Search

Credit-risk prediction is one of the challenging tasks in the banking industry. In this study, a hybrid convolutional neural network—support vector machine/random forest/decision tree (CNN—SVM/RF/DT) model has been proposed for efficient credit-risk prediction. We proposed four classifiers to develop the model. A fully connected layer with soft-max trained using an end-to-end process makes up the first classifier and by deleting the final fully connected with soft-max layer, the other three classifiers—a SVM, RF, and DT classifier stacked after the flattening layer. Different parameter values were considered and fine-tuned throughout testing to select appropriate parameters. In accordance with the experimental findings, a fully connected CNN and a hybrid CNN with SVM, DT, and RF, respectively, achieved a prediction performance of 86.70%, 98.60%, 96.90%, and 95.50%. According to the results, our suggested hybrid method exceeds the fully connected CNN in its ability to predict credit risk. [ABSTRACT FROM AUTHOR]

Venture capital firms are always faced with insufficient information and insufficient time when evaluating whether startups are worth investing in. This paper focuses on how to combine the public information of startups with the decision tree algorithm to assist investors in project screening. By extracting the public information of 1104 AI and big data companies from January 2016 to June 2017 and the financing progress in the following 18 months, this paper finds that: the six indicators of having a working background in well-known companies, being reported by well-known media, having patents and being invested by excellent institutions, working experience is highly related to this venture, and having well-known financing consultants can effectively help investors screen out projects that can obtain sustainable financing, that is, high potential projects. Considering the problem of data availability in the real world, combined with industry experience, this paper makes a more detailed variable mining for semistructured information, such as the team resume of start-ups, and selects a decision tree algorithm that is insensitive to missing values and has strong interpretability to amplify the value of fragmented information. Finally, by the improvement of the algorithm, a project screening model that can meet the needs of investment practice is designed, and the fusion mode of public information and private information is discussed, which has a more complete guiding significance for optimizing investment work. [ABSTRACT FROM AUTHOR]

To improve the governance effect of public communities and protect community security, combined with the basic principles and network structure of CNN network in deep learning, a community security risk prediction model based on improved single-channel CNN network and decision tree is constructed. The experimental results show that expanding the single channel to the multichannel network greatly extends the receptive field of CNN network. Simultaneously, the accuracy of the prediction model is improved, which is as high as 87.7%. After inputting the output values of every single model into the comprehensive model, the prediction accuracy of the comprehensive model is improved by 4.8%. The feasibility and effectiveness of this method are further demonstrated. [ABSTRACT FROM AUTHOR]

Improving the employment rate and quality of women's employment has been a hot spot of social concern in recent years. Traditional female employment information has not been fully utilized; only simple storage and query functions have been completed. In order to mine and use female employment information, we find the rules that exist in it, and to better understand the current female employment problems, this article focuses on the data mining of female employment information data. This paper introduces in detail the current employment trends of women and the advantages of decision tree algorithms, the hot content and key technical points of data mining technology, the research progress of this technology at home and abroad, etc. Decision tree analysis algorithm for association rules: According to the formula calculus, the advantages of the decision tree algorithm and the association rule analysis method are displayed more clearly. The model of female employment information is mainly constructed, and the process of data collection and data model establishment is introduced. According to a set of female employment information data, the algorithm is analyzed through the decision tree analysis algorithm based on association rules, and the reliability of the algorithm is verified. Finally, the whole article is summarized, and its basic contents are explained. The decision tree analysis method based on association rules can effectively dig out the information hidden in the female employment information data, and it has an important role in guiding the self planning of college women. This algorithm has the characteristics of high operating efficiency and stable results, and it also has a positive effect on other types of data mining. [ABSTRACT FROM AUTHOR]

The development of a financial analysis system is essential for modern businesses to improve their management systems. In light of the global financial crisis, it is even more critical for businesses to develop a rigorous financial analysis system to avoid risks. DM does not necessitate the development of a complex mathematical theory; as long as data are filtered, hidden features between data can be found. The decision tree algorithm is one of several DM methods. With the rapid advancement of DM technology, theories and applications related to it are maturing at a rapid pace. This study will develop a decision tree-based enterprise financial risk analysis and early warning model, analyze enterprise financial influencing factors, apply the decision tree method to enterprise financial risk analysis and early warning, and provide a reference for enterprise financial risk early warning and risk control decision-making. [ABSTRACT FROM AUTHOR]

This paper requires a lot of assumptions for financial risk, which cannot use all of the data and is often limited to financial data; and in the past, most early warning models for financial crises did not, so they could not track the fluctuation and change trend of financial indicators. A decision tree algorithm model is used to propose a financial risk early warning method. Enterprises have suffered as a result of the financial crisis, and some have even gone bankrupt. Any financial crisis, on the other hand, has a gradual and deteriorating course. As a result, it is critical to track and monitor the company's financial operations so that early warning signs of a financial crisis can be identified and effective measures taken to mitigate the company's business risk. This paper establishes a financial early warning system to predict financial operations using the decision tree algorithm in big data. Operators can take measures to improve their enterprise's operation and prevent the failure of the embryonic stage of the financial crisis, to avoid greater losses after discovering the bud of the enterprise's financial crisis, and to avoid greater losses after discovering the bud of the enterprise's financial crisis. This prediction can be used by banks and other financial institutions to help them make loan decisions and keep track of their loans. Relevant businesses can use this signal to make credit decisions and effectively manage accounts receivable; CPAs can use this early warning information to determine their audit procedures, assess the enterprise's prospects, and reduce audit risk. As a result, the principle of steady operation should guide modern enterprise management. Prepare emergency plans in advance of a business risk or financial crisis to resolve the financial crisis and reduce the financial risk. [ABSTRACT FROM AUTHOR]

When traditional methods analyze the audit data of enterprise financing alliance, there are some problems, such as long algorithm modeling time and low accuracy of interest distribution algorithm of enterprise financing alliance. Therefore, this paper proposes an analysis method of interest distribution of enterprise audit data financing alliance based on the decision tree algorithm. The audit data collection process of enterprise financing alliance is given, and the continuous attributes of audit data are discretized by the C4.5 algorithm. We perform enterprise financing alliance audit data analysis, remove inconsistencies from audit data through data cleaning, and finally realize enterprise financing alliance audit data analysis based on the improved C4.5 algorithm. The experimental results show that this method can shorten the modeling time and improve the accuracy of interest distribution algorithm of enterprise financing alliance. We achieved an average accuracy of 84.7% with the C4.5 algorithm while 84.35% with NBTree. [ABSTRACT FROM AUTHOR]

