Dynamic Neural Network Approach Research Articles

Jointly Optimizing Terahertz Based Sensing and Communications in Vehicular Networks: A Dynamic Graph Neural Network Approach

Jointly Optimizing Terahertz Based Sensing and Communications in Vehicular Networks: A Dynamic Graph Neural Network Approach

A Time-Series-Based Sample Amplification Model for Data Stream with Sparse Samples

The data stream is a dynamic collection of data that changes over time, and predicting the data class can be challenging due to sparse samples, complex interdependent characteristics between data, and random fluctuations. Accurately predicting the data stream in sparse data can create complex challenges. Due to its incremental learning nature, the neural networks suitable approach for streaming visualization. However, the high computational cost limits their applicability to high-speed streams, which has not yet been fully explored in the existing approaches. To solve these problems, this paper proposes an end-to-end dynamic separation neural network (DSN) approach based on the characteristics of data stream fluctuations, which expands the static sample at a given moment into a sequence of sample streams in the time dimension, thereby increasing the sparse samples. The Temporal Augmentation Module (TAM) can overcome these challenges by modifying the sparse data stream and reducing time complexity. Moreover, a neural network that uses a Variance Detection Module (VDM) can effectively detect the variance of the input data stream through the network and dynamically adjust the degree of differentiation between samples to enhance the accuracy of forecasts. The proposed method adds significant information regarding the data sparse samples and enhances low dimensional samples to high data samples to overcome the sparse data stream problem. In VDM the preprocessed data achieve data augmentation and the samples are transmitted to VDM. The proposed method is evaluated using different types of data streaming datasets to predict the sparse data stream. Experimental results demonstrate that the proposed method achieves a high prediction accuracy and that the data stream has significant effects and strong robustness compared to other existing approaches.

A Hybrid Dynamic Programming and Neural Network Approach to Unit Commitment with High Renewable Penetration

window.dataLayer = window.dataLayer || []; function gtag(){dataLayer.push(arguments);} gtag("js", new Date()); gtag("config", "UA-72322659-1");

Dynamic neural network approach to targeted balance assessment of individuals with and without neurological disease during non-steady-state locomotion

BackgroundClinical balance assessments often rely on functional tasks as a proxy for balance (e.g., Timed Up and Go). In contrast, analyses of balance in research settings incorporate quantitative biomechanical measurements (e.g., whole-body angular momentum, H) using motion capture techniques. Fully instrumenting patients in the clinic is not feasible, and thus it is desirable to estimate biomechanical quantities related to balance from measurements taken from a subset of the body segments. Machine learning algorithms are well-suited for this type of low- to high-dimensional mapping. Thus, our goal was to develop and test an artificial neural network that to predict segment contributions to whole-body angular momentum from linear acceleration and angular velocity signals (i.e., those typically available to wearable inertial measurement units, IMUs) taken from a sparse set of body segments.MethodsOptical motion capture data were collected from five able-bodied individuals and five individuals with Parkinson's disease (PD) walking on a non-steady-state locomotor circuit comprising stairs, ramps and changes of direction. Motion data were used to calculate angular momentum (i.e., “gold standard” output data) and body-segment linear acceleration and angular velocity data from local reference frames at the wrists, ankles and neck (i.e., network input). A dynamic nonlinear autoregressive neural network was trained using the able-bodied data (pooled across subjects). The neural network was tested on data from individuals with PD with noise added to simulate real-world IMU data.ResultsCorrelation coefficients of the predicted segment contributions to whole-body angular momentum with the gold standard data were 0.989 for able-bodied individuals and 0.987 for individuals with PD. Mean RMS errors were between 2 and 7% peak signal magnitude for all body segments during completion of the locomotor circuits.ConclusionOur results suggest that estimating segment contributions to angular momentum from mechanical signals (linear acceleration, angular velocity) from a sparse set of body segments is a feasible method for assessing coordination of balance—even using a network trained on able-bodied data to assess individuals with neurological disease. These targeted estimates of segmental momenta could potentially be delivered to clinicians using a sparse sensor set (and likely in real-time) in order to enhance balance rehabilitation of people with PD.

