Search

Abstract In the realm of ophthalmology, precise measurement of tear film break-up time (TBUT) plays a crucial role in diagnosing dry eye disease (DED). This study aims to introduce an automated approach utilizing artificial intelligence (AI) to mitigate subjectivity and enhance the reliability of TBUT measurement. We employed a dataset of 47 slit lamp videos for development, while a test dataset of 20 slit lamp videos was used for evaluating the proposed approach. The multistep approach for TBUT estimation involves the utilization of a Dual-Task Siamese Network for classifying video frames into tear film breakup or non-breakup categories. Subsequently, a postprocessing step incorporates a Gaussian filter to smooth the instant breakup/non-breakup predictions effectively. Applying a threshold to the smoothed predictions identifies the initiation of tear film breakup. Our proposed method demonstrates on the evaluation dataset a precise breakup/non-breakup classification of video frames, achieving an Area Under the Curve of 0.870. At the video level, we observed a strong Pearson correlation coefficient (r) of 0.81 between TBUT assessments conducted using our approach and the ground truth. These findings underscore the potential of AI-based approaches in quantifying TBUT, presenting a promising avenue for advancing diagnostic methodologies in ophthalmology.

As climate change continues to present daunting obstacles in the eastern region of Morocco, the reuse of treated wastewater has emerged as a vital solution for combating water scarcity, particularly for irrigation purposes. This investigation delves into the implications of reusing treated wastewater along the seasonal Isly River, with a specific focus on its downstream area, commonly referred to as "Oued Bou Naim". A comprehensive campaign was conducted in 2023 to analyse the physicochemical quality of 12 water samples from Oued Bou Naim and 13 soil samples from nearby agricultural plots. The findings from the water analysis show a marginal increase in temperature downstream from the wastewater treatment plant (WWTP) in Oujda, ranging from 19.0°C to 24.8°C. The pH varied between 7.08 and 8.33 and generally remained within acceptable limits. However, the electrical conductivity levels, ranging from 2154 to 2898 μS·cm⁻¹, exceeded WHO standards, indicating potential risks to the soil‒plant‒health ecosystem. Additionally, the total dissolved solids increased significantly downstream from the WWTP, reaching 1437 mg·l⁻¹. For the nitrites, a level exceeding the limits, especially upstream, had an average of 2.03 and a maximum of 5.48 mg·l⁻¹. Upon studying the soil samples, a substantial increase in orthophosphates, nitrites, and nitrates was observed downstream. Orthophosphate levels increased significantly downstream, with an average of 361.25 mg·kg⁻¹, indicating the contribution of treated wastewater. The nitrite concentration (average of 11.61 mg·kg⁻¹) and nitrate level (average of 60 mg·kg⁻¹) raise concerns regarding contamination through irrigation with treated wastewater. This research highlights the critical need for responsible irrigation practices to safeguard the delicate balance of the "Water‒Soil‒Plant" ecosystem and the well-being of humans. Although wastewater treatment plants play an important role, the presence of high levels of harmful pollutants downstream emphasizes the urgent need to carefully manage this treatment combined with the reasonable use of agrochemical inputs to prevent their leaching into nearby ecosystems. By doing so, we can effectively reduce the risks to both the ecosystem and human health in the study region.