The combination of Spark distributed platform and High-Utility Itemset Mining can solve the problem of long running time issue of High-Utility Itemset Mining. In the experiment, we conclude that Spark-based parallel D2HUP and EFIM algorithms have a greater improvement in running time efficiency than serial algorithms. The existing research has shown that the EFIM and D2HUP algorithms are the two best algorithms for High-Utility Itemset Mining. This paper generates 118 datasets by generating and collecting the running time of the two algorithms in the real and simulated datasets, taking into account the characteristics of each dataset's length, sparse degree, and dataset size as characteristics with running time as the prediction target and then establishing a model. The accuracy of the prediction was evaluated through experiments, and a set of rules based on decision trees was generated. According to the rules, the fastest algorithm between EFIM and D2HUP can be predicted very well. [ABSTRACT FROM AUTHOR]

This paper focuses on the application of traditional culture in the intelligent advertising design system in the internet era. The existence form of traditional culture is abstract and vivid. It is extremely charming when used in advertising design. It is unique and subtle and has the beauty of holding a pipa half-covered. The classic colors reveal the splendor of history, which is fascinating, and it seems to want people to integrate into it and appreciate its beauty. This paper, firstly, introduces the background of traditional culture and intelligent advertising design and discusses its significance and innovation. Combined with the research methods and experiments put forward by the related work, the advertising system model is, firstly, proposed. The process of ad request processing, system hardware topology, and ad real-time bidding process are introduced. It will talk about the feature association algorithm in advertising design, explain the linear logistic regression and nonlinear algorithms, and describe the GBDT feature processing process. It combines stochastic gradient descent, decision trees, etc., to calculate ad click-through rates. It also explained the allocation algorithm of traffic and quality and market competition in advertising design. It is guided by a probabilistic filtering mechanism that tests ad spend, bidding, and market competition. Finally, the effect evaluation experiment of intelligent advertising system based on traditional culture fusion is carried out. It displays the application of traditional culture, such as Dunhuang Feitian and blue and white porcelain, Huizhou architecture, and Miao embroidery. It uses pictures to show its beauty, and it compares the advertising situation in the perspective of traditional culture and modern fashion. It is concluded that the introduction of traditional culture into advertisements is more attractive. Through the establishment of an outdoor advertising evaluation system based on face gesture recognition to calculate the pedestrian parking viewing rate, it is concluded that the system has a very high accuracy rate and a very small error, only 3.76%, which can be effectively applied to actual scenarios. [ABSTRACT FROM AUTHOR]

Support vector machines (SVMs) are designed to solve the binary classification problems at the beginning, but in the real world, there are a lot of multiclassification cases. The multiclassification methods based on SVM are mainly divided into the direct methods and the indirect methods, in which the indirect methods, which consist of multiple binary classifiers integrated in accordance with certain rules to form the multiclassification model, are the most commonly used multiclassification methods at present. In this paper, an improved multiclassification algorithm based on the balanced binary decision tree is proposed, which is called the IBDT-SVM algorithm. In this algorithm, it considers not only the influence of "between-classes distance" and "class variance" in traditional measures of between-classes separability but also takes "between-classes variance" into consideration and proposes a new improved "between-classes separability measure." Based on the new "between-classes separability measure," it finds out the two classes with the largest between-classes separability measure and uses them as the positive and negative samples to train and learn the classifier. After that, according to the principle of the class-grouping-by-majority, the remaining classes are close to these two classes and merged into the positive samples and the negative samples to train SVM classifier again. For the samples with uneven distribution or sparse distribution, this method can avoid the error caused by the shortest canter distance classification method and overcome the "error accumulation" problem existing in traditional binary decision tree to the greatest extent so as to obtain a better classifier. According to the above algorithm, each layer node of the decision tree is traversed until the output classification result is a single-class label. The experimental results show that the IBDT-SVM algorithm proposed in this paper can achieve better classification accuracy and effectiveness for multiple classification problems. [ABSTRACT FROM AUTHOR]

Ransomware (RW) is a distinctive variety of malware that encrypts the files or locks the user's system by keeping and taking their files hostage, which leads to huge financial losses to users. In this article, we propose a new model that extracts the novel features from the RW dataset and performs classification of the RW and benign files. The proposed model can detect a large number of RW from various families at runtime and scan the network, registry activities, and file system throughout the execution. API-call series was reutilized to represent the behavior-based features of RW. The technique extracts fourteen-feature vector at runtime and analyzes it by applying online machine learning algorithms to predict the RW. To validate the effectiveness and scalability, we test 78550 recent malign and benign RW and compare with the random forest and AdaBoost, and the testing accuracy is extended at 99.56%. [ABSTRACT FROM AUTHOR]

As an important language tool, literature in business English defines rights and obligations in business activities from the perspective of literature translation. This article discusses business English from the perspective of literature translation, which should not only preserve the characteristics of literature, but also ensure the smooth and correct language. In order to improve the accuracy of the automatic translation of business English literature and optimize the design of the teaching platform for business English literature translation, a design method of the teaching platform for business English literature translation based on the decision tree logistic model is proposed. The platform design consists of two modules: automatic translation algorithm design and software development of the platform. Using the decision tree logistics model to analyze the semantic features of business English translation and context feature matching and adaptive semantic variable optimization method to analyze automation lexical features of business English translation and to extract the correlation between vocabulary and vocabulary characteristics, in the context of a specific business translation difference correction, the accuracy of English translation is improved. The software design of the platform is carried out under the decision tree logistics model. The platform construction is mainly divided into vocabulary database module, English information processing module, network interface module, and human-computer interaction interface module. B/S framework protocol is used for integrated development and the design of translation platform. According to the characteristics of the data business application and the particularity of data security risk monitoring, from business English requirement analysis, the study of business English translation behavior monitoring ability and analysis in the process of abnormal behavior monitoring techniques and methods, including data access, data processing, experience in engine, and model engine puts forward the future research direction. The platform test results show that this method has good accuracy and strong automatic translation ability in business English literature translation. [ABSTRACT FROM AUTHOR]

Enterprise finance has become an indispensable financial channel for people to invest in their lives, and business management can provide a better economic environment for the development of enterprise finance. The structure of enterprises is gradually becoming more and more complex, and business administration shoulders considerable responsibilities and obligations in the organization and supervision of today's social management structure. How can China play its functions under the new situation after the world economic exchanges are more frequent is an important link to promote the stable development of financial markets. In view of the problems of economic activity behavior and certainty of financial index system under the background of existing business administration, this paper puts forward the deep learning model to make risk analysis, income analysis, profit and loss analysis, and so on. The formula of deep learning model is used to calculate the data graph of financial economy, and finally, various data are compared to get the research of several business management methods on the development of enterprise financial economy. Among them, the model of current management mode belongs to two modes: e-commerce and EPR management. They not only have very unique management characteristics but also greatly promote the development of modern management, and their roles also well interpret the characteristics of modern management. The experiment also analyzes the financial data under the four algorithms for uncertainty comparison, profit and loss comparison, discreteness comparison, volatility comparison, and possibility analysis. Finally, after the source of uncertainty, the risk prediction and risk management are carried out by constructing decision trees, and these structural models are used to bring comprehensive analysis to the financial economy of enterprises and to build the impact of good trends and development prospects. [ABSTRACT FROM AUTHOR]

