Prediction Model Research Articles

Multi-factor dynamic correlation prediction and analysis of carbon peaking for building sector: a case study of Shaanxi province

The factors influencing carbon emissions in the construction sector are numerous, and the relationships between these factors are complex. Previous studies on carbon peaking have often overlooked the dynamic changes between influencing factors and limited the number of variables to simplify the computation of predictive models. Based on the goal of carbon peaking, this study explores the relationships between internal factors within the construction industry and establishes a network of factor correlation. Furthermore, this network is embedded into an improved STIRPAT model, and a multi-factor dynamic correlation prediction model is constructed by incorporating scenario analysis. Taking Shaanxi Province, China, as a case for empirical analysis, the study explores carbon-peaking solutions for the building sector under different development scenarios. The findings indicate that carbon emissions in Shaanxi's building sector continuously increased during the study period, reaching 213 MtCO2 in 2020. Through factor screening, 12 driving factors were found to be significantly related to carbon emissions, all showing positive correlations, with the urbanization rate contributing the most to emissions. The dynamic association prediction model constructed had an accuracy of 0.996. Using this model, nine carbon emission scenarios were predicted, with optimizing the energy structure identified as the critical pathway, achieving a 5.01% reduction in emissions. A comprehensive strategy could achieve a 12.49% reduction and meet the carbon peaking target. Finally, the study proposes policy recommendations for the coordinated management of emissions reductions in cities and the construction industry, contributing to the development of sustainable cities and societies.

Percutaneous radiofrequency ablation of liver metastases from colorectal cancer: Development of a prognostic score to predict overall survival

PurposeTo develop a model for pretreatment prediction of overall survival (OS) after radiofrequency ablation (RFA) for colorectal liver metastasis (CRLM). MethodThis retrospective study included 491 patients (median age, 61 years; 348 men) who underwent percutaneous RFA for CRLM between 2000 and 2021. The Kaplan–Meier method was used to estimate OS rates. Independent factors affecting OS were investigated using multivariable Cox regression analysis. Risk scores were assigned to the risk factors and pretreatment prediction models were created using the risk factors. ResultsAfter RFA, the 5-, 10-, and 20-year OS rates were 44 %, 31 %, and 24 %, respectively, and the median OS was 46 months. Multivariate Cox regression analysis showed that a largest tumor size ≥ 2 cm (P<0.001), positive nodal status of primary tumor (P<0.001), carcinoembryonic antigen level > 30 ng/mL (P=0.049), multiple tumors (P=0.008), and T4 stage of the primary tumor (P=0.029) were independently associated with OS. In patients with a single CRLM, tumor diameter (P<0.001), positive nodal status of primary tumor (P=0.001), disease-free interval <12 months (P=0.045), and subcapsular location (P=0.03) were risk factors affecting OS. According to our prediction models, which included the aforementioned risk factors, OS rates progressively decreased as the risk scores increased, with significantly different OS rates between contiguous groups (P<0.001). ConclusionsOur prediction models can be used as a prognostic stratification tool in patients with CRLM, and can help select those candidates who will benefit most from RFA.

Mortality prediction of COVID-19 patients using supervised machine learning

Hospitalized patients with COVID-19 are at higher risk of mortality. Machine learning (ML) algorithms have been proposed as a possible strategy for predicting mortality rates among patients hospitalized with COVID-19. This study analyzed various ML algorithms and identified the best model to predict COVID-19 mortality based on demographic, clinical, and laboratory data collected at registration. Data from 4,314 eligible patients (3,384 survivors and 930 who died) was collected from the register of three hospitals in Yogyakarta province, Indonesia, based on the confirmed predictors. Next, ML algorithms were utilized to predict mortality. Finally, the confusion matrix was used to evaluate how effective the models performed. The best five predictors from 26 features were myocardial infarction, SpO2, neutrophil, D dimer, and creatinine. The results indicate that the random forest algorithm showed better performance than other ML algorithms in terms of accuracy, sensitivity, precision, specificity, and area under the curve (AUC), achieving values of 84.15%, 84.0%, 84.1%, 83.9%, and 90.02%, respectively. Implementing ML techniques can accurately predict the mortality rate associated with COVID-19. Therefore, this predictive model can help clinicians and hospitals predict COVID patients with a greater risk of death and effectively target more appropriate treatments.