A Dynamic Neural Network Approach for Efficient Control of Manipulators

Redundancy resolution is a critical problem in the control of manipulators. The dual neural network, as a special type of recurrent neural networks that are inherently parallel processing models, is widely investigated in past decades to control manipulators. However, to the best of our knowledge, existing dual neural networks require a full knowledge about manipulator parameters for efficient control. We make progress along this direction in this paper by proposing a novel model-free dual neural network, which is able to address the learning and control of manipulators simultaneously in a unified framework. Different from pure learning problems, the interplay of the control part and the learning part allows us to inject an additive noise into the control channel to increase the richness of signals for the purpose of efficient learning. Due to a deliberate design, the learning error is guaranteed for convergence to zero despite the existence of additive noise for stimulation. Theoretical analysis reveals the global stability of the proposed neural network control system. Simulation results verify the effectiveness of the proposed control scheme for redundancy resolution of a PUMA 560 manipulator.

Determining China's CO2 emissions peak with a dynamic nonlinear artificial neural network approach and scenario analysis

The global community and the academic world have paid great attention to whether and when China's carbon dioxide (CO2) emissions will peak. Our study investigates the issue with the Nonlinear Auto Regressive model with exogenous inputs (NARX), a dynamic nonlinear artificial neural network that has not been applied previously to this question. The key advance over previous models is the inclusion of feedback mechanisms such as the influence of past CO2 emissions on current emissions. The results forecast that the peak of China's CO2 emissions will occur in 2029, 2031 or 2035 at the level of 10.08, 10.78 and 11.63 billion tonnes under low-growth, benchmark moderate-growth, and high-growth scenarios. Based on the methodology of the mean impact value (MIV), we differentiate and rank the importance of the influence factors on CO2 emissions whereas previous studies included but did not rank factors. We suggest that China should choose the moderate growth development road and achieve its peak target in 2031, focusing on reducing CO2 emissions as a percent of GDP, less carbon-intensive industrialization, and choosing technologies that reduce CO2 emissions from coal or increasing the use of less carbon-intensive fuels.

Dynamic Neural Network Modelling of Soil Moisture Content for Predictive Irrigation Scheduling.

Sustainable freshwater management is underpinned by technologies which improve the efficiency of agricultural irrigation systems. Irrigation scheduling has the potential to incorporate real-time feedback from soil moisture and climatic sensors. However, for robust closed-loop decision support, models of the soil moisture dynamics are essential in order to predict crop water needs while adapting to external perturbation and disturbances. This paper presents a Dynamic Neural Network approach for modelling of the temporal soil moisture fluxes. The models are trained to generate a one-day-ahead prediction of the volumetric soil moisture content based on past soil moisture, precipitation, and climatic measurements. Using field data from three sites, a value above 0.94 was obtained during model evaluation in all sites. The models were also able to generate robust soil moisture predictions for independent sites which were not used in training the models. The application of the Dynamic Neural Network models in a predictive irrigation scheduling system was demonstrated using AQUACROP simulations of the potato-growing season. The predictive irrigation scheduling system was evaluated against a rule-based system that applies irrigation based on predefined thresholds. Results indicate that the predictive system achieves a water saving ranging between 20 and 46% while realizing a yield and water use efficiency similar to that of the rule-based system.

Dynamic L-RNN recovery of missing data in IoMT applications

One of the most important factors of success of the Internet of Medical Things (IoMT) applications is reliable data delivery. The high quality of data delivery is a vital issue for IoMT applications to provide a high-quality of services to the end users. However, IoMT applications may suffer from low quality of data delivery due to several reasons, such as sensing errors, bad connections or outside attacks. As a result, the collected data is incomplete. IoMT applications require a complete data to provide a high-quality of services to the end users; otherwise, the performance will decrease and not meet the main requirements of IoMT applications. In reality, missing data should be intelligently recovered to save time and cost. In this paper, we propose a Dynamic Layered-Recurrent Neural Network (Dynamic L-RNN) approach to recover missing data from IoMT applications. The main idea is to perform a dynamic L-RNN to predict any missing value in a simple fast manner to save time and cost. The collected data is divided into two categories, complete and incomplete data. A dynamic L-RNN is trained based on complete data, which is used to predict the missing data from incomplete data. This proposed method is able to recover the missing data for IoMT applications with high AUC value when applied to two different datasets. The obtained results show great enhancement in the AUC values after recovering the missing data.

