Search Results (680)

Autism Spectrum Disorder (ASD) is a complex developmental condition marked by challenges in social interaction, communication, and behavior, often involving restricted interests and repetitive actions. The diversity in symptoms and skill profiles across individuals creates a diagnostic landscape that requires a multifaceted approach for accurate understanding and intervention. This study employed advanced machine-learning techniques to enhance the accuracy and reliability of ASD diagnosis. We used a standard dataset comprising 1054 patient samples and 20 variables. The research methodology involved rigorous preprocessing, including selecting key variables through data mining (DM) visualization techniques including Chi-Square tests, analysis of variance, and correlation analysis, along with outlier removal to ensure robust model performance. The proposed DM and logistic regression (LR) with Shapley Additive exPlanations (DMLRS) model achieved the highest accuracy at 99%, outperforming state-of-the-art methods. eXplainable artificial intelligence was incorporated using Shapley Additive exPlanations to enhance interpretability. The model was compared with other approaches, including XGBoost, Deep Models with Residual Connections and Ensemble (DMRCE), and fast lightweight automated machine learning systems. Each method was fine-tuned, and performance was verified using k-fold cross-validation. In addition, a real-time web application was developed that integrates the DMLRS model with the Django framework for ASD diagnosis. This app represents a significant advancement in medical informatics, offering a practical, user-friendly, and innovative solution for early detection and diagnosis. Full article

This study introduces a novel measure for evaluating attribute relevance, specifically designed to accurately identify attributes that are intrinsically related to a phenomenon, while being sensitive to the asymmetry of those relationships and noise conditions. Traditional variable selection techniques, such as filter and wrapper methods, often fall short in capturing these complexities. Our methodology, grounded in decision trees but extendable to other machine learning models, was rigorously evaluated across various data scenarios. The results demonstrate that our measure effectively distinguishes relevant from irrelevant attributes and highlights how relevance is influenced by noise, providing a more nuanced understanding compared to established methods such as Pearson, Spearman, Kendall, MIC, MAS, MEV, GMIC, and $Ph{i}_k$. This research underscores the importance of phenomenon-centric explainability, reproducibility, and robust attribute relevance evaluation in the development of predictive models. By enhancing both the interpretability and contextual accuracy of models, our approach not only supports more informed decision making but also contributes to a deeper understanding of the underlying mechanisms in diverse application domains, such as biomedical research, financial modeling, astronomy, and others. Full article

Hyperaccumulators within the Noccaea genus possess many promising genetic and metabolic adaptations that could be potentially exploited to support phytoremediation efforts and/or crop improvement and biofortification. Although hyperaccumulation is very common in this genus, individual species display specific traits as they can accumulate different elements (e.g., zinc, cadmium, and/or nickel). Moreover, there appears to be some populational variability with natural selection increasing the metal tolerance in metallicolous populations. Therefore, employing robust methods, such as integrated analysis of the transcriptome and metabolome, is crucial for uncovering pivotal candidate genes and pathways orchestrating the response to metal stress in Noccaea hyperaccumulators. Our study highlights several species-specific traits linked to the detoxification of metals and metal-induced oxidative stress in hyperaccumulating N. praecox when compared to a closely related model species, N. caerulescens, when grown in the field. Transcriptome analysis revealed distinct differences between the three studied natural Noccaea populations. Notably, we observed several pathways frequently connected to metal stress, i.e., glutathione metabolism, phenylpropanoid biosynthesis, and flavonoid biosynthesis, which were enriched. These differences were observed despite the relative evolutionary closeness of studied species, which emphasizes the importance of further expanding our knowledge on hyperaccumulators if we want to exploit their mechanisms for phytoremediation efforts or food quality improvements. Full article

