Search

MOTIVATION: With the enhancement of people's awareness of the protection of personal privacy information, how to provide better services on the premise of protecting users' privacy has become an urgent problem to be solved. Therefore, it is a necessary motivation to build a network intelligent platform for privacy protection and integrated big data mining. OBJECTIVE: In view of the existing network platform of data privacy leakage, low efficiency of data mining and user satisfaction is not high, this paper will adopt advanced privacy technology, to ensure the confidentiality of users' personal information and security, to enhance the user trust and use experience, to better meet the needs of users. METHODS: In order to better protect the privacy of users, the network intelligent platform should adopt more advanced privacy protection technology. This paper uses the differential privacy algorithm to reduce the risk of data leakage and abuse, and ensure the accuracy and efficiency of data analysis and mining. In the design of the platform, the performance of the platform is fully taken into account to realize the secure storage and efficient processing of data, with good scalability and flexibility to meet the growing user needs and business needs. The performance of the network intelligent platform is also analyzed by experimental simulation. RESULT: The experimental results of this article indicated that in a network intelligent platform based on privacy protection and integrated big data mining, its data transmission encryption score was 9.5; the data storage encryption score was 9.8; the score of access control mechanism was 9.3; the privacy protection score was 9.6; the response time was 80 ms; the processing speed was 121GB/h; the user satisfaction rating was 6.6. CONCLUSION: This indicated that the network intelligent platform had good platform performance and user friendliness while ensuring data security and privacy protection. It could efficiently conduct data mining and ensure data security and privacy. [ABSTRACT FROM AUTHOR]

Under the influence of the coronavirus disease and other factors, agricultural product prices show non-stationary and non-linear characteristics, making it increasingly difficult to forecast accurately. This paper proposes an innovative combinatorial model for Chinese hog price forecasting. First, the price is decomposed using the Seasonal and Trend decomposition using the Loess (STL) model. Next, the decomposed data are trained with the Long Short-term Memory (LSTM) and Seasonal Autoregressive Integrated Moving Average (SARIMA) models. Finally, the prepared data and the multivariate influence factors after Factor analysis are predicted using the gated recurrent neural network and attention mechanisms (AttGRU) to obtain the final prediction values. Compared with other models, the STL-FA-AttGRU model produced the lowest errors and achieved more accurate forecasts of hog prices. Therefore, the model proposed in this paper has the potential for other price forecasting, contributing to the development of precision and sustainable agriculture. [ABSTRACT FROM AUTHOR]

Due to intensified off-balance sheet disclosure by regulatory authorities, financial reports now contain a substantial amount of information beyond the financial statements. Consequently, the length of footnotes in financial reports exceeds that of the financial statements. This poses a novel challenge for regulators and users of financial reports in efficiently managing this information. Financial reports, with their clear structure, encompass abundant structured information applicable to information extraction, automatic summarization, and information retrieval. Extracting headings and paragraph content from financial reports enables the acquisition of the annual report text's framework. This paper focuses on extracting the structural framework of annual report texts and introduces an OpenCV-based method for text framework extraction using computer vision. The proposed method employs morphological image dilation to distinguish headings from the main body of the text. Moreover, this paper combines the proposed method with a traditional, rule-based extraction method that exploits the characteristic features of numbers and symbols at the beginning of headings. This combination results in an optimized framework extraction method, producing a more concise text framework. [ABSTRACT FROM AUTHOR]

Fuzzy complementary β-neighborhoods (FCNs) are used to find information relevant to the target in data mining. Based on FCNs, there are six types of covering-based multigranulation fuzzy rough set (CMFRS) models have been constructed, which can be used to deal with the problem of multi-criteria information systems. These CMFRS models are calculated by set representations. However, it is time-consuming and error-prone when set representations are used to compute these CMFRS models in a large multi-criteria information system. Hence, it is important to present a novel method to compute them quickly, which is our motivation for this paper. In this paper, we present the matrix representations of six types of CMFRS models on FCNs. Firstly, some new matrices and matrix operations are given in a multi-criteria information system. Then, matrix representations of three types of optimistic CMFRSs on FCNs are proposed. Moreover, matrix approaches are also used for computing three types of pessimistic CMFRSs on FCNs. Finally, some experiments are presented to show the effectiveness of our approaches. [ABSTRACT FROM AUTHOR]

How to better grasp students' learning preferences in the environment of rapid development of engineering and science and technology so as to guide them to high-quality learning is one of the important research topics in the field of educational technology research today. In order to achieve this goal, this paper utilizes the LDA (Latent Dirichlet Allocation) model for text mining of the survey results on the basis of a survey on students' self-perception evaluation. The results show that the LDA model is capable of extracting terms from text, fuzzy identifying groups of students at different levels and presenting potential logical relationships between the groups, and further analyzing the learning preferences of students at different levels for IT courses. Based on the student's learning needs, this paper proposes recommendations for developing students' learning effectiveness. The LDA method proposed in this paper is a feasible and effective method for assessing students' learning dynamics as it generates cognitive content about students' learning and allows for the timely discovery of students' learning expectations and cutting-edge dynamics. [ABSTRACT FROM AUTHOR]

Awareness of Network Security Situation (abbreviated as NSS for short) technology is in a period of vigorous development recently. NSS technology means network security situational awareness technology. It refers to the technology of collecting, processing, and analyzing various real-time information in the network to understand and evaluate the current network security status. It can not only find network security threats, but also reflect the NSS in the system security metrics, and provide users with targeted security protection measures. Based on data mining methods, this paper analyzed and models perceived threats and security events with data mining algorithms, and improved information security measurement methods based on association analysis. This paper proposed network security information analysis and NSS based on data mining, and analyzed the experimental results of network awareness of NSS information security measurement. The experimental results showed that when the Timer was 8, the accuracy of the awareness of NSS information security measurement method based on data mining can reach 92.89%. The data mining model had the highest accuracy of 93.14% in situation understanding and evaluation of KDDCup-99 dataset. The results showed that the model can accurately predict the NSS. When Timer was 6, the highest accuracy of the model was 92.71%. In general, the NSS prediction mining model based on KDDCup-99 can better understand, evaluate and predict the situation. [ABSTRACT FROM AUTHOR]

