Learning Capability Research Articles

Effects of a Steno Diabetes Dialogue Card-Based Intervention on Self-Perceived Health, Health Literacy, and Glycemic Control in Older Adults With Type 2 Diabetes Mellitus Living in the Community

The process of aging is associated with the deterioration of normal body functions as well as lower health awareness due to a reduced ability to acquire and understand health-related information. The subjects of this study were older adults with diabetes mellitus living in community settings. Visual-learning-based Steno diabetes dialogue cards were used to strengthen the learning and knowledge absorption capabilities of the subjects to improve diabetes health knowledge and increase compliance with blood sugar control protocols to achieve blood sugar control goals and delay / reduce the severity of complications. This study was designed to assess the comparative effects of Steno diabetes dialogue cards and conventional health interventions on self-perceived health, health literacy, glycated hemoglobin (HbA1c) level, and fasting blood glucose level in older adults with diabetes. An experimental study was conducted in an outpatient clinic of the department of metabolism in a hospital in northern Taiwan. The subjects were randomized into the experimental group (receiving the Steno diabetes dialogue cards intervention) and control group (receiving conventional health education). Individual health education interventions of 15-20 min each were conducted once a month for 3 consecutive months in both groups. There were 51 subjects in the experimental group and 47 in the control group, with an attrition rate of 10.91%. The changes in the experimental group and the control group before the intervention and three months after the intervention were analyzed, with significant between-group differences found in health literacy and self-perceived health (p < .001). The experimental group's three-month post-test scores were both greater than the pre-test. Significantly, there were significant, positive differences between pre- and post-test values for self-perceived health (p = .005), health literacy (p < .001), glycated hemoglobin (p < .001) and fasting blood glucose (p = .002). Moreover, the improvements were greater in the experimental than the control group. The individual health education interventions improved glycemic control efficacy in all of the subjects. However, the experimental group showed more significant improvements in all measures. Therefore, Steno diabetes dialogue cards offer a clear benefit in enhancing older adults' knowledge regarding self-glycemic control and improving compliance with disease behaviors.

The impact of artificial intelligence in the global hospitality industry by 2030

Interest in the impact of AI within the hospitality industry by the year 2030 is very high; therefore, this paper will discuss the latest applications and trends that are likely to take over in revolutionizing the whole landscape. It effectively brings into relief the transformative capability of AI technologies-machine learning, natural language processing, and robotics-that sublimely enhance operational efficiencies and attend to the ever-growing need for personalized guest experiences in a profoundly captivating manner. The paper thereby identifies, with full comprehensiveness, a range of applications of AI on hospitality enterprise segments via smart room technologies that perfectly merge state-of-the-art developments to offer an unprecedented level of comfort; automated customer service systems that seamlessly streamline the consumer interaction; and data analytics for revenue management by AI systems to outline unparalleled revenue optimization and organizational success. It goes into detail on what the future of AI in hospitality holds: a tremendous explosion automating tasks to take some of the load off from manual work and increasing productivity while fostering smarter data analytics that will, in turn, enable businesses to make data-driven decisions with the highest degree of precision and accuracy. This foresighted exploration further embraces the idea of seamless integration with Internet of Things devices, therefore making a future possible where smart devices would smoothly cooperate and communicate to create an unparalleled guest experience. The complex challenges and ethical considerations that arise regarding the implementation of AI within the hospitality industry are also explored with minute detail. The act recognizes the very critical aspect of data privacy and gives great emphasis on how important it is to safeguard the personal information of the guests by leveraging its AI capabilities. It goes further by delving into the sensitive issue of job displacement, aware of the potential impact of integration with AI on the workforce. It does so in a manner that aptly demonstrates the essence of achieving a delicate balance between the wonderful advantages gained from AI and the urgent need to observe morality. Lastly, the strategic recommendations to be provided within this paper, targeted at industry stakeholders themselves, really underscore how important it is to consider proactive AI strategies that not only realize the full transformative value of these technologies but also seek ethical conduct. This pioneering research doggedly insists that AI will indeed form an integral part of the reshaping of the hospitality landscape, which emphasizes the critical need for continuous innovation and unrelenting adaptability in today's fast-changing technological environment. In other words, this research plunges into the world of artificial intelligence in the global hospitality industry and outlines its exceptional potential to reform every aspect of the industry as we know it. The agreement unequivocally states that AI should be embraced as a driving force for innovation and progress while ensuring that ethical considerations are placed first and best practices come to the front in the transformation of industries. But as that future comes into view, it is a timely reminder that monumental shift awaiting the hospitality landscape from every corner demands the industry stakeholders take bold moves in reaching out to clasp this technological revolution with open arms and unyielding dedication to remarkable guest experiences.

