Research on student behavior recognition method based on human physiological information perception

Indonesian's Batik is one of culture heritage that recognized around the world. Batik has many variations of motif based on their region. This paper discusses feature extraction methods for classifying batik motifs in digital images. A single feature extraction method may result feature vector that is similar for two different images. In this research, the using of Gray Level Co-occurence Matrix (GLCM) and statistical color RGB features can represent more characteristics in extracting batik images. The extracted features vectors are furthermore classified into motifs using Backpropagation Neural Network with several scenarios for testing the level of accuracy. Some experiment by using single feature and combination of GLCM and statistical color RGB features show that the best result for classifying batik image is the combination of feature extraction with rate of precision 90.66%, recall 94% and accuracy 94%.

Feature engineering is treated as a crucial step in any intelligent system pipeline and practitioners often spend 70–80% of their time in this phase before modeling. Especially, in machine learning (ML), the performance of the classification systems deteriorates as irrelevant features are added, even when the features presented contain enough information about the problem. ML researchers often use feature selection and feature extraction techniques individually to filter out the redundant information from the data, but would not get desired results or performance due to choosing a single method only. In this article, we take an attempt to combine both feature selection and feature extraction methods that give an improvement in the prediction performance than using a single feature selection or feature extraction method. In the application of the proposed method, we consider the Indian liver disease patient dataset to classify liver disease using machine learning classifiers. In addition, ensemble classifiers also take into account reproducing and robustifying classification accuracy. The performance is evaluated and compared with different metrics such as accuracy, precision, recall, and F1-score. Using the proposed method, the KNN classifier can diagnosis 76.03% with a precision of 76.69%, recall 96.23%, and 85.36% F1-score which is much better than the individual feature selection and feature extraction approach. The proposed method can also be extended to medical datasets other than liver disease so that these types of deadly diseases can be correctly diagnosed for the betterment of humanity.

The PET/CT imaging technology combining positron emission tomography (PET) and computed tomography (CT) is the most advanced imaging examination method currently, and is mainly used for tumor screening, differential diagnosis of benign and malignant tumors, staging and grading. This paper proposes a method for breast cancer lesion segmentation based on PET/CT bimodal images, and designs a dual-path U-Net framework, which mainly includes three modules: encoder module, feature fusion module and decoder module. Among them, the encoder module uses traditional convolution for feature extraction of single mode image; The feature fusion module adopts collaborative learning feature fusion technology and uses Transformer to extract the global features of the fusion image; The decoder module mainly uses multi-layer perceptron to achieve lesion segmentation. This experiment uses actual clinical PET/CT data to evaluate the effectiveness of the algorithm. The experimental results show that the accuracy, recall and accuracy of breast cancer lesion segmentation are 95.67%, 97.58% and 96.16%, respectively, which are better than the baseline algorithm. Therefore, it proves the rationality of the single and bimodal feature extraction method combining convolution and Transformer in the experimental design of this article, and provides reference for feature extraction methods for tasks such as multimodal medical image segmentation or classification.

The manifold growth of malware in recent years has resulted in extensive research being conducted in the domain of malware analysis and detection, and theories from a wide variety of scientific knowledge domains have been applied to solve this problem. The algorithms from the machine learning paradigm have been particularly explored, and many feature extraction methods have been proposed in the literature for representing malware as feature vectors to be used in machine learning algorithms. In this paper we present a comparison of several feature extraction techniques by first applying them on system call logs of real malware, and then evaluating them using a random forest classifier. In our experiment the HMM-based feature extraction method outperformed the other methods by obtaining an F-measure of 0.87. We also explored the possibility of using ensembles of feature extraction methods, and discovered that combination of HMM-based features with bigram frequency features improved the F-measure by 1.7%.

Research on human facial expression recognition has become a growing field. One important step in the recognition of facial expressions is feature extraction. This research uses Geometric Moment Invariants (GMI) as a feature extraction method. Research on facial expression recognition using either the GMI method or another method use single face image as the dataset. Therefore, in this study uses GMI feature extraction to classify facial expressions on multiple face images. Face detection process uses Viola-Jones method on OpenCV and classification process uses Multi Class SVM method. The results are features for each expression and a small average accuracy of 5 times. Therefore, the classification is also done with the k-fold cross validation technique with another classification method. The average accuracy results are still small. It caused by the training image also using outer area of face in the image, so the background included as the image features. It is tested from k value 2 to10, and produce Multi Class SVM 10.2%, Decision Tree Classifier 14.73%, Random Forest Classifier 14.78%, Gaussian Naive Bayes 14.73%, Nearest Centroid 14.66%, MLP Classifier 11.09%, and Stochastic Gradient Descent Classifier 14.19%. The highest accuracy result is Random Forest Classifier method 14.78%. In Random Forest method, the best k value obtained is 4 with an average accuracy 16.18%.

