Integrated Learning Method Research Articles

Research on energy consumption analysis of air conditioning and refrigeration equipment based on perceptron model

Abstract This paper mainly studies the energy consumption of air conditioning and refrigeration system from the perspective of the dynamic operation of air conditioning systems and selects the energy consumption of a chiller system, cooling tower system, chilled water pump system and fan coil system, which affect the energy consumption of air conditioning system, as model variables. An integrated learning method based on a multilayer perceptron is proposed to integrate spatial features with temporal features, and a spatio-temporal prediction model for air conditioning energy consumption analysis is established under the Seq2Seq framework, and then the input curves of the four variables with load change under the optimal operation of the air conditioning system under dynamic load are derived. The results show that the deviation between the simulated value and the measured, calculated value of the energy consumption analysis model of air conditioning and refrigeration equipment based on the multilayer perceptron is within 5%, which can effectively and accurately predict and reduce air conditioning energy consumption by 15% to 20%. The maximum energy-saving efficiency can reach 30% when the air conditioning system is in optimal operation under dynamic load, and the energy-saving effect of the chiller, chilled water pump and cooling water pump is relatively significant. The research results of this paper have a certain reference value for reducing the energy consumption of air conditioning systems in practice.

ECOC-based integrated learning method for fault diagnosis in nuclear power plants

Abstract The fault diagnosis system of nuclear power plants plays an important role in ensuring the safety and economy of nuclear power plant operations. This paper first analyzes typical faults of nuclear power plants and their phenomena, and fault samples are obtained. A comprehensive study of the structure of the nuclear power plant system, its working mode and the association between each subsystem is carried out to analyze the monitoring parameters and fault characteristics and establish the fault data set. Secondly, an IFWA (Improved Fireworks Algorithm - Integrated Learning) algorithm is proposed to assess the severity of faults in the first circuit of a nuclear power plant. Finally, the fault diagnosis module is divided into three units according to the functional logic, i.e., condition monitoring unit, fault identification unit, and fault severity assessment unit. The results show that the diagnostic accuracy of the IFWA algorithm is 94.25% for SGTR in the single-fault diagnosis experiment and 96.25% for SGTR-LOCA in the multiple-fault diagnosis experiment. It shows that the IFWA algorithm proposed in this paper has the optimal performance capability when applied to nuclear power plant fault diagnosis and effectively assists managers in diagnosing faults and giving maintenance recommendations.

Study of Sailboat Price Forecasting Based on Random Forest Regression

This paper aims to solve the problem of predicting the listing price of sailboats, using random forest, decision tree and integrated learning methods for analysis. First, data cleaning is performed to remove missing data. Then, the data are analyzed to find that the make, model, size, time and regional factors of sailboats may affect their listing prices. In terms of regional characteristics, annual income per capita was extracted as one of the influencing factors. Using all available characteristics, regression trees and random forest regression models were built and R2 was used as an evaluation criterion for model prediction accuracy. Finally, the R2 value of the monohull sailboat listing price prediction model was calculated to be 0.84, and the R2value of the catamaran listing price prediction model was 0.99.In addition, this paper also involves the exploration of other features. Ultimately, this paper provides an estimate of the listed price per sailboat and discusses the issue of estimation accuracy.

An improved integration strategy for prediction of shear wave velocity using petrophysical logs: Integration of spatiotemporal and small sample nonlinear feature

Shear wave velocity (Vs) plays an important role in seismic data inversion and accurately determining petrophysical parameters. However, owing to the high acquisition cost of S-wave logging, Vs-related data cannot be obtained from all wells, especially the older ones. Therefore, developing an efficient and fast intelligent prediction method for Vs using existing petrophysical logging data is necessary. Owing to the advantages of conventional machine learning (CML) and deep learning (DL) methods, this study developed a data-driven integrated learning (IL) method for Vs prediction, which uses sensitive logging data as input, builds multiple sample sets, analyzes the performance differences of the CML and DL methods for predicting Vs in each dataset, and optimizes the support vector machine (SVM) in the CML method and convolutional neural network-long short-term memory (CNN-LSTM) in the DL method to construct an integrated CNN-LSTM-SVM neural network (ICLSNN). The spatiotemporal feature extraction capability of CNN-LSTM was used to effectively extract the deposition information of the formation from the logging data, and the small sample nonlinear feature extraction capability of SVM was used to alleviate the limitations of overfitting in DL for data-driven intelligent Vs prediction. The ICLSNN showed a higher Vs prediction accuracy than SVM or CNN-LSTM alone. The Vs prediction results of the single well in the discovery without training were better than those of the other IL and empirical models, proving the strong generalization applicability of the proposed model. This method compensates for the limitations of individual machine learning or DL models for Vs prediction and provides a novel research idea. The effective implementation of this scheme will facilitate the efficient prediction of Vs in areas with few wells.

