Search Results Heading

MBRLSearchResults

mbrl.module.common.modules.added.book.to.shelf
Title added to your shelf!
View what I already have on My Shelf.
Oops! Something went wrong.
Oops! Something went wrong.
While trying to add the title to your shelf something went wrong :( Kindly try again later!
Are you sure you want to remove the book from the shelf?
Oops! Something went wrong.
Oops! Something went wrong.
While trying to remove the title from your shelf something went wrong :( Kindly try again later!
    Done
    Filters
    Reset
  • Discipline
      Discipline
      Clear All
      Discipline
  • Is Peer Reviewed
      Is Peer Reviewed
      Clear All
      Is Peer Reviewed
  • Item Type
      Item Type
      Clear All
      Item Type
  • Subject
      Subject
      Clear All
      Subject
  • Year
      Year
      Clear All
      From:
      -
      To:
  • More Filters
249 result(s) for "68T01"
Sort by:
Efficiency of AI Technology Application in Music Education - A Perspective Based on Deep Learning Model DLMM
In recent years, the active attempts and breakthroughs of artificial intelligence in music applications and music education have been amazing. The study proposes a lightweight music score recognition method, CRNN-lite, which achieves both lightweight and improved accuracy. In order that the method can be better and faster migrated to be applied to music education, the article designs a new multimodal domain adaptation algorithm based on differential learning, which effectively utilizes the variability of different modal models for multimodal domain adaptation. Finally, the performance comparison analysis and practical application effects of the proposed method in this paper are discussed. Comprehensive experiments show that the multimodal domain adaptation algorithm DLMM based on differential learning proposed in this paper both achieve better recognition results than other methods, and compared with the original recognition algorithm CRNN-Lite, CRNN-Lite+DLMM precision rises by 2.9%, and the recall rate rises by 1.1%, mAP@0.5 increased by 1.3%.
Trust-driven reinforcement selection strategy for federated learning on IoT devices
Federated learning is a distributed machine learning approach that enables a large number of edge/end devices to perform on-device training for a single machine learning model, without having to share their own raw data. We consider in this paper a federated learning scenario wherein the local training is carried out on IoT devices and the global aggregation is done at the level of an edge server. One essential challenge in this emerging approach is IoT devices selection (also called scheduling), i.e., how to select the IoT devices to participate in the distributed training process. The existing approaches suggest to base the scheduling decision on the resource characteristics of the devices to guarantee that the selected devices would have enough resources to carry out the training. In this work, we argue that trust should be an integral part of the decision-making process and therefore design a trust establishment mechanism between the edge server and IoT devices. The trust mechanism aims to detect those IoT devices that over-utilize or under-utilize their resources during the local training. Thereafter, we introduce DDQN-Trust, a double deep Q learning-based selection algorithm that takes into account the trust scores and energy levels of the IoT devices to make appropriate scheduling decisions. Finally, we integrate our solution into four federated learning aggregation approaches, namely, FedAvg, FedProx, FedShare and FedSGD. Experiments conducted using a real-world dataset show that our DDQN-Trust solution always achieves better performance compared to two main benchmarks: the DQN and random scheduling algorithms. The results also reveal that FedProx outperforms the competitor aggregation models in terms of accuracy when integrated into our DDQN-Trust solution.
Design and Implementation of Dance Personalized Teaching System Assisted by Artificial Intelligence
Current online dance learning faces problems such as the inability to capture accurate information about dance movements and the difficulty of gaining insights into the key flaws of skillful movements. In this paper, a personalized dance teaching system based on motion recognition is constructed. Firstly, RGB and infrared cameras are used to carry out 25 joint point coordinates calibration to establish the human skeletal structure, and combined with depth information to realize the representation of the human skeleton structure in three-dimensional space. The image sequence is converted into a batch of images by a sequence folding layer, and independent CNN convolutional computation is performed in the time dimension, and then the images are converted into feature vector output by a spreading layer. The backbone network is constructed by stacking three LSTM layers for dance movement recognition. In the experiment, we analyze the recognition effect of the system on six types of dance movements, the performance is verified and then applied to the dance teaching practice and invite 50 dance practitioners to subjectively evaluate the system in this paper, and the scores obtained are higher than 8, and the effectiveness of the system is affirmed. The effectiveness of the system is confirmed. This paper provides a useful exploration for the intelligentization of dance teaching.
Study on Innovation and Practice of Grassroots Governance Mode in Hebei Province Promoted by Fengqiao Experience in the New Era Based on Blockchain Technology
From the perspective of social governance in the new era, this paper combines the governance advantages of the Maple Bridge experience with blockchain technology to establish a grassroots governance model of blockchain + Maple Bridge experience, which serves the people’s livelihoods, economy, industry, culture, education, and health care at the grassroots level. The governance effect of Y townships in Hebei Province after applying the blockchain + maple bridge experience model is discussed through the fuzzy hierarchical analysis related technology. The results show that the population of grassroots Y townships in Hebei is concentrated in the age of 20 to 60 years old, accounting for 66.38% of the le The total number of party members in Y townships is 1,924, accounting for about 14.02% of the total number of party members in Y townships. The comprehensive index of grassroots governance status in Y township in Hebei province is 0.4576, and the lowest comprehensive evaluation index of social services is only 0.3873, indicating that the governance effect of the blockchain + maple bridge experience model is remarkable, but there are still problems such as insufficient digitization. The governance effect is the most ideal, with the comprehensive evaluation index of grassroots ecological environment reaching the highest at 0.5402. According to the conclusion of the study, in the future governance work, the investment in digitalization construction can be increased.
