Neuro Model Research Articles

An adept approach to ascertain and elude probable social bots attacks on twitter and twitch employing machine learning approach

There has been a tremendous increase in the popularity of social media such as blogs, Instagram, twitter, online websites etc. The increasing utilization of these platforms have enabled the users to share information on a regular basis and also publicize social events. Nevertheless, most of the multimedia events are filled with social bots which raise concerns on the authenticity of the information shared in these events. With the increasing advancements of social bots, the complexity of detecting and fact-checking is also increasing. This is mainly due to the similarity between authorized users and social bots. Several researchers have introduced different models for detecting social bots and fact checking. However, these models suffer from various challenges. In most of the cases, these bots become indistinguishable from existing users and it is challenging to extract relevant attributes of the bots. In addition, it is also challenging to collect large scale data and label them for training the bot detection models. The performance of existing traditional classifiers used for bot detection processes is not satisfactory. This paper presents:•A machine learning based adaptive fuzzy neuro model integrated with a hist gradient boosting (HGB) classifier for identifying the persisting pattern of social bots for fake news detection.•And Harris Hawk optimization with Bi-LSTM for social bot prediction.•Results validate the efficacy of the HGB classifier which achieves a phenomenal accuracy of 95.64 % for twitter bot and 98.98 % for twitch bot dataset.

Design of Resources Allocation in 6G Cybertwin Technology Using the Fuzzy Neuro Model in Healthcare Systems.

In 6G edge communication networks, the machine learning models play a major role in enabling intelligent decision-making in case of optimal resource allocation in case of the healthcare system. However, it causes a bottleneck, in the form of sophisticated memory calculations, between the hidden layers and the cost of communication between the edge devices/edge nodes and the cloud centres, while transmitting the data from the healthcare management system to the cloud centre via edge nodes. In order to reduce these hurdles, it is important to share workloads to further eliminate the problems related to complicated memory calculations and transmission costs. The effort aims mainly to reduce storage costs and cloud computing associated with neural networks as the complexity of the computations increases with increasing numbers of hidden layers. This study modifies federated teaching to function with distributed assignment resource settings as a distributed deep learning model. It improves the capacity to learn from the data and assigns an ideal workload depending on the limited available resources, slow network connection, and more edge devices. Current network status can be sent to the cloud centre by the edge devices and edge nodes autonomously using cybertwin, meaning that local data are often updated to calculate global data. The simulation shows how effective resource management and allocation is better than standard approaches. It is seen from the results that the proposed method achieves higher resource utilization and success rate than existing methods. Index Terms are fuzzy, healthcare, bioinformatics, 6G wireless communication, cybertwin, machine learning, neural network, and edge.

The Feasibility of Three Prediction Techniques of the Artificial Neural Network, Adaptive Neuro-Fuzzy Inference System, and Hybrid Particle Swarm Optimization for Assessing the Safety Factor of Cohesive Slopes

In this paper, a neuro particle-based optimization of the artificial neural network (ANN) is investigated for slope stability calculation. The results are also compared to another artificial intelligence technique of a conventional ANN and adaptive neuro-fuzzy inference system (ANFIS) training solutions. The database used with 504 training datasets (e.g., a range of 80%) and testing dataset consists of 126 items (e.g., 20% of the whole dataset). Moreover, variables of the ANN method (for example, nodes number for each hidden layer) and the algorithm of PSO-like swarm size and inertia weight are improved by utilizing a total of 28 (i.e., for the PSO-ANN) trial and error approaches. The key properties were fed as input, which were utilized via the analysis of OptumG2 finite element modelling (FEM), containing undrained cohesion stability of the baseline soil (Cu), angle of the original slope (β), and setback distance ratio (b/B) where the target is selected factor of safety. The estimated data for datasets of ANN, ANFIS, and PSO-ANN models were examined based on three determined statistical indexes. Namely, root mean square error (RMSE) and the coefficient of determination (R2). After accomplishing the analysis of sensitivity, considering 72 trials and errors of the neurons number, the optimized architecture of 4 × 6 × 1 was determined to the structure of the ANN model. As an outcome, the employed methods presented excellent efficiency, but based on the ranking method, the PSO-ANN approach might have slightly better efficiency in comparison to the algorithms of ANN and ANFIS. According to statistics, for the proper structure of PSO-ANN, the indexes of R2 and RMSE values of 0.9996, and 0.0123, as well as 0.9994 and 0.0157, were calculated for the training and testing networks. Nevertheless, having the ANN model with six neurons for each hidden layer was formulized for further practical use. This study demonstrates the efficiency of the proposed neuro model of PSO-ANN in estimating the factor of safety compared to other conventional techniques.

Neuromorphic Vision Datasets for Pedestrian Detection, Action Recognition, and Fall Detection.

