Average Test Time Research Articles

A Lightweight Convolutional Neural Network-Reformer Model for Efficient Epileptic Seizure Detection.

A real-time and reliable automatic detection system for epileptic seizures holds significant value in assisting physicians with rapid diagnosis and treatment of epilepsy. Aiming to address this issue, a novel lightweight model called Convolutional Neural Network-Reformer (CNN-Reformer) is proposed for seizure detection on long-term EEG.The CNN-Reformer consists of two main parts: the Data Reshaping (DR) module and the Efficient Attention and Concentration (EAC) module. This framework reduces network parameters while retaining effective feature extraction of multi-channel EEGs, thereby improving model computational efficiency and real-time performance. Initially, the raw EEG signals undergo Discrete Wavelet Transform (DWT) for signal filtering, and then fed into the DR module for data compression and reshaping while preserving local features. Subsequently, these local features are sent to the EAC module to extract global features and perform categorization. Post-processing involving sliding window averaging, thresholding, and collar techniques is further deployed to reduce the false detection rate (FDR) and improve detection performance. On the CHB-MIT scalp EEG dataset, our method achieves an average sensitivity of 97.57%, accuracy of 98.09%, and specificity of 98.11% at segment-based level, and a sensitivity of 96.81%, along with FDR of 0.27/h, and latency of 17.81 s at the event-based level. On the SH-SDU dataset we collected, our method yielded segment-based sensitivity of 94.51%, specificity of 92.83%, and accuracy of 92.81%, along with event-based sensitivity of 94.11%. The average testing time for 1[Formula: see text]h of multi-channel EEG signals is 1.92[Formula: see text]s. The excellent results and fast computational speed of the CNN-Reformer model demonstrate its potential for efficient seizure detection.

Self-Training-Transductive-Learning Broad Learning System (STTL-BLS): A model for effective and efficient image classification

A novel model called Self-Training-Transductive-Learning Broad Learning System (STTL-BLS) is proposed for image classification. The model consists of two key blocks: Feature Block (FB) and Enhancement Block (EB). The FB utilizes the Proportion of Large Values Attention (PLVA) technique and an Encoder for feature extraction. Multiple FBs are cascaded in the model to learn discriminative features. The Enhancement Block (EB) enhances feature learning and prevents under-fitting on complex datasets. Additionally, an architecture that combines characteristics of Broad Learning System (BLS) and gradient descent is designed for STTL-BLS, enabling the model to leverage the advantages of both BLS and Convolutional Neural Networks (CNNs). Moreover, a training algorithm (STTL) that combines self-training and transductive learning is presented for the model to improve its generalization ability. Experimental results demonstrate that the accuracy of the proposed model surpasses all compared BLS variants and performs comparably or even superior to deep networks: on small-scale datasets, STTL-BLS has an average accuracy improvement of 14.82 percentage points compared to other models; on large-scale datasets, 12.95 percentage points. Notably, the proposed model exhibits low time complexity, particularly with the shortest testing time on the small-scale datasets among all compared models: it has an average testing time of 46.4 s less than other models. It proves to be an additional valuable solution for image classification tasks on both small- and large-scale datasets. The source code for this paper can be accessed at https://github.com/threedteam/sttl_bls.

A Systematic Analysis and Review on Intrusion Detection Systems Using Machine Learning and Deep Learning Algorithms

