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 $R^2$ 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.

Developing reliable, quantifiable, and accessible metrics for dyslexia diagnosis and tracking represents an important goal, considering the widespread nature of dyslexia and its negative impact on education and quality of life. In this study, we observe eye-tracking data from 15 dyslexic and 15 neurotypical Serbian school-age children who read text segments presented on different color configurations. Two new eye-tracking features were introduced that quantify the amount of spatial complexity of the subject’s gaze through time and inherently provide information regarding the locations in the text in which the subject struggled the most. The features were extracted from the raw eye-tracking data (x, y coordinates), from the original data gathered at 60 Hz, and from the downsampled data at 30 Hz, examining the compatibility of features with low-cost or custom-made eye-trackers. The features were used as inputs to machine learning algorithms, and the best-obtained accuracy was 88.9% for 60 Hz and 87.8% for 30 Hz. The features were also used to analyze the influence of background/overlay color on the quality of reading, and it was shown that the introduced features separate the dyslexic and control groups regardless of the background/overlay color. The colors can, however, influence each subject differently, which implies that an individualistic approach would be necessary to obtain the best therapeutic results. The performed study shows promise in dyslexia detection and evaluation, as the proposed features can be implemented in real time as feedback during reading and show effectiveness at detecting dyslexia with data obtained using a lower sampling rate.

The negative influence of developmental dyslexia on academic performance is a well-documented 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.

Public air quality monitoring relies on expensive monitoring stations which are highly reliable and accurate but require significant maintenance and cannot be used to form a high spatial resolution measurement grid. Recent technological advances have enabled air quality monitoring that uses low-cost sensors. Being inexpensive and mobile, with wireless transfer support, such devices represent a very promising solution for hybrid sensor networks comprising public monitoring stations supported by many low-cost devices for complementary measurements. However, low-cost sensors can be influenced by weather and degradation, and considering that a spatially dense network would include them in large numbers, logistically adept solutions for low-cost device calibration are essential. In this paper, we investigate the possibility of a data-driven machine learning calibration propagation in a hybrid sensor network consisting of One public monitoring station and ten low-cost devices equipped with NO₂, PM₁₀, relative humidity, and temperature sensors. Our proposed solution relies on calibration propagation through a network of low-cost devices where a calibrated low-cost device is used to calibrate an uncalibrated device. This method has shown an improvement of up to 0.35/0.14 for the Pearson correlation coefficient and a reduction of 6.82 µg/m³/20.56 µg/m³ for the RMSE, for NO₂ and PM₁₀, respectively, showing promise for efficient and inexpensive hybrid sensor air quality monitoring deployments.

Because the number of air quality measurement stations governed by a public authority is limited, many methodologies have been developed in order to integrate low-cost sensors and to improve the spatial density of air quality measurements. However, at the large-scale level, the integration of a huge number of sensors brings many challenges. The volume, velocity and processing requirements regarding the management of the sensor life cycle and the operation of system services overcome the capabilities of the centralized cloud model. In this paper, we present the methodology and the architectural framework for building large-scale sensing infrastructure for air quality monitoring applicable in urban scenarios. The proposed tiered architectural solution based on the adopted fog computing model is capable of handling the processing requirements of a large-scale application, while at the same time sustaining real-time performance. Furthermore, the proposed methodology introduces the collection of methods for the management of edge-tier node operation through different phases of the node life cycle, including the methods for node commission, provision, fault detection and recovery. The related sensor-side processing is encapsulated in the form of microservices that reside on the different tiers of system architecture. The operation of system microservices and their collaboration was verified through the presented experimental case study.