Classifying the difficulty levels of working memory tasks by using pupillary response.

Knowing the difficulty of a given task is crucial for improving the learning outcomes. This paper studies the difficulty level classification of memorization tasks from pupillary response data. Developing a difficulty level classifier from pupil size features is challenging because of the inter-subject variability of pupil responses. Eye-tracking data used in this study was collected while students solved different memorization tasks divided as low-, medium-, and high-level. Statistical analysis shows that values of pupillometric features (as peak dilation, pupil diameter change, and suchlike) differ significantly for different difficulty levels. We used a wrapper method to select the pupillometric features that work the best for the most common classifiers; Support Vector Machine (SVM), Decision Tree (DT), Linear Discriminant Analysis (LDA), and Random Forest (RF). Despite the statistical difference, experiments showed that a random forest classifier trained with five features obtained the best F1-score (82%). This result is essential because it describes a method to evaluate the cognitive load of a subject performing a task using only pupil size features.

Pupillary Responses for Cognitive Load Measurement to Classify Difficulty Levels in an Educational Video Game: Empirical Study.

BACKGROUND: A learning task recurrently perceived as easy (or hard) may cause poor learning results. Gamer data such as errors, attempts, or time to finish a challenge are widely used to estimate the perceived difficulty level. In other contexts, pupillometry is widely used to measure cognitive load (mental effort); hence, this may describe the perceived task difficulty. OBJECTIVE: This study aims to assess the use of task-evoked pupillary responses to measure the cognitive load measure for describing the difficulty levels in a video game. In addition, it proposes an image filter to better estimate baseline pupil size and to reduce the screen luminescence effect. METHODS: We conducted an experiment that compares the baseline estimated from our filter against that estimated from common approaches. Then, a classifier with different pupil features was used to classify the difficulty of a data set containing information from students playing a video game for practicing math fractions. RESULTS: We observed that the proposed filter better estimates a baseline. Mauchly's test of sphericity indicated that the assumption of sphericity had been violated (χ214=0.05; P=.001); therefore, a Greenhouse-Geisser correction was used (ε=0.47). There was a significant difference in mean pupil diameter change (MPDC) estimated from different baseline images with the scramble filter (F5,78=30.965; P<.001). Moreover, according to the Wilcoxon signed rank test, pupillary response features that better describe the difficulty level were MPDC (z=-2.15; P=.03) and peak dilation (z=-3.58; P<.001). A random forest classifier for easy and hard levels of difficulty showed an accuracy of 75% when the gamer data were used, but the accuracy increased to 87.5% when pupillary measurements were included. CONCLUSIONS: The screen luminescence effect on pupil size is reduced with a scrambled filter on the background video game image. Finally, pupillary response data can improve classifier accuracy for the perceived difficulty of levels in educational video games.

Testing multiple polynomial models for eye-tracker calibration.

The straightforward approach to eye-tracker calibration considers that the calibration data do not have erroneous associations, and the calibration function is defined. The violation of the non-erroneous assumption could cause an arbitrarily large bias. The MMransac algorithm proposed in this paper is a modified version of the Random Sample Consensus. that achieves robust calibrations. On the other hand, polynomials in two variables (i.e., with terms in the form κxayb) are commonly used to map eye-tracker measurements to points on the screen. High-degree polynomials tend to be more accurate; however, as the order is increased, the function becomes more complex and less smooth, which could cause over-fitting. In this sense, this paper proposes an algorithmic approach that enables model selection criteria even in the presence of outliers. This approach was tested using different model selection criteria. Results show that more accurate calibrations are obtained with the combined robust fitting and model selection approach using the Akaike information criterion (AIC) and the Kullback information criterion (KIC).

Boron and Coumaphos Residues in Hive Materials Following Treatments for the Control of Aethina tumida Murray.

In the search of alternatives for controlling Aethina tumida Murray, we recently proposed the BAA trap which uses boric acid and an attractant which mimics the process of fermentation caused by Kodamaea ohmeri in the hive. This yeast is excreted in the feces of A. tumida causing the fermentation of pollen and honey of infested hives and releasing compounds that function as aggregation pheromones to A. tumida. Since the boron is the toxic element in boric acid, the aim of this article is to assess the amount of boron residues in honey and beeswax from hives treated with the BAA trap. For this aim, the amount of bioaccumulated boron in products of untreated hives was first determined and then compared with the amount of boron of products from hives treated with the BAA trap in two distinct climatic and soil conditions. The study was conducted in the cities of Padilla, Tamaulipas, and Valladolid, Yucatan (Mexico) from August 2014 to March 2015. The quantity of boron in honey was significantly less in Yucatan than in Tamaulipas; this agrees with the boron deficiency among Luvisol and Leptosol soils found in Yucatan compared to the Vertisol soil found in Tamaulipas. In fact, the honey from Yucatan has lower boron levels than those reported in the literature. The BAA treatment was applied for four months, results show that the BAA trap does not have any residual effect in either honey or wax; i.e., there is no significant difference in boron content before and after treatment. On the other hand, the organophosphate pesticide coumaphos was found in 100% of wax samples and in 64% of honey samples collected from Yucatan. The concentration of coumaphos in honey ranges from 0.005 to 0.040 mg/kg, which are below Maximum Residue Limit (MRL) allowed in the European Union (0.1 mg/kg) but 7.14% of samples exceeded the MRL allowed in Canada (0.02 mg/kg).