scholarly journals Neurons vs Weights Pruning in Artificial Neural Networks

2015 ◽  
Vol 3 ◽  
pp. 22 ◽  
Author(s):  
Andrey Bondarenko ◽  
Arkady Borisov ◽  
Ludmila Alekseeva
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Classification Accuracy ◽  
Classification Rate ◽  
Good Classification ◽  
Pruning Algorithms ◽  
Artificial Neural ◽  
Accuracy Rates ◽  
Pruning Techniques ◽  
Growing Neural Networks

<p class="R-AbstractKeywords">Artificial neural networks (ANN) are well known for their good classification abilities. Recent advances in deep learning imposed second ANN renaissance. But neural networks possesses some problems like choosing hyper parameters such as neuron layers count and sizes which can greatly influence classification rate. Thus pruning techniques were developed that can reduce network sizes, increase its generalization abilities and overcome overfitting. Pruning approaches, in contrast to growing neural networks approach, assume that sufficiently large ANN is already trained and can be simplified with acceptable classification accuracy loss.</p><p class="R-AbstractKeywords">Current paper compares nodes vs weights pruning algorithms and gives experimental results for pruned networks accuracy rates versus their non-pruned counterparts. We conclude that nodes pruning is more preferable solution, with some sidenotes.</p>

scholarly journals The Use of Artificial Neural Networks and a General Discriminant Analysis for Predicting Culling Reasons in Holstein-Friesian Cows Based on First-Lactation Performance Records

Animals ◽  
2021 ◽  
Vol 11 (3) ◽  
pp. 721
Author(s):  
Krzysztof Adamczyk ◽  
Wilhelm Grzesiak ◽  
Daniel Zaborski
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Discriminant Analysis ◽  
Multilayer Perceptrons ◽  
Correct Classification ◽  
Correct Classification Rate ◽  
Classification Rate ◽  
Holstein Friesian ◽  
Artificial Neural ◽  
Friesian Cows

The aim of the present study was to verify whether artificial neural networks (ANN) may be an effective tool for predicting the culling reasons in cows based on routinely collected first-lactation records. Data on Holstein-Friesian cows culled in Poland between 2017 and 2018 were used in the present study. A general discriminant analysis (GDA) was applied as a reference method for ANN. Considering all predictive performance measures, ANN were the most effective in predicting the culling of cows due to old age (99.76–99.88% of correctly classified cases). In addition, a very high correct classification rate (99.24–99.98%) was obtained for culling the animals due to reproductive problems. It is significant because infertility is one of the conditions that are the most difficult to eliminate in dairy herds. The correct classification rate for individual culling reasons obtained with GDA (0.00–97.63%) was, in general, lower than that for multilayer perceptrons (MLP). The obtained results indicated that, in order to effectively predict the previously mentioned culling reasons, the following first-lactation parameters should be used: calving age, calving difficulty, and the characteristics of the lactation curve based on Wood’s model parameters.

Optimization Artificial Neural Network Using Artificial Bee Colony in Letter Recognition Classification

2020 ◽  
Vol 8 (4) ◽  
pp. 469
Author(s):  
I Gusti Ngurah Alit Indrawan ◽  
I Made Widiartha
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Classification Accuracy ◽  
Artificial Bee Colony Algorithm ◽  
Artificial Bee Colony ◽  
Letter Recognition ◽  
Bee Colony ◽  
Artificial Neural ◽  
Hidden Layer

Artificial Neural Networks or commonly abbreviated as ANN is one branch of science from the field of artificial intelligence which is often used to solve various problems in fields that involve grouping and pattern recognition. This research aims to classify Letter Recognition datasets using Artificial Neural Networks which are weighted optimally using the Artificial Bee Colony algorithm. The best classification accuracy results from this study were 92.85% using a combination of 4 hidden layers with each hidden layer containing 10 neurons.

scholarly journals Structural Features for Furan-Derived Fruity and Meaty Aroma Impressions

2016 ◽  
Vol 11 (10) ◽  
pp. 1934578X1601101
Author(s):  
Bettina Wailzer ◽  
Johanna Klocker ◽  
Peter Wolschann ◽  
Gerhard Buchbauer
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Network Architecture ◽  
Structural Features ◽  
Classification Rule ◽  
Classification Rate ◽  
Furan Derivatives ◽  
Information Index ◽  
The Neural Network ◽  
Artificial Neural