Modelos de predicción para detectar pacientes con enfermedades cardiacas empleando redes neuronales y las bibliotecas Pytorch y TensorFlow

Neural Networks are used to generate prediction models aimed at determining whether an individual has heart conditions. The PyTorch and TensorFlow libraries are applied to a dataset of patients related to heart diseases, containing 17 predictor variables. The purpose of this work is to compare the results obtained using the aforementioned libraries with Neural Networks, analyzing the behavior of loss functions and the outcomes from the confusion matrix when creating the prediction model. DownSampling and UpSampling techniques are employed to address the imbalance in the dataset, which consists of a total of 319,795 patients, of whom only 27,373 have heart disease. It was found that for this dataset, the best results with PyTorch are achieved in models of 100 epochs and above, with execution times of only a few seconds, while TensorFlow shows good results starting from models with 10 epochs, though its execution time is considerably longer. An analysis is conducted on the difference in computation time between PyTorch and TensorFlow.

Spatial-spectral feature mining in hyperspectral corn leaf venation structure and its application in nitrogen content estimation

The growth of corn plants requires a significant amount of nitrogen nutrient supply to ensure the yield. Meanwhile, overfertilization could result in adverse environmental impacts, making it crucial to monitor the nitrogen supply condition in corn plants precisely. Hyperspectral imaging (HSI) could be the solution to this challenge, as HSI plant phenotyping technology has been widely utilized to nondestructively identify plant traits, such as mineral nutrient deficiencies in corn plants. However, limitations persist where the conventional HSI nitrogen prediction models mainly relied on the overall colors of the plant tissue extracted from the spectral domain but rarely included the spatially distributed information on the leaf level. This study aimed to examine if including new information from the spatial domain could potentially improve the performance of HSI models. Because the venation structure plays a crucial role in the distribution of various nutrients across the leaf, a series of physiological responses caused by nitrogen deficiency could result in non-uniform color patterns related to the veins. The recent advancement of HSI techniques such as LeafSpec, whose imaging quality and spatial-spectral resolution have been significantly improved, made it possible to extract the venation structure together with high-resolution spatial-spectral features. In this study, the hypothesis was that utilizing high-resolution spatial-spectral features extracted based on the venation structure could yield a better-performed nitrogen content prediction model compared to the averaged spectrum of the corn leaf. First, a venation structure segmentation algorithm was developed using the Local Binary Patterns (LBP) method for hyperspectral corn leaf images scanned with LeafSpec. Second, for every hyperspectral leaf image, 131 spectral index heatmaps were generated, and 30 leaf regions were picked based on the venation structure, resulting in 3930 spatial-spectral features. Third, the features were picked using the Least Absolute Shrinkage and Selection Operator (LASSO) regression. As the results tested with a field assay involving two different corn genotypes and two nitrogen treatments, the Partial Least Square Regression (PLS-R) model built with selected spatial-spectral features outperformed the model built with the averaged leaf spectra in terms of the Root Mean Squared Error (RMSE) of predictions. The results provided encouraging proof and guidance for the potential benefit of using high-resolution spatial-spectral features derived from hyperspectral leaf images to improve the accuracy and robustness of the nitrogen content prediction models for corn plants.