IoT Device Identification Method Based on Causal Inference

With the development of 5G, the number of IoT (Internet of Things) devices connected to the Internet will grow explosively. However, due to the vulnerability of the devices, attackers can launch attacks on the vulnerable IoT devices, causing great impact on the security of the network environment. Fine-grained identification of IoT devices can help network administrators set up appropriate security policies based on the functionality and heterogeneity of the devices, while enabling timely updates and upgrades for devices with security vulnerabilities or the isolation of these dangerous devices. However, most of the existing IoT device identification methods rely on a priori knowledge or expert experience in selecting features, which cannot weigh the identification performance and labor cost. In this paper, we design a fine-grained identification method for IoT devices based on causal inference, which automatically extracts key features in the protocol fields of device communication from the perspective of causality and then classifies key features using a Stacking integrated learning method to achieve high-precision and fine-grained device identification. Through experimental verification, the proposed method achieves 96.3% and 97.7% device model identification accuracy under HTTP/TCP and SSH/TCP protocol clusters.

The implementation of listening and speaking learning using the integrated learning method in the faculty of language and culture UNTAG Semarang

ABSTRACT Teaching listening and speaking can be done by listening to audio, then assigning students to retell English. The author believes that listening teaching methods can be combined with speaking or other basic skills. This research reveals the application of listening and speaking teaching using the Integrated Learning method at the Faculty of Language and Culture, Semarang University, on August 17, 1945, and the obstacles faced in its application. The aim is to implement the integration of this method effectively, and in the future, it can be a reference for curriculum renewal according to the community's wishes. This research uses a research and development (R&D) design. Researchers collected data using listening tests and recordings of students' English speaking while listening to materials or tests. After that, the researcher conducted interviews with students as input for the application of this integration. The recordings were then transcribed and analyzed using a qualitative description. From the discussion, most of the students agreed with the application of integration, but a small number disagreed. From the experiment, the method of teaching the listening test combined with the English/speaking assignment in the first semester can be integrated or blended. The result will be that students' speaking abilities will be better and more effective because only 3 out of 20 students will answer only a few sentences that do not represent the content of the test. Two students answered in Bahasa Indonesia. Most of the others responded well.

A survey of face recognition based on machine learning

Face recognition technology based on machine learning methods is the most popular nowadays. This research, based on existing literature and data, was mainly focused on the face recognition system. The paper is written on the basis of existing face detection methods. Then, according to the difference in feature information, five methods were used to extract face features to apply them to face recognition. Then, this paper focused on two kinds of neural networks: support vector machines (SVM) and integrated learning methods, especially the Adaboost algorithm. Finally, the hidden danger of privacy disclosure was specially discussed. The results showed that the main direction of future research should be to expand the functional dimension and promote more applications to the public on the basis of ensuring the real-time and accuracy of the system.

Pengaruh Metode Pembelajaran Cooperative Integretet Reading And Composition Terhadap Peningkatan Reasoning Ability Pembelajaran Fiqih Pada Siswa Kelas VIII MTs YASPEND Muslim Pematang Tengah Kec. Tanjung Pura


 
 
 
 The background of this research is that based on the identification carried out by the researchers at the research location, namely: The learning that has been carried out so far in class VIII of MTs Yaspend Muslim specifically for Fiqh subjects does not emphasize learning by providing direct learning experiences through the development of process skills, scientific attitudes and lack of developing reasoning. This causes the low reasoning ability of students. The objectives of this research are: To determine the effect of the cooperative learning method integretet reading and composition on increasing reasoning in learning fiqh students in class VIII MTs Yaspend Muslim. The type of research used in this study is a quantitative research method. In this study the form of the instrument used is in the form of a questionnaire using a Likert scale attitude that has been modified with the following assessments: often scores 3, Rarely scores 2, and Never scores 1. The results of this study are: The results of hypothesis testing are also carried out independently. partial with the significance or the effect of the independent variable on the dependent variable that, the tcount (partial) for the cooperative integret reading and composition learning method is 2,672 with a significance level of 0.01, the cooperative integrete reading and composition learning method variable has a positive and significant effect on increasing reasoning Students with a value of tcount (2.672) > ttable (2.021) and a significant value (0.01) <0.05 indicates that the cooperative integretet reading and composition learning method has a positive and significant effect on the improvement of students' reasoning. This can be seen with a significant value of 0.01 which is smaller than = 0.05. The cooperative integret reading and composition learning method will be able to improve students' reasoning because the better and better the cooperative integrete reading and composition learning method made by the teacher, students will get an increase in affective, cognitive, and psychomotor aspects in the classroom. Students will also look more active and critical, this is what causes the positive effect of the cooperative integrated reading and composition learning method on the improvement of students' reasoning.
 
