The k-nearest neighbor learning algorithm is indeed one of the most commonly used supervised algorithms in machine learning. KNN is a lazy learner, and one of the most important similarity features used in this algori...
详细信息
With the development of deep learning and the knowledge graph, artificial intelligence has had a significant influence on the area of education as a result of the rapid growth of this age, which has profoundly altered...
With the development of deep learning and the knowledge graph, artificial intelligence has had a significant influence on the area of education as a result of the rapid growth of this age, which has profoundly altered human productivity and daily life. The university is undergoing a digital transformation. The essence of the knowledge graph is the knowledge base of the semantic network. Using natural language processing (NLP) technology, the university can construct a knowledge graph. Integrating knowledge graphs and deep learning has become one of the most important aspects of further improving the effect of deep learning. The solution to knowledge graph processing data is “algorithm, totalization, and implementation”. The key technologies of constructing knowledge graphs in multi-dimensional data mainly focus on knowledge ontology definition, knowledge representation, knowledge modeling, knowledge extraction, knowledge fusion, knowledge processing, knowledge computing, and other technologies. The research in this paper shows that the RDF model and algorithm of the knowledge graph have application prospects in multi-dimensional data.
With high-quality teaching content and low-threshold learning methods, Massive Open Online Courses (MOOCs) have drawn hundreds of millions of users. However, the high dropout rate is its weakness compared to offline t...
With high-quality teaching content and low-threshold learning methods, Massive Open Online Courses (MOOCs) have drawn hundreds of millions of users. However, the high dropout rate is its weakness compared to offline teaching. To address this problem, this study proposes a convolutional network-based student dropout prediction model, Squeeze Excitation Temporal Convolutional Network (SETCN), to predict learners’ dropout based on student learning clickstream data of MOOCs courses. Firstly, students’ learning record data are converted into users’ learning behavior matrix. Then, local features of the learning matrix are extracted through convolutional techniques. These extracted learning features are then passed into a temporal convolutional network to further refine the data. The students’ temporal learning features are extracted through dilated causal convolution. Finally, a multilayer perceptron is used to derive the dropout prediction for students. Experiments are conducted on public datasets, and the accuracy of the model is 87.9%, which is higher than previous prediction models.
Indoor distance measurement plays a critical role in positioning services. The complexity of indoor environments, coupled with a limited and small sample size, results in suboptimal distance accuracy. This paper propo...
详细信息
The formation model of digital competence of future specialists in electrical engineering during distancelearning of the computer technologies in the design of electromechanical systems, which is based on narrative-d...
详细信息
This study analyzes the effectiveness of virtual laboratory-based distancelearning as a means of improving the learning outcomes of students’ cognitive abilities and practical skills in the computer Numerical Contro...
详细信息
In order to make full use of the interaction between images and texts, improve the extraction effect of each modal feature, and improve the accuracy of multi-modal classification, this paper proposed a sentiment class...
In order to make full use of the interaction between images and texts, improve the extraction effect of each modal feature, and improve the accuracy of multi-modal classification, this paper proposed a sentiment classification method based on Transformer and image-text collaborative interaction. In this model, the image and text features are extracted based on Transformer, and the bidirectional long short-term memory network and attention mechanism are introduced while the text features are extracted, and the Vision Transformer is used to obtain the visual features of the image. Then, a fusion method based on information adaptive weight adjustment is designed, which adjusts the weight parameters of model fusion in real time according to the feature information of image and text to perform weighted fusion. Experiments show that the model improves the accuracy and F1 value.
Adopting distancelearning with a high level of quality in universities and educational institutions is a real challenge. Therefore, several studies and organizations have provided different standards to evaluate the ...
详细信息
The A* algorithm has been widely employed in the automatic navigation of mobile robots. However, the traditional A* algorithm faces challenges in handling complex environments and large-scale maps due to high computat...
The A* algorithm has been widely employed in the automatic navigation of mobile robots. However, the traditional A* algorithm faces challenges in handling complex environments and large-scale maps due to high computational complexity, large memory requirements, and suboptimal performance under real-time constraints. To address these issues and enhance search efficiency, reduce memory usage, and improve path quality, an improved A* algorithm based on a 24-neighborhood search is proposed. Firstly, a safety strategy is introduced to improve path safety by setting appropriate buffer zones and disabling unsafe search. Secondly, the 24-neighborhood is reduced to eight search intervals according to the orientation of the destination, which reduces the number of turning points and improves search speed. Then, the evaluation function is improved by adding an exponentially weighted turning cost, which speeds up the search process and reduces the total turning angle. Finally, the modified A* algorithm is simulated multiple times using Python, and the results show improvements in planning time, number of turning points, path safety, and total turning angle.
In the realm of modern distance education, the application of web content recommendation algorithms has emerged as a pivotal means to enhance learning efficiency and personalize the educational experience. This paper ...
详细信息
ISBN:
(纸本)9798400710353
In the realm of modern distance education, the application of web content recommendation algorithms has emerged as a pivotal means to enhance learning efficiency and personalize the educational experience. This paper aims to explore the various technologies of web-based personalized recommendation within the context of remote education and their impact on learning outcomes. Through the analysis of recommendation methods based on content, rules, collaborative filtering, demographic information, and association rules, this study systematically discusses the design and implementation of personalized recommendation algorithms in distance education. Notably, a detailed analysis of collaborative filtering algorithms, including user-based and item-based collaborative filtering as well as model-based approaches, provides both theoretical and technical support for remote education. Experimental results indicate that personalized recommendation algorithms not only significantly improve the matching of learning resources but also effectively enhance students' satisfaction and learning outcomes. This research offers valuable insights for the design and optimization of future distance education systems.
暂无评论