Browse Articles

A joint complex network and machine learning approach for the identification of discriminative gene communities in autistic brain

Autism is a genetically and clinically very heterogeneous group of disorders. Gene co-expression network analysis can help unravel its complex genetic architecture through the identification of communities of genes that are dysregulated. Using a publicly available brain microarray dataset (experiment GSE28475), we performed a gene co-expression analysis based on Leiden community detection to identify stable communities of genes and used them within a robust machine learning framework with feature selection. We reached an accuracy as high as ( 98 ± 1 ) % in discriminating between autism and control subjects and validated our results on an independent microarray experiment obtaining an accuracy of ( 88 ± 3 ) % . Furthermore, we found two communities of 43 and 44 genes that were enriched for genetically associated variants and reached an accuracy of ( 78 ± 5 ) % and ( 75 ± 4 ) % on the independent set, respectively. An eXplainable Artificial Intelligence analysis on these two causal communities confirmed the pivotal role of autism specific variants thus independently validating our analysis. Further analysis on the restricted number of genes in the identified communities may reveal essential mechanisms responsible for autism spectrum disorder.

ekofertile and microfertile plant biostimulants enhanced wheat productivity and water use efficiency

Root cause analysis of accidents and examining their interrelations from the perspective of workers, supervisors, and safety officers

Identifying the root causes of accidents and analyzing their causal relationships is a fundamental step in designing effective preventive strategies. This study aimed to uncover the root causes of mining accidents and determine the interactions among them from the perspectives of workers, supervisors, and safety officers using a mixed qualitative-quantitative approach and the fuzzy DEMATEL method. The study was designed as a mixed-method approach (qualitative-quantitative). In the qualitative phase, a total of 69 interviews were conducted (23 with workers, 21 with supervisors, and 25 with safety officers) to identify and categorize the root causes of accidents. In the quantitative phase, 33 participants (11 from each group) took part in expert panels where the fuzzy DEMATEL method was employed to analyze the relationships among the factors. The qualitative phase results revealed that workers primarily pointed to operational deficiencies, equipment issues, and workplace conditions. Supervisors emphasized human behavior, psychological stress, and a lack of safety culture, while safety officers highlighted managerial weaknesses and inefficient communication structures. The quantitative phase results identified management as the primary and most influential factor, whereas other factors, including humans, machinery, environment, and materials, predominantly appeared as dependent factors. This study’s findings suggest that understanding and analyzing the causal relationships among factors, coupled with integrating diverse perspectives, can aid in designing effective preventive strategies and reducing mining accidents. This approach enhances safety, productivity, and job satisfaction.

Chirality-Regulated Spin-Polarization of Perovskite Nanoplates for Photocatalytic CO ₂ Reduction Reaction

Optimization of energy consumption in the gas refinery sweetening unit using RSM, ANN, and Aspen HYSYS

Deep learning-based automated detection of supernumerary teeth in pediatric panoramic radiographs

Introduction Supernumerary teeth are a common developmental anomaly in pediatric patients, potentially leading to complications such as impaction, crowding, and delayed eruption. Accurate and early detection is critical to prevent these sequelae and guide appropriate intervention strategies. This study aims to evaluate the diagnostic accuracy and clinical applicability of a convolutional neural networks-based deep learning model (YOLOv8) for the automated localization and binary classification of supernumerary teeth on pediatric panoramic radiographs. Materials and methods A retrospective analysis was conducted on 2000 pediatric panoramic radiographs following ethical approval. Three calibrated pediatric dentists independently examined the dataset and annotated a representative subset of 140 radiographs (71 positive, 69 negative), achieving substantial inter-rater agreement (Cohen’s κ = 0.92). Performance was assessed in two stages: (1) segmentation of supernumerary teeth and (2) binary classification of radiographs. An independent validation set of 20 radiographs was used for secondary evaluation. Evaluation metrics included precision, recall, F1-score, and McNemar’s test to compare model predictions with expert labelling. Results The mean age of the patients was 9.6 ± 2.3 years; 52% were male, 48% were female. The segmentation model yielded 100% precision, 38% recall, and an F1-score of 55%, indicating strong localization when detections were made but limited sensitivity. The classification model achieved 100% accuracy, precision, recall, and F1-score on both internal and external datasets. McNemar’s test revealed no statistically significant discrepancy between the model and expert decisions (p > 0.05). The segmentation model demonstrated high precision in localizing supernumerary teeth; however, recall performance was more modest, indicating occasional under-detection. Due to the limited validation sample size, these findings should be interpreted with caution. Conclusions The YOLOv8-based pipeline demonstrated robust diagnostic accuracy in classifying panoramic radiographs for supernumerary teeth and promising but preliminary results in lesion-level segmentation. These findings highlight the potential utility of advanced deep learning systems in augmenting early diagnosis and streamlining pediatric dental radiology workflows.

