Search Results (17)

This study examines the effectiveness of in-service training programs aimed at enhancing teachers’ knowledge and self-efficacy in the context of learning disabilities (LD) in mathematics. Despite the increasing use of both interactive online learning and face-to-face training methods in professional development, limited research has compared their relative effectiveness in this specific field. Furthermore, existing studies have not adequately addressed whether improvements in teachers’ knowledge and self-efficacy are sustained over time. To address this gap, the present study employed a quasi-experimental design with two experimental groups. The sample consists of 80 classroom teachers, with 40 participants in the interactive online learning education group and 40 in the face-to-face education group. The training program consists of 16 h of instruction over four weeks. Data were collected using a demographic questionnaire and the Mathematics Learning Difficulty Area Teacher Self-Efficacy Scale, and statistical analyses were conducted. The findings indicate that, prior to the intervention, teachers in the interactive online learning education group exhibited significantly higher levels of knowledge and self-efficacy. However, the post-intervention results revealed no statistically significant differences between the two groups. Cohen’s d analysis indicated a moderate effect size for interactive online learning education before the intervention, which diminished to a small effect size afterward. This study validates the efficiency of interactive online learning from smart learning environments for in-service training programs aimed at enhancing teachers’ knowledge and self-efficacy about learning disabilities in mathematics. These results suggest that both training modalities effectively improve teachers’ knowledge and self-efficacy, but neither demonstrate a clear long-term advantage. This study underscores the need for further research to determine optimal strategies for sustaining professional development in this domain. Full article

Ship detection technology represents a significant research focus within the application domain of synthetic aperture radar. Among all the detection methods, the deep learning method stands out for its high accuracy and high efficiency. However, large-scale deep learning algorithm training requires huge computing power support and large equipment to process, which is not suitable for real-time detection on edge platforms. Therefore, to achieve fast data transmission and little computation complexity, the design of lightweight computing models becomes a research hot point. In order to conquer the difficulties of the high complexity of the existing deep learning model and the balance between efficiency and high accuracy, this paper proposes a lightweight dual-domain feature fusion detection model (LD-Det) for ship target detection. This model designs three effective modules, including the following: (1) a wavelet transform method for image compression and the frequency domain feature extraction; (2) a lightweight partial convolutional module for channel feature extraction; and (3) an improved multidimensional attention module to realize the weight assignment of different dimensional features. Additionally, we propose a hybrid IoU loss function specifically designed to enhance the detection of small objects, improving localization accuracy and robustness. Then, we introduce these modules into the Yolov8 detection algorithm for implementation. The experiments are designed to verify LD-Det’s effectiveness. Compared with other algorithm models, LD-Det can not only achieve lighter weight but also take into account the precision of ship target detection. The experimental results from the SSDD dataset demonstrate that the proposed LD-Det model improves precision (P) by 1.4 percentage points while reducing the number of model parameters by 20% compared to the baseline. LD-Det effectively balances lightweight efficiency and detection accuracy, making it highly advantageous for deployment on edge platforms compared to other models. Full article

