AI-Powered Personalized Therapy for Children with Autism: A Reinforcement Learning Approach

Autistic people are often disadvantaged in employment, education, etc. In fact, autistic students/employees face several challenges navigating and communicating with their superiors and colleagues. Mobile applications for people with Autism Spectrum Disorder (ASD apps for short) have been increasingly being adapted to help autistic people manage their conditions and daily activities. User feedback analysis is an effective method that can be used to improve ASD apps' services. In this article, we investigate the usage of ASD apps to improve the quality of life for autistic students/employees based on user feedback analysis. For this purpose, we analyze user reviews suggested on highly ranked ASD apps for college students, and workers. A total of 97,051 reviews have been collected from 13 ASD apps available on Google Play and Apple App stores. The collected reviews have been classified into negative, positive, and neutral opinions. This analysis has been performed using machine learning and deep learning models. The best performances were provided by combining RNN and LSTM models with an accuracy of 96.58% and an AUC of 99.41%. Finally, we provide some recommendations to improve ASD apps to assist developers in upgrading the main services provided by their apps.

Assisted reproductive technology and risk for autism spectrum disorder

The early detection and level assignment are very important in autism spectrum disorder (ASD) cases.In this paper, we introduce an autism diagnosing and level identification mobile application based on a deep-learning model.The application is designed with two stages; the first stage classifies children as either ASD children or potentially normal, while the second stage identifies the ASD level.For feature extraction and image classification, a convolutional neural network (CNN) is proposed.The 2,122 photos that were removed from the 3000 original dataset because of poor quality and racial imbalances made up the dataset used to develop and evaluate this model.Results show that the accuracy is 97.3% and the area under the curve is 99.8%.The identification of ASD level is performed using two welldefined scales in the literature that are adopted in the traditional examinations.Depending on the child's ASD level, psychiatrists provide specific and standard learning support.The application provides caregivers with fast decisions (about 20 minutes) to get an idea of the learning strategy to be followed with their child.Early intervention is very beneficial for children diagnosed with ASD, and these applications assist children in underfunded nations or those without access to healthcare.

Logical games often require players to solve various puzzles and strategic challenges. Thanks to the active implementation of Artificial Intelligence, it has possible to use Deep Learning models in such games, which has led to a significant breakthrough in solving other related tasks in the field. This paper presents a study on the development and training of two Reinforcement Learning algorithms, Q-learning and Deep Q-Network (DQN) for playing the game Togyz qumalaq. Both models were trained and evaluated in a game against MiniMax, which was also implemented by the authors of this research. The experiments were conducted with MiniMax recursion depths of 2, 3, and 4, respectively. The article presents the training parameters of models based on Q-learning and DQN, which achieved the best results. For each of the models, reward and training episode graphs are provided. The paper also includes the architecture of DQN, which demonstrated promising results. The results show that DQN has achieved significant success in solving this task, demonstrating notable performance. A comparative analysis also revealed that, unlike DQN, Q-learning requires more significant computational and memory resources for training.

This paper takes the problems and ways of diversified curriculum construction of vocal music education in colleges and universities as the entry point and constructs a deep blended learning model of vocal music diversified curriculum based on the deep learning model. The deep evolutionary knowledge tracking model is constructed by combining the self-attention mechanism embedding model with vocal music knowledge evolution based on Transformer. To verify the effectiveness of the deep blended learning model constructed in this paper, model comparison experiments and empirical analysis were conducted. The results show that compared with the SAKT model, the DBL model in this paper has a 5.19% improvement in the average ROC-AUC value. The vocal posttest scores of the students in the experimental class were 5.09 points higher than those of the control class, with a two-tailed significance value of 0.027, which is less than 0.05 and a significant difference. This indicates that the deep learning model can effectively promote the innovative design of diversified curricula for vocal music education in colleges and universities and enhance students’ vocal music learning ability.

Autism Spectrum Disorder (ASD) is a complex neurodevelopmental condition characterized by challenges in social interaction, communication, and behavior. Traditional diagnostic methods rely heavily on behavioral assessments, such as the Autism Diagnostic Observation Schedule (ADOS) and Autism Diagnostic Interview-Revised (ADI-R), which are often subjective and limited by the absence of definitive biomarkers. Recent advances in neuroimaging techniques, including structural MRI (sMRI), functional MRI (fMRI), and positron emission tomography (PET), have provided valuable insights into the structural and functional abnormalities associated with ASD. However, the analysis of neuroimaging data is complex, requiring sophisticated machine learning (ML) and artificial intelligence (AI) models. This paper reviews state-of-the-art machine learning approaches, such as Random Forests, Support Vector Machines (SVM), and deep learning models, aimed at improving the diagnostic accuracy of ASD. We particularly focus on multimodal deep learning models that integrate neuroimaging data with behavioral assessments. In this review, we critically evaluate the strengths and limitations of these approaches, and how emerging AI tools not only enhance classification accuracy but also hold potential for identifying biomarkers and tracking the disorder's progression. Our analysis underscores the need for advanced methods that exploit both spatial and temporal features of brain data to better understand ASD, paving the way for improved diagnostics and personalized treatments.