Educational data mining is becoming a more and more popular research field in recent years, mainly with the help of cross research conducted by various disciplines, so as to solve various difficult problems in the teaching and education process. In this paper, we proposed a hybrid approach for student performance prediction. We collected the dataset, including 15 characteristics of students from three categories (individual basic information, individual education information, and individual behavior information). Based on the random forest (RF) and simulated annealing (SA) algorithms, we binary encode the relevant parameters (number of features, tree size, and tree decision weights) as the target variables for algorithm optimization, use the out-of-bag error as the optimization objective function, and then propose the IRFC (improved random forest classifier) algorithm in this paper. Compared with other mainstream improved random forest algorithms, the research results demonstrate that the proposed algorithm in this paper has higher generalization ability and smaller OOB error. This study provides a methodological reference for the prediction of student achievement and also makes a marginal contribution to student management work. [ABSTRACT FROM AUTHOR]

Flight delay is the most common preoccupation of aviation stakeholders around the world. Airlines, which suffer from a monetary and customer loyalty loss, are the most affected. Various studies have attempted to analyze and solve flight delays using machine learning algorithms. This research aims to predict flights' arrival delay using Artificial Neural Network (ANN). We applied a MultiLayer Perceptron (MLP) to train and test our data. Two approaches have been adopted in our work. In the first one, we used historical flight data extracted from Bureau of Transportation Statistics (BTS). The second approach improves the efficiency of the model by applying selective-data training. It consists of selecting only most relevant instances from the training dataset which are delayed flights. According to BTS, a flight whose difference between scheduled and actual arrival times is 15 minutes or greater is considered delayed. Departure delays and flight distance proved to be very contributive to flight delays. An adjusted and optimized hyperparameters using grid search technique helped us choose the right architecture of the network and have a better accuracy and less error than the existing literature. The results of both traditional and selective training were compared. The efficiency and time complexity of the second method are compared against those of the traditional training procedure. The neural network MLP was able to predict flight arrival delay with a coefficient of determination R 2 of 0.9048, and the selective procedure achieved a time saving and a better R 2 score of 0.9560. To enhance the reliability of the proposed method, the performance of the MLP was compared with that of Gradient Boosting (GB) and Decision Trees (DT). The result is that the MLP outperformed all existing benchmark methods. [ABSTRACT FROM AUTHOR]

Terrorist attacks pose a great threat to global security, and their analysis and prediction are imperative. Considering the high frequency of terrorist attacks and the inherent difficulty in finding related terrorist organizations, we propose a classification framework based on ensemble learning for classifying and predicting terrorist organizations. The framework includes data preprocessing, data splitting, five classifier prediction models, and model evaluation. Based on a quantitative statistical analysis of terrorist organization activities in GTD from 1970 to 2017 and feature selection using the SelectKBest method in scikit learn, we constructed five classification and prediction models of terrorist organizations, namely, decision tree, bagging, random forest, extra tree, and XGBoost, and utilized a 10-fold cross-validation method to verify the performance and stability of the proposed model. Experimental results showed that the five models achieved excellent performance. The XGBoost and random forest models achieved the best accuracies (97.16% and 96.82%, respectively) of predicting 32 terrorist organizations with the highest attack frequencies. The proposed classifier framework is useful for the accurate and efficient prediction of terrorist organizations responsible for attacks and can be extended to predict all terrorist organizations. [ABSTRACT FROM AUTHOR]

Human emotion recognition from videos involves accurately interpreting facial features, including face alignment, occlusion, and shape illumination problems. Dynamic emotion recognition is more important. The situation becomes more challenging with multiple persons and the speedy movement of faces. In this work, the ensemble max rule method is proposed. For obtaining the results of the ensemble method, three primary forms, such as CNNHOG-KLT, CNNHaar-SVM, and CNNPATCH are developed parallel to each other to detect the human emotions from the extracted vital frames from videos. The first method uses HoG and KLT algorithms for face detection and tracking. The second method uses Haar cascade and SVM to detect the face. Template matching is used for face detection in the third method. Convolution neural network (CNN) is used for emotion classification in CNNHOG-KLT and CNNHaar-SVM. To handle occluded images, a patch-based CNN is introduced for emotion recognition in CNNPATCH. Finally, all three methods are ensembles based on the Max rule. The CNNENSEMBLE for emotion classification results in 92.07% recognition accuracy by considering both occluded and nonoccluded facial videos. [ABSTRACT FROM AUTHOR]

Dry beans are the most widely grown edible legume crop worldwide, with high genetic diversity. Crop production is strongly influenced by seed quality. So, seed classification is important for both marketing and production because it helps build sustainable farming systems. The major contribution of this research is to develop a multiclass classification model using machine learning (ML) algorithms to classify the seven varieties of dry beans. The balanced dataset was created using the random undersampling method to avoid classification bias of ML algorithms towards the majority group caused by the unbalanced multiclass dataset. The dataset from the UCI ML repository is utilised for developing the multiclass classification model, and the dataset includes the features of seven distinct varieties of dried beans. To address the skewness of the dataset, a Box-Cox transformation (BCT) was performed on the dataset's attributes. The 22 ML classification algorithms have been applied to the balanced and preprocessed dataset to identify the best ML algorithm. The ML algorithm results have been validated with a 10-fold cross-validation approach, and during validation, the CatBoost ML algorithm achieved the highest overall mean accuracy of 93.8 percent, with a range of 92.05 percent to 95.35 percent. [ABSTRACT FROM AUTHOR]