An intrusion detection system (IDS) is crucial for defending computer networks and systems from cyberattacks, unauthorized entry, and harmful activities. Machine learning (ML) and deep learning (DL) based IDS is a security solution that uses sophisticated algorithms to automatically identify and predict malicious activity occurring within a computer network. It improves the network's security and identification of threats using various algorithms to monitor network traffic patterns, spot anomalies, and discern between normal and abnormal behavior. This study reviews 60 papers on the topic of IDS that implement various ML and DL techniques. The most commonly used techniques are the support vector machine (SVM), decision tree (DT), random forest (RF), K nearest neighbors, gradient boosting(GB), Naïve-Bayes (NB), multilayer perceptron (MLP), artificial neural network, recurrent neural network, and convolutional neural network (CNN). These techniques are tested on four different datasets: KDD Cup, NSL-KDD, UNSW-NB15, and Kyoto. The experimentation showed that, among ML algorithms, the DT classifier has the best average training time of 2.8 s, the best average testing time of 0.08 s, but achieved an average accuracy of 97.46% across all datasets. On the other hand, the NB classifier is easier to implement but took an average of 4.40 s in training time, 1.28 s in testing time, and has the least average accuracy of 74.22% across all datasets. The more sophisticated techniques such as SVM, MLP, GB, and CNN are time consuming with CNN taking the highest time in three out of four datasets. The RF algorithm achieved an average accuracy of 99.51%, the highest level of accuracy among all algorithms. In this way, a comprehensive analysis of the strengths and weaknesses of various ML and DL algorithms for IDS is presented.

Measuring Visual Fields in Children With Glaucoma Using a Portable Tablet.

To compare perimetric outcomes of an iPad perimetry app (Melbourne Rapid Fields [MRF]) with those of the Humphrey Field Analyser (HFA) testing children with glaucoma. Sixteen children diagnosed and treated for glaucoma were recruited to evaluate their perimetric performance over two visits. At each visit, they undertook visual field assessment using the MRF application as well as the HFA. The HFA test was part of their usual clinical work up and a clinical assistant judged which test format (24-2 SITA standard or SITA fast) might be suited to the testing of that child. The primary outcome measure was the association and repeatability of mean deviation (MD) for the MRF and HFA tests, by way of regression, intraclass correlation coefficient and Bland-Altman analysis. Secondary measures were comparisons of pattern deviation indices, test times as well as an indication of participant test preference. Summary data show means ± standard deviation. The age for our cohort was 7 to 15 years of age (mean, 10.0 ± 2.4years of age). The MRF MD was in close concordance to HFA MD with an intraclass correlation coefficient of 0.91 (95% confidence interval, 0.82-0.95). Bland-Altman analysis found little bias (-0.6dB) and a 95% coefficient of repeatability of 2.1dB in eyes having a normal HFA MD. In eyes with glaucomatous visual field defects the 95% coefficient of repeatability at retest was much larger for both the MRF (10.5dB) as well as for the HFA (10.0dB). Average MRF test times (5.6 ± 1.2 minutes) were similar to SITA Fast (5.4 ± 1.9 minutes) with both being significantly faster than SITA standard (8.6 ± 1.4 minutes; P < 0.001). All children chose testing with the MRF as their preference. MRF correlated strongly with HFA and was preferred by the children over the HFA. MRF is suitable for perimetric evaluation of children with glaucoma. This study finds that an iPad based visual field test can be used with children having glaucoma to yield outcomes similar to SITA-fast. Children indicate a preference for such testing.

Dementia U-Care: Comprehensive Cognitive Screening Application for Seniors

The prevalence of cognitive impairment increases with age, particularly impacting seniors as it advances to severe dementia. These conditions pose significant challenges for afflicted individuals and their caregivers, manifesting as profound impacts on daily life and imposing considerable emotional and financial burdens on families. Mild cognitive impairment (MCI) denotes an intermediate stage between normal cognitive function and dementia, signifying a decline in cognitive abilities while maintaining normal daily life activities. Identifying MCI early in seniors within the community is pivotal to preventing further cognitive decline.In response to the challenge of traditional cognitive function assessments, which require trained healthcare professionals and take 20-30 minutes per case, we introduce "Dementia U-Care," an innovative app designed to assist community health workers in screening, monitoring, and collecting cognitive data. Accessible on mobile devices, it allows seniors to respond through drawing and writing, simplifying data collection compared to paper forms. Dementia U-Care streamlines preliminary assessments, empowering professionals and reducing fatigue and errors. This tool enables prompt screening, minimizing test-related stress, with an average testing time of 13.06 minutes, ranging from 9 to 20 minutes. The evaluation indicates high satisfaction with Dementia U-Care, with a mean score of 9.37±1.12. Users are generally pleased with its quality and user experience, demonstrating its effectiveness in meeting their needs and providing a positive experience.