GPT-based data-driven urban building energy modeling (GPT-UBEM): Concept, methodology, and case studies

Achieving carbon neutrality is a critical global goal, with urban building energy modeling (UBEM) playing a pivotal role by providing data-driven insights to optimize energy consumption and reduce emissions. This paper introduces GPT-based urban building energy modeling (GPT-UBEM), a novel approach utilizing GPT’s advanced capabilities to address key UBEM challenges using GPT-4o. The study aimed to demonstrate the effectiveness of GPT-UBEM in performing UBEM tasks and to explore its potential in overcoming traditional limitations. Specifically, (1) basic analytics of urban data, (2) data analysis and energy prediction, (3) building feature engineering and optimization, and (4) energy signature analysis were conducted in four case studies. These analyses were applied to 2,000 buildings in Seoul and 31 buildings in Gangwon-do, South Korea. Through case study, the findings highlighted the ability of GPT-UBEM to integrate diverse data sources, optimize building features for high accuracy in prediction models, and provide valuable insights for urban planners and policymakers through the use of expert domain knowledge and intervention. Additionally, based on the results derived from GPT-UBEM in this study, the current limitations of GPT-UBEM (L1 to L3) and future research directions (F1 to F4) have been outlined.

IoT-based Ubiquitous Healthcare System with Intelligent Approach to an Epidemic

Background:: The recent pandemic has shown its different shades across various solicitations, especially in the healthcare sector. It has a great impact on transforming the traditional healthcare architecture, which is based on the physical approaching model, into the modern or remote healthcare system. The remote healthcare approach is quite achievable now by utilizing multiple modern technological paradigms like AI, Cloud Computing, Feature Learning, the Internet of Things, etc. Accordingly, the pharmaceutical section is the most fascinating province to be inspected by medical experts in restoring the evolutionary healthcare approaches. COVID-19 has created chaos in the society for which many unexpected deaths occur due to delays in medication and the improper prognosis at an irreverent plan. As medical management applications have become ubiquitous in nature and technology-oriented, patient monitoring systems are getting more popular among medical actors. Method: The Internet of Things (IoT) has achieved the solution criteria for providing such a huge service across the globe at any time and in any place. A quite feasible and approachable framework has evolved through this work regarding hardware development and predictive patent analysis. The desired model illustrates various approaches to the development of a wearable sensor medium that will be directly attached to the body of the patients. These sensor mediums are mostly accountable for observing body parameters like blood pressure, heart rate, temperature, etc., and transmit these data to the cloud storage via various intermediate steps. The storage medium in the cloud will be storing the sensor-acquired data in a time-to-time manner for a detailed analysis. Further, the stored data will be normalized and processed across various predictive models. Results and Conclusion: The model with the best accuracy will be treated as the resultant model among the numerous predictive models deployed in the cloud. During the hardware development process, several hardware modules are discussed. After receiving sensor-acquired data, it will be processed by the cloud's multiple machine-learning models. Finally, thorough analytics will be developed based on a meticulous examination of the patients' cardinal, essential, and fundamental data and communicated to the appropriate physicians for action. This model will then be used for the data dissemination procedure, in which an alarm message will be issued to the appropriate authorities.

Fast prediction of key parameters in FEBA using the COSINE subchannel code and artificial neural network

Numerical techniques have emerged as an essential tool for operators and designers to preemptively acquire key parameters in accidents analysis. However, due to insufficient experience, it is difficult for them to obtain satisfactory numerical results. Moreover, the uncertainty analysis and quantification necessitate the simulation of a substantial number of samples, which requires a significant amount of computational time. Therefore, the development of a fast prediction model becomes imperative. In this work, a prediction model based on the in-house COSINE subchannel code and Multi-Head Perceptron (MHP) is developed. The COSINE subchannel code is employed to provide data sets for training neural networks. Firstly, the numerical results of COSINE subchannel code are compared with experimental data to ensure the accuracy of data sets. Secondly, input features for neural networks are selected by evaluating the impact of input parameters on numerical results, and a series of simulations is carried out to generate data sets. Then, a comparative analysis was conducted between the Multi-Layer Perceptron (MLP) and Support Vector Regression (SVR) models, and the MLP model performs better. Subsequently, the MLP was compared with the MHP, demonstrating the advantage of MHP model. Based on this, the predictions are conducted using the MHP model and the distribution of key parameters is compared with that obtained by COSINE subchannel code. The results illustrate that developed MHP model is an efficient tool for predicting key parameters during the reflooding phase.