Text detection and recognition are widely used in daily life. Although it is a very rich market, it has very difficult challenges in practical application. The complex and changeable natural scenes lead to the complex background of the text in the image, which also reflects the research value of text information recognition and extraction in natural scenes. To solve the many problems faced by the recognition of Chinese characters, such as complex shapes and diverse structures, this paper uses VGG16 to extract features and introduces a two-layer bidirectional LSTM network. It improves Faster R-CNN by using a RPN to extract candidate boxes and adjust the position of candidate regions. In this paper, the improved model Faster BLSTM-CNN is tested, and the effectiveness experiment of feature extraction, the difference comparison before and after the improvement of the algorithm, and the comparison experiment with the traditional recognition algorithm are carried out respectively. And it finally carried out an experimental comparison of the combination of text recognition and positioning, and obtained the results. The algorithm Faster BLSTM-CNN in this paper is better in the localization and recognition of Chinese characters in the dataset. In the natural scene, the recognition rate of Faster BLSTM-CNN in this paper is 81.54%, the positioning accuracy is 88.14%, and the detection speed is 86 ms, which has improved performance. Therefore, the improvement of Faster R-CNN is effective. It can effectively locate and recognize Chinese characters in natural scenes. [ABSTRACT FROM AUTHOR]

The commonly used high utility itemsets mining method for massive data is the intelligent optimization algorithm. In this paper, the WHO (Whale-Hawk Optimization) algorithm is proposed by integrating the harris hawk optimization (HHO) algorithm with the beluga whale optimization (BWO) algorithm. Additionally, a whale initialization strategy based on good point set is proposed. This strategy helps to guide the search in the initial phase and increase the diversity of the population, which in turn improve the convergence speed and algorithm performance. By applying this improved algorithm to the field of high utility itemsets mining, it provides new solutions to optimization problems and data mining problems. To evaluate the performance of the proposed WHO, a large number of experiments are conducted on six datasets, chess, connect, mushroom, accidents, foodmart, and retail, in terms of convergence, recall rates, and runtime. The experimental results show that the convergence of the proposed WHO is optimal in five datasets and has the shortest runtime in all datasets. Compared to PSO, AF, BA, and GA, the average recall rate in the six datasets increased by 32.13%, 49.95%, 12.15%, and 16.24%, respectively. [ABSTRACT FROM AUTHOR]

With the development of artificial intelligence, deep-learning-based log anomaly detection proves to be an important research topic. In this paper, we propose LogCSS, a novel log anomaly detection framework based on the Context-Semantics-Statistics Convolutional Neural Network (CSSCNN). It is the first model that uses BERT (Bidirectional Encoder Representation from Transformers) and CNN (Convolutional Neural Network) to extract the semantic, temporal, and correlational features of the logs. We combine the features with the statistic information of log templates for the classification model to improve the accuracy. We also propose a technique, DOOT (Deals with the Out-Of-Templates), for online template matching. The experimental research shows that our framework improves the average F1 score of the six best algorithms in the industry by more than 5% on the open-source dataset HDFS, and improves the average F1 score of the six best algorithms in the industry by more than 8% on the BGL dataset, LogCSS also performs better than other similar methods on our own constructed dataset. [ABSTRACT FROM AUTHOR]

Assessing the effectiveness of physical education instruction, students' learning, and the feedback received from the teaching process are all vital components of the physical education teaching process in colleges and universities. Improving the quality of physical education instruction in these settings is essential. With its ability to drive the digital revolution of physical education in schools, intelligent technology is bringing about significant changes in the field of education and drawing attention from people from all walks of life. To assess intelligent technology's impact on physical education instruction in a scientific manner, this study utilizes the latest intelligent analysis and sensing data mining to design an intelligent physical education measurement and evaluation model, which utilizes GPS positioning, built-in maps, and gravity sensing to provide real-time feedback on the trajectory, distance, and time of the movement, and then calculates the real-time and average speed of the movement, as different students' body postures to achieve the the same effect when the required speed is not the same, this paper randomly selected students with different BMI index for empirical analysis. The experimental results show that the principal components of the factor analysis extracted four common factors with a cumulative contribution rate of 69.5%, and the test-retest reliability of the four dimensions is 0.665–0.862. [ABSTRACT FROM AUTHOR]

Addressing missing values is a persistent challenge in the field of data mining. The presence of incomplete data can significantly compromise the overall data quality. Consequently, it is crucial to handle incomplete data efficiently. This paper presents a novel approach for imputing missing values that incorporates Kernelized Fuzzy C-Means (KFCM) clustering and proposes a method termed LIKFCM, which combines its benefits with Linear Interpolation (LI). The proposed LIKFCM's performance is assessed through a comparison against nine state-of-the-art imputation techniques (mean, median, LI, EMI, KNNI, KMI, FKMI, LIFCM, and LIPFCM) across ten widely used real-world datasets from the UCI repository with six combinations of missing ratios to assess the efficacy of the proposed imputation method. From the experimental results, it is evident that our proposed method outperforms the existing imputation methods with significant improvements in terms of RMSE & MAE for these datasets. Additionally, experiments examining the effect of missing values validate the robustness of the proposed approach by handling different missing ratios. The performance validation of the proposed approach against other state-of-the-art imputation methods has been conducted utilizing a Kendall's W statistical test, involving a comparison of their mean ranks across different missing ratios. The outcomes indicate that LIKFCM has outperformed other imputation methods, attaining the highest rank in terms of different evaluation criteria. [ABSTRACT FROM AUTHOR]

Association rule mining (ARM) is an important research issue in the field of data mining that aims to find relations among different items in binary databases. The conventional ARM algorithms consider the frequency of the items in binary databases, which is not sufficient for real time applications. In this paper, a novel hash table based Type-2 fuzzy mining algorithm (T2FM) with an efficient pruning strategy is presented for discovering multiple fuzzy frequent itemsets from quantitative databases. The algorithm employs a hash table based structure for efficient storage and retrieval of item/itemset which reduces the search efficiency to O(1) or constant time. Previously, type-2 based Apriori and FP-growth based fuzzy frequent itemsets mining were proposed, which required large amounts of computation and a greater number of candidate generation and processing. Meanwhile, the proposed approach reduces a huge amount of computation by finding the common keys before the actual intersection operation takes place. An efficient pruning strategy is proposed to avoid unpromising candidates in order to speed up the computations. Several experiments are carried out to verify the efficiency of the approach in terms of runtime and memory for different minimum support threshold and the results show that the designed approach provides better performance compared to the state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Outlier detection is critically important in the field of data mining. Real-world data have the impreciseness and ambiguity which can be handled by means of rough set theory. Information entropy is an effective way to measure the uncertainty in an information system. Most outlier detection methods may be called unsupervised outlier detection because they are only dealt with unlabeled data. When sufficient labeled data are available, these methods are used in a decision information system, which means that the decision attribute is discarded. Thus, these methods maybe not right for outlier detection in a a decision information system. This paper proposes supervised outlier detection using conditional information entropy and rough set theory. Firstly, conditional information entropy in a decision information system based on rough set theory is calculated, which provides a more comprehensive measure of uncertainty. Then, the relative entropy and relative cardinality are put forward. Next, the degree of outlierness and weight function are presented to find outlier factors. Finally, a conditional information entropy-based outlier detection algorithm is given. The performance of the given algorithm is evaluated and compared with the existing outlier detection algorithms such as LOF, KNN, Forest, SVM, IE, and ECOD. Twelve data sets have been taken from UCI to prove its efficiency and performance. For example, the AUC value of CIE algorithm in the Hayes data set is 0.949, and the AUC values of LOF, KNN, SVM, Forest, IE and ECOD algorithms in the Hayes data set are 0.647, 0.572, 0.680, 0.676, 0.928 and 0.667, respectively. The advantage of the proposed outlier detection method is that it fully utilizes the decision information. [ABSTRACT FROM AUTHOR]