Maximizing waste heat recovery from a building-integrated edge data center

Abstract Small data centers can be integrated into the energy systems of commercial and tertiary buildings to capture waste heat generated by servers, mitigate environmental impacts and enhance energy efficiency. This study introduces a novel methodology for maximizing waste heat capture from the cooling coils by optimizing workload distribution in an edge data center consisting of air-cooled servers. The maximization of outlet temperatures algorithm (MOTA) was developed using a validated fast thermal evaluation approach. Experimental studies were conducted to characterize parameters of the cooling system such as air and water flow rates and effectiveness of the coil. A multi-region conjugate heat transfer (CHT) numerical model was developed to demonstrate feasibility of the proposed approach. Heat transfer through the cooling coil was numerically modeled using the effectiveness-NTU method. Good agreement was achieved between the simulated and measured water temperatures at the outlet of the cooling coil. Numerical simulations conducted using the validated CHT model show that the MOTA can improve heat recovery by up to 17.1% under various IT loads. Furthermore, optimizing the water flow rate can reduce the cooling load by up to 53.2%. These combined results highlight the potential of the proposed algorithm for energy-efficient management of data centers. Computational cost and real-world applicability of the proposed algorithm were discussed in detail.

Utilizing big data and artificial intelligence to improve the cross-border trade english education

Strong verbal and written communication abilities are more valuable in today’s globalized world because of the increased frequency and complexity of cross-border encounters. Professionals require a high degree of linguistic competency and flexibility because of the frequent international communication necessary to handle complex business scenarios, laws, and fluctuating market conditions. The study is driven by a desire to customize language instruction to suit the unique needs of professionals involved in cross-border trade. The goal is to ensure that the skills students learn are relevant to the complexities of this industry. This study tackles the challenge of improving Cross-Border Trade English Education by integrating big data and Artificial Intelligence (AI). The Artificial Intelligence-based Cross-Border Trade English Education (AI-CTEE) uses Long Short-Term Memory (LSTM) networks to create personalized learning experiences, adapt the curriculum dynamically, and provide real-time language support. The AI-CTEE model examines long-term dependencies in sequential data to determine how LSTM-powered language education affects linguistic competency in cross-border trade. The longitudinal study uses LSTM networks to track language proficiency. Academics, communication, and cross-cultural adaptability are assessed. This study investigates the effects of ongoing exposure to LSTM-powered language instruction on the maintenance of language acquisition and the effectiveness of its practitioners in foreign trade settings. Insights into the long-term effects of combining AI with big data in the AI-CTEE model are provided by the study’s main conclusions and outcomes. This study highlights the necessity to strategically enhance language skills to survive in the ever-changing world of global trade, contributing to the continuing discourse regarding new language education methods. The proposed AI-CTEE model increases the retention rate by 98.5%, CPU utilization by 59%, memory consumption rate by 60%, response time analysis of 194 milliseconds, and interaction period by 78 minutes compared to other existing models.

Variability in water quality and chlorophyll a in the middle route of the south to north water diversion project