Reliability of Regression Based Hybrid Machine Learning Models for the Prediction of Solar Photovoltaics Power Generation

Solar Photovoltaics (PVs) have become widespread as micro-distributed electric power generators in urban residential and commercial areas due to their affordability and minimal maintenance requirements. Despite these advantages, PV generation is intermittent, necessitating the implementation of robust predictive algorithms to capture power generation trends effectively. Accurate PV generation prediction is crucial for balancing energy demand and supply. Precise predictions help utilities use other grid resources efficiently, enhance market participation, and make informed planning decisions. Therefore, ensuring the precise performance of predictive models is imperative in the power generation industry. However, the performance of the predictive models typically fluctuates over time, necessitating a reliability assessment of their performance. This paper develops a hybrid machine learning model by integrating the support vector machine (SVM), random forest (RF), and gradient boosting machine (GBM) with multivariate adaptive regression spline (MARS) to predict the hourly PV power generation for 3-day and 7-day periods in three urban areas of North Dakota. The performance of the models has been recorded over a year, and a probability distribution model is proposed to demonstrate the hybrid algorithm’s reliability and effectiveness. Results show the proposed prediction model is more reliable for shorter prediction periods. The hybrid-MARS models significantly improve prediction reliability compared to the stand-alone MARS model. Among these models, MARS-SVM exhibits the highest reliability and consistently better accuracy than other hybrid models.

Prediction of clinical prognosis and drug sensitivity in hepatocellular carcinoma through the combination of multiple cell death pathways.

Hepatocellular carcinoma (HCC) is the sixth most common malignant tumor, highlighting a significant need for reliable predictive models to assess clinical prognosis, disease progression, and drug sensitivity. Recent studies have highlighted the critical role of various programmed cell death pathways, including apoptosis, necroptosis, pyroptosis, ferroptosis, cuproptosis, entotic cell death, NETotic cell death, parthanatos, lysosome-dependent cell death, autophagy-dependent cell death, alkaliptosis, oxeiptosis, and disulfidptosis, in tumor development. Therefore, by investigating these pathways, we aimed to develop a predictive model for HCC prognosis and drug sensitivity. We analyzed transcriptome, single-cell transcriptome, genomic, and clinical information using data from the TCGA-LIHC, GSE14520, GSE45436, and GSE166635 datasets. Machine learning algorithms were used to establish a cell death index (CDI) with seven gene signatures, which was validated across three independent datasets, showing that high CDI correlates with poorer prognosis. Unsupervised clustering revealed three molecular subtypes of HCC with distinct biological processes. Furthermore, a nomogram integrating CDI and clinical information demonstrated good predictive performance. CDI was associated with immune checkpoint genes and tumor microenvironment components using single-cell transcriptome analysis. Drug sensitivity analysis indicated that patients with high CDI may be resistant to oxaliplatin and cisplatin but sensitive to axitinib and sorafenib. In summary, our model offers a precise prediction of clinical outcomes and drug sensitivity for patients with HCC, providing valuable insights for personalized treatment strategies.

Sensitivity analysis of carbon fiber reinforced asphalt pavements: Experimental study and data driven predictive model using machine learning

It is well known that the impact of fibers on reinforcing asphalt pavement (AP) has been extensively investigated. However, the optimal fiber length and content considering various temperatures is still an unresolved issue in this field. To reach this goal, this research aims to study the impact of carbon fiber (CF) reinforcement on the fracture energy and toughness of AP under varying environmental conditions. Several mix designs considering different CF length (10–30 mm) and content (1–3.5 %) at 5 °C and ambient temperatures were evaluated to determine the optimal values. The results demonstrated that while increasing CF length and content generally improves fracture energy and toughness, there is an optimal threshold beyond which additional CF content yields diminishing returns. Notably, the sample with a 1.5 % replacement ratio and 15 mm CF length exhibited superior performance, significantly enhancing the AP’s resistance to fracture due to effective stress distribution and crack bridging. Conversely, samples with the higher fiber content and length showed decreased fracture toughness, due to fiber clustering and reduced workability. Additionally, experimental results indicated higher values at 5 °C for fracture energy and toughness. Advanced machine learning techniques were also utilized to develop predictive models to accurately simulate the fracture behavior of CF-reinforced AP mixtures. Among all models, Gaussian process regression demonstrated superior performance and exhibited lower error in predicting experimental data. Moreover, a sensitivity analysis of this model was conducted to determine how the length and content of CF, as well as temperature, influence fracture energy and toughness, guiding the optimization of CF integration in AP design. These findings provide valuable insights for engineering durable and resilient asphalt pavements capable of withstanding diverse climatic stresses, ultimately contributing to more sustainable and cost-effective infrastructuresolutions.

