scholarly journals A Method for Wheat Head Detection Based on Yolov4

2020 ◽  
Author(s):  
Bo Gong ◽  
Daji Ergu ◽  
Ying Cai ◽  
Bo Ma
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Deep Neural Network ◽  
Detection Method ◽  
Computer Hardware ◽  
Detection Methods ◽  
Plant Phenotyping ◽  
Wide Range ◽  
Head Detection ◽  
Multi Level

Abstract Background: Plant phenotyping by deep learning has increased attention. The detection of wheat head in the field is an important mission for estimating the characteristics of wheat heads such as the density, health, maturity, and presence or absence of awns. Traditional wheat head detection methods have problems such as low efficiency, strong subjectivity, and poor accuracy. However, with the development of deep learning theory and the iteration of computer hardware, the accuracy of object detection method using deep neural networks has been greatly improved. Therefore, using a deep neural network method to detect wheat heads in images has a certain value. Results: In this paper, a method of wheat head detection based on deep neural network is proposed. Firstly, for improving the backbone network part, two SPP networks are introduced to enhance the ability of feature learning and increase the receptive field of the convolutional network. Secondly, the top-down and bottom-up feature fusion strategies are applied to obtain multi-level features. Finally, we use Yolov3's head structures to predict the bounding box of object. The results show that our proposed detection method for wheat head has higher accuracy and speed. The mean average precision of our method is 94.5%, and the detection speed of our proposed method is 88fps. Conclusion: The proposed deep neural network can accurately and quickly detector the wheat head in the image which is based on Yolov4. In addition, the training dataset is a wheat head dataset with accurate annotations and rich varieties, which makes the proposed method more robust and has a wide range of application values. The proposed detector is also more suitable for wheat detection task, with the deeper backbone networks. The use of spatial pyramid pooling (SPP) and multi-level features fusion, which all play a crucial role in improving detector performance. Our method provides beneficial help for the breeding of wheat

scholarly journals Real-Time Detection for Wheat Head Applying Deep Neural Network

Sensors ◽  
2020 ◽  
Vol 21 (1) ◽  
pp. 191
Author(s):  
Bo Gong ◽  
Daji Ergu ◽  
Ying Cai ◽  
Bo Ma
Keyword(s):  
Neural Network ◽  
Real Time ◽  
Deep Neural Network ◽  
Data Augmentation ◽  
Detection Methods ◽  
Convolutional Network ◽  
Head Detection ◽  
Real Time Detection ◽  
Low Efficiency ◽  
Basic Network

Wheat head detection can estimate various wheat traits, such as density, health, and the presence of wheat head. However, traditional detection methods have a huge array of problems, including low efficiency, strong subjectivity, and poor accuracy. In this paper, a method of wheat-head detection based on a deep neural network is proposed to enhance the speed and accuracy of detection. The YOLOv4 is taken as the basic network. The backbone part in the basic network is enhanced by adding dual spatial pyramid pooling (SPP) networks to improve the ability of feature learning and increase the receptive field of the convolutional network. Multilevel features are obtained by a multipath neck part using a top-down to bottom-up strategy. Finally, YOLOv3′s head structures are used to predict the boxes of wheat heads. For training images, some data augmentation technologies are used. The experimental results demonstrate that the proposed method has a significant advantage in accuracy and speed. The mean average precision of our method is 94.5%, and the detection speed is 71 FPS that can achieve the effect of real-time detection.

scholarly journals Research on the application of target detection based on deep learning technology in power grid operation inspection

2021 ◽  
Vol 236 ◽  
pp. 01035
Author(s):  
Peng Weifu ◽  
Du Shu ◽  
Chen Shaolei ◽  
Zhou Qing ◽  
Tang Na
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Power System ◽  
Target Detection ◽  
Early Warning ◽  
Deep Neural Network ◽  
Detection Method ◽  
Video Data ◽  
Detection Speed ◽  
External Damage

