Search Results (53)

Student retention analytics often treats withdrawal as a single outcome, although students may attribute dropout intention to personal, socioeconomic, and academic pressures simultaneously. We benchmarked nine supervised classifiers for identifying a concurrent three-domain attribution profile in a cross-sectional survey of 333 undergraduates at a Colombian public university campus. The response came from a semi-structured weight-allocation item; an audit found that literal label matching altered 21 classifications because of spelling variants and decimal notation. Nine classifiers—logistic regression, decision tree, random forest, neural network, Gaussian Naïve Bayes, k-nearest neighbors, AdaBoost, gradient boosting, and XGBoost—were fitted using six pre-specified predictors. Models were compared by repeated nested stratified cross-validation (five outer folds, three repeats), inner tuning, fold-contained preprocessing, and training-only threshold selection. The concurrent profile occurred in 256 students (76.9%). Logistic regression achieved the highest mean held-out ROC AUC (0.674, 95% CI 0.644–0.704), closely followed by random forest (0.671, 0.641–0.702); their paired difference was nonsignificant after Holm adjustment. Logistic regression had the highest F1 score (0.788), whereas random forest had the highest balanced accuracy (0.617). AdaBoost did not retain its apparent single-holdout advantage. Housing and financial aid had the largest held-out permutation importance. The predictors provided moderate discrimination of a perceptual profile, not a validated prediction of future dropout. Outcome auditing and leakage-free validation materially changed the model ranking. Full article

Reliable rainfall information is fundamental for climate-risk analysis and operational monitoring in Mediterranean regions such as Apulia (Southern Italy), one of the areas most affected by climate change-driven shifts in rainfall patterns. Recent evaluations across Italy and comparable Mediterranean settings consistently show that gridded precipitation performance is highly dependent on orography and dataset typology: reanalyses often provide the best overall agreement with gauges, while satellite and blended products can exhibit larger biases, with persistent challenges in complex terrain and for high-intensity events. In this context—and given the documented spatial heterogeneity of rainfall extremes within Apulia—validation of such gridded datasets with respect to ground observations remains essential for early warning and climatological applications. In the present work, we evaluate four widely used precipitation products—CHIRPS-v2, the newly released CHIRPS-v3, IMERG, and ERA5—benchmarking them against the Apulia region Civil Protection rain-gauge network. We provide diagnostics aligned with early warning and climate monitoring: bias and error statistics, rainfall intensity distributions, and dry spell duration. A key contribution is, to our knowledge, the first dedicated validation of CHIRPS-v3 in Apulia, which is timely given that CHIRPS-v3 was explicitly developed to address shortcomings such as underestimated temporal variance and to leverage expanded station inputs. The results indicate that CHIRPS-v3 yields systematic improvements over CHIRPS-v2 across multiple metrics, while ERA5 generally shows the strongest overall agreement with gauges—consistent with broader Italian evidence. Full article

In hot, semi-arid zones, cities are experiencing longer and more intense warm spells. Although the literature offers strategies to mitigate this threat, studies verifying their feasibility are limited. In this study, we aim to ascertain the feasibility of reducing land surface temperature (LST) through greening. We combine LST analysis with a feasibility assessment of cooling measures and consider physical and ownership dimensions alongside environmental and social factors, with Ouagadougou (Burkina Faso) serving as a case study. The average LST during the hottest period (April–May) was calculated from ECOSTRESS and Landsat remotely sensed data, and multiple regression models were used to analyse the relationship between LST and land cover/land use across the city’s districts and sectors. Our assessment incorporates greening scenarios, SWOT analyses, and equity assessments, and our results indicate that barren land is the primary determinant of diurnal LST. Planting 0.45 million trees could reduce LST by up to 2.4 °C in peripheral sectors if large roads, utilities, and vacant lands are targeted. This may reduce disparities in tree cover between sectors but could widen the gap between districts. Recommendations include a more hierarchical street network, enhancing utility provision, and reducing barren land in the peripheral sectors. Full article

