Neural Network Logic Research Articles

Learning explanatory logical rules in non-linear domains: a neuro-symbolic approach

Deep neural networks, despite their capabilities, are constrained by the need for large-scale training data, and often fall short in generalisation and interpretability. Inductive logic programming (ILP) presents an intriguing solution with its data-efficient learning of first-order logic rules. However, ILP grapples with challenges, notably the handling of non-linearity in continuous domains. With the ascent of neuro-symbolic ILP, there’s a drive to mitigate these challenges, synergising deep learning with relational ILP models to enhance interpretability and create logical decision boundaries. In this research, we introduce a neuro-symbolic ILP framework, grounded on differentiable Neural Logic networks, tailored for non-linear rule extraction in mixed discrete-continuous spaces. Our methodology consists of a neuro-symbolic approach, emphasising the extraction of non-linear functions from mixed domain data. Our preliminary findings showcase our architecture’s capability to identify non-linear functions from continuous data, offering a new perspective in neural-symbolic research and underlining the adaptability of ILP-based frameworks for regression challenges in continuous scenarios.

Solar Fed 15 Level Cascaded Multilevel Inverter with ANFIS Control Strategy for Enhancement of Power Quality

Solar PV energy conversion systems suffer from degraded power quality issues because of harmonics in the system. In order to eliminate harmonics, this paper focuse on a solar-powered 15-level cascaded inverter. A number of controllers such as PI, Fuzzy Logic Neural Network and ANFIS are used in this study in order to manage the PWM frequency (Proportional Integral, Fuzzy Logic, NN and Adaptive Neuro Fuzzy Inference System, respectively). A PV-fed 15-level cascaded multilevel inverter for power quality improvement will be developed by using an ANFIS controller. The suggested ANFIS controller has a lower harmonic distortion than conventional controllers; hence the quality of the power improves. The PI, FL, ANN, and ANFIS controllers simulated results are analysed in MATLAB.

Bayesian logical neural networks for human-centered applications in medicine.

Background: Medicine is characterized by its inherent uncertainty, i.e., the difficulty of identifying and obtaining exact outcomes from available data. Electronic Health Records aim to improve the exactitude of health management, for instance using automatic data recording techniques or the integration of structured as well as unstructured data. However, this data is far from perfect and is usually noisy, implying that epistemic uncertainty is almost always present in all biomedical research fields. This impairs the correct use and interpretation of the data not only by health professionals but also in modeling techniques and AI models incorporated in professional recommender systems. Method: In this work, we report a novel modeling methodology combining structural explainable models, defined on Logic Neural Networks which replace conventional deep-learning methods with logical gates embedded in neural networks, and Bayesian Networks to model data uncertainties. This means, we do not account for the variability of the input data, but we train single models according to the data and deliver different Logic-Operator neural network models that could adapt to the input data, for instance, medical procedures (Therapy Keys depending on the inherent uncertainty of the observed data. Result: Thus, our model does not only aim to assist physicians in their decisions by providing accurate recommendations; it is above all a user-centered solution that informs the physician when a given recommendation, in this case, a therapy, is uncertain and must be carefully evaluated. As a result, the physician must be a professional who does not solely rely on automatic recommendations. This novel methodology was tested on a database for patients with heart insufficiency and can be the basis for future applications of recommender systems in medicine.

Intelligent Construction Optimization Control of Construction Project Schedule Based on the Fuzzy Logic Neural Network Algorithm

At present, the field of construction engineering is limited by various situations, such as complex construction environments and many uncertain factors. Therefore, on the basis of the engineering network diagram, this paper proposes a construction project schedule management method based on the fuzzy logic neural network algorithm. By building a neural network, a large amount of historical data is input, and computers are allowed to calculate the key routes, thus predicting the construction period, and a construction project in a city is taken as an example for simulation experiments. The traditional construction period management scheme expects a construction period of 55 days. The planned construction period optimized by the project management technology integrating fuzzy logic neural network algorithm is 55 days, which is 2 days less than the traditional construction project schedule management technology and will not cause construction period delay. The simulation results show that this algorithm is more accurate and more efficient in calculating the key lines when dealing with large-scale projects, which can help the construction unit to quickly find the optimal strategy and effectively reduce the construction delay and capital loss caused by uncertainty factors.

