Prediction Methodology Research Articles

Life prediction method of battery energy storage system in frequency modulation application

Abstract To tackle the challenge of lifespan reduction in lithium batteries during frequency modulation, this study introduces a novel Remaining Useful Life (RUL) prediction methodology. The proposed approach integrates Variational Mode Decomposition (VMD) with Gated Recurrent Unit (GRU) networks, thereby efficiently synthesizing data from both operational parameters and capacity metrics. Firstly, VMD is utilized to decompose the initial capacity data of lithium batteries into separate components characterized by high and low frequencies. Subsequently, for the high-frequency elements, GRU is employed for rolling iterative prediction, while for the low-frequency elements, features are extracted from the operational data and inputted into GRU for prediction. Finally, the component prediction results are restored to obtain capacity prediction values. Validation conducted using the NASA dataset shows that the root mean square error of capacity prediction is minimized to 0.0122, with a corresponding minimum average absolute error of 0.0096, and RUL prediction errors are generally within 2 cycles.

High-Precision Sensorless Control of High-Speed Permanent Magnet Synchronous Motor Based on the Prediction Methodology

High-Precision Sensorless Control of High-Speed Permanent Magnet Synchronous Motor Based on the Prediction Methodology

A New Methodology for User Equipment Trajectory Prediction in Cellular Networks

A New Methodology for User Equipment Trajectory Prediction in Cellular Networks

Leveraging multiple data types for improved compound-kinase bioactivity prediction

Machine learning provides efficient ways to map compound-kinase interactions. However, diverse bioactivity data types, including single-dose and multi-dose-response assay results, present challenges. Traditional models utilize only multi-dose data, overlooking information contained in single-dose measurements. Here, we propose a machine learning methodology for compound-kinase activity prediction that leverages both single-dose and dose-response data. We demonstrate that our two-stage approach yields accurate activity predictions and significantly improves model performance compared to training solely on dose-response labels. This superior performance is consistent across five diverse machine learning methods. Using the best performing model, we carried out extensive experimental profiling on a total of 347 selected compound-kinase pairs, achieving a high hit rate of 40% and a negative predictive value of 78%. We show that these rates can be improved further by incorporating model uncertainty estimates into the compound selection process. By integrating multiple activity data types, we demonstrate that our approach holds promise for facilitating the development of training activity datasets in a more efficient and cost-effective way.

Active control of road vehicle’s drag for varying upstream flow conditions using a recursive subspace based predictive control methodology

The growing focus on reducing energy consumption, particularly in electric vehicles with limited autonomy, has prompted innovative solutions. In this context, we propose a real-time flap-based control system aimed at improving aerodynamic drag in real driving conditions. Employing a Recursive Subspace based Predictive Control approach, we conducted wind tunnel tests on a representative model vehicle at reduced scale equipped with flaps. Comprehensive assessments using pressure measurements and Particle Image Velocimetry were undertaken to evaluate the control efficiency. Static and dynamic perturbation tests were conducted, revealing the system’s effectiveness in both scenarios. The closed-loop controlled system demonstrated a substantial gain, achieving a 5% base pressure recovery.

CRYPTOCURRENCY PRICE PREDICTION USING LSTM

Cryptocurrency, a digital form of currency, has emerged as a prominent asset class with unique characteristics such as decentralization, security, and global accessibility. As the adoption of cryptocurrencies continues to grow, the need for accurate price prediction using machine learning (ML) algorithms becomes crucial for various stakeholders in the financial ecosystem. This paper presents a comprehensive approach to cryptocurrency price prediction, focusing on the following key aspects: The data for this study is collected from the Binance platform, a leading cryptocurrency exchange known for its extensive market data and liquidity. The dataset includes historical price data across different time frames, including 1-hour, 4-hour, and daily intervals. Prior to analysis, the collected data undergoes thorough preprocessing steps to ensure data quality and consistency. This process includes handling missing values, removing outliers, and standardizing data formats for further analysis. Long Short-Term machine learning model algorithm is employed for price prediction. This model is chosen for its ability to capture complex patterns and dynamics in cryptocurrency price movements. The prediction phase involves training and testing the ML model using the preprocessed data. Performance evaluation metrics such as R-squared, Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and Mean absolute percentage error (MAPE) are utilized to assess the accuracy and robustness of the prediction model across different time frames. Accurate cryptocurrency price prediction is essential for various stakeholders, including investors, traders, businesses, and regulators. It facilitates informed decision- making, risk management, market analysis, trading strategy development, business planning, and regulatory compliance in the dynamic cryptocurrency market. By addressing these key elements, this study aims to contribute to the advancement of cryptocurrency price prediction methodologies using ML techniques, thereby enhancing decision-making processes and fostering a more efficient and transparent digital asset market ecosystem.