Hybrid CFD-ANN Scheme for Air Flow and Heat Transfer Across In-Line Flat Tubes Array

Flat tubes are vital components of various technical applications including modern heat exchangers, thermal power plants, and automotive radiators. This paper presents the hybridization of computational fluid dynamic (CFD) and artificial neural network (ANN) approach to predict the thermal-hydraulic characteristics of in-line flat tubes heat exchangers. A 2D steady state and an incompressible laminar flow in a tube configuration are considered for numerical analysis. Finite volume technique and body-fitted coordinate system are used to solve the Navier–Stokes and energy equations. The Reynolds number based on outer hydraulic diameter varies between 10 and 320. Heat transfer coefficient and friction are analyzed for various tube configurations including transverse and longitudinal pitches. The numerical results from CFD analysis are used in the training and testing of the ANN for predicting thermal characteristics and friction factors. The predicted results revealed a satisfactory performance, with the mean relative error ranging from 0.39% to 5.57%, the root-mean-square error ranging from 0.00367 to 0.219, and the correlation coefficient (R2) ranging from 99.505% to 99.947%. Thus, this study verifies the effectiveness of using ANN in predicting the performance of thermal-hydraulic systems in engineering applications such as heat transfer modeling and fluid flow in tube bank heat exchangers.

Modeling response of runoff and evapotranspiration for predicting water table depth in arid region using dynamic recurrent neural network

The investigation of the dynamic response of aquifer to rainfall with variation of the atmospheric conditions is a key issue for groundwater resource management. A data-driven dynamic recurrent neural network approach, based on multi-objective optimization is used here to forecast groundwater levels as a function of rainfall, temperature, humidity, runoff and evapotranspiration data. Recurrent Neural Network (RNN) with variable transfer functions like tangential sigmoidal, purelin and logarithmic sigmoidal are used to compute the relative performance of the model. The results demonstrate the transition behavior due to changing evapotranspiration and runoff. Statistical and graphical indicators are used to compare the results. The statistical indicators used in this work are Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Coefficient of Determination (R2). From the results, evapotranspiration loss and run off are the influencing parameters which affect the depth to water table in the ground water reservoir. It is observed that calculated losses due to evapotranspiration are comparatively less during high precipitation in the Rengali province. Results of R2 suggest that inclusion of evapotranspiration and runoff in different scenario improves the model efficiency in predicting water table depth.

A Wiener-Type Dynamic Neural Network Approach to the Modeling of Nonlinear Microwave Devices

A new Wiener-type dynamic neural network (DNN) approach for nonlinear device modeling is proposed in this paper. The proposed analytical formulation of Wiener-type DNN structure consists of a cascade of a simplified linear dynamic part and a nonlinear static part. The simplified linear dynamic equations are obtained by vector fitting enhancing the efficiency of the model. A new formulation and new sensitivity analysis technique is derived to train the proposed Wiener-type DNN with dc, small- and large-signal data. A new gradient-based training algorithm is also formulated to speed up the training of proposed Wiener-type DNN model. The proposed Wiener-type DNN model can be trained to be accurate relative to device data. Furthermore, the proposed Wiener-type DNN provides enhanced convergence properties over existing neural network approaches such as time delay neural network (TDNN) and TDNN with extrapolation. Application examples on modeling GaAs metal-semiconductor-field-effect transistor, GaAs high-electron mobility transistor (HEMT), and a real <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$2 \times 50$ </tex-math></inline-formula> gatewidth GaAs pseudomorphic HEMT are presented. The use of Wiener-type DNN model in harmonic balance simulations demonstrates that the Wiener-type DNN is a robust method for developing models for different types of microwave devices. These models could be implemented into circuit simulators conveniently.