PENGARUH VARIASI DIAMETER PULI TERHADAP KONSUMSI BAHAN BAKAR MESIN PEMIPIL JAGUNG TIPE MCT 5-60

Abstract Corn is one of the main ingredients that can be processed into several types of food to meet the needs of the community. The process of processing corn using tools is growing rapidly along with technological advances so as to provide convenience for the community, especially farmers, in processing agricultural products. The machine used is a sheller type which is expected to reduce long processing times and save fuel costs if used in the long term. The purpose of this study was to determine the effect of variations in pulley diameter on fuel consumption of the MCT 5-60 corn sheller engine using a Mct 5-60 15 sheller engine and an additional GX 160 diesel engine with a power of 5.5 PK for the purpose of experimenting data collection with pulley 2 inch, 2.5 inch, and 3 inch with a fixed rpm of 1500 at the time of this test with 3 trials each. Specific fuel consumption is defined as the amount of fuel used to produce a unit of power to determine the effect of variations in pulley diameter on fuel consumption. The test method uses the experimental method, namely by changing the variation of the diameter of the pulley on the engine that is driven with a load of 3 kg, the diameter of the pulley is 2 inch, the fuel is 16 ml and the average time is 2.27 minutes, the pulley is 2.5 inch the average material burn 12 ml and the average time is 1.22 minutes. The 3 inch pulley is 5 ml and the average time is 1.04 minutes. and the size of the diameter of the pulley which is driven by a 4.5 inch diameter engine and the best results on a 3 inch diameter pulley with an average fuel consumption of 5 ml and an average testing time of 1.04 minutes.

Research on the Application of Speech Database based on Emotional Feature Extraction in International Chinese Education and Teaching

The advanced analysis of the relationship between acoustic and emotional characteristics of speech signals can effectively improve the interactivity and intelligence of computers. Given the current status of speech recognition and the problems encountered in international Chinese education, the study proposes to extract emotional characteristics to achieve speech construction of the database. Based on considering the emotional characteristics of speech, a hybrid algorithm based on spectral sequence context features is proposed. The DBN-BP algorithm is used to process emotional data of different dimensions, and a speech database is constructed. After testing and analyzing the algorithm model, it is found that the dynamic recognition accuracy of the DBN-BP model fused with emotional features is over 90%, and the negative emotion recognition rates in the three databases are all above 60%. At the same time, the accuracy rate of the model in the algorithm comparison experiment remains above 85%, the data information extraction is relatively complete, and the average test time of less than 1s is less than 3%. The speech database based on multi-emotional feature extraction can effectively provide a new reference for the improvement of the quality of Chinese international education and the improvement of the speech recognition system.

EEGProgress: A fast and lightweight progressive convolution architecture for EEG classification

Because of the intricate topological structure and connection of the human brain, extracting deep spatial features from electroencephalograph (EEG) signals is a challenging and time-consuming task. The extraction of topological spatial information plays a crucial role in EEG classification, and the architecture of the spatial convolution greatly affects the performance and complexity of convolutional neural network (CNN) based EEG classification models. In this study, a progressive convolution CNN architecture named EEGProgress is proposed, aiming to efficiently extract the topological spatial information of EEG signals from multi-scale levels (electrode, brain region, hemisphere, global) with superior speed. To achieve this, the raw EEG data is permuted using the empirical topological permutation rule, integrating the EEG data with numerous topological properties. Subsequently, the spatial features are extracted by a progressive feature extractor including prior, electrode, region, and hemisphere convolution blocks, progressively extracting the deep spatial features with reduced parameters and speed. Finally, the comparison and ablation experiments under both cross-subject and within-subject scenarios are conducted on a public dataset to verify the performance of the proposed EEGProgress and the effectiveness of the topological permutation. The results demonstrate the superior feature extraction ability of the proposed EEGProgress, with an average increase of 4.02% compared to other CNN-based EEG classification models under both cross-subject and within-subject scenarios. Furthermore, with the obtained average testing time, FLOPs, and parameters, the proposed EEGProgress outperforms other comparison models in terms of model complexity.