Background: During the last decades, a small number of studies reported a wide range of variability in the estimated prevalence of mitral valve prolapse (MVP) among individuals with pectus excavatum (PE). The present systematic review and meta-analysis has been primarily designed to summarize the main findings of these studies and to estimate the overall prevalence of MVP among PE individuals. Methods: All imaging studies assessing the prevalence of MVP in PE individuals vs. healthy controls, selected from PubMed and EMBASE databases, were included. The risk of bias was assessed by using the National Institutes of Health (NIH) Quality Assessment of Case–Control Studies. Events (presence of MVP) and nonevents (absence of MVP) in PE individuals and control groups were recorded. The main outcome was the measure of odds ratio (OR) for MVP presence pooled with 95% confidence intervals, using a fixed-effects model. Results: The full texts of eight studies with 303 PE patients (mean age 25.7 yrs) and 498 healthy controls (mean age 31 yrs) were analyzed. Three studies assessed MVP prevalence in children and early adolescents, whereas the remaining five studies examined PE adults. The prevalence of MVP in PE individuals and healthy controls was 40.6% and 12.8%, respectively. In the pooled sample, the OR for MVP presence was significantly higher in PE individuals compared to controls (OR = 5.80, 95%CI = 3.83–8.78, Z = 8.30, p < 0.001). Subgroup analysis revealed that MVP prevalence was approximately three-fold higher among PE children and early adolescents compared with PE adults. Overall, high consistency was observed in the pooled effect sizes, due to the low statistical heterogeneity among the included studies (I² = 22.7%, p = 0.25). Egger’s test for a regression intercept gave a p-value of 0.07, indicating no publication bias. The sensitivity analysis supported the robustness of the results. Conclusions: PE individuals are nearly six times more likely to have MVP than controls. MVP prevalence is three-fold higher in PE individuals during childhood and early adolescence, compared to PE adults. Given the strong association between MVP and PE, MVP should be suspected in all individuals with anterior chest wall deformity. Full article

Accurate and efficient short-term load forecasting (STLF) is essential for optimizing power system operations. This study proposes a novel hybrid forecasting model that integrates XGBoost-RF feature selection with a CNN-GRU neural network to enhance prediction performance while reducing model complexity. The XGBoost-RF approach is first applied to select the most predictive features from historical load data, weather conditions, and time-based variables. A convolutional neural network (CNN) is then employed to extract spatial features, while a gated recurrent unit (GRU) captures temporal dependencies for load forecasting. By leveraging a dual-channel structure that combines long- and short-term historical load trends, the proposed model significantly mitigates cumulative errors from recursive predictions. Experimental results demonstrate that the model achieves superior performance with an average root mean square error (RMSE) of 53.29 and mean absolute percentage error (MAPE) of 3.56% on the test set. Compared to traditional models, the prediction accuracy improves by 28.140% to 110.146%. Additionally, the model exhibits strong robustness across different climatic conditions. This research validates the efficacy of integrating XGBoost-RF feature selection with CNN-GRU for STLF, offering reliable decision support for power system management. Full article

Cardiovascular diseases (CVDs) are a leading cause of mortality worldwide, with a particularly high burden in India. Non-invasive methods like Phonocardiogram (PCG) analysis capture the acoustic activity of the heart. This holds significant potential for the early detection and diagnosis of heart conditions. However, the complexity and variability of PCG signals pose considerable challenges for accurate classification. Traditional methods of PCG signal analysis, including time-domain, frequency-domain, and time-frequency domain techniques, often fall short in capturing the intricate details necessary for reliable diagnosis. This study introduces an innovative approach that leverages harmonic–percussive source separation (HPSS) to extract distinct harmonic and percussive spectral features from PCG signals. These features are then utilized to train a deep feed-forward artificial neural network (ANN), classifying heart conditions as normal or abnormal. The methodology involves advanced digital signal processing techniques applied to PCG recordings from the PhysioNet 2016 dataset. The feature set comprises 164 attributes, including the Chroma STFT, Chroma CENS, Mel-frequency cepstral coefficients (MFCCs), and statistical features. These are refined using the ROC-AUC feature selection method to ensure optimal performance. The deep feed-forward ANN model was rigorously trained and validated on a balanced dataset. Techniques such as noise reduction and outlier detection were used to improve model training. The proposed model achieved a validation accuracy of 93.40% with sensitivity and specificity rates of 82.40% and 80.60%, respectively. These results underscore the effectiveness of harmonic-based features and the robustness of the ANN in heart sound classification. This research highlights the potential for deploying such models in non-invasive cardiac diagnostics, particularly in resource-constrained settings. It also lays the groundwork for future advancements in cardiac signal analysis. Full article