Dynamic Modelling of Aerobic Granular Sludge Artificial Neural Networks

Aerobic Granular Sludge (AGS) technology is a promising development in the field of aerobic wastewater treatment system. Aerobic granulation usually happened in sequencing batch reactors (SBRs) system. Most available models for the system are structurally complex with the nonlinearity and uncertainty of the system makes it hard to predict. A reliable model of AGS is essential in order to provide a tool for predicting its performance. This paper proposes a dynamic neural network approach to predict the dynamic behavior of aerobic granular sludge SBRs. The developed model will be applied to predict the performance of AGS in terms of the removal of Chemical Oxygen Demand (COD). The simulation uses the experimental data obtained from the sequencing batch reactor under three different conditions of temperature (30˚C, 40˚C and 50˚C). The overall results indicated that the dynamic of aerobic granular sludge SBR can be successfully estimated using dynamic neural network model, particularly at high temperature.

Dynamic neural network architectures for on field stochastic calibration of indicative low cost air quality sensing systems

In the last few years, the interest in the development of new pervasive or mobile implementations of air quality multisensor devices has significantly grown. New application opportunities appeared together with new challenges due to limitations in dealing with rapid pollutants concentrations transients both for static and mobile deployments. In this work, we propose a Dynamic Neural Network (DNN) approach to the stochastic prediction of air pollutants concentrations by means of chemical multisensor devices. DNN architectures have been devised and tested in order to tackle the cross sensitivities issues and sensors inherent dynamic limitations. Testing have been performed using an on-field recorded dataset from a pervasive deployment in Cambridge (UK), encompassing several weeks. The results obtained with the dynamic model are compared with the response of the static neural network and the performance analysis indicates the capability of the on-field dynamic multivariate calibration to ameliorate the static calibration approach performance in this real world air quality monitoring scenario. Interestingly, results analysis also suggests that the improvements are more significant when pollutants concentration changes more rapidly.

Biological modeling the undulatory locomotion of C. elegans using dynamic neural network approach

This paper provides an undulatory locomotion model of C. elegans to achieve the chemotaxis behaviors based on the biological neuronal and neuromuscular structure. The on-cell and off-cell mechanism, as well as the proprioceptive mechanism is incorporated into the locomotion model. The nervous system of C. elegans is modeled by a dynamic neural network (DNN) that involves two parts: head DNN and motor neurons. The head DNN perceives the outside concentrations and generates the undulatory wave to the body. The motor neurons are responsible for transiting the undulatory wave along the body. The body of C. elegans is represented as a multi-joint rigid link model with 11 links. The undulatory locomotion behavior is achieved by using the DNN to control the lengths of muscles on ventral and dorsal sides, and then using the muscle lengths to control the angles between two consecutive links. In this work, the relations between the outputs of DNN and muscle lengths, as well as the muscle lengths and the angles between two consecutive links, are determined. Furthermore, owing to the learning capability of DNN, a set of nonlinear functions that are designed to represent the chemotaxis behaviors of C. elegans are learned by the head DNN. The testing results show good performance of the locomotion model for the chemotaxis behaviors of finding food and avoiding toxin, as well as slight and Ω turns. At last, quantitative analyses by comparing with the experiment results are provided to verify the realness and effectiveness of the locomotion model, which could serve as a prototype for other footless animals.

Predicting oil price movements: A dynamic Artificial Neural Network approach

Price of oil is important for the economies of oil exporting and oil importing countries alike. Therefore, insight into the likely future behaviour and patterns of oil prices can improve economic planning and reduce the impacts of oil market fluctuations. This paper aims to improve the application of Artificial Neural Network (ANN) techniques to prediction of oil price. We develop a dynamic Nonlinear Auto Regressive model with eXogenous input (NARX) as a form of ANN to account for the time factor. We estimate the model using macroeconomic data from OECD countries. In order to compare the results, we develop time series and ANN static models. We then use the output of time series model to develop a NARX model. The NARX model is trained with historical data from 1974 to 2004 and the results are verified with data from 2005 to 2009. The results show that NARX model is more accurate than time series and static ANN models in predicting oil prices in general as well as in predicting the occurrence of oil price shocks.