Data mining (DM) approaches have been applied in the field of Educational Data Mining (EDM) to obtain the important insights about student preferences and behaviors. By using a variety of strategies to increase the effectiveness of e-learning environments, the design aims to enhance learning processes by forecasting the traits of students. Academic data can be used to study trends in student behavior using a selection of DM, such as grouping, classification, and forecasting. This study presents a novel approach to learning behaviors prediction in the Chaotic-Tuned Shuffled Frog Leaping Optimized Random Forest (CSFLO-RF). The CSFLO technique, which accelerates the global convergence of the traditional SFLO technique, improves the accuracy of RF categorization in the suggested methodology. The K-Means Clustering (KMC) methodology uses the student behavior patterns recorded in the log record to group learners into specific categories based on their e-learning system usage. The generated clusters were allocated multiple learning styles based on the framework for learning styles. Following that, the specified behaviors were employed as input for the proposed CSFLO-RF classification to evaluate the degree to predict the students’ learning behavior. According to the results of the suggested technique, which is implemented to utilize the Weka platform, the CSFLO-RF approach yielded more successful outcomes than other existing strategies.

<span lang="EN-US">Teaching style is the most essential factor in the implementation of learning. Learning is not merely a transfer of knowledge but also a process of shaping individuals to think critically, independently, and responsibly. This study aims to examine the influence of technological teaching styles of Buddhist Sunday school teachers on the learning behaviour of Sunday school students. The research was conducted at Buddhist Sunday schools in Pringsewu Regency. This study uses a quantitative approach with a survey method, and data processing is done using SPSS 16. The population in this study consists of 66 Buddhist Sunday school students. The results show that the technological teaching style of Buddhist Sunday school teachers has a positive and significant effect on the learning behaviour of Sunday school students in Pringsewu Regency. It emphasizes that the technological teaching style is one component in shaping students' learning behaviour; however, external factors also play an essential role in developing learning behaviour. The results of this study have a significant impact on the context of shaping students' learning behaviour. It can be applied in the Buddhist Sunday School environment in Pringsewu Regency, where students are encouraged to be more active and independent in the technology-based learning process.</span>

The classification and recognition technology of underwater acoustic signal were always an important research content in the field of underwater acoustic signal processing. Currently, wavelet transform, Hilbert-Huang transform, and Mel frequency cepstral coefficients are used as a method of underwater acoustic signal feature extraction. In this paper, a method for feature extraction and identification of underwater noise data based on CNN and ELM is proposed. An automatic feature extraction method of underwater acoustic signals is proposed using depth convolution network. An underwater target recognition classifier is based on extreme learning machine. Although convolution neural networks can execute both feature extraction and classification, their function mainly relies on a full connection layer, which is trained by gradient descent-based; the generalization ability is limited and suboptimal, so an extreme learning machine (ELM) was used in classification stage. Firstly, CNN learns deep and robust features, followed by the removing of the fully connected layers. Then ELM fed with the CNN features is used as the classifier to conduct an excellent classification. Experiments on the actual data set of civil ships obtained 93.04% recognition rate; compared to the traditional Mel frequency cepstral coefficients and Hilbert-Huang feature, recognition rate greatly improved.

Learning: Sunburn o r Behavioral Change. Scientists are beginning to develop an image of the optimal learning situation. The teacher may not be surprised to discover that current and traditional pedagogical techniques a re greatly a t variance with this image. Many teachers continue to be burdened with the sunburn model of learning. knowledge, light, (and, occasionally, heat) exposes students to his ideas; they soak it up and, in turn, become enlightened!' Students who fail to learn a re simply not sensitive o r receptive, they do not see the light. A newer, more workable model is emerging from current behavioral research, a model that defines learning in terms of a change of behavior. Consider the student who is about to learn French. He does not distinguish properly among French sounds; he does not respond appropriately when addressed in French; he does not produce most French sounds correctly; he cannot read French from a text; and so on. The teacher's task is to modify the student's behavior so that he will hear, understand, speak, and read French. To change the student's behavior from what it is now to what it should be: (1) the student's current behavior must be carefully assessed; (2) the desired terminal behavior must be carefully analyzed; and (3) a program must be set down that will lead in small steps from initial to terminal behavior. Exactly what a re the desired terminal behaviors in language learning? Descriptive linguistics can provide an account of the terminal behavior required for foreign language fluency. How can this terminal behavior best be developed from the initial behavior repertory of the student? Psychology is building the bridge between initial and terminal behavior by specifying programming techniques that will facilitate learning. What role The teacher, prime source of