The land transportation is a cause of noise in cities, thus breaking the natural balance and bringing with it physiological and mental illnesses, as well as occupational accidents. In this sense, the objective of the research was to estimate the sound pressure in land terminals in the city of Jaen, Peru, using data mining algorithms. The methodology consisted in environmentally monitoring six terminals in the city of Jaen, during 2019, using a class 1 sound level meter; the exploratory analysis of the collected variables that influence the noise of the terminals (minimum and maximum sound pressure level, number of light and heavy vehicles, and equivalent sound pressure level) was performed, which were grouped into three groups of variables for the purpose of using data mining algorithms. Three algorithms were used, namely, artificial neural network, linear regression, and M5Rules, using the free software Weka. Considering all variables, the M5Rules method performed the best, because the value of the mean absolute error (0.7462), the root mean square error (1.0575), and uncertainty analysis (0.09) was the smallest compared to the other two methods. However, for the two remaining groups of variables, the linear regression model showed the lowest mean absolute error and mean square root of the error; in addition to presenting coefficients of determination close to one. The algorithms show good behavior when estimating the sound pressure of the terminals in the city of Jaen. [ABSTRACT FROM AUTHOR]

Building an efficient and effective credit scorer for enterprises is an important and urgent demand in the cross-border e-commerce industry. In this paper, we present a framework to build a credit scorer using e-commerce data integrated from various sources. First, an improved dependency graph approach is proposed to recognize distinct records in the dataset. Then, we apply logistic regression using a prejudice remover regularizer to train the model, preceded by predictor preparation through binning and evaluating their information value. Lastly, we build the credit scorer according to the coefficients of the model. We implement our framework on a dataset from the official customs database and a large cross-border e-commerce platform. The empirical results demonstrate that the scorer built by our methodology can be used to effectively evaluate enterprises, while also removing prejudice against small and medium enterprises to a certain extent. [ABSTRACT FROM AUTHOR]

Named entity recognition (NER) is a subfield of natural language processing (NLP). It is able to identify proper nouns, such as person names, locations, and organizations, and has been widely used in various tasks. NER can be practical in extracting information from social media data. However, the unstructured and noisy nature of social media (such as grammatical errors and typos) causes new challenges for NER, especially for low-resource languages such as Persian, and existing NER methods mainly focus on formal texts and English social media. To overcome this challenge, we consider Persian NER as an optimization problem and use the binary Gray Wolf Optimization (GWO) algorithm to segment posts into small possible phrases of named entities. Later, named entities are recognized based on their score. Also, we prove that even human opinion can differ in the NER task and compare our method with other systems with the S e p _ T D _ T e l 01 dataset and the results show that our proposed system obtains a higher F1 score in comparison with other methods. [ABSTRACT FROM AUTHOR]

With the increasing import volume of China's oil and natural gas, the structure of China's energy supply chain (ESC) has become more and more complex. How to use the "Belt and Road" (OBOR) layout to promote China's regional energy cooperation and ensure China's energy security has become an important international issue facing China. This paper constructs an ESC network model in the context of the OBOR, and finds out the position of China in this network model. This paper also finds out the role law of each risk influencing factor, analyzes the degree of its influence, and puts forward some suggestions on the risk management of ESC according to the analysis results. This paper proposes to use decision tree algorithm to guide the development and construction of Sino-Lao economic and trade cooperation, which will help analyze and help the construction and research of Sino-Lao economic and trade cooperation and sustainable energy freight corridor. Based on the energy cooperation between China and the countries along the "Belt and Road," this paper analyzes the network structure of energy cooperation under the "Belt and Road" background based on the small-world network theory. This paper analyzes the important role of core countries in the ESC through the analysis of the basic parameters of the small-world network, the efficiency of energy cooperation, and the stability of energy cooperation. According to the value of each vertex degree obtained by the calculation formula of entropy value, the entropy value of the ESC network structure under the background of OBOR can be obtained as 2.408. It calculates that the maximum and minimum entropy of the ESC network structure at this time are 3.09 and 2.21 respectively. [ABSTRACT FROM AUTHOR]

Modern landscape greening plays an important role in the construction of modern cities and plays a positive role in improving the natural environment of cities and building a good image of cities. With the continuous progress of society and technology, human's understanding of artificial intelligence is deepening, and intelligent technology is gradually integrated into all aspects of life. Because media technology has rich design elements and can carry out rich design structures, it will be more intuitive to use multimedia means for garden landscape design. Therefore, for meeting people's requirements for the diversification of modern urban gardening construction, this study makes a deep analysis of the current status and problems of landscape design and tries to study the effective application methods of artificial intelligence technology in landscape design, to promote the combination of landscape design and artificial intelligence design. At the same time, the combination of AI lighting planning, AI water landscape planning, AI sprinkler planning, and AI paving planning is used to illustrate the application of AI in the specific project design of landscape design. The use of artificial intelligence not only promotes the innovation and optimization of landscape design, but also ensures the quality of modern landscape design and effectively improves the efficiency of modern landscape design. [ABSTRACT FROM AUTHOR]

With the rapid development of deep learning, its application in the field of education has gradually attracted attention. This study introduces a deep learning-based moral education evaluation system for college students. The evaluation of the ideological and political education of college students is an important driving force to strengthen and improve the ideological and political education of college students, and its connotation is very rich. However, at present, there are many difficulties in the evaluation of ideological and political education in colleges and universities, such as narrow evaluation objectives, monotonous evaluation structures, lack of pertinence in the evaluation process, and subjective evaluation standards. The internal mechanism and external mechanism of the evaluation mechanism, the qualitative analysis and quantitative analysis of the evaluation method, the absoluteness and relativity of the evaluation standard, the dynamic and static evaluation process, and the systematic and specialized evaluation are combined to ensure the college students' thinking the objectivity and effectiveness of political education evaluation. [ABSTRACT FROM AUTHOR]

With the growing development of the era of big data, data acquisition and analysis have become hot spots, and Python-based crawler technology is one of the most widely used tools in data analysis work at present. In this paper, we apply Python crawler key technology to acquire data of movie list and hot movies on Cat's Eye movie network, analyze data based on Python development environment Spyder, use the Numpy system to store and process large data, Chinese Jieba word separation tool to crawl data for word separation text processing, Snownlp library to process text sentiment, and finally by the word cloud map and web dynamic map display information such as viewers' emotional tendency and movie rating statistics, and provide decision support for users' movie viewing. [ABSTRACT FROM AUTHOR]

In order to further improve the identification efficiency of tobacco mildew, a rapid identification model of tobacco mildew based on random forest algorithm was proposed in this study. In order to ensure the feasibility and pertinence of the model study, this study takes redried leaf tobacco as the research object, selects high-temperature and high-humidity environment as the experimental conditions, and obtains the sample data of the degree of tobacco mildew under different experimental conditions. At the same time, this paper constructs a rapid identification model of tobacco mildew with the help of random forest algorithm. Through the model experimental results, it is found that the accuracy of the model for the rapid identification of training samples can reach 93.82%, while the accuracy of independent testing is 94.84%. The experimental results fully reflect the availability and efficiency of the random forest algorithm model in the rapid identification of tobacco mildew. [ABSTRACT FROM AUTHOR]