Integrative in silico approaches to analyse microRNA-mediated responses in human diseases.

Advancements in sequencing technologies have facilitated omics level information generation for various diseases in human. High-throughput technologies have become a powerful tool to understand differential expression studies and transcriptional network analysis. An understanding of complex transcriptional networks in human diseases requires integration of datasets representing different RNA species including microRNA (miRNA) and messenger RNA (mRNA). This review emphasises on conceptual explanation of generalized workflow and methodologies to the miRNA mediated responses in human diseases by using different in silico analysis. Although,there have been many prior explorations in miRNA-mediated responses in human diseases, the advantages, limitations and overcoming the limitation through different statistical techniques have not yet been discussed. This review focuses on miRNAs as important gene regulators in human diseases, methodologies for miRNA-target gene prediction and data driven methods for enrichment and network analysis for miRnome-targetome interactions. Additionally, it proposes an integrative workflow to analyse structural components of networks obtained from high-throughput data. This review explains how to apply the existing methods to analyse miRNA-mediated responses in human diseases. It addresses unique characteristics of different analysis, its limitations and its statistical solutions influencing the choice of methods for the analysis through a workflow. Moreover, it provides an overview of promising common integrative approaches to comprehend miRNA-mediated gene regulatory events in biological processes in humans. The proposed methodologies and workflow shall help in the analysis of multi-source data to identify molecular signatures of various human diseases.

Ensemble seasonal forecasting of typhoon frequency over the western North Pacific using multiple machine learning algorithms

Abstract This study introduces an ensemble prediction methodology employing multiple machine learning algorithms for forecasting the frequency of typhoons (TYFs) over the western North Pacific (WNP) during June‒November. Potential predictors were initially identified based on the relationships between the year-by-year variation (DY) of the TYFs and preseason (March–May) environmental factors. These predictors were subsequently further refined, resulting in the selection of eight key predictors. Prediction models were constructed using twenty machine learning algorithms, utilizing data from 1965 to 2010. These trained models were then applied to perform hindcasts of TYFs from 2011 to 2023. The forecasted DY was added to the observed TYF of the preceding year to obtain the current year’s TYF. The results indicate that the TYFs predicted by the multi-model ensemble (MME) closely align with the observation during the hindcast period. Compared to individual models, the MME improves the prediction skill for the DY by at least 5.56% and up to 56.92%. Furthermore, the mean bias of the MME for TYF is notably smaller than that of the ECMWF’s most recent seasonal forecasting system (SEAS5) in the years of 2017‒2023. The superior performance of the ensemble prediction approach was also validated through leave-one-out cross-validation. This research underscores the potential of ensemble prediction approach utilizing multiple machine learning algorithms to improve the forecasting skill of TYF over the WNP.

Structural Particularities, Prediction, and Synthesis Methods in High-Entropy Alloys

High-Entropy Alloys (HEAs) represent a transformative class of materials characterized by multiple principal elements and high configurational entropy. This review article provides an in-depth examination of their structural particularities, prediction methodologies, and synthesis techniques. HEAs exhibit unique structural stability due to high-entropy effects, severe lattice distortions, and slow diffusion processes. Predictive models, including thermodynamic and kinetic approaches, are essential for understanding phase stability. Various synthesis methods impact HEA properties, and advanced characterization techniques are crucial for their study. The article highlights current applications and future research directions, emphasizing the potential of HEAs in diverse technological fields.

Prediction of disease-free survival using strain elastography and diffuse optical tomography in patients with T1 breast cancer: a 10-year follow-up study