Interpretable seizure detection with signal temporal logic neural network

In this work, we develop a novel neuro-symbolic model for automated seizure detection using multi-views of data representation. Firstly, the spectral and line length features are extracted using a multi-view feature extraction technique. Next, a signal temporal logic neural network (STONE) that combines the benefits of neural networks and temporal logics is constructed to classify the seizure and nonseizure data. STONE is designed in such a way that each neuron has a symbolic representation corresponding to a component in a weighted signal temporal logic (wSTL) formula. Compared with traditional STL inference algorithms, STONE is end-to-end differentiable such that the learning can be accomplished through back-propagation. In addition, STONE improves the interpretability of seizure detection models as the outcome of STONE is a wSTL formula that is interpretable and human-readable. Importantly, the wSTL formula reveals the reasoning behind seizure as a description of the evolution of EEG signals. STONE is tested on two popular EEG databases and demonstrated to achieve promising detection performance in terms of accuracy, sensitivity, and specificity when compared with existing state-of-the-art models. Furthermore, STONE can provide a human-readable formula as a description of the seizure characteristics, and the formula is also visualizable for easy interpretation of the classifier, which is a missing property in existing seizure detection methods.

Fuzzy logic, genetic algorithms, and artificial neural networks applied to cognitive radio networks: A review

Cognitive radios are expected to play an important role in capturing the constantly growing traffic interest on remote networks. To improve the usage of the radio range, a cognitive radio hub detects the weather, evaluates the open-air qualities, and then makes certain decisions and distributes the executives’ space assets. The cognitive radio works in tandem with artificial intelligence and artificial intelligence methodologies to provide a flexible and intelligent allocation for continuous production cycles. The purpose is to provide a single source of information in the form of a survey research to enable academics better understand how artificial intelligence methodologies, such as fuzzy logics, genetic algorithms, and artificial neural networks, are used to various cognitive radio systems. The various artificial intelligence approaches used in cognitive radio engines to improve cognition capabilities in cognitive radio networks are examined in this study. Computerized reasoning approaches, such as fuzzy logic, evolutionary algorithms, and artificial neural networks, are used in the writing audit. This topic also covers cognitive radio network implementation and the typical learning challenges that arise in cognitive radio systems.

Neuro-Symbolic Inductive Logic Programming with Logical Neural Networks

Recent work on neuro-symbolic inductive logic programming has led to promising approaches that can learn explanatory rules from noisy, real-world data. While some proposals approximate logical operators with differentiable operators from fuzzy or real-valued logic that are parameter-free thus diminishing their capacity to fit the data, other approaches are only loosely based on logic making it difficult to interpret the learned ``rules". In this paper, we propose learning rules with the recently proposed logical neural networks (LNN). Compared to others, LNNs offer a strong connection to classical Boolean logic thus allowing for precise interpretation of learned rules while harboring parameters that can be trained with gradient-based optimization to effectively fit the data. We extend LNNs to induce rules in first-order logic. Our experiments on standard benchmarking tasks confirm that LNN rules are highly interpretable and can achieve comparable or higher accuracy due to their flexible parameterization.

Mathematical, fuzzy logic and artificial neural network modeling of extraction kinetics of essential oil from aerial parts of yarrow (Achillea millefolium L.) using ohmic-assisted hydrodistillation

Mathematical, fuzzy logic and artificial neural network modeling of extraction kinetics of essential oil from aerial parts of yarrow (Achillea millefolium L.) using ohmic-assisted hydrodistillation

Addressing Uncertainty by Designing an Intelligent Fuzzy System to Help Decision Support Systems for Winter Road Maintenance

One of the main challenges in developing efficient and effective winter road maintenance is to design an accurate prediction model for the road surface friction coefficient. A reliable and accurate prediction model of road surface friction coefficient can help decision support systems to significantly increase traffic safety, while saving time and cost. High dynamicity in weather and road surface conditions can lead to the presence of uncertainties in historical data extracted by sensors. To overcome this issue, this study uses an adaptive neuro-fuzzy inference system that can appropriately address uncertainty using fuzzy logic neural networks. To investigate the ability of the proposed model to predict the road surface friction coefficient, real data were measured at equal time intervals using optical sensors and road-mounted sensors. Then, the most critical features were selected based on the Pearson correlation coefficient, and the dataset was split into two independent training and test datasets. Next, the input variables were fuzzified by generating a fuzzy inference system using the fuzzy c-means clustering method. After training the model, a testing set was used to validate the trained model. The model was evaluated by means of graphical and numerical metrics. The results show that the constructed adaptive neuro-fuzzy model has an excellent ability to learn and accurately predict the road surface friction coefficient.