The bulk of the fault tolerance techniques that are in use today laid their primary emphasis, in the event that a virtual machine fails, on the production of clones to replace it, rather than on the early prediction of the failure itself in advance. Several of the currently used techniques give migration priority over recovery in the event that a virtual machine (VM) fails. This is due to resource constraints and concerns with server availability. Examples of algorithms with a single objective include fault tolerance, migration prediction, and simply expecting failure. Another example is fault tolerance. In this research, we are aiming to determine the most effective strategy to transition from a system that is not operating well to one that does. It is essential to be able to predict the failure of a virtual machine in a timely manner due of issues such as squandered resources, energy, and cost. Since the beginning of cloud computing, there has been an issue with the dependability of virtual computers, often known as VMs. As an integral component of a fault tolerance system, preemptive measures are an absolute need in order to guarantee the continuation of service. As a consequence of this, it is vital to work toward enhancing and emphasizing the proactive failure prediction of virtual machines. The key motivations for this are decreased periods of downtime and enhanced scalability. A technique was utilized to transfer the resources that were predicted to fail from one virtual machine (VM) to another VM in a safe manner. Using the compression strategy reduced the amount of time needed to complete the migration, and resource utilization increased. This article provides artificial intelligence that enables effective fault prediction techniques in cloud computing to improve resource optimization. [ABSTRACT FROM AUTHOR]

Although the statistics show a slow decline in traffic accidents in many countries over the last few years, drunk or drug-influenced driving still contributes to enough shares in those records to act. Nowadays, breath analysers are used to estimate breath alcohol content (BAC) by law enforcement as a preliminary alcohol screening in many countries. Therefore, since breath analysers or field sobriety testers do not accurately measure BAC, the analysis of blood samples of individuals is required for further action. Many researchers have presented various approaches to detect drunk driving, for example, using sensors, face recognition, and a driver's behaviour to confound the shortcomings of the time-honoured approach using breath analysers. But each one has some limitations. This study proposed a plan to distinguish between drivers' states, that is, sober or drunk, by the use of transfer learning from the convolutional neural network (CNN) features to the random forest (RF) features with an accuracy of up to 93%, which is higher than that of existing models. With the same dataset, to validate our research, a comparative analysis was performed with other existing model classifiers such as the simple vector machine (SVM) with an accuracy of 65% and the K-nearest neighbour (KNN) with an accuracy of 62%, and it was found that our approach is an optimized approach in terms of accuracy, precision, recall, F1-score, AUC-ROC curve, and Matthew's correlation coefficient (MCC) with confusion matrix. [ABSTRACT FROM AUTHOR]

With the technological advancements, practical challenges of establishing long-distance communication should be addressed using hop-oriented routing networks. However, long-distance data transmissions usually deteriorate the quality of service (QoS) especially in terms of considerable communication delay. Therefore, in the presented work, a reward-based routing mechanism is proposed that aims at minimizing the overall delay which is evaluated under various scenarios. The routing process involved a refined CH selection mechanism based on a mathematical model until a threshold simulation is not attained. The illustrations for the coverage calculations of CH in the route discovery are also provided for possible routes between the source and the destination to deliver quality service. Based on this information, the data gathered from the past simulations is passed to the learning mechanism using the Q-learning model. The work is evaluated in terms of throughput, PDR, and first dead node in order to achieve minimal transmission delay. Furthermore, area variation is also involved to investigate the effect of an increase in the deployment area and number of nodes on a Q-learning-based mechanism aimed to minimize the delay. The comparative analysis against four existing studies justifies the success of the proposed mechanism in terms of throughput, first dead node, and delay analysis. [ABSTRACT FROM AUTHOR]

India experiences severe weather events around the year. Severe thunderstorms occur during the premonsoon season (March-May), cyclonic storms occur over the Bay of Bengal/Arabian Sea during the premonsoon and postmonsoon seasons (October-December), and heavy rainfall occurs during the monsoon season (June-September). It causes a lot of damage to property and the lives of humans. Smart urban areas aim to improve residents' personal satisfaction by utilizing data about urban scale procedures separated from heterogeneous information sources gathered on city-wide arrangements using sensors. The Internet of Things (IoT) is an empowering concept for forecasting weather situations on an urban scale. A multisource detecting framework influences IoT innovation to accomplish city-scale detection of climatic changes and forecasts them to citizens in a smart city. The existing models gather the data in an unstructured process that need to be structured. This is a complex task that needs to be reduced. The proposed model gathers data from various regions in a city and uses it to identify the weather regions. A novel approach is introduced to detect this climate information gathered by utilizing various sensors arranged in a city. The information gathered from the sensors is thoroughly examined to see if there is any inconsistency in weather reports in any of its key hubs, and cautions are activated to the city for prompt actions. In this proposed work, an efficient method for weather casting using an IoT mechanism is introduced, and the results state that the proposed method is effective in terms of accuracy and speed when contrasted with the traditional methodologies. [ABSTRACT FROM AUTHOR]

With the development of remote sensing technology, remote sensing image data plays an active role in the dynamic monitoring of global resource changes and land cover utilization. Remote sensing image land cover classification is an important application direction of remote sensing data; how to further improve the accuracy of remote sensing image land cover classification is very important for the effective application of remote sensing data. The traditional remote sensing image land cover classification is mainly to classify remote sensing data according to the spectral data of ground objects. However, due to the complex environment of remote sensing images and the dynamic changes of the environment, traditional classification methods based only on pixel spectral data are often unable to achieve. A satisfactory classification result is achieved. In addition, some researchers have also proposed to combine pixel neighborhood texture information to supplement spectral feature data. Although the traditional classification method based on spectral features solves the problem of time-consuming visual interpretation, to a certain extent, due to the limited semantic expression ability and poor generalization ability of the design features, the classification accuracy is still not very satisfactory. This paper mainly studies the classification method of land cover remote sensing image based on pattern recognition. This paper is based on the experimental results of remote sensing data in Nanjing Yuhuatai District in 2018 and 2019. The ground resolution of the data is 2.5 meters. Data is projected, corrected, and equalized. Half of the images covering 43.75 square kilometers are used as training samples, and the remaining 50 square kilometers are used for detection. In the classification results of this IndianPines data, OA only increased by nearly 10% to 86.2%, AA increased by 13%, r was 82.77%, and Kappa coefficient was 0.84. In the classification results of Salinas data, both OA and AA increase by about 5%, and the optimization effect is not obvious. [ABSTRACT FROM AUTHOR]

