Advanced Model Research Articles

Chemical engineering and the circular water economy: Simulations for sustainable water management in environmental systems

In the face of escalating water scarcity and environmental degradation, the imperative for sustainable water management has never been more urgent. Chemical engineering emerges as a pivotal discipline in the pursuit of solutions to these pressing challenges. This review explores the role of chemical engineering in advancing the circular water economy paradigm through simulations aimed at fostering sustainable water management within environmental systems. The circular water economy concept advocates for the efficient utilization, recycling, and reclamation of water resources to minimize waste and maximize resource efficiency. Chemical engineering techniques play a fundamental role in realizing this vision through the design and optimization of water treatment processes, resource recovery systems, and advanced simulation methodologies. This review delves into the application of computational simulations within the realm of chemical engineering to model and analyze various aspects of the water cycle. Such simulations enable the assessment of complex environmental systems, aiding in the identification of optimal strategies for water resource allocation, pollution control, and ecosystem preservation. Key areas of focus include the simulation of wastewater treatment processes, such as biological, physical, and chemical treatment methods, to enhance pollutant removal efficiency and promote water reuse. Furthermore, advanced modeling techniques facilitate the evaluation of innovative technologies like membrane filtration, adsorption, and electrochemical processes for the purification and desalination of water resources. Moreover, chemical engineering simulations enable the assessment of integrated water management strategies, encompassing aspects of urban water systems, industrial processes, and agricultural practices. By considering the interconnectedness of various sectors, holistic approaches to water resource management can be formulated, promoting resilience and sustainability in the face of changing environmental conditions. The integration of chemical engineering simulations into the framework of the circular water economy offers a promising avenue for advancing sustainable water management practices. Through comprehensive modeling and analysis, informed decision-making can pave the way towards a more resilient and equitable water future, ensuring the long-term viability of our environmental systems.

Progress and Opportunities for Machine Learning in Materials and Processes of Additive Manufacturing.

In recent years, there has been widespread adoption of machine learning (ML) technologies to unravel intricate relationships among diverse parameters in various additive manufacturing (AM) techniques. These ML models excel at recognizing complex patterns from extensive, well-curated datasets, thereby unveiling latent knowledge crucial for informed decision-making during the AM process. The collaborative synergy between ML and AM holds the potential to revolutionize the design and production of AM-printed parts. This review delves into the challenges and opportunities emerging at the intersection of these two dynamic fields. It provides a comprehensive analysis of the publication landscape for ML-related research in the field of AM, explores common ML applications in AM research (such as quality control, process optimization, design optimization, microstructure analysis, and material formulation), and concludes by presenting an outlook that underscores the utilization of advanced ML models, the development of emerging sensors, and ML applications in emerging AM-related fields. Notably, ML has garnered increased attention in AM due to its superior performance across various AM-related applications. It is envisioned that the integration of ML into AM processes will significantly enhance 3D printing capabilities across diverse AM-related research areas.

An adaptive weighted ensemble learning network for diabetic retinopathy classification.

Diabetic retinopathy (DR) is one of the leading causes of blindness. However, because the data distribution of classes is not always balanced, it is challenging for automated early DR detection using deep learning techniques. In this paper, we propose an adaptive weighted ensemble learning method for DR detection based on optical coherence tomography (OCT) images. Specifically, we develop an ensemble learning model based on three advanced deep learning models for higher performance. To better utilize the cues implied in these base models, a novel decision fusion scheme is proposed based on the Bayesian theory in terms of the key evaluation indicators, to dynamically adjust the weighting distribution of base models to alleviate the negative effects potentially caused by the problem of unbalanced data size. Extensive experiments are performed on two public datasets to verify the effectiveness of the proposed method. A quadratic weighted kappa of 0.8487 and an accuracy of 0.9343 on the DRAC2022 dataset, and a quadratic weighted kappa of 0.9007 and an accuracy of 0.8956 on the APTOS2019 dataset are obtained, respectively. The results demonstrate that our method has the ability to enhance the ovearall performance of DR detection on OCT images.