BackgroundEarly-stage breast cancer (BC) presents a certain risk of recurrence, leading to variable prognoses and complicating individualized management. Yet, preoperative noninvasive tools for accurate prediction of disease-free survival (DFS) are lacking. This study assessed the potential of strain elastography (SE) and diffuse optical tomography (DOT) for non-invasive preoperative prediction of recurrence in T1 BC and developed a prediction model for estimating the probability of DFS.MethodsA total of 565 eligible patients with T1 invasive BC were enrolled prospectively and followed to investigate the recurrence. The associations between imaging features and DFS were evaluated and a best-prediction model for DFS was developed and validated.ResultsDuring the median follow-up period of 10.8 years, 77 patients (13.6%) developed recurrences. The fully adjusted Cox proportional hazards model showed a significant trend between an increasing strain ratio (SR) (P < 0.001 for trend) and the total hemoglobin concentration (TTHC) (P = 0.001 for trend) and DFS. In the subgroup analysis, an intensified association between SR and DFS was observed among women who were progesterone receptor (PR)-positive, lower Ki-67 expression, HER2 negative, and without adjuvant chemotherapy and without Herceptin treatment (all P < 0.05 for interaction). Significant interactions between TTHC status and the lymphovascular invasion, estrogen receptor (ER) status, PR status, HER2 status, and Herceptin treatment were found for DFS(P < 0.05).The imaging–clinical combined model (TTHC + SR + clinicopathological variables) proved to be the best prediction model (AUC = 0.829, 95% CI = 0.786–0.872) and was identified as a potential risk stratification tool to discriminate the risk probability of recurrence.ConclusionThe combined imaging-clinical model we developed outperformed traditional clinical prognostic indicators, providing a non-invasive, reliable tool for preoperative DFS risk stratification and personalized therapeutic strategies in T1 BC. These findings underscore the importance of integrating advanced imaging techniques into clinical practice and offer support for future research to validate and expand on these predictive methodologies.

A deep learning approach for supercapacitor remaining useful life prediction using pre-classifying strategy

Accurate prediction of the remaining useful life (RUL) of supercapacitors (SCs) is essential for the application of energy storage systems. In the existing end-to-end RUL prediction methods, there exist large errors in life prediction in SCs, especially in the early cycle prediction. This paper proposes an augmentation of the end-to-end RUL prediction method to improve the precision named pre-classifying. First, the pre-classifying is used to divide SCs’ cycling data into different classes to ensure consistency in each class. Then the end-to-end models are built for each class to predict the RULs. In this work, a novel hybrid model that combines convolutional neural networks and long short-term memory networks is proposed to capture spatiotemporal features from the cycling data. The experiment results demonstrate that the proposed hybrid model outperforms various deep neural networks in terms of prediction accuracy. When using the same hybrid model as the backbone, we report competitive results of the pre-classifying method on the public dataset with the root mean square error (RMSE) of 147.67 cycles, a 69.5% improvement compared with the RMSE of 484.18 cycles of the classical end-to-end RUL prediction model. Furthermore, experiment results indicate that the proposed pre-classification method significantly enhances the prediction accuracy of the standard end-to-end RUL prediction method with different deep neural network architectures. These results demonstrate that the pre-classifying method can be a general and effective methodology for RUL prediction of complex SC systems.

A data-driven approach to predict the in vitro dissolution time of sustained-release tablets using raw material databases and machine learning algorithms

Tablets are the most typical dosage forms of pharmaceutical inventions. Sustained-release (SR) tablet formulations are designed to release the drug gradually in the bloodstream and often require less frequent dosing. Current strategies to optimize sustained-release tablet dissolution time still rely on the traditional approach, which is time-consuming and expensive. In the present context, we have demonstrated alternate machine learning and deep learning models through the TPOT AutoML platform. Six machine learning (ML) models were compared to improve the methodology for dissolution time prediction, particularly the decision tree regressor (DTR), gradient boost regressor (GBR), random forest regressor (RFR), extra tree regressor (ETR), XGBoost regressor (XGBR), and deep learning (DL). The obtained results indicated that machine learning methods are convincing in speculating the dissolution time, especially the random forest regressor, but upon hypertuning of the deep neural network, the deep learning model with a 10-fold cross-validation scheme demonstrated superior predictive performance with an NRMSE of 8% and an R2 of 0.92. The major essentials affecting the dissolution time of SR tablets were explained using the SHAP method.

Multi‐Pop: Enhancing user engagement with content‐based multimodal popularity prediction in social media

AbstractSocial media has entrenched itself as an indispensable marketing tool. We introduce a quantitative approach to predicting the popularity of social media posts within the café and bakery sector. Employing Multi‐Pop, a multimodal popularity prediction model that harnesses both images and text from post content, it utilizes the features of posts that significantly influence their popularity on one of the most widely used platforms, Instagram. By focusing solely on post‐content features and excluding user information, we analysed 8765 Instagram posts from the cafe and bakery domain, revealing that our model attains a superior accuracy rate of 82.0% compared with existing popularity prediction methods. Furthermore, the study identifies hashtags and post captions as exerting a greater impact on post popularity than images. This research furnishes valuable insights, particularly for small business owners and individual entrepreneurs, by introducing novel computational and empirical methodologies for Instagram marketing strategy and post popularity prediction, thereby enhancing the comprehension of social media marketing dynamics.