Machine learning aided prediction of martensite transformation temperature of NiTi-based shape memory alloy

The martensitic transformation temperature (Ms) of shape memory alloys plays a crucial role in their performance. To achieve rapid prediction of Ms in shape memory alloys, this study employs machine learning techniques, using NiTi-based SMAs, the most widely used type, as an example. The results show that the gradient boosting machine algorithm provides the best prediction accuracy, with an R² of 0.92 and a mean absolute error (MAE) of 23.42 °C on the test set. Through correlation analysis, recursive feature elimination, and exhaustive search methods, six key features were identified. Subsequently, SHapley Additive exPlanations (SHAP) values were introduced to analyze the model interpretability, revealing the feature importance ranking and the dependence relationship between features and SHAP values. To address the issue of low Ms in NiTi-based shape memory alloys, the concept of high-entropy alloys was introduced. The study designed a TiZrHfNiCu high-entropy shape memory alloy and efficiently screened alloy compositions using the predictive model. This approach successfully increased the Ms, with the Ti19Zr19Hf19Ni37Cu6 alloy exhibiting an Ms exceeding 400 °C, significantly enhancing high-temperature application performance.

Influence of steam curing on cyclic triaxial characteristics of recycled aggregate concrete: Experimental analysis and DEM simulation

The engineering application of steam-cured recycled aggregate concrete (often in a cyclic triaxial stress state) can not only improve the recycling efficiency of resources, but also accelerate the construction progress. In this paper, we adopt a combination of laboratory experiments, theoretical analysis and numerical simulation to study the cyclic triaxial characteristics of recycled aggregate concrete (RAC) under different curing regimes (20℃, 40℃, 60℃ and 80℃). The results indicate that as the steam curing temperature increases, the internal damage caused by high temperature continues to intensify, and the cyclic triaxial failure mode of RAC transitions from shear failure to compression failure, and its peak strength, dynamic elastic modulus, and dilatancy angle all show a downward trend. A linear prediction model is established based on the strong correlation between peak strength and steam curing temperature. As the loading cycles increase, the dynamic elastic modulus and dilatancy angle of RAC show exponential and linear downward trends respectively, and the decline rate increases with the increase of steam curing temperature, and the prediction models for dynamic elastic modulus and dilatancy angle are established based on quantitative relationships between variables. On the basis of experimental analysis results, a cyclic triaxial DEM model considering real recycled aggregates is established by introducing steam-cured damage indexes into the mesoscopic parameters, and its applicability in predicting cyclic triaxial mechanical properties of RAC under different curing regimes is verified. The research outcomes can save a lot of test cost and time consumption for developing steam-cured concrete with better performance, and have important theoretical guidance and practical significance for the wide application of steam-cured concrete.