This study aimed to explore the prevalence of learning disabilities (LDs) and the emotional–behavioral difficulties in 208 children from the Crete region in Greece, and who voluntarily presented themselves for study and were evaluated by a university-based interdisciplinary team of mental health professionals. The Greek version of the Wechsler Intelligence Scale for Children–Fifth Edition (WISC-V GR) was used, with its five Primary Index scores and full-scale IQ (Verbal Comprehension Index, VCI; Visual Spatial Index, VSI; Fluid Reasoning Index, FRI; Working Memory Index, WMI; and Processing Speed, PCI). Five diagnostic categories were established for the purpose of analysis: (a) no LDs (TD group), (b) Attention Deficit Hyperactivity Disorder (ADHD), (c) Specific Learning Disabilities (SLDs), (d) Extremely Low FSIQ (below 79), and (e) Emotional/Behavioral difficulties. The results revealed a 25.5% prevalence of SLDs, 18.75% ADHD, 8.65% Extremely Low FSIQ, and 5.29% emotional/behavioral problems, suggesting that 58% of the study population struggled with some kind of learning difficulty. Statistically significant differences were observed between the “Extremely Low FSIQ” group, the “SLD”, the “ADHD”, and the “TD” diagnostic groups in terms of the “VCI”, “FRI”, and the “FSIQ” scales (p < 0.001). Likewise, the “Extremely Low FSIQ” group differed significantly from the “SLD” and “TD” groups in terms of the “VSI”, the WMI, and the “PSI” (p < 0.001). The “Behavioural/emotional” and “SLD” groups differed in terms of “VCI” and “Full scale IQ” (p < 0.001). The analysis indicated that the children with severe learning difficulties differed from the other groups in terms of their cognitive profiles and that they needed tailor-made educational programs and interventions in a typical classroom. This study offers comparative data from a community sample of children, as well as generated initial evidence from non-clinical settings on the usability and the diagnostic accuracy of the Wechsler Intelligence Scale for Children–Fifth Edition (WISC-V). Further research is suggested. The present study was funded by the Crete Region (MIS 5162111). Full article

Developmental coordination disorder (DCD/Dyspraxia) is a commonly misunderstood and under-recognized specific learning difficulty (SpLD) in educational settings. This lifelong condition affects fine and gross motor coordination and significantly interferes with many activities of daily living, academic achievement, and employment opportunities. However, most Higher Education Institutions (HEIs) are unaware of its prevalence within their context, even though 5% of the general population have DCD and the enrolment of students in UK Higher Education with a known disability has increased by 42.4% between 2018 and 2023. Thus, understanding the lived experiences of students with DCD within Higher Education in the UK remains a considerable gap in knowledge. Through the use of focus groups, the lived experiences of 10 students with DCD at two UK HEIs were investigated. The thematic analysis identified four main themes: ‘Awareness of DCD’, ‘Participation in Higher Education for individuals with DCD’, ‘Wellbeing’, and ‘Everyday living’. Students shared that HEIs appeared to lack awareness of DCD and felt they had an inability to specify the correct support at university. Importantly, whilst the students in the study were not always confident in identifying the specific support they needed, they shared the strategies they used to aid their university experience. The students described the physical toll that many everyday living tasks can take, which subsequently negatively impact academic participation and wellbeing. On a positive note, many of the students discussed positive experiences at university, such as enjoying their own autonomy (and flexibility) to be independent and inform strategies for their own learning. Importantly, the findings from this work highlight the complexity and heterogeneity of DCD and the need for a tailored approach to supporting individuals with this condition. Given the importance of educational qualifications to enter the workplace, and the contribution of employment to quality of life, these findings help signpost areas where HEIs can improve the experiences of students with DCD that may also enhance academic success. Full article

Working memory (WM) is a crucial cognitive function, and a deficit in this function is a critical factor in learning difficulties (LDs). As a result, there is growing interest in exploring different approaches to training WM to support students with LDs. Following the PRISMA 2020 guidelines, this systematic review aims to identify current computer-based WM training applications and their theoretical foundations, explore their effects on improving WM capacity and other cognitive/academic abilities, and extract design principles for creating an effective WM application for children with LDs. The 22 studies selected for this review provide strong evidence that children with LDs have low WM capacity and that their WM functions can be trained. The findings revealed four commercial WM training applications—COGMED, Jungle, BrainWare Safari, and N-back—that were utilized in 16 studies. However, these studies focused on suggesting different types of WM tasks and examining their effects rather than making those tasks user-friendly or providing practical guidelines for the end-user. To address this gap, the principles of the Human–Computer Interaction, with a focus on usability and user experience as well as relevant cognitive theories, and the design recommendations from the selected studies have been reviewed to extract a set of proposed guidelines. A total of 15 guidelines have been extracted that can be utilized to design WM training programs specifically for children with LDs. Full article

