Dance movement error correction based on decision tree algorithm

This paper propose a novel dance action dataset – YNU-Dance. To preserve and inherit ethnic dances, we have collected and constructed a dataset of ethnic dance actions. The dataset encompasses unique dances from 10 different ethnic groups, including multi-view synchronized RGB images and precise motion data captured using motion capture devices. The dataset comprises 256320 frames of RGB images, with a total video duration of 1 hour and 11 minutes, and consists of 3402 action data segments. We compare the YNU-Dance dataset with other publicly available 3D action recognition datasets, highlighting its uniqueness and importance in the field of dance action. Furthermore, we evaluate the YNU-Dance dataset using skeleton action recognition methods and introduces a Prototypical Spatial Temporal model based on prototype networks (ProtoST) to address the small-sample challenge and achieve improved ethnic dance action classification. Dance action data is segmented into time segments suitable for the current model, and data augmentation is applied to enhance model generalization performance. The experiments show that the YNU-Dance dataset, with its multimodal and multi-view characteristics, provides a more complex challenge for action recognition models. This emphasizes the practical research value of the ethnic dance dataset we have constructed and encourages further in-depth studies on this dataset. The video and motion data will be made available for download in the subsequent stages.

In order to improve the effect of dance teaching action analysis, this paper uses dance action skill feature identification method to analyze dance teaching action and combines teaching and technology to simulate dance action. Moreover, this paper conducts dynamic modeling of dance movements and analyzes the typical properties of several dynamic modeling techniques. At the same time, this paper takes the double-joint dance movement limb as the control object for comparative analysis. The comparison shows that the fractional sliding mode approaching law has better smoothing properties. In addition, this paper selects the control method combining fractional calculus and sliding mode control theory to improve the tracking speed and following effect of the double joints of dance movements. Finally, this paper studies the variance virtual spindle cross-coupling control method based on fractional-order sliding mode to further improve the synchronization accuracy of dance movement limb joints. From the experimental data, it can be seen that the application effect of dance movement skill feature recognition in dance teaching movement analysis is very good.

This study aims to explore Korean students’ pragmatic and grammatical awareness with attention to whether there are any differences between college and university students in their level of pragmatic and grammatical awareness. For this purpose, this study employs a language awareness task, which covers three sub-tasks: error recognition, error severity ratings, and error correction. Correlation analyses show that there was a positive correlation between the college group’s grammatical error correction and their pragmatic error correction and between the university group’s pragmatic error recognition and correction. The results also show that the college group recognized pragmatic errors better than grammatical ones and that the university group outperformed the college group at grammatical error recognition. The analysis also reveals that both college and university groups rated pragmatic errors as more severe than grammatical ones. However, the error correction task reveals the opposite, showing that the two learner groups performed grammatical error correction much better than pragmatic error correction. On the basis of the results, pedagogical implications are provided to help learners promote their pragmatic and grammatical awareness.

Action recognition technology is an important part of artificial intelligence. In order to improve the rate of action recognition, this paper designs an action recognition method based on Weighted DTW algorithm. Firstly, the Kinect2.0 is used to obtain the three-dimensional data of the human joint points. Then the quaternion method is used to define the action sequences. The weight of joint is calculated according to the participation in different types of action. Then the improved DTW algorithm is used to design the action recognition experiment. The experimental results show that the action recognition algorithm designed in this paper has better recognition rate and timeliness than traditional DTW algorithm and F-DTW algorithm.

In spite of the importance of activity recognition (AR) for intelligent human-computer interaction in emerging smart space applications, state-of-the-art AR technology is not ready or adequate for real-world deployments due to its insufficient accuracy. The accuracy limitation is directly attributed to uncertainties stemming from multiple sources in the AR system. Hence, one of the major goals of AR research is to improve system accuracy by minimizing or managing the uncertainties encountered throughout the AR process. As we cannot manage uncertainties well without measuring them, we must first quantify their impact. Nevertheless, such a quantification process is very challenging given that uncertainties come from diverse and heterogeneous sources. In this article, we propose an approach, which can account for multiple uncertainty sources and assess their impact on AR systems. We introduce several metrics to quantify the various uncertainties and their impact. We then conduct a quantitative impact analysis of uncertainties utilizing data collected from actual smart spaces that we have instrumented. The analysis is intended to serve as groundwork for developing “diagnostic” accuracy measures of AR systems capable of pinpointing the sources of accuracy loss. This is to be contrasted with the currently used accuracy measures.

