ICTCE

Traditional target detection models struggle to maintain accuracy and improve inference speed for small target detection on computationally limited embedded devices. To solve this problem, this paper proposes an improved YOLOv5 model: GM-YOLO. First, the ...

As small target detection requires identifying and localizing objects of small size in an image or video. Compared with large target detection, small target detection requires less information to be processed and is more susceptible to factors such as ...

In view of the problems of low accuracy, high false detection rate, and complex model in the current PCB (printed circuit board) defect detection model, this paper proposes an improved PCB defect detection model YOLO-CAMN based on YOLOv8n. Firstly, in the ...

Insect infestation is a very serious natural disaster in agricultural production. Therefore, the detection of pest species is of great significance for agricultural insect control and production. However, the current traditional pest detection methods ...

The majority of contemporary watermark detection methodologies are founded upon the examination of natural images, with comparatively limited investigation into the domain of text images. The conventional detection techniques are not specifically ...

This paper aims to achieve precise identification of diseases and pests affecting pear trees through the integration of YOLOv5, Jetson Nano, big data, and deep learning techniques. The objective is to facilitate timely detection of these issues, thereby ...

In the task of hand-object detection, tradition nal object detection models often face challenges such as large sizes and high parameter counts, making them unsuitable for devices with limited storage and computational resources. To address these issues, ...

In the context of smart cities, edge-aware machine vision systems are widely used. These systems involve scenarios where large volumes of image data are stored locally. They also involve scenarios where image data is uploaded to edge clouds, posing ...

Radar-based fall detection technology demonstrates significant application value in healthcare, especially for ensuring the safety of elderly individuals living alone at home. To improve the accuracy and real-time performance of fall detection, this ...

Edge feature extraction in 3D point cloud constitutes an essential component of point cloud processing and reconstruction. Addressing the issue of inaccurate extraction of the feature point set for the egde of building point cloud, this paper presents a ...

With the rapid development of knowledge graphs (KG), enhancing the performance of knowledge graph completion has become a critical research challenge. Traditional methods for KG completion rely heavily on entity and relation embeddings, often neglecting ...

To suppress noise of varying levels in seismic signals and obtain effective seismic data, a denoising approach based on joint loss and feature fusion network is proposed. The network architecture comprises two parts: a 5-layer convolutional neural ...

The importance of detecting motor faults to ensure the stable operation of industrial equipment and reduce maintenance costs cannot be overstated. This research introduces a motor fault detection technology based on analyzing acoustic signals. The ...

Aiming at the problem that the accuracy of environmental sound classification model is affected by the lack of sufficient labeling data, a data enhancement method based on GAN network is proposed. The data set expanded by GAN network data is used to ...

This paper introduces an embedded motor fault diagnosis system that utilizes vibration signal analysis and machine learning. The system is centered around the STM32H753 microcontroller and gathers real-time vibration signals from the motor using a ...

This study proposes an optimized energy detection method that can be applied to cognitive radio systems. The algorithm firstly combines the single-threshold and dual-threshold techniques, which not only solves the problem of perception failure inherent ...

In this paper, a wide-band and compact MIMO antenna is proposed, which achieves a bandwidth of 5.6-19GHz and an antenna size of 18×34mm². In order to improve the isolation, rectangular slots are cut off in the T-shaped structure of the ground layer to ...

To achieve time-frequency synchronization for Orthogonal Frequency Division Multiplexing (OFDM) systems, this paper proposes a synchronization algorithm based on Constant Amplitude Zero Autocorrelation (CAZAC) sequences. In this algorithm, a repetitive ...

GNU Radio is a globally popular software-defined radio (SDR) design framework used for modeling and simulating communication systems, allowing for practical testing and validation on supported SDR hardware platforms. In response to the GNU Radio design ...

Using DSM and LDPC coding, we successfully achieved error-free transmission for the PDM-1024QAM signal and high-quality transmission for the 2048QAM signal in the 400G photonic-assisted terahertz communication system. Without using LDPC, the BER of 1024-...

This work presents a low-noise, high-precision CMOS bandgap reference with chopper stabilization and trimming technique. The chopper technology is used to eliminate the op-amp's distortion voltage and 1/f noise. The polysilicon resistor trimming network ...

The automatic driving car system uses MSPM0G3507 as the main control chip. It is mainly composed of gyroscope module, sensor module, key module and power module. Two PWM drive motors are used to complete the starting and braking of the trolley. Five gray ...

With the increasing demand for computing power by deep neural networks, the demand for memory and network resources is also growing. The majority of weight data exhibit sparse characteristics. Therefore, as a dedicated hardware accelerator for deep ...

In today's rapidly evolving technological landscape, humanity's exploratory ambitions extend to higher and more distant skies, as urban skylines are filled with countless modern structures. These towering skyscrapers, reaching heights of several dozen ...

With the development of science and technology, new application scenarios have new demands for power distribution management system. The purpose of the research is to use the Internet of Things technology and cloud computing technology to achieve ...

This design builds a self-driving car based on the MSPM0 series MCU development board, which can navigate and drive automatically along a designated path. Meanwhile, the car can also perform functions such as emitting sound and light signals at a fixed ...

A power analyzer is an instrument used to test the performance of electrical appliances and troubleshoot electrical faults. At present, the power analyzer on the market generally has the disadvantages of difficult to use, high energy consumption, ...