Artificial Neural Network Fusion Research Articles

Application of Physics-Informed Neural Networks to River Silting Simulation

Water resource pollution, particularly in river channels, presents a grave environmental challenge that necessitates a comprehensive and systematic approach encompassing assessment, forecasting, and effective management. This article provides a comprehensive exploration of the methodology and modeling tools employed to scrutinize the process of river channel pollution due to silting, rooted in the fundamental principles of hydrodynamics and pollutant transport dynamics. The study’s methodology seamlessly integrates numerical simulations with state-of-the-art neural network techniques, with a specific focus on the physics-informed neural network (PINN) method. This innovative approach represents a groundbreaking fusion of artificial neural networks (ANNs) and physical equations, offering a more efficient and precise means of modeling a wide array of complex processes and phenomena. The proposed mathematical model, grounded in the Euler equation, has been meticulously implemented using the Ansys Fluent software package, ensuring accuracy and reliability in the computations. In a pivotal phase of the research, a thorough comparative analysis was conducted between the results derived using the PINN method and those obtained using conventional numerical approaches with the Ansys Fluent software package. The outcomes of this analysis revealed the superior performance of the PINN method, characterized by the generation of smoother pressure fluctuation profiles and a significantly reduced computation time, underscoring its potential as a transformative modeling tool. The calculated data originating from this study assume paramount significance in the ongoing battle against river sedimentation. Beyond this immediate application, these findings also serve as a valuable resource for creating predictive materials pertaining to river channel silting, thereby empowering decision-makers and environmental stakeholders with essential information. The utilization of modeling techniques to address pollution concerns in river channels holds the potential to revolutionize risk management and safeguard the integrity of our vital water resources. However, it is imperative to underscore that the effectiveness of such models hinges on ongoing monitoring and frequent data updates, ensuring that they remain aligned with real-world conditions. This research not only contributes to the enhanced understanding and proactive management of river channel pollution due to silting but also underscores the pivotal role of advanced modeling methodologies in the preservation of our invaluable water resources for present and future generations.

Neuro-Fuzzy Networks and Their Applications in Medical Fields.

The fusion of artificial neural networks and fuzzy logic systems allows researchers to model real-world problems through the development of intelligent and adaptive systems. Artificial neural networks are able to adapt and learn by adjusting the interconnections between layers, while fuzzy logic inference systems provide a computing framework based on the concept of fuzzy set theory, fuzzy if-then rules, and fuzzy reasoning. The combined use of those adaptive structures is known as "neuro-fuzzy" systems. In this paper, the basic elements of both approaches are analyzed, noticing that this blending could be applied for pattern recognition in medical applications.

Semisupervised Two-Level Fusion-Based Autoencoded Approach for Low-Cost Domain Adaptation of Remotely Sensed Images

In this letter, a low-cost semisupervised domain adaptation technique has been proposed using a two-level fusion of artificial neural networks. The proposed technique has been aimed to solve the problem of sample selection bias using a one-time collection of a few patterns from the target domain under semisupervised framework. To assess the effectiveness, experiments are conducted on the two source–target data sets acquired over India. The results are found to be encouraging.

Fusion of Artificial Intelligence in Neuro-Rehabilitation Video Games

In this paper, an intuitive neuro-rehabilitation video game has been developed employing the fusion of artificial neural networks (ANNs), inverse kinematics (IK), and fuzzy logic (FL) algorithms. The embedded algorithms automatically adjust the game difficulty level based on the player’s interaction with the game. Moreover, it is manifested as an alternative approach for possible movements to improve incorrect positioning through real-time visual feedback on the screen; 52 participants volunteered to engage in the program. Motor assessment scale (MAS) was determined to assess the participants’ functional ability pre- and post-treatments. The system input is received via the Microsoft Kinect, a foot Pedal (Saitek), and the Thalmic Myo armband. The ANN classifier integrates the limb joints orientation, angular velocity, lower arms’ muscle activity, hand gestures, feet sole (plantar) pressure parameters, and the MAS scores to learn from data and predict the improvement following the intervention. The fuzzy input generates a crisp output and provides a personalized rehabilitation program with the potential to be integrated into clinical protocols. Experiments to obtain the input signals and desired outputs were conducted for the learning and validation of the network. The networks pattern recognition, self-organizing map, and non-linear auto-regression analysis performed using feed-forward and Levenberg–Marquardt backpropagation (LMBP) procedure. The results showed the effectiveness of the non-linear auto-regression using the optimized LMBP algorithm to classify and visualize the target categories. Furthermore, the state of the network demonstrates the prediction accuracy exceeding 94%. Clustering algorithm grouped the data based on the similarity. Self-organizing map trained the network to learn the topology of samples with high correlation, presented outputs with high achievement.