A Data-Driven Seismic Fragility Model for Post-Earthquake Repairable Performance of Highway Curved Bridge Portfolios

The rapid assessment of seismic fragility for highway curved bridges is crucial for enhancing the seismic resilience of transportation infrastructure. However, commonly used performance limit states fail to fully capture post-earthquake rehabilitation requirements. To address this, this paper proposes a data-driven, system-level seismic fragility assessment method for post-earthquake repairable performance of highway curved bridge portfolios. A sample database of curved bridge portfolios is generated using uniform design (UD) and a parametric finite element program, which then drives machine learning (ML) algorithms to develop a seismic fragility prediction model for post-earthquake repairable performance. The model is used to analyze the influence of various structural attributes on the median values of fragility curves (mR) for curved bridges. Additionally, a simplified fragility estimation method is developed based on the analysis results, and its reliability is validated through typical case studies. The results show that the central discrepancy of the UD sampling method is 0.0649, providing reliable and comprehensive data support for the ML prediction model. The fragility prediction model based on an artificial neural network (ANN) exhibits favorable fidelity and robustness. Curved bridges with central angles (α) in the range of 00.5rad show significant variations in mR, with a coupling effect observed between α and column height (H). The median absolute percentage error (MAPE) of the simplified fragility parameter calculation formula is below 11%, offering a preliminary reference for assessing the post-earthquake repairable performance of curved bridges.

Weighted average algorithm: a novel meta-heuristic optimization algorithm based on the weighted average position concept

To address the ever-increasing complexity of real-world engineering challenges, meta-heuristic algorithms have been extensively studied and applied. However, balancing exploration and exploitation remains a significant challenge. In this paper, a novel meta-heuristic optimization algorithm based on the weighted average position concept, and named weighted average algorithm (WAA), is proposed and implemented. In this algorithm, the weighted average position for the whole population is first established at each iteration. Subsequently, WAA applies one of two movement strategies to balance exploration and exploitation, determined by a parameter function that depends on random constants and iteration numbers. To validate the effectiveness and reliability of WAA, it is applied to various optimization challenges, amongst which unconstrained benchmark functions and constrained engineering challenges. Based on the Friedman and Wilcoxon analyses, it can be concluded that the proposed algorithm obtained the best performance for the considered benchmark functions and engineering problems. The WAA is applied to prediction and optimization of surface waviness in Wire Arc Additive Manufacturing (WAAM) components. First, two prediction models relating WAAM process parameters and surface waviness are established based on an Artificial Neural Network (ANN) optimized by WAA, and Particle Swarm Optimization (PSO), respectively. The WAA optimized ANN (WAA/ANN) model outperforms both the standard ANN models and those optimized by PSO. Finally, leveraging the developed WAA/ANN prediction model, WAA and other optimization algorithms are applied to minimize waviness of a WAAM component, with WAA exhibiting promising performance.

Validation of Hemispherectomy Outcome Prediction Scale in Treatment of Medically Intractable Epilepsy

The Hemispherectomy Outcome Prediction Scale (HOPS) was developed to aid both clinicians and patients in determining the chance of success after hemispheric surgery for medically refractory epilepsy. The original study generating HOPS had a multi-institutional, large cohort format yielding near perfect patient stratification. Evidence suggests that methodologies utilized to create such predictive models, including cross-validation as well as stratification utilizing the same data employed for model generation, may be at risk of an undesirable modeling phenomenon known as overfitting. We posed the question of whether overfitting may be influencing HOPS results and aimed for preliminary evidence of external validation with parameters from patients at our institution not included in the original HOPS study. We found HOPS to stratify our limited post-operative cohort adequately. However, the likelihood of complete seizure freedom among the patients predicted by HOPS to be at greatest chance of success was ~75%, about 20 points lower than in the original HOPS cohort. This reduction in absolute chance of success predicted by HOPS may represent some degree of overfitting. It will be informative to aim for external validation of HOPS utilizing patient cohorts entirely separate from those used for model generation. External validation of HOPS and similar models could optimize realistic prediction of success after intervention.