It is obvious that the problem of Frequent Itemset Mining (FIM) is very popular in data mining, which generates frequent itemsets from a transaction database. An extension of the frequent itemset mining is High Utility Itemset Mining (HUIM) which identifies itemsets with high utility from the transaction database. This gains popularity in data mining, because it identifies itemsets which have more value but the same was not identified as frequent by Frequent Itemset Mining. HUIM is generally referred to as Utility Mining. The utility of the items is measured based on parameters like cost, profit, quantity or any other measures preferred by the users. Compared to high utility itemsets (HUIs) mining, high average utility itemsets (HAUIs) mining is more precise by considering the number of items in the itemsets. In state-of-the-art algorithms that mines HUIS and HAUIs use a single fixed minimum utility threshold based on which HAUIs are identified. In this paper, the proposed algorithm mines HAUIs from transaction databases using Artificial Fish Swarm Algorithm (AFSA) with computed multiple minimum average utility thresholds. Computing the minimum average utility threshold for each item with the AFSA algorithm outperforms other state-of-the-art HAUI mining algorithms with multiple minimum utility thresholds and user-defined single minimum threshold in terms of number of HAUIs. It is observed that the proposed algorithm outperforms well in terms of execution time, number of candidates generated and memory consumption when compared to the state-of-the-art algorithms. [ABSTRACT FROM AUTHOR]

Concept prerequisite relation refers to the learning order of concepts, which is useful in education. Concept prerequisite learning refers to using machine learning methods to infer prerequisite relation of a concept pair. The process of concept prerequisite learning requires large amounts of labeled data to train classifier. Usually, the labels of prerequisite relation are assigned by specialists. The specialist labelling method is costly. Thus, it is necessary to reduce labeling expense. An effective strategy is using active learning methods. In this paper, we propose a pool-based active learning framework for concept prerequisite learning named PACOL. It is a fact that concept u and concept v cannot be prerequisite of each other simultaneously. The idea of PACOL is to select the concept pair with the greatest deviation between the classifier's prediction and the fact. Besides, PACOL can be used in two situations: when specialists assign three kinds of labels or two kinds of labels. In experiments, we constructed data sets for three subjects. Experimental results on both our constructed data sets and public data sets demonstrate that PACOL outperforms than existing active learning methods in all situations. [ABSTRACT FROM AUTHOR]

Rule acquisition is significant in real life and extensively utilized in data mining. Currently, most studies have constructed rule acquisition algorithms based on the equivalence relation. However, these algorithms need to be more suitable for dominance-based decision systems and should consider applications in multi-scale environments. In this paper, we establish the dominance relation of the single-valued neutrosophic rough set model using the ranking method with the relative distance favorable degree. We then introduce this approach into a multi-scale environment to obtain the dominance relation of the multi-scale single-valued neutrosophic rough set model, resulting in two discernibility matrices and functions. We propose the algorithm for lower approximation optimal scale reduction and further examine the method of rule acquisition based on the discernibility matrix. Finally, we apply these algorithms to four random data sets to verify their effectiveness. [ABSTRACT FROM AUTHOR]

In the initial construction process of smart grid dispatching control system in power grid dispatching control center, because different subsystems are in decentralized development, independent operation and independent management, it is easy to reduce data interconnection, which leads to difficulties in data sharing and restricts the information level of the system. The data is multi-source, and the data format is inconsistent, resulting in the application problems that the data can not be shared, accessed, managed, analyzed and mined in real time among different subsystems. In order to solve the problems of data sharing and mining, this paper constructs a knowledge map entity extraction model to study the power grid fault events. Based on the knowledge map theory, the structured and unstructured data related to power grid dispatching are processed to improve the application efficiency of data. Cleaning the preprocessed data to obtain the corresponding entity value and attribute value. The knowledge extraction model of power grid fault event reasoning knowledge mapping is constructed, and the power grid fault event reasoning knowledge edge mapping system is designed to extract the relationship between events and complete data storage. The experimental results show that the text prediction degree of the proposed model is high, which can reach more than 95; The accuracy is 96.71%, the recall rate is 94.88%, and the F1 value is 9.27%. This proves the feasibility of this study, in order to provide data and theoretical support for intelligent management and real-time dispatching of power grid. [ABSTRACT FROM AUTHOR]

Clustering is widely used in data mining and machine learning. The possibilistic c-means clustering (PCM) method loosens the constraint of the fuzzy c-means clustering (FCM) method to solve the problem of noise sensitivity of FCM. But there is also a new problem: overlapping cluster centers are not suitable for clustering non-cluster distribution data. We propose a novel possibilistic c-means clustering method based on the nearest-neighbour isolation similarity in this paper. All samples are taken as the initial cluster centers in the proposed approach to obtain k sub-clusters iteratively. Then the first b samples farthest from the center of each sub-cluster are chosen to represent the sub-cluster. Afterward, sub-clusters are mapped to the distinguishable space by using these selected samples to calculate the nearest-neighbour isolation similarity of the sub-clusters. Then, adjacent sub-clusters can be merged according to the presented connecting strategy, and finally, C clusters are obtained. Our method proposed in this paper has been tested on 15 UCI benchmark datasets and a synthetic dataset. Experimental results show that our proposed method is suitable for clustering non-cluster distribution data, and the clustering results are better than those of the comparison methods with solid robustness. [ABSTRACT FROM AUTHOR]