Furan derivatives are part of nearly all food aromas. They are mainly formed by thermal degradation of carbohydrates and ascorbic acid and from sugar-amino acid interactions during food processing. Caramel-like, sweet, fruity, nutty, meaty, and burnt odor impressions are associated with this class of compounds. In the presented work, structure-activity relationship (SAR) investigations are performed on a series of furan derivatives in order to find structural subunits, which are responsible for the particular characteristic flavors. Therefore, artificial neural networks are applied on a set of 35 furans with the aroma categories “meaty” or “fruity” to calculate a classification rule and class boundaries for these two aroma impressions. By training a multilayer perceptron network architecture with a backpropagation algorithm, a correct classification rate of 100% is obtained. The neural network is able to distinguish between the two studied groups by using the following significant descriptors as inputs: number of sulfur atoms, Looping Centric Information Index, Folding Degree Index and Petitjean Shape Indices. Finally, the results clearly demonstrate that artificial neural networks are successful tools to investigate non-linear qualitative structure-odor relationships of aroma compounds.

scholarly journals Leg Motion Classification with Artificial Neural Networks Using Wavelet-Based Features of Gyroscope Signals

Sensors ◽  
2011 ◽  
Vol 11 (2) ◽  
pp. 1721-1743 ◽  
Author(s):  
Birsel Ayrulu-Erdem ◽  
Billur Barshan
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Classification Accuracy ◽  
Discrete Wavelet ◽  
Daubechies Wavelet ◽  
Motion Classification ◽  
Artificial Neural ◽  
Leg Motion ◽  
Function Selection ◽  
Selection Of

We extract the informative features of gyroscope signals using the discrete wavelet transform (DWT) decomposition and provide them as input to multi-layer feed-forward artificial neural networks (ANNs) for leg motion classification. Since the DWT is based on correlating the analyzed signal with a prototype wavelet function, selection of the wavelet type can influence the performance of wavelet-based applications significantly. We also investigate the effect of selecting different wavelet families on classification accuracy and ANN complexity and provide a comparison between them. The maximum classification accuracy of 97.7% is achieved with the Daubechies wavelet of order 16 and the reverse bi-orthogonal (RBO) wavelet of order 3.1, both with similar ANN complexity. However, the RBO 3.1 wavelet is preferable because of its lower computational complexity in the DWTdecomposition and reconstruction.

scholarly journals Integrating MNF and HHT Transformations into Artificial Neural Networks for Hyperspectral Image Classification

2020 ◽  
Vol 12 (14) ◽  
pp. 2327
Author(s):  
Ming-Der Yang ◽  
Kai-Hsiang Huang ◽  
Hui-Ping Tsai
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Classification Accuracy ◽  
Hyperspectral Image ◽  
Critical Issue ◽  
Training Sample ◽  
Ann Model ◽  
Hilbert Huang Transform ◽  
Training Samples ◽  
Artificial Neural

The critical issue facing hyperspectral image (HSI) classification is the imbalance between dimensionality and the number of available training samples. This study attempted to solve the issue by proposing an integrating method using minimum noise fractions (MNF) and Hilbert–Huang transform (HHT) transformations into artificial neural networks (ANNs) for HSI classification tasks. MNF and HHT function as a feature extractor and image decomposer, respectively, to minimize influences of noises and dimensionality and to maximize training sample efficiency. Experimental results using two benchmark datasets, Indian Pine (IP) and Pavia University (PaviaU) hyperspectral images, are presented. With the intention of optimizing the number of essential neurons and training samples in the ANN, 1 to 1000 neurons and four proportions of training sample were tested, and the associated classification accuracies were evaluated. For the IP dataset, the results showed a remarkable classification accuracy of 99.81% with a 30% training sample from the MNF1–14+HHT-transformed image set using 500 neurons. Additionally, a high accuracy of 97.62% using only a 5% training sample was achieved for the MNF1–14+HHT-transformed images. For the PaviaU dataset, the highest classification accuracy was 98.70% with a 30% training sample from the MNF1–14+HHT-transformed image using 800 neurons. In general, the accuracy increased as the neurons increased, and as the training samples increased. However, the accuracy improvement curve became relatively flat when more than 200 neurons were used, which revealed that using more discriminative information from transformed images can reduce the number of neurons needed to adequately describe the data as well as reducing the complexity of the ANN model. Overall, the proposed method opens new avenues in the use of MNF and HHT transformations for HSI classification with outstanding accuracy performance using an ANN.