Early diagnosis and access to resources, support and therapy are critical for improving long-term outcomes for children with autism spectrum disorder (ASD). ASD is typically detected using a case-finding approach based on symptoms and family history, resulting in many delayed or missed diagnoses. While population-based screening would be ideal for early identification, available screening tools have limited accuracy. This study aims to determine whether machine learning models applied to health administrative and birth registry data can identify young children (aged 18 months to 5 years) who are at increased likelihood of developing ASD. We assembled the study cohort using individually linked maternal-newborn data from the Better Outcomes Registry and Network (BORN) Ontario database. The cohort included all live births in Ontario, Canada between April 1st, 2006, and March 31st, 2018, linked to datasets from Newborn Screening Ontario (NSO), Prenatal Screening Ontario (PSO), and Canadian Institute for Health Information (CIHI) (Discharge Database (DAD) and National Ambulatory Care Reporting System (NACRS)). The NSO and PSO datasets provided screening biomarker values and outcomes, while DAD and NACRS contained diagnosis codes and intervention codes for mothers and offspring. Extreme Gradient Boosting models and large-scale ensembled Transformer deep learning models were developed to predict ASD diagnosis between 18 and 60 months of age. Leveraging explainable artificial intelligence methods, we determined the impactful factors that contribute to increased likelihood of ASD at both an individual- and population-level. The final study cohort included 707,274 mother-offspring pairs, with 10,956 identified cases of ASD. The best-performing ensemble of Transformer models achieved an area under the receiver operating characteristic curve of 69.6% for predicting ASD diagnosis, a sensitivity of 70.9%, a specificity of 56.9%. We determine that our model can be used to identify an enriched pool of children with the greatest likelihood of developing ASD, demonstrating the feasibility of this approach.This study highlights the feasibility of employing machine learning models and routinely collected health data to systematically identify young children at high likelihood of developing ASD. Ensemble transformer models applied to health administrative and birth registry data offer a promising avenue for universal ASD screening. Such early detection enables targeted and formal assessment for timely diagnosis and early access to resources, support, or therapy.

This study proposes a reinforcement learning-based link selection method for Low Earth Orbit satellite networks, aiming to reduce handover frequency while extending link duration under highly dynamic orbital environments. The proposed approach relies solely on basic satellite positional information, namely latitude, longitude, and altitude, to construct compact state representations without requiring complex sensing or prediction mechanisms. Using relative satellite and terminal geometry, each state is represented as a vector consisting of azimuth, elevation, range, and direction difference. To validate the feasibility of policy learning under realistic conditions, a total of 871,105 orbit based data samples were generated through simulations of 300 LEO satellite orbits. The reinforcement learning environment was implemented using the OpenAI Gym framework, in which an agent selects an optimal communication target from a prefiltered set of candidate satellites at each time step. Three reinforcement learning algorithms, namely SARSA, Q-Learning, and Deep Q-Network, were evaluated under identical experimental conditions. Performance was assessed in terms of smoothed total reward per episode, average handover count, and average link duration. The results show that the Deep Q-Network-based approach achieves approximately 77.4% fewer handovers than SARSA and 49.9% fewer than Q-Learning, while providing the longest average link duration. These findings demonstrate that effective handover control can be achieved using lightweight state information and indicate the potential of deep reinforcement learning for future LEO satellite communication systems.

Developmental Trajectories in Adolescents and Adults With Autism: The Case of Daily Living Skills

Background: This systematic review examines artificial intelligence (AI) applications in neuroimaging for autism spectrum disorder (ASD), addressing six research questions regarding biomarker optimization, modality integration, social function prediction, developmental trajectories, clinical translation challenges, and multimodal data enhancement for earlier detection and improved outcomes. Methods: Following PRISMA guidelines, we conducted a comprehensive literature search across 8 databases, yielding 146 studies from an initial 1872 records. These studies were systematically analyzed to address key questions regarding AI neuroimaging approaches in ASD detection and prognosis. Results: Neuroimaging combined with AI algorithms demonstrated significant potential for early ASD detection, with electroencephalography (EEG) showing promise. Machine learning classifiers achieved high diagnostic accuracy (85-99%) using features derived from neural oscillatory patterns, connectivity measures, and signal complexity metrics. Studies of infant populations have identified the 9-12-month developmental window as critical for biomarker detection and the onset of behavioral symptoms. Multimodal approaches that integrate various imaging techniques have substantially enhanced predictive capabilities, while longitudinal analyses have shown potential for tracking developmental trajectories and treatment responses. Conclusions: AI-driven neuroimaging biomarkers represent a promising frontier in ASD research, potentially enabling the detection of symptoms before they manifest behaviorally and providing objective measures of intervention efficacy. While technical and methodological challenges remain, advancements in standardization, diverse sampling, and clinical validation could facilitate the translation of findings into practice, ultimately supporting earlier intervention during critical developmental periods and improving outcomes for individuals with ASD. Future research should prioritize large-scale validation studies and standardized protocols to realize the full potential of precision medicine in ASD.