Background: The Internet of Things (IoT) has improved many aspects that have impacted the industry and the people’s daily lives. To begin with, the IoT allows communication to be made across a wide range of devices, from household appliances to industrial machinery. This connectivity allows for a better integration of the pervasive computing, making devices “smart” and capable of interacting with each other and with the corresponding users in a sublime way. However, the widespread adoption of IoT devices has introduced some security challenges, because these devices usually run in environments that have limited resources. As IoT technology becomes more integrated into critical infrastructure and daily life, the need for stronger security measures will increase. These devices are exposed to a variety of cyber-attacks. This literature review synthesizes the current research of artificial intelligence (AI) technologies to improve IoT security. This review addresses key research questions, including: (1) What are the primary challenges and threats that IoT devices face?; (2) How can AI be used to improve IoT security?; (3) What AI techniques are currently being used for this purpose?; and (4) How does applying AI to IoT security differ from traditional methods? Methods: We included a total of 33 peer-reviewed studies published between 2020 and 2024, specifically in journal and conference papers written in English. Studies irrelevant to the use of AI for IoT security, duplicate studies, and articles without full-text access were excluded. The literature search was conducted using scientific databases, including MDPI, ScienceDirect, IEEE Xplore, and SpringerLink. Results were synthesized through a narrative synthesis approach, with the help of the Parsifal tool to organize and visualize key themes and trends. Results: We focus on the use of machine learning, deep learning, and federated learning, which are used for anomaly detection to identify and mitigate the security threats inherent to these devices. AI-driven technologies offer promising solutions for attack detection and predictive analysis, reducing the need for human intervention more significantly. This review acknowledges limitations such as the rapidly evolving nature of IoT technologies, the early-stage development or proprietary nature of many AI techniques, the variable performance of AI models in real-world applications, and potential biases in the search and selection of articles. The risk of bias in this systematic review is moderate. While the study selection and data collection processes are robust, the reliance on narrative synthesis and the limited exploration of potential biases in the selection process introduce some risk. Transparency in funding and conflict of interest reporting reduces bias in those areas. Discussion: The effectiveness of these AI-based approaches can vary depending on the performance of the model and the computational efficiency. In this article, we provide a comprehensive overview of existing AI models applied to IoT security, including machine learning (ML), deep learning (DL), and hybrid approaches. We also examine their role in enhancing the detection accuracy. Despite all the advances, challenges still remain in terms of data privacy and the scalability of AI solutions in IoT security. Conclusion: This review provides a comprehensive overview of ML applications to enhance IoT security. We also discuss and outline future directions, emphasizing the need for collaboration between interested parties and ongoing innovation to address the evolving threat landscape in IoT security. Full article

Accelerated urbanization challenges cities globally. Ensuring good quality of life and environmental protection requires innovative, data-driven solutions. Sustainable and smart cities (SSCs) offer a promising response, but effective implementation depends on selecting and using appropriate dimensions and indicators. The main objective of this article is to present a systematic review within the framework of SSCs to study trends in the use of dimensions and indicators. A citation frequency index (Q) considering quartiles is used to determine the importance of the variables considered in this study. A spatiotemporal analysis of the dimensions and indicators detected is also performed. The results suggest that the multifaceted nature of SSCs necessitates a holistic approach, with environmental (Q3 = 0.536) and social (Q2 = 0.403) dimensions being principal. Despite the lower ranking (Q1 = 0.080) of the information and communication technology (ICT) dimension, its pervasive influence highlights its evolving importance. Effective ICT implementation relies on robust social and environmental foundations, illustrating their interdependence. The governance (Q1 = 0.169) dimension is also essential for the creation of transparent and equitable urban policies. Key indicators related to energy systems (Q2 = 0.379), data analysis (Q2 = 0.327), and resource management (Q2 = 0.291) are crucial for operational efficiency and sustainability. Continental differences in prioritizing SSC dimensions highlight the importance of context-specific strategies, reflecting unique challenges and opportunities faced by different continental areas. By understanding and addressing these continental differences, policymakers and urban planners can more effectively promote sustainable and resilient urban development worldwide. Full article

Carefully selecting variables in problems with large volumes of data are extremely important, as it reduces the complexity of the model, improves the interpretation of the results, and increases computational efficiency, ensuring more accurate and relevant analyses. This paper presents a comprehensive approach to selecting variables in multiple regression models using the stepwise procedure. As the main contribution of this study, we present the stepwise function implemented in Python to improve the effectiveness of statistical analyses, allowing the intuitive and efficient selection of statistically significant variables. The application of the function is exemplified in a real case study of real estate pricing, validating its effectiveness in improving the fit of regression models. In addition, we presented a methodological framework for treating joint problems in data analysis, such as heteroskedasticity, multicollinearity, and nonadherence of residues to normality. This framework offers a robust computational implementation to mitigate such issues. This study aims to advance the understanding and application of statistical methods in Python, providing valuable tools for researchers, students, and professionals from various areas. Full article