Background/Objective: Learning difficulties (LDs) are lifelong neurodevelopmental disorders with multifactorial causes, including perinatal factors like mode of delivery. This study aims to explore whether cesarean section (CS) delivery is linked to the occurrence of specific learning disabilities (SLDs), attention-deficit/hyperactivity disorder (ADHD), or their comorbidity. Methods: An online questionnaire was distributed via Google Forms to Greek mothers and parents of children with and without diagnoses, shared through school-related groups and various Greek pages focused on child development, special education, and learning difficulties. Conducted over eight months (October 2023–May 2024), this cross-sectional study involved 256 children, 137 with LDs diagnoses, and 119 controls. Results: In total, 59.9% of CS-born children had a diagnosis, compared to 40.1% of those born vaginally (X²(1) = 4.19, p = 0.045). CS delivery was associated with a 68% increased likelihood of LDs (OR = 1.68, 95% CI [1.02, 2.76]), with higher risks for ADHD (OR = 2.25, 95% CI [1.06, 4.79]) and comorbid SLD/ADHD diagnoses (OR = 2.75, 95% CI [1.17, 6.46]). Stratified analyses showed birthweight and gestational age as effect modifiers rather than confounders. Key postnatal risk factors identified were family history (OR = 4.65, 95% CI [2.41, 8.94]) and language acquisition difficulties (OR = 5.28, 95% CI [1.36, 20.47]). Conclusions: The findings suggest a possible association between CS and LDs, along with a novel link between CS and increased comorbidities. These results underscore the need for further research and provide valuable insights into how CS delivery may influence the risk of LDs, depending on the type of diagnosis. Full article

Facial expression recognition (FER) techniques can be widely used in human-computer interaction, intelligent robots, intelligent monitoring, and other domains. Currently, FER methods based on deep learning have become the mainstream schemes. However, these methods have some problems, such as a large number of parameters, difficulty in being applied to embedded processors, and the fact that recognition accuracy is affected by facial deflection. To solve the problem of a large number of parameters, we propose a DSC-DenseNet model, which improves the standard convolution in DenseNet to depthwise separable convolution (DSC). To solve the problem wherein face deflection affects the recognition effect, we propose a posture normalization model based on GAN: a GAN with two local discriminators (LD-GAN) that strengthen the discriminatory abilities of the expression-related local parts, such as the parts related to the eyes, eyebrows, mouth, and nose. These discriminators improve the model’s ability to retain facial expressions and evidently benefits FER. Quantitative and qualitative experimental results on the Fer2013 and KDEF datasets have consistently shown the superiority of our FER method when working with multi-pose face images. Full article

The aim of the present study was to investigate goal orientations and classroom goal structures and their relationship with strategies of self-regulated learning (SRL) in students with and without learning disabilities (LD) and reading comprehension difficulties (RCD). The sample consisted of 537 students attending the two last grades of primary school, fifth and sixth grade (Mage = 11.28 years, SD = ±0.59). Of these, 58 students were diagnosed with LD, and 70 students, after individually administered assessments in reading accuracy and reading comprehension, were assigned to the RCD group. Self-reported questionnaires were administered, assessing students’ personal goal orientations, classroom goal structures, and strategies of SRL. The results showed that students with LD and students with RCD scored lower in mastery orientation and higher in performance avoidance compared to their peers without difficulties (ND). LD students reported lower scores of adaptive strategies than their peers. In addition, the results confirmed the adaptive character of mastery-approach goals and mastery goal structures and the negative effects of performance-avoidance goals and performance goal structures on the adaptive strategies of SRL. Performance-approach goals predicted adaptive behaviors for all students, confirming the argument of an adaptive type of motivation. The findings of the current study highlight the importance of goal orientations and classroom goal structures for students’ SRL. Implications of the findings for enhancing motivation for students with LD and students with RCD are discussed. Full article