 
 

Estimation of Pb and Cd Content in Soil Using Sentinel-2A Multispectral Images Based on Ensemble Learning

With the increasing economic growth in developing nations, soil heavy metal pollution has become a growing concern. Monitoring the heavy metal concentration in soil through remote sensing is crucial for safeguarding the ecological environment. However, the current indoor spectral measurement method has limitations, such as the discrete soil sampling space and weak spectral characteristics of soil heavy metals, leading to a poor robustness of remote sensing inversion models. This study presents a novel approach to address these challenges by incorporating a spatial feature of pollution sources and sinks to evaluate the spatial factors affecting pollutant diffusion and concentration. An integrated learning model, combining spatial and spectral information, is developed to estimate heavy metal content in soil using Sentinel-2A satellite data. A total of 235 soil samples were collected in Jiyuan, China, and the effective spectral transformation characteristics of Sentinel-2A data were screened. The impact of spectral characteristics, topographic characteristics, and spatial characteristics on retrieving soil heavy metal lead (Pb) and cadmium (Cd) content were analyzed. The optimal inversion method was determined through various integrated learning models, and the spatial distribution of heavy metals Pb and Cd was mapped. The results indicate that the accuracy of the inversion model was significantly improved by incorporating terrain features and spatial features of pollution sources. The Blending integrated learning method showed a 65.9% and 73.2% reduction in the RMSE of Pb and Cd, respectively, compared to other regression models. With R2 values of 0.9486 and 0.9489 for Pb and Cd, respectively, and a MAPE less than 0.2, the Blending model demonstrated high prediction accuracy.

Research on the impact of underground excavation metro on surface traffic safety and assessment method

ABSTRACT This study focuses on a problem that has been seriously troubled urban traffic managers: the impact of underground excavation metros on surface traffic safety during construction. In underground construction, surface subsidence and road collapse due to concealed underground construction constantly occur, resulting in casualties property damage and seriously impairing normal urban road traffic. Urban road managers urgently need a quick, objective, and easy-to-use method for the early warning and prevention of such risks. Therefore, this study collates relevant accident cases that have occurred in China over the last 20 years and summarises the impact mechanisms of concealed underground works affecting surface road traffic capacity through a detailed study of natural factors, engineering geology, types of structures, and types of workmanship. Two indices, Rank() and , are proposed to describe the impact of concealed underground works on surface traffic capacity, while an early warning method based on data on the impact of urban road capacity by concealed underground works is established using integrated learning methods and is well applied in practical projects. The results of this study are important for helping city managers quickly assess urban road traffic risks.

Collaboration Based Clinical Learning Model For Ners Professional Education Students At RSUP M.Djamil Padang

Clinical learning is an educational process that must be passed by undergraduate nursing students at the nursing professional education level, with a study period of 2 semesters, by applying a collaboration-based clinical learning model, but in reality students experience obstacles in achieving learning objectives, resulting in low learning outcomes in clinic. This research is intended to apply the Collaboration-based Clinical Learning Model to Nursing Education students. This research method uses pre-experimental research conducted in the Surgery Room of M.Djamil Hospital, Padang. The samples in this study were selected purposively. Respondents included 12 students who took the Medical Surgical Nursing course for 8 effective weeks. The research data was collected through participatory observation and distributing questionnaires. Data were analyzed using descriptive analysis and dependent T-test. The results of this study indicate that the learning methods applied include: conferences twice a week, clinical tutorials conducted twice for 8 weeks, teaching actions and bedside observations once a week, client care, resumes, and case seminars conducted once for 8 weeks. Among the methods that scored high were: conference 54.5%, BST 54.5%, tutorial clinic 45.4%, client care 72.7%, and case seminar 45.5%. The results of the T-test showed a significant effect of collaboration-based integrated clinical learning methods on learning methods (p=0.006; correlation 43.2%). Discussion of Collaboration-based clinical learning models for Nursing students to be able to apply learning methods that enable students to achieve maximum learning competence. Therefore, this model needs to be continuously developed to help improve optimal learning according to each competency level.