A Fast Learning Control Strategy for Unmanned Aerial Manipulators

We present an artificial intelligence-based control approach, the fusion of artificial neural networks and type-2 fuzzy logic controllers, namely type-2 fuzzy-neural networks, for the outer adaptive position controller of unmanned aerial manipulators. The performance comparison of proportional-derivative (PD) controller working alone and the proposed intelligent control structures working in parallel with a PD controller is presented. The simulation and real-time results show that the proposed online adaptation laws eliminate the need for precise tuning of conventional controllers by learning system dynamics and disturbances online. The proposed approach is also computationally inexpensive due to the implementation of the fast sliding mode control theory-based learning algorithm which does not require matrix inversions or partial derivatives. Both simulation and experimental results have shown that the proposed artificial intelligence-based learning controller is capable of reducing the root-mean-square error by around 50% over conventional PD and PID controllers.

Neural networks fusion for temperature forecasting

Weather conditions have a direct relationship with energy consumption, touristic activities, and farm tasks. By means of the fusion of artificial neural networks, this work presents a system with a general method that obtains an accurate temperature prediction. The objective is temperature, but the method is easily scalable to obtain any other meteorological parameter; this is one strength of the model. This research carries out a temperature prediction modeling that contributes to obtain better results with different applications as energy generation or in other different fields such as tourism or farming. The database contains data of 5 years from stations located in Gran Canaria at Gran Canaria Airport and in Tenerife at Tenerife Sur Airport. Data are collected hourly, what means more than 100,000 samples. This quantity of samples gives sturdiness to the study. With this method, our best result in terms of mean absolute error and using data from meteorological stations in Canary Islands is 0.41 °C.

Fusion of artificial neural networks for learning capability enhancement: Application to medical image classification

AbstractArtificial neural network (ANN) is one of the commonly used tools for computational applications. The specific advantages of ANN are high accuracy, less convergence time, less computational complexity, and so forth. However, all these merits are not available in the same ANN. Even though back propagation neural (BPN) networks are accurate, their computational complexity is significantly high. BPN networks are also not stable. On the other hand, Hopfield neural network (HNN) is better than BPN in terms of computational efficiency. But the accuracy of HNN is low. In this work, a modified ANN is proposed to overcome this specific problem. The modified ANN is a fusion of BPN and HNN. The technical concepts of BPN and HNN are mixed in the training algorithm of the proposed back propagation‐Hopfield network (BPHN). The objective of this fusion is to improve the performance of conventional ANN. Magnetic resonance brain image classification experiments are used to analyse the proposed BPHN. Experimental results have suggested improvement in the learning process of the proposed BPHN. A comparative analysis with the conventional networks is performed to validate the performance of the proposed approach.

EVALUATION OF STUDENT ACADEMIC PERFORMANCE USING ADAPTIVE NEURO-FUZZY APPROACH

The Fusion of Artificial Neural Networks (ANN) and Fuzzy Inference System (FIS) has attracted a growing interest of researchers in various scientific and engineering areas. Due to the growing need for adaptive intelligent systems to solve real world problems. ANN learns by adjusting the interconnections between layers. FIS is a popular computing framework based on the concept of fuzzy set theory and fuzzy if-then rules. The advantages of the combination of ANN and FIS are apparent. The developed method uses a fuzzy system to support neural networks to enhance some of its characteristics like flexibility, speed and adaptability which is called the Adaptive Neuro-fuzzy inference system (ANFIS). Evaluating and assessing the student academic performance is not an easy task, especially when it involves many attributes or factors. Moreover, the knowledge of the human experts is acquired to determine the criteria of students’ academic performance and the decisions about their level of assimilation but most of the information is incomplete and vague. To overcome the problem, this work evaluates the student’s academic performance based on ANFIS tools which was implemented on MATLAB 7.6.0 (R2008a). The method produces crisp numerical outcomes that evaluate the student’s academic performance. The student performance after the training of the two inputs was at the average for semester1 and semester 2. Â

Fusion of artificial neural network and fuzzy system for short term weather forecasting

Weather forecasting is the challenging problem for the modern life. Some researches have been conducted to design the accurate prediction in some past years but still it is incomplete. In this paper, we propose the system of short period weather forecasting designed based on the current weather parameter consisted of temperature, humidity, air pressure, wind direction and speed and present weather condition. This system uses fusion of feed forward artificial neural network (ANN) and fuzzy system architecture as main algorithm of weather prediction, Lavendberg-Marquadt as learning algorithm and fuzzy C-mean (FCM) as clustering method in initialisation step. Based on the system architecture, this method can predict the weather continuously despite the change of unpredictable patterns. Furthermore, this system has clear reasoning logic on the fuzzy logic instead of its adaptation ability on its neural network architecture. The performance of proposed system has accuracy up to 78% for validity among three possible weathers, i.e., shiny, cloudy and rainy.