Data clustering is a machine learning method for unsupervised learning that is popular in the two areas of data analysis and data mining. The objective is to partition a given dataset into distinct clusters, aiming to maximize the similarity among data objects within the same cluster. In this paper, an improved honey badger algorithm called DELHBA is proposed to solve the clustering problem. In DELHBA, to boost the population's diversity and the performance of global search, the differential evolution method is incorporated into algorithm's initial step. Secondly, the equilibrium pooling technique is included to assist the standard honey badger algorithm (HBA) break free of the local optimum. Finally, the updated honey badger population individuals are updated with Levy flight strategy to produce more potential solutions. Ten famous benchmark test datasets are utilized to evaluate the efficiency of the DELHBA algorithm and to contrast it with twelve of the current most used swarm intelligence algorithms and k-means. Additionally, DELHBA algorithm's performance is assessed using the Wilcoxon rank sum test and Friedman's test. The experimental results show that DELHBA has better clustering accuracy, convergence speed and stability compared with other algorithms, demonstrating its superiority in solving clustering problems. [ABSTRACT FROM AUTHOR]

Gene selection is an important research topic in data mining. A gene decision space means a real-valued decision information system (RVDIS) where objects, conditional attributes and information values are cells, genes and gene expression values, respectively. This paper explores gene selection in a gene decision space based on information entropy and considers its application for gene expression data classification. In the first place, the distance between two cells in a given decision subspace is constructed. In the next place, the binary relations induced by this decision subspace are defined. After that, some information entropy for a gene decision space are investigated. Lastly, several gene selection algorithms in a gene decision space are presented by using the presented information entropy. The presented algorithms are applied to gene expression data classifications. Multiple publicly available gene expression datasets are employed to evaluate the gene selection performances of the proposed algorithms, while two commonly-used classifiers, KNN and CART, are utilized to obtain 10 fold cross validation accuracy of classification (ACC). The classification results demonstrated that the proposed algorithms can lower significantly the number genes selected, achieve the higher ACC, and outperform the other competing methods, such as raw data, Fisher, tSNE, PCA, FMIFRFS and DNEAR, with respect to gene number and ACC. [ABSTRACT FROM AUTHOR]

Detecting and warning Advanced Persistent Threat (APT) malware in Endpoint is essential because the current trend of APT attacker groups is to find ways to spread malware to users and then escalate privileges in the system. In this study, to improve the ability to detect APT malware on Endpoint machines, we propose a novel intelligent cognitive calculation method based on a model combining graph embeddings and Attention using processes generated by executable files. The proposed intelligent cognitive computation method performs 3 main tasks: i) extracting behaviors of processes; ii) aggregating the malware behaviors based on the processes; iii) detecting APT malware based on behavior analysis. To carry out the task (i), we propose to use several data mining techniques: extracting processes from Event IDs in the operating system kernel; extracting abnormal behaviors of processes. For task (ii), a graph embedding (GE) model based on the Graph Convolutional Networks (GCN) network is proposed to be used. For task (iii), based on the results of task (ii), the paper proposes to use a combination of the Convolutional Neural Network (CNN) network and Attention network (called CNN-Attention). The novelty and originality of this study is an intelligent cognitive computation method based on the use, combination, and synchronization of many different data mining techniques to compute, extract, and represent relationships and correlations among APT malware behaviors from processes. Based on this new intelligent cognitive computation method, many meaningful anomalous features and behaviors of APT malware have been synthesized and extracted. The proposals related to data mining methods to extract malware's features and the list of malware's behaviors provided in this paper are new information that has not been published in previous studies. In the experimental section, to demonstrate the effectiveness of the proposed method in detecting APT malware, the study has compared and evaluated it with other approaches. Experimental results in the paper have shown the outstanding efficiency of the proposed method when ensuring all metrics from 96.6% or more (that are 2% to 6% higher than other approaches). Experimental results in the paper have proven that our proposed method not only has scientifically significant but also has practical meaning because the method has helped to improve the efficiency of analyzing and detecting APT malware on Endpoint devices. In addition, this research result also has opened up a new approach for the task of detecting other anomalies on the Endpoint such as malware, unauthorized intrusion, insider, etc. [ABSTRACT FROM AUTHOR]

Visually rich documents, such as forms, invoices, receipts, and ID cards, are ubiquitous in daily business and life. Various methods have been used to convey such diverse information, including text, layout, font size, or text position. Combining these elements in information extraction can improve the result performance. However, previous works have not effectively utilized the cooperation between these rich information sources. Text detection and recognition have been performed without semantic supervision (e.g., entity name annotation), and text information extraction has been performed using only serialized plain text, ignoring rich visual information. This paper presents a method for extracting information from such documents, which integrates textual, non-spatial, and spatial visual features. The method consists of two main steps and uses three deep neural networks. The first step, Text Reading, employs two CNN models (Lightweight DB and C-PREN) for OCR tasks, based on the state-of-the-art models DB and PREN, with two improvements. These improvements include reducing noise by removing the SE block of DB and integrating both context and position features in PREN. The second step, Text Information Extraction, uses a graph convolutional network, RGCN, for name entity recognition. Experiments on self-collected and two public datasets have demonstrated that our method improves the performance of the original models and outperforms other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Complex time series appear in numerous applications and are related to some essential physiological and natural systems. Their comparison faces big challenges: 1) with different complexity; 2) with significant phase shift in one series or shift∖on the time axis. Existing methods work well for periodic time-series data, but fail to produce satisfactory results in complex time-series. In this paper, we introduce a novel distance function based on the evolution rule for complex time series comparison. Here, the evolution rule, as the innate generative mechanism of time series, is creatively used to characterize complicated dynamics from complex time series. The comparison includes different level comparisons: the coarse level is to compare the difference in complexity, and the fine level is to compare the difference in actual evolution behavior. The proposed method is inspired by the observation that similar sequences come from the same source, e.g. a person's heart, in the case of ECG, thus two similar series will have the same innate generative mechanism. The performance has been verified by the conducting experiments, and the experiment results show that the proposed method is superior to the previously existing methods in clustering and classification on some real data sets. [ABSTRACT FROM AUTHOR]

In today's big data era, there are a large number of unstructured information resources on the web. Natural language processing researchers have been working hard to figure out how to extract useful information from them. Entity Relation Extraction is a crucial step in Information Extraction and provides technical support for Knowledge Graphs, Intelligent Q&A systems and Intelligent Retrieval. In this paper, we present a comprehensive history of entity relation extraction and introduce the relation extraction methods based on Machine Mearning, the relation extraction methods based on Deep Learning and the relation extraction methods for open domains. Then we summarize the characteristics and representative results of each type of method and introduce the common datasets and evaluation systems for entity relation extraction. Finally, we summarize current entity relation extraction methods and look forward to future technologies. [ABSTRACT FROM AUTHOR]