Anisotropic elastoplasticity and fracture of SCFR-PEEK composites in complex biaxial loading: Experiments and modelling

This research aims to gain insight into the anisotropic deformation and fracture behaviours of short carbon fibre reinforced polyether-ether ketone composites (SCFR-PEEK) under complex loading using experimental and modelling approaches. Novel biaxial tensile experiments using optimised cruciform specimens are designed and performed to study the anisotropic elastoplasticity and fracture behaviours of SCFR-PEEK in various stress states. An advanced anisotropic constitutive model was developed, experimentally calibrated, numerically implemented, and successfully verified by mechanical responses of biaxial tension with various stress ratios. Furthermore, using a hybrid experimental-numerical approach, the biaxial failure stress at crack initiation sites captured by a high-speed camera in biaxial tension was obtained. Employing experimental failure stresses at various uniaxial and biaxial stress states, a maximum stress based failure criterion was developed, which is coupled with the anisotropic elastoplastic model, thus enabling the description the anisotropic elastoplastic and failure behaviours under complex loading. The prediction of the failure of SCFR-PEEK in complex biaxial stress states using the coupled model is in good agreement with biaxial tensile experimental results using circular-notched specimens. Therefore, the developed model is verified to be capable of describing both elastoplastic deformation and fracture failure behaviours of SCFR-PEEK composites in complex loading.

Comprehensive Assessment of Ischemic Stroke in Nonhuman Primates: Neuroimaging, Behavioral, and Serum Proteomic Analysis.

Ischemic strokes, prevalence and impactful, underscore the necessity of advanced research models closely resembling human physiology. Our study utilizes nonhuman primates (NHPs) to provide a detailed exploration of ischemic stroke, integrating neuroimaging data, behavioral outcomes, and serum proteomics to elucidate the complex interplay of factors involved in stroke pathophysiology. We observed a consistent pattern in infarct volume, peaking at 1-month postmiddle cerebral artery occlusion (MCAO) and then stabilized. This pattern was strongly correlated to notable changes in motor function and working memory performance. Using diffusion tensor imaging (DTI), we detected significant alterations in fractional anisotropy (FA) and mean diffusivity (MD) values, signaling microstructural changes in the brain. These alterations closely correlated with the neurological and cognitive deficits that we observed, highlighting the sensitivity of DTI metrics in stroke assessment. Behaviorally, the monkeys exhibited a reliance on their unaffected limb for compensatory movements, a common response to stroke impairment. This adaptation, along with consistent DTI findings, suggests a significant impact of stroke on motor function and spatial perception. Proteomic analysis through MS/MS functional enrichment identified two distinct groups of proteins with significant changes post-MCAO. Notably, MMP9, THBS1, MB, PFN1, and YWHAZ were identified as potential biomarkers and therapeutic targets for ischemic stroke. Our results underscore the complex nature of stroke and advocate for an integrated approach, combining neuroimaging, behavioral studies, and proteomics, for advancing our understanding and treatment of this condition.

Bearing capacity analysis and mechanism study of shared caisson under multidirectional loading

Shared anchor foundations experience loads from various directions throughout their operational lifespan. As a result of environmental loads or the possibility of anchor chain failures, the loading direction of the shared foundation may alter, affecting its normal functionality. This study investigates the bearing capacity of the shared caisson in sand using an advanced model and numerical methods under multidirectional loading. Moreover, the research investigates soil responses to clarify the mechanisms governing bearing capacity. The study delves into factors such as load angles, sand density, and previous load magnitudes to comprehend their impact on the bearing capacity of shared caissons. The findings suggest that subsequent loading on dense soil enhances bearing capacity, whereas loading on loose soil reduces it. Key factors influencing the shared caisson's bearing capacity include plastic deformation of the surrounding soil and density changes resulting from previous loads. A coefficient was proposed for designing the shared caisson, taking into account multidirectional loads, thereby providing insights for future shared anchor foundation designs.