Breast cancer remains a major public health concern, and early detection is crucial for improving survival rates. Metabolomics offers the potential to develop non-invasive screening and diagnostic tools based on metabolic biomarkers. However, the inherent complexity of metabolomic datasets and the high dimensionality of biomarkers complicates the identification of diagnostically relevant features, with multiple studies demonstrating limited consensus on the specific metabolites involved. Unlike previous studies that rely on singular feature selection techniques such as Partial Least Square (PLS) or LASSO regression, this research combines supervised and unsupervised machine learning methods with random sampling strategies, offering a more robust and interpretable approach to feature selection. This study aimed to identify a parsimonious and robust set of biomarkers for breast cancer diagnosis using metabolomics data. Plasma samples from 185 breast cancer patients and 53 controls (from the Cooperative Human Tissue Network, USA) were analyzed. This study also overcomes the common issue of dataset imbalance by using propensity score matching (PSM), which ensures reliable comparisons between cancer and control groups. We employed Univariate Naïve Bayes, L2-regularized Support Vector Classifier (SVC), Principal Component Analysis (PCA), and feature engineering techniques to refine and select the most informative features. Our best-performing feature set comprised 11 biomarkers, including 9 metabolites (SM(OH) C22:2, SM C18:0, C0, C3OH, C14:2OH, C16:2OH, LysoPC a C18:1, PC aa C36:0 and Asparagine), a metabolite ratio (Kynurenine-to-Tryptophan), and 1 demographic variable (Age), achieving an area under the ROC curve (AUC) of 98%. These results demonstrate the potential for a robust, cost-effective, and non-invasive breast cancer screening and diagnostic tool, offering significant clinical value for early detection and personalized patient management. Full article

Traffic stops represent a crucial point of interaction between citizens and law enforcement, with potential implications for bias and discrimination. This study performs a rigorously validated comparative machine learning model analysis, creating artificial intelligence (AI) technologies to predict the results of traffic stops using a dataset sourced from the Montgomery County Maryland Data Centre, focusing on variables such as driver demographics, violation types, and stop outcomes. We repeated our rigorous validation of AI for the creation of models that predict outcomes with and without race and with and without gender informing the model. Feature selection employed regularly selects for gender and race as a predictor variable. We also observed correlations between model performance and both race and gender. While these findings imply the existence of discrimination based on race and gender, our large-scale analysis (>600,000 samples) demonstrates the ability to produce top performing models that are gender and race agnostic, implying the potential to create technology that can help mitigate bias in traffic stops. The findings encourage the need for unbiased data and robust algorithms to address biases in law enforcement practices and enhance public trust in AI technologies deployed in this domain. Full article

To develop agricultural risk management strategies, the early identification of water deficits during the growing cycle is critical. This research proposes a deep learning hybrid approach for multi-step soil moisture forecasting in the Bundaberg region in Queensland, Australia, with predictions made for 1-day, 14-day, and 30-day, intervals. The model integrates Geospatial Interactive Online Visualization and Analysis Infrastructure (Giovanni) satellite data with ground observations. Due to the periodicity, transience, and trends in soil moisture of the top layer, time series datasets were complex. Hence, the Maximum Overlap Discrete Wavelet Transform (moDWT) method was adopted for data decomposition to identify the best correlated wavelet and scaling coefficients of the predictor variables with the target top layer moisture. The proposed 3-phase hybrid moDWT-Lasso-LSTM model used the Least Absolute Shrinkage and Selection Operator (Lasso) method for feature selection. Optimal hyperparameters were identified using the Hyperopt algorithm with deep learning LSTM method. This proposed model’s performances were compared with benchmarked machine learning (ML) models. In total, nine models were developed, including three standalone models (e.g., LSTM), three integrated feature selection models (e.g., Lasso-LSTM), and three hybrid models incorporating wavelet decomposition and feature selection (e.g., moDWT-Lasso-LSTM). Compared to alternative models, the hybrid deep moDWT-Lasso-LSTM produced the superior predictive model across statistical performance metrics. For example, at 1-day forecast, The moDWT-Lasso-LSTM model exhibits the highest accuracy with the highest $R^2\approx 0.92469$ and the lowest RMSE $\approx 0.97808$, MAE $\approx 0.76623$, and SMAPE $\approx 4.39700$%, outperforming other models. The moDWT-Lasso-DNN model follows closely, while the Lasso-ANN and Lasso-DNN models show lower accuracy with higher RMSE and MAE values. The ANN and DNN models have the lowest performance, with higher error metrics and lower R2 values compared to the deep learning models incorporating moDWT and Lasso techniques. This research emphasizes the utility of the advanced complementary ML model, such as the developed moDWT-Lasso-LSTM 3-phase hybrid model, as a robust data-driven tool for early forecasting of soil moisture. Full article

