Search Results (45,188)

This article presents an overview of selected research focusing on digital real-time simulation (DRTS) in the context of digital twin (DT) realization with the primary aim of enabling the intelligent fault diagnosis (FD) and condition-based monitoring (CBM) of electrical machines. The concept of standalone DTs in conventional multiphysics digital offline simulations (DoSs) is widely utilized during the conceptualization and development phases of electrical machine manufacturing and processing, particularly for virtual testing under both standard and extreme operating conditions, as well as for aging assessments and lifecycle analysis. Recent advancements in data communication and information technologies, including virtual reality, cloud computing, parallel processing, machine learning, big data, and the Internet of Things (IoT), have facilitated the creation of real-time DTs based on physics-based (PHYB), circuit-oriented lumped-parameter (COLP), and data-driven approaches, as well as physics-informed machine learning (PIML), which is a combination of these models. These models are distinguished by their ability to enable real-time bidirectional data exchange with physical electrical machines. This article proposes a predictive-level framework with a particular emphasis on real-time multiphysics modeling to enhance the efficiency of the FD and CBM of electrical machines, which play a crucial role in various industrial applications. Full article

The polymer industry gained increasing importance due to the ability of polymers to replace traditional materials such as wood, glass, and metals in various applications, offering advantages such as high strength-to-weight ratio, corrosion resistance, and ease of fabrication. Among key performance indicators, melt flow rate (MFR) plays a crucial role in determining polymer quality and processability. However, conventional offline laboratory methods for measuring MFR are time-consuming and unsuitable for real-time quality control in industrial settings. To address this challenge, the study proposes a leveraging artificial intelligence with machine learning-based melt flow rate prediction for polymer properties analysis (LAIML-MFRPPPA) model. A dataset of 1044 polymer samples was used, incorporating six input features such as reactor temperature, pressure, hydrogen-to-propylene ratio, and catalyst feed rate, with MFR as the target variable. The input features were normalized using min–max scaling. Two ensemble models—kernel extreme learning machine (KELM) and random vector functional link (RVFL)—were developed and optimized using the pelican optimization algorithm (POA) for improved predictive accuracy. The proposed method outperformed traditional and deep learning models, achieving an R² of 0.965, MAE of 0.09, RMSE of 0.12, and MAPE of 3.4%. A SHAP-based sensitivity analysis was conducted to interpret the influence of input features, confirming the dominance of melt temperature and molecular weight. Overall, the LAIML-MFRPPPA model offers a robust, accurate, and deployable solution for real-time polymer quality monitoring in manufacturing environments. Full article

Background: There is considerable evidence that breast feeding has a beneficial effect on the neurocognition of a child. However, most studies have confined their attention to the Intelligence Quotient (IQ), tending to ignore other aspects of neurodevelopment. Methodology: Here we present the relationship between breast feeding for at least 6 months with 373 neurocognitive outcomes measured from infancy through to late adolescence using data collected in the Avon Longitudinal Study of Parents and Children (ALSPAC). We first examined unadjusted regression associations with breast feeding at age 6 months. Where the unadjusted p-value was < 0.0001 (n = 152 outcomes), we adjusted for social and other factors. Results: This resulted in 42 outcomes with adjusted associations at p < 0.001. Specifically, these included associations with full-scale IQ at ages 8 and 15 years (adjusted mean differences [95% confidence interval (CI)] +4.11 [95% CI 2.83, 5.39] and +5.12 [95% CI 3.57, 6.67] IQ points, respectively, compared to not breastfeeding for 6 months). As well as the components of IQ, the other phenotypes that were strongly related to breast feeding for at least 6 months were measures of academic ability (reading, use of the English language and mathematics). In accordance with the literature, we show that children who are breast fed are more likely to be right-handed. The one association that has not been recorded before concerned aspects of pragmatic speech at 9 years where the children who had been breast fed were shown to perform more appropriately. Conclusions: We conclude that breast feeding for at least 6 months has beneficial effects on a number of neurocognitive outcomes that are likely to play a major part in the offspring’s future life course. We point out, however, the possibility that by using such stringent p-value criteria, other valid associations may have been ignored. Full article

