RESUMEN

BACKGROUND: Sensitive measures to predict neuromotor outcomes from data collected early in infancy are lacking. Measures derived from the recordings of infant movement using wearable sensors may be a useful new technique. METHODS: We collected full-day leg movement of 41 infants in rural Guatemala across 3 visits between birth and 6 months of age using wearable sensors. Average leg movement rate and fuzzy entropy, a measure to describe the complexity of signals, of the leg movements' peak acceleration time series and the time series itself were derived. We tested the three measures for the predictability of infants' developmental outcome, Bayley Scales of Infant and Toddler Development III motor, language, or cognitive composite score assessed at 12 months of age. We performed quantile regressions with clustered standard errors, accounting for the multiple visits for each infant. RESULTS: Fuzzy entropy was associated with the motor composite score at the 0.5 quantiles; this association was not found for the other two measures. Also, no leg movement characteristic was associated with language or cognitive composite scores. CONCLUSION: We propose that the entropy of leg movement associated peak accelerations calculated from the wearable sensor data collected for a full-day can be considered as one predictor for infants' motor developmental outcome assessed with Bayley Scales of Infant and Toddler Development III at 12 months of age.

Asunto(s)

RESUMEN

The synergy between eco-friendly biopolymeric films and printed devices leads to the production of plant-wearable sensors for decentralized analysis of pesticides in precision agriculture and food safety. Herein, a simple method for fabrication of flexible, and sustainable sensors printed on cellulose acetate (CA) substrates has been demonstrated to detect carbendazim and paraquat in agricultural, water and food samples. The biodegradable CA substrates were made by casting method while the full electrochemical system of three electrodes was deposited by screen-printing technique (SPE) to produce plant-wearable sensors. Analytical performance was assessed by differential pulse (DPV) and square wave voltammetry (SWV) in a linear concentration range between 0.1 and 1.0 µM with detection limits of 54.9 and 19.8 nM for carbendazim and paraquat, respectively. The flexible and sustainable non-enzymatic plant-wearable sensor can detect carbendazim and paraquat on lettuce and tomato skins, and also water samples with no interference from other pesticides. The plant-wearable sensors had reproducible response being robust and stable against multiple flexions. Due to high sensitivity and selectivity, easy operation and rapid agrochemical detection, the plant-wearable sensors can be used to detect biomarkers in human biofluids and be used in on-site analysis of other hazardous chemical substances.

Asunto(s)

RESUMEN

The recognition of human activities (HAR) using wearable device data, such as smartwatches, has gained significant attention in the field of computer science due to its potential to provide insights into individuals' daily activities. This article aims to conduct a comparative study of deep learning techniques for recognizing activities of daily living (ADL). A mapping of HAR techniques was performed, and three techniques were selected for evaluation, along with a dataset. Experiments were conducted using the selected techniques to assess their performance in ADL recognition, employing standardized evaluation metrics, such as accuracy, precision, recall, and F1-score. Among the evaluated techniques, the DeepConvLSTM architecture, consisting of recurrent convolutional layers and a single LSTM layer, achieved the most promising results. These findings suggest that software applications utilizing this architecture can assist smartwatch users in understanding their movement routines more quickly and accurately.

Asunto(s)

RESUMEN

Presently, miniaturized sensors can be embedded in any small-size wearable to recognize movements on some parts of the human body. For example, an electrooculography-based sensor in smart glasses recognizes finger movements on the nose. To explore the interaction capabilities, this paper conducts a gesture elicitation study as a between-subjects experiment involving one group of 12 females and one group of 12 males, expressing their preferred nose-based gestures on 19 Internet-of-Things tasks. Based on classification criteria, the 912 elicited gestures are clustered into 53 unique gestures resulting in 23 categories, to form a taxonomy and a consensus set of 38 final gestures, providing researchers and practitioners with a larger base with six design guidelines. To test whether the measurement method impacts these results, the agreement scores and rates, computed for determining the most agreed gestures upon participants, are compared with the Condorcet and the de Borda count methods to observe that the results remain consistent, sometimes with a slightly different order. To test whether the results are sensitive to gender, inferential statistics suggest that no significant difference exists between males and females for agreement scores and rates.

Asunto(s)

RESUMEN

Gold is among the most used materials in electrocatalysis. Despite this, this noble metal is still too expensive to be used in the fabrication of low cost and disposable devices. In the present work, gold-leaf sheets, usually employed in decorative crafts and wedding candies, is introduced as an inexpensive source of gold. Planar-disc and nanoband gold electrodes were simply and easily manufactured by combining gold leaf and polyimide tape. The planar disc electrode exhibited electrochemical behavior similar to that of a commercial gold electrode in 0.2molL-1 H2SO4; cyclic voltammetry of a 1mmolL-1 solution of potassium ferricyanide (K3[Fe(CN)6]) in 0.2molL-1 KNO3, using this novel electrode, displayed an 80mV difference between the oxidation and reduction peak potentials. The electrode also delivers promising prospects for the development of wearable devices. When submitted to severe mechanical deformation, this electrode exhibited neither loss of electrical contact nor significant variation in electrode response, even after fifteen bending and/or folding cycles. The thickness of the gold-leaf sheet facilitates the production of nanoband electrodes with behavior similar to that of ultramicroelectrodes. The electrode surface is easily renewed by cutting a thin slice off its end with a razor blade; this process led to limiting currents that were reproducible, presenting a relative standard deviation (RSD) of 3.8% (n = 5).

RESUMEN

This study introduces the One-Class K-means with Randomly-projected features Algorithm (OCKRA). OCKRA is an ensemble of one-class classifiers built over multiple projections of a dataset according to random feature subsets. Algorithms found in the literature spread over a wide range of applications where ensembles of one-class classifiers have been satisfactorily applied; however, none is oriented to the area under our study: personal risk detection. OCKRA has been designed with the aim of improving the detection performance in the problem posed by the Personal RIsk DEtection(PRIDE) dataset. PRIDE was built based on 23 test subjects, where the data for each user were captured using a set of sensors embedded in a wearable band. The performance of OCKRA was compared against support vector machine and three versions of the Parzen window classifier. On average, experimental results show that OCKRA outperformed the other classifiers for at least 0.53% of the area under the curve (AUC). In addition, OCKRA achieved an AUC above 90% for more than 57% of the users.