Neuromorphic Vision Datasets for Pedestrian Detection, Action Recognition, and Fall Detection.

Neuro Model for Passive Suspension of a Light Car

The system model is neccessery to be determined in control systems engineering which is generally represented in mathematical form. The mathematical model can be utilized for analysing the system’s characteristics or designing the controller parameters of the system. Here, a neuro model for passive suspension system of a light car is proposed. The candidate structure of the neuro model is contructed from non-linear system of passive suspension of a quarter car mathematical model. Weights estimation of neuro model is conducted by applying iterative weighted least square algorithm. Actual input output data of a test car for training process are acquired by driving the test vehicle on an artificial surface of road. An artificial surface of road is a kind of real road surface imitation. Experimental findings show that the proposed model is able to imitate sucessfully the dynamic properties of the passive suspension system of the light car. The model response shows similar trend and has smallest error.

Ensemble Genetic Fuzzy Neuro Model Applied for the Emergency Medical Service via Unbalanced Data Evaluation

Equally partitioned data are essential for prediction. However, in some important cases, the data distribution is severely unbalanced. In this study, several algorithms are utilized to maximize the learning accuracy when dealing with a highly unbalanced dataset. A linguistic algorithm is applied to evaluate the input and output relationship, namely Fuzzy c-Means (FCM), which is applied as a clustering algorithm for the majority class to balance the minority class data from about 3 million cases. Each cluster is used to train several artificial neural network (ANN) models. Different techniques are applied to generate an ensemble genetic fuzzy neuro model (EGFNM) in order to select the models. The first ensemble technique, the intra-cluster EGFNM, works by evaluating the best combination from all the models generated by each cluster. Another ensemble technique is the inter-cluster model EGFNM, which is based on selecting the best model from each cluster. The accuracy of these techniques is evaluated using the receiver operating characteristic (ROC) via its area under the curve (AUC). Results show that the AUC of the unbalanced data is 0.67974. The random cluster and best ANN single model have AUCs of 0.7177 and 0.72806, respectively. For the ensemble evaluations, the intra-cluster and the inter-cluster EGFNMs produce 0.7293 and 0.73038, respectively. In conclusion, this study achieved improved results by performing the EGFNM method compared with the unbalanced training. This study concludes that selecting several best models will produce a better result compared with all models combined.

GIS-Based Rainfall-Runoff Neuro Model for Streamflow Prediction

TOPMODEL is a semi-distributed rainfall runoff model that has been widely used in numerous water resources’ applications in the last few decades. However, literature has identified the weakness in the TOPMODEL performances in streamflow prediction. In this paper, a multilayer perceptron neural network (MLP-NN) has been adopted to improve the accuracy of streamflow prediction in a flash flood in Pinang catchment area. Two daily hydro-meteorological datasets of year 2007-2008 and 2009-2010 were used for calibration and validation periods, respectively. The new method presented in this study uses the TOPMODEL input-output datasets during the calibration period to train the MLP-NN to predict the output. Then, the trained MLP-NN model structure is used to predict the streamflow based on validation period datasets. The three efficiencies considered to evaluate the model performances are the Nash-Sutcliffe model (NS), the Relative Volume Error (RVE) and the Correlation Coefficient (CoC). The results indicated an improvement from 0.749, -19.2 and 0.893 of NS, RVE and CoC of the calibration period to 0.978, 0.364 and 0.989, respectively. Moreover, for the validation periods, the performance has been improved from 0.774, -19.84 and 0.933 of NS, RVE and CoC to 0.975, -0.029 and 0.789, respectively. The ability of MLP-NN to improve TOPMODEL daily streamflow prediction has been demonstrated in this study.

A model of flow separation controlled by dielectric barrier discharge

Flow separation, asan aerodynamic phenomenon, occurs in specific conditions. The conditions are studied in a wind tunnel on different airfoils. The phenomenon can be delayed or suppressed by exerting an external momentum to the flow. Dielectric barrier discharge actuators arranged in a row of 8 and perpendicular to the flow direction can delay flow separation by exerting the momentum. In this study, a mathematical model is developed to predict a parameter, which is utilized to represent flow separation on an NACA0012 airfoil. The model is based on the neuro-fuzzy method applied to experimental datasets. The neuro model is trained in different flow conditions and the parameter is measured by pressure sensors.

Application of fuzzy – Neuro to model weather parameter variability impacts on electrical load based on long-term forecasting

Long-term load forecasting provides vital information about future load and it helps the power industries to make decision regarding electrical energy generation and delivery. In this work, fuzzy – neuro model is developed to forecast a year ahead load in relation to weather parameter (temperature and humidity) in Mubi, Adamawa State. It is observed that: electrical load increased with increase in temperature and relative humidity does not show notable effect on electrical load. The accuracy of the prediction is obtained at 98.78% with the corresponding mean absolute percentage error (MAPE) of 1.22%. This confirms that fuzzy – neuro is a good tool for load forecasting.

