Considering the detrimental effects of dyslexia on academic performance and its common occurrence, developing tools for dyslexia detection, monitoring, and treatment poses a task of significant priority. The research performed in this paper was focused on detecting and analyzing dyslexic tendencies in Serbian children based on eye-tracking measures. The group of 30 children (ages 7–13, 15 dyslexic and 15 non-dyslexic) read 13 different text segments on 13 different color configurations. For each text segment, the corresponding eye-tracking trail was recorded and then processed offline and represented by nine conventional features and five newly proposed features. The features were used for dyslexia recognition using several machine learning algorithms: logistic regression, support vector machine, k-nearest neighbor, and random forest. The highest accuracy of 94% was achieved using all the implemented features and leave-one-out subject cross-validation. Afterwards, the most important features for dyslexia detection (representing the complexity of fixation gaze) were used in a statistical analysis of the individual color effects on dyslexic tendencies within the dyslexic group. The statistical analysis has shown that the influence of color has high inter-subject variability. This paper is the first to introduce features that provide clear separability between a dyslexic and control group in the Serbian language (a language with a shallow orthographic system). Furthermore, the proposed features could be used for diagnosing and tracking dyslexia as biomarkers for objective quantification.

Existing government air quality monitoring networks consist of static measurement stations, which are highly reliable and accurately measure a wide range of air pollutants, but they are very large, expensive and require significant amounts of maintenance. As a promising solution, low-cost sensors are being introduced as complementary, air quality monitoring stations. These sensors are, however, not reliable due to the lower accuracy, short life cycle and corresponding calibration issues. Recent studies have shown that low-cost sensors are affected by relative humidity and temperature. In this paper, we explore methods to additionally improve the calibration algorithms with the aim to increase the measurement accuracy considering the impact of temperature and humidity on the readings, by using machine learning. A detailed comparative analysis of linear regression, artificial neural network and random forest algorithms are presented, analyzing their performance on the measurements of CO, NO2 and PM10 particles, with promising results and an achieved R2 of 0.93–0.97, 0.82–0.94 and 0.73–0.89 dependent on the observed period of the year, respectively, for each pollutant. A comprehensive analysis and recommendations on how low-cost sensors could be used as complementary monitoring stations to the reference ones, to increase spatial and temporal measurement resolution, is provided.

In this paper, we explore the impact of the COVID-19 lockdown in Serbia on the air pollution levels of CO, NO2 and PM10 alongside the possibility for low-cost sensor usage during this period. In the study, a device with low-cost sensors collocated with a reference public monitoring station in the city of Belgrade is used for the same period of 52 days in 2019 (pre-COVID-19 period), 2020 (COVID-19 lockdown) and 2021 (post-COVID-19 period). Low-cost sensors’ measurements are improved by using a convolutional neural network that applies corrections of the influence of temperature and relative humidity on the low-cost sensors. As a result of this study we have noticed a remarkable decrease in NO2 (primarily related to traffic density), while on the other hand CO and PM10, related to domestic heating sources and heating plants, showed constant or slightly higher levels. The obtained results are in accordance with other published work in this area. The low-cost sensors have shown a satisfactory correlation with the reference CO measurements during the lockdown, while the NO2 and PM10 measurements of 2020 were corrected using a convolutional neural network trained on meteorological and pollutant data from 2019. The results include an improvement of 0.35 for the R2 of NO2 and an improvement of 0.13 for the R2 of PM10, proving that our neural network model trained on data from 2019 can improve the performance of the sensor in the lockdown period in 2020. This means that our neural network model is very robust, as it exhibits good performance even in the case where training data from the prior year (2019) are used in the following year (2020) in very different environment circumstances—a lockdown.

No abstract

The negative influence of developmental dyslexia on academic performance is a welldocumented and researched topic. Although research focused on developmental dyslexia detection and evaluation is plentiful, the study designs vary to a great degree, making the exchange of obtained knowledge often difficult. This paper focuses on bridging the gap between different study designs by developing a machine learning based pipeline that was evaluated on two completely different eye-tracking datasets (training on one, testing on the other, and vice versa). One dataset included 30 subjects who read text written in Serbian on different color configurations and were tracked with a remote eye-tracker. The second dataset included 185 subjects who read text written in Swedish, and recorded eye-tracking data using a goggle-based system. The data from both datasets was converted to grayscale images, using various time window configurations to parse the signals, and plotting the data in a 2D plane. The train images were used to train an Autoencoder neural network, and the images' reconstruction error was used to create features that describe each instance of both the training and test sets. The train feature set was used to train various machine learning algorithms, which were then evaluated on the testing feature dataset. A classification accuracy of 85.6% was obtained when testing on Serbian readers' data and 82.9% when testing on Swedish readers. The proposed pipeline was shown to be transferable between the datasets, despite many differences in the experiment design, showing potential in combining various eye-tracking dyslexia studies.