scholarly journals Use of Convolutional Neural Network for Fish Species Classification

2020 ◽  
Vol 59 (1) ◽  
pp. 131-142
Author(s):  
Daniel Štifanić ◽  
Zlatan Car
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Fish Species ◽  
Video Recording ◽  
Activation Function ◽  
Classification Performance ◽  
Learning Rate ◽  
Machine Learning Algorithms ◽  
Species Classification ◽  
The Impact

Fish population monitoring systems based on underwater video recording are becoming more popular nowadays, however, manual processing and analysis of such data can be time-consuming. Therefore, by utilizing machine learning algorithms, the data can be processed more efficiently. In this research, authors investigate the possibility of convolutional neural network (CNN) implementation for fish species classification. The dataset used in this research consists of four fish species (Plectroglyphidodon dickii, Chromis chrysura, Amphiprion clarkii, and Chaetodon lunulatus), which gives a total of 12859 fish images. For the aforementioned classification algorithm, different combinations of hyperparameters were examined as well as the impact of different activation functions on the classification performance. As a result, the best CNN classification performance was achieved when Identity activation function is applied to hidden layers, RMSprop is used as a solver with a learning rate of 0.001, and a learning rate decay of 1e-5. Accordingly, the proposed CNN model is capable of performing high-quality fish species classifications.

scholarly journals Tree Species Classification Based on Hybrid Ensembles of a Convolutional Neural Network (CNN) and Random Forest Classifiers

2019 ◽  
Vol 11 (23) ◽  
pp. 2788 ◽  
Author(s):  
Uwe Knauer ◽  
Cornelius Styp von Rekowski ◽  
Marianne Stecklina ◽  
Tilman Krokotsch ◽  
Tuan Pham Minh ◽  
...  
Keyword(s):  
Neural Network ◽  
Random Forest ◽  
Convolutional Neural Network ◽  
Tree Species ◽  
Classification Performance ◽  
Majority Voting ◽  
Imaging Data ◽  
Species Classification ◽  
Weighted Voting ◽  
Linear Discriminant

In this paper, we evaluate different popular voting strategies for fusion of classifier results. A convolutional neural network (CNN) and different variants of random forest (RF) classifiers were trained to discriminate between 15 tree species based on airborne hyperspectral imaging data. The spectral data was preprocessed with a multi-class linear discriminant analysis (MCLDA) as a means to reduce dimensionality and to obtain spatial–spectral features. The best individual classifier was a CNN with a classification accuracy of 0.73 +/− 0.086. The classification performance increased to an accuracy of 0.78 +/− 0.053 by using precision weighted voting for a hybrid ensemble of the CNN and two RF classifiers. This voting strategy clearly outperformed majority voting (0.74), accuracy weighted voting (0.75), and presidential voting (0.75).

scholarly journals Accelerating Convolutional Neural Network Using Discrete Orthogonal Transforms

2021 ◽  
Author(s):  
Eduardo Reis ◽  
Rachid Benlamri
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Activation Function ◽  
Learning Rate ◽  
Step Size ◽  
Linear Operation ◽  
Input Size ◽  
Non Linear ◽  
Discrete Orthogonal ◽  
Complex Dataset

<div> <div> <div> <div> <p>All experiments are implemented in Python, using the PyTorch and the Torch-DCT libraries under the Google Colab environment. The Intel(R) Xeon(R) CPU @ 2.00GHz and a Tesla V100-SXM2-16GB GPU were assignment to the Google Colab runtime when profiling the DOT models. It should be noted that the current stable version of the PyTorch library, version 1.8.1, offers only the implementation of the FFT algorithm. Therefore, the implementations of the Hartley and Cosine transforms, listed in Table 1, are not implemented using the same optimizations (algorithm and code wise) adopted in the FFT. We benchmark the DOT methods using the LENET-5 network shown in Figure 10. The ReLU activation function is adopted a non-linear operation across the entire architecture. In this network, the convolutional operations have a kernel of size K = 5. The convolution is of type “valid”, i.e., padding is not applied to the input. Hence the output size M of each layer is smaller than its input size N, that is M=N−K+1. The optimizers used in our experiments are Adam, SGD, SGD with Momentum of 0.9, and RMSProp with α = 0.99. The StepLR scheduler is used with a step size of 20 epochs and a γ = 0.5. We train our model for 40 epochs using a mini-batch of size 128 and a learning rate of 0.001. Five datasets are used in order to benchmark the proposed DOT methods. Among them, we have the MNIST dataset and some variants of the MNIST dataset such as EMNIST, KMNIST and Fashion-MNIST. Additionally, a more complex dataset, CIFAR-10 is also used in our benchmark.</p> </div> </div> </div> </div>

scholarly journals Accelerating Convolutional Neural Network Using Discrete Orthogonal Transforms