-External damage to power facilities caused by crane, excavator and other construction operations increases year by year, which will seriously threaten the safe operation of power system. It is an important measure to ensure the safe and reliable operation of power system to implement intelligent monitoring and early warning of power external breakdown through video and other non-contact observation means. The video data of power mainly comes from the fixed monitoring of helicopters, uavs and transformation poles and towers, which is characterized by large amount of data, complex scenes and serious environmental interference. The traditional target detection method usually selects the candidate area first, and then makes judgment based on the characteristics of human construction. The detection speed is slow and the accuracy is low, which makes it impossible to monitor the video data in real time, so as to make timely and accurate early warning and intervention fbr external damage. The target detection method based on deep learning optimizes or even eliminates the selection of candidate regions, which greatly speeds up the detection speed. By learning a lot of target samples through the deep neural network, the characteristics of high robustness are gradually fitted to make the target judgment more accurate. There are three key problems in introducing the target detection method based on deep learning into the power video detection: Firstly, the target detection method based on deep learning has a large amount of calculation and many parameters. In order to realize in-place operation on terminals with limited computing and storage capacity, it is necessary to find a practical method to simplify the network and reduce the amount of operational data in the detection process, which is the key to realize in-place operation and terminal operation of deep neural network. Secondly, for specific application scenarios, the effect of different target detection algorithms varies greatly, and there is a strong particularity of power video. Finding an effective target detection method is the key to improve the detection speed and accuracy. Finally, with the continuous development of deep learning, the structure of deep neural network changes with each passing day, and each has its own characteristics, which network structure is used as the feature extraction layer of target detection algorithm is the focus of research.

scholarly journals A deep neural network approach to predicting clinical outcomes of neuroblastoma patients

2019 ◽  
Author(s):  
Léon-Charles Tranchevent ◽  
Francisco Azuaje ◽  
Jagath C. Rajapakse
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Clinical Outcomes ◽  
Deep Neural Network ◽  
Superior Performance ◽  
Support Vector ◽  
Disease Etiology ◽  
Topological Features ◽  
Wide Range

AbstractThe availability of high-throughput omics datasets from large patient cohorts has allowed the development of methods that aim at predicting patient clinical outcomes, such as survival and disease recurrence. Such methods are also important to better understand the biological mechanisms underlying disease etiology and development, as well as treatment responses. Recently, different predictive models, relying on distinct algorithms (including Support Vector Machines and Random Forests) have been investigated. In this context, deep learning strategies are of special interest due to their demonstrated superior performance over a wide range of problems and datasets. One of the main challenges of such strategies is the “small n large p” problem. Indeed, omics datasets typically consist of small numbers of samples and large numbers of features relative to typical deep learning datasets. Neural networks usually tackle this problem through feature selection or by including additional constraints during the learning process.We propose to tackle this problem with a novel strategy that relies on a graph-based method for feature extraction, coupled with a deep neural network for clinical outcome prediction. The omics data are first represented as graphs whose nodes represent patients, and edges represent correlations between the patients’ omics profiles. Topological features, such as centralities, are then extracted from these graphs for every node. Lastly, these features are used as input to train and test various classifiers.We apply this strategy to four neuroblastoma datasets and observe that models based on neural networks are more accurate than state of the art models (DNN: 85%-87%, SVM/RF: 75%-82%). We explore how different parameters and configurations are selected in order to overcome the effects of the small data problem as well as the curse of dimensionality. Our results indicate that the deep neural networks capture complex features in the data that help predicting patient clinical outcomes.

scholarly journals Emerging accessibility solutions for physical and mobility impairments

2021 ◽  
Vol 6 (18) ◽  
Author(s):  
Anirban Lahiri
Keyword(s):  
Neural Network ◽  
Communication Technology ◽  
Deep Neural Network ◽  
Computer Hardware ◽  
Information Communication ◽  
Mobility Impairments ◽  
The Past ◽  
Wide Range ◽  
Innovative Solutions ◽  
The Impact

Innovation has played a substantial role in the field of Accessibility to the Information Communication Technology (ICT) throughout the past decade. The impact of these groundbreaking achievements has been reflected throughout all industries including Accessibility and Inclusive Technologies. The technological breakthroughs in areas like miniaturized computer hardware (e.g. wearables, smartphones, etc.), Artificial Intelligence (AI), Deep Neural Network, Machine Learning, Robotics, and Internet of Things (IoT) have paved the way for innovative solutions to meet a wide range of needs for people with disabilities.

scholarly journals A Multi-Scale and Multi-Level Fusion Approach for Deep Learning-Based Liver Lesion Diagnosis in Magnetic Resonance Images with Visual Explanation

Life ◽  
2021 ◽  
Vol 11 (6) ◽  
pp. 582
Author(s):  
Yuchai Wan ◽  
Zhongshu Zheng ◽  
Ran Liu ◽  
Zheng Zhu ◽  
Hongen Zhou ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Magnetic Resonance ◽  
Deep Neural Network ◽  
Liver Lesion ◽  
Magnetic Resonance Images ◽  
Complementary Information ◽  
Multi Scale ◽  
Multi Level ◽  
Level Fusion

