Prediction Accuracy Of Method Research Articles

Abstract LB434: Rapid and reproducible expansion of rare tumor cells: The R3CE platform for personalized medicine

Abstract We have developed a novel single-cell derived 3D organoid culture platform, Rapid, Reproducible, Rare Cell 3D Expansion (R3CE), capable of generating 3D organoids from solid tumors and normal tissues obtained via surgical tissues and needle biopsies within one week. This method demonstrates over 90% success in banking for at least two passages with over 106 cells across various cancer types, including breast cancer, colorectal cancer, hepatoma cancer, and ovarian cancer. The organoids maintain high fidelity to original tissues, as evidenced by H&E staining, WES, and protein marker analysis across generations. Notably, the R3CE platform can also cultivate circulating tumor cells (CTCs) from peripheral blood. The drug sensitivity profiles of RCE-cultured CTCs closely mirrored clinical outcomes in breast cancer patients. For a patient with stage IV HER2-positive breast cancer, our real-time assay results led to an adjustment in treatment from lapatinib/5-FU to lapatinib/Trastuzumab emtansine (TDM-1), which resulted in substantial clinical improvement. To our knowledge, the R3CE platform is the first 3D organoid system that does not require aggregation or 3D scaffold such as matrigel system. These advancements position the R3CE platform as a promising tool for personalized medicine, offering a rapid and accurate method for drug screening and therapeutic response prediction to guide clinical decision-making in cancer treatment. Citation Format: Wen-Hung Kuo, Yen-Jang Huang, Jia-Yang Chen, Yi-Chun Wu, Chia-Chun Chen, Mark D. Pegram, Ying-Chih Chang. Rapid and reproducible expansion of rare tumor cells: The R3CE platform for personalized medicine [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(7_Suppl):Abstract nr LB434.

Hybrid joints consisting of pre-tensioned bolts and a bonded connection—The influence of adhesives on the load-bearing capacity

This study explores the intricate mechanics of hybrid joints, which combine prestressed bolts and adhesive bonding, with a focus on increasing the joint capacity of steel structures. Despite their potential, the fundamental behaviour of these joints is not fully understood. The research focuses on unravelling the load-bearing capacity of these hybrid joints, emphasising the influence of the adhesive properties. The unique manufacturing process, involving the pre-tensioning of bolts while the adhesive is uncured, introduces additional dependencies not present in conventional adhesive joints. Analysis of the mechanical and physical properties of five adhesives provides key insights into the mechanics of load transfer and failure modes in hybrid joints, providing a comprehensive understanding. The study shows that load transfer occurs through micron-thin adhesive layers, highlighting the significant influence of adhesive properties on joint performance. Epoxies emerge as the top performers, with 2.5 times the average friction joint and more than five times the average bonded joint capacity, indicating their superiority in hybrid joint applications. Hybrid joints show significantly less variation than adhesive and friction joints, underlining their consistency and reliability in structural applications. When comparing hybrid and bonded joints with the same adhesive (SW7240), the variance was suppressed to one seventh by the application of preloaded bolts, with practical implications for design values based on quantiles. The study establishes correlations between joint strength and adhesive properties, emphasising the critical role of Young's modulus and tensile strength. It also finds that the elongation of hybrid joints at break is almost entirely dependent on load capacity, with viscosity having a lesser effect. Fracture surface investigations provide insight into the failure modes of hybrid joints, highlighting differences from those observed in frictional or purely bonded joints. This comprehensive study, combining experimental campaigns and in-depth analysis, provides valuable insights into the intricate relationships between joint capacity and adhesive properties in hybrid joints. The findings guide the selection of appropriate adhesives and provide the basis for the development of accurate load prediction methods, unlocking the full potential of hybrid joints and overcoming the limitations of conventional joining techniques in steel structures. Further research is encouraged to investigate the influence of adhesive class, post-tensioning stability and the nuanced mechanics of load transfer in these innovative joints.