In the era of big data, the traditional governance model of student behavior management gradually shows the disadvantage of “post positioning”. Therefore, the research uses relevant data mining algorithms to extract and analyze students’ behavior characteristics, and constructs a SPC system model for students’ behavior analysis and performance prediction. At the same time, the experiment verifies its effectiveness. The experimental results show that in the factor analysis, the overall variance of the first seven indicators is 69.942\%, which shows that there is a significant correlation between students’ learning behavior and academic performance. In the model performance analysis of SPC system, the accuracy of the five algorithms is kept at 40% - 60%, while SVM has higher stability than other methods. In addition, the prediction accuracy and response rate of SPC model reached 86.90% and 81.57% respectively. When the sequence length was increased from 1 to 20, the accuracy of SPC model exceeded 70%; However, when the feature dimension exceeds 50, the model representation ability will decline. Therefore, appropriate feature dimensions are needed to predict student performance. To sum up, the SPC model built by the research is effective in analyzing student behavior and predicting students’ performance, and practical in actual student management.

Preparing nursing students to be competent for future professional practice: applying the team-based learning-teaching strategy.

A classification algorithm of an SSVEP brain-Computer interface based on CCA fusion wavelet coefficients

Behavioral problems become special attention to learning. Some teachers confronted with a variety of student behaviors and varied learning outcomes. This research was aimed to determine the relationship between learning outcomes and student learning behavior with ranking score. A total of 91 of 10th-grade students with three different classes became respondents. The research was used Mixed methods with the sequential explanatory approach. Quantitative data were obtained by giving multiple-choice questions. The interview method was used to collect qualitative data. Kruskal Wallis test was used to analyze quantitative data and the interview transcript analyzed by the keyword of student behavior in learning physics. The results show that behavior while learning is very significant towards student learning outcomes. Interview findings show that student behavior during the learning process could affect learning outcomes.

In the contemporary era of big data, the educational landscape is undergoing significant transformations. Literature education, as a vital component, faces both emerging opportunities and challenges. This study develops a framework for analyzing learning behaviors specific to literature education. It employs both an enhanced K-means clustering algorithm and a refined Apriori algorithm for mining data on student learning behaviors. Through cluster analysis and the investigation of association rules, this research explores the interconnections between students’ learning behaviors and their literary education. The findings categorize students into four distinct groups based on their learning behaviors. Students in Category 1 are identified as the most proficient learners, consistently achieving test scores above 85. Conversely, Category 2 students display the least motivation and effectiveness, with their examination scores not exceeding 70. Students in Categories 3 and 4 exhibit comparable levels of performance. Crucially, the analysis reveals that the most significant predictors of students’ literary achievement are their regular and examination scores, with correlation coefficients of 0.627 and 0.653, respectively. This segmentation and analysis of student behaviors facilitate the early detection of atypical learning patterns by educational practitioners, enabling timely intervention strategies to enhance academic outcomes.

In order to accurately identify various types of ships and develop coastal defenses, a single feature extraction method based on slope entropy (SlEn) and a double feature extraction method based on SlEn combined with permutation entropy (SlEn&PE) are proposed. Firstly, SlEn is used for the feature extraction of ship-radiated noise signal (SNS) compared with permutation entropy (PE), dispersion entropy (DE), fluctuation dispersion entropy (FDE), and reverse dispersion entropy (RDE), so that the effectiveness of SlEn is verified, and SlEn has the highest recognition rate calculated by the k-Nearest Neighbor (KNN) algorithm. Secondly, SlEn is combined with PE, DE, FDE, and RDE, respectively, to extract the feature of SNS for a higher recognition rate, and SlEn&PE has the highest recognition rate after the calculation of the KNN algorithm. Lastly, the recognition rates of SlEn and SlEn&PE are compared, and the recognition rates of SlEn&PE are higher than SlEn by 4.22%. Therefore, the double feature extraction method proposed in this paper is more effective in the application of ship type recognition.