Logo detection is one of the crucial branches in computer vision due to various real-world applications, such as automatic logo detection and recognition, intelligent transportation, and trademark infringement detection. Compared with traditional handcrafted-feature-based methods, deep learning-based convolutional neural networks (CNNs) can learn both low-level and high-level image features. Recent decades have witnessed the great feature representation capabilities of deep CNNs and their variants, which have been very good at discovering intricate structures in high-dimensional data and are thereby applicable to many domains including logo detection. However, logo detection remains challenging, as existing detection methods cannot solve well the problems of a multiscale and large aspect ratios. In this paper, we tackle these challenges by developing a novel long-range dependence involutional network (LDI-Net). Specifically, we designed a strategy that combines a new operator and a self-attention mechanism via rethinking the intrinsic principle of convolution called long-range dependence involution (LD involution) to alleviate the detection difficulties caused by large aspect ratios. We also introduce a multilevel representation neural architecture search (MRNAS) to detect multiscale logo objects by constructing a novel multipath topology. In addition, we implemented an adaptive RoI pooling module (ARM) to improve detection efficiency by addressing the problem of logo deformation. Comprehensive experiments on four benchmark logo datasets demonstrate the effectiveness and efficiency of the proposed approach. Full article

The Strengths and Difficulties Questionnaire (SDQ) is a worldwide questionnaire used for the early identification of behavioural/emotional symptoms in children and adolescents with neuropsychiatric disorders. Although its prognostic power has been studied, it has not yet been tested whether SDQ: (i) can identify pathognomonic symptoms across a variety of neurodevelopmental and neuropsychiatric disorders, (ii) can capture emotional and behavioural problems associated with the main diagnosis, as well as shared transdiagnostic dimensions, and (iii) can detect changes in symptomatology with age. The present study evaluated nearly 1000 children and adolescents overall with Global Developmental Delay (GDD), Intellectual Disability (ID), Language Disorder (LD), Specific Learning Disorder (SLD), Autism Spectrum Disorder (ASD), Attention Deficit/Hyperactivity Disorder (ADHD), Mood Disorder (MD), Anxiety Disorder (AD), and Eating Disorders (ED). We found that SDQ: (i) can identify the core symptoms in children with ASD, ADHD, MD, and AD via specific subscales; (ii) can capture the associated emotional and behavioural symptoms in children with LD, GDD, ID, SLD, and ED; and (iii) can detect changes in the symptomatology, especially for GDD, LD, ASD, ADHD, and AD. SDQ is also able to recognise the transdiagnostic dimensions across disorders. Our results underscore the potential of SDQ to specifically differentiate and identify behavioural/emotional profiles associated with clinical diagnosis. Full article

The aim of the present study was to investigate the effects of the coronavirus crisis on behavioral and emotional parameters in children and adolescents with ADHD and Learning Difficulties. A total of 101 children, 5–18 years old, were included in the study, 63 (44 boys) of which were diagnosed with ADHD and learning difficulties (ADHD/LD) and 38 were healthy children (19 boys). The CRISIS questionnaire for parents/caregivers was used. The questionnaire was completed during the first national lockdown in Greece and the data referred to two time-points: 3 months before, and the past 2 weeks. A significant deterioration in the “Emotion/Worries (EW)” symptoms was observed during the pandemic in the control group (2.62 ± 0.16 vs. 2.83 ± 0.18, p < 0.001). No such differences were noted in the ADHD group: 3.08 ± 0.25 vs. 3.12 ± 0.29, p = 0.12. Provision of educational and activities support was related to increased EW before the crisis. In ADHD/LD children, higher parental education and child’s younger age were related to increased symptoms of EW. In the entire group, previous mental health conditions, increasing stress due to restrictions, and increased COVID-related worries were positively associated with the EW symptoms during the crisis. Less affected relations with friends and less reduction in contact with people outside the home were negatively related with EW during the crisis. The study revealed specific parameters that negatively affected the emotional and behavioral variables of children with ADHD and learning difficulties. Full article