A modified CFD-DEM method for accurate prediction of the minimum fluidization velocity

Monodisperse fluidized bed experiments have been carried out on 13 kinds of particles with different particle sizes in a cylindrical fluidized bed. The accuracy of nine commonly used monodisperse drag models, including the Gidsapow, BVK, and Zhou–Fan models is verified. It is found that the Zhou–Fan model is the most accurate at low and moderate values of the particle Reynolds number. It is found that with the traditional computational fluid dynamics–discrete element method (CFD-DEM) method it is difficult to obtain an accurate minimum fluidization velocity owing to difficulty in obtaining an accurate value of the minimum fluidization solid volume fraction. A modified method is proposed to increase the accuracy of prediction of the minimum fluidized solid volume fraction by using a virtual particle size in the calculation of the particle collision process. The effectiveness of the modified method is verified by comparing the CFD-DEM simulation results with experimental results for Geldart-D particles. The relative error of the minimum fluidization velocity is found to be reduced from 24.6% to 2%.

Interpretable Cognitive Ability Prediction: A Comprehensive Gated Graph Transformer Framework for Analyzing Functional Brain Networks.

Graph convolutional deep learning has emerged as a promising method to explore the functional organization of the human brain in neuroscience research. This paper presents a novel framework that utilizes the gated graph transformer (GGT) model to predict individuals' cognitive ability based on functional connectivity (FC) derived from fMRI. Our framework incorporates prior spatial knowledge and uses a random-walk diffusion strategy that captures the intricate structural and functional relationships between different brain regions. Specifically, our approach employs learnable structural and positional encodings (LSPE) in conjunction with a gating mechanism to efficiently disentangle the learning of positional encoding (PE) and graph embeddings. Additionally, we utilize the attention mechanism to derive multi-view node feature embeddings and dynamically distribute propagation weights between each node and its neighbors, which facilitates the identification of significant biomarkers from functional brain networks and thus enhances the interpretability of the findings. To evaluate our proposed model in cognitive ability prediction, we conduct experiments on two large-scale brain imaging datasets: the Philadelphia Neurodevelopmental Cohort (PNC) and the Human Connectome Project (HCP). The results show that our approach not only outperforms existing methods in prediction accuracy but also provides superior explainability, which can be used to identify important FCs underlying cognitive behaviors.

An Ensemble of the Convolutional Neural Network Model with Fuzzy Fusion Rank Algorithm for the Identification of Parkinson’s Disease Using Magnetic Resonance Imaging Images

Abstract Background: Parkinson’s disease (PD) is a degenerative condition of the central nervous system primarily affecting the substantia nigra in the brain, resulting in the loss of dopamine-producing neurons and subsequent motor function deterioration. Early symptoms typically include hand tremors followed by bradykinesia, rigidity, postural instability, and decreased balance. Early diagnosis and proactive management are crucial for improving patients’ quality of life. Methods: In this study, an ensemble of deep learning (DL) models was developed to predict PD using DaTscan images. Initially, DL models (VGG16, ResNet50, Inception-V3 were utilized to classify PD in its early stage. Subsequently, to enhance the overall performance of the classification model, an ensemble strategy based on the fuzzy fusion rank algorithm was employed. The Parkinson’s Progression Markers Initiative database served as the evaluation dataset for the proposed model. This may offer some insight into why certain involuntary symptoms of PD occur, such as fatigue, irregular blood pressure, diminished peristalsis, and unexpected decreases in blood pressure. The ensemble model demonstrated superior recognition accuracy, precision, sensitivity, specificity, and F1-score, achieving 98.45%, 98.84%, 98.84%, 97.67%, and 98.84%, respectively. Results: Compared to individual models, the ensemble model demonstrated superior recognition accuracy, precision, sensitivity, specificity, and F1-score, achieving 98.92%, 98.84%, 98.84%, 97.67%, and 98.84%, respectively. In addition, a publicly available graphical user interface (GUI)-based software program was developed, leveraging magnetic resonance imaging for efficient and accurate classification of PD and its subclasses. The method outperformed contemporary techniques in PD detection, offering significant potential for real-time disease identification. Conclusion: The establishment of a GUI-based software application can substantially aid in the timely detection of PD, facilitating proactive management and improving patient outcomes. The study underscores the importance of leveraging advanced DL techniques and ensemble methods for accurate and efficient disease prediction. Moreover, the development of user-friendly software tools holds promise for widespread adoption and enhanced patient care in the field of PD diagnosis and management.