Transfer learning attempts to use the knowledge learned from one task and apply it to improve the learning of a separate but similar task. This article proposes to evaluate this technique's effectiveness in classifying images from the medical domain. The article presents a model TrFEMNet (Transfer Learning with Feature Extraction Modules Network), for classifying medical images. Feature representations from General Feature Extraction Module (GFEM) and Specific Feature Extraction Module (SFEM) are input to a projection head and the classification module to learn the target data. The aim is to extract representations at different levels of hierarchy and use them for the final representation learning. To compare with TrFEMNet, we have trained three other models with transfer learning. Experiments on the COVID-19 dataset, brain MRI binary classification, and brain MRI multiclass data show that TrFEMNet performs comparably to the other models. Pretrained model ResNet50 trained on a large image dataset, the ImageNet, is used as the base model. [ABSTRACT FROM AUTHOR]

Medical image segmentation identifies an area that should be analyzed later in the processing process, such as for disease recognition and classification. As the image search area is reduced, this action allows for faster computation and analysis. We propose the use of a heuristic red fox heuristic optimization algorithm (RFOA) for medical image segmentation in this paper. The heuristics' operation was adapted to the analysis of two-dimensional images, with a focus on equation modification and the novel fitness function. The proposed solution analyzes the image by converting the selected pixels to one of two color variants, black or white, based on the threshold value used. Their number is counted, allowing analysis of the chosen threshold. As a result, such analysis results in the automatic selection of the segmentation threshold parameter. Our method propose a new fitness function and the adjustment of RFOA to image analysis. We used a publicly available database of lung X-ray images for evaluation, and based on the results, an accuracy analysis was performed, as well as a discussion of the benefits and drawbacks is presented. [ABSTRACT FROM AUTHOR]

In recent years, the interdisciplinary exploration of combining traditional visual communication design with somatosensory interaction technology has become a new form of artistic expression. In order to explore the feasibility of somatosensory interaction technology in visual communication design, this study proposes a 2D dynamic graphic generation method based on somatosensory interaction parameterisation and uses traditional Chinese elements as an example for specific applications in visual communication design. Firstly, the motion parameters recognised using the Kinect somatosensory interaction device are bound to the function variables used to generate the images in the development environment, thus enabling human somatosensory interaction with different characters in the scene. Secondly, a linear discriminant analysis based on kernel functions is used to reduce the dimensionality of the vector space, thus solving the problem of real-time and accurate capture of human movements. Then, using the skeletal parameter binding technique, the association between the motion parameters of the somatosensory interaction and the two-dimensional dynamic graphics is achieved. The experimental results show that the visual communication technique based on somatosensory interaction has a high recognition accuracy. Distinguished from traditional digital video, the proposed method can greatly enrich the visual representation of traditional Chinese elements. [ABSTRACT FROM AUTHOR]

In the present study, a spatial quantitative model of landslide hazards based on a deep belief network (DBN) is constructed. Firstly, environmental similarity-based sampling (ESBS) was used to determine the negative sampling area. Secondly, multiple data sets are constructed. Each data set contains seven landslide-conditioning factors; 70% of the data are used for training; and 30% are used for validation. The performance evaluation index of the spatial quantitative model of landslide hazards was established; that is, the AUC mean (AUCmean) was used to measure the stability of the model, and the AUC standard deviation (AUCSD) was used to measure the uncertainty of the model. Finally, the accuracy of the prediction results of the DBN model is analyzed. The results show that the area with negative sample reliability greater than 0.51 is the best negative sample sampling area, and the stability of the DBN model is maintained at a relatively good level in both the training step (AUCmean = 0.9597) and the validation step (AUCmean = 0.8897). The standard deviation of AUC is close to 0 (AUCSD = 0.0081 in the training step and AUCSD = 0.0085 in the validation step), indicating that the selected negative samples have a weak impact on the performance of the model. The susceptibility areas of very high obtained by the DBN model (landslide points in the susceptibility areas of very high accounted for 55.03%) are realistic. Therefore, the DBN model constructed in the present study is effective and can be used in the field of landslide hazard spatial prediction. [ABSTRACT FROM AUTHOR]

Financial marketing is a method of risky investment, but in a shorter duration, the individual can expect a profit or loss, depending on the current market rate for the organization. Though it has a higher risk of getting a profit, many individuals are ready to take a chance to benefit. In the current era, much research is going on to provide a better prediction rate. Most researchers prefer Ant Colony Optimization (ACO) as a more trustworthy optimization algorithm among the existing optimization algorithms. In this research work, a novel optimization algorithm is proposed; it is a hybrid algorithm with Ant Colony Optimization (ACO) and financial marketing crisis prediction (FMCP) and is termed ACO-FMCP. This hybrid algorithm was applied to the economic sanctions dataset, and the results were generated. The results were compared with ACO and FMCP algorithms and it was found that the hybrid ACO-FMCP shows improved performance than the other two algorithms. [ABSTRACT FROM AUTHOR]

The deep mining of passengers' travel data can identify competitive segments and gain insights into passengers' characteristics and differentiated demands. This can not only effectively support precise marketing strategy adjustment of railway transport but also improve its competitiveness in the passenger transportation market. In this paper, hidden railway travel behaviour is introduced and integrated with railway travel behaviour to create a complete passenger travel chain, based on existing distance-based competitive segment recognition methods. The loyalty index values of passengers are calculated using this travel chain to identify competitive segments. Furthermore, passenger classification and grouping currently ignore social relationships as well as personal travel characteristics. Therefore, a novel passenger grouping method is proposed; it integrates individuals' travel characteristics and social relations. Individual travel labels are created for travellers based on their travel data. Social relation topologies, such as ticketing relation, the relation of travelling together, and benefit relation via point redemption, can be extracted using these labels. Social relation traits can be retrieved using graph attention networks and multigraph fusion. Finally, travellers are categorised based on their individual travel characteristics. As an example, and a case study, the grouping of Guangzhou–Shanghai passengers in 2020 is taken which shows that the suggested method has the potential to improve both the precision and the feasibility of grouping railway passengers. As a result, new ideas for passenger grouping in railway marketing might be offered. [ABSTRACT FROM AUTHOR]

In modern society, the rapid development of the knowledge economy makes education become the core resource of a country's economic and social modernization development. Under this circumstance, student management has been paid more and more attention by people. This paper aims to study how to use the internet of things technology to study the student management evaluation system. This paper proposes a data mining algorithm based on the internet of things technology and proposes a decision tree method and an association rule algorithm based on the data mining algorithm. The experimental results of this paper show that the student growth rate in 2018 increased from 10% to 33% in 2019 and then from 21% in 2020 to 35% in 2021. It can be seen that with the development of the economy, the enrollment rate is also increasing, and the number of people who can go to college has increased rapidly. This also increases the difficulty of student management, making teachers' work more arduous, and the complexity of the amount of information leads to a drop in the efficiency of student management. However, the student management evaluation system based on the internet of things technology is beneficial to solving this problem. [ABSTRACT FROM AUTHOR]

