. We therefore performed a feasibility study to assess children's and SLPs' experiences towards speech-controlled games, game feature preferences and ASR accuracy. Method: Ten children with childhood apraxia of speech (CAS), six typically developing (TD) children and seven SLPs trialled five games and answered questionnaires. Researchers also compared the results of ASR to perceptual judgment. Result: Children and SLPs found speech-controlled games interesting and fun, despite ASR-human disagreements. They preferred games with rewards, challenge and multiple difficulty levels. Automatic speech recognition-human agreement was higher for SLPs than children, similar between TD and CAS and unaffected by CAS severity (77% TD, 75% CAS - incorrect; 51% TD, 47% CAS, 71% SLP - correct). Manual stop recording yielded higher agreement than automatic. Word length did not influence agreement. Conclusion: Children's and SLPs' positive responses towards speech-controlled games suggest that they can engage children in higher intensity practice. Our findings can guide future improvements to the ASR, recording methods and game features to improve the user experience and therapy adherence.

Knowledge-driven dictionaries for sparse representation of continuous glucose monitoring signals

Continuous glucose monitoring (CGM) of patients with diabetes allows the effective management of the disease and reduces the risk of hypoglycemic or hyperglycemic episodes. Towards this goal, the development of reliable CGM models is essential for representing the corresponding signals and interpreting them with respect to factors and outcomes of interest. We propose a sparse decomposition model to approximate CGM time-series as a linear combination of a small set of exemplar atoms, appropriately designed through parametric functions to capture the main fluctuations of the CGM signal. Sparse decomposition is performed through the orthogonal matching pursuit (OMP). Results indicate that the proposed model provides 0.1 relative reconstruction error with 0.8 compression rate on a publicly available dataset containing 25 patients diagnosed with Type 1 diabetes. The atoms selected from the OMP procedure can be further interpreted in relation to the clinically meaningful components of the CGM signal (e.g. glucose spikes, hypoglycemic episodes, etc.

Real-Time Gas Mixture Analysis Using Mid-Infrared Membrane Microcavities

Real-time gas analysis on-a-chip was demonstrated using a mid-infrared (mid-IR) microcavity. Optical apertures for the microcavity were made of ultrathin silicate membranes embedded in a silicon chip using the complementary metal-oxide-semiconductor (CMOS) process. Fourier transform infrared spectroscopy (FTIR) shows that the silicate membrane is transparent in the range of 2.5-6.0 μm, a region that overlaps with multiple characteristic gas absorption lines and therefore enables gas detection applications. A test station integrating a mid-IR tunable laser, a microgas delivery system, and a mid-IR camera was assembled to evaluate the gas detection performance. CH₄, CO₂, and N₂O were selected as analytes due to their strong absorption bands at λ = 3.25-3.50, 4.20-4.35, and 4.40-4.65 μm, which correspond to C-H, C-O, and O-N stretching, respectively. A short subsecond response time and high gas identification accuracy were achieved. Therefore, our chip-scale mid-IR sensor provides a new platform for an in situ, remote, and embedded gas monitoring system.

BioPad: Leveraging off-the-Shelf Video Games for Stress Self-Regulation

This paper presents an approach to use commercial videogames for biofeedback training. It consists of intercepting signals from the game controller and adapting them in real-time based on physiological measurements from the player. We present three sample implementations and a case study for teaching stress self-regulation via an immersive car racing game. We use a crossover gaming device to manipulate controller signals, and a respiratory sensor to monitor the players' breathing rate. We then alter the speed of the car to encourage slow deep breathing, in this way, allowing players to reduce their arousal while playing the game. We evaluate the approach against an alternative form of biofeedback that uses a graphic overlay to convey physiological information, and a control condition (playing the game without biofeedback). Experimental results show that our approach can promote deep breathing during gameplay, and also during a subsequent task, once biofeedback is removed. Our results also indicate that delivering biofeedback through subtle changes in gameplay can be as effective as delivering them directly through a visual display. These results open the possibility to develop low-cost and engaging biofeedback interventions using a variety of commercial videogames to promote adherence.