Bridging the digital divide with cloud-powered applications

Cloud-based Java solutions are revolutionizing how small and medium enterprises access sophisticated technology capabilities. This technological democratization bridges the digital divide between well-resourced organizations and smaller entities by providing scalable, cost-effective alternatives to traditional enterprise software deployments. The transformation encompasses platform independence, enhanced security measures, and optimized resource utilization through modern architectural patterns. Through serverless computing and microservices architectures, organizations can now leverage enterprise-grade capabilities while maintaining flexibility and cost efficiency. The impact extends beyond operational efficiencies to foster innovation, enable strategic growth, and create new opportunities across various business sectors. Small businesses and non-profits particularly benefit from reduced barriers to entry, improved competitive capabilities, and access to enterprise-grade tools that were previously beyond their reach. The integration of artificial intelligence and machine learning capabilities, combined with edge computing solutions, further enhances the value proposition of cloud adoption. These advancements enable organizations to focus on core competencies while automating routine tasks and improving decision-making processes. The democratization of technology through cloud solutions also creates significant socio-economic benefits, increasing digital literacy in underserved communities and generating new employment opportunities in the technology sector. As cloud technologies mature, their role in fostering digital equality and enabling business transformation becomes increasingly vital for sustainable economic growth and innovation across all business segments.

Abdominal LIPUS Stimulation Prevents Cognitive Decline in Hind Limb Unloaded Mice by Regulating Gut Microbiota.

Weightlessness usually causes disruption of the gut microbiota and impairs cognitive function. There is a close connection between gut microbiota and neurological diseases. Low-intensity pulsed ultrasound (LIPUS) has a beneficial effect on reducing intestinal inflammation. So we wondered if abdominal LIPUS stimulation can have a positive impact on weightlessness induced cognitive decline by reducing intestinal dysfunction. The findings revealed that the hind limb unloaded mice exhibited evident disruption in intestinal structure and gut microbial homeostasis, along with impairment in their learning and memory capabilities. However, 4-week abdominal LIPUS treatment improved intestinal function in hind limb unloaded mice, characterized by upregulation of tight junction proteins ZO-1 and Occludin expression in the colon, increased diversity and abundance of intestinal microbiota, decreased serum lipopolysaccharide (LPS), and increased short chain fatty acids in colon contents. The hind limb unloaded mice treated with LIPUS exhibited heightened activity levels, improved exploratory tendencies, and significantly enhanced learning and memory faculties, and elevated expression of neuroadaptation-related proteins such as PSD95, GAP43, P-CREB, BDNF, and its receptor TRKB in the hippocampus. Furthermore, the hind limb unloaded mice receiving fecal transplants from the mice whose abdomens were irradiated with LIPUS displayed enhanced cognitive abilities and improved intestinal structure, akin to the outcomes observed in hind limb unloaded mice who received LIPUS abdominal treatment directly. The above results indicate that LIPUS enhances intestinal structure and microbiota, which helps alleviate cognitive impairment caused by weightlessness. LIPUS could be a potential strategy to simultaneously improve gut dysfunction and cognitive decline in astronauts or bedridden patients.