The urgency of addressing farmland contamination is undeniable. However, the environmental impacts associated with soil remediation, especially during the production of remediation materials, are often overlooked. This study seeks to fill this gap by conducting a comprehensive environmental impact assessment of remediation material production processes. We apply a Life Cycle Assessment (LCA) framework, enhanced by a multi-objective optimization model combining the Analytic Hierarchy Process (AHP) and Techniques for Order Preference by Similarity to an Ideal Solution (TOPSIS). This method enables the integration of multiple environmental indicators into a high-dimensional reference system, reducing subjectivity in decision-making. The study focuses on the environmental impacts of 11 types of biochar materials used in soil remediation. Among these, alkali-modified biochar loaded with nano TiO₂ exhibited the highest environmental impact index. Sensitivity analysis further confirmed the robustness of the method, with impact variations ranging from 0.44 to 0.52, suggesting the model’s reliability in comparing different remediation materials. Our findings highlight the significant environmental variability between remediation materials and underscore the necessity of incorporating comprehensive environmental assessments in material selection processes. This study provides a valuable framework for optimizing the environmental sustainability of soil remediation efforts. Full article

Stock depletion level is an important concept in the assessment and management of exploited fish stocks because it is often used in conjunction with reference points to infer stock status. Both the depletion level and reference points can be highly dependent on the stock–recruitment relationship. Here, we show how depletion level is estimated in stock assessment models, what data inform the depletion level, and how the stock–recruitment relationship influences the depletion level. There are a variety of data that provide information on abundance. In addition, to estimate the depletion level, unexploited absolute abundance needs to be determined. This often means extrapolating the abundance back in time to the start of the fishery, accounting for the removals and the productivity. Uncertainty in the depletion level arises because the model can account for the same removals by either estimating low productivity (e.g., low natural mortality) and high carrying capacity or high productivity and a low carrying capacity, and by estimating different relationships between productivity and depletion level, which are strongly controlled by the stock–recruitment relationship. Therefore, estimates of depletion are particularly sensitive to uncertainty in the biological processes related to natural mortality and the stock–recruitment relationship and to growth when length composition data are used. In addition, depletion-based reference points are highly dependent on the stock–recruitment relationship and need to account for recruitment variability, particularly autocorrelation, trends, and regime shifts. Future research needs to focus on estimating natural mortality, the stock–recruitment relationship, asymptotic length, shape of the selectivity curve, or management strategies that are robust to uncertainty in these parameters. Tagging studies, including close-kin mark-recapture, can address some of these issues. However, the stock–recruitment relationship will remain uncertain. Full article

This meta-analysis investigated the concurrent validity between virtual reality (VR)-based assessments and traditional neuropsychological assessments of executive function, with a focus on subcomponents such as cognitive flexibility, attention, and inhibition. A total of 1605 articles were identified through searches of PubMed, Web of Science, and ScienceDirect from 2013 to 2023. After removing duplicates, 1313 articles were screened based on their titles and abstracts, with 77 articles selected for full-text eligibility review. Of these, nine articles fully met the inclusion and exclusion criteria for this study. The effect size for overall executive function was assessed, with subcomponents categorized based on the specific assessment tools used in the studies. The effect size for each subcomponent—cognitive flexibility, attention, and inhibition—was then analyzed to provide a more detailed understanding of their relationships with traditional measures. The results revealed statistically significant correlations between VR-based assessments and traditional measures across all subcomponents. Additionally, sensitivity analyses confirmed the robustness of the findings, even when low-quality studies were excluded. These results support the use of VR-based assessments as a valid alternative to traditional methods for evaluating executive function. Moreover, the study highlights the potential of VR-based assessments as a valid alternative to traditional methods, emphasizing the need to address variability in executive function subcomponents and integrate diverse cognitive and motor metrics for greater ecological validity. Full article