Digital Twin and Blockchain Extension in Smart Buildings Platform as Cyber-Physical Systems

Cyber-physical systems is integrated computation with the physical world. CPS increasing in a wide range of applications, from smart homes to smart buildings. Digital twins are promising way to solve challenges with combination of CPS, 3D technology, and IoT. The system provides users with immersive interfaces to control and interact with devices within the smart building environment. Blockchain was chosen to secure user data using cryptographic algorithms and ensure data protection against manipulation, spying, and theft. Average load testing data for digital twin platform implemented in smart buildings range from 1 to 11 floors. The results reveal a gradual increase in average test times as the buildings' size and complexity grow, with the following values: 5.663s for 1 floor until 11 floors 7.294s. The data obtained from of the blockchain test using Hyperledger Besu provide essential insights into the system's performance with several bandwidth that used in the system. Average time for each test trial ranged from 1.066 seconds to 2.006 seconds, showing slight variations based on the bandwidth used. However, transactions per second (TPS) values were relatively fast, ranging from 1.066 tps to 0.499 tps with positive aspect of the retention rate for all trials was 100% success.

Research on road damage recognition and classification based on improved VGG-19

In recent years, methods of road damage detection, recognition and classification have achieved remarkable results, but there are still problems of efficient and accurate damage detection, recognition and classification. In order to solve this problem, this paper proposes a road damage VGG-19 model construction method that can be used for road damage detection. The road damage image is processed by digital image processing technology (DIP), and then combined with the improved VGG-19 network model to study the method of improving the recognition speed and accuracy of VGG-19 road damage model. Based on the performance evaluation index of neural network model, the feasibility of the improved VGG-19 method is verified. The results show that compared with the traditional VGG-19 model, the road damage VGG-19 road damage recognition model proposed in this paper shortens the training time by 79 % and the average test time by 68 %. In the performance evaluation of the neural network model, the comprehensive performance index is improved by 2.4 % compared with the traditional VGG-19 network model. The research is helpful to improve the model performance of VGG-19 road damage identification network model and its fit to road damages.

Classification of multiple power quality disturbances based on continuous wavelet transform and lightweight convolutional neural network

AbstractAiming at the problems of noise interference and too many network parameters for power quality disturbances' (PQDs') classification based on deep learning, the lightweight convolutional neural network combining maximum likelihood Kalman filter and continuous wavelet transform is proposed. In this proposed method, the disturbed PQD signals are denoised by maximum likelihood Kalman filter, and then the denoised PQDs are converted to time‐frequency diagrams, which can provide rich time and frequency domain information, and finally the lightweight convolution neural network is used for automatically extracting and classifying multiple PQDs. To verify the effectiveness and superiority of the proposed method, a variety of PQDs were tested under different noise levels, the experiment results indicate that the average classification accuracy can reach more than 99% even in the case of 10 dB noise. Compared with the existing classification methods, the accuracy and noise immunity ability are improved. Additionally, the proposed method has decided advantages, as evidenced by its low parameter count of 0.73M and short average test time with only 0.7 ms.

Central Aortic Blood Pressure Waveform Estimation with a Temporal Convolutional Network.