scholarly journals Analysis of Children’s Prosodic Features Using Emotion Based Utterances in Urdu Language

2018 ◽  
Vol 8 (3) ◽  
pp. 2954-2957
Author(s):  
S. Khan ◽  
S. A. Ali ◽  
J. Sallar
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Significant Role ◽  
Classification Accuracy ◽  
Naive Bayes ◽  
Naïve Bayes ◽  
Prosodic Features ◽  
Basic Emotions ◽  
Learning Classifiers ◽  
Artificial Neural

Emotion plays a significant role in identifying the states of a speaker using spoken utterances. Prosodic features add sense in spoken utterances providing speaker emotions. The objective of this research is to analyze the behavior of prosodic features (individual and in combination with others’ prosodic features) with different learning classifiers on emotion based utterances of children in the Urdu language. In this paper, three different prosodic features (intensity, pitch, formant and their combinations) with five different learning classifiers(ANN, J-48, K-star, Naïve Bayes, decision stump) and four basic emotions (happy, sad, angry, and neutral) were used to develop the experimental framework. Demonstrative experiments expressed that, in terms of classification accuracy, artificial neural networks show significant results with both individual and combination of prosodic features in comparison with other learning classifiers.

scholarly journals Artificial Neural Networks to Assess Emotional States from Brain-Computer Interface

Electronics ◽  
2018 ◽  
Vol 7 (12) ◽  
pp. 384 ◽  
Author(s):  
Roberto Sánchez-Reolid ◽  
Arturo García ◽  
Miguel Vicente-Querol ◽  
Luz Fernández-Aguilar ◽  
María López ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Classification Accuracy ◽  
Brain Computer Interface ◽  
Application Programming Interface ◽  
Computer Interface ◽  
Emotional States ◽  
Artificial Neural ◽  
Highly Correlated ◽  
Interface Devices

Estimation of human emotions plays an important role in the development of modern brain-computer interface devices like the Emotiv EPOC+ headset. In this paper, we present an experiment to assess the classification accuracy of the emotional states provided by the headset’s application programming interface (API). In this experiment, several sets of images selected from the International Affective Picture System (IAPS) dataset are shown to sixteen participants wearing the headset. Firstly, the participants’ responses in form of a self-assessment manikin questionnaire to the emotions elicited are compared with the validated IAPS predefined valence, arousal and dominance values. After statistically demonstrating that the responses are highly correlated with the IAPS values, several artificial neural networks (ANNs) based on the multilayer perceptron architecture are tested to calculate the classification accuracy of the Emotiv EPOC+ API emotional outcomes. The best result is obtained for an ANN configuration with three hidden layers, and 30, 8 and 3 neurons for layers 1, 2 and 3, respectively. This configuration offers 85% classification accuracy, which means that the emotional estimation provided by the headset can be used with high confidence in real-time applications that are based on users’ emotional states. Thus the emotional states given by the headset’s API may be used with no further processing of the electroencephalogram signals acquired from the scalp, which would add a level of difficulty.

scholarly journals Feature subset selection in dynamic stability assessment power system using artificial neural networks

2015 ◽  
Vol 18 (2) ◽  
pp. 15-24
Author(s):  
Au Ngoc Nguyen ◽  
Anh Huy Nguyen ◽  
Binh Thi Thanh Phan
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Power System ◽  
Dynamic Stability ◽  
Subset Selection ◽  
Feature Subset Selection ◽  
Feature Subset ◽  
Stability Assessment ◽  
Classification Rate ◽  
Artificial Neural

This paper presents method of feature subset selection in dynamic stability assessment (DSA) power system using artificial neural networks (ANN). In the application of ANN on DSA power system, feature subset selection aims to reduce the number of training features, cost and memory computer. However, the major challenge is to reduce the number of features but classification rate gets a high accuracy. This paper proposes applying Sequential Forward Selection (SFS), Sequential Backward Selection (SBS), Sequential Forward Floating Selection (SFFS) and Feature Ranking (FR) algorithm to feature subset selection. The effectiveness of the algorithms was tested on the GSO-37bus power system. With the same number of features, the calculation results show that SFS algorithm yielded higher classification rate than FR, SBS algorithm. SFS algorithm yielded the same classification rate as SFFS algorithm.

Sign in / Sign up

Export Citation Format

Share Document