Platelet Detection Based on Improved YOLO_v3

Liu, Renting; Ren, Chunhui; Fu, Miaomiao; Chu, Zhengkang; Jie, Guo

doi:10.34133/2022/9780569

Cited by 23 publications

(8 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In recent years, the field of object detection has seen notable advancements, with the You Only Look Once (YOLO) series of algorithms, as proposed by Redmon and Liu [14,15], demonstrating advantages such as high speeds, accuracy, and relatively low computational costs. Addressing the specific application to pipeline defect detection, Chen et al [16] introduced an improved YOLOv5 algorithm, based on Cycle-GAN.…”

Section: Introductionmentioning

confidence: 99%

YOLOv5-Sewer: Lightweight Sewer Defect Detection Model

Zhao,

Xiao,

Cai

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

In the field of defect detection in sewers, some researches focus on high accuracy. However, it is challenging for portable on-site devices to provide high performance. This paper proposes a lightweight sewer defect detection model, You Only Look Once (YOLO) v5-Sewer. Firstly, the backbone network of YOLOv5s is replaced with a stacked MobileNetV3 block. Secondly, the C3 module of the neck of YOLOv5s is improved with a C3-Faster module. Thirdly, to compensate for the accuracy loss due to the lightweight network, a channel attention (CA) and convolutional block attention module (CBAM) are added to the proposed method. Finally, the Efficient Intersection over Union (EIOU) is adopted as the localization loss function. Experimental validation on the dataset shows that YOLOv5-Sewer achieves a 1.5% reduction in mean Average Precision (mAP) while reducing floating-point operations by 68%, the number of parameters by 55%, and the model size by 54%, compared to the YOLOv5s model. The detection speed reaches 112 frames per second (FPS) with the GPU (RTX 3070Ti). This model successfully implements a lightweight design while maintaining the detection accuracy, enhancing its functionality on low-performance devices.

show abstract

Section: Introductionmentioning

confidence: 99%

YOLOv5-Sewer: Lightweight Sewer Defect Detection Model

Zhao,

Xiao,

Cai

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

show abstract

“…Machine learning and deep learning are widely leveraged in the field of AD, hoping to improve the performance of AD systems, such as misuse based detection [ 2 ], deception based detection, and bio-based detection [ 3 ]. Machine learning uses algorithms to parse network data, learn characteristics of traffic data, and then classify and predict a certain class of things.…”

Section: Introductionmentioning

confidence: 99%

A Biological Immunity-Based Neuro Prototype for Few-Shot Anomaly Detection with Character Embedding

Ma,

Chen,

Zheng

et al. 2024

Cyborg Bionic Syst

View full text Add to dashboard Cite

Anomaly detection has wide applications to help people recognize false, intrusion, flaw, equipment failure, etc. In most practical scenarios, the amount of the annotated data and the trusted labels is low, resulting in poor performance of the detection. In this paper, we focus on the anomaly detection for the text type data and propose a detection network based on biological immunity for few-shot detection, by imitating the working mechanism of the immune system of biological organisms. This network enabling the protected system to distinguish the aggressive behavior of “nonself” from the legitimate behavior of “self” by embedding characters. First, it constructs episodic task sets and extracts data representations at the character level. Then, in the pretraining phase, Word2Vec is used to embed the representations. In the meta-learning phase, a dynamic prototype containing encoder, routing, and relation is designed to identify the data traffic. Compare to the mean-based prototype, the proposed prototype applies a dynamic routing algorithm that assigns different weights to samples in the support set through multiple iterations to obtain a prototype that combines the distribution of samples. The proposed method is validated on 2 real traffic datasets. The experimental results indicate that (a) the proposed anomaly detection prototype outperforms state-of-the-art few-shot techniques with 1.3% to 4.48% accuracy and 0.18% to 4.55% recall; (b) under the premise of ensuring the accuracy and recall, the number of training samples is reduced to 5 or 10; (c) ablation experiments are designed for each module, and the results show that more accurate prototypes can be obtained by using the dynamic routing algorithm.

show abstract

“…In recent years, applications of artificial intelligence technology, especially Machine Learning (ML), in the field of auxiliary diagnosis have developed rapidly, and efficient progress has been made in automatic detection applications [7][8][9][10]. The advantage of ML methods is that they can diagnose diseases, such as heart disease, with low-cost and reasonable accuracy [11].…”

Section: Introductionmentioning

confidence: 99%

“…Figure 3 shows the normal distribution of jellyfish scattering around the mean point with the normal distribution. The equations 𝑑𝑓 and 𝑒 𝑐 can be rewritten as Equations ( 6) and (7), respectively:…”

mentioning

confidence: 99%

Prediction of Heart Disease Based on Machine Learning Using Jellyfish Optimization Algorithm

Ahmad

Polat

2023

Diagnostics

View full text Add to dashboard Cite

Heart disease is one of the most known and deadly diseases in the world, and many people lose their lives from this disease every year. Early detection of this disease is vital to save people’s lives. Machine Learning (ML), an artificial intelligence technology, is one of the most convenient, fastest, and low-cost ways to detect disease. In this study, we aim to obtain an ML model that can predict heart disease with the highest possible performance using the Cleveland heart disease dataset. The features in the dataset used to train the model and the selection of the ML algorithm have a significant impact on the performance of the model. To avoid overfitting (due to the curse of dimensionality) due to the large number of features in the Cleveland dataset, the dataset was reduced to a lower dimensional subspace using the Jellyfish optimization algorithm. The Jellyfish algorithm has a high convergence speed and is flexible to find the best features. The models obtained by training the feature-selected dataset with different ML algorithms were tested, and their performances were compared. The highest performance was obtained for the SVM classifier model trained on the dataset with the Jellyfish algorithm, with Sensitivity, Specificity, Accuracy, and Area Under Curve of 98.56%, 98.37%, 98.47%, and 94.48%, respectively. The results show that the combination of the Jellyfish optimization algorithm and SVM classifier has the highest performance for use in heart disease prediction.

show abstract

Platelet Detection Based on Improved YOLO_v3

Cited by 23 publications

References 22 publications

YOLOv5-Sewer: Lightweight Sewer Defect Detection Model

YOLOv5-Sewer: Lightweight Sewer Defect Detection Model

A Biological Immunity-Based Neuro Prototype for Few-Shot Anomaly Detection with Character Embedding

Prediction of Heart Disease Based on Machine Learning Using Jellyfish Optimization Algorithm

Contact Info

Product

Resources

About