This study presents a comprehensive assessment of long-term nutrient dynamics in the northern South China Sea (NSCS), a region that hosts the world’s largest marine ranching cluster and serves as a cornerstone of China’s “Blue Granary” initiative. By integrating multi-sensor satellite remote sensing data (Landsat and Sentinel-2, 2002–2024) with in situ observations, we developed robust retrieval algorithms for total nitrogen (TN) and total phosphorus (TP), achieving high accuracy (TN: R² = 0.82, RMSE = 0.09 mg/L; TP: R² = 0.94, RMSE = 0.0071 mg/L; n = 63). Results showed that TP concentrations increased significantly faster than TN, leading to a decline in the TN:TP ratio (NP) from 19.2 to 13.2 since 2013. This shift indicates a transition from phosphorus (P) limitation to nitrogen (N) limitation, driven by warming sea surface temperatures (SST) (about 1.16 °C increase) and increased anthropogenic phosphorus inputs (about 27.84% increase). The satellite-based framework offers a scalable, cost-effective solution for monitoring aquaculture water quality. When integrated with artificial intelligence (AI) technologies, these near-real-time nutrient anomaly data can support early warning of harmful algal blooms (HABs), offering key insights for ecosystem-based management and climate adaptation. Overall, our findings highlight the utility of remote sensing in advancing sustainable marine resource governance amid environmental change. Full article

The volume and diversity of digital information have led to a growing reliance on Machine Learning (ML) techniques, such as Natural Language Processing (NLP), for interpreting and accessing appropriate data. While vector and graph embeddings represent data for similarity tasks, current state-of-the-art pipelines lack guaranteed explainability, failing to accurately determine similarity for given full texts. These considerations can also be applied to classifiers exploiting generative language models with logical prompts, which fail to correctly distinguish between logical implication, indifference, and inconsistency, despite being explicitly trained to recognise the first two classes. We present a novel pipeline designed for hybrid explainability to address this. Our methodology combines graphs and logic to produce First-Order Logic (FOL) representations, creating machine- and human-readable representations through Montague Grammar (MG). The preliminary results indicate the effectiveness of this approach in accurately capturing full text similarity. To the best of our knowledge, this is the first approach to differentiate between implication, inconsistency, and indifference for text classification tasks. To address the limitations of existing approaches, we use three self-contained datasets annotated for the former classification task to determine the suitability of these approaches in capturing sentence structure equivalence, logical connectives, and spatiotemporal reasoning. We also use these data to compare the proposed method with language models pre-trained for detecting sentence entailment. The results show that the proposed method outperforms state-of-the-art models, indicating that natural language understanding cannot be easily generalised by training over extensive document corpora. This work offers a step toward more transparent and reliable Information Retrieval (IR) from extensive textual data. Full article

The low quality of mechanized tea harvesting in China’s hilly plantations, often caused by irregular canopy morphology, necessitates improved technology. This study addresses this issue by proposing a contact-based profiling mechanism and a corresponding control method for tea cutting platforms. This cutting platform mainly consists of a canopy profiling mechanism, a tea harvesting unit, a lifting actuator, and a control system, containing a mathematical model correlating the tea canopy pose with sensor signals. Following a theoretical analysis of key components of the profiling device, we determined their structural parameters. Subsequently, a profiling control strategy was formulated, and an automatic control system for the profiling cutting platform was developed. Finally, a prototype was constructed and subjected to experimental validation to assess the dynamic characteristics of its pose adjustment and its profiling-based harvesting performance. The results of this experiment illustrate that after implementing the profiling system, the proportion of time the cutting blade remained in an optimal cutting position increased from 26.5% to 95.0%, an improvement of 68.5%, demonstrating that the system successfully achieves its design objective of the adaptive profiling apparatus in response to variation in canopy morphology. In addition, the integrity rate of harvested tea leaves increased from 50.7% without profiling to 74.6% with profiling, an improvement of 47.1%, which indicates the good performance of this profiling cutting platform. Therefore, this research provides a valuable reference for the design of intelligent tea harvesting machinery for the hilly tea plantations in China. Full article

To address urban flooding challenges exacerbated by climate change and urbanization, this study develops an integrated assessment framework combining the analytic hierarchy process (AHP), entropy weight method, and cloud model to quantify urban flood resilience. Resilience is deconstructed into resistance, adaptability, and recovery and evaluated through 24 indicators spanning water resources, socio-economic systems, and ecological systems. Subjective (AHP) and objective (entropy) weights are optimized via minimum information entropy, with the cloud model enabling qualitative–quantitative resilience mapping. Analyzing 2014–2024 data from 27 Chinese sponge city pilots, the results show resilience improved from “poor to average” to “good to average”, with a 2.89% annual growth rate. Megacities like Beijing and Shanghai excel in resistance and recovery due to infrastructure and economic strengths, while cities like Sanya enhance resilience via ecological restoration. Key drivers include water allocation (27.38%), economic system (18.41%), and social system (17.94%), with critical indicators being population density, secondary industry GDP ratio, and sewage treatment rate. Recommendations emphasize upgrading rainwater storage, intelligent monitoring networks, and resilience-oriented planning. The model offers a scientific foundation for urban disaster risk management, supporting sustainable development. This approach enables systematic improvements in adaptive capacity and recovery potential, providing actionable insights for global flood-resilient urban planning. Full article