Engineering AI for provable retention of objectives over time

AbstractI argue that ensuring artificial intelligence (AI) retains alignment with human values over time is critical yet understudied. Most research focuses on static alignment, neglecting crucial retention dynamics enabling stability during learning and autonomy. This paper elucidates limitations constraining provable retention, arguing key gaps include formalizing dynamics, transparency of advanced systems, participatory scaling, and risks of uncontrolled recursive self‐improvement. I synthesize technical and ethical perspectives into a conceptual framework grounded in control theory and philosophy to analyze dynamics. I argue priorities should shift towards capability modulation, participatory design, and advanced modeling to verify enduring alignment. Overall, I argue that realizing AI safely aligned throughout its lifetime necessitates translating principles into formal methods, demonstrations, and systems integrating technical and humanistic rigor.

Self-supervised category selective attention classifier network for diabetic macular edema classification.

This study aims to develop an advanced model for the classification of Diabetic Macular Edema (DME) using deep learning techniques. Specifically, the objective is to introduce a novel architecture, SSCSAC-Net, that leverages self-supervised learning and category-selective attention mechanisms to improve the precision of DME classification. The proposed SSCSAC-Net integrates self-supervised learning to effectively utilize unlabeled data for learning robust features related to DME. Additionally, it incorporates a category-specific attention mechanism and a domain-specific layer into the ResNet-152 base architecture. The model is trained using an ensemble of unsupervised and supervised learning techniques. Benchmark datasets are utilized for testing the model's performance, ensuring its robustness and generalizability across different data distributions. Evaluation of the SSCSAC-Net on multiple datasets demonstrates its superior performance compared to existing techniques. The model achieves high accuracy, precision, and recall rates, with an accuracy of 98.7%, precision of 98.6%, and recall of 98.8%. Furthermore, the incorporation of self-supervised learning reduces the dependency on extensive labeled data, making the solution more scalable and cost-effective. The proposed SSCSAC-Net represents a significant advancement in automated DME classification. By effectively using self-supervised learning and attention mechanisms, the model offers improved accuracy in identifying DME-related features within retinal images. Its robustness and generalizability across different datasets highlight its potential for clinical applications, providing a valuable tool for clinicians in diagnosing DME effectively.

Assessing the 2023 Canadian wildfire smoke impact in Northeastern US: Air quality, exposure and environmental justice

The Canadian wildfires in June 2023 significantly impacted the northeastern United States, particularly in terms of worsened air pollution and environmental justice concerns. While advancements have been made in low-cost sensor deployments and satellite observations of atmospheric composition, integrating dynamic human mobility with wildfire PM2.5 exposure to fully understand the environmental justice implications remains underinvestigated. This study aims to enhance the accuracy of estimating ground-level fine particulate matter (PM2.5) concentrations by fusing chemical transport model outputs with empirical observations, estimating exposures using human mobility data, and evaluating the impact of environmental justice. Employing a novel data fusion technique, the study combines the Weather Research and Forecasting model with Chemistry (WRF-Chem) outputs and surface PM2.5 measurements, providing a more accurate estimation of PM2.5 distribution. The study addresses the gap in traditional exposure assessments by incorporating human mobility data and further investigates the spatial correlation of PM2.5 levels with various environmental and demographic factors from the US Environmental Protection Agency (EPA) Environmental Justice Screening and Mapping Tool (EJScreen). Results reveal that despite reduced mobility during high PM2.5 levels from wildfire smoke, exposure for both residents and individuals on the move remains high. Regions already burdened with high environmental pollution levels face amplified PM2.5 effects from wildfire smoke. Furthermore, we observed mixed correlations between PM2.5 concentrations and various demographic and socioeconomic factors, indicating complex exposure patterns across communities. Urban areas, in particular, experience persistent high exposure, while significant correlations in rural areas with EJScreen factors highlight the unique vulnerabilities of these populations to smoke exposure. These results advocate for a comprehensive approach to environmental health that leverages advanced models, integrates human mobility data, and addresses socio-demographic disparities, contributing to the development of equitable strategies against the growing threat of wildfires.