Football sports automatic judgment model based on improved YOLOv7 and RNN

The extraction, classification, and judgment of sports video scenes can improve work efficiency and accuracy. To understand sports videos in dynamic scenes, this study applies deep learning technology, firstly introducing clustering algorithm and attention mechanism to improve the target detection technology You Only Look Once v7, and identifying the targets existing in the scene. Then, the sparrow search algorithm in artificial intelligence algorithm is taken to optimize the parameter search of the recurrent neural network and automatically extract the target scene. After introducing three optimization strategies, the proposed model achieved a detection accuracy of 0.993 (as measured by classification accuracy), a floating-point calculation times of 244, and a detection speed of 264.245 fps. The average detection accuracy of this model was 0.95, and the loss function curve converged with the minimum number of iterations and convergence value. The maximum correlation accuracy was 0.958, and the detection accuracy was 0.926. Meanwhile, the model had the highest intersection over union ratio and recall rate on different datasets, reaching 0.885 and 0.961 respectively on the TrackingNet dataset. The improved scene extraction model had the smallest three error values, with the highest accuracy of 0.932, F1 of 0.955, and subject working characteristic curve area of 0.969. The R-squared value and semantic consistency of scene extraction perform well, improving the accuracy and fairness of football sports judgment. This study proposes an innovative solution to address sports video scene recognition, improving the accuracy of sports video scene recognition and bringing new effective technological means to the field of sports video analysis. Meanwhile, this study contributes to the rapid development of the sports industry and promotes the automation and popularization of football.

The multi-level image segmentation in dermatology application using an enhance Secretary Bird Optimization Algorithm

FastKAN-DDD: A novel fast Kolmogorov-Arnold network-based approach for driver drowsiness detection optimized for TinyML deployment

Driver drowsiness is a leading cause of traffic accidents and fatalities, highlighting the urgent need for intelligent systems capable of real-time fatigue detection. Although recent advancements in machine learning (ML) and deep learning (DL) have significantly improved detection accuracy, most existing models are computationally demanding and not well-suited for deployment in resource-limited environments such as microcontrollers. While the emerging domain of TinyML presents promising avenues for such applications, there remains a substantial gap in the development of lightweight, interpretable, and high-performance models specifically tailored for embedded automotive systems. This paper introduces FastKAN-DDD, an innovative driver drowsiness detection model grounded in the Fast Kolmogorov-Arnold Network (FastKAN) architecture. The model incorporates learnable nonlinear activation functions based on radial basis functions (RBFs), facilitating efficient function approximation with a minimal number of parameters. To enhance suitability for TinyML deployment, the model is further optimized through post-training quantization techniques, including dynamic range, float-16, and weight-only quantization. Comprehensive experiments were conducted using the UTA-RLDD dataset—a real-world benchmark for driver drowsiness detection—evaluating the model across various input resolutions and quantization schemes. The FastKAN-DDD model achieved a test accuracy of 99.94%, with inference latency as low as 0.04 ms and a total memory footprint of merely 35 KB, rendering it exceptionally well-suited for real-time inference on microcontroller-based systems. Comparative evaluations further confirm that FastKAN surpasses several state-of-the-art TinyML models in terms of accuracy, computational efficiency, and model compactness. Our code’s are publicly available at: https://github.com/sihamess/driver_drowsiness_detection_TinyML .

Study on ice condensation characteristics and deformation laws of two-dimensional orthopermafrost

Predicting coastal erosion susceptibility in Bangladesh under climate scenario via machine learning techniques

Using advanced machine learning methods along with geospatial data and climate estimates, this study found areas in Bangladesh that are likely to experience coastal erosion. Twenty important factors were looked at, such as meteorological, geographical, hydrological, tropological, and land-use variables. The normalized difference vegetation index (NDVI) was found to be the most important factor. An ensemble machine learning technique was used to figure out how susceptible coastal areas are to erosion. Several types of boosting techniques were used, including Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LightGBM), Categorical Boosting (CatBoost), Gradient Boosted Decision Trees (GBDT), and AdaBoost. Random Forest, Decision Tree, Treebag, Bagging, and Averaged Neural Network (avNNet) were also used. The area under the curve (AUC) and receiver operating characteristic (ROC) values were used to check how well the model worked. XGBoost had the best AUC, at 0.95, which means it did a very good job of classifying places that are likely to be washed away by erosion. The study of geography showed that most of the models showed moderate-risk areas, which made up 71.82% to 79.36% of the whole area. Some of the districts that were identified as mostly high-risk were Bhola (19.41%), Cox’s Bazar (26.20%), and Patuakhali (21.47%). A lot of low-risk zones were found in places like Jashore and Narail, on the other hand. Predictions of how likely erosion will be in the future based on different warming models to make Representative Concentration Pathways (RCPs 2.6, 4.5, 6.0, and 8.5) for the years 2040, 2060, 2080, and 2100, we used data from the Coupled Model Intercomparison Project (CMIP5). In line with RCP 8.5, the number of high-risk places is expected to rise to 50% by 2080 and to 40% by 2100. RCP 6.0 had a smooth shift, and in high-risk areas, there were only small rises. RCP 2.6, 4.5, and 6.0 all went up a little. These results show that Bangladesh’s shore is becoming more likely to be worn away by erosion as temperatures rise. They stress how important it is to quickly react, handle coastal areas, and use planning methods that are resilient to climate change.