2021 ◽  
Author(s):  
Eduardo Reis ◽  
Rachid Benlamri
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Activation Function ◽  
Learning Rate ◽  
Step Size ◽  
Linear Operation ◽  
Input Size ◽  
Non Linear ◽  
Discrete Orthogonal ◽  
Complex Dataset

<div> <div> <div> <div> <p>All experiments are implemented in Python, using the PyTorch and the Torch-DCT libraries under the Google Colab environment. The Intel(R) Xeon(R) CPU @ 2.00GHz and a Tesla V100-SXM2-16GB GPU were assignment to the Google Colab runtime when profiling the DOT models. It should be noted that the current stable version of the PyTorch library, version 1.8.1, offers only the implementation of the FFT algorithm. Therefore, the implementations of the Hartley and Cosine transforms, listed in Table 1, are not implemented using the same optimizations (algorithm and code wise) adopted in the FFT. We benchmark the DOT methods using the LENET-5 network shown in Figure 10. The ReLU activation function is adopted a non-linear operation across the entire architecture. In this network, the convolutional operations have a kernel of size K = 5. The convolution is of type “valid”, i.e., padding is not applied to the input. Hence the output size M of each layer is smaller than its input size N, that is M=N−K+1. The optimizers used in our experiments are Adam, SGD, SGD with Momentum of 0.9, and RMSProp with α = 0.99. The StepLR scheduler is used with a step size of 20 epochs and a γ = 0.5. We train our model for 40 epochs using a mini-batch of size 128 and a learning rate of 0.001. Five datasets are used in order to benchmark the proposed DOT methods. Among them, we have the MNIST dataset and some variants of the MNIST dataset such as EMNIST, KMNIST and Fashion-MNIST. Additionally, a more complex dataset, CIFAR-10 is also used in our benchmark.</p> </div> </div> </div> </div>

scholarly journals CONVOLUTIONAL NEURAL NETWORK ARCHITECTURES PERFORMANCE EVALUATION FOR FISH SPECIES CLASSIFICATION

2021 ◽  
Vol 16 (5) ◽  
pp. 124-139
Author(s):  
HAMIZAH ISMAIL ◽  
◽  
AHMAD FAISAL MOHAMAD AYOB ◽  
AIDY @ MUHAMED SHAWAL M MUSLIM ◽  
MOHAMAD FAKHRATUL RIDWAN ZULKIFLI ◽  
...  
Keyword(s):  
Neural Network ◽  
Performance Evaluation ◽  
Convolutional Neural Network ◽  
Fish Species ◽  
Network Architectures ◽  
Species Classification ◽  
Neural Network Architectures

scholarly journals Validating Deep Neural Networks for Online Decoding of Motor Imagery Movements from EEG Signals

Sensors ◽  
2019 ◽  
Vol 19 (1) ◽  
pp. 210 ◽  
Author(s):  
Zied Tayeb ◽  
Juri Fedjaev ◽  
Nejla Ghaboosi ◽  
Christoph Richter ◽  
Lukas Everding ◽  
...  
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Deep Learning ◽  
Convolutional Neural Network ◽  
Motor Imagery ◽  
Classification Performance ◽  
Feature Engineering ◽  
Learning Models ◽  
Eeg Signals ◽  
Learning Methods

Non-invasive, electroencephalography (EEG)-based brain-computer interfaces (BCIs) on motor imagery movements translate the subject’s motor intention into control signals through classifying the EEG patterns caused by different imagination tasks, e.g., hand movements. This type of BCI has been widely studied and used as an alternative mode of communication and environmental control for disabled patients, such as those suffering from a brainstem stroke or a spinal cord injury (SCI). Notwithstanding the success of traditional machine learning methods in classifying EEG signals, these methods still rely on hand-crafted features. The extraction of such features is a difficult task due to the high non-stationarity of EEG signals, which is a major cause by the stagnating progress in classification performance. Remarkable advances in deep learning methods allow end-to-end learning without any feature engineering, which could benefit BCI motor imagery applications. We developed three deep learning models: (1) A long short-term memory (LSTM); (2) a spectrogram-based convolutional neural network model (CNN); and (3) a recurrent convolutional neural network (RCNN), for decoding motor imagery movements directly from raw EEG signals without (any manual) feature engineering. Results were evaluated on our own publicly available, EEG data collected from 20 subjects and on an existing dataset known as 2b EEG dataset from “BCI Competition IV”. Overall, better classification performance was achieved with deep learning models compared to state-of-the art machine learning techniques, which could chart a route ahead for developing new robust techniques for EEG signal decoding. We underpin this point by demonstrating the successful real-time control of a robotic arm using our CNN based BCI.

Sign in / Sign up

Export Citation Format

Share Document