Solar-Assisted Carbon Capture Process Integrated with a Natural Gas Combined Cycle (NGCC) Power Plant—A Simulation-Based Study

In the realm of Natural Gas Combined Cycle (NGCC) power plants, it is crucial to prioritize the mitigation of CO2 emissions to ensure environmental sustainability. The integration of post-combustion carbon capture technologies plays a pivotal role in mitigating greenhouse gas emissions enhancing the NGCC’s environmental profile by minimizing its carbon footprint. This research paper presents a comprehensive investigation into the integration of solar thermal energy into the Besmaya Natural Gas Combined Cycle (NGCC) power plant, located in Baghdad, Iraq. Leveraging advanced process simulation and modeling techniques employing Aspen Plus software, the study aims to evaluate the performance and feasibility of augmenting the existing NGCC facility with solar assistance for post-carbon capture. The primary objective of this research is to conduct a thorough simulation of the Besmaya NGCC power plant under its current operational conditions, thereby establishing a baseline for subsequent analyses. Subsequently, a solar-assisted post-combustion capture (PCC) plant is simulated and seamlessly integrated into the existing power infrastructure. To accurately estimate solar thermal power potential at the Baghdad coordinates, the System Advisor Model (SAM) is employed. The integration of solar thermal energy into the NGCC power plant is meticulously examined, and the resulting hybrid system’s technical viability and performance metrics are rigorously evaluated. The paper contributes to the field by providing valuable insights into the technical feasibility and potential benefits of incorporating solar thermal energy into conventional natural gas power generation infrastructure, particularly in the context of the Besmaya NGCC plant in Baghdad. The power generation capacity of the plant was set at 750 MW. With this capacity, the annual CO2 generation was estimated at 2,119,318 tonnes/year which was reduced to 18,064 tonnes/year (a 99% reduction). The findings aim to inform future decisions in the pursuit of sustainable and efficient energy solutions, addressing both environmental concerns and energy security in the region.

Geochemical Evaluation of Manganese Neutralization Sludge for Mn-Containing Mine Drainage Treatment

Conventional neutralization treatment for manganese (Mn)-bearing mine drainage provides a challenge of cost-efficiency, and new approaches should be explored for efficient removal of Mn. We focused on Mn neutralization sludge, a by-product of the Mn-bearing drainage treatment process, which was assumed to be useful as a water purification material. Mn and zinc (Zn) removal tests in simulated drainage were performed using Mn neutralization sludge, and the reaction mechanism was elucidated using geochemical modeling and X-ray absorption fine structure (XAFS) analysis. The results showed that the addition of sludge enabled to lower the Mn and Zn concentration below Japanese effluent standard (10 mg dm−3 for Mn; 2 mg dm−3 for Zn) within 1 h. Furthermore, heavy metal immobilization was achieved at neutral pH (7–8) with the sludge addition, while the conventional neutralization process without adding the sludge requires higher pH (>10) to lower Mn concentration. These removal behaviors were not explainable by considering only well-known phenomena: hydroxide precipitation, surface complexation reaction onto δ-MnO2, and autocatalytic Mn oxidation. Hence, we advanced the geochemical model for simulation, suggesting that a surface complexation reaction onto γ-MnOOH greatly contributed to the removal of Mn. Besides, Zn was calculated to be predominantly precipitated as ZnMn2O4. Solid residue analysis by XAFS measurement supported the result of above calculation, validating the reliability of the constructed geochemical model. Overall, we concluded that the advanced geochemical model would be useful in predicting the Mn and Zn behavior during mine drainage treatment with Mn neutralization sludge.Graphical abstract

Simulation of CO2 dissolution reactions in saline aquifers using lattice Boltzmann method