Under climate change conditions, optimizing water resources management in rainfed agricultural production systems requires the reasonable choice of crops. In this context, the adoption of crops diversification is promoted to increase the agricultural production and the added value per cubic meter of rain water (green water) used by crops. Contributing, therefore, to increase agricultural production and to preserve soil and water resources. The objective of this study is: (i) to identify mixed crops within agricultural fields and, (ii) to evaluate the biomass production and the water productivity in the Lebna watershed (Cap-Bon, Tunisia) using remote sensing and field measurements. The study area, covering 210 km2, is characterized by the predominant of cereals, legumes and fodder cropping systems. The experiments allowed the quantification of crop evapotranspiration and the observed biomass production at the agricultural field plots. The use of the sentinel images and the observations at different agricultural fields allowed to produce NDVI maps. The results first confirmed a good correlation between biomass production and NDVI values. The exponential relationships showed a values of R2 greater than 0.7. The use of sentinel images and GIS allowed to compute water productivity from field to watershed scale. The results revealed a considerable spatial variation in water productivity values for different crops. Compared to a single crop, the cereal-legume mixture cropping improved the water productivity. The maximum value with 9.07 kg m−3 is observed for the mixture crops. The lowest value (0.12 to 2.40 kg m−3) was obtained for the cereal crop. These results help to recommend adaptation measures in agricultural production systems to climate change.

Morocco is currently facing significant challenges due to the ever–changing climate, with its critical water sources crucial for agriculture, economy, and daily life being greatly affected. In order to thoroughly understand the impact of climate change on the Ghis–Nekor watershed, an in–depth study spanning 38 years (1978–2016) was conducted. This involved examining meteorological data from three stations and utilizing advanced indices such as SPI, RDI, and DI. The findings of this study reveal prominent shifts in precipitation patterns, indicating a vulnerability in the region. While there was a general increase in annual rainfall during the specified time period, a sharp decline was observed post–2008. Further analysis of drought confirmed the presence of persistent dry spells and recurring episodes, highlighting the urgent need for effective water management strategies. These crucial findings must be considered by decision–makers for successful climate adaptation, emphasizing the crucial role played by this study in mitigating the effects of climate change.

In deep learning, various optimizers use a starting value for the learning rate. In general, this value is the one defined by default in the optimizer or chosen by the user after searching for a value giving the best performances of the studied neural network. Finding this value in the case of complex models with large-scale data, either by fine-tuning it manually or by applying a grid search algorithm requires several training sessions, which is penalizing in terms of learning time. To solve this problem, we propose an efficient optimizer using an automatic setting of the learning rate value. Learning then requires a single training session. The proposed optimizer is based on the inexact linear search of Armijo’s rule that we adapt for neural networks. We have experimented with this optimizer for several types of loss functions such as mean squared error, mean absolute error, and cross-entropy. Different types of models such as regression and classification are studied. Also, the robustness of this optimizer against the noisy labels is verified. Empirical results demonstrate that the proposed optimizer works well in practice, it outperforms other state-of-the-art optimizers that use default learning rate in terms of accuracy in addition to the time saving when searching for the optimal value of the learning rate.

