A review of convolutional neural network architectures and their optimizations

Cong, Shuang; Zhou, Yang

doi:10.1007/s10462-022-10213-5

Cited by 82 publications

(23 citation statements)

References 162 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…CNNs consist of multiple layers of interconnected nodes, where the nodes in each layer perform mathematical operations on the outputs from the previous layer, as depicted in Figure 2. The key feature of a CNN is the convolutional layer, where a small matrix (called a filter or kernel) is applied to local regions of the input data, producing a filtered output that is then passed on to the next layer [10]. The filters are designed to extract useful features from the input datasets, which are then processed in subsequent layers to perform object recognition.…”

Section: Convolutional Neural Network (Cnn)mentioning

confidence: 99%

“…The filters are designed to extract useful features from the input datasets, which are then processed in subsequent layers to perform object recognition. CNNs can also be trained end-to-end using supervised learning techniques, making them highly adaptable to various image processing and recognition tasks [10].…”

Section: Convolutional Neural Network (Cnn)mentioning

confidence: 99%

“…The weights of the fully connected layer are optimally designed to be learned during training. The CNN has many advantages, such as good performance on classification and object recognition tasks, robustness to translation and deformation, parameter sharing and pooling layers, reduced parameters and computational cost, and end-to-end training with supervised learning, which allow for high adaptability [10]. However, the limitations that need to be overcome with further innovative modeling improvement are the requirement of large amounts of training data, the high computational expense, and overfit if not properly regularized.…”

Section: Convolutional Neural Network (Cnn)mentioning

confidence: 99%

See 2 more Smart Citations

A Comprehensive Review of Deep-Learning Applications to Power Quality Analysis

et al. 2023

View full text Add to dashboard Cite

Power quality (PQ) monitoring and detection has emerged as an essential requirement due to the proliferation of sensitive power electronic interfacing devices, electric vehicle charging stations, energy storage devices, and distributed generation energy sources in the recent smart grid and microgrid scenarios. Even though, to date, the traditional approaches play a vital role in providing a solution to the above issue, the limitations, such as the requirement of significant human effort and not being scalable for large-scale power systems, force us to think of alternative approaches. Looking at a better perspective, deep-learning (DL) has gained the main attraction for various researchers due to its inherent capability to classify the data by extracting dominating and prominent features. This manuscript attempts to provide a comprehensive review of PQ detection and classification based on DL approaches to explore its potential, efficiency, and consistency to produce results accurately. In addition, this state-of-the-art review offers an overview of the novel concepts and the step-by-step method for detecting and classifying PQ events. This review has been presented categorically with DL approaches, such as convolutional neural networks (CNNs), autoencoders, and recurrent neural networks (RNNs), to analyze PQ data. This paper also highlights the challenges and limitations of using DL for PQ analysis, and identifies potential areas for future research. This review concludes that DL algorithms have shown promising PQ detection and classification results, and could replace traditional methods.

show abstract

Section: Convolutional Neural Network (Cnn)mentioning

confidence: 99%

Section: Convolutional Neural Network (Cnn)mentioning

confidence: 99%

Section: Convolutional Neural Network (Cnn)mentioning

confidence: 99%

See 1 more Smart Citation

A Comprehensive Review of Deep-Learning Applications to Power Quality Analysis

et al. 2023

View full text Add to dashboard Cite

show abstract

“…In recent years, due to the powerful feature representations of deep learning, the methods based on convolutional neural networks (CNNs) [7] have become the dominant approach for object detection, which has shown remarkable progress in detection accuracy in complex scenarios. These detection methods have been introduced for the bus passenger detection.…”

Section: Introductionmentioning

confidence: 99%

A lightweight bus passenger detection model based on YOLOv5

Li,

Wu,

et al. 2023

IET Image Processing

View full text Add to dashboard Cite

The bus passenger detection algorithm is a key component of a public transportation bus management system. The detection techniques based on the convolutional neural network have been widely used in bus passenger detection. However, they require high memory and computational requirements, which hinder the deployment of bus passenger detectors in the bus system. In this paper, a lightweight bus passenger detection model based on YOLOv5 is introduced. To make the model more lightweight, the inner and outer cross‐stage bottleneck modules, called ICB and OCB, respectively, are proposed. The proposed module reduces the quantity of parameter and floating point operations and increases the detection speed. In addition, the neighbour feature attention pooling is adopted to improve detection accuracy. The performance of the lightweight model on the bus passenger dataset is empirically demonstrated. The experiment results demonstrate that the proposed model is lightweight and efficient. Compared lightweight YOLOv5n with the original algorithm, the model weight is reduced by 31% to 2.6M, and the detection speed is increased by 6% to 40FPS without an accuracy drop.

show abstract

“…They can effectively handle non-normal data and capture nonlinear relationships. Neural networks(Cong & Zhou, 2023) are a powerful option due to their ability to learn complex patterns and relationships in data. They can adapt to various distributions, including non-normal ones, and offer exibility in modelling.…”

mentioning

confidence: 99%

Predictive Modelling of Thermal Conductivity in Single-Material Nanofluids: A Novel Approach

Onyiriuka

2023

Preprint

View full text Add to dashboard Cite

Background This research introduces a novel approach for modelling single-material nanofluids, considering the constituents and characteristics of the fluids under investigation. The primary focus of this study was to develop models for predicting the thermal conductivity of nanofluids using a range of machine learning algorithms, including ensembles, trees, neural networks, linear regression, Gaussian process regressors, and support vector machines. The main body of the abstract To identify the most relevant features for accurate thermal conductivity prediction, the study compared the performance of established feature selection algorithms, such as minimum redundancy, maximum relevance, Ftest, and RReliefF, with a newly proposed feature selection algorithm. The novel algorithm eliminated features lacking direct implications for fluid thermal conductivity. The selected features encompassed temperature as a thermal property of the fluid itself, multiphase features such as volume fraction and particle size, and material features including nanoparticle material and base fluid material, which could be fixed based on any two intensive properties. Statistical methods were employed to select the features accordingly. Results The results demonstrated that the novel feature selection algorithm outperformed the established approaches in predicting the thermal conductivity of nanofluids. The models were evaluated using 5-fold cross-validation, and the best model based on the proposed feature selection algorithm exhibited a root mean squared error of validation of 1.83 and an R-squared value of 0.94. The model achieved a root mean squared error of 1.46 for the test set and an R-squared value of 0.97. Conclusions The developed predictive model holds practical significance by enabling nanofluids' numerical study and optimisation before their creation. This model facilitates the customisation of conventional fluids to attain desired fluid properties, particularly emphasising thermal properties. Additionally, the model permits the exploration of numerous nanofluid variations based on permutations of their features. Consequently, this research contributes valuable insights to the design and optimisation of nanofluid systems, advancing our understanding and application of thermal conductivity in nanofluids.

show abstract

A review of convolutional neural network architectures and their optimizations

Cited by 82 publications

References 162 publications

A Comprehensive Review of Deep-Learning Applications to Power Quality Analysis

A Comprehensive Review of Deep-Learning Applications to Power Quality Analysis

A lightweight bus passenger detection model based on YOLOv5

Predictive Modelling of Thermal Conductivity in Single-Material Nanofluids: A Novel Approach

Contact Info

Product

Resources

About