Development of Machine Learning Methods for Accurate Prediction of Plant Disease Resistance

The traditional method of screening plants for disease resistance phenotype is both time-consuming and costly. Genomic selection offers a potential solution to improve efficiency, but accurately predicting plant disease resistance remains a challenge. In this study, we evaluated eight different machine learning (ML) methods, including random forest classification (RFC), support vector classifier (SVC), light gradient boosting machine (lightGBM), random forest classification plus kinship (RFC_K), support vector classification plus kinship (SVC_K), light gradient boosting machine plus kinship (lightGBM_K), deep neural network genomic prediction (DNNGP), and densely connected convolutional networks (DenseNet), for predicting plant disease resistance. Our results demonstrate that the three plus kinship (K) methods developed in this study achieved high prediction accuracy. Specifically, these methods achieved accuracies of up to 95% for rice blast (RB), 85% for rice black-streaked dwarf virus (RBSDV), and 85% for rice sheath blight (RSB) when trained and applied to the rice diversity panel I (RDPI). Furthermore, the plus K models performed well in predicting wheat blast (WB) and wheat stripe rust (WSR) diseases, with mean accuracies of up to 90% and 93%, respectively. To assess the generalizability of our models, we applied the trained plus K methods to predict RB disease resistance in an independent population, rice diversity panel II (RDPII). Concurrently, we evaluated the RB resistance of RDPII cultivars using spray inoculation. Comparing the predictions with the spray inoculation results, we found that the accuracy of the plus K methods reached 91%. These findings highlight the effectiveness of the plus K methods (RFC_K, SVC_K, and lightGBM_K) in accurately predicting plant disease resistance for RB, RBSDV, RSB, WB, and WSR. The methods developed in this study not only provide valuable strategies for predicting disease resistance, but also pave the way for using machine learning to streamline genome-based crop breeding.

Periodic analysis of scenic spot passenger flow based on combination neural network prediction model

Abstract To prevent in a short time the rapid increase of tourists and corresponding traffic restriction measures’ lack in scenic areas, this study established a prediction model based on an improved convolutional neural network (CNN) and long- and short-term memory (LSTM) combined neural network. The study used this to predict the inflow and outflow of tourists in scenic areas. The model uses a residual unit, batch normalization, and principal component analysis to improve the CNN. The experimental results show that the model works best when batches’ quantity is 10, neurons’ quantity in the LSTM layer is 50, and the number of iterations is 50 on a workday; on non-working days, it is best to choose 10, 100, or 50. Using root mean square error (RMSE), normalized root mean square error (NRMSE), mean absolute percentage error (MAPE), and mean absolute error (MAE) as evaluation indicators, the inflow and outflow RMSEs of this study model are 82.51 and 89.80, MAEs are 26.92 and 30.91, NRMSEs are 3.99 and 3.94, and MAPEs are 1.55 and 1.53. Among the various models, this research model possesses the best prediction function. This provides a more accurate prediction method for the prediction of visitors’ flow rate in scenic spots. Meanwhile, the research model is also conducive to making corresponding flow-limiting measures to protect the ecology of the scenic area.

Adaptive Meta-Learning Probabilistic Inference Framework for Long Sequence Prediction

Long sequence prediction has broad and significant application value in fields such as finance, wind power, and weather. However, the complex long-term dependencies of long sequence data and the potential domain shift problems limit the effectiveness of traditional models in practical scenarios. To this end, we propose an Adaptive Meta-Learning Probabilistic Inference Framework (AMPIF) based on sequence decomposition, which can effectively enhance the long sequence prediction ability of various basic models. Specifically, first, we decouple complex sequences into seasonal and trend components through a frequency domain decomposition module. Then, we design an adaptive meta-learning task construction strategy, which divides the seasonal and trend components into different tasks through a clustering-matching approach. Finally, we design a dual-stream amortized network (ST-DAN) to capture shared information between seasonal-trend tasks and use the support set to generate task-specific parameters for rapid generalization learning on the query set. We conducted extensive experiments on six datasets, including wind power and finance scenarios, and the results show that our method significantly outperforms baseline methods in prediction accuracy, interpretability, and algorithm stability and can effectively enhance the long sequence prediction capabilities of base models. The source code is publicly available at https://github.com/Zhu-JP/AMPIF.