A tracking control method for electricity-carbon emission forecasting

This paper introduces a novel carbon emission prediction method based on tracking control, leveraging historical CO2 emission prediction errors and feed-forward integration of electricity consumption data to enhance forecasting accuracy and minimize lag. Comparative analysis with pre-trained models such as LSTM and ARDL using Python showcases the proposed method's substantial reduction in prediction errors compared to singular reliance on electricity data, while also significantly reducing computational time in contrast to LSTM models. The findings establish a valuable reference for policymakers and researchers in refining carbon emission prediction methodologies and formulating effective carbon reduction policies.

A new short-term wind power prediction methodology based on linear and nonlinear hybrid models

Fast and accurate wind power prediction is of great significance for grid planning. However, wind power dataset tends to be highly stochastic and volatile, while showing more stable seasonal and cyclical changes, which is a linear and nonlinear superposition features, and it is difficult to use a single linear or nonlinear model to make accurate predictions. Considering these essential features of wind power data, a short-term wind power prediction method based on linear and nonlinear hybrid models is proposed in this paper. First, the complete ensemble empirical mode decomposition (CEEMD) is used to decompose and reconstruct the wind speed and direction in the original dataset to reduce the volatility. Then, to capture the linear features in the dataset, the autoregressive integrated moving average model with exogenous input variables (AIRMAX) is used for linear modeling, and the sparrow search algorithm optimized gated recurrent unit (SSA-GRU) is used to model the nonlinear features. At the same time, to improve the efficiency of model training, federated learning (FL) is utilized for distributed model training. Finally, the ARIMAX and SSA-GRU models are weighted and summed the prediction results to gain the final prediction results using equal weighted averaging (EWA), minimum sum of squares error (MSSE), and maximum grey relational analysis (MGRA), which are commonly used to compute the weights of the combined models, respectively. The wind power dataset from a wind farm in northwest China from January 1, 2022 to October 31, 2022 are used for experiments and analysis, and the results show that the root mean square error (RMSE), R-square (R2), and accuracy (ACC) of the proposed method are 11.944, 0.987, and 0.613, respectively, which are better than all the compared models. The main contribution of this paper is twofold, on the one hand, it indirectly proves that the wind power dataset is formed by the superposition of linear and nonlinear features, and on the other hand, it puts forward a theoretical model and research paradigm for predicting short-term wind power and presents a scientific basis for grid scheduling.

Chloride Penetration of Surface-Coated Concrete: Review and Outlook.

Concrete coatings show significant promise in shielding concrete substrates from corrosion by effectively resisting harmful ions and moisture. Thanks to their practicality, high efficiency, and cost-effectiveness, coatings are considered a potent technique for enhancing the chloride resistance of reinforced concrete structures. Over recent decades, extensive research has concentrated on employing coatings to bolster concrete's ability to withstand chloride penetration. This paper provides a holistic review of the current studies on chloride infiltration in concrete surfaces treated with coating materials, primarily focused on chloride resistance improvement efficiency and chloride transport modeling. Firstly, by comparing the functions of assorted coatings, four inherent protection mechanisms are summarized and elaborated thoroughly. Afterwards, the chloride resistance improvement efficiency of assorted coatings reported in current studies are reviewed and compared in great detail, with a specific focus on inorganic, organic, and organic-inorganic composite coatings. Furthermore, the theoretical research about methodologies for chloride transport behavior prediction is summarized. Finally, this paper outlines the potential research directions in this field and the theoretical, technical, and practical application challenges. This review not only identifies critical areas necessitating further investigation and problem-solving in this domain but also aids in selecting appropriate coating materials and refining corrosion management strategies.

Improved Methodology for Breast Cancer Prediction through Integration of Hard Voting Ensemble Classifier on WDBC Data Set

Improved Methodology for Breast Cancer Prediction through Integration of Hard Voting Ensemble Classifier on WDBC Data Set

Refined Prediction Method for Production Performance of Deep-Water Turbidite Sandstone Oilfield: A Case Study of AKPO in Niger Delta Basin, West Africa.