Automated design of state transition rules in ant colony optimization by genetic programming: a comprehensive investigation

The automated design of Ant Colony Optimization (ACO) algorithms has become increasingly significant, particularly in addressing complex combinatorial optimization problems. Although existing methods have achieved some success, they still face limitations, particularly the high dependency on expert knowledge, pre-solved data, and challenges in interpretability. Genetic Programming (GP), as a proven technology, has shown potential in optimizing the automated design state transition rules of ACO. However, existing research on GP-ACO is insufficient, particularly in terms of experimental validation and systematic evaluation. To address these issues, this study conducts comprehensive experiments to explore several key questions: the generality of GP-ACO on homogeneously distributed maps, the impact of different ACO variants on the learning capabilities of GP-ACO, the effect of 2-opt local search on the learning capabilities of GP-ACO, the enhancement of learning capabilities through the addition of more global information, and the interpretability of GP-ACO. The findings indicate that GP-ACO exhibits robust generality; variations among ACO variants have minimal impact on learning performance; 2-opt local search can somewhat diminish the performance of GP-ACO in the Max–Min Ant System; additional global information can significantly enhance the learning capabilities of GP-ACO; and GP-ACO has good interpretability.

DPRA: a dual pooling attention network for point cloud classification and segmentation

Abstract Point cloud data, widely used in fields such as autonomous driving and robotic navigation, involves classification and segmentation tasks. The extraction of local and global features has become a major research focus. The paper proposes two modules: the Dual Pooling Attention model (DP-Attention) and the Residual Attention Module model (RA-MLP). DP-Attention utilizes max pooling and average pooling to compute attention, extracting information between points as well as between features to enhance local feature extraction. RA-MLP integrates self-attention and residual connections to improve global feature extraction. These modules are combined to construct the DPRA network, which is tailored for point cloud classification and segmentation tasks. The DPRA network architecture is based on the encoder-decoder structure of U-Net, using DP-Attention and RA-MLP in the encoder, and only RA-MLP in the decoder. Experimental results on three datasets demonstrate that the DPRA network achieves outstanding performance in the synthetic ModelNet40 classification experiment, with a mean class accuracy of 91.6%. It also achieves the highest mean class accuracy (85.3%) and overall accuracy (86.1%) in the real-world ScanObjectNN classification experiment. Additionally, it attains the highest mean Intersection over Union (mIoU) of 85.2% in the synthetic ShapeNet segmentation experiment. These results indicate that DPRA is applicable to various tasks, demonstrating strong generalization, robustness, and multi-task learning capabilities.&amp;#xD;

The Contribution of R&amp;D İnvestments to Technological Learning Capability: Evidence from Manufacturing İndustry Sectors of the Turkish Economy

Learning-by-searching is the process of experience in the emergence of new high-value-added products with the new knowledge and skills that an enterprise achieves through the network system it establishes with its own R&amp;D unit, other enterprises, universities, and other information sources. The most important factor that contributes to learning-by-searching is undoubtedly the investments made in research and development in economic sectors. A review of the literature on the subject reveals that R&amp;D expenditures are only used as the second independent variable in linear learning curve models. For this reason, in the existing applied studies, only a fixed representative learning rate, which is the average of the learning rates in the period in question, is determined. In this study, a two-factor dynamic learning curve model is used to measure the cost-reducing effect of R&amp;D expenditures. Thus, in addition to learning-by-doing ratios, the evolution of learning-by-searching ratios over time is also taken into account. The findings of the study support the view in the literature that the learning-by-doing rates in the one-factor dynamic learning model are biased. In addition, in the two-factor dynamic learning curve model, it was also found that in periods when learning-by-doing loses its effect, learning-by-searching increases its effect.

