N. Belknap's Four-Valued Logic, Belknap Computer and New Proximity Functions for Comparing Discrete Objects

2021 ◽  
Vol 1 (2 (6)) ◽  
Author(s):  
Valerii Dmitrienko ◽  
Sergey Leonov ◽  
Mykola Mezentsev
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
The Other ◽  
Proximity Function ◽  
Input Information ◽  
Proximity Measures ◽  
The One ◽  
True Values

The idea of ​​Belknap's four-valued logic is that modern computers should function normally not only with the true values ​​of the input information, but also under the conditions of inconsistency and incompleteness of true failures. Belknap's logic introduces four true values: T (true - true), F (false - false), N (none - nobody, nothing, none), B (both - the two, not only the one but also the other).  For ease of work with these true values, the following designations are introduced: (1, 0, n, b). Belknap's logic can be used to obtain estimates of proximity measures for discrete objects, for which the functions Jaccard and Needhem, Russel and Rao, Sokal and Michener, Hamming, etc. are used. In this case, it becomes possible to assess the proximity, recognition and classification of objects in conditions of uncertainty when the true values ​​are taken from the set (1, 0, n, b). Based on the architecture of the Hamming neural network, neural networks have been developed that allow calculating the distances between objects described using true values ​​(1, 0, n, b). Keywords: four-valued Belknap logic, Belknap computer, proximity assessment, recognition and classification, proximity function, neural network.

Application of Probabilistic Neural Network in Pattern Classification

2013 ◽  
Vol 441 ◽  
pp. 738-741 ◽  
Author(s):  
Shuo Ding ◽  
Xiao Heng Chang ◽  
Qing Hui Wu
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Pattern Classification ◽  
Probabilistic Neural Network ◽  
Back Propagation ◽  
Back Propagation Neural Networks ◽  
Training Samples ◽  
The One ◽  
Speed Accuracy

The network model of probabilistic neural network and its method of pattern classification and discrimination are first introduced in this paper. Then probabilistic neural network and three usually used back propagation neural networks are established through MATLAB7.0. The pattern classification of dots on a two-dimensional plane is taken as an example. Probabilistic neural network and improved back propagation neural networks are used to classify these dots respectively. Their classification results are compared with each other. The simulation results show that compared with back propagation neural networks, probabilistic neural network has simpler learning rules, faster training speed and it needs fewer training samples; the pattern classification method based on probabilistic neural network is very effective, and it is superior to the one based on back propagation neural networks in classifying speed, accuracy as well as generalization ability.

Predicting vibrancy of metro station areas considering spatial relationships through graph convolutional neural networks: The case of Shenzhen, China

2020 ◽  
pp. 239980832097786
Author(s):  
Longzhu Xiao ◽  
Siuming Lo ◽  
Jiangping Zhou ◽  
Jixiang Liu ◽  
Linchuan Yang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Built Environment ◽  
Empirical Study ◽  
Decision Makers ◽  
The Other ◽  
Spatial Relationships ◽  
Transit Oriented Development ◽  
Metro Station ◽  
The One

Vibrancy is one of the most desirable outcomes of transit-oriented development (TOD). The vibrancy of a metro station area (MSA) depends partially on the MSA’s built-environment features. Predicting an MSA’s vibrancy with its built-environment features is of great interest to decision makers as these features are often modifiable by public interventions. However, little has been done on MSAs’ vibrancy in existing studies. On the one hand, seldom has the vibrancy of MSAs been explicitly explored, and measuring the vibrancy is essential. On the other hand, because MSAs are interconnected, one MSA’s vibrancy depends on the MSA’s features and those of relevant MSAs. Hence, selecting a suitable metric that quantifies spatial relationships between MSAs can better predict MSAs’ vibrancy. In this study, we identify four single-dimensional vibrancy proxies and fuse them into an integrated index. Moreover, we design a two-layer graph convolutional neural network model that accounts for both the built-environment features of MSAs and spatial relationships between MSAs. We employ the model in an empirical study in Shenzhen, China, and illustrate (1) how different metrics of spatial relationships influence the prediction of MSAs’ vibrancy; (2) how the predictability varies across single-dimensional and integrated proxies of MSAs’ vibrancy; and (3) how the findings of this study can be used to enlighten decision makers. This study enriches our understandings of spatial relationships between MSAs. Moreover, it can help decision makers with targeted policies for developing MSAs towards TOD.

scholarly journals Learning Fully Dense Neural Networks for Image Semantic Segmentation