A new LSTNet-based temperature prediction model for permanent magnet

Permanent magnet synchronous motors (PMSMs) can effectively protect against demagnetization by accurate permanent magnet (PM) temperature prediction; nevertheless, due to the nonlinear properties and intricate internal structure of PMSMs, accurate PM temperature prediction methods still encounter difficulties. This paper proposes a new PM temperature prediction model (LSTNet-Improved) based on long- and short-term time series network (LSTNet) to increase the prediction accuracy of PM temperature. By adding a multi-scale convolutional (MSC) layer to the convolutional neural network (CNN) layer of LSTNet, the short-term detail-dependent information between PMSM variables can be obtained by the model, and adds a CNN skip (CNN-skip) layer in place of the gate recurrent unite skip (GRU-skip) layer to find the long- and short-term local repetitive patterns between the variables, which yields additional feature information. Furthermore, a nonlinear bias term (MNB) is added to the original multi-head attention layer in order to solve the complex nonlinear relationship between multivariate time series. These layers are applied after the CNN-skip layer and gated recurrent unite (GRU) layers, respectively. This allows the model to become more robust and automatically learn to the complex nonlinear relationship between the sequences, focus on the important feature information, and lessen the impact of redundant information on the PMs’ temperature prediction task. The experimental results show that the goodness of fit (R2), root mean square error (RMSE) and mean absolute error (MAE) of the proposed model are 99.93%, 14.55% and 9.45%, respectively, and compared with LSTNet, the R2 is improved by 0.09%, the RMSE and MAE are reduced by 7.03% and 6.51%. These results confirm that the model can correctly predict the PM temperature, efficiently extract both long- and short-term patterns among the variables of the PMSM, and effectively focus on the key feature information in the intricate nonlinear series.

Optimizing Building Short-Term Load Forecasting: A Comparative Analysis of Machine Learning Models

The building sector, known for its high energy consumption, needs to reduce its energy use due to rising greenhouse gas emissions. To attain this goal, a projection for domestic energy usage is needed. This work optimizes short-term load forecasting (STLF) in the building sector while considering several variables (energy consumption/generation, weather information, etc.) that impact energy use. It performs a comparative analysis of various machine learning (ML) models based on different data resolutions and time steps ahead (15 min, 30 min, and 1 h with 4-step-, 2-step-, and 1-step-ahead, respectively) to identify the most accurate prediction method. Performance assessment showed that models like histogram gradient-boosting regression (HGBR), light gradient-boosting machine regression (LGBMR), extra trees regression (ETR), ridge regression (RR), Bayesian ridge regression (BRR), and categorical boosting regression (CBR) outperformed others, each for a specific resolution. Model performance was reported using R2, root mean square error (RMSE), coefficient of variation of RMSE (CVRMSE), normalized RMSE (NRMSE), mean absolute error (MAE), and execution time. The best overall model performance indicated that the resampled 1 h 1-step-ahead prediction was more accurate than the 15 min 4-step-ahead and the 30 min 2-step-ahead predictions. Findings reveal that data preparation is vital for the accuracy of prediction models and should be model-adjusted.

Optimizing serverless computing: A comparative analysis of multi-output regression models for predictive function invocations

In the rapidly evolving domain of serverless computing, the need for efficient and accurate predictive methods of function invocation becomes paramount. This study introduces a comprehensive suite of innovations to improve the predictability and efficiency of function invocation within serverless architectures. By employing multi-output regression models, we perform a multi-level analysis of function invocation patterns across user, application, and function levels, revealing insights into granular workload behaviors. We rigorously investigate the impact of windowing techniques and dimensionality reduction on model performance via Principal Component Analysis (PCA), offering a nuanced understanding of data complexities and computational implications. Our novel comparative analysis framework meticulously evaluates the performance of these methods against various windowing configurations, utilizing the Azure Functions dataset for real-world applicability. In addition, we assess the temporal stability of the models and the variation of day-to-day performance, providing a holistic view of their operational viability. Our contributions address critical gaps in the predictive modeling of serverless computing and set a new benchmark for operational efficiency and data-driven decision-making in cloud environments. This study is poised to guide future advancements in serverless computing, driving theoretically sound and practically viable innovations.

