Current Issue : January-March Volume : 2024 Issue Number : 1 Articles : 5 Articles
Instrument recognition is a critical task in the field of music information retrieval and deep neural networks have become the dominant models for this task due to their effectiveness. Recently, incorporating data augmentation methods into deep neural networks has been a popular approach to improve instrument recognition performance. However, existing data augmentation processes are always based on simple instrument spectrogram representation and are typically independent of the predominant instrument recognition process. This may result in a lack of coverage for certain required instrument types, leading to inconsistencies between the augmented data and the specific requirements of the recognition model. To build more expressive instrument representation and address this inconsistency, this paper constructs a combined two-channel representation for further capturing the unique rhythm patterns of different types of instruments and proposes a new predominant instrument recognition strategy called Augmentation Embedded Deep Convolutional neural Network (AEDCN). AEDCN adds two fully connected layers into the backbone neural network and integrates data augmentation directly into the recognition process by introducing a proposed Adversarial Embedded Conditional Variational AutoEncoder (ACEVAE) between the added fully connected layers of the backbone network. This embedded module aims to generate augmented data based on designated labels, thereby ensuring its compatibility with the predominant instrument recognition model. The effectiveness of the combined representation and AEDCN is validated through comparative experiments with other commonly used deep neural networks and data augmentation-based predominant instrument recognition methods using a polyphonic music recognition dataset. The results demonstrate the superior performance of AEDCN in predominant instrument recognition tasks....
Due to their enormous characteristics and applicability, quadrotor unmanned aerial vehicles (UAVs) have enjoyed much popularity lately. However, designing a stable control strategy for quadrotors still remains one of the major concerns mainly due to the requirement of an accurate system model. They are naturally underactuated systems, with complex and nonlinear dynamics as well as interaxes couplings. Considering the dynamical complexities of these vehicles, one of the efficient methods is to utilize the relay feedback experiments and automatic tuning approach to tackle these issues. This paper investigates the employment of the relay with embedded integrator approach, wherein the quadrotor dynamics are estimated effectively with minimal parameters as compared to previously utilized relay with hysteresis technique. Frequency sampling filter (FSF) is further utilized for the extraction of the needful data through the signals obtained using the relay experiments, followed by the estimation of the plant dynamics. PID controllers have then been developed using the approximated quadrotor models. Which are used in the proposed cascade control structure for the quadrotor. The demonstrated results and analysis present the efficacy of designed control system technique for the quadrotor UAV....
A recommendation algorithm combined with a knowledge graph enables auxiliary information on items to be obtained by using the knowledge graph to achieve better recommendations. However, the recommendation performance of existing methods relies heavily on the quality of the knowledge graph. Knowledge graphs often contain noise and irrelevant connections between items and entities in the real world. This knowledge graph sparsity and noise significantly amplifies the noise effects and hinders the accurate representation of user preferences. In response to these problems, an improved collaborative recommendation model is proposed which integrates knowledge embedding and graph contrastive learning. Specifically, we propose a knowledge contrastive learning scheme to mitigate noise within the knowledge graph during information aggregation, thereby enhancing the embedding quality of items. Simultaneously, to tackle the issue of insufficient user-side information in the knowledge graph, graph convolutional neural networks are utilized to propagate knowledge graph information from the item side to the user side, thereby enhancing the personalization capability of the recommendation system. Additionally, to resolve the oversmoothing issue in graph convolutional networks, a residual structure is employed to establish the message propagation network between adjacent layers of the same node, which expands the information propagation path. Experimental results on the Amazon-book and Yelp2018 public datasets demonstrate that the proposed model outperforms the best baseline models by 11.4% and 11.6%, respectively, in terms of the Recall@20 evaluation metric. This highlights the method’s efficacy in improving the recommendation accuracy and effectiveness when incorporating knowledge graphs into the recommendation process....
Nowadays, due to the cleanliness and high efficiency of grid-connected new energy, it has become more and more popular in the market. However, there are still some problems in grid-connected power control and cannot be well supervised. Therefore, this paper studies a new energy grid-connected power control method based on predictive regulation performance and embedded systems, aiming to control new energy grid-connected power through predictive regulation performance and embedded systems. In this paper, the predictive regulation performance and energy conversion rate of the embedded system new energy grid connection are tested. In the experiment, the energy conversion rate was between 60% and 70%, while the traditional new energy grid connection rate was between 40% and 60%. The maximum power generation efficiency of new energy grid-connected with predictive regulation performance and embedded systems was 83%, while the maximum power generation efficiency of traditional new energy grid-connected was 68%. It can be seen from these experimental results that predictive regulation performance and embedded systems have good effects on new energy grid-connected power control....
This article introduces a novel approach to human activity recognition (HAR) by presenting a sensor that utilizes a real-time embedded neural network. The sensor incorporates a low-cost microcontroller and an inertial measurement unit (IMU), which is affixed to the subject’s chest to capture their movements. Through the implementation of a convolutional neural network (CNN) on the microcontroller, the sensor is capable of detecting and predicting the wearer’s activities in real-time, eliminating the need for external processing devices. The article provides a comprehensive description of the sensor and the methodology employed to achieve real-time prediction of subject behaviors. Experimental results demonstrate the accuracy and high inference performance of the proposed solution for real-time embedded activity recognition....
Loading....