The relevance of the research is due to the growing need to automate the processes of text analysis and correction, in particular for Ukrainian-language content, which is characterized by a wealth of morphological and syntactic structure. Due to the wide range of errors that can occur in texts, from spelling to contextual, there is an urgent need to create systems that can accurately identify errors and offer their correct corrections. The specificity of the Ukrainian language, including its grammatical complexity and multifacetedness, requires the adaptation of machine learning models to local features. The purpose of the research is to develop a mathematical model of a decision support system for identifying and correcting errors in Ukrainian-language texts. The task includes both the formalization and mathematical description of the text processing process, and the construction of a model with an orientation to the tasks of classification and text generation. Special attention is paid to the effective consideration of structural features specific to the Ukrainian language in order to increase the accuracy and productivity of the system. The research method is based on the construction of a mathematical model of error correction, which is presented as a context-aware text generation problem. The study used statistical methods and machine learning approaches. Special attention is paid to the formation of a training sample, which combines texts with real and artificial errors to ensure a balanced learning process. The correction module includes generation mechanisms based on contextual models capable of predicting the correct correction for erroneous tokens. Approaches to text vectorization are mathe- matically substantiated, taking into account the peculiarities of the morphology and syntax of the Ukrainian language. The constructed model is a universal basis for creating intelligent systems for automatic editing of Ukrainian-language text. As a result of the research, approaches to building an error correction model in Ukrainian-language texts are formulated and mathematically substantiated. The main result was the creation of an integrated system that uses contextual information to ensure high accuracy of error recognition and correction. The applied mathematical methods include probabilistic approaches and vector representation of tokens, which allows adapting the system to the peculiarities of the Ukrainian language with its high morphological and syntactic complexity. The formed basis of the model creates opportunities for scaling and further use in practical tasks, such as automatic text editing or improving the quality of content in the Ukrainian-speaking environment.

With the technological development of movement recognition based on machine learning model algorithms, the content and movements for physical dance teaching are also seeking changes and innovations. In this paper, a set of three-dimensional convolutional neural network recognition algorithms based on a machine learning model is constructed through the collection to recognition of sports dance movement data. By collecting the skeleton information of typical movements of physical dance, a typical movement dataset of physical dance is constructed, which is recognized by the improved 3D convolutional neural network recognition algorithm under the machine learning model, and the method is validated on the public dataset. The experimental results show that the 3D CNNs in this paper can produce relatively satisfactory results for sports dance action recognition with high accuracy of action recognition, which verifies the feasibility of the 3D convolutional neural network action recognition algorithm under the machine learning model for the acquisition to recognition of sports dance actions. It illustrates that the future can be better to open a new direction of physical dance education content through machine learning models in this form.

In this paper, we first count the dance action motion information and compute different lengths of dance action videos through the threshold of segmentation as the input of a convolutional neural network. Combined with the two-layer level optimization function, the dance action trajectory values can be solved. The dance action trajectory values are compared with the standard action in terms of point distance, which suggests the location of the error for dance teaching assistance training. Finally, based on the three-dimensional data capture to establish a three-dimensional dance teaching model, the dance student’s various parts of the movement error results only between 0.25-2.21, the movement trajectory and the Kinect standard movement trajectory curve is highly fitted, and the dance amplitude, dance strength, dance consistency, dance standardization degree of performance is excellent.

Sports action recognition helps athletes correct their action range and standardize their poses. But it is not an easy task to recognize sports actions, due to the individual difference in action execution. Besides, the difficulty of action recognition increases with the diversity of actions and the complexity of background. The previous studies have not fully considered temporal changes, and failed to determine the exact staring point of actions. To solve the problem, this paper proposes a new method to recognize dance actions and estimate poses based on deep convolutional neural network (DCNN). Firstly, the authors presented full-effect expression of global and local features of dance actions, and derived an optimal model based on DeepPose. Next, a dance pose evaluation model was established based on time sequence segmentation network, and the sparse time sampling strategy was introduced to realize efficient and effective learning of the frame sequence of the whole video. Experimental results confirm the superiority of the full-effect expression of global and local features, and the effectiveness of the proposed model. The research results provide a reference for the application of deep learning (DL) in other scenarios of action recognition and pose estimation.

Although commercial dictation systems and speech-enabled telephone voice user interfaces have become readily available, speech recognition errors remain a serious problem in the design and implementation of speech user interfaces. Previous work hypothesized that switching modality could speed up interactive correction of recognition errors. This article presents multimodal error correction methods that allow the user to correct recognition errors efficiently without keyboard input. Correction accuracy is maximized by novel recognition algorithms that use context information for recognizing correction input. Multimodal error correction is evaluated in the context of a prototype multimodal dictation system. The study shows that unimodal repair is less accurate than multimodal error correction. On a dictation task, multimodal correction is faster than unimodal correction by respeaking. The study also provides empirical evidence that system-initiated error correction (based on confidence measures) may not expedite error correction. Furthermore, the study suggests that recognition accuracy determines user choice between modalities: while users initially prefer speech, they learn to avoid ineffective correction modalities with experience. To extrapolate results from this user study, the article introduces a performance model of (recognition-based) multimodal interaction that predicts input speed including time needed for error correction. Applied to interactive error correction, the model predicts the impact of improvements in recognition technology on correction speeds, and the influence of recognition accuracy and correction method on the productivity of dictation systems. This model is a first step toward formalizing multimodal interaction.