ANALISIS PERBANDINGAN METODE ARIMA DAN LEAST SQUARE UNTUK PREDIKSI HARGA EMAS : PENDEKATAN PROBABILISTIK DAN STATISTIK

Gold, a precious metal renowned for its value in various sectors, including investment and jewelry, is often considered a secure asset within investment portfolios. However, its prices exhibit high volatility influenced by economic, geopolitical, and global financial factors. Previous research has focused on predictive methods to anticipate gold price movements. In recent years, heightened complexity and uncertainty, exacerbated by global factors such as economic shifts and the Covid-19 pandemic, emphasizes the urgency of accurate gold price predictions. This study comprehensively analyzes and compares the performance of Autoregressive Integrated Moving Average (ARIMA) and Ordinary Least Squares (OLS) in forecasting gold prices, utilizing statistical and probabilistic approaches. ARIMA excels in handling time series data, identifying complex patterns, and forecasting price changes based on historical trends. Conversely, OLS, a probabilistic method, stands out in adjusting linear models to gold price data, providing detailed insights into influencing factors. The research employs a 5-year gold price dataset (2018-2023) and evaluates the models' performance using Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE). Results indicate OLS outperforms ARIMA, with lower MSE (45.79 vs. 284.83) and MAPE (0.0026 vs. 0.0066). This study contributes nuanced insights for market participants, investors, and researchers to comprehend commodity market behaviour, particularly in gold, emphasizing the importance of accurate prediction methods in strategic decision-making.

A novel method for accurate pressure drop prediction in horizontal and near horizontal pipes using adaptive neuro fuzzy inference system based model

Effective flow line and piping network design depends on the accurate prediction of pressure drop in multiphase flow for horizontal and near horizontal pipes. Since early 1950, several empirical correlations and mechanistic models have been developed to predict pressure drop. All correlations used by the industry, in addition to their applicability limitations, fall short of providing the necessary precision of pressure drop predictions. However, compared to empirical correlations, the recently developed mechanistic models improved pressure drop prediction. To design and construct more dependable and economical surface piping networks and wells, it is still necessary to improve prediction accuracy. This study uses the Adaptive Neuro-Fuzzy Inference System (ANFIS) to create a model that predicts pressure drop in horizontal and near-horizontal pipelines with greater accuracy and simplicity. Using the ANFIS method, the fuzzy modelling procedure can gather knowledge about a set of data to determine the membership function parameters that will enable the associated fuzzy inference system to track input/output data most effectively. The model was created and tested using field data encompassing various variables. The model was developed using 450 different data sets that were collected from the Asian continent. 113 data sets were used for testing, and a total of 337 data sets were used for training. Trend analysis was carried out during the model development phase prior to the model’s completion. This is performed to make sure the model is stable and to make sure the created model is physically sound and accurately simulates the real physical process. To determine the percentage of error between the predicted value and the actual measured data, statistical analysis was carried out. To compare the performance of the new ANFIS model to earlier empirical correlations and mechanistic models, graphical and statistical techniques were also used. The new model outperformed known correlations and the most recent mechanistic models by a significant margin in producing incredibly accurate pressure drop predictions. The Dukler et al. empirical correlation, Beggs and Brill empirical correlation, Xiao mechanistic model, and Gomez mechanistic model had values of 25.284, 20.940, 30.122, and 20.817, respectively, while the ANFIS model had a value of 13.256 for the lowest average absolute percentage error. Additionally, the Duckler and Beggs & Brill models came in second and third, with values of 0.908 and 0.906, respectively, and the ANFIS model had the highest coefficient of determination at 0.955.

Evaluating Machine Learning Stability in Predicting Depression and Anxiety Amidst Subjective Response Errors.

Major Depressive Disorder (MDD) and Generalized Anxiety Disorder (GAD) pose significant burdens on individuals and society, necessitating accurate prediction methods. Machine learning (ML) algorithms utilizing electronic health records and survey data offer promising tools for forecasting these conditions. However, potential bias and inaccuracies inherent in subjective survey responses can undermine the precision of such predictions. This research investigates the reliability of five prominent ML algorithms-a Convolutional Neural Network (CNN), Random Forest, XGBoost, Logistic Regression, and Naive Bayes-in predicting MDD and GAD. A dataset rich in biomedical, demographic, and self-reported survey information is used to assess the algorithms' performance under different levels of subjective response inaccuracies. These inaccuracies simulate scenarios with potential memory recall bias and subjective interpretations. While all algorithms demonstrate commendable accuracy with high-quality survey data, their performance diverges significantly when encountering erroneous or biased responses. Notably, the CNN exhibits superior resilience in this context, maintaining performance and even achieving enhanced accuracy, Cohen's kappa score, and positive precision for both MDD and GAD. This highlights the CNN's superior ability to handle data unreliability, making it a potentially advantageous choice for predicting mental health conditions based on self-reported data. These findings underscore the critical importance of algorithmic resilience in mental health prediction, particularly when relying on subjective data. They emphasize the need for careful algorithm selection in such contexts, with the CNN emerging as a promising candidate due to its robustness and improved performance under data uncertainties.