Many computer-aided diagnosis methods, especially ones with deep learning strategies, of liver cancers based on medical images have been proposed. However, most of such methods analyze the images under only one scale, and the deep learning models are always unexplainable. In this paper, we propose a deep learning-based multi-scale and multi-level fusing approach of CNNs for liver lesion diagnosis on magnetic resonance images, termed as MMF-CNN. We introduce a multi-scale representation strategy to encode both the local and semi-local complementary information of the images. To take advantage of the complementary information of multi-scale representations, we propose a multi-level fusion method to combine the information of both the feature level and the decision level hierarchically and generate a robust diagnostic classifier based on deep learning. We further explore the explanation of the diagnosis decision of the deep neural network through visualizing the areas of interest of the network. A new scoring method is designed to evaluate whether the attention maps can highlight the relevant radiological features. The explanation and visualization make the decision-making process of the deep neural network transparent for the clinicians. We apply our proposed approach to various state-of-the-art deep learning architectures. The experimental results demonstrate the effectiveness of our approach.

scholarly journals A deep neural network approach to predicting clinical outcomes of neuroblastoma patients

2019 ◽  
Vol 12 (S8) ◽  
Author(s):  
Léon-Charles Tranchevent ◽  
Francisco Azuaje ◽  
Jagath C. Rajapakse
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Clinical Outcomes ◽  
Deep Neural Network ◽  
Superior Performance ◽  
Support Vector ◽  
Disease Etiology ◽  
Topological Features ◽  
Wide Range

Abstract Background The availability of high-throughput omics datasets from large patient cohorts has allowed the development of methods that aim at predicting patient clinical outcomes, such as survival and disease recurrence. Such methods are also important to better understand the biological mechanisms underlying disease etiology and development, as well as treatment responses. Recently, different predictive models, relying on distinct algorithms (including Support Vector Machines and Random Forests) have been investigated. In this context, deep learning strategies are of special interest due to their demonstrated superior performance over a wide range of problems and datasets. One of the main challenges of such strategies is the “small n large p” problem. Indeed, omics datasets typically consist of small numbers of samples and large numbers of features relative to typical deep learning datasets. Neural networks usually tackle this problem through feature selection or by including additional constraints during the learning process. Methods We propose to tackle this problem with a novel strategy that relies on a graph-based method for feature extraction, coupled with a deep neural network for clinical outcome prediction. The omics data are first represented as graphs whose nodes represent patients, and edges represent correlations between the patients’ omics profiles. Topological features, such as centralities, are then extracted from these graphs for every node. Lastly, these features are used as input to train and test various classifiers. Results We apply this strategy to four neuroblastoma datasets and observe that models based on neural networks are more accurate than state of the art models (DNN: 85%-87%, SVM/RF: 75%-82%). We explore how different parameters and configurations are selected in order to overcome the effects of the small data problem as well as the curse of dimensionality. Conclusions Our results indicate that the deep neural networks capture complex features in the data that help predicting patient clinical outcomes.

scholarly journals Multifeature Fusion Neural Network for Oceanic Phenomena Detection in SAR Images

Sensors ◽  
2019 ◽  
Vol 20 (1) ◽  
pp. 210 ◽  
Author(s):  
Zhuofan Yan ◽  
Jinsong Chong ◽  
Yawei Zhao ◽  
Kai Sun ◽  
Yuhang Wang ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Detection Method ◽  
Synthetic Aperture ◽  
Detection Methods ◽  
Sar Images ◽  
Detection Thresholds ◽  
Generalization Ability ◽  
Spatial Pyramid Pooling ◽  
Spatial Pyramid

Oceanic phenomena detection in synthetic aperture radar (SAR) images is important in the fields of fishery, military, and oceanography. The traditional detection methods of oceanic phenomena in SAR images are based on handcrafted features and detection thresholds, which have a problem of poor generalization ability. Methods based on deep learning have good generalization ability. However, most of the deep learning methods currently applied to oceanic phenomena detection only detect one type of phenomenon. To satisfy the requirements of efficient and accurate detection of multiple information of multiple oceanic phenomena in massive SAR images, this paper proposes an oceanic phenomena detection method in SAR images based on convolutional neural network (CNN). The method first uses ResNet-50 to extract multilevel features. Second, it uses the atrous spatial pyramid pooling (ASPP) module to extract multiscale features. Finally, it fuses multilevel features and multiscale features to detect oceanic phenomena. The SAR images acquired from the Sentinel-1 satellite are used to establish a sample dataset of oceanic phenomena. The method proposed can achieve 91% accuracy on the dataset.