Active wavelength selection for mixture identification with tunable mid-infrared detectors

This article presents a wavelength selection framework for mixture identification problems. In contrast with multivariate calibration, where the mixture constituents are known and the goal is to estimate their concentration, in mixture identification the goal is to determine which of a large number of chemicals is present. Due to the combinatorial nature of this problem, traditional wavelength selection algorithms are unsuitable because the optimal set of wavelengths is mixture dependent. To address this issue, our framework interleaves wavelength selection with the sensing process, such that each subsequent wavelength is determined on-the-fly based on previous measurements. To avoid early convergence, our approach starts with an exploratory criterion that samples the spectrum broadly, then switches to an exploitative criterion that selects increasingly more relevant wavelengths as the solution approaches the true constituents of the mixture. We compare this "active" wavelength selection algorithm against a state-of-the-art passive algorithm (successive projection algorithm), both experimentally using a tunable spectrometer and in simulation using a large spectral library of chemicals. Our results show that our active method can converge to the true solution more frequently and with fewer measurements than the passive algorithm. The active method also leads to more compact solutions with fewer false positives.

Physiological Modalities for Relaxation Skill Transfer in Biofeedback Games

We present an adaptive biofeedback game for teaching self-regulation of stress. Our approach consists of monitoring the user's physiology during gameplay and adapting the game using a positive feedback loop that rewards relaxing behaviors and penalizes states of high arousal. We evaluate the approach using a casual game under three biofeedback modalities: electrodermal activity, heart rate variability, and breathing rate. The three biosignals can be measured noninvasively with wearable sensors, and represent different degrees of voluntary control and selectivity toward arousal. We conducted an experiment trial with 25 participants to compare the three modalities against a standard treatment (deep breathing) and a control condition (the game without biofeedback). Our results indicate that breathing-based game biofeedback is more effective in inducing relaxation during treatment than the other four groups. Participants in this group also showed greater retention of the relaxation skills (without biofeedback) during a subsequent stressor.

Development of a Remote Therapy Tool for Childhood Apraxia of Speech

We present a multitier system for the remote administration of speech therapy to children with apraxia of speech. The system uses a client-server architecture model and facilitates task-oriented remote therapeutic training in both in-home and clinical settings. The system allows a speech language pathologist (SLP) to remotely assign speech production exercises to each child through a web interface and the child to practice these exercises in the form of a game on a mobile device. The mobile app records the child's utterances and streams them to a back-end server for automated scoring by a speech-analysis engine. The SLP can then review the individual recordings and the automated scores through a web interface, provide feedback to the child, and adapt the training program as needed. We have validated the system through a pilot study with children diagnosed with apraxia of speech, their parents, and SLPs. Here, we describe the overall client-server architecture, middleware tools used to build the system, speech-analysis tools for automatic scoring of utterances, and present results from a clinical study. Our results support the feasibility of the system as a complement to traditional face-to-face therapy through the use of mobile tools and automated speech analysis algorithms.

Reduction of non-native accents through statistical parametric articulatory synthesis

This paper presents an articulatory synthesis method to transform utterances from a second language (L2) learner to appear as if they had been produced by the same speaker but with a native (L1) accent. The approach consists of building a probabilistic articulatory synthesizer (a mapping from articulators to acoustics) for the L2 speaker, then driving the model with articulatory gestures from a reference L1 speaker. To account for differences in the vocal tract of the two speakers, a Procrustes transform is used to bring their articulatory spaces into registration. In a series of listening tests, accent conversions were rated as being more intelligible and less accented than L2 utterances while preserving the voice identity of the L2 speaker. No significant effect was found between the intelligibility of accent-converted utterances and the proportion of phones outside the L2 inventory. Because the latter is a strong predictor of pronunciation variability in L2 speech, these results suggest that articulatory resynthesis can decouple those aspects of an utterance that are due to the speaker's physiology from those that are due to their linguistic gestures.