Deep neural network enhanced modeling and adaptive control of a malfunctional spacecraft under unknown accessory breakage

This manuscript presents a sophisticated deep neural networks (DNNs)-driven adaptive control paradigm for concurrently regulating the attitude and suppressing structural oscillations of a flexible spacecraft in a fully three-dimensional domain. By leveraging Hamilton’s principle, the spacecraft’s motion is formulated as an infinite-dimensional dynamic model described by partial differential equations, capturing the subtle interactions between rigid-body rotational maneuvers and flexible panel deformations. In contrast to traditional schemes, the proposed control methodology integrates a DNNs module to compensate for uncertain actuator anomalies and external input disturbances in real time, thereby ensuring fault tolerance under arbitrary, potentially unbounded actuator malfunctions. A rigorously constructed Lyapunov-based stability analysis corroborates that the system’s energy, angular rates, and transverse deflections remain uniformly bounded and asymptotically converge to zero, even in the face of multiple actuator failures. This theoretical guarantee stems from the synergistic interplay between the network’s representational power and the adaptive control law’s robust learning capabilities. Extensive computational experiments demonstrate the efficacy of the developed framework in orchestrating high-precision attitude stabilization while simultaneously mitigating detrimental vibrations, showcasing the superior performance and resiliency of the proposed DNNs-infused control architecture.

Anti-interference Technology of Intelligent Communication Based on Improved GA and GWO

Chaotic mapping enhances anti-interference in frequency hopping communication by optimizing genetic algorithm population initialization. An intelligent decision engine model employs optimized grey wolf parameters and individual exchange mechanisms, enhancing grey wolf optimization convergence speed for constructing frequency hopping patterns. Experimental data reveals the improved genetic algorithm's efficiency with average run times of 0.312s and 0.057s for adaptive and enhanced versions, respectively. Achieving optimal solution convergence rates of 99.3% and 100%, the enhanced algorithm boosts decision-making accuracy and efficiency. The intelligent decision engine exhibits strong anti-interference capabilities, suitable for −2dB to 10dB signal-to-interference ratios with error rates below 10−6. The improved grey wolf optimization algorithm surpasses traditional approaches, yielding a 9.5% profit increment with a total value of 2310. This technology showcases adept learning and anti-interference capabilities, offering innovative solutions for communication systems and anti-interference technology advancements.

A novel framework for online decision-making and feedback optimization of complex products process parameter based on edge-cloud collaboration

Background Intelligent manufacturing is perceived as a manufacturing mode with powerful learning and cognitive capabilities empowered by information technologies such as the internet of things, edge computing, and cloud computing. The mode can be used to address the problems of low intelligence and poor timeliness of traditional process planning. Methods The framework includes the multi-objective process planning method based on real-time data, and the process closed-loop optimization mechanism of “cloud-based theoretical process planning plus edge MEC side online simulation verification and real-time feedback adjustment”, which realizes online process planning and iterative optimization in mass customization. Results The feasibility of the online analysis method for thin-walled part milling deformation is verified by taking the finishing process of aerospace thin-walled parts as an example. The experimental results show that the simulation time on the single analysis step is reduced from 6s to 1s, and the accuracy rate is 86.9%. Conclusions A new intelligent process planning theoretical framework integrating with online process planning and autonomous collaborative control, namely, digital twin and multi-access edge computing process planning (DT-MEC-PP) is proposed in this paper.

Empowering PET imaging reporting with retrieval-augmented large language models and reading reports database: a pilot single center study.

The potential of Large Language Models (LLMs) in enhancing a variety of natural language tasks in clinical fields includes medical imaging reporting. This pilot study examines the efficacy of a retrieval-augmented generation (RAG) LLM system considering zero-shot learning capability of LLMs, integrated with a comprehensive database of PET reading reports, in improving reference to prior reports and decision making. We developed a custom LLM framework with retrieval capabilities, leveraging a database of over 10 years of PET imaging reports from a single center. The system uses vector space embedding to facilitate similarity-based retrieval. Queries prompt the system to generate context-based answers and identify similar cases or differential diagnoses. From routine clinical PET readings, experienced nuclear medicine physicians evaluated the performance of system in terms of the relevance of queried similar cases and the appropriateness score of suggested potential diagnoses. The system efficiently organized embedded vectors from PET reports, showing that imaging reports were accurately clustered within the embedded vector space according to the diagnosis or PET study type. Based on this system, a proof-of-concept chatbot was developed and showed the framework's potential in referencing reports of previous similar cases and identifying exemplary cases for various purposes. From routine clinical PET readings, 84.1% of the cases retrieved relevant similar cases, as agreed upon by all three readers. Using the RAG system, the appropriateness score of the suggested potential diagnoses was significantly better than that of the LLM without RAG. Additionally, it demonstrated the capability to offer differential diagnoses, leveraging the vast database to enhance the completeness and precision of generated reports. The integration of RAG LLM with a large database of PET imaging reports suggests the potential to support clinical practice of nuclear medicine imaging reading by various tasks of AI including finding similar cases and deriving potential diagnoses from them. This study underscores the potential of advanced AI tools in transforming medical imaging reporting practices.