The generalized neighborhood system-based rough set is an important extension of Pawlak's rough set. The rough sets based on generalized neighborhood systems include two basic models: optimistic and pessimistic rough sets. In this paper, we give a further study on pessimistic rough sets. At first, to regain some properties of Pawlak's rough sets that are lost in pessimistic rough sets, we introduce the mediate, transitive, positive (negative) alliance conditions for generalized neighborhood systems. At second, some approximation operators generated by special generalized neighborhood systems are characterized, which include serial, reflexive, symmetric, mediate, transitive, and negative alliance generalized neighborhood systems and their combinations (e.g. reflexive and transitive). At third, we discuss the topologies generated by the upper and lower approximation operators of the pessimistic rough sets. Finally, combining practical examples, we apply pessimistic rough sets to rule extraction of incomplete information systems. Particularly, we prove that different decision rules can be obtained when different neighborhood systems are chosen. This enables decision makers to choose decisions based on personal preferences. [ABSTRACT FROM AUTHOR]

Advanced Persistent Threat (APT) attack detection and monitoring has attracted a lot of attention recently when this type of cyber-attacks is growing in both number and dangerous levels. In this paper, a new APT attack model, which is the combination of three different neural network layers including: Multi-layer Perceptron (MLP), Inference (I), and Graph Convolutional Networks (GCN) is proposed. The new model is named MIG for short. In this model, the MLP layer is in charge of aggregating and extracting properties of the IPs based on flow network in Network traffic, while the Inference layer is responsible for building IP information profiles by grouping and concatenating flow networks generated from the same IP. Finally, the GCN layer is used for analyzing and reconstructing IP features based on the behavior extraction process from IP information records. The APT attacks detection method based on network traffic using this MIG model is new, and has yet been proposed and applied anywhere. The novelty and uniqueness of this method is the combination of many different data mining techniques in order to calculate, extract and represent the relationship and the correlation between APT attack behaviors based on Network traffic. In MIG model, many meaningful anomalous properties and behaviors of APT attacks are synthesized and extracted, which help improve the performance of APT attack detection. The experimental results showed that the proposed method is meaningful in both theory and practice since the MIG model not only improves the ability to correctly detect APT attacks in network traffic but also minimizes false alarms. [ABSTRACT FROM AUTHOR]

Clustering plays a fundamental task in the process of data mining, which remains more demanding due to the ever-increasing dimension of accessible datasets. Big data is considered more populous as it has the ability to handle various sources and formats of data under numerous highly developed technologies. This paper devises a robust and effective optimization-based Internet of Things (IoT) routing technique, named Student Psychology Based Optimization (SPBO) -based routing for the big data clustering. When the routing phase is done, big data clustering is carried out using the Deep Fractional Calculus-Improved Invasive Weed Optimization fuzzy clustering (Deep FC-IIWO fuzzy clustering) approach. Here, the Mapreduce framework is used to minimizing the over fitting issues during big data clustering. The process of feature selection is performed in the mapper phase in order to select the major features using Minkowski distance, whereas the clustering procedure is carried out in the reducer phase by Deep FC-IIWO fuzzy clustering, where the FC-IIWO technique is designed by the hybridization of Improved Invasive Weed Optimizer (IIWO) and Fractional Calculus (FC). The developed SPBO-based routing approach achieved effective performance in terms of energy, clustering accuracy, jaccard coefficient, rand coefficient, computational time and space complexity of 0.605 J, 0.935, 0.947, 0.954, 2100.6 s and 72KB respectively. [ABSTRACT FROM AUTHOR]

Feature selection is one basic technology for data mining. This paper investigates feature selection for interval-valued data via fuzzy rough iterative computation model (FRIC-model). To depict the similarity between samples in an interval-valued decision information system (IVDIS), the fuzzy symmetry relation in an IVDIS is first introduced from the perspective of "The similarity between information values is fed back to the feature set". After that, several attribute evaluation functions, such as fuzzy positive regions, dependency functions and attribute importance functions are defined. Subsequently, FRIC-model for interval-valued data is established by using the iterations of these functions. Next, An feature selection algorithm in an IVDIS based on this model is presented. Lastly, numerical experiments and statistics tests are carried out to estimate the performance of the presented algorithm. The experimental results illustrate that the presented algorithm maintains high classification accuracy, and does not occupy too much memory. These findings will provide new perspective for feature selection in an IVDIS. [ABSTRACT FROM AUTHOR]

Mining high utility itemsets (HUIs) from transaction databases is one of the current research areas in the data mining field. HUI mining finds itemsets whose utility meets a predefined threshold. It enables users to quantify the usefulness or preferences of products by utilizing different values. Since utility mining approaches do not satisfy the downward closure property, the cost of candidate generation for HUI mining in terms of time and memory space is excessive. This paper presents Genetic Algorithm based Particle Swarm Optimization (GA-PSO), which can efficiently prune down the number of candidates and optimally acquire the complete set of high utility itemsets. The proposed algorithm's performance is assessed using the synthetic dataset T20.I6.D100K and the real-time supermarket dataset, which comprises 38765 transactions and 167 unique products. It performs very effectively in terms of time and memory on large databases constituted of small transactions, which are challenging for existing high utility itemsets mining algorithms to manage. Experiments on real-world applications show the importance of high utility itemsets in business decisions, as well as the distinction between frequent and high utility itemsets. [ABSTRACT FROM AUTHOR]

The important task in the medical field is the early detection of disease. Heart disease is one of the greatest challenging diseases in all other diseases subsequently 17.3 million people died once a year due to heart disease. A minute error in heart disease diagnosis is a risk for an individual lifespan. Precise heart disease diagnosis is consequently critical. Different approaches including data mining have been used for the prediction of heart disease. However, there are some solemn concerns related to the data quality for example inconsistencies, missing values, noise, high dimensionality, and imbalanced statistics. In order to improve the accuracy of Data Mining based prediction systems, techniques for data preparation were applied to increase the quality of the data. The foremost objective of this paper is to highlight and summarize the research work about (i) data preparation techniques mostly used, (ii) the impact of pre-processing procedures on the accuracy of a heart disease prediction system, (iii) classifier enactment with data pre-processing techniques, (4) comparison in terms of accuracy of the different pre-processing model. A systematic literature review on the use of data pre-processing in heart disease diagnosis is carried out from January 2001 to July 2021 by studying the published material. Almost 30 studies were designated and examined related to the above-mentioned benchmarks. The literature review concludes that data reduction and data cleaning pre-processing techniques are mostly used in heart disease prediction systems. Overall this study concludes that data pre-processing has improved the accuracy of models used for heart disease prediction. Some hybrid models including (ANN+CHI), (ANN+PCA), (DNN+CHI) and (SVM+PCA) have shown improved accuracy level. However, due to the lack of clarification, there is a number of limitations and challenges in order to implementing these models in the real world. [ABSTRACT FROM AUTHOR]