Exploring the Joint Cultivation Mechanism of College Students’ Information Literacy and Innovation Ability in the Digital Era
This paper systematizes the teaching system, teaching principles and teaching process of joint cultivation of information literacy and innovation ability. The joint cultivation is applied to practical teaching, and the results of the experiments are analyzed using comparative experiments and questionnaires to analyze the changes in information literacy and innovation ability as well as the dimensions of literacy. After analyzing, it can be seen that compared with traditional teaching, the joint cultivation constructed in this study can effectively improve the information literacy and innovation ability of college students (P=0.001). Among the six dimensions, digital information innovation ability before and after the teaching practice improved by 1.057 over the average value, which is the largest. More than 50% of the students think they can use information technology equipment and tools correctly and solve practical problems creatively.
Decoding the Symbolism of Natural Elements in Oil Painting from the Perspective of Ecological Aesthetics
Based on the concept of ecological aesthetics, this paper explains the concept of imagery oil painting, its development history and the artistic expression of imagery oil painting. Then it takes the visual sense of imagery as the research direction and analyzes the construction of natural element forms in oil paintings. Finally, using the comparative analysis method, we will examine the differences between 14 different types of natural element imagery in China and the Western world. And the questionnaires are used to analyze the attention of different groups of people of all ages to natural imagery. After the research and analysis, the 3 largest dots in the shape representing the house are placed at the forefront of the image, breaking through the boundaries of the image and showing a vitality that breaks free outward. The trees are all tilted at about 45 degrees, which can show the mood of the spring breeze blowing the willow. The road in the village is outlined with two triangles, one big and one small, which gives a clear sense of direction. In the comparison between Chinese and Western natural elements imagery, Chinese oil paintings always have the attitude of “similarity or dissimilarity”, while the West has a strong religious culture. Natural elements have a significant positive effect on the beauty of oil paintings, P<0.001. 20.9% of people like and appreciate the natural elements in oil paintings.
A Practical Study of Creative Stage Performance in the Integration of Vocal Singing and Artificial Intelligence
In this paper, a stage scene modeling and virtual design method based on 3d Max 3D virtual is proposed in the vocal singing creative research. Combined with the Unity3D platform, the scene, characters, objects, photography, and lighting and other peripheral environments are constructed to provide a vivid, realistic and visualized virtual effect for the vocal singing creative stage. It was applied to actual performance programs and musicals, etc., to test the performance and functions of the system. The results show that the 2015 musical Alice’s Adventures in Wonderland, applying virtual reality and other technologies, won audience recognition. Compared with the other two technologies, the 3d Max method of this paper designed the virtual stage scene effect fidelity with an average value of up to 90%. In the choreography production of the Spring Festival gala, the average CPU usage rate is 48%, and it is also able to display the results in each link of the choreography production to achieve the optimization of the production process.
Research on Design Trends and User Experience of Smart Home Furniture
This study primarily focuses on the current state of smart home development and systematically analyzes the future design trend of smart homes from this perspective. The user experience obtained was analyzed using the KANO model to derive the user’s product experience with the smart home. The hierarchical analysis method analyzes and ranks the weights of the resulting user experience hierarchically. The results show that the IoT smart home will have a market size of more than 300 billion yuan in 2023. In 2030, we anticipate that 30.4% of households will consist of just one person. Regardless of the time, safety designs and basic home designs are still essential. Functionality, operability, intelligence, user knowledge, and styling collectively carry a weight of 0.749 and significantly influence the user experience of smart furniture and appliances.
Intelligent Logistics Supply Chain Management: Cost Management and Service Quality Improvement
This paper applies RFID technology to the enterprise’s supply chain system, combined with supply chain management, through RFID to achieve the automated collection of logistics information to improve the operational efficiency and management service level. Relying on the case enterprise through continuous recording and tracking for the application of this technology in a supply chain system to carry out further research through the combination of theory and data, showing more advantages of an intelligent logistics supply chain. The results show that compared with the original system, the intelligent logistics supply chain has better efficiency and accuracy, and label identification has reached 100%. After the implementation of the RFID intelligent supply chain, JZ company’s purchasing, logistics, and production costs showed a downward trend, while profitability and operating capacity showed an upward trend.
Research on the Application of Montage Technique in the Integration of Construction Technique and Design of Cultural Elements of Patchwork Clothing
In modern clothing design, quilting as a means of emphasizing pattern decoration and enriching fabric texture form, its application has presented a diversified and diversified trend. This paper utilizes the montage technique in the process of designing patchwork clothing. The cultural elements of quilted clothing are being innovated through the use of the unique creative art technique of montage. Patchwork clothing design and montage techniques are cross-analyzed to explore the commonality of the two in creative techniques and artistic expression. In order to objectively measure the design effect, AHP is used to determine the weights of the indicators, and then TOPSIS is used for the comprehensive evaluation, which is constructed into a comprehensive evaluation model of quilted apparel design integrating the montage technique. The design evaluation results were achieved by combining the consistency test of the model and the hierarchical total ranking. According to the hierarchical analysis method, the weights of the secondary indicators are calculated, and practicality (25.46%), comfort (20.96%), and functionality (15.37%) rank in the top three, which have a greater impact on the effect of quilting garment design incorporating the montage technique. When the two techniques are applied to apparel design, the understanding and application of practicality, comfort, and functionality should be deepened.