As health issues continue to become more prevalent as the population grows, building a public health network is critical for enhancing the overall health quality of the community. This study offers an Internet of Things (IoT) based health care system that can be employed in the context of community medical care industrial areas. The main focus of this research is to develop a disease prediction strategy that could be applied to community health services using theoretical modelling. Using principal component analysis (PCA) and cluster analysis, an artificial bee colony (ABC) creates a nonlinear support vector machine (SVM) classifier pair. Feature-level fusion analysis was performed to detect probable abnormalities. The results of the experiments reveal that the SVM model offers significant benefits in disease prediction. In the SVM illness prediction model, the ABC algorithm has the best parameter optimization effect in terms of accuracy, time, and other factors. The suggested method outperformed the traditional SVM and BP neural network methods by 17.24 percent and 72.41 percent, respectively. It can lower the RMSE and improve assessment indicators like the precision recall rate and the F-measure, demonstrating the method's validity and accuracy. As a result, it is frequently used in community health management, geriatric community monitoring, and clinical medical therapy in an industrial environment. [ABSTRACT FROM AUTHOR]

This paper presents an in-depth study and analysis of sports training decision support systems through data mining techniques, and designs a corresponding sports training decision support system for application in practical situations. It investigates the application of data mining techniques in solving the problem of optimal analysis of sports training indicators. The Apriori algorithm is used to find out the hidden correlations behind the data, while the correlation study applicable to college students' physical fitness indicators is proposed and practiced, and the potential hidden relationships between the indicator data are found. The analysis results are further verified by the improved AP algorithm, FP algorithm, which provides important opinions for college physical education curriculum reform and youth physical culture development. Then, the Shi-Tomasi algorithm is used for feature point tracking and the support vector machine approach for human motion posture recognition. Considering that the collected action data contain a large amount of stationary action data, a threshold-based action segmentation algorithm is designed to extract useful action segments; after extracting the action segments, common action features are extracted from both statistical features, such as mean, variance, skewness, kurtosis, and physical features, such as acceleration and plantar pressure, to give a specific description of human daily actions. Thus, the fatigue of different postures is judged according to their number of occurrences and a preliminary assessment result is obtained. Then, the surface EMG data collected by the sensors are pre-processed to reduce noise, and the surface EMG signals are fused at the feature level based on the wavelet change algorithm, and the feature vectors are trained with BP neural networks to evaluate the fatigue of human muscle movements and obtain a preliminary evaluation result. Finally, by studying the application of information fusion technology at the decision level, the assessment results of the comprehensive human movement analysis are obtained using D-S evidence theory. In addition, a web platform is built on this basis to display and manage human exercise data and assessment results, and to facilitate the storage and query of historical exercise records. [ABSTRACT FROM AUTHOR]

This article proposes a computer network security defense system model based on multisource big data, which makes the security of computer networks more complete because of the shortage of current computer network security defense systems. The current network security situation is analyzed, and the problems faced in the field of network security are pointed out; then, multisource big data is introduced, and the characteristics of the multisource big data model are analyzed. This article proposes an information system network security model, which formally describes the relationship between network behavior among nodes, security threats, network attacks, and defense capability of security devices in an information system. After that, a network security defense system measurement scheme is constructed based on hierarchical analysis, and quantitative indicators of defense effectiveness are defined in two dimensions: risk severity of security threats and defense response actions of security devices, which enables quantitative evaluation of the security defense system, and then identifies omissions and defects of the network security defense system. A defense system measurement and optimization system is designed based on the proposed network security system measurement and optimization scheme. The application analysis of the project is combined with the actual scenarios. Through the evaluation and optimization of the security defense system in the natural methods, it is proved that the network security defense system evaluation and optimization scheme proposed in this article has reasonableness and effectiveness in the actual application. [ABSTRACT FROM AUTHOR]

Modeling fire susceptibility in fire-prone areas of forest ecosystems was essential for providing guidance to implement prevention and control measures of forest fires. Traditional models were developed on the basis of random selection of absence data (i.e., nonfire data from unburned areas), which could bring uncertainties to modeling results. Here, a new model with the genetic algorithm for Rule-set Production (GARP) algorithm and 10 environmental layers was proposed to process presence-only data in the susceptibility modeling of forest fires in Chongqing city. To do this, 70% of 684 fire occurrence data (479) during the period of 2000–2018 were applied to train the proposed model. And, 30% of these fire occurrence data (205) and the same amount of no-fire data (205) were emerged as validation dataset. The results showed that, for some environmental layers (i.e., distance to the nearest road, land cover, precipitation, distance to the nearest settlement, aspect, relative humidity, elevation, wind speed, and temperature), their P values were less than 0.05, indicating that these 9 environmental layers have significant influence on the spatial distribution of fire susceptibility in Chongqing city. On the contrary, with a higher P value (i.e., 0.126), the slope layer has an insignificant effect on fire susceptibility in the study area. Furthermore, the results of receiver operating characteristic analysis (ROC) showed that the proposed model has a good performance with an AUC value of 0.869, an accuracy value of 0.732, a sensitivity value of 0.59, a specificity value of 0.873, a positive predictive value of 0.823, and a negative predictive value of 0.681. This study revealed the validity of the proposed model in modeling the susceptibility of forest fires. [ABSTRACT FROM AUTHOR]

With the continuous innovation of Internet technology and the substantial improvement of network basic conditions, e-commerce has developed rapidly. Online shopping has become the mainstream mode of e-commerce. In order to solve the problem of information overload and information loss in the selection of e-commerce online shopping platform, a personalized recommendation system using information filtering technology has come into being. An e-commerce online shopping platform recommendation model is proposed based on integrated multiple personalized recommendation algorithms: random forest, gradient boosting decision tree, and eXtreme gradient boosting. The proposed model is tested on the public data set. The experimental results of the separate model and mixed model are compared and analyzed. The results show that the proposed model reduces the recommendation sparsity and improves the recommendation accuracy. [ABSTRACT FROM AUTHOR]