Multi-scale feature fusion for prediction of IDH1 mutations in glioma histopathological images

Background and objectiveMutations in isocitrate dehydrogenase 1 (IDH1) play a crucial role in the prognosis, diagnosis, and treatment of gliomas. However, current methods for determining its mutation status, such as immunohistochemistry and gene sequencing, are difficult to implement widely in routine clinical diagnosis. Recent studies have shown that using deep learning methods based on pathological images of glioma can predict the mutation status of the IDH1 gene. However, our research focuses on utilizing multi-scale information in pathological images to improve the accuracy of predicting IDH1 gene mutations, thereby providing an accurate and cost-effective prediction method for routine clinical diagnosis. MethodsIn this paper, we propose a multi-scale fusion gene identification network (MultiGeneNet). The network first uses two feature extractors to obtain feature maps at different scale images, and then by employing a bilinear pooling layer based on Hadamard product to realize the fusion of multi-scale features. Through fully exploiting the complementarity among features at different scales, we are able to obtain a more comprehensive and rich representation of multi-scale features. ResultsBased on the Hematoxylin and Eosin stained pathological section dataset of 296 patients, our method achieved an accuracy of 83.575 % and an AUC of 0.886, thus significantly outperforming other single-scale methods. ConclusionsOur method can be deployed in medical aid systems at very low cost, serving as a diagnostic or prognostic tool for glioma patients in medically underserved areas.

Assessing the complementary information from an increased number of biologically relevant features in liquid biopsy-derived RNA-Seq data

Liquid biopsy-derived RNA sequencing (lbRNA-seq) exhibits significant promise for clinic-oriented cancer diagnostics due to its non-invasiveness and ease of repeatability. Despite substantial advancements, obstacles like technical artefacts and process standardisation impede seamless clinical integration. Alongside addressing technical aspects such as normalising fluctuating low-input material and establishing a standardised clinical workflow, the lack of result validation using independent datasets remains a critical factor contributing to the often low reproducibility of liquid biopsy-detected biomarkers.Considering the outlined drawbacks, our objective was to establish a workflow/methodology characterised by: 1. Harness the rich diversity of biological features accessible through lbRNA-seq data, encompassing a holistic range of molecular and functional attributes. These components are seamlessly integrated via a Machine Learning-based Ensemble Classification framework, enabling a unified and comprehensive analysis of the intricate information encoded within the data. 2. Implementing and rigorously benchmarking intra-sample normalisation methods to heighten their relevance within clinical settings. 3. Thoroughly assessing its efficacy across independent test sets to ascertain its robustness and potential utility.Using ten datasets from several studies comprising three different sources of biological material, we first show that while the best-performing normalisation methods depend strongly on the dataset and coupled Machine Learning method, the rather simple Counts Per Million method is generally very robust, showing comparable performance to cross-sample methods. Subsequently, we demonstrate that the innovative biofeature types introduced in this study, such as the Fraction of Canonical Transcript, harbour complementary information. Consequently, their inclusion consistently enhances prediction power compared to models relying solely on gene expression-based biofeatures. Finally, we demonstrate that the workflow is robust on completely independent datasets, generally from different labs and/or different protocols. Taken together, the workflow presented here outperforms generally employed methods in prediction accuracy and may hold potential for clinical diagnostics application due to its specific design.