Unraveling the Relationship between Microstructure and Mechanical Properties of Friction Stir-Welded Copper Joints by Fuzzy Logic Neural Networks

In this study, fuzzy logic neural networks were employed to optimize the friction stir welding (FSW) process parameters in the joining of copper plates. The FSW parameters were considered as the input variables, for which micro-hardness, nano-hardness, and yield strength of the joints were the responses. The micro-hardness and nano-hardness were measured by Vickers hardness and nanoindentation tests, respectively. The microstructure and substructure of the joints were evaluated by optical, scanning electron, and orientation imaging microscopes. The optimum process parameters through which the maximum strength was achieved were the tool rotational rate of 560 rpm, tool traverse speed of 175 mm/min, and tool axial force of 2.27 kN. The low heat input joints, owing to the finer grain sizes, high density of dislocations, and larger Taylor factors, indicated greater strength relative to the high input joints. Microstructure characterization revealed that dominant strengthening mechanisms of the joints were dislocation density, texture effect, and grain boundary hardening.

Analysis of the results of using logical methods and neural networks in diagnostic tasks

The article analyzes the results of the work of neural networks and logical algorithms in the tasks of pattern recognition. Approaches to the creation of correctors that improve the results of neural network solutions are discussed. It is assumed that the data is presented in the form of objects and their characteristics, and various neural network methods can be used to process these data. However, if you examine the data by logical methods, then you can say that. neural networks provide some of the possible solutions. The solutions themselves are shown as lines of a logical function that describes the dependence of objects and their characteristics. Therefore, it is proposed to analyze and supplement these solutions. To do this, the article considers the possibility of constructing a corrector capable of constructing a logical function based on the structure of a neural network, and then implementing it in the form of logical neural networks. The construction of the corrector is carried out in two stages. At the first stage, a classifier is built in the form of disjunctions of possible solutions, and the classifier can be built only on the basis of the structure of the neural network, the data may be unknown. The second one proposes the implementation of this classifier in the form of a logical neural network. The use of such a hybrid approach can significantly affect the quality of solutions.

On a Certain Learning Algorithm for Logical Neural Networks

In this paper, we propose an algorithm for constructing variable-valued logical functions in the case of adding new production rules. The algorithm proposed serves as the basis for the method of constructive learning for logical neural networks based on variable-valued predicates.

A fuzzy logic neural network algorithm for compressor crankshaft-rolling bearing system optimization

Taking the crankshaft-rolling bearing system in a certain type of compressor as the research objective, dynamic analysis software is used to conduct detailed dynamic analysis and optimal design under the rated power of the compressor. Using Hertz mathematical formula and the analysis method of the superstatic orientation problem, the relationship expression between the bearing force and deformation of the rolling bearing is solved, and the dynamic analysis model of the elastic crankshaft-rolling bearing system is constructed in the simulation software ADAMS. The weighted average amplitude of the center of the neck between the main bearings is used as the target, and the center line of the compressor cylinder is selected as the design variable. Finally, an example analysis shows that by introducing the fuzzy logic neural network algorithm into the compressor crankshaft-rolling bearing system design, the optimal solution between the design variables and the objective function can be obtained, which is of great significance to the subsequent compressor dynamic design.

A RBF fuzzy logic neural network algorithm for construction resource scheduling

Rapid progress has been made in the intelligent technology of prefabricated buildings in recent years, and the related scheduling in many fields such as component production, workshop assembly, and road transportation is used for the optimization of resources. In this paper, the prefabricated building project is taken as the research objective to analyze the constraint conditions between prefabricated building projects in detail. It is proposed that the radial basis function (RBF) fuzzy logic neural network algorithm should be introduced into the optimization of building resource scheduling. Finally, the results of the experimental analysis suggest that the proposed method can effectively address the problem of resource scheduling in the prefabricated construction project, which can also provide a reference for the managers of prefabricated construction projects.

Fuzzy logic neural network based growth enterprise market analysis for registration-based IPO system

In real life, the stock price is always easy to be mispriced after listing, too high or too low. There are numerous reasons behind mispricing. Many scholars believe that the information asymmetry is one of them. In an inefficient market, the information asymmetry is bound to exist and be very high. In order to investigate the impact of registration-based IPO system reforms in mispricing, this paper takes the GEM market as an example to analyze the impact of the GEM market on mispricing. And we proposed a method with fuzzy logic neural network for Growth Enterprise Market analysis for IPO system. After processing data, we use ARIMA and EGARCH model to find the results. The immaturity will result in the negative impact caused by reformation, which will deviate from the goal that makes Chinese stock market become better.

Applicability of Fuzzy Logic and Artificial Neural Network for Unpaved Airfield Surface Bearing Strength Prediction.