Background: Recent studies have shown that gut microbiota have important roles in different human diseases. There has been an ever-increasing application of high-throughput technologies for the characterization of microbial ecosystems. This led to an explosion of various molecular profiling data, and the analysis of such data has shown that machine-learning algorithms have been useful in identifying key molecular signatures. Results: In this review, we first analyze how dysbiosis of the intestinal microbiota relates to human disease and how possible modulation of the gut microbial ecosystem may be used for disease intervention. Further, we introduce categories and the workflows of different machine-learning approaches and how they perform integrative analysis of multi-omics data. Last, we review advances of machine learning in gut microbiome applications and discuss challenges it faces. Conclusions: We conclude that machine learning is indeed well suited for analyzing gut microbiome and that these approaches are beneficial for developing gut microbe-targeted therapies, helping in achieving personalized and precision medicine. Full article

AI-driven agricultural automation increasingly demands efficient data generation methods for training deep learning models in autonomous robotic systems. Traditional bounding box annotation methods for agricultural objects present significant challenges including subjective boundary determination, inconsistent labeling across annotators, and physical strain from extensive mouse movements required for elongated objects. This study proposes a novel base-width standardized annotation method that utilizes the base width of a vine trunk and a support post as a reference parameter for automated bounding box generation. The method requires annotators to specify only the left and right endpoints of object bases, from which the system automatically generates standardized bounding boxes with predefined aspect ratios. Performance assessment utilized Precision, Recall, F1-score, and Average Precision metrics across vine trunks and support posts. The study reveals that vertically elongated rectangular bounding boxes outperform square configurations for agricultural object detection. The proposed method is expected to reduce time consumption from subjective boundary determination and minimize physical strain during bounding box annotation for AI-based autonomous navigation models in agricultural environments. This will ultimately enhance dataset consistency and improve the efficiency of artificial intelligence learning. Full article

In multi-pass welding processes, achieving a uniform and smooth weld surface is crucial for mechanical performance and dimensional accuracy. However, the complex nonlinear relationships between welding parameters and weld bead geometry present significant challenges for traditional optimization methods. This study proposes an intelligent prediction and optimization framework that integrates a backpropagation (BP) neural network with an improved hill-climbing algorithm to enhance weld surface smoothness in automated multi-bead overlay welding. Experimental data collected under varying arc voltages, wire feed rates, and welding speeds were used to train the neural network. The improved hill-climbing algorithm adaptively adjusts weights and biases in the BP model to overcome issues of local minima and slow convergence. Comparative results demonstrate that the proposed method significantly outperforms conventional BP approaches in terms of prediction accuracy and convergence efficiency. Furthermore, optimal welding parameters identified by the model yield smoother weld surfaces, reducing the need for post-processing. This work provides a novel solution for intelligent control and real-time optimization in advanced welding systems. Full article

The development of medical question-answering systems (QASs) encounters substantial challenges due to the complexities of medical terminologies and the lack of reliable datasets. The shortcomings of traditional artificial intelligence (AI) driven QAS lead to generating outcomes with a higher rate of hallucinations. In order to overcome these limitations, there is a demand for a reliable QAS to understand and process complex medical queries and validate the quality and relevance of its outcomes. In this study, we develop a medical QAS by integrating SPARQL, retrieval-augmented generation (RAG), and generative pre-trained transformer (GPT)-Neo models. Using this strategy, we generate a synthetic dataset to train and validate the proposed model, addressing the limitations of the existing QASs. The proposed QAS was generalized on the MEDQA dataset. The findings revealed that the model achieves a generalization accuracy of 87.26% with a minimal hallucination rate of 0.16. The model outperformed the existing models by leveraging deep learning techniques to handle complex medical queries. The dynamic responsive capability of the proposed model enables it to maintain the accuracy of medical information in a rapidly evolving healthcare environment. Employing advanced hallucination reduction and query refinement techniques can fine-tune the model’s performance. Full article