Deep-water oilfields frequently employ large or superlarge well spacing, leading to significant production dynamics influenced by reservoir factors. Traditional methodologies often disregard these influences, resulting in poor accuracy. Therefore, an enhanced prediction methodology rooted in reservoir characteristics is proposed. This approach introduces the dynamic relative permeability law as a bridge, capturing macroscopic oil/water movement within the reservoir. For the first time, it integrates production dynamics with key controlling reservoir factors, encompassing reservoir architecture, injection-production connectivity, and reservoir heterogeneity. The results indicate that (1) In deep-water turbidite sandstone fields with ultralarge injector-producer well spacings, the distribution of oil-water movement is primarily influenced by reservoir connectivity and heterogeneity. The injection water sweeping ability coefficient can quantitatively describe the water flooding capacity, with a strong negative correlation between the injection water sweeping ability coefficient and interwell nonconnectivity coefficient and reservoir homogeneity coefficient. This suggests that better reservoir connectivity or weaker heterogeneity results in stronger water flooding capacity, leading to a wider range of water flooding under the same injection volume. (2) For regions with strong water flooding capacity (injection water sweeping ability coefficient 0.30-0.80), the water-free production period is the main production stage, with a focus on improving the planar flooding conditions. For regions with poor water flooding capacity (injection water sweeping ability coefficient 0.00-0.10), the middle and late water-cut periods are the main production stages, with a focus on improving interlayer dynamic differences in the later stages. For regions with moderate water flooding capacity (injection water sweeping ability coefficient 0.10-0.30), the initial focus should be on expanding planar flooding, followed by a focus on improving interlayer dynamic differences in the later stages. (3) The dynamic relative permeability law, capable of comprehensively portraying the reservoir's influence on macroscopic oil/water movement, emerges as a rational choice for production performance prediction in such contexts. Our method can improve the accuracy, compared with traditional method without geographical factors, from 45% to 90% during water-cut rising stage and 31% to 81% during production declining stage. The high prediction accuracy (90%) observed in the AKPO oilfields underscores the method's efficacy in directing on-site optimization and adjustments for the development of deep-water turbidite sandstone oilfields.

Geometric deep learning for molecular property predictions with chemical accuracy across chemical space

Chemical engineers heavily rely on precise knowledge of physicochemical properties to model chemical processes. Despite the growing popularity of deep learning, it is only rarely applied for property prediction due to data scarcity and limited accuracy for compounds in industrially-relevant areas of the chemical space. Herein, we present a geometric deep learning framework for predicting gas- and liquid-phase properties based on novel quantum chemical datasets comprising 124,000 molecules. Our findings reveal that the necessity for quantum-chemical information in deep learning models varies significantly depending on the modeled physicochemical property. Specifically, our top-performing geometric model meets the most stringent criteria for “chemically accurate” thermochemistry predictions. We also show that by carefully selecting the appropriate model featurization and evaluating prediction uncertainties, the reliability of the predictions can be strongly enhanced. These insights represent a crucial step towards establishing deep learning as the standard property prediction workflow in both industry and academia.Scientific contributionWe propose a flexible property prediction tool that can handle two-dimensional and three-dimensional molecular information. A thermochemistry prediction methodology that achieves high-level quantum chemistry accuracy for a broad application range is presented. Trained deep learning models and large novel molecular databases of real-world molecules are provided to offer a directly usable and fast property prediction solution to practitioners.

Multidisciplinary cancer disease classification using adaptive FL in healthcare industry 5.0

Emerging Industry 5.0 designs promote artificial intelligence services and data-driven applications across multiple places with varying ownership that need special data protection and privacy considerations to prevent the disclosure of private information to outsiders. Due to this, federated learning offers a method for improving machine-learning models without accessing the train data at a single manufacturing facility. We provide a self-adaptive framework for federated machine learning of healthcare intelligent systems in this research. Our method takes into account the participating parties at various levels of healthcare ecosystem abstraction. Each hospital trains its local model internally in a self-adaptive style and transmits it to the centralized server for universal model optimization and communication cycle reduction. To represent a multi-task optimization issue, we split the dataset into as many subsets as devices. Each device selects the most advantageous subset for every local iteration of the model. On a training dataset, our initial study demonstrates the algorithm's ability to converge various hospital and device counts. By merging a federated machine-learning approach with advanced deep machine-learning models, we can simply and accurately predict multidisciplinary cancer diseases in the human body. Furthermore, in the smart healthcare industry 5.0, the results of federated machine learning approaches are used to validate multidisciplinary cancer disease prediction. The proposed adaptive federated machine learning methodology achieved 90.0%, while the conventional federated learning approach achieved 87.30%, both of which were higher than the previous state-of-the-art methodologies for cancer disease prediction in the smart healthcare industry 5.0.