CO2 dissolution reactions in saline aquifers during geologic carbon sequestration (GCS) involve multiple physicochemical processes and pose a challenge for both experimental and numerical techniques to capture reactive transport features and complex porous structures. Benefited from advanced models in the lattice Boltzmann (LB) community, namely, multiphase flow LB model and multicomponent transport LB model with chemical reactions, dynamics of CO2-water interfaces, concentration evolution of ions, and heterogeneous and homogeneous reactions could be readily captured by the proposed LB model to characterize CO2 dissolution reactions applicable to far-field applications. This LB model can not only emphasize CO2 dissolution processes at the scale of a few pores but also elaborate on the corresponding controlling mechanisms in porous media during GCS in saline aquifers. LB simulations herein indicate that both diffusion coefficient and reactive interfacial length may change the total concentration gradient at the CO2-water interface to further affect CO2 dissolution reactions. It is also confirmed that CO2 dissolution is a non-equilibrium process, which could not be neglected in reservoir-scale simulations. The effect of reactive interfacial length on CO2 dissolution is negligible due to a narrower range of contact angles in saline aquifers. Influenced by the structural complexity of porous media, the dissolution of CO2 clusters shows a strong heterogeneous characteristic evaluated by the pore size distribution. The evolution of pH in homogeneous reactions is estimated via mass action equations. Besides, the effects of partial pressure, formation temperature, and salinity, as three key factors in the practical application, are thoroughly probed. The high pressure is conducive for sequestration because of its greater sequestration efficiency, but the temperature has both positive and negative impacts on CO2 dissolution trapping and should be carefully evaluated in a certain saline aquifer before the operation. High ion strength would decrease the efficiency of dissolution trapping to some extent.

Investigation on the modeling and simulation of hydrodynamics in asymmetric conduction laser micro-welding of austenitic stainless steel and its process optimization

Laser micro-welding is a joining technology utilized across various high-value industries, like medical, automotive, e-mobility, and aerospace. A trial-and-error process to identify welding parameters does not necessarily lead to optimized quality levels. Furthermore, offline non-destructive examination methods often launched to verify welding quality may inadvertently trigger excessive costs and time delays, ultimately failing to guarantee defect-free welds. In response to these challenges, this article introduces an advanced multiscale model designed to unravel the intricate dynamics of hydrodynamics and the overarching physics within laser micro-welding melting pools. Developed using the COMSOL software package, the model adeptly demonstrates how surface tension gradients shape the geometry of welds, thus influencing their quality. This knowledge allows the mapping of welding defects. One of the novelties of the article is to introduce geometric dissimilar welding conditions by simulating an asymmetric edge joint. It shows a study on a new, unstudied way to laser weld with many applications in the field. The model further establishes its utility in design experiments to determine parameter, tolerance, and system design. Moreover, the insights garnered from understanding and controlling these drivers have far-reaching implications for the advancement of subsequent methodological research and the development of in-situ quality control practices by characterizing the welding defects. Finally, the results shows that the discouragingly high computational costs restrict its potential application to support a Digital Twin.

Automated detection and recognition system for chewable food items using advanced deep learning models

Identifying and recognizing the food on the basis of its eating sounds is a challenging task, as it plays an important role in avoiding allergic foods, providing dietary preferences to people who are restricted to a particular diet, showcasing its cultural significance, etc. In this research paper, the aim is to design a novel methodology that helps to identify food items by analyzing their eating sounds using various deep learning models. To achieve this objective, a system has been proposed that extracts meaningful features from food-eating sounds with the help of signal processing techniques and deep learning models for classifying them into their respective food classes. Initially, 1200 audio files for 20 food items labeled have been collected and visualized to find relationships between the sound files of different food items. Later, to extract meaningful features, various techniques such as spectrograms, spectral rolloff, spectral bandwidth, and mel-frequency cepstral coefficients are used for the cleaning of audio files as well as to capture the unique characteristics of different food items. In the next phase, various deep learning models like GRU, LSTM, InceptionResNetV2, and the customized CNN model have been trained to learn spectral and temporal patterns in audio signals. Besides this, the models have also been hybridized i.e. Bidirectional LSTM + GRU and RNN + Bidirectional LSTM, and RNN + Bidirectional GRU to analyze their performance for the same labeled data in order to associate particular patterns of sound with their corresponding class of food item. During evaluation, the highest accuracy, precision,F1 score, and recall have been obtained by GRU with 99.28%, Bidirectional LSTM + GRU with 97.7% as well as 97.3%, and RNN + Bidirectional LSTM with 97.45%, respectively. The results of this study demonstrate that deep learning models have the potential to precisely identify foods on the basis of their sound by computing the best outcomes.