Environmental Prediction Model of Solar Greenhouse Based on Improved Harris Hawks Optimization-CatBoost

Solar greenhouses provide a favorable climate environment for the production of counter-seasonal crops in northern China. The greenhouse environment is a key factor affecting crop growth, so accurate prediction of greenhouse environment changes helps to precisely regulate the crop growth environment and helps to promote the growth of fruits and vegetables. In this study, an environmental prediction model based on the combination of a gradient boosting tree and the Harris hawk optimization algorithm (IHHO-Catboost) is constructed, and in response to the problems of the HHO algorithm, such as the fact that the adjustment of the search process is not flexible enough, it cannot be targeted to carry out a stage search, and sometimes it will fall into the local optimum to make the algorithm’s search accuracy relatively poor, an algorithm based on the improved Harris hawk optimization (IHHO) algorithm-based parameter identification method is constructed. The model considers the internal and external environmental and regulatory factors affecting crop growth, which include indoor temperature and humidity, light intensity, carbon dioxide concentration, soil temperature and humidity, outdoor temperature and humidity, light intensity, carbon dioxide concentration, wind direction, wind speed, and opening and closing of upper and lower air openings of the cotton quilt, and is input into a prediction model with a time series for training and testing. The experimental results show that the MAE (mean absolute error) values of temperature, relative humidity, carbon dioxide concentration, and light intensity of the model are reduced to 49.8%, 35.3%, 72.7%, and 32.1%, respectively, compared with LSTM (Long Short-Term Memory), which is a significant decrease in error. It shows that the proposed multi-parameter prediction model for solar greenhouse environments presents an effective method for accurate prediction of environmental data in solar greenhouses. The model not only improves prediction accuracy but also reduces dependence on large data volumes, reduces computational costs, and improves the transparency and interpretability of the model. Through this approach, an effective tool for greenhouse agriculture is provided to help farmers optimize the use of resources, reduce waste, and improve crop yield and quality, ultimately leading to a more efficient and environmentally friendly agricultural production system.

Enhanced PV Power Prediction Considering PM10 Parameter by Hybrid JAYA-ANN Model

The demand for electrical energy is continuously increasing in these days, particularly due to advancements in the industrial sector. This surge in demand has underscored the importance of seeking alternative energy sources, with solar energy emerging as a standout option due to its low investment costs and environmental friendliness. However, the variability in photovoltaic power production, influenced by meteorological data, necessitates accurate prediction methods. To enhance the precision of these predictions, incorporating new parameters alongside existing meteorological data is advantageous. In this regard, this study explores the impact of the particulate matter (PM10) parameter on photovoltaic power prediction using artificial neural network (ANN) model and JAYA-ANN. Comparing the prediction results based on root mean squared and mean absolute percentage errors reveals that the hybrid JAYA-ANN model consistently outperforms the ANN and persistence models. Notably, the PM10 parameter proves to be a significant input in forecasting daily photovoltaic power.

Data Cleansing and Sub-Unit-Based Molecular Description Enable Accurate Prediction of The Energy Levels of Non-Fullerene Acceptors Used in Organic Solar Cells.

Non-fullerene acceptors (NFAs) have recently emerged as pivotal materials for enhancing the efficiency of organic solar cells (OSCs). To further advance OSC efficiency, precise control over the energy levels of NFAs is imperative, necessitating the development of a robust computational method for accurate energy level predictions. Unfortunately, conventional computational techniques often yield relatively large errors, typically ranging from 0.2 to 0.5 electronvolts (eV), when predicting energy levels. In this study, the authors present a novel method that not only expedites energy level predictions but also significantly improves accuracy , reducing the error margin to 0.06eV. The method comprises two essential components. The first component involves data cleansing, which systematically eliminates problematic experimental data and thereby minimizes input data errors. The second component introduces a molecular description method based on the electronic properties of the sub-units comprising NFAs. The approach simplifies the intricacies of molecular computation and demonstrates markedly enhanced prediction performance compared to the conventional density functional theory (DFT) method. Ourmethodology will expedite research in the field of NFAs, serving as a catalyst for the development of similar computational approaches to address challenges in other areas of material science and molecular research.

Deep Transfer Learning Based on LSTM Model for Reservoir Flood Forecasting

In recent years, deep learning has been widely used as an efficient prediction algorithm. However, this algorithm has strict requirements on the size of training samples. If there are not enough samples to train the network, it is difficult to achieve the desired effect. In view of the lack of training samples, this article proposes a deep learning prediction model integrating migration learning and applies it to flood forecasting. The model uses random forest algorithm to extract the flood characteristics, and then uses the transfer learning strategy to fine-tune the parameters of the model based on the model trained with similar reservoir data; and is used for the target reservoir flood prediction. Based on the calculation results, an autoregressive algorithm is used to intelligently correct the error of the prediction results. A series of experimental results show that our proposed method is significantly superior to other classical methods in prediction accuracy.