A 3D undulatory locomotion model inspired by C. elegans through DNN approach

In this work, a 3D undulatory locomotion model inspired by Caenorhabditis elegans is constructed. Following the anatomical structure of C. elegans, the body of the model is represented as a multi-joint rigid link system with 12 links. The angle between two consecutive links is determined by the muscle lengths in four quadrants that are controlled by the nervous system. The nervous system of this locomotion model is represented by a dynamic neural network (DNN) that involves three parts: head DNN, central pattern generator (CPG), and body DNN. The head DNN decides turning or not, and CPG produces the sinusoid waves that are transmitted through the body DNN to control the lengths of muscles. The 3D locomotion behavior is achieved by using the DNN to control the muscle lengths, and then using the muscle lengths to control the angles between two consecutive links on both horizontal plane and vertical plane. In this work, the relations between the outputs of DNN and muscle lengths, as well as the muscle lengths and the angles between two consecutive links, are determined. Furthermore, due to the learning capability of DNN, a set of nonlinear functions that are designed to represent the chemotaxis behaviors of C. elegans are learned by the head DNN using Differential Evolution Algorithm. The testing results show good 3D performance of this locomotion model in both forward and backward locomotion, as well as slight turn and Ω turn. Furthermore, this locomotion model performs the chemotaxis behaviors of finding food and avoiding toxin successfully. Finally, quantitative analyses by comparing with the experiment results are provided to verify the realness and effectiveness of this locomotion model, which could serve as a prototype for the worm-like robot.

A dynamic neural network approach for solving nonlinear inequalities defined on a graph and its application to distributed, routing-free, range-free localization of WSNs

In this paper, we are concerned with the problem of finding a feasible solution to a class of nonlinear inequalities defined on a graph. A recurrent neural network is proposed to tackle this problem. The convergence of the neural network and the solution feasibility to the defined problem are both theoretically proven. The proposed neural network features a parallel computing mechanism and a distributed topology isomorphic to the corresponding graph. Thus it is suitable for distributed real-time computation. The proposed neural network is applied to range-free localization of wireless sensor networks (WSNs). The analog circuit implementation of the neural network for such an application is also explored. Simulations demonstrate the effectiveness of the proposed method.

Fault Detection of Excavator’s Hydraulic System Using Dynamic General Regression Neural Network

In order to improve reliability of excavator’s hydraulic system, a fault detection approach based upon dynamic general regression neural network (GRNN) approach was proposed. Dynamic GRNN is an extension of GRNN, which could effectively caputure the dynamic behavior of the nonlinear process. With this approach, normal samples were used as training data to develop a dynamic GRNN model in the first step. Secondly, this dynamic GRNN model performed as a fault determinant of the test fault. Experimental faults were used to validate the approach. Experimental results show that the proposed fault detection approach could effectively applied to the excavator’s hydraulic system.

Static and Dynamic Neural Network Approach for Short Term Flood Forecasting A Comparative Study

artificial neural networks (ANNs) have been applied to various hydrologic problems recently. This research demonstrates static and dynamic neural approach by applying Time lagged recurrent neural network and Radial basis function neural network to rainfall-runoff modeling for the upper area of Wardha River in India. The model is developed by processing online data over time using static and dynamic connections. Methodologies and techniques of the two models are presented in this paper and a comparison of the short term runoff prediction results between them is also conducted. The prediction results of the Time lagged recurrent neural network indicate a satisfactory performance in the three hours ahead of time prediction. The conclusions also indicate that Time lagged recurrent neural network is more versatile than Radial basis function neural network and can be considered as an alternate and practical tool for predicting short term flood flow. General Terms:- Prediction, Radial basis function neural network, Time lagged recurrent neural network.

A hybrid dynamic pre-emptive and competitive neural-network approach in solving the multi-objective dispatching problem for TFT-LCD manufacturing

This research addresses a hybrid dynamic pre-emptive and competitive neural-network approach in solving the multi-objective dispatching problem. It optimises three performance criteria simultaneously, namely: cycle time, slack time, and throughput. A case study is adopted to illustrate the performance of applying the methodology. Thin film transistor-liquid crystal display (TFT-LCD) is a high-technology industry, with a growing market. The manufacturing process is complex. It involves multi-products, sequence-dependent set-ups, random breakdowns, and multiple-objectives, with bias-weighted optimisation problems. To determine appropriate dispatching strategies, under various system conditions, is a non-trivial challenge to control the complex systems. There has been little research on these problems aimed at solving them simultaneously. This paper presents an event-triggered dynamic dispatching system that combines artificial intelligence methods to archive optimum dispatching strategies under diverse shop-floor conditions. Results show this system to be superior to previous researches.