Transformational Versus Transactional Leadership: Implications for SME Management

Leadership styles play a crucial role in shaping the performance and outcomes of Small and Medium-sized Enterprises (SMEs). This paper discusses two prominent leadership styles, transactional and transformational leadership, on various organizational aspects within the SME context. Transactional leadership, characterized by structured exchanges based on rewards and penalties, is found to positively influence employee performance, operational efficacy, and strategic success in diverse settings. While transactional leadership is noted for its direct impact on organizational processes, its relationship with innovation and learning capabilities is nuanced. On the other hand, transformational leadership, focusing on inspiration and motivation through a shared vision, has a significant positive influence on innovation, employee performance, and retention in SMEs. Studies highlight how transformational leadership fosters a culture of trust, innovation, and continuous improvement, impacting areas such as knowledge sharing, organizational citizenship behavior, and sustainability practices. The findings stress the critical role of both leadership styles in driving success within SMEs, emphasizing the need to consider specific practices, sectoral contexts, and organizational environments for optimal impact.

Optimized Bi-LSTM Model for Short-Term Predicting of Ship State with Definitions of Surf-Riding and Broaching

This paper introduces a hybrid prediction method that combines the Bi-LSTM neural network with definitions of surf-riding, wave-blocking and broaching to enhance the safety and stability of ship navigation. The hybrid method can accurately predict ships’ attitude motions and states by recognizing ship states and encoding them into one-hot representations. The Bi-LSTM model’s bidirectional learning capability captures significant temporal dependencies, enabling precise and timely predictions of complex maritime events across various conditions. Additionally, the direct output approach of state features improves prediction accuracy by eliminating intermediate steps, allowing for the better anticipation of and response to critical events. Validated with ship navigation data from autopilot simulations in wave conditions, the hybrid method outperforms conventional methods based on LSTM and Bi-LSTM models, demonstrating strong generalization capabilities and significantly contributing to safer and more stable ship navigation.

ADA-NAF: Semi-Supervised Anomaly Detection Based on the Neural Attention Forest

In this study, we present a novel model called ADA-NAF (Anomaly Detection Autoencoder with the Neural Attention Forest) for semi-supervised anomaly detection that uniquely integrates the Neural Attention Forest (NAF) architecture which has been developed to combine a random forest classifier with a neural network computing attention weights to aggregate decision tree predictions. The key idea behind ADA-NAF is the incorporation of NAF into an autoencoder structure, where it implements functions of a compressor as well as a reconstructor of input vectors. Our approach introduces several technical advances. First, a proposed end-to-end training methodology over normal data minimizes the reconstruction errors while learning and optimizing neural attention weights to focus on hidden features. Second, a novel encoding mechanism leverages NAF’s hierarchical structure to capture complex data patterns. Third, an adaptive anomaly scoring framework combines the reconstruction errors with the attention-based feature importance. Through extensive experimentation across diverse datasets, ADA-NAF demonstrates superior performance compared to state-of-the-art methods. The model shows particular strength in handling high-dimensional data and capturing subtle anomalies that traditional methods often do not detect. Our results validate the ADA-NAF’s effectiveness and versatility as a robust solution for real-world anomaly detection challenges with promising applications in cybersecurity, industrial monitoring, and healthcare diagnostics. This work advances the field by introducing a novel architecture that combines the interpretability of attention mechanisms with the powerful feature learning capabilities of autoencoders.

A Novel session-based recommendation system using capsule graph neural network.