In regions lacking sufficient data, remote sensing (RS) offers a reliable alternative for precipitation estimation, enabling more effective drought management. This study comprehensively evaluates four commonly used RS datasets—Climate Hazards Center InfraRed Precipitation with Station data (CHIRPS), Tropical Applications of Meteorology using Satellite data (TAMSAT), Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks–Climate Data Record (PERSIANN-CDR), and Multi-Source Weighted-Ensemble Precipitation (MSWEP) against ground-based data—with respect to their performance in detecting precipitation and drought patterns in the Great Ruaha River Basin (GRRB), Tanzania (1983–2020). Statistical metrics including the Pearson correlation coefficient (r), mean error (ME), root mean square error (RMSE), and bias were employed to assess the performance at daily, monthly, seasonal (wet/dry), and annual timescales. Most of the RS products exhibited lower correlations (r < 0.5) at daily timestep and low RMSE, bias, and ME. Monthly performance improved substantially (r > 0.8 at most stations) particularly during the wet season (r = 0.52–0.82) while annual and dry-season performance declined (r < 0.5 and r < 0.3, respectively). Performance under RMSE, bias, and ME declined at higher timescales, particularly during the wet season and annually. CHIRPS, MSWEP, and PERSIANN generally overestimated precipitation while TAMSAT consistently underestimated it. Spatially, CHIRPS and MSWEP reproduced coherent basin-scale patterns of drought persistence, with longer dry-spells concentrated in the northern, central, and western parts of the basin and shorter dry-spells in the eastern and southern regions. Trend analysis further revealed that most products captured consistent large-scale changes in dry-spell characteristics, although localized drought events were more variably detected. CHIRPS and MSWEP showed superior performance especially in capturing monthly precipitation patterns and major drought events in the basin. Most products struggled to detect extreme dry conditions with the exception of CHIRPS and MSWEP at certain stations and periods. Based on these findings, CHIRPS and MSWEP are recommended for drought monitoring and water resource planning in the GRRB. Their appropriate use can help water managers make informed decisions, promote sustainable resource use, and strengthen resilience to extreme weather events. Full article

P300 detection is a difficult task in brain–computer interface (BCI) systems due to the low signal-to-noise ratio (SNR). In BCI systems, P300 waves are generated in electroencephalogram (EEG) signals using various oddball paradigms. Convolutional neural networks (CNNs) have previously shown excellent results for P300 detection compared to different machine learning models. However, current CNN architectures limit P300 detection accuracy because these models usually only extract single-scale features. Aiming to enhance P300 detection accuracy, an inception module-based CNN architecture, namely Inception-CNN, is introduced. Inception-CNN effectively learns discriminative features from both spatial and temporal information to reduce overfitting and computational complexity. Furthermore, it can extract multi-scale features, which effectively improves P300 detection accuracy and increases character spelling accuracy. To analyze the effect of the inception layer, two additional models are proposed: Inception-CNN-S, which uses the inception layer with a spatial convolution layer, and Inception-CNN-T, which uses the inception layer with a temporal convolution layer. The proposed model was evaluated on dataset II of BCI Competition III and dataset IIb of BCI Competition II. The experimental results show that Inception-CNN provides a promising solution for improving the accuracy of P300 detection, with F1 scores of 47.14%, 55.28%, and 78.94% for dataset II of BCI Competition III (Subject A and Subject B) and dataset IIb of BCI Competition II, respectively. Full article

The Mediterranean faces frequent heavy precipitation, deadly heatwaves, and wildfires fueled by its climate. Greece, with its complex topography, experiences severe and extreme weather events that have escalated in recent years and are projected to continue rising under future climate conditions. This paper analyzes severe weather events and trends in Greece from 2010 to 2023, leveraging data from an expanded network of weather stations spanning across Greece, as well as long-term meteorological data from the reference weather station in the center of Athens. The focus includes analysis of heat waves, intense rainfall and droughts, thunderstorms, hail, tornadoes, and fire weather conditions. The societal impact of severe weather events is also discussed. The paper aims to provide both long-term (1901–2023) and recent year analyses (2010–2023). The main results show that between 2010 and 2023, Greece experienced: nearly one heatwave per summer; heavy rainfall events, most common in winter and autumn, showing a significant increase, particularly in the eastern Aegean and western continental Greece; dry spells, which are longest in southern Greece; thunderstorm and hail events peaking in spring and summer; fire weather conditions and risk peaking in southern Greece. Finally, societal impacts from weather hazards have increased in Greece over the past 14 years, with flash floods being the most frequent and damaging events, while public preparedness and effective risk communication remain low. Full article