The present study examines the application of interactive software models for training on the topic of “Cyclic Codes” in order to increase the success rate and engagement of students in technical disciplines. Two models have been developed—based on the polynomial method and the LFSR approach—through an established methodology adapted to the specifics of the content. A pedagogical experiment with a control and experimental group was conducted, and ANCOVA analysis was applied to eliminate the influence of initial grades. The results show a statistically significant advantage of the experimental group in terms of final grades, which confirms the positive effect of using interactive models. The analysis of engagement and solved tasks reveals that the polynomial model is used more widely and contributes to the systematic application of algorithmic steps, while the LFSR model has an illustrative nature and supports intuitive understanding through visualization of processes. The feedback received from students shows high satisfaction and points to improvements in the interface and functionality. In conclusion, interactive models prove their effectiveness as complementary tools for learning complex technical concepts, and prospects for future development through the integration of artificial intelligence and enhanced gamification are also discussed. Full article

In an era of information overload, artificial intelligence plays a pivotal role in supporting everyday decision-making. This paper introduces EverydAI, a virtual AI-powered assistant designed to help users make informed decisions across various daily domains such as cooking, fashion, and fitness. By integrating advanced natural language processing, object detection, augmented reality, contextual understanding, digital 3D avatar models, web scraping, and image generation, EverydAI delivers personalized recommendations and insights tailored to individual needs. The proposed framework addresses challenges related to decision fatigue and information overload by combining real-time object detection and web scraping to enhance the relevance and reliability of its suggestions. EverydAI is evaluated through a two-phase survey, each one involving 30 participants with diverse demographic backgrounds. Results indicate that on average, 92.7% of users agreed or strongly agreed with statements reflecting the system’s usefulness, ease of use, and overall performance, indicating a high level of acceptance and perceived effectiveness. Additionally, EverydAI received an average user satisfaction score of 4.53 out of 5, underscoring its effectiveness in supporting users’ daily routines. Full article

The increasing complexity and scale of service-oriented architectures in cloud computing have heightened the demand for intelligent, decentralized, and adaptive service composition techniques. This study proposes an advanced framework that integrates a Multi-Agent System (MAS) with a novel hybrid metaheuristic optimization method, the Integrated Particle-Ant Algorithm (IPAA), to achieve efficient, scalable, and Quality of Service (QoS)-aware service composition. The IPAA dynamically combines the global search capabilities of Particle Swarm Optimization (PSO) with the local exploitation strength of Ant Colony Optimization (ACO), thereby enhancing convergence speed and solution quality. The proposed system is structured into three logical layers—agent, optimization, and infrastructure—facilitating autonomous decision-making, distributed coordination, and runtime adaptability. Extensive simulations using a synthetic cloud service dataset demonstrate that the proposed approach significantly outperforms traditional optimization methods, including standalone PSO, ACO, and random composition strategies, across key metrics such as utility score, execution time, and scalability. Moreover, the framework enables real-time monitoring and automatic re-optimization in response to QoS degradation or Service-Level Agreement (SLA) violations. Through decentralized negotiation and minimal communication overhead, agents exhibit high resilience and flexibility under dynamic service availability. These results collectively suggest that the proposed IPAA-based framework provides a robust, intelligent, and scalable solution for service composition in complex cloud computing environments. Full article

Offensive language and hate speech have a detrimental effect on victims and have become a significant problem on social media platforms. Recent research has developed automated techniques for detecting Arabic offensive language and hate speech but remains limited, and further research is required compared to the research on high-resource languages such as English due to limited resources, annotated corpora, and morphological analysis. Most social media users who use profanities attempt to modify their text while maintaining the same meaning, thereby deceiving detection methods that forbid offending phrases. Therefore, this study proposes an adversarially robust multitask learning framework for detection of Arabic offensive and hate speech. For this purpose, this study used the OSACT2020 dataset, augmented with additional posts collected from the X social media platform. To improve contextual understanding, classification models based on various configurations were constructed using four pre-trained Arabic language models integrated with various sequential layers that were trained and evaluated in three different settings: single-task learning with the original dataset, single-task learning with the augmented dataset, and multitask learning with the augmented dataset. The multitask MARBERTv2+BiGRU model achieved the best results, with an 88% macro-F1 for hate speech and 93% for offensive language on clean data. To improve the model’s robustness, adversarial samples were generated using attacks on both the character and sentence levels. These attacks subtly change the text to mislead the model while maintaining the overall appearance and meaning. The clean model’s performance dropped significantly under attack, especially for hate speech, to a 74% macro-F1; however, adversarial training, which re-trains the model using both clean and adversarial data, improved the results to a 78% macro-F1 for hate speech. Further improvements were achieved with input transformation techniques, boosting the macro-F1 to 81%. Notably, the adversarially trained model maintained high performance on clean data, demonstrating both robustness and generalization. Full article