The main objective of this paper is to describe a building process of a model predicting the soil strength at unpaved airport surfaces (unpaved runways, safety areas in runway proximity, runway strips, and runway end safety areas). The reason for building this model is to partially substitute frequent and meticulous inspections of an airport movement area comprising the bearing strength evaluation and provide an efficient tool to organize surface maintenance. Since the process of building such a model is complex for a physical model, it is anticipated that it might be addressed by a statistical model instead. Therefore, fuzzy logic (FL) and artificial neural network (ANN) capabilities are investigated and compared with linear regression function (LRF). Large data sets comprising the bearing strength and meteorological characteristics are applied to train the likely model variations to be subsequently compared with the application of standard statistical quantitative parameters. All the models prove that the inclusion of antecedent soil strength as an additional model input has an immense impact on the increase in model accuracy. Although the M7 model out of the ANN group displays the best performance, the M3 model is considered for practical implications being less complicated and having fewer inputs. In general, both the ANN and FL models outperform the LRF models well in all the categories. The FL models perform almost equally as well as the ANN but with slightly decreased accuracy.

A Review of Fuzzy Logic and Artificial Neural Network Technologies Used for MPPT

Solar electric power generating stations play a major role in meeting the growing demand for electric power. These generating stations make use of solar photovoltaic (PV) panels to perform the conversion of solar energy to electric energy. However, the solar panel output is highly unpredictable because the output is a function of number of factors; some of which are not in the control of humans like the weather conditions, and the output is also a function of the age of PV panel, dust and other debris collected on the panel, direction and angle of elevation and so on. The solar panels exhibit a low efficiency. Currently, a lot of research is going on to overcome these issues. This paper represents a review of two modern techniques used in solar photovoltaic systems which enhance the extraction of maximum output power in an efficient manner. The Artificial Intelligence Based MPPT Techniques for PV Applications, and, a Forecasting System of Solar PV Power Generation using Wavelet Decomposition and Bias- compensated Random Forest are reviewed and compared in this paper.

The Method of Construction of Logical Neural Networks on the Basis of Variable-Valued Logical Functions

In this paper, we suggest a method of constructing logical neural networks on the basis of variable-valued logical functions. We prove the theorem on a possibility of representation of any logical function as a logical neural network. The proof given in the paper contains an algorithm of the construction of the logical neural network. We point out the possibility of the generalization of the result obtained to the case of fuzzy logic.

A study of Comparative analysis of fuzzy logic controller and neural network for dc–dc buck converter

This paper presents the comparative analysis between fuzzy logic controller and neural network for DC-DC Buck converter. The major drawback in the conventional buck converter is when the input voltage or load change, the output voltage also changes which reduces the overall efficiency of the buck converter. So here we are using non linear controllers for buck converter which respond quickly for perturbations and maintains the fixed load voltage even when there are non-linearity’s occurs compared to a linear controllers like P,PI,PID controllers which can’t withstand when perturbations occur. Simplicity, low cost and adaptability to the complex systems without mathematical modeling are the best features of Fuzzy Logic controller and neural networks. The Two implementations are analyzed in detail and simulated in MATLAB/SIMULINK environment and results presented. Proposed approach is implemented on DC to DC step down converter for an input of 230V and performance characteristics like maximum overshoot, settling time and efficiency of the converter are studied.

The Estimation of the Critical Flashover Voltage of Insulators Using the Computational Intelligence

Background: Electric insulation is generally a vital factor in both the technical and economic feasibility of complex power and electronic systems. Several researches focus on the behavior of insulators under polluted conditions. That they are mathematical and physical models of insulators, experiments and simulation programs. Also experiments on critical flashover voltage are timeconsuming and have more limitations such as high cost and need for especial equipment’s. Objective: This paper focused on optimized predicting of critical flashover voltage of Polluted insulators based on artificial intelligence. Methods: Fuzzy logic and artificial neural networks are used in order to have the best estimation of the critical flashover. Results: In this way the correlation index (regression coefficient) improved about 2% toward previous works with same experimental data sets. Additionally, with using the properties of nonlinear artificial neural networks we can have the perfect (R=100%) prediction of the critical flashover voltage on experimental dataset. Conclusion: In this paper two methods for the estimation of critical flashover voltage of polluted insulators using fuzzy logic and neural networks was presented. the regression coefficient R achieved by the optimal parameters is 98.4% while in previous work is 96.7%. In neural network model we have regression coefficient 100% and in previous neural network model it was 99%. our test set is the same as previous works and achieved from experiments. These results show that fuzzy proposed methods are powerful and useful tools lead to a more accurate, generalized and objective estimation of the critical flashover voltage.