Session-based recommendation systems (SBRS) are essential for enhancing the customer experience, improving sales and loyalty, and providing the possibility to discover products in dynamic and real-world scenarios without needing user history. Despite their importance, traditional or even current SBRS algorithms face limitations, notably the inability to capture complex item transitions within each session and the disregard for general patterns that can be derived from multiple sessions. This paper proposes a novel SBRS model, called Capsule GraphSAGE for Session-Based Recommendation (CapsGSR), that marries GraphSAGE's scalability and inductive learning capabilities with the Capsules network's abstraction levels by generating multiple integrations for each node from different perspectives. Consequently, CapsGSR addresses challenges that may hinder the optimal item representations and captures transitions' complex nature, mitigating the loss of crucial information. Our system significantly outperforms baseline models on benchmark datasets, with improvements of 8.44% in HR@20 and 4.66% in MRR@20 , indicating its effectiveness in delivering precise and relevant recommendations.

Exploring the anticancer activities of Sulfur and magnesium oxide through integration of deep learning and fuzzy rough set analyses based on the features of Vidarabine alkaloid

Drug discovery and development is a challenging and time-consuming process. Laboratory experiments conducted on Vidarabine showed IC50 6.97 µg∕mL, 25.78 µg∕mL, and ˃ 100 µg∕mL against non-small Lung cancer (A-549), Human Melanoma (A-375), and Human epidermoid Skin carcinoma (skin/epidermis) (A-431) respectively. To address these challenges, this paper presents an Artificial Intelligence (AI) model that combines the capabilities of Deep Learning (DL) to identify potential new drug candidates, Fuzzy Rough Set (FRS) theory to determine the most important chemical compound features, Explainable Artificial Intelligence (XAI) to explain the features’ importance in the last layer, and medicinal chemistry to rediscover anticancer drugs based on natural products like Vidarabine. The proposed model aims to identify potential new drug candidates. By analyzing the results from laboratory experiments on Vidarabine, the model identifies Sulfur and magnesium oxide (MgO) as new potential anticancer agents. The proposed model selected Sulfur and MgO based on Interpreting their promising features, and further laboratory experiments were conducted to validate the model’s predictions. The results demonstrated that, while Vidarabine was inactive against the A-431 cell line (IC50 ˃ 100 µg∕mL), Sulfur and MgO exhibited significant anticancer activity (IC50 4.55 and 17.29 µg/ml respectively). Sulfur displayed strong activity against A-549 and A-375 cell lines (IC50 3.06 and 1.86 µg/ml respectively) better than Vidarabine (IC50 6.97 and 25.78 µg/ml respectively). However, MgO showed weaker activity against these two cell lines. This paper emphasizes the importance of uncovering hidden chemical features that may not be discernible without the assistance of AI. This highlights the ability of AI to discover novel compounds with therapeutic potential, which can significantly impact the field of drug discovery. The promising anticancer activity exhibited by Sulfur and MgO warrants further preclinical studies.

Integrating Machine Learning for Predictive Maintenance on Resource-Constrained PLCs: A Feasibility Study.

This study investigates the potential of deploying a neural network model on an advanced programmable logic controller (PLC), specifically the Finder Opta™, for real-time inference within the predictive maintenance framework. In the context of Industry 4.0, edge computing aims to process data directly on local devices rather than relying on a cloud infrastructure. This approach minimizes latency, enhances data security, and reduces the bandwidth required for data transmission, making it ideal for industrial applications that demand immediate response times. Despite the limited memory and processing power inherent to many edge devices, this proof-of-concept demonstrates the suitability of the Finder Opta™ for such applications. Using acoustic data, a convolutional neural network (CNN) is deployed to infer the rotational speed of a mechanical test bench. The findings underscore the potential of the Finder Opta™ to support scalable and efficient predictive maintenance solutions, laying the groundwork for future research in real-time anomaly detection. By enabling machine learning capabilities on compact, resource-constrained hardware, this approach promises a cost-effective, adaptable solution for diverse industrial environments.