As our society increasingly relies on digital platforms for information, the spread of fake news has become a pressing concern. This study investigates the ability of Greek and Portuguese Instagram users to identify fake news, highlighting the influence of cultural differences. The responses of 220 Instagram users were collected through questionnaires in Greece and Portugal. The data analysis investigates characteristics of Instagram posts, social endorsement, and platform usage duration. The results reveal distinct user behaviors: Greeks exhibit a unique inclination towards social connections, displaying an increased trust in friends’ content and investing more time on Instagram, reflecting the importance of personal connections in their media consumption. They also give less importance to a certain post’s characteristics, such as content opposing personal beliefs, emotional language, and poor grammar, spelling, or formatting when identifying fake news, compared to the Portuguese, suggesting a weaker emphasis on content quality in their evaluations. These findings show that cultural differences affect how people behave on Instagram. Hence, content creators, platforms, and policymakers need specific plans to make online spaces more informative. Strategies should focus on enhancing awareness of key indicators of fake news, such as linguistic quality and post structure, while addressing the role of personal and social networks in the spread of misinformation. Full article

The Mexican deaf community primarily uses Mexican Sign Language (MSL) for communication, but significant barriers arise when interacting with hearing individuals unfamiliar with the language. Learning MSL requires a substantial commitment of at least 18 months, which is often impractical for many hearing people. To address this gap, we present an MSL-to-Spanish translation system that facilitates communication through a spelling-based approach, enabling deaf individuals to convey any idea while simplifying the AI’s task by limiting the number of signs to be recognized. Unlike previous systems that focus exclusively on static signs for individual letters, our solution incorporates dynamic signs, such as “k”, “rr”, and “ll”, to better capture the nuances of MSL and enhance expressiveness. The proposed Hybrid Neural Network-based algorithm integrates these dynamic elements effectively, achieving an F1 score of 90.91%, precision of 91.25%, recall of 91.05%, and accuracy of 91.09% in the extended alphabet classification. These results demonstrate the system’s potential to improve accessibility and inclusivity for the Mexican deaf community. Full article

Sensory integration is the province of the parietal lobe. The non-dominant hemisphere is responsible for both body sides, while the dominant hemisphere is responsible for the contralateral hemi-body. Furthermore, the posterior cingulate cortex (PCC) participates in a network involved in spatial orientation, attention, and spatial and episodic memory. Laser interstitial thermotherapy (LiTT) is a minimally invasive surgery for focal drug-resistant epilepsy (DRE) that can target deeper brain regions, and thus, region-specific symptoms can emerge. Here, we present an 18-year-old right-handed male with focal DRE who experienced seizures characterized by sensations of déjà vu, staring spells, and language disruption. A comprehensive evaluation localized the seizure focus and revealed a probable focal cortical dysplasia (FCD) in the left posterior cingulate gyrus. The patient underwent uneventful LiTT of the identified lesion. Post-operatively, he developed transient ipsilateral spatial neglect and contralateral sensory loss, as well as acalculia. His sensory symptoms gradually improved after the surgery, and he remained seizure-free after the intervention for at least 10 months (until the time of this writing). This rare case of ipsilateral spatial and visual hemineglect post-LiTT in epilepsy underscores the importance of recognizing atypical neurosurgical outcomes and considering individual variations in brain anatomy and function. Understanding the dynamics of cortical connectivity and handedness, particularly in pediatric epilepsy, may be crucial in anticipating and managing neurocognitive effects following epilepsy surgery. Full article