Protein Interaction Prediction Method Based on Feature Engineering and XGBoost

Human protein interaction prediction studies occupy an important place in systems biology. The understanding of human protein interaction networks and interactome will provide important insights into the regulation of developmental, physiological and pathological processes. In this study, we propose a method based on feature engineering and integrated learning algorithms to construct protein interaction prediction models. Principal Component Analysis (PCA) and Locally Linear Embedding (LLE) dimensionality reduction methods were used to extract sequence features from the 174-dimensional human protein sequence vector after Normalized Difference Sequence Feature (NDSF) encoding, respectively. The classification performance of three integrated learning methods (AdaBoost, Extratrees, XGBoost) applied to PCA and LLE features was compared, and the best combination of parameters was found using cross-validation and grid search methods. The results show that the classification accuracy is significantly higher when using the linear dimensionality reduction method PCA than the nonlinear dimensionality reduction method LLE. the classification with XGBoost achieves a model accuracy of 99.2%, which is the best performance among all models. This study suggests that NDSF combined with PCA and XGBoost may be an effective strategy for classifying different human protein interactions.

Redshift Estimation of SDSS Photometric Data Based on AutoGluon-Mix

Redshift is an important parameter of galaxies, and the use of photometry data for redshift estimation has always been a focus in the field of astronomy. This study explores a redshift estimation method for SDSS photometric data based on the AutoGluonMix algorithm, in which the integrated learning methods, including K-nearest neighbors, random forests, XGBoosted trees, LightGBM boosted trees, CatBoost boosted trees, Extremely Randomized Trees, and neural networks, improve the accuracy of redshift estimation through comprehensive strategies. The experimental results show that AutoGluon-Mix performs extremely well compared to other algorithms for both early and late type galaxies.

LightingNet: An Integrated Learning Method for Low-Light Image Enhancement

Images captured in low-light environments suffer from serious degradation due to insufficient light, leading to the performance decline of industrial and civilian devices. To address the problems of noise, chromatic aberration, and detail distortion for enhancing low-light images using existing enhancement methods, this paper proposes an integrated learning approach (LightingNet) for low-light image enhancement. The LightingNet consists of two core components: 1) the complementary learning sub-network and 2) the vision transformer (VIT) low-light enhancement sub-network. VIT low-light enhancement sub-network is designed to learn and fit the current data to provide local high-level features through a full-scale architecture, and the complementary learning sub-network is utilized to provide global fine-tuned features through learning transfer. Extensive experiments confirm the effectiveness of the proposed LightingNet.

Quantitative Estimation of Fe-Based Amorphous Coating Thickness Based on Pulsed Eddy Current Technology

Fe-based amorphous coatings prepared by high-velocity oxy-fuel (HVOF) spraying have the advantages of good mechanical properties, high density, low porosity, and high amorphous content. The service life and bonding strength of coating greatly depend on its thickness; however, the characterization of ferromagnetic coating thickness is a very difficult problem. Pulsed eddy current (PEC) is characterized by abundant signals in frequency domains. In this paper, the thickness measurement principle of ferromagnetic coating was explored, and the typical and entropy features from PEC signals were extracted. Seven integrated learning methods were combined to quantitatively characterize the coating thickness, namely ridge regression (RR), lasso regression (LR), random forest regression (RFR), extra trees regression (ETR), gradient boosting tree regression (GBTR), addaptive boost regression (ABR) and eXtreme Gradient Boosting Regression (XGBR) algorithms. By comparing typical features with new ones, it was verified that the effective combination of entropy features and typical features could be used as effective feature parameters of eddy current signal. Statistical scores (RMSE and R2) and GridsearchCV features were used to evaluate and optimize the established model. As indicated by the results, the proposed XGBR machine learning model well predicted the coating thickness, and the relative error less than 0.05 mm.

Repurchase Prediction of Community Group Purchase Users Based on Stacking Integrated Learning

Recently, fewer scholars consider the prediction of repeat purchases in new retail models. Based on the real data of community group buying enterprises, this paper will study the prediction of community group buying users' repurchase behavior. Firstly, this paper carries out feature engineering according to the characteristics of the community groups buying industry. Finally, 313 features are extracted from the user dimension, head dimension, and business personnel dimension, respectively. Then, based on the heterogeneous integrated learning method stacking, three two-tier fusion models with the same primary learners but different secondary learners are constructed. Two homogeneous ensemble learning models, random forest and lightgbm, and the traditional single machine learning model are introduced for comparative experiments. Experiments show that the fusion model based on ensemble learning method has better prediction performance than a single model. Among the fusion models, the stacking two-layer fusion model with neural network model as secondary learner is the best.