A novel temporal convolutional network (TCN) model is utilized to reconstruct the central aortic blood pressure (aBP) waveform from the radial blood pressure waveform. The method does not need manual feature extraction as traditional transfer function approaches. The data acquired by the SphygmoCor CVMS device in 1,032 participants as a measured database and a public database of 4,374 virtual healthy subjects were used to compare the accuracy and computational cost of the TCN model with the published convolutional neural network and bi-directional long short-term memory (CNN-BiLSTM) model. The TCN model was compared with CNN-BiLSTM in the root mean square error (RMSE). The TCN model generally outperformed the existing CNN-BiLSTM model in terms of accuracy and computational cost. For the measured and public databases, the RMSE of the waveform using the TCN model was 0.55 ± 0.40 mmHg and 0.84 ± 0.29 mmHg, respectively. The training time of the TCN model was 9.63 min and 25.51 min for the entire training set; the average test time was around 1.79 ms and 8.58 ms per test pulse signal from the measured and public databases, respectively. The TCN model is accurate and fast for processing long input signals, and provides a novel method for measuring the aBP waveform. This method may contribute to the early monitoring and prevention of cardiovascular disease.

Multilabel image analysis on Polyethylene Terephthalate bottle images using PETNet Convolution Architecture

Packaging is one of the important aspects of the product. Good packaging can increase the competitiveness of a product. Therefore, to maintain the quality of the packaging of a product, it is necessary to have a visual inspection. Furthermore, an automatic visual inspection can reduce the occurrence of human errors in the manual inspection process. This research will use the convolution network to detect and classify PET (Polyethylene Terephthalate) bottles. The Convolutional Neural Network (CNN) method is one approach that can be used to detect and classify PET bottle packaging. This research was conducted by comparing seven network architecture models, namely VGG-16, Inception V3, MobileNet V2, Xception, Inception ResNet V2, Depthwise Separable Convolution (DSC), and PETNet, which is the architectural model proposed in this study. The results of this study indicate that the PETNet model gives the best results compared to other models, with a test score of 96.04%, by detecting and classifying 461 of 480 images with an average test time of 0.0016 seconds.

What Influences Proprioceptive Impairments in Patients with Rheumatic Diseases? Analysis of Different Factors.

Rheumatic diseases lead to postural problems, which increase the risk of falls and lead to greater disability. The aim of the present work is to evaluate posture disorders in patients with osteoarthritis (OA) and rheumatoid arthritis (RA), as well as to evaluate the influence of other factors. A total of 71 subjects were enrolled in this study. Joint position sense (JPS) and the functional assessment of proprioception on a balance platform for both lower limbs were examined. The Average Trace Error (ATE), test time (t), and Average Platform Force Variation (AFV) were calculated. Additionally, an equilibrium test was carried out in the one-legged standing position (Single Leg Stance-SLS). The results were compared in several ways and revealed the following: (1) A JPS of 10° plantar flexion in RA obtained significantly worse results when repeating the movement than OA; the ATEs were significantly lower in RA; and RA needed more support during SLS assessment. (2) RA patients with higher DAS28 had statistically significantly higher values in JPS, with 5° plantar flexion and 10° dorsal flexion, SLS assessment, and stabilometric rates. A statistically significant correlation between DAS28 and RA was found in a JPS of 10° plantar flexion. The VAS ruler demonstrated a significant moderate correlation with t. (3) Patients who experienced at least one fall demonstrated higher JPS and t. Our study shows that proprioception is the most influenced by the nature of the disease and the level of disease activity. We can see that the stability and balance functions are also greatly influenced by the patient's falling experience and the level of pain. These findings may be useful in designing an optimal proprioception-enhancing movement training plan.

