Photovoltaic (PV) panel surface-defect detection technology is crucial for the PV industry to perform smart maintenance. Using computer vision technology to detect PV panel surface defects can ensure better accuracy while reducing the workload of traditional worker field inspections. However, multiple tiny defects on the PV panel surface and the high similarity between different defects make it challenging to accurately identify and detect such defects. This paper proposes an approach named Ghost convolution with BottleneckCSP and a tiny target prediction head incorporating YOLOv5 (GBH-YOLOv5) for PV panel defect detection. To ensure better accuracy on multiscale targets, the BottleneckCSP module is introduced to add a prediction head for tiny target detection to alleviate tiny defect misses, using Ghost convolution to improve the model inference speed and reduce the number of parameters. First, the original image is compressed and cropped to enlarge the defect size physically. Then, the processed images are input into GBH-YOLOv5, and the depth features are extracted through network processing based on Ghost convolution, the application of the BottleneckCSP module, and the prediction head of tiny targets. Finally, the extracted features are classified by a Feature Pyramid Network (FPN) and a Path Aggregation Network (PAN) structure. Meanwhile, we compare our method with state-of-the-art methods to verify the effectiveness of the proposed method. The proposed PV panel surface-defect detection network improves the mAP performance by at least 27.8%.

Intelligent learning diagnosis is a critical engine of intelligent tutoring systems, which aims to estimate learners’ current knowledge mastery status and predict their future learning performance. The significant challenge with traditional learning diagnosis methods is the inability to balance diagnostic accuracy and interpretability. Although the existing psychometric‐based learning diagnosis methods provide some domain interpretation through cognitive parameters, they have insufficient modeling capability with a shallow structure for large‐scale learning data. While the deep learning‐based learning diagnosis methods have improved the accuracy of learning performance prediction, their inherent black‐box properties lead to a lack of interpretability, making their results untrustworthy for educational applications. To settle the abovementioned problem, the proposed unified interpretable intelligent learning diagnosis framework, which benefits from the powerful representation learning ability of deep learning and the interpretability of psychometrics, achieves a better performance of learning prediction and provides interpretability from three aspects: cognitive parameters, learner‐resource response network, and weights of self‐attention mechanism. Within the proposed framework, this paper presents a two‐channel learning diagnosis mechanism LDM‐ID as well as a three‐channel learning diagnosis mechanism LDM‐HMI. Experiments on two real‐world datasets and a simulation dataset show that our method has higher accuracy in predicting learners’ performances compared with the state‐of‐the‐art models and can provide valuable educational interpretability for applications such as precise learning resource recommendation and personalized learning tutoring in intelligent tutoring systems.

Knowledge tracing (KT) serves as a primary part of intelligent education systems. Most current KTs either rely on expert judgments or only exploit a single network structure, which affects the full expression of learning features. To adequately mine features of students’ learning process, Deep Knowledge Tracing Based on Spatial and Temporal Deep Representation Learning for Learning Performance Prediction (DKT-STDRL) is proposed in this paper. DKT-STDRL extracts spatial features from students’ learning history sequence, and then further extracts temporal features to extract deeper hidden information. Specifically, firstly, the DKT-STDRL model uses CNN to extract the spatial feature information of students’ exercise sequences. Then, the spatial features are connected with the original students’ exercise features as joint learning features. Then, the joint features are input into the BiLSTM part. Finally, the BiLSTM part extracts the temporal features from the joint learning features to obtain the prediction information of whether the students answer correctly at the next time step. Experiments on the public education datasets ASSISTment2009, ASSISTment2015, Synthetic-5, ASSISTchall, and Statics2011 prove that DKT-STDRL can achieve better prediction effects than DKT and CKT.

A robust and scientifically grounded teaching evaluation system holds significant importance in modern education, serving as a crucial metric that reflects the quality of classroom instruction. However, current methodologies within smart classroom environments have distinct limitations. These include accommodating a substantial student population, grappling with object detection challenges due to obstructions, and encountering accuracy issues in recognition stemming from varying observation angles. To address these limitations, this paper proposes an innovative data augmentation approach designed to detect distinct student behaviors by leveraging focused behavioral attributes. The primary objective is to alleviate the pedagogical workload. The process begins with assembling a concise dataset tailored for discerning student learning behaviors, followed by the application of data augmentation techniques to significantly expand its size. Additionally, the architectural prowess of the Extended-efficient Layer Aggregation Networks (E-ELAN) is harnessed to effectively extract a diverse array of learning behavior features. Of particular note is the integration of the Channel-wise Attention Module (CBAM) focal mechanism into the feature detection network. This integration plays a pivotal role, enhancing the network’s ability to detect key cues relevant to student learning behaviors and thereby heightening feature identification precision. The culmination of this methodological journey involves the classification of the extracted features through a dual-pronged conduit: the Feature Pyramid Network (FPN) and the Path Aggregation Network (PAN). Empirical evidence vividly demonstrates the potency of the proposed methodology, yielding a mean average precision (mAP) of 96.7%. This achievement surpasses comparable methodologies by a substantial margin of at least 11.9%, conclusively highlighting the method’s superior recognition capabilities. This research has an important impact on the field of teaching evaluation system, which helps to reduce the burden of educators on the one hand, and makes teaching evaluation more objective and accurate on the other hand.