Identifying Sign Language Videos in Video Sharing Sites

Video sharing sites enable members of the sign language community to record and share their knowledge, opinions, and worries on a wide range of topics. As a result, these sites have formative digital libraries of sign language content hidden within their large overall collections. This article explores the problem of locating these sign language (SL) videos and presents techniques for identifying SL videos in such collections. To determine the effectiveness of existing text-based search for locating these SL videos, a series of queries were issued to YouTube to locate SL videos on the top 10 news stories of 2011 according to Yahoo!. Overall precision for the first page of results (up to 20 results) was 42%. An approach for automatically detecting SL video is then presented. Five video features considered likely to be of value were developed using standard background modeling and face detection. The article compares the results of an SVM classifier when given all permutations of these five features. The results show that a measure of the symmetry of motion relative to the face position provided the best performance of any single feature. When tested against a challenging test collection that included many likely false positives, an SVM provided with all five features achieved 82% precision and 90% recall. In contrast, the text-based search (queries with the topic terms and “ASL” or “sign language”) returned a significant portion of non-SL content---nearly half of all videos found. By our estimates, the application of video-based filtering techniques such as the one proposed here would increase precision from 42% for text-based queries up to 75%.

Using an ambulatory stress monitoring device to identify relaxation due to untrained deep breathing

The objective of this paper is to assess the efficacy of deep breathing as a relaxation activity using a wearable stress monitor. For this purpose, we developed a protocol with different mentally stressful activities interleaved with regular sessions of deep breathing. We used three physiological sensors: a heart rate monitor, a respiration sensor, and an electrodermal activity sensor, to extract parameters that are consistent with the dominance of the sympathetic nervous system. Our results indicate that a large number of subjects were not able to perform the paced deep breathing exercise properly, which caused their stress levels to increase rather than to decrease. The study also showed that our wearable stress monitor can be used to monitor breathing technique and assess its effectiveness in relaxing individuals.

A method for evaluating data-preprocessing techniques for odour classification with an array of gas sensors

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.

Habituation in the KIII olfactory model with chemical sensor arrays

This paper presents a novel combination of chemical sensors and the KIII model for simulating mixture perception with a habituation process triggered by local activity. Stimuli are generated by partitioning feature space with labeled lines. Pattern completion is demonstrated through coherent oscillations across granule populations using experimental odor mixtures.

Consistency and validity of self-reporting scores in stress measurement surveys

Stress has been attributed to physiological and psychological demands that exceed the natural regulatory capacity of a person. Chronic stress is not only a catalyst for diseases such as hypertension, diabetes, insomnia but may also lead to social problems such as marriage breakups, suicide and violence. Objective assessment of stress is difficult so self-reports are commonly used to indicate the severity of stress. However, empirical information on the validity of self-reports is limited. The present study investigated the authenticity and validity of different self-report surveys. An analysis, based on a three-pronged strategy, was performed on these surveys. It was concluded that although subjects are prone to systematic error in reporting, self-reports can provide a useful substitute for data modeling specifically in stress evaluation where other objective assessments such as determination of stress using only physiological response are difficult.

Development and evaluation of an ambulatory stress monitor based on wearable sensors

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.

Web GIS in practice X: a Microsoft Kinect natural user interface for Google Earth navigation

This paper covers the use of depth sensors such as Microsoft Kinect and ASUS Xtion to provide a natural user interface (NUI) for controlling 3-D (three-dimensional) virtual globes such as Google Earth (including its Street View mode), Bing Maps 3D, and NASA World Wind. The paper introduces the Microsoft Kinect device, briefly describing how it works (the underlying technology by PrimeSense), as well as its market uptake and application potential beyond its original intended purpose as a home entertainment and video game controller. The different software drivers available for connecting the Kinect device to a PC (Personal Computer) are also covered, and their comparative pros and cons briefly discussed. We survey a number of approaches and application examples for controlling 3-D virtual globes using the Kinect sensor, then describe Kinoogle, a Kinect interface for natural interaction with Google Earth, developed by students at Texas A&M University. Readers interested in trying out the application on their own hardware can download a Zip archive (included with the manuscript as additional files 1, 2, &3) that contains a 'Kinnogle installation package for Windows PCs'. Finally, we discuss some usability aspects of Kinoogle and similar NUIs for controlling 3-D virtual globes (including possible future improvements), and propose a number of unique, practical 'use scenarios' where such NUIs could prove useful in navigating a 3-D virtual globe, compared to conventional mouse/3-D mouse and keyboard-based interfaces.