scholarly journals Modeling a Practical Dual-Fuel Gas Turbine Power Generation System Using Dynamic Neural Network and Deep Learning

2022 ◽  
Vol 14 (2) ◽  
pp. 870
Author(s):  
Mohammad Alsarayreh ◽  
Omar Mohamed ◽  
Mustafa Matar
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Gas Turbine ◽  
Gas Turbines ◽  
Deep Neural Network ◽  
Control Valve ◽  
Dual Fuel ◽  
Dynamic Neural Network ◽  
Fuel Gas ◽  
Wide Range

Accurate simulations of gas turbines’ dynamic performance are essential for improvements in their practical performance and advancements in sustainable energy production. This paper presents models with extremely accurate simulations for a real dual-fuel gas turbine using two state-of-the-art techniques of neural networks: the dynamic neural network and deep neural network. The dynamic neural network has been realized via a nonlinear autoregressive network with exogenous inputs (NARX) artificial neural network (ANN), and the deep neural network has been based on a convolutional neural network (CNN). The outputs selected for simulations are: the output power, the exhausted temperature and the turbine speed or system frequency, whereas the inputs are the natural gas (NG) control valve, the pilot gas control valve and the compressor variables. The data-sets have been prepared in three essential formats for the training and validation of the networks: normalized data, standardized data and SI units’ data. Rigorous effort has been carried out for wide-range trials regarding tweaking the network structures and hyper-parameters, which leads to highly satisfactory results for both models (overall, the minimum recorded MSE in the training of the MISO NARX was 6.2626 × 10−9 and the maximum MSE that was recorded for the MISO CNN was 2.9210 × 10−4, for more than 15 h of GT operation). The results have shown a comparable satisfactory performance for both dynamic NARX ANN and the CNN with a slight superiority of NARX. It can be newly argued that the dynamic ANN is better than the deep learning ANN for the time-based performance simulation of gas turbines (GTs).

scholarly journals p1-FP: Extraction, Classification, and Prediction of Website Fingerprints with Deep Learning

2019 ◽  
Vol 2019 (3) ◽  
pp. 191-209 ◽  
Author(s):  
Se Eun Oh ◽  
Saikrishna Sunkam ◽  
Nicholas Hopper
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Deep Neural Network ◽  
State Of The Art ◽  
Machine Learning Techniques ◽  
Feature Engineering ◽  
Engineering Process ◽  
Learning Techniques ◽  
Wide Range

Abstract Recent advances in Deep Neural Network (DNN) architectures have received a great deal of attention due to their ability to outperform state-of-the-art machine learning techniques across a wide range of application, as well as automating the feature engineering process. In this paper, we broadly study the applicability of deep learning to website fingerprinting. First, we show that unsupervised DNNs can generate lowdimensional informative features that improve the performance of state-of-the-art website fingerprinting attacks. Second, when used as classifiers, we show that they can exceed performance of existing attacks across a range of application scenarios, including fingerprinting Tor website traces, fingerprinting search engine queries over Tor, defeating fingerprinting defenses, and fingerprinting TLS-encrypted websites. Finally, we investigate which site-level features of a website influence its fingerprintability by DNNs.

scholarly journals Research on Time Series Anomaly Detection: Based on Deep Learning Methods

2021 ◽  
Vol 2132 (1) ◽  
pp. 012012
Author(s):  
Jiaqi Zhou
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Time Series ◽  
Deep Learning ◽  
Anomaly Detection ◽  
Deep Neural Network ◽  
Deep Neural Networks ◽  
Detection Task ◽  
Detection Methods ◽  
Learning Methods

Abstract Time series anomaly detection has always been an important research direction. The early time series anomaly detection methods are mainly statistical methods and machine learning methods. With the powerful functions of deep neural network being continuously mined by researchers, the effect of deep neural network in anomaly detection task has been significantly better than the traditional methods. In view of the continuous development and application of deep neural networks such as transformer and graph neural network (GNN) in time series anomaly detection in recent years, the body of research lacks a comparative evaluation of deep learning methods in recent years. This paper studies various deep neural networks suitable for time series, which are divided into three categories according to anomaly detection methods. The evaluation is conducted on public datasets. By analyzing the evaluation criteria, this paper discusses the performance of each model, as well as the problems and development direction in the field of time series anomaly detection in the future. This study found that in the time series anomaly detection task, transformer is suitable for dealing with long-time series prediction, and studying the graph structure of time series may be the best way to deal with time series anomaly detection in the future

Sign in / Sign up

Export Citation Format

Share Document