In the deep learning-based video action recognitio, the function of the neural network is to acquire spatial information, motion information, and the associated information of the above two kinds of information over an uneven time span. This paper puts forward a network extracting video sequence semantic information based on deep integration of local Spatial-Temporal information. The network uses 2D Convolutional Neural Network (2DCNN) and Multi Spatial-Temporal scale 3D Convolutional Neural Network (MST_3DCNN) respectively to extract spatial information and motion information. Spatial information and motion information of the same time quantum receive 3D convolutional integration to generate the temporary Spatial-Temporal information of a certain moment. Then, the Spatial-Temporal information of multiple single moments enters Temporal Pyramid Net (TPN) to generate the local Spatial-Temporal information of multiple time scales. Finally, bidirectional recurrent neutral network is used to act on the Spatial-Temporal information of all parts so as to acquire the context information spanning the length of the entire video, which endows the network with video context information extraction capability. Through the experiments on the three video action recognitio common experimental data sets UCF101, UCF11, UCFSports, the Spatial-Temporal information deep fusion network proposed in this paper has a high correct recognition rate in the task of video action recognitio. [ABSTRACT FROM AUTHOR]

In the deep learning-based video action recognitio, the function of the neural network is to acquire spatial information, motion information, and the associated information of the above two kinds of information over an uneven time span. This paper puts forward a network extracting video sequence semantic information based on deep integration of local Spatial-Temporal information. The network uses 2D Convolutional Neural Network (2DCNN) and Multi Spatial-Temporal scale 3D Convolutional Neural Network (MST_3DCNN) respectively to extract spatial information and motion information. Spatial information and motion information of the same time quantum receive 3D convolutional integration to generate the temporary Spatial-Temporal information of a certain moment. Then, the Spatial-Temporal information of multiple single moments enters Temporal Pyramid Net (TPN) to generate the local Spatial-Temporal information of multiple time scales. Finally, bidirectional recurrent neutral network is used to act on the Spatial-Temporal information of all parts so as to acquire the context information spanning the length of the entire video, which endows the network with video context information extraction capability. Through the experiments on the three video action recognitio common experimental data sets UCF101, UCF11, UCFSports, the Spatial-Temporal information deep fusion network proposed in this paper has a high correct recognition rate in the task of video action recognitio. [ABSTRACT FROM AUTHOR]

The researcher proposed the concept of Top-K high-utility itemsets mining over data streams. Users directly specify the number K of high-utility itemsets they wish to obtain for mining with no need to set a minimum utility threshold. There exist some problems in current Top-K high-utility itemsets mining algorithms over data streams including the complex construction process of the storage structure, the inefficiency of threshold raising strategies and utility pruning strategies, and large scale of the search space, etc., which still can not meet the requirement of real-time processing over data streams with limited time and memory constraints. To solve this problem, this paper proposes an efficient algorithm based on dataset projection for mining Top-K high-utility itemsets from a data stream. A data structure CIUDataListSW is also proposed, which stores the position of the item in the transaction to effectively obtain the initial projected dataset of the item. In order to improve the projection efficiency, this paper innovates a new reorganization technology for projected transactions in common batches to maintain the sort order of transactions in the process of dataset projection. Dual pruning strategy and transaction merging mechanism are also used to further reduce search space and dataset scanning costs. In addition, based on the proposed CUDHSW structure, an efficient threshold raising strategy CUD is used, and a new threshold raising strategy CUDCB is designed to further shorten the mining time. Experimental results show that the algorithm has great advantages in running time and memory consumption, and it is especially suitable for the mining of high-utility itemsets of dense datasets. [ABSTRACT FROM AUTHOR]

To improve the data mining effect of large-scale (sports) competitions and improve the results of competition prediction and analysis, based on the online data migration model, this paper establishes a system model for processing applications of transmitting nodes, relay nodes and receiving nodes in the competition network, and proposes an online distributed cost optimization control strategy to be responsible for the operation and processing of applications in the communication system. The control strategy realizes that while ensuring the stability of the application queue, the optimization target system overhead is infinitely close to the theoretical optimal value. In addition, according to the competition data mining and prediction requirements, this paper constructs a system structure model, and designs experiments to verify the system performance. The research results show that the performance of the data mining and prediction system of large-scale (sports) competition constructed in this paper meets actual needs. [ABSTRACT FROM AUTHOR]

In order to improve the efficiency of sentiment analysis of students in ideological and political classrooms, under the guidance of artificial intelligence ideas, this paper combines data mining and machine learning algorithms to improve and propose a method for quantifying the semantic ambiguity of sentiment words. Moreover, this paper designs different quantitative calculation methods of sentiment polarity intensity, and constructs video image sentiment recognition, text sentiment recognition, and speech sentiment recognition functional modules to obtain a combined sentiment recognition model. In addition, this article studies student emotions in ideological and political classrooms from the perspective of multimodal transfer learning, and optimizes the deep representation of images and texts and their corresponding deep networks through single-depth discriminative correlation analysis. Finally, this paper designs experiments to verify the model effect from two perspectives of single factor sentiment analysis and multi-factor sentiment analysis. The research results show that comprehensive analysis of multiple factors can effectively improve the effect of sentiment analysis of students in ideological and political classrooms, and enhance the effect of ideological and political classroom teaching. [ABSTRACT FROM AUTHOR]

In present scenario, Heart Disease has become the vital cause of mortality and diagnosis of heart diseases is a great confrontation in the field of medical data analysis. Data Mining is an efficient technique for processing and analyzing larger databases for deriving hidden knowledge appropriately. Hence, it is incorporated in medical data analysis for assisting in effective decision making and disease predictions. With that concern, this paper concentrates on framing an Integrated Model for Heart Disease Diagnosis (IM-HDD) using the advanced data mining conceits. The model considers the significant features of patient data that are available in benchmark datasets. Here, the main objective of the proposed model is to enhance the classification accuracy of patient data on classes under NORMAL and ABNORMAL. For enhancing the classification accuracy, the proposed integrated model utilizes the algorithms such as Decision Tree Algorithm, Naive Baye's Classification and Ensemble Classifiers called Random Forest and Bagging. Further, performance evaluation is performed for analyzing the proposed work. For that, images from UCI repository are utilized and the comparative analysis shows that the proposed work produces better results than the existing models compared. [ABSTRACT FROM AUTHOR]