2019 ◽  
Vol 33 ◽  
pp. 9283-9290 ◽  
Author(s):  
Mingmin Zhen ◽  
Jinglu Wang ◽  
Lei Zhou ◽  
Tian Fang ◽  
Long Quan
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Loss Function ◽  
Spatial Information ◽  
Semantic Segmentation ◽  
The Other ◽  
Feature Maps ◽  
Spatial Reconstruction ◽  
Benchmark Datasets ◽  
The One

Semantic segmentation is pixel-wise classification which retains critical spatial information. The “feature map reuse” has been commonly adopted in CNN based approaches to take advantage of feature maps in the early layers for the later spatial reconstruction. Along this direction, we go a step further by proposing a fully dense neural network with an encoderdecoder structure that we abbreviate as FDNet. For each stage in the decoder module, feature maps of all the previous blocks are adaptively aggregated to feedforward as input. On the one hand, it reconstructs the spatial boundaries accurately. On the other hand, it learns more efficiently with the more efficient gradient backpropagation. In addition, we propose the boundary-aware loss function to focus more attention on the pixels near the boundary, which boosts the “hard examples” labeling. We have demonstrated the best performance of the FDNet on the two benchmark datasets: PASCAL VOC 2012, NYUDv2 over previous works when not considering training on other datasets.

scholarly journals A Study of $\tau^-$ and $\mu^-$ in the Field of Nuclei Using Neural Network Techniques

2021 ◽  
Vol 12 ◽  
pp. 130
Author(s):  
N. Panagiotides ◽  
T. S. Kosmas
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Wave Function ◽  
Analytical Calculation ◽  
The Other ◽  
Calculation Algorithm ◽  
Heavy Lepton ◽  
Electron Conversion ◽  
The One ◽  
Sigmoid Functions

The rate of a heavy lepton (muon or tau) capture by nuclei as well as the heavy lepton to electron conversion rate can be calculated when the heavy lepton wavefunction is known. Analytical calculation of the wavefunction of any of these leptons around any nucleus is not feasible owning to their small Bohr radii, on the one hand, and to the finite nuclear extend on the other. A new numerical calculation algorithm is proposed hereby, which makes use of the concept of neural networks. The main advantage of this new technique is that the wave function is produced analytically as a sum of sigmoid functions.

Somatoform disorders: diseases of the civilization

2020 ◽  
pp. 25-30
Author(s):  
I. Kukhtevich
Keyword(s):  
Health Professionals ◽  
Somatoform Disorders ◽  
Neuropsychiatric Disorders ◽  
The Other ◽  
Significant Part ◽  
Organic Basis ◽  
Autonomic Disorders ◽  
The One ◽  
Somatic Diseases

Functional autonomic disorders occupy a significant part in the practice of neurologists and professionals of other specialties as well. However, there is no generally accepted classification of such disorders. In this paper the authors tried to show that functional autonomic pathology corresponds to the concept of somatoform disorders combining syndromes manifested by visceral, borderline psychopathological, neurological symptoms that do not have an organic basis. The relevance of the problem of somatoform disorders is that on the one hand many health professionals are not familiar enough with manifestations of borderline neuropsychiatric disorders, often forming functional autonomic disorders, and on the other hand they overestimate somatoform symptoms that are similar to somatic diseases.

Classification of Alloys with an Artificial Neural Network and Multivariate Calibration of Glow-Discharge Emission Spectra

1991 ◽  
Vol 45 (10) ◽  
pp. 1706-1716 ◽  
Author(s):  
Mark Glick ◽  
Gary M. Hieftje
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Glow Discharge ◽  
Multivariate Calibration ◽  
Emission Spectra ◽  
K Nearest Neighbor ◽  
The Neural Network ◽  
Calibration Sets ◽  
Artificial Neural

Artificial neural networks were constructed for the classification of metal alloys based on their elemental constituents. Glow discharge-atomic emission spectra obtained with a photodiode array spectrometer were used in multivariate calibrations for 7 elements in 37 Ni-based alloys (different types) and 15 Fe-based alloys. Subsets of the two major classes formed calibration sets for stepwise multiple linear regression. The remaining samples were used to validate the calibration models. Reference data from the calibration sets were then pooled into a single set to train neural networks with different architectures and different training parameters. After the neural networks learned to discriminate correctly among alloy classes in the training set, their ability to classify samples in the testing set was measured. In general, the neural network approach performed slightly better than the K-nearest neighbor method, but it suffered from a hidden classification mechanism and nonunique solutions. The neural network methodology is discussed and compared with conventional sample-classification techniques, and multivariate calibration of glow discharge spectra is compared with conventional univariate calibration.