Neuro Model Approach for a Quarter Car Passive Suspension Systems

The road handling, load carrying and passenger comfort are three intension factors on car suspension’s system. They should be compromised to achieve the good the car suspension dynamics. To fulfill the requirement, the car suspension system must be controlled and analyzed. To design and analyze the suspension controller, the realistic dynamics model of car suspension is needed. In this paper, the car suspension is assumed as a quarter car and has a model structure as a neural network structure. The model is assumed consist of nonlinear properties that are contributed by spring stiffness and damping elements of suspension system. The tire is assumed has linear properties and represented by spring stiffness element and damping element. The model responses are generated in simulation term. The random type of artificial road surface signal as an input variable is used in this simulation. The results show that the trend of neuro model have the same with the response of a quarter car nonlinear model from dynamic derivation. It means that the developed neuro model structure capable to represent the nonlinear model of a quarter car passive suspension system dynamics.

Optimization of nonlinear characteristics of ball burnishing process using Sugeno fuzzy neural system

Aluminium alloy (Al 63400) is burnished using different burnishing parameters. It deals with the modelling of nonlinear characteristics of ball burnishing using Sugeno fuzzy neural system. A fuzzy neural network or neuro-fuzzy system is a learning machine that finds the parameters of the fuzzy systems (i.e. fuzzy sets, fuzzy rules) by exploiting approximation techniques from neural networks. Input parameters are designed for experimental process using Box–Behnken method. Ball burnishing tool is used in CNC machining centre to surface finish the milling process. The tool and work-piece material are tungsten carbide and aluminium, respectively. The input parameters are force, table feed, step over, ball diameter and number of passes. The output parameters are surface roughness along feed direction, surface roughness across feed direction and surface micro-hardness. The minimum surface roughness obtained for ball burnishing process along the tool path (x-axis) is 0.032 μm and across the tool path (y-axis) is 0.232 μm and its micro-hardness is 91.63 HV. Sugeno fuzzy neuro system is used to model the nonlinear characteristics of the surface roughness (along the tool path and across the tool path) and micro-hardness. The Pearson product moment correlation is used to validate the fuzzy neuro model.

A Rough - Neuro Model for Classifying Opponent Behavior in Real Time Strategy Games

Real Time strategy games offer an environment where game AI is known to conduct actuality. One feature of realistic behavior in game AI is the ability to recognize the strategy of the opponent player. This is known as opponent modeling. In this paper, aclassification Rough-Neuro hybrid model of the RTS opponent player behavior process is proposed. As a mean to achieve better game performance, reduction of the agent decision space andbetter high-level winning of real-time strategy games. The Rough -Neuro methodology allows the classification model to some extent simulate opponent behavior in playing RTS games. The methodology incorporates a two -stage hybrid mechanism. Rough sets for reduction of relevant attributes and artificial neural networks forclassification opponent behavior during game playing. The proposed hybrid approach has been tested on an open source 3D RTS game called Glest. From our results we can deduce that the tactic may be successfully used for foretelling the demeanor of contender in the Glest game.

Model Predictive Control of Nonlinear Distributed Parameter Systems Using Spatial Neural-Network Architectures

In this paper the distributed parameter systems comprise first-order partial differential equations coupled with ordinary differential equations. Through time and space discretization the explicit formulation of finite-difference model is constructed. Under effects of unknown disturbances and parameter uncertainties, an online learning algorithm, by virtue of the minimal output error between the system and neuro model, is developed. If only a few output measurements are available, the spatial feedforward neural-network architecture is integrated into the nondistributed predictive control framework. The stability analysis of the closed-loop control system is addressed through the discrete-time Lyapunov function approach. Two examples including a bioreactor system governed by the population balance equation and the nonisothermal tubular reactor system are used to verify the effectiveness of the proposed method.

NEURO BASED MODEL REFERENCE ADAPTIVE CONTROL OF A CONICAL TANK LEVEL PROCESS

This paper deals with the adaptive control of a continuous time nonlinear system of conical tank level process using neural networks. An adaptive system based on MRAC technique is proposed and proved to be useful in adjusting the trained parameter of the neural network for approximating the non-linearity of the dynamical system and for the process parameter variations. A neuro model is also developed for this purpose. The weight adaptive laws are developed using an adaptive neural network. The tracking error, which is the difference between the neuro model and the plant output, converge to the required accuracy through the adaptive control algorithm derived by combining the inverse neural network and adaptive neural network. A lab scale experimental setup for the conical tank level process was fabricated. Experimental studies were carried out for conventional control, fuzzy control, neuro control, and adaptive neuro control. The performances of all the above schemes were investigated. The advantages of the proposed scheme, over other methods, were highlighted.