Simulating fish autonomous swimming behaviours using deep reinforcement learning based on Kolmogorov–Arnold Networks

The study of fish swimming behaviours and locomotion mechanisms holds significant scientific and engineering value. With the rapid advancements in artificial intelligence, a new method combining deep reinforcement learning (DRL) with computational fluid dynamics has emerged and been applied to simulate the fish's adaptive swimming behaviour, where the complex fish behaviour is decoupled to focus on the fish's response to the hydrodynamic field, and the simulation is driven by reward-based objectives to model the fish's swimming behaviour. However, the scale of this cross-disciplinary method is directly affected by the efficiency of the DRL model. To promote it to more general application scenarios, there is a pressing need for further research on more efficient and economical network architectures to address the challenge of approximating state-value function in high-dimensional, dynamic, and uncertain environments. Building upon a previously proposed computational platform for the simulation of fish autonomous swimming behaviour, we integrated Kolmogorov-Arnold Networks(KANs) and tested their performance in point-to-point swimming and Kármán gait swimming environments. Experimental results demonstrated that, compared to long short-term memory Networks(LSTMs) and multilayer perceptron networks(MLPs), the introduction of KANs significantly enhanced the perception and decision-making abilities of the intelligent fish in complex fluid environments. With a smaller network scale, in the point-to-point swimming case, KANs effectively approximated the state-value function, achieving average reward improvements of up to 88.0% and 94.1% over MLPs and LSTMs networks, respectively, and increased by 766.7% and 105.6% in the Kármán gait swimming case. Under comparable network sizes, the intelligent fish with KANs exhibited faster learning capabilities and more stable swimming performance in complex fluid settings.

A study on hybrid-architecture deep learning model for predicting pressure distribution in 2D airfoils

This study introduces a novel deep learning-based technique for predicting pressure distribution images, aimed at application in image-based approximate optimal design. The proposed approach integrates both unsupervised and supervised learning paradigms, employing autoencoders (AE) for the unsupervised component and fully connected neural networks (FNN) for the supervised component. A surrogate model based on 2D image data was developed, enabling a comparative analysis of three distinct methods: the conventional AE, the convolutional autoencoder (CAE), and a hybrid CAE, which combines the CAE with a conventional AE. Extensive experiments demonstrated that the CAE method achieved the highest learning capability and restoration rate for pressure distribution images of 2D airfoils. The compressed latent image data were utilized as inputs for the FNN, which was trained to predict latent features. These features were decoded to forecast the corresponding pressure distribution images. The results showed excellent concordance with those derived from computational fluid dynamics (CFD) simulations, achieving a match rate exceeding 99.99%. This methodology significantly simplifies and accelerates image prediction, rendering it feasible without requiring specialized CFD knowledge. Moreover, it enhances accuracy while streamlining the neural network structure. Consequently, it provides foundational technology for image data-based optimization, establishing a platform for future AI-driven design and optimization advancements.

Unleashing the Potential of Deep Learning Methods for Detecting Defective Expressions Using Hyperparameter Optimization Techniques

Natural Language Processing (NLP) has emerged remarkable progress in the field of deep learning studies. Not only a superior alternative to rule-based NLP methods, deep learning-based techniques have also succeeded more accurate performances in various NLP tasks such as text classification, sentiment analysis or document clustering. Since the performance of a deep learning model undoubtedly depends on adjusting its hyperparameters ideally, tuning the most optimum hyperparameters determines the capability of the model learning in terms of meaningful pattern extraction from the input data. In this paper, hyperparameter optimization techniques of Bayesian Optimization, Random Search and Grid Search have been applied on the deep learning models of Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) for the purpose of detecting defective expressions in Turkish sentences. The hyperparameters of previously implemented LSTM and CNN models for this purpose have been adjusted using trial-and-error approach, which is time-consuming and cannot guarantee the most ideal model in general. After these hyperparameters have been adjusted using optimization techniques, the performances in terms of accuracy have been increased from 87.94% to 92.82% and from 84.33% to 89.79% for the models of LSTM and CNN respectively.