Innovation of Flipped Classroom Mode for College English in the Integrated Environment of the Internet of Things

The flipped classroom, which flips the traditional method of learning and teaching, has become a revolutionary teaching approach as an outcome of the fast progress of data information technology. Flipped classrooms are a strategy that prioritizes learning and teaching and has proven successful in various contexts, including college English instruction, by increasing student autonomy and engagement. The specific effect of the flipped classroom approach on college students’ capacity for independent English learning, particularly in the context of Internet of Things (IoT) integration, is still not well recognized. This research presents an innovative college English flipped classroom teaching model that leverages IoT technologies to enhance student learning experiences. The research, involving 186 English college students, utilizes IoT-enabled devices to track learning progress, offer personalized material, and provide real-time feedback. This research employed an Intelligent Raven Roosting-tuned Dynamic Long Short Term Memory (IRR-DLSTM) algorithm to predict and analyze the student’s learning abilities. The data were preprocessed using clean data, handling missing values, and normalizing the features. Fast Fourier Transform (FFT) is used to extract the features from preprocessed data. The results illustrate that while the IRR-DLSTM model accurately predicted student performance and autonomy in terms of Precision (97.1%), Accuracy (97.5%), F1-score (97%), and recall (97%). The research enhances IoT-enhanced flipped classrooms, demonstrates deep learning’s (DL) effectiveness in teaching methods, and promotes higher education practices and IoT technology use for language learning.