Fuzzy clustering is an important research field in pattern recognition, machine learning and image processing. The fuzzy C-means (FCM) clustering algorithm is one of the most common fuzzy clustering algorithms. However, it requires a given number of clusters in advance for accurate clustering of data sets, so it is necessary to put forward a better clustering validity index to verify the clustering results. This paper presents a ratio component-wise design method of clustering validity function based on FCM clustering method. By permutation and combination of six clustering validity components representing different meanings in the form of ratio, 49 different clustering validity functions are formed. Then, these functions are verified experimentally under six kinds of UCI data sets, and a clustering validity function with the simplest structure and the best classification effect is selected by comparison. Finally, this function is compared with seven traditional clustering validity functions on eight UCI data sets. The simulation results show that the proposed validity function can better verify the classification results and determine the optimal clustering number of different data sets. [ABSTRACT FROM AUTHOR]

Datasets mainly consist of ambiguous objects, redundant and uncertain attribute values which increase complexity, time and cost in Knowledge Discovery in Databases (KDD) process. Rough set-based attribute reduction techniques deals with ambiguity but fails to handle uncertainty available in a real-valued dataset. Combining rough set with intuitionistic fuzzy set provides a great opportunity to the researchers working on attribute reduction of real-valued datasets as it provides better results when compared to the traditional fuzzy rough set theory. In this paper, we present a new intuitionistic fuzzy rough set model for attribute reduction to avoid misclassification and perturbation by handling hesitancy, ambiguity and uncertainty present in a dataset. We define an intuitionistic fuzzy tolerance relation between two objects along with lower and upper approximations based on that relation. Next, the concept of Degree of dependency is utilized to present attribute reduction by using model due to its better performing nature over other methods. The algorithm of the proposed technique is applied on benchmark datasets to perform a comparative study with recent approaches. We obtain the best result for the reduced Breast Cancer dataset by our proposed approach, with an accuracy of 98.96% along with 0.90 standard deviation by using SMO classifier. Finally, our proposed method is used to present a methodology to improve the prediction of umami peptides. Here, we record the best results with sensitivity, specificity, accuracy, AUC, and MCC of 96.8%, 93.6%, 97.7%, 0.988, and 0.899, respectively. From the experiments, it can be concluded that our method outperforms the existing methods. [ABSTRACT FROM AUTHOR]

The ultimate goal of listed companies is to maximize shareholders' wealth. With the increasingly fierce market competition, enterprise managers are constantly exploring the key indicators that have an important impact on the financial performance (FP) of enterprises, and achieve the expected FP of shareholders by improving these key indicators. On the basis of the existing enterprise performance measurement system and index research, through expert scoring to determine the secondary indicators, this paper selects 87 small and medium-sized board listed companies which officially announced the implementation of equity incentive from 2009 to 2012 as the sample, takes the financial information disclosed in 2013 as the empirical data, and analyzes the traditional multiple linear regression analysis (MLR) When dealing with big data, especially the data with hierarchical structure, this paper proposes a partial regression coefficient calculation model based on hierarchical data, constructs a multiple nonlinear regression model, and concludes through empirical analysis that there is a nonlinear correlation between equity incentive ratio and corporate performance, and that there is an interval effect between equity incentive ratio and corporate performance. We also present Fuzzy based financial performance prediction of listed companies. Finally, we demonstrate Comparative analysis for financial prediction in term of accuracy between multiple regression model and fuzzy logic system and result deduce that fuzzy logic gives better accuracy than regression model. [ABSTRACT FROM AUTHOR]

At present, the theoretical and experimental teaching parts of chemistry teaching are difficult to present through online teaching, and the teaching effect is difficult to effectively improve. In order to improve the effect of online teaching of chemistry courses and discover the problems in teaching in a timely and effective manner, this paper builds the corresponding teaching system, optimizes the performance of the system with key information search and big data cloud platform, improves the data mining ability and data analysis ability, and improves the system running speed. Moreover, this article constructs functional modules according to the actual needs of chemistry course network teaching and constructs sub-modules for functional modules. The constructed model can be displayed in the form of a webpage, and the model has the ability of data mining and problem analysis of chemistry course network teaching. In addition, in order to verify the effect of the model, this paper designs experiments to analyze its performance. The research results show that the system constructed in this paper has good performance. [ABSTRACT FROM AUTHOR]

The association rule algorithm in data mining is used to study the factors that may affect students' performance, to make suggestions for teaching work, and to provide decision-making basis for teachers and teaching administrators, which has practical significance. There are many potential applications for facial expression recognition technology. For example, in the teaching process, facial expression recognition technology helps teachers understand students and judge students' reactions to certain things. Based on the current research status of emotion recognition and data mining algorithms, this paper improves the AprioriTid algorithm and constructs an online teaching quality evaluation model based on teaching needs. In addition, this article applies the model constructed in this article to the evaluation of English online teaching quality and evaluates teaching quality through data mining. The experimental research shows that the model constructed in this paper has good performance. [ABSTRACT FROM AUTHOR]

The heterogeneity of inflation expectations, especially the residents' inflation expectations, has a great influence on controlling the actual inflation rate and the effective implementation of my country's monetary policy. In the process of monetary policy formulation, the monetary authorities need to pay more attention to the heterogeneous expectations among microeconomic individuals. This paper introduces the genetic algorithm, a new artificial intelligence method, to analyze the demand for the heterogeneity of inflation expectations and explains the basic steps to use it and how to apply it to explain problems in economics. Moreover, this paper uses a genetic algorithm-based generation overlap model to simulate the dynamic evolution of inflation heterogeneity among residents and the equilibrium selection process of price levels in a wide search space. The results of the simulation experiment show that it is of practical significance to use genetic algorithms to simulate the dynamic process of the heterogeneity of residents' inflation expectations. [ABSTRACT FROM AUTHOR]