Integration of Febio as an Instructional Tool in the Undergraduate Biomechanics Curriculum.

Computer simulations play an important role in a range of biomedical engineering applications. Thus, it is important that biomedical engineering students engage with modeling in their undergraduate education and establish an understanding of its practice. In addition, computational tools enhance active learning and complement standard pedagogical approaches to promote student understanding of course content. Herein, we describe the development and implementation of learning modules for computational modeling and simulation (CM&S) within an undergraduate biomechanics course. We developed four CM&S learning modules that targeted predefined course goals and learning outcomes within the febio studio software. For each module, students were guided through CM&S tutorials and tasked to construct and analyze more advanced models to assess learning and competency and evaluate module effectiveness. Results showed that students demonstrated an increased interest in CM&S through module progression and that modules promoted the understanding of course content. In addition, students exhibited increased understanding and competency in finite element model development and simulation software use. Lastly, it was evident that students recognized the importance of coupling theory, experiments, and modeling and understood the importance of CM&S in biomedical engineering and its broad application. Our findings suggest that integrating well-designed CM&S modules into undergraduate biomedical engineering education holds much promise in supporting student learning experiences and introducing students to modern engineering tools relevant to professional development.

Mesosilicate materials for environmental applications: Adsorption separation analysis via hybrid computational and machine learning tools

In this extensive analysis, we delve into the utilization of advanced hybrid model for molecular separation description via mesoporous materials. The process considered here is adsorption which is utilized for molecular separation in liquid solution. Data for adsorption are obtained in terms of solute concentration by solving mass transfer equations numerically. Then, the data is used for training and validation of several machine learning techniques to establish the hybrid model. For machine learning model, several methods are utilized including three robust tree-based ensemble models, namely Gradient Boosting (GB), Random Forest (RF), and Extra Trees (ET). The methos were utilized to tackle the challenging task of predicting chemical concentrations in a dataset comprising an array of over 19,000 data. These data points are characterized by input variables representing coordinates (x and y), while the output variable encapsulates chemical concentration (C). By subjecting these models to a meticulous optimization process, we achieved substantial enhancements in their predictive capabilities. RF emerged as the standout performer, boasting a remarkable R2 score of 0.99902. ET and GB also demonstrated commendable performance improvements, underscoring the versatility of tree-based ensemble models in delivering precise and reliable predictions for chemical concentrations within intricate and multifaceted datasets.

Reducing Hospital Readmission Risk Using Predictive Analytics

This study highlights the development and application of a predictive analytics system in a Midwestern hospital to assess and manage the risk of patient readmissions within 30 days of discharge. By integrating advanced analytical modeling with electronic health records, the system enables the creation of personalized care plans by accurately predicting patients' readmission risks and the optimal timing for interventions. The results suggest that such models can significantly improve resource allocation and the personalization of care plans, thereby reducing unnecessary readmissions and aligning with value-based, patient-centered healthcare goals.

Enhancing Natural Language Processing (NLP) through VIKOR Method: A Comprehensive Approach for Improved Computational Linguistics