The Fast Cognitive Evaluation (FaCE): a screening tool to detect cognitive impairment in patients with cancer

Cancer-related cognitive impairment (CRCI) is one of the most concerning conditions experienced by patients living with cancer and has a major impact on their quality of life. Available cognitive assessment tools are too time consuming for day-to-day clinical setting assessments. Importantly, although shorter, screening tools such as the Montreal Cognitive Assessment or the Mini-Mental State Evaluation have demonstrated a ceiling effect in persons with cancer, and thus fail to detect subtle cognitive changes expected in patients with CRCI. This study addresses this lack of cognitive screening tools by developing a novel tool, the Fast Cognitive Evaluation (FaCE).A population of 245 patients with 11 types of cancer at different illness and treatment time-points was enrolled for the analysis. FaCE was developed using Rasch Measurement Theory, a model that establishes the conditions for a measurement tool to be considered a rating scale.FaCE shows excellent psychometric properties. The population size was large enough to test the set of items (item-reliability-index=0.96). Person-reliability (0.65) and person-separation (1.37) indexes indicate excellent internal consistency. FaCE’s scale is accurate (reliable) with high discriminant ability between cognitive levels. Within the average testing time of five minutes, FaCE assesses the main cognitive domains affected in CRCI.FaCE is a rapid, reliable, and sensitive tool for detecting even minimal cognitive changes over time. This can contribute to early and appropriate interventions for better quality of life in patients with CRCI. In addition, FaCE could be used as a measurement tool in research exploring cognitive disorders in cancer survivors.

Road Pothole Detection Using Unmanned Aerial Vehicle Imagery and Deep Learning Technique

Potholes are considered the main factor for road defects, which leads to road status deterioration, which, consequently will lead to increased road accidents. The first step in road maintenance is to inspect the road surface and then accurately detect potholes. However, manually identifying them is costly and time-consuming. In this study, unmanned aerial vehicle (UAV) imagery was used to create orthophotos of the roads and, using deep learning methods, potholes were detected. The used deep learning method in this study is the "you only look once" (YOLO) algorithm. YOLO is one of the "deep learning-based approaches" to detecting objects and is a single-stage network which requires only one forward propagation across the neural network and focuses on the entire image. The fourth version of YOLO is YOLOV4, which has two different architectures (YOLOv4 and YOLOv4-tiny). Two roads were chosen as the study areas, and to generate the orthophotos of the roads, UAV was used to acquire images. To train both methods in the process of detecting potholes using deep learning, 5300 images were used, 90% used for training and 10% applied for testing. The two used architectures were trained for 6000 iterations. Both methods were evaluated based on the average loss, mean average precision (mAP), and training and testing time. The results showed that the (mAP) values for YOLOv4 and YOLOv4-tiny were 91. 2% and 85.7%, respectively. At the end of the 6000 iterations, the average loss for YOLOv4 is 0.30% and for YOLOv4-tiny is 0.34%. In the training process, YOLOv4 needs 29 seconds for each iteration, while YOLOv4-tiny requires only 8 seconds. In the test process, YOLOv4-tiny is faster at detecting potholes than YOLOv4. The approaches were tested on orthophotos created by processing UAV photos. When comparing the detection of both architectures with visual detection, the results showed that YOLOv4 was able to detect most of the potholes on roads, but YOLOv4-tiny detected a lower number of potholes.

Machine learning ensemble approach for healthcare data analytics

In healthcare machine learning is used mainly for disease diagnosis or acute condition detection based on patient data analysis. In the proposed work diabetic patient dataset analysis is done for hypoglycemia detection which means the lowering of blood glucose level. Often in healthcare it is observed that the dataset is imbalanced. Therefore an Ensemble Approach using imbalanced dataset techniques Synthetic Minority Over-sampling Technique and Adaptive Synthetic oversampling methods with different evaluation methods like train-test, k-fold, Stratified K-Fold and repeat train-test were used. This ensemble approach was implemented on diabetic dataset using K-Nearest Neighbor, Support Vector Machine, Random Forest, Naïve Bayes and Logistic Regression classifiers with average Stacking-C method thereafter to conclude. Comparative analysis was done using three different considerations. The results showed that KNN and Random forest gives more stable metric values both on balanced and imbalanced dataset. The confusion matrix consideration concluded that KNN and Random Forest were found to be better with least false negative and maximum true positive count. But if average train and test time is taken into consideration then Naïve Bayes and Random forest had least average train-test time. Thus the three different considerations concluded that the proposed ensemble approach gives better clarity for different classifier implementation using machine learning.