Precision marketing is faced with multiple levels of problems, such as pollution of the data environment and unscientific algorithms, which need to be sorted out urgently. Based on neural network technology, this paper constructs a neural network-based precision marketing model and focuses on data mining to study user churn prediction and user value enhancement, which are the two most important factors affecting marketing revenue. Moreover, this paper conducts an empirical test of the product strategy and market strategy adopted by big data precision marketing. According to the characteristics of the user population and the application scenarios of the product, this paper puts the corresponding precision marketing methods in a targeted manner and analyzes the performance of the model through experimental research. The research results show that precision marketing methods based on big data information platforms need to be more detailed and more comprehensive. At the same time, precision marketing methods need to correspond to the sensitive information characteristics of target users and consider the background and current situation of actual market execution to effectively play it role. [ABSTRACT FROM AUTHOR]

The irrationality between the procurement and distribution of the logistics system increases unnecessary circulation links and greatly reduces logistics efficiency, which not only causes a waste of transportation resources, but also increases logistics costs. In order to improve the operation efficiency of the logistics system, based on the improved neural network algorithm, this paper combines the logistic regression algorithm to construct a logistics demand forecasting model based on the improved neural network algorithm. Moreover, according to the characteristics of the complexity of the data in the data mining task itself, this article optimizes the ladder network structure, and combines its supervisory decision-making part with the shallow network to make the model more suitable for logistics demand forecasting. In addition, this paper analyzes the performance of the model based on examples and uses the grey relational analysis method to give the degree of correlation between each influencing factor and logistics demand. The research results show that the model constructed in this paper is reasonable and can be analyzed from a practical perspective. [ABSTRACT FROM AUTHOR]

Outlier detection is an important branch of data mining. This paper proposes an advanced fast density peak outlier detection algorithm based on the characteristics of big data. The algorithm is an outlier detection method based on the improved density peak clustering algorithm. This paper improves the original algorithm. From the perspective of outlier detection, although it is a clustering idea, it avoids the clustering process, reduces the time complexity of the cluster-based outlier detection algorithm, and absorbs. The outlier detection based on neighbors is not sensitive to data dimensions and other advantages. In the power industry, outlier detection can be used in areas such as grid fault detection, equipment fault detection, and power abnormality detection. The simulation experiment of outlier detection based on the daily load curve of single and multiple transformers in a certain province shows that the improved algorithm can effectively detect outliers in the data. [ABSTRACT FROM AUTHOR]

With the development of information technology, intelligent control technology is the comprehensive application of modern management techniques and methods. This paper mainly studies the intelligent financial decision support system based on data mining. This paper mainly introduces data mining technology, an intelligent financial decision support system and the application of data mining technology in an intelligent financial decision support system. The intelligent financial decision support system proposed in this paper uses a relational database to store massive business data, to improve the system expansion ability. By using mathematical model and data mining technology, an intelligent financial decision support system can automatically analyze data, discover the internal relationship between data, and mine the model that plays an important role in prediction and decision-making behavior, to establish a new business model, help decision-makers to make marketing strategies in line with the market and make correct decisions. The experimental results show that: the actual total profit of the company in 2019 is 43.37 million yuan, and the predicted total profit in 2019 is 43.38 million yuan. The similarity between the actual total profit in 2019 and the predicted total profit in 2019 is 99.98%. In 2019, the company’s sales revenue is 37.61 million yuan. The predicted sales revenue in 2019 is 37.62 million yuan, which is 99.97% similar to the actual sales revenue in 2019. The managers of the company can make marketing strategies and make correct decisions according to the sales revenue forecast in 2020. [ABSTRACT FROM AUTHOR]

Frequent pattern mining (FIM) identifies the most important patterns in data sets. However, due to the huge and high-dimensional nature of transactional data, classical pattern mining techniques suffer from the limitations of dimensions and data annotations. Recently, data mining while preserving privacy is considered as an important research area. Information privacy is a tradeoff that must be considered when using data. Through many years, privacy-preserving data mining (PPDM) made use of methods that are mostly based on heuristics. The operation of deletion was used to hide the sensitive information in PPDM. In this study, we used deep active learning to protect private and sensitive information. This paper combines entropy-based active learning with an attention-based approach to effectively hide sensitive patterns. The constructed models are then validated using high-dimensional transactional data with attention-based and active learning methods in a reinforcement environment. The results show that the proposed model can support and improve the effectiveness of decision-making by increasing the number of training instances through the use of a pooling technique and an entropy uncertainty measure. The proposed paradigm can achieve data sanitization by the hiding sensitive items and avoiding to hide the non-sensitive items. The model outperforms greedy, genetic, and particle swarm optimization approaches. [ABSTRACT FROM AUTHOR]

Artificial intelligence model combined with data mining technology can mine useful data from college ideological and political education management, and conduct process evaluation and teaching management. Therefore, based on the superiority of data mining technology and artificial intelligence system, this paper improves the traditional algorithm and constructs a university ideological and political education management model based on big data artificial intelligence. Moreover, this study uses a local sensitive hash function to generate representative point sets and uses the generated representative point sets for clustering operations. In order to verify the performance of the algorithm model, a control experiment is designed to compare the algorithm of this paper with traditional data mining methods. It can be seen from the research results that the algorithm model constructed in this paper has good performance and can be applied to practice. [ABSTRACT FROM AUTHOR]

This article first studies and designs the college English test framework and performance analysis system. The author analyzes a large number of data collected by the system in three dimensions: using data mining title association models, using machine learning to merge college English score prediction models, and finally diagnosing on the basis of the sexual evaluation model, the author designed and implemented a test paper algorithm based on the association rules of the question type, and carried out relevant verification from the three aspects of test paper time, test question recommendation and improvement according to scores. Finally, according to the needs analysis, the author uses the diagnostic evaluation model and related test paper algorithm to design and implement the diagnostic evaluation model, which is added to the college English diagnostic practice system. It can be obtained through comparative experiments that the paper-based algorithm based on the diagnostic evaluation model proposed in this paper can effectively give better practice guidance and test question recommendation to the learner’s learning status and knowledge point problem obstacles, and can effectively improve learning. The achievements of the authors have broad application prospects and research value. [ABSTRACT FROM AUTHOR]

At present, the data mining technology is introduced into the analysis of English scores, the data is deeply explored and analyzed reasonably, and the analysis results are used to guide the smooth development of teaching, which is conducive to improving the quality of English teaching. The main work of this thesis is based on the background of this study: taking the academic performance of college students as the application background, this paper first introduces the basic theoretical knowledge of data mining and the application status of data mining technology in education field. Secondly, this paper establishes a student performance database and uses data mining technology to carry out in-depth mining of the established performance database. Finally, the mining results are analyzed, and the factors affecting students' academic performance are obtained. These analysis results have important reference value for the future improvement of teaching work in colleges and universities. [ABSTRACT FROM AUTHOR]