Neural Predictive Control Design for Uncertain Nonlinear Systems

In this paper, adaptive neural-network predictive control strategies for general nonlinear systems are presented. The system is described by an unknown NARMAX model and neuro model is used to on-line learn the system. Despite state/parameter estimation, the neural predictive control scheme associated with the constrained optimization framework is implemented in a straightforward manner. Through the Lyapunov stability analysis, the network weight adaptation rule is derived, and guarantees the minimum error between the neuro output and plant output. An unstable reactor system is given to demonstrate the effectiveness of the proposed control schemes.

Fault diagnosis for unknown non-linear systems via neural networks and its comparisons and combinations with recursive least-squares based techniques

In this paper, an algorithm for the detection and diagnosis of faults in sensors and actuators in unknown non-linear systems is presented. Firstly, the normal operation of the non-linear system is modelled via a feedforward neural network in order to produce a healthy model which is used later as a redundant relation. It is assumed that every faulty sensor or actuator can be modelled by a single parameter f. Such a parameter is defined to be f=1 when the system is healthy and 0 < f < 1 otherwise. A residual signal is evaluated from the difference of the output of the healthy model and that of the system. A simple threshold function is used to detect the faulty behaviour of the system. The estimation of f is then computed by minimizing the differences between the output of the system and that of the healthy neuro model with the help of the gradient descent rule. It has been shown that the algorithm is able to estimate the fault with large magnitude accurately. However, if the deviation of f from its healthy value is small, a linearized healthy model, together with the recursive least-squares algorithm, can be used to estimate the fault. As a result, a combination of both methods will provide a powerful technique for accurate fault diagnosis.

Neural hybrid control of manipulators, stability analysis

The design and implementation of adaptive control for nonlinear unknown systems is extremely difficult. The nonlinear adaptive control for assembly robots performing a peg-in-hole insertion is one such an example. The recently intensively studied neural networks brings a new stage in the development of adaptive control, particularly for unknown nonlinear systems. The aim of this paper is to propose a new approach of hybrid force position control of an assembly robot based on artificial neural networks systems. An appropriate neural network is used to model the plant and is updated online. An artificial neural network controller is then directly evaluated using the updated neuro model. Two control structures are proposed and the stability analysis of the closed-loop system is investigated using the Lyapunov method. Experimental results demonstrate that the identification and control schemes suggested in this paper are efficient in practice.

Integration of Linear Systems and Neural Networks for Identification and Output Feedback Control of Nonlinear Systems

Abstract This paper analyzes the integration of linear systems and neural networks for the identification, state estimation and output feedback control of weakly nonlinear systems. Considering previous knowledge about the system given by approximated linear state-space models, linear observers and linear controllers; training algorithms for neuro-identification, state neuroestimation and neuro-control were derived considering the dynamics of the nonlinear system. It was found that the integrated linear-neuro model can identify the dynamics of the system much more accurately than a purely linear model or a purely neuro model. It was also found that the state estimation and control performance of the system with integrated linear-neuro output feedback control is better than the system with linear control or neuro-control.

An alternative for neuroendoscopic hands-on: the pig modeI. Technical note

Summary Technical advances are rapidly being introduced in neurosurgical practice. Besides the changes in therapeutical options, the question of special training and quality assurance is of extreme importance if the «less invasive» alternatives are to replace the more standard microsurgical interventions. We have introduced a live neuro model for neuroendoscopic training taking into consideration the anatomical similarity of the human and pig brain. The possibility of having biological feedback and observing the functional repercussions caused by our manipulations is superior for training fellow neurosurgeons than just the standard cadaver and dummy options available till now. We consider that a live animal tissue model should be introduced in the training program before performing neuroendoscopic procedures in the clinical setting. Our model is presented and a video band is available to demostrate aspects of the procedure.

Actuator fault diagnosis for nonlinear dynamic systems

In this paper a novel approach for the fault detection and diagnosis of the actuators in nonlinear systems is presented. The faults are assumed to be any unexpected changes of the parameters in the actuators, which include either abrupt changes or slowly drifting changes. Firstly a known nonlinear system is considered, where an adaptive diagnostic model incorporating the estimate of fault is constructed. The diagnostic algorithm is then developed which produces the estimate of the fault so that the error between the system output and that of the model is minimised. Unknown nonlinear systems are then studied using a feedforward neural network trained to estimate the system under healthy conditions. Taking the trained neural network as the neuro model of the system, similar detection and diagnostic algorithms to that of known systems are obtained which are still capable of producing a good estimate for the fault. The method is demonstrated using a simulated nonlinear system and good results are obtained.