Feature selection for inductive generalization

Judging similarities among objects, events, and experiences is one of the most basic cognitive abilities, allowing us to make predictions and generalizations. The main assumption in similarity judgment is that people selectively attend to salient features of stimuli and judge their similarities on the basis of the common and distinct features of the stimuli. However, it is unclear how people select features from stimuli and how they weigh features. Here, we present a computational method that helps address these questions. Our procedure combines image-processing techniques with a machine-learning algorithm and assesses feature weights that can account for both similarity and categorization judgment data. Our analysis suggests that a small number of local features are particularly important to explain our behavioral data.

Adaptive microsensor systems

We provide a broad review of approaches for developing chemosensor systems whose operating parameters can adapt in response to environmental changes or application needs. Adaptation may take place at the instrumentation level (e.g., tunable sensors) and at the data-analysis level (e.g., adaptive classifiers). We discuss several strategies that provide tunability at the device level: modulation of internal sensing parameters, such as frequencies and operation voltages; variation of external parameters, such as exposure times and catalysts; and development of compact microanalysis systems with multiple tuning options. At the data-analysis level, we consider adaptive filters for change, interference, and drift rejection; pattern classifiers that can adapt to changes in the statistical properties of training data; and active-sensing techniques that can tune sensing parameters in real time. We conclude with a discussion of future opportunities for adaptive sensing in wireless distributed sensor systems.

Foreign accent conversion in computer assisted pronunciation training

Learners of a second language practice their pronunciation by listening to and imitating utterances from native speakers. Recent research has shown that choosing a well-matched native speaker to imitate can have a positive impact on pronunciation training. Here we propose a voice-transformation technique that can be used to generate the (arguably) ideal voice to imitate: the own voice of the learner with a native accent. Our work extends previous research, which suggests that providing learners with prosodically corrected versions of their utterances can be a suitable form of feedback in computer assisted pronunciation training. Our technique provides a conversion of both prosodic and segmental characteristics by means of a pitch-synchronous decomposition of speech into glottal excitation and spectral envelope. We apply the technique to a corpus containing parallel recordings of foreign-accented and native-accented utterances, and validate the resulting accent conversions through a series of perceptual experiments. Our results indicate that the technique can reduce foreign accentedness without significantly altering the voice quality properties of the foreign speaker. Finally, we propose a pedagogical strategy for integrating accent conversion as a form of behavioral shaping in computer assisted pronunciation training.

Processing of chemical sensor arrays with a biologically inspired model of olfactory coding

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.

Use of a gas-sensor array for detecting volatile organic compounds (VOC) in chemically induced cells

An application of gas sensors for rapid bioanalysis is presented. An array of temperature-modulated semiconductor sensors was used to characterize the headspace above a cell culture. Recombinant Saccharomyces cerevisiae yeast cells, able to respond to 17 beta-estradiol by producing a reporter protein, were used as a model system. Yeast cells had the DNA sequence of the human estrogen receptor stably integrated into the genome, and contained expression plasmids carrying estrogen-responsive sequences and the reporter gene lac-Z, encoding the enzyme beta-galactosidase. The sensor-response profiles showed small but noticeable discrimination between cell samples induced with 17 beta-estradiol and non-induced cell samples. The sensor array was capable of detecting changes in the volatile organic compound composition of the headspace above the cultured cells, which can be associated with metabolic changes induced by a chemical compound. This finding suggests the possibility of using cross-selective gas-sensor arrays for analysis of drugs or bioactive molecules through their interaction with cell systems, with the advantage of providing information on their bioavailability.

Pattern completion through phase coding in population neurodynamics

This article presents an alternative phase coding mechanism for Freeman's KIII model of population neurodynamics. Motivated by experimental evidence that supports the existence of a neural code based on synchronous oscillations, we propose an analogy between synchronization in neural populations and phase locking in KIII channels. An efficient method is proposed to extract phase differences across granule channels from their state-space trajectories. First, the scale invariance of the KIII model with respect to phase information is established. The phase code is then compared against the conventional amplitude code in terms of their bit-wise and across-fiber pattern recovery capabilities using decision-theoretic principles and a Hamming-distance classifier. Graph isomorphism in the Hebbian connections is exploited to perform an exhaustive evaluation of patterns on an 8-channel KIII model. Simulation results show that phase information outperforms amplitude information in the recovery of incomplete or corrupted stimuli.