Short-term dentin-pulp complex repair with four pulp capping materials: a double-blind randomized crossover histological study

Retraction: Genistein Improves 3-NPA-Induced Memory Impairment in Ovariectomized Rats: Impact of Its Antioxidant, Anti-Inflammatory and Acetylcholinesterase Modulatory Properties

Impact of preoperative comorbidities on postoperative complication rates and survival outcome in patients with head and neck cancer undergoing surgical treatment

Seasonal variability of coccolith fluxes in sediment traps of the Perdido and Coatzacoalcos regions in the Southern Gulf of Mexico

We present new results of the coccolith fluxes in the Perdido and Coatzacoalcos areas of the Gulf of Mexico (GoM) and explore the environmental variables that may control them. The deep-water region of the GoM is known for its oligotrophic, nutrient-limited surface waters, which are relatively isolated from eutrophic waters near the coast; however, it is seasonally affected by nutrient-rich plumes of coastal waters that increase export production. Two sediment trap moorings located at a water depth of 1100 m collected settling particles from June 2016 to July 2017. The Perdido trap collected 47 species of coccoliths, and the Coatzacoalcos trap 56 species throughout the study period. Total coccolith fluxes showed a seasonal response in both trap locations, with lower fluxes during spring and summer, associated with highly stratified water column conditions that were evident in the Coatzacoalcos trap, and higher fluxes during late autumn and winter, associated with deepening mixed layer in response to cooling and to the strong “Nortes” winds. The Perdido trap showed higher total coccolith fluxes with an annual average of 3.1 x 10 9  ± 0.9 x 10 9 coccoliths per m -2 d -1 , than the Coatzacoalcos trap of 1.9 x 10 9  ± 1.1 x 10 9 coccoliths m -2 d -1 . The upper photic zone (mainly, Emiliania huxleyi and Gephyrocapsa oceanica ) showed high fluxes throughout the study period in both traps, reflecting the coastal shelf influence. Overall, three species dominated the composition of the coccolith fluxes in both areas: E. huxleyi , G. oceanica , and Florisphaera profunda , reaching 88% in the Perdido and 84% in the Coatzacoalcos trap. These results suggest that the coccolith export production in the Perdido and Coatzacoalcos traps is strongly influenced by the cooling and deepening of the mixed layer depth during autumn and winter, as well as advection processes between the continental shelf and the offshore region, and multifactorial processes such as loop current mesoscale eddies that affect the GoM.

Deep reinforcement learning-based intrusion detection scheme for software-defined networking

Effect of wheat straw biochar addition on canola growth in different soils

Biochar has been demonstrated as a soil amendment to improve soil health and plant yield. The present study aimed at investigating the potential of wheat straw biochar on canola morphology and yield grown in different soils. The influence of biochar on soil physical and chemical properties was also assessed. A completely randomised design pot experiment was carried out in glasshouse where canola was planted in eight different soils with and without biochar treatment. Wheat straw biochar was incorporated in pots at 1% of the total soil weight. Canola was grown for 105 days after which its morphological and yield parameters were evaluated. Analysis of variance confirmed that biochar exerted a significant effect on shoot length, shoot and root dry weights, flower count and 100 seeds weight. Soil texture also affected canola growth and yield parameters with higher clay content in clay loam resulting in less yield compared to others. Biochar also led to improved leaf fresh and dry weight, shoot and root dry weight in loam with lower seeds weight. The seeds weight was the greatest in sandy clay loam, silty clay and silty clay loam which could be ascribed to pH changes, soil texture, decline in soil particle density and improved nutrient availability. Biochar also inflluenced increase in carbon, nitrogen and potassium levels which all helped in maximizing the yield.