Development of an American Sign Language Recognition System using Canny Edge and Histogram of Oriented Gradient

Sign language is used by people who have hearing and speaking difficulties, but not understood by many without these difficulties. Therefore, sign language recognition systems are developed to aid communication between hearing impaired people and others. This paper developed a static American Sign Language Recognition (ASLR) system using canny-edge and histogram of oriented gradient (HOG) for feature extraction with K-Nearest Neighbour (K-NN) as classifier. The sign language image datasets used consist of English alphabets from both Massey University and Kaggle, and numbers (0-9) from Massey University. Median filter was used to remove noise after images were converted to grayscale. Otsu algorithm was used for segmentation while edges in the images were preserved using canny edge detection technique with HOG parameters tuning to obtain feature vectors. The extracted features were used by K-NN for classification. An average recognition accuracy and computational testing time of 97.6% and 0.39s respectively were obtained based on experiments with the Massey University dataset. Similarly, an average recognition accuracy and computational testing time of 99.0% and 0.43s respectively were obtained based on experiments with the Kaggle dataset. The developed system successfully recognized static English alphabets and numbers and outperformed some existing systems.

Construction and Application of a New Metal Random Matrix-Based Theory in a Numerical Phantom of the Metaverse NFT

As the metaverse is hot, nonhomogenized tokens (NFT) as digital artwork identifiers present different characteristics and application values from other homogenized tokens, and their use for copyright verification will suffer from the problems of storage space limitation and data verification reliance on database, this study designs an NFT digital copyright authentication model for textual works. To cater for the uncontrollability of conventional Hash algorithms in stream matching due to the high conflict rate, a new random matrix theory is applied to propose a new Hash algorithm, which is used on the block structure of NFT credential authentication, while extending the block structure so that the data within the work is completely stored in the blockchain with NFT as the credential, allowing the database to store the work data in a relatively safe manner. The verification of the work data has the immutability and unique cryptographic solution of NFT. The NFT-based digital model collects TR information and conducts 30 tests, and the average test time for generating blocks is 0.53 s. Through the block query for detection, 248,655 words have exceeded the number of words of an article, and the consumption time is only 0.23s, to meet the customer's real-time query requirements for the system. According to the overhead ratio, the record storage expenditure is about 2-3 times of the text storage expenditure, the work storage expenditure, and the storage expenditure for storing 240,000 words for authentication is about 3720 KB.

Integration and Recommendation of Multimedia Network-Assisted English Instructional Resources Based on Association Rules Mining

The integration of multimedia teaching refers to a novel teaching mode that combines multimedia, information resources, and information methods with content and teaching process in the teaching process with the guidance of contemporary educational ideas and organically unifies them on a spatial and temporal platform, so as to better accomplish the teaching tasks. However, with the deepening of network teaching and school connotation construction, various resources such as media materials, courseware, network courses, and teaching cases generated by education and teaching, as well as academic works, papers, patents, project results, and lectures of experts and professors gathered by scientific research, are increasing. In this situation, how to integrate teaching resources and courses to provide students with an independent learning platform and an information-based learning environment has become an urgent issue. For this problem, data mining has shown a strong vitality, and data mining can find out the potential connection between datasets. Association rule mining is the most researched and widely used data mining method. In this paper, we propose a multimedia network-assisted English integration of educational resources method based on association rule algorithm to give full play to the role of “multimedia technology” and realize the integration of traditional English teaching and information network culture, so as to achieve the purpose of optimizing English teaching. The experimental results show that with the increase of data volume, the average testing time of Apriori is reduced by 56.49 s compared with MapReduce, so the advantage of Apriori algorithm is more obvious. Therefore, this research can effectively provide students with rich and colorful personalized resources, realize high-performance interactive learning, and help students cultivate their independent learning ability as well as their lifelong learning habits.