Natural Language Processing (NLP) is a revolutionary discipline that resides at the crossroads of computer science and linguistics, with its primary emphasis on the interaction between computers and human language. With roots in artificial intelligence, NLP seeks to equip machines with the ability to comprehend, interpret, and respond to natural language, enabling more intuitive and meaningful communication between humans and computers. This multidisciplinary domain leverages advanced algorithms and models to tackle a range of linguistic challenges, from language translation and sentiment analysis to speech recognition. Recent breakthroughs, particularly in deep learning and neural networks, have propelled NLP to new heights, with applications spanning diverse sectors such as healthcare, finance, and education. As NLP continues to advance, its potential impact on enhancing human-machine interaction and information processing is increasingly evident, promising a future where technology seamlessly integrates with our natural modes of communication. The significance of Natural Language Processing (NLP) in research lies in its capacity to revolutionize human-computer interaction. NLP empowers machines to understand and generate human language, enabling advancements in sentiment analysis, language translation, and conversational AI. This transformative capability has profound implications across various industries, including healthcare, finance, and education. NLP research not only enhances the efficiency of information retrieval and processing but also holds the key to developing more intuitive and user-friendly technologies. As the frontier of NLP research expands, its potential to bridge the communication gap between humans and machines continues to shape the future of technology and information access. VIKOR functions as a multi-criteria decision-making technique that determines the best option by comparing it to the ideal option. The ranking procedure comprises determining distances concerning the optimal solution. VIKOR uses linear normalization to get the best possible outcomes. This technique was first presented by Opricovic in 1998 and was intended to optimize multi-attribute complex systems. Its main focus is on ranking lists that allow for flexibility in the strategy weight interval and incorporate compromise alternatives to obtain desired results. Alternative taken as Open AI GPT-4, Google BERT, Microsoft Azure Text Analytics, IBM Watson Natural Language Understanding, spaCy, NLTK (Natural Language Toolkit), Amazon Comprehend. Evaluation Parameter taken as Sentiment Analysis (F1 Score), NER Performance, Language Support, Processing Speed (Response Time) (ms), Translation Accuracy (BLEU Score), Data Privacy. The result it is seen that Amazon Comprehend is got the first rank where as is the IBM Watson Natural Language Understanding is having the lowest rank.

Design of corporate human capital value measurement model based on binary tree

The measurement process of corporate human capital value ignores the in-depth analysis of the influencing factors of value measurement, which leads to the inaccuracy of the measurement result of corporate human capital value. Therefore, taking an enterprise in Heilongjiang Province as the research object, a measurement model of enterprise human capital value based on binary tree is designed. Establish the corporate human capital value measurement index system, and initially fix the human capital value. Calculate the floating value of human capital under the complete information, and determine the influencing factors of human capital value measurement. The human capital value of enterprise under incomplete information is calculated to complete the construction of the measurement model of human capital value of enterprise based on binary tree. Taking the actual human resource performance score of an enterprise from 2019 to 2022 as an example, the experiment proved that the design model and the traditional measurement model evaluated the enterprise human resource performance, and proved that the measurement model based on binary tree was more accurate than the traditional model, and the final measurement accuracy of the design model reached 93.5%. Compared with the traditional measurement model ahead of 18.5%–10.3%, compared with the current advanced measurement model ahead of 5.2%–5.7%. The evaluation Angle in the research is slightly lacking of practical significance, and further research can carry out further evaluation on income to maximize the practical significance of the research. However, the model is evaluated from the perspective of pricing, but in real life, the value of enterprise human capital is reflected in income distribution. Therefore, if the measurement of human capital value is combined with income distribution in the next step, the research results will be closer to the actual situation and will have more practical significance.

DGAMDA: Predicting miRNA-disease association based on dynamic graph attention network.

MiRNA (microRNA)-disease association prediction has essential applications for early disease screening. The process of traditional biological experimental validation is both time-consuming and expensive. However, as artificial intelligence technology continues to advance, computational methods have become efficient tools for predicting miRNA-disease associations. These methods often rely on the combination of multiple sources of association data and require improved feature mining. This study proposes a dynamic graph attention-based association prediction model, DGAMDA, which combines feature mapping and dynamic graph attention mechanisms through feature mining on a single miRNA-disease association network. DGAMDA effectively solves the problems of feature heterogeneity and inadequate feature mining by previous static graph attention mechanisms and achieves high-precision feature mining and association scoring prediction. We conducted a five-fold cross-validation experiment and obtained the mean values of Accuracy, Precision, Recall, and F1-score, which were .8986, .8869, .9115, and .8984, respectively. Our proposed model outperforms other advanced models in terms of experimental results, demonstrating its effectiveness in feature mining and association prediction based on a single association network. In addition, our model can also be used to predict miRNAs associated with unknown diseases.