The aim of this research was to investigate the impact of the COVID-19 pandemic on teachers, particularly on their self-esteem and self-efficacy, their difficulty in the transition to distance learning, the difficulty of students, and specially of students with learning disabilities (LDs students), as perceived by teachers. 226 teachers were invited to complete an online questionnaire. Our results showed lower self-esteem and lower self-efficacy by the teachers compared with the normative sample. Self-esteem and self-efficacy also decrease in teachers with greater service seniority at work. Teachers perceived a greater difficulty in students than in their own difficulty. The concentration of the school system’s efforts on the massive and, for long periods, exclusive organisation of distance learning risks favouring only cognitive aspects to the detriment of affective dynamics. This aspect could make teaching more complex for teachers and learning poorer for students, impoverishing the complex relational process that forms the basis of the learning process. Full article

Reading and writing skills influence the social status of students, exerting effects not only on learning, but also on wellbeing. This study aimed to assess the impact of diagnosis of specific learning disorder on well-being in secondary-school students, comparing students with a diagnosis of specific learning disorder (SLD-group), students showing learning difficulties without diagnosis (LD-group) and students without learning difficulties (control-group). Students were tested with neuropsychological screening tests in order to identify learning difficulties and were further assessed by means of psychological and school well-being questionnaires. The results show that LD group perceive themselves as having a low sense of mastery and autonomy, less interest and engagement in daily activities and low peer social support than their schoolmates. This result highlights, for the LD group, a low well-being experience, which is not observed in the SLD and control groups. On the contrary, SLD group students do not differ from control group students in any dimensions except for the perceived parents’ support and involvement in school life, in which the SLD group show the highest scores. This work underlines the importance of having a diagnosis as it seems to work as a protective factor for both the psychological and school well-being of the student. Full article

Learning disabilities (LDs) have an estimated prevalence between 5% and 9% in the pediatric population and are associated with difficulties in reading, arithmetic, and writing. Previous electroencephalography (EEG) research has reported a lag in alpha-band development in specific LD phenotypes, which seems to offer a possible explanation for differences in EEG maturation. In this study, 40 adolescents aged 10–15 years with LDs underwent 10 sessions of Live Z-Score Training Neurofeedback (LZT-NF) Training to improve their cognition and behavior. Based on the individual alpha peak frequency (i-APF) values from the spectrogram, a group with normal i-APF (ni-APF) and a group with low i-APF (li-APF) were compared in a pre-and-post-LZT-NF intervention. There were no statistical differences in age, gender, or the distribution of LDs between the groups. The li-APF group showed a higher theta absolute power in P4 (p = 0.016) at baseline and higher Hi-Beta absolute power in F3 (p = 0.007) post-treatment compared with the ni-APF group. In both groups, extreme waves (absolute Z-score of ≥1.5) were more likely to move toward the normative values, with better results in the ni-APF group. Conversely, the waves within the normal range at baseline were more likely to move out of the range after treatment in the li-APF group. Our results provide evidence of a viable biomarker for identifying optimal responders for the LZT-NF technique based on the i-APF metric reflecting the patient’s neurophysiological individuality. Full article

Research has shown that academic success is strongly associated with positive academic self-efficacy beliefs and that individuals with learning disabilities (LDs) usually report a lower perception of competence than their peers in most learning domains. The aim of this study was two-fold: (1) To compare the performance of inaccurate writers who were not diagnosed with an LD with that of students who were diagnosed with an LD, in order to identify which tasks were the most challenging for individuals with LDs, and (2) to investigate whether inaccurate writers with and without a diagnosis differ in terms of self-perceived difficulties. Two groups were selected from a total sample of 639 students attending seven Italian universities: The first group included 48 participants (24 females) with scores on writing tasks below the 5th percentile, and the second included 51 participants (24 females) who were diagnosed with an LD. The results showed that the two groups significantly differed in the articulatory suppression condition tasks, but not in the standard condition tasks. When groups were matched for performance on writing tasks, students who were diagnosed with an LD reported significantly more perceived difficulties than students without an LD. The implications of these results in terms of the self-efficacy beliefs of students with an LD are discussed. Full article