Résumé Introduction-Les traumatismes bucco-dentaires sont des accidents fréquemment ren­contrés ai cours de l’intubation orotrachéale pratiquée en urgence ou au cours de l’anes­thésie générale. le but de ce travail était d’évaluer les pratiques des personnels de santé lorsqu’un traumatisme buccodentaire s’est produit au cours de l’intubation orotrachéale. Méthodes- Il s’agissait d’une étude transversale qui s’est déroulée dans les hôpitaux tu­nisiens durant la période s’étalant du mois de septembre au mois de novembre 2022. Un questionnaire auto-administré pré-testé était distribué auprès des personnels de santé pratiquant l’intubation orotrachéale dans un contexte d’urgence ou d’anesthésie géné­rale. Les données collectées ont été saisies et traitées avec le logiciel SPSS version 18. Résultats- Soixante-sept personnes ont répondu au questionnaire. D’après les résultats de l’étude, au cours de leurs pratiques quotidiennes, 88 % des enquêtés ont déclaré avoir assisté à un traumatisme bucco-dentaire liés à l’intubation orotrachéale. Lors de la consultation pré-anesthésique, si une mobilité des dents antérieures ou un problème parodontal ont été détectés, 42% des praticiens ont déclaré changer la technique de l’intubation, 36,5% ne faisaient rien, 11,2% prenaient l’avis du médecin dentiste, 11,2 % utilisaient des protèges dents. Au cours de l’intubation orotrachéale, si une fracture dentaire s’est produite accidentellement au cours de l’intubation, 75,8 % de praticiens conservaient le fragment fracturé pour une éventuelle prise en charge dentaire, l’avis du médecin dentiste au cours de la chirurgie a été sollicité par 12,9 % des praticiens, 11,3 % jetaient le fragment fracturé. Conclusion-: les pratiques des personnels de santé face à un traumatisme dentaire lié à l’intubation orotrachéale sont hétérogènes et nécessite une consolidation par des forma­tions sur la modalité de prise en charge des lésions dentaires. Abstract Introduction-Oral trauma is an accident occurred frequently during orotracheal intubation performed in an emergency or during general anesthesia. the aim of this work was to eva­luate the practices of health personnel when oral trauma appeared during orotracheal in­tubation. Methods- This is a cross-sectional study conducted in Tunisian hospitals during the period from September to November 2022. A pre-tested self-administered questionnaire was dis­tributed to health personnel practicing orotracheal intubation in an emergency or general anesthesia context. The data collected was entered and analysed with SPSS version 18 sof­tware. Results- Sixty-seven people responded to the questionnaire. According to the results of the study, 88% of respondents declared having met oral and dental trauma linked to orotracheal intubation during their daily practices. During the pre-anesthetic consultation, if an anterior teeth mobility or a periodontal problem was detected, 42% of practitioners declared chan­ging the intubation technique, 36.5% did nothing, 11.2% took the dentist advice, 11.2% would use mouth guards. During orotracheal intubation, if a dental fracture occurred accidentally during intubation, 75.8% of practitioners kept the fractured fragment for possible dental treatment, the advice of the dentist during surgery was requested by 12.9% of practitioners, 11.3% threw away the fractured fragment. Conclusion- : The practices of health personnel faced with dental trauma related to orotracheal intubation are heterogeneous and require consolidation through training on ma­nagement of dental lesions.

Magnetocaloric refrigeration is an integral part of technology and is under constant investigation. In this regard, the characterization of the magnetocaloric materials used is of major concern. In this study, we used different approaches to better understand the mechanisms underlying the magnetic and magnetocaloric properties of Rh2S mIn Full-Heusler. A physical model is suggested to explain the magnetic interaction within this material. Utilizing the density functional theory, exchange couplings and magnetic phase stability in Rh2SmIn have been attempted as well in order to understand and clarify the various magnetic interactions in this compound. The magnetic and magnetocaloric properties were examined with Monte Carlo simulation (MCS) based on the Ising model. The transition temperature, magnetic entropy change, and relative cooling power (RCP) were computed and found to be in good agreement with experimental evidence. According to the results, Rh2S mIn is a good candidate to be used in magnetic refrigeration applications at high temperature.

This study aimed to assess groundwater quality in the Errachidia region, southeast Morocco, where a total of one hundred wells were periodically surveyed, and ten wells were selected for monthly monitoring based on their proximity to known surface pollution sources. Various physicochemical parameters were measured. Results outcomes encompass temperature fluctuations ranging from 21°C to 30°C, generally neutral pH levels, heightened electrical conductivity (900 to 2220 µS/cm), diminished dissolved oxygen levels (1.91 mg/L), and the presence of nitrates within prescribed thresholds for potable water. Nevertheless, one station exceeded the nitrate threshold (30 mg/L). Elevated sulfate ion concentrations were detected (764.6 mg/L), potentially originating from urban wastewater. Chloride levels fell within acceptable limits (67.45 to 245 mg/L), and calcium content displayed variability (89.6 to 208.6 mg/L), but remained below authorized values. Hierarchical clustering identified four distinctive well groups predicated on their physicochemical attributes, thereby underscoring the impact of pollution sources on water quality. The study indicated an improvement in the region's water quality, transitioning from poor to moderate, and in some instances, to good quality.