Electricity load forecasting is a crucial undertaking within all the deregulated markets globally. Among the research challenges on a global scale, the investigation of deep transfer learning (DTL) in the field of electricity load forecasting represents a fundamental effort that can inform artificial intelligence applications in general. In this paper, a comprehensive study is reported regarding day-ahead electricity load forecasting. For this purpose, three sequence-to-sequence (Seq2seq) deep learning (DL) models are used, namely the multilayer perceptron (MLP), the convolutional neural network (CNN) and the ensemble learning model (ELM), which consists of the weighted combination of the outputs of MLP and CNN models. Also, the study focuses on the development of different forecasting strategies based on DTL, emphasizing the way the datasets are trained and fine-tuned for higher forecasting accuracy. In order to implement the forecasting strategies using deep learning models, load datasets from three Greek islands, Rhodes, Lesvos, and Chios, are used. The main purpose is to apply DTL for day-ahead predictions (1–24 h) for each month of the year for the Chios dataset after training and fine-tuning the models using the datasets of the three islands in various combinations. Four DTL strategies are illustrated. In the first strategy (DTL Case 1), each of the three DL models is trained using only the Lesvos dataset, while fine-tuning is performed on the dataset of Chios island, in order to create day-ahead predictions for the Chios load. In the second strategy (DTL Case 2), data from both Lesvos and Rhodes concurrently are used for the DL model training period, and fine-tuning is performed on the data from Chios. The third DTL strategy (DTL Case 3) involves the training of the DL models using the Lesvos dataset, and the testing period is performed directly on the Chios dataset without fine-tuning. The fourth strategy is a multi-task deep learning (MTDL) approach, which has been extensively studied in recent years. In MTDL, the three DL models are trained simultaneously on all three datasets and the final predictions are made on the unknown part of the dataset of Chios. The results obtained demonstrate that DTL can be applied with high efficiency for day-ahead load forecasting. Specifically, DTL Case 1 and 2 outperformed MTDL in terms of load prediction accuracy. Regarding the DL models, all three exhibit very high prediction accuracy, especially in the two cases with fine-tuning. The ELM excels compared to the single models. More specifically, for conducting day-ahead predictions, it is concluded that the MLP model presents the best monthly forecasts with MAPE values of 6.24% and 6.01% for the first two cases, the CNN model presents the best monthly forecasts with MAPE values of 5.57% and 5.60%, respectively, and the ELM model achieves the best monthly forecasts with MAPE values of 5.29% and 5.31%, respectively, indicating the very high accuracy it can achieve.

Attention-based deep learning models for predicting anomalous shock of wastewater treatment plants.

Background: Early intervention will help children with autism spectrum disorder (ASD) to attain early learning reinforcement. This study focuses on exploring the ability of preschool teachers to identify children with ASD and their referral decision-making process. Method: This is a mixed-method study (qualitative and quantitative methods) involving 20 respondents. The qualitative study is based on an open question case study, while the quantitative study consists of questionnaire with demographic variables to identify the effect of the demographic variables on the preschool teachers’ ability to identify children with ASD. Sample: The sample was selected via convenience sampling among mainstream preschool teachers. The data was analyzed using SPSS software and thematic analysis. Results: The findings show that preschool teachers did not have skills at identifying children with ASD, and the majority of them labelled children with ASD as spoilt or hyperactive children. They also viewed children with ASD as having other disorders such as attention deficit hyperactivity disorder (ADHD) or communication disorders such as introversion. Moreover, preschool teachers expressed that the reason for the child’s behaviour could be due to the parents’ inability to properly educate their child. Additionally, the demographic variables of the preschool teachers, such as age, education level and teaching experience, were found not to affect their ASD identification skills. Conclusion: Preschool teachers need to improve their skills in identifying ASD among children via training.

Development of cortical thickness and surface area in autism spectrum disorder.

IntroductionChildren with Autism Spectrum Disorder (ASD) often find it difficult to maintain eye contact, which is vital for social communication. Eye tracking (ET) technology helps determine how long children with ASD focus on someone, how frequently they do so, and in which direction their gaze moves. ET provides insights into social attention by enabling precise, real-time tracking of gaze patterns as individuals process social information visually. It is a dependable method for identifying and developing social attentional biomarkers, particularly in challenging conditions like ASD.ObjectiveThis study aims to implement deep learning (DL) algorithms using eye-tracking data from social attention tasks involving children with ASD.MethodsThe approach was tested using standard datasets collected from individuals with and without ASD through eye-tracking technology. Convolutional neural networks (CNNs) and long short-term memory (LSTM) models were used to analyze data from children with ASD. Data preprocessing techniques addressed missing data and converted categorical features into numerical values. Mutual information-based feature selection was employed to reduce the feature set by identifying the most relevant features, thereby improving system performance. These features were then analyzed using LSTM and CNN-LSTM models to evaluate their potential for diagnosing ASD.ResultsThe experimental results showed that the highest accuracy achieved was 99.78% with the CNN-LSTM model. Furthermore, the findings indicated that the proposed method outperformed previous studies.ConclusionThe system successfully diagnosed ASD using the ET dataset. This approach shows promise for clinical application, assisting healthcare professionals in diagnosing ASD more accurately through advanced artificial intelligence technology.