Transfer Learning of Individualized Treatment Rules from Experimental to Real-World Data

Individualized treatment effect lies at the heart of precision medicine. Interpretable individualized treatment rules (ITRs) are desirable for clinicians or policymakers due to their intuitive appeal and transparency. The gold-standard approach to estimating the ITRs is randomized experiments, where subjects are randomized to different treatment groups and the confounding bias is minimized to the extent possible. However, experimental studies are limited in external validity because of their selection restrictions, and therefore the underlying study population is not representative of the target real-world population. Conventional learning methods of optimal interpretable ITRs for a target population based only on experimental data are biased. On the other hand, real-world data (RWD) are becoming popular and provide a representative sample of the target population. To learn the generalizable optimal interpretable ITRs, we propose an integrative transfer learning method based on weighting schemes to calibrate the covariate distribution of the experiment to that of the RWD. Theoretically, we establish the risk consistency for the proposed ITR estimator. Empirically, we evaluate the finite-sample performance of the transfer learner through simulations and apply it to a real data application of a job training program. Supplementary materials for this article are available online.

Promoting language development in physically disabled adults through sports: The content and language integrated learning method

This study reports on the outcomes of a qualitative study which explores the perceptions of ten wheelchair basketball players of the implementation of a content and language integrated learning (CLIL) program. The participants were all members of the official wheelchair basketball team of the Sports Federation for the Disabled in North Cyprus. They were all young adults (18-35 years old) and their level of English language proficiency ranged from elementary to beginner. After a 4-month CLIL intervention period, the data were elicited through individual interviews from the participants. A qualitative analysis of the textual data revealed the themes such as improved self-image, high motivation, developed social skills, and better speaking skills in the target language. The results have a few practical implications for English such as foreign language teachers, sports coaches, and local disability committees.

Logistics Finance Collaborative Development Model Based on Machine Learning.

In the context of rapid social development, a logistics financial model that can meet the financing needs of small and medium-sized enterprises and has high returns is widely used in all aspects of the logistics financial industry. Logistics finance is a new financing model that can effectively integrate logistics enterprises, financial companies, and financing institutions to achieve mutual benefit and win-win results. The uncertainty of financial information, the motivation of each business service object to pursue high returns in a short period of time, and the inadequate risk preuniversal conditions have led to credit risks in the development of logistics financial services. Promoting the close integration of improved neural network algorithms based on machine learning and logistics financial financing models is inseparable from the active cooperation of all aspects, the trust of various business service objects, and the construction of logistics financial information platforms. Based on machine learning, this paper analyzes and models the collaborative development of logistics finance, analyzes the original data, and constructs sample characteristics. Due to the small amount of information in part of the sample features, this causes problems such as overfitting in the process of model building. Therefore, we designed a new feature selection based on Pearson correlation coefficient and PCA. Method. Using this algorithm for feature selection, an integrated learning method is proposed. In order to solve the shortcomings of traditional neural network logistics algorithms, a neural network-based noncomplete vehicle path optimization mining model is proposed. By weighting the time domain length and spatial probability of logistics finance, the stable state of the neural network is restricted. Simulation results show that this method can effectively improve logistics efficiency and maximize the economic value of the transportation process.

Activity prediction of anti-cancer drug candidate ER<bold>α</bold> inhibitor

Breast cancer is the most common malignancy which threats the women's health worldwide. Studies have revealed that the estrogen receptor alpha subtype (ERα) plays an important role in breast development and is considered as an important target for breast cancer treatment. Compounds that can antagonize ERα activity may be candidates for breast cancer treatment. A quantitative structure-activity relationship prediction model is proposed to predict the bioactivity of compounds that can be applied to anti-breast cancer drugs under small samples and multi-characteristic conditions. First, the descriptive statistics and multicollinearity diagnosis are performed on the information of 729 molecular descriptors of 1 974 compounds, and the random forest method is used to screen 20 significant variables with variable importance measure that is greater than 0.01. Then, a CNN-based two-dimensional feature matrix is constructed, and a Bayesian hyperparametric optimization (BHO) method is used to perform hyperparametric optimization of the Bi-LSTM model. Finally, the prediction effect of model is analyzed and evaluated. The results show that compared with the GBDT integrated learning method, the prediction effect of Mul-BHO-Bi-LSTM integrated machine learning prediction model is better, and the model error indexes MSE, NRMSE, error mean, and error std are less than 0.15, and the correlated indicators <italic>R</italic>² and <italic>r</italic> are above 0.99, indicating that the integrated machine learning predictionmodel of Mul-BHO-Bi-LSTM has the good robustness and generalization, and the model can provide a method for the screening and design of anti-breast cancer drugs.