Aerial images play a key role in remote sensing as they can provide high-quality surface object information for continuous communication services. With advances in UAV-aided data collection technologies, the volume of aerial images has been greatly promoted. To this end, semantic understandings for these images can significantly improve the quality of service for smart devices. Recently, the multilabel aerial image classification (MAIC) task has been widely researched in academics and applied in industries. However, existing MAIC methods suffer from suboptimal performance as objects are located in different sizes and scales. To address these issues, we propose a novel multigrained semantic grouping model for aerial image learning, named MSGM. First, image features presented by the backbone are sent to spatial pyramid convolutional layers which extract the instances in a parallel manner. Then, three grouping mechanisms are designed to integrate the instances from the pyramid framework. In addition, MSGM builds a concept graph to represent the label relationship. MSGM resorts to the graph convolutional network to learn the concept graph directly. We extensively evaluate MSGM on two benchmark aerial image datasets, the commonly used UCM dataset, and the high-resolution DFC15 dataset. Quantitative and qualitative results support the effectiveness of the proposed MSGM. [ABSTRACT FROM AUTHOR]

With the development of sports, competition is becoming more and more confrontational and modern sports are developing in the direction of fast speed, fast rhythm, good skills, and high-altitude combat. And, this development requires good conditions and technology as a guarantee. Sports denote a competitive physical activity, which follows four aspects of competition: technology is the foundation, tactics are the means, the body is the cornerstone, and the psychology is the decisive point. Among these four factors, if the athlete does not have a good body, all techniques and know-how are empty talks. In this paper, two algorithms are introduced to track the athletes' physical training and tactical training videos and the relevant data in the game are counted to obtain the physical indicators required by the athletes in each position. In a certain game, the sprint distance in the first round was 1979 m, the high-speed running distance was 2426 m, the high-intensity running distance was 4398 m, and the jogging distance was 1267 m. [ABSTRACT FROM AUTHOR]

In mobile cloud services, smartphones may depend on IoT-based cloud infrastructure and information storage tools to conduct technical errands, such as quest, information processing, and combined networks. In addition to traditional finding institutions, the smart IoT-cloud often upgrades the normal impromptu structure by treating mobile devices as corporate hubs, e.g., by identifying institutions. This has many benefits from the start, with several significant problems to be overcome in order to enhance the unwavering consistency of the cloud environment while Internet of things connects and improves decision support system of the entire network. In fact, similar issues apply to monitor loading, resistance, and other security risks in the cloud state. Right now, we are looking at changed arrangement procedures in MATLAB utilizing cardiovascular failure information and afterward protecting that information with the assistance of RSA calculation in mobile cloud. The calculations tried are SVM, RF, DT, NB, and KNN. In the outcome, the order strategies that have the best exactness result to test respiratory failure information will be recommended for use for enormous scope information. Instead, the collected data will be transferred to the mobile cloud for preservation using the RSA encryption algorithm. [ABSTRACT FROM AUTHOR]

One of the challenges in e-learning is the customization of the learning environment to avoid learners' failures. This paper proposes a Stacked Generalization for Failure Prediction (SGFP) model to improve students' results. The SGFP model mixes three ensemble learning classifiers, namely, Light Gradient Boosting Machine (LGBM), eXtreme Gradient Boosting machine (XGB), and Random Forest (RF), using a Multilayer Perceptron (MLP). In fact, the model relies on high-quality training and testing datasets that are collected automatically from the analytic reports of the Blackboard Learning Management System (i.e., analytic for learn (A4L) and full grade center (FGC) modules. The SGFP algorithm was validated using heterogeneous data reflecting students' interactivity degrees, educational performance, and skills. The main output of SGFP is a classification of students into three performance-based classes (class A: above average, class B: average, class C: below average). To avoid failures, the SGFP model uses the Blackboard Adaptive Release tool to design three learning paths where students have to follow automatically according to the class they belong to. The SGFP model was compared to base classifiers (LGBM, XGB, and RF). The results show that the mean and median accuracies of SGFP are higher. Moreover, it correctly identified students' classifications with a sensitivity average of 97.3% and a precision average of 97.2%. Furthermore, SGFP had the highest F1-score of 97.1%. In addition, the used meta-classifier MLP has more accuracy than other Artificial Neural Network (ANN) algorithms, with an average of 97.3%. Once learned, tested, and validated, SGFP was applied to students before the end of the first semester of the 2020-2021 academic year at the College of Computer Sciences at Umm al-Qura University. The findings showed a significant increase in student success rates (98.86%). The drop rate declines from 12% to 1.14% for students in class C, for whom more customized assessment steps and materials are provided. SGFP outcomes may be beneficial for higher educational institutions within fully online or blended learning schemas to reduce the failure rate and improve the performance of program curriculum outcomes, especially in pandemic situations. [ABSTRACT FROM AUTHOR]

The traditional English teaching mode is that the teacher simply imparts textbook knowledge and students understand and absorb it. However, this method has obvious problems; that is, it is difficult to ensure that students can quickly understand the content taught and cannot get fast feedback. The video feedback method is a method of English teaching combined with audiovisual technology. Teachers can use video technology to record key English knowledge through video and then give feedback and explain the learning through video. At the same time, the intelligent video feedback system teaching method will greatly improve the teaching quality of English classroom and make students' learning more fun. This paper mainly designs the English teaching system based on the video feedback method and finally realizes the intelligent feedback scheme of the English teaching system. Firstly, the neural network method, classification method, and video shooting technology are used to extract and predict the characteristics of students' classroom expressions, speech, and so on, and analyze through the video feedback system of English classroom. The research results show that the classification method proposed in this study can better complete the body movements such as student expressions and speech collected by the English teaching system, and the neural network method can more accurately predict and feed back the teaching content through the video feedback method with the largest error. It was only 2.98%, and the linear correlation also reached more than 0.98. The minimum error of the video feedback information is only 0.95%, and the prediction errors of the other two kinds of English classroom information are also 2%. The classification and prediction of intelligent video feedback information have achieved good results. [ABSTRACT FROM AUTHOR]

Due to the low efficiency of traditional data analysis methods for massive e-commerce data analysis, an e-commerce data analysis and prediction method based on the GBDT deep learning model was proposed. Purchase behavior is divided into another category, which transforms the problem of e-commerce data analysis and prediction into a binary classification problem. At the same time, we extract 107 features that can reflect the user behavior and construct the GBDT model. The characteristics include counting class, sorting class, time difference class, conversion rate class, and so on. It follows from the above that the analysis and prediction of e-commerce data are realized. In addition, the results show that when the learning rate of GBDT model parameters is 0.05, the number of basic learners is 200, the tree depth is 20, the threshold is 0.5, the model prediction effect is best, and the F1 value can reach 0.12. Compared with the traditional prediction model based on logistic regression and neural network, the proposed GBDT model is more suitable for e-commerce data analysis and prediction. [ABSTRACT FROM AUTHOR]