Named entity recognition is a critical task in the electronic medical record management system for rehabilitation robots. Handwritten documents often contain spelling errors and illegible handwriting, and healthcare professionals frequently use different terminologies. These issues adversely affect the robot’s judgment and precise operations. Additionally, the same entity can have different meanings in various contexts, leading to category inconsistencies, which further increase the system’s complexity. To address these challenges, a novel medical entity recognition algorithm for Chinese electronic medical records is developed to enhance the processing and understanding capabilities of rehabilitation robots for patient data. This algorithm is based on a fusion classification strategy. Specifically, a preprocessing strategy is proposed according to clinical medical knowledge, which includes redefining entities, removing outliers, and eliminating invalid characters. Subsequently, a medical entity recognition model is developed to identify Chinese electronic medical records, thereby enhancing the data analysis capabilities of rehabilitation robots. To extract semantic information, the ALBERT network is utilized, and BILSTM and MHA networks are combined to capture the dependency relationships between words, overcoming the problem of different meanings for the same entity in different contexts. The CRF network is employed to determine the boundaries of different entities. The research results indicate that the proposed model significantly enhances the recognition accuracy of electronic medical texts by rehabilitation robots, particularly in accurately identifying entities and handling terminology diversity and contextual differences. This model effectively addresses the key challenges faced by rehabilitation robots in processing Chinese electronic medical texts, and holds important theoretical and practical value. Full article

Chinese spelling errors are commonplace in our daily lives, which might be caused by input methods, optical character recognition, or speech recognition. Due to Chinese characters’ phonetic and visual similarities, the Chinese spelling check (CSC) is a very challenging task. However, the existing CSC solutions cannot achieve good spelling check performance since they often fail to fully extract the contextual information and Pinyin information. In this paper, we propose a novel CSC framework based on multi-label annotation (MLSL-Spell), consisting of two basic phases: spelling detection and correction. In the spelling detection phase, MLSL-Spell uses the fusion vectors of both character-based pre-trained context vectors and Pinyin vectors and adopts the sequence labeling method to explicitly label the type of misspelled characters. In the spelling correction phase, MLSL-Spell uses Masked Language Mode (MLM) model to generate candidate characters, then performs corresponding screenings according to the error types, and finally screens out the correct characters through the XGBoost classifier. Experiments show that the MLSL-Spell model outperforms the benchmark model. On SIGHAN 2013 dataset, the spelling detection F1 score of MLSL-Spell is 18.3% higher than that of the pointer network (PN) model, and the spelling correction F1 score is 10.9% higher. On SIGHAN 2015 dataset, the spelling detection F1 score of MLSL-Spell is 11% higher than that of Bert and 15.7% higher than that of the PN model. And the spelling correction F1 of MLSL-Spell score is 6.8% higher than that of PN model. Full article

Currently, approaches to correcting misspelled words have problems when the words are complex or massive. This is even more serious in the case of Spanish, where there are very few studies in this regard. So, proposing new approaches to word recognition and correction remains a research topic of interest. In particular, an interesting approach is to computationally simulate the brain process for recognizing misspelled words and their automatic correction. Thus, this article presents an automatic recognition and correction system of misspelled words in Spanish texts, for the detection of misspelled words, and their automatic amendments, based on the systematic theory of pattern recognition of the mind (PRTM). The main innovation of the research is the use of the PRTM theory in this context. Particularly, a corrective system of misspelled words in Spanish based on this theory, called Ar2p-Text, was designed and built. Ar2p-Text carries out a recursive process of analysis of words by a disaggregation/integration mechanism, using specialized hierarchical recognition modules that define formal strategies to determine if a word is well or poorly written. A comparative evaluation shows that the precision and coverage of our Ar2p-Text model are competitive with other spell-checkers. In the experiments, the system achieves better performance than the three other systems. In general, Ar2p-Text obtains an F-measure of 83%, above the 73% achieved by the other spell-checkers. Our hierarchical approach reuses a lot of information, allowing for the improvement of the text analysis processes in both quality and efficiency. Preliminary results show that the above will allow for future developments of technologies for the correction of words inspired by this hierarchical approach. Full article