Fusion of learning automata theory and granular inference systems: ANLAGIS. Applications to pattern recognition and machine learning

In this paper the fusion of artificial neural networks, granular computing and learning automata theory is proposed and we present as a final result ANLAGIS, an adaptive neuron-like network based on learning automata and granular inference systems. ANLAGIS can be applied to both pattern recognition and learning control problems. Another interesting contribution of this paper is the distinction between pre-synaptic and post-synaptic learning in artificial neural networks. To illustrate the capabilities of ANLAGIS some experiments on knowledge discovery in data mining and machine learning are presented. The main, novel contribution of ANLAGIS is the incorporation of Learning Automata Theory within its structure; the paper includes also a novel learning scheme for stochastic learning automata.

A Study of Neuro-fuzzy System in Approximation-based Problems

The Fusion of Artificial Neural Networks (ANN) and Fuzzy Inference System (FIS) has attracted a growing interest of researchers in various scientific and engineering areas due to the growing need for adaptive intelligent systems to solve real world problems. ANN learns by adjusting the interconnections between layers. FIS is a popular computing framework based on the concept of fuzzy set theory and fuzzy if-then rules. The advantages of the combination of ANN and FIS are apparent. This paper implements a hybrid neuro-fuzzy system underlying ANFIS (Adaptive Neuro Fuzzy Inference System), a fuzzy inference system implemented in the framework of neural networks. The motivation stems from a desire to achieve performance in terms of accuracy and several simulations studies regarding the determination of the optimal number of membership functions have been done. In our simulations, we utilize the ANFIS architecture to model nonlinear functions. In addition, the effects of using different types of membership functions were compared. Based upon numerical evidence, some general guidelines for choosing the number of membership function have been proposed. To experiment with the technique that allows the combination of neural network and fuzzy system, we have implemented ANFIS to a real world application (Phytoplankton concentration problem); and yielding good results. Keywords: ANFIS; Neuro-fuzzy system; membership function; function approxima-tion.

Fusion of artificial neural networks and genetic algorithms for multi-objective system reliability design optimization

In this work, artificial neural networks (ANNs) are used to include the decision-maker's preference structure within a genetic algorithm (GA) search of the optimal system reliability configuration. For verification, the proposed approach is applied to two literature case studies of increasing complexity concerning the optimization of the reliability design of a series system.

A neuro‐fuzzy theoretic approach to safety control at crude oil exploration platforms

PurposeThe purpose of this paper is to present a new approach in viewing the control of safety at crude oil exploration platforms.Design/methodology/approachThe approach utilized in this work is the fusion of artificial neural network and fuzzy logic. The approach is adopted in view of the better presentation of solutions to the safety control problem that neuro‐fuzzy exhibits. It is better than the individual application of either artificial neural network or fuzz logic to the problem at hand. The model captures uncertainties and imprecision that are prevalent in the quantification or data gathering stage of safety control measurement.FindingsIt was demonstrated that the application of neuro‐fuzzy is feasible. The results seem applicable to similar settings with similar system characteristics.Practical implicationsSince more confidence is obtained with the use of this more effective tool, there is improvement in decision making based on reliance on the model. Thus, the improved quality of decision made would positively affect lives of workers at the oil platforms or the materials or equipment used for exploration purposes.Originality/valueThe work is original in that it is the first time the neuro‐fuzzy methodology would be applied to offshore oil platform safety control.

An Efficient Method for Selecting the Optimal Structure of a Fuzzy Neural Network Architecture

The fusion of artificial neural networks with soft computing enables to construct learning machines that are superior compared to classical artificial neural networks, because knowledge can be extracted and explained in the form of simple rules. An efficient method for selecting the optimal structure of a fuzzy neural network architecture is developed. The Vapnik Chervonenkis (VC) dimension is introduced as a measure of the capacity of the learning machine. A prediction of the expected error on the yet unseen examples is estimated with the help of the VC dimension. The structural risk minimization principle is introduced for constructing the optimal architecture with the lowest expected error for the small data sets. A comparison between fuzzy neural network and the neural network ARX model is presented.