Inclusion of Multiple Cycling of the Potential into Deep Neural Network Classification of Voltammetric Reaction Mechanisms

2021 ◽  
Author(s):  
Luke Gundry ◽  
Gareth Kennedy ◽  
Alan Bond ◽  
Jie Zhang
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Reaction Mechanisms ◽  
Deep Neural Network ◽  
Deep Neural Networks ◽  
Neural Network Classification ◽  
Initial Cycle

The use of Deep Neural Networks (DNNs) for the classification of electrochemical mechanisms based on training with simulations of the initial cycle of potential have been reported. In this paper,...

scholarly journals Verbal Monomials in English for Audit and Accounting

2021 ◽  
Vol 04 (03) ◽  
Author(s):  
Oksana Chaika ◽  
Keyword(s):  
Functional Properties ◽  
Functional Property ◽  
The Other ◽  
Discussion Section ◽  
Work In Progress ◽  
The One

The paper research is work in progress and makes part of a publication set devoted the study of the English monomials and polynomials in the professional domain of audit and accounting, on the one hand. On the other, the research can be treated as a standalone piece for the study into the nature of verbal monomials as set term clusters in English for Audit and Accounting. The scope of research arrives at the following objectives. One objective is to give an overview of the term ‘monomial’ in English for Audit and Accounting, or English for A&A, which leads to understanding of the verbal monomial in English for A&A, correspondingly. The other objective refers to the classification introduced earlier as attributable to the analysis of the structure of the mentioned monomials and polynomials in English for A&A from a morphological perspective of the head term in a monomial, i.e. nounal, verbal, adjectival and adverbial. The said classification in this work associates with verbal monomials in English for A&A only, and provides a relevant sub-classification of the relevant verbal monomials through the lens of their functional properties and roles in a sentence, under the professional language framework. The results and discussion section presents five distinct groups of verbal monomials in English for Audit and Accounting, each corresponding to a specific syntactical role and functional property in a sentence. A variety of the examples helps see and identify the type of the English verbal monomial in the area of audit and accounting.

scholarly journals Statistical and Artificial Neural Networks Models for Electricity Consumption Forecasting in the Brazilian Industrial Sector

Energies ◽  
2022 ◽  
Vol 15 (2) ◽  
pp. 588
Author(s):  
Felipe Leite Coelho da Silva ◽  
Kleyton da Costa ◽  
Paulo Canas Rodrigues ◽  
Rodrigo Salas ◽  
Javier Linkolk López-Gonzales
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Statistical Approach ◽  
Electricity Consumption ◽  
Industrial Sector ◽  
Neural Network Approach ◽  
Artificial Neural ◽  
The One ◽  
Mlp Model

Forecasting the industry’s electricity consumption is essential for energy planning in a given country or region. Thus, this study aims to apply time-series forecasting models (statistical approach and artificial neural network approach) to the industrial electricity consumption in the Brazilian system. For the statistical approach, the Holt–Winters, SARIMA, Dynamic Linear Model, and TBATS (Trigonometric Box–Cox transform, ARMA errors, Trend, and Seasonal components) models were considered. For the approach of artificial neural networks, the NNAR (neural network autoregression) and MLP (multilayer perceptron) models were considered. The results indicate that the MLP model was the one that obtained the best forecasting performance for the electricity consumption of the Brazilian industry under analysis.

scholarly journals Proton drip line evaluation by complementing the Finite Range Droplet Model with neural networks

2020 ◽  
Vol 15 ◽  
pp. 258
Author(s):  
S. Athanasopoulos ◽  
E. Mavrommatis ◽  
K. A. Gernoth ◽  
J. W. Clark
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Atomic Mass ◽  
Drip Line ◽  
Finite Range ◽  
Mass Excess ◽  
Droplet Model ◽  
Mass Model ◽  
Proton Drip Line ◽  
The One

We evaluate the location of the proton drip line in the regions 31≤Z≤49 and 73≤Z≤91 based on the one- and two-proton separation energies predicted by our latest Hybrid Mass Model. The latter is constructed by complementing the mass-excess values ΔM predicted by the Finite Range Droplet Model (FRDM) of Moeller et al. with a neural network model trained to predict the differences ΔMexp − ΔMFRDM between these values and the experimental mass-excess values published in the 2003 Atomic Mass Evaluation AME03.

Sign in / Sign up

Export Citation Format

Share Document