In the past decade, Saudi Arabia has witnessed a surge in flash floods, resulting in significant losses of lives and property. This raises a need for accurate near-real-time precipitation estimates. Satellite products offer precipitation data with high spatial and temporal resolutions. Among these, the Precipitation Estimation from Remotely Sensed Information using Artificial Neural Networks–Dynamic Infrared Rain Rate near-real-time (PDIR-Now) stands out as a novel, global, and long-term resource. In this study, a rigorous comparative analysis was conducted from 2017 to 2022, contrasting PDIR-Now with rain gauge data. This analysis employs six metrics to assess the accuracy of PDIR-Now across various daily rainfall rates and four yearly extreme precipitation indices. The findings reveal that PDIR-Now slightly underestimates light precipitation but significantly underestimates heavy precipitation. Challenges arise in regions characterized by orographic rainfall patterns in the southwestern area of Saudi Arabia, emphasizing the importance of spatial resolution and topographical considerations. While PDIR-Now successfully captures annual maximum 1-day and 5-day precipitation measurements across rain gauge locations, it exhibits limitations in the length of wet and dry spells. This research highlights the potential of PDIR-Now as a valuable tool for precipitation estimation, offering valuable insights for hydrological, climatological, and water resource management studies. Full article

The current aim is to illustrate our research on dyslexia conducted at the Developmental Psychology section of the Department of Psychology, University of Amsterdam, in collaboration with the nationwide IWAL institute for learning disabilities (now RID). The collaborative efforts are institutionalized in the Rudolf Berlin Center. The first series of studies aimed at furthering the understanding of dyslexia using a gamified tool based on an artificial script. Behavioral measures were augmented with diffusion modeling in one study, and indices derived from the electroencephalogram were used in others. Next, we illustrated a series of studies aiming to assess individuals who struggle with reading and spelling using similar research strategies. In one study, we used methodology derived from the machine learning literature. The third series of studies involved intervention targeting the phonics of language. These studies included a network analysis that is now rapidly gaining prominence in the psychopathology literature. Collectively, the studies demonstrate the importance of letter-speech sound mapping and word decoding in the acquisition of reading. It was demonstrated that focusing on these abilities may inform the prediction, classification, and intervention of reading difficulties and their neural underpinnings. A final section examined dyslexia, conceived as a neurobiological disorder. This analysis converged on the conclusion that recent developments in the psychopathology literature inspired by the focus on research domain criteria and network analysis might further the field by staying away from longstanding debates in the dyslexia literature (single vs. a multiple deficit, category vs. dimension, disorder vs. lack of skill). Full article

Due to the increasing reliance on social network platforms in recent years, hate speech has risen significantly among online users. Government and social media platforms face the challenging responsibility of controlling, detecting, and removing massively growing hateful content as early as possible to prevent future criminal acts, such as cyberviolence and real-life hate crimes. Twitter is used globally by people from various backgrounds and nationalities; it contains tweets posted in different languages, including code-mixed language, such as Hindi–English. Due to the informal format of tweets with variations in spelling and grammar, hate speech detection is especially challenging in code-mixed text. In this paper, we tackle the critical issue of hate speech detection on social media, with a focus on a mix of English and Hindi–English (code-mixed) text messages on Twitter. More specifically, we aim to evaluate the impact of data pre-processing on hate speech detection. Our method first performs 10-step data cleansing; then, it builds a detection method based on two architectures, namely a convolutional neural network (CNN) and a combination of CNN and long short-term Memory (LSTM) algorithms. We tune the hyperparameters of the proposed model architectures and conduct extensive experimental analysis on real-life tweets to evaluate the performance of the models in terms of accuracy, efficiency, and scalability. Moreover, we compare our method with a closely related hate speech detection method from the literature. The experimental results suggest that our method results in an improved accuracy and a significantly improved runtime. Among our best-performing models, CNN-LSTM improved accuracy by nearly 2% and decreased the runtime by almost half. Full article