A predictive model for the security and stability of the lithium-ion battery industry chain based on price modal combinations

Prices act as crucial market signals within industrial chains, and the smooth transmission of prices has significantly impacts on the safety and stability of the entire chain. This paper considers the lithium-ion battery industry chain as a complex system and uses prices as modal signals to construct an FEEMD-NAR-HMM industrial chain safety and stability prediction model. The research findings are as follows: (1) The lithium-ion industry chain exhibits a typical "price-stability" dissipative structure, where the consistency of price fluctuations within the industry chain has a significant impact on its overall safety and stability. (2) When products at different stages of the lithium-ion industry chain experience simultaneous price increases or decreases, the safety and stability of the industry chain are at a high level. When the transmission smoothness of price fluctuations across different stages of the lithium-ion industry chain is low, the safety and stability of the industry chain are at a low level. (3) In the near future, the lithium-ion industry chain will continue to exposed to volatility risks. The government should implement macroeconomic control measures to stabilize the lithium-ion market and increase research investment in lithium resource recycling to prevent a crisis of lithium resource shortages.

Machine Learning for Enhancing Prediction of Biogas Production and Building a VFA/ALK Soft Sensor in Full-Scale Dry Anaerobic Digestion of Kitchen Food Waste

Based on operational data collected over 1.5 years from four industrial-scale dry anaerobic digesters used for kitchen food waste treatment, this study adopted eight typical machine learning algorithms to distinguish the best methane prediction model and to develop a soft sensor based on the VFA/ALK ratio. Among all the eight tested models, the CatBoost (CB) algorithm demonstrated superior performance in terms of prediction accuracy and model fitting. Specifically, the CB model achieved a biogas production prediction accuracy (R2) ranging from 0.604 to 0.915, and a VFA/ALK R2 between 0.618 and 0.768 on the test dataset. Furthermore, the feature importance analysis revealed that biomass amount into the dry anaerobic digester was the primary factor influencing biogas production. Chemical oxygen demand (COD) and total ammonia nitrogen (TAN) were identified as the most significant factors impacting the VFA/ALK indicator during dry anaerobic digestion, collectively contributing to nearly 50% of the influence. Overall, this study verifies the feasibility of using machine learning to predict biogas production in industrial-scale dry anaerobic digestion and provides a crucial foundation for monitoring the stability of dry anaerobic digesters.

Predictive modeling and anomaly detection in large-scale web portals through the CAWAL framework

This study presents an approach that uses session and page view data collected through the CAWAL framework, enriched through specialized processes, for advanced predictive modeling and anomaly detection in web usage mining (WUM) applications. Traditional WUM methods often rely on web server logs, which limit data diversity and quality. Integrating application logs with web analytics, the CAWAL framework creates comprehensive session and page view datasets, providing a more detailed view of user interactions and effectively addressing these limitations. This integration enhances data diversity and quality while eliminating the preprocessing stage required in conventional WUM, leading to greater process efficiency. The enriched datasets, created by cross-integrating session and page view data, were applied to advanced machine learning models, such as Gradient Boosting and Random Forest, which are known for their effectiveness in capturing complex patterns and modeling non-linear relationships. These models achieved over 92% accuracy in predicting user behavior and significantly improved anomaly detection capabilities. The results show that this approach offers detailed insights into user behavior and system performance metrics, making it a reliable solution for improving large-scale web portals’ efficiency, reliability, and scalability.

Brain-Inspired Image Perceptual Quality Assessment Based on EEG: A QoE Perspective.

Human-oriented image communication should take the quality of experience (QoE) as an optimization goal, which requires effective image perceptual quality metrics. However, traditional user-based assessment metrics are limited by the deviation caused by human high-level cognitive activities. To tackle this issue, in this paper, we construct a brain response-based image perceptual quality metric and develop a brain-inspired network to assess the image perceptual quality based on it. Our method aims to establish the relationship between image quality changes and underlying brain responses in image compression scenarios using the electroencephalography (EEG) approach. We first establish EEG datasets by collecting the corresponding EEG signals when subjects watch distorted images. Then, we design a measurement model to extract EEG features that reflect human perception to establish a new image perceptual quality metric: EEG perceptual score (EPS). To use this metric in practical scenarios, we embed the brain perception process into a prediction model to generate the EPS directly from the input images. Experimental results show that our proposed measurement model and prediction model can achieve better performance. The proposed brain response-based image perceptual quality metric can measure the human brain's perceptual state more accurately, thus performing a better assessment of image perceptual quality.