The purpose of the study is to assess the effectiveness of the developed method for forming the skill of self-regulation of plantar pressure during the performance of the dance "Samba" for the personal development of the dancer, their ability for self-expression, and the formation of the image of the real "I" as a generalized self-assessment of the effectiveness of the established model and action scheme in the surrounding space. Research methods and organization. The formative experiment utilized the version v1.3.30de Freestep gait analysis system, produced by Sensor Medica of Italy, as well as six psychodiagnostic methodologies. Research results and conclusions. A reliable increase in the level of self-regulation, courage, independence, and self-control not only while performing dance movements but also in everyday life testifies to the effectiveness of the developed methodology for forming the skill of self-regulation of plantar pressure for the development of personality traits in dancers.

Action recognition technology is widely used in soccer match analysis, helping to evaluate player performance and game strategies. However, soccer actions vary significantly in speed and movement complexity, making it challenging for models to capture motion dynamics accurately. Optical Flow has been widely used to enhance motion representation, but its high computational cost makes it impractical for real-time applications. To address this issue, recent studies have proposed feature-level motion as an alternative, effectively reducing computational overhead while maintaining motion modeling capabilities. Building upon this approach, we extend motion features to 3D CNNs to further enhance spatio-temporal feature learning. In the soccer action recognition task, our method achieves an accuracy of 91.63%, outperforming the baseline by 4.42% while reducing computational cost by 18.9%. These results demonstrate the effectiveness of our approach as a more accurate and efficient solution for real-time applications such as sports broadcasting and match analysis.

Action recognition technology has many application fields including gaming, human-computer interaction, security, virtual reality, etc. The technology has recently advanced and simplified by the introduction of real time depth cameras. The most famous depth camera, Kinect, has shown its success in human action recognitions by supervised learning methods. However, those method require a large number of motion capture data as the ground truth of each skeleton points. This paper proposes a human skeleton extraction method without using reference data. The method extracts the minimum number of articulation points instead of full skeleton data. The articulation points are used as an real-time interface for 3D interaction games.

Human Activity Recognition (HAR) deals with the automatic recognition of physical activities and plays a crucial role in healthcare and sports where wearable sensors and intelligent computational techniques are used. We propose a HAR algorithm that uses the smartphones accelerometer data for human activity recognition. In particular, we present a recurrent convolutional neural network-based HAR algorithm that combines a Convolutional Neural Network (CNN) to extract temporal features from the sensor data, a Fuzzy C-Means (FCM) clustering algorithm to cluster the features extracted by the CNN, and a Long Short-Term Memory (LSTM) network to learn the temporal dependencies between the features. We evaluate the proposed methodology on two distinct datasets: the MotionSense dataset and the WISDM dataset. We evaluate the proposed CNN-FCM-LSTM model on the publicly available MotionSense dataset to classify ten activity types: 1) walking upstairs, 2) walking downstairs, 3) jogging, 4) sitting, 5) standing, 6) level ground walking, 7) jumping jacks, 8) brushing teeth, 9) writing, and 10) eating. Next, we evaluate the model’s performance on the WISDM dataset to assess its ability to generalize to unseen data. On the MotionSense test dataset, CNN-FCM-LSTM achieves a classification accuracy of 99.69%, a sensitivity of 99.62%, a specificity of 99.63%, and a false positive rate per hour (FPR/h) of 0.37%. Meanwhile, it achieves a classification accuracy of 97.27% on the WISDM dataset. The CNN-FCM-LSTM model’s capability to classify a diverse range of activities within a single architecture is noteworthy. The results suggest that the proposed CNN-FCM-LSTM model using smartphone inputs is more accurate, reliable, and robust in detecting and classifying activities than the state-of-the-art models. It should be noted that activity recognition technology has the potential to aid in studying the underpinnings of physical activity, designing more effective training regimens, and simulating the rigors of competition in sports.

The canonical video action recognition methods usually label categories with numbers or one-hot vectors and train neural networks to classify a fixed set of predefined categories, thereby constraining their ability to recognise complex actions and transferable ability to unseen concepts. In contrast, cross-modal learning can improve the performance of individual modalities. Based on the facts that a better action recogniser can be built by reading the statements used to describe actions, we exploited the recent multimodal foundation model CLIP for action recognition. In this study, an effective Vision-Language action recognition adaptation was implemented based on few-shot examples spanning different modalities. We added semantic information to action categories by treating textual and visual label as training examples for action classifier construction rather than simply labelling them with numbers. Due to the different importance of words in text and video frames, simply averaging all sequential features may result in ignoring keywords or key video frames. To capture sequential and hierarchical representation, a weighted token-wise interaction mechanism was employed to exploit the pair-wise correlations adaptively. Extensive experiments with public datasets show that cross-modal action recognition learning helps for downstream action images classification, in other words, the proposed method can train better action classifiers by reading the sentences describing action itself. The method proposed in this study not only reaches good generalisation and zero-shot/few-shot transfer ability on Out of Distribution (OOD) test sets, but also performs lower computational complexity due to the lightweight interaction mechanism with 84.15% Top-1 accuracy on the Kinetics-400.