Back-propagation Network Research Articles

Implementation and efficient evaluation of backpropagation network training algorithms in parametric simulations of soil hydraulic conductivity curve

The estimation of the soil hydraulic conductivity curve (SHCC) through machine learning tools for determining pedotransfer functions (PTFs) is essential in various agriculture, hydrological, and environmental management-related studies. The accuracy and reliability of machine learning tools such as backpropagation neural network (BNN) for estimating SHCC mainly depends on the optimization of its architecture, specifically the selection of the network training algorithms. By comparing the performance of network training algorithms, various researchers related to agriculture science, hydrology and environmental can choose the appropriate algorithm that provides the best balance of accuracy, speed, computational efficiency, and robustness for hydrological modeling purposes. Therefore, the present study assessed and compared the performance of 4 training algorithms including, gradient descent with momentum (GDM), Quasi-Newton (QN), Bayesian regularization (BR) and Levenberg-Marquardt (LM) for the estimation of the parametric-based PTFs of the van Genuchten-Mualem hydraulic conductivity equation as novelty of this research, which has not been investigated, so far. In this study four GDM, BR, LM and QN-based PTFs were derived to estimate the SHCC from different combinations of readily available properties of 86 soil samples from UNSODA database. The integral root mean square error (IRMSE) and coefficient of determination (R2) and were used to assess the estimations. The performance of BR algorithm-based PTFs on testing data varied from 4.634 to 6.690 with average 5.476 cm day−1 in terms of IRMSE, and 0.958 to 0.966 with average 0.963 in terms of R2, which provided better simulation than other training algorithms. The outcome of the present study on testing data showed that the BR algorithm was stable and robust to heterogeneous and noisy data compared to other training algorithms. Finally, development of accurate and reliable PTFs using efficient algorithms can play a crucial role in soil resource assessments, water resource management, irrigation planning, and designing effective drainage systems, because accurate knowledge of SHCC is vital for optimizing irrigation and fertilization practices and minimizing wastage of water and nutrients.

Density control in pedestrian evacuation with incorrect feedback information: Data correction

Improving evacuation efficiency is a central concern in evacuation simulation research. Incorrect feedback information can affect the effectiveness of evacuation control in partially observable evacuation. In this paper, we introduce a framework for evacuation guidance control, emphasizing data prediction and correction to mitigate the impact of abnormal observed data. The framework is built upon force-driven Cellular Automaton (CA) models and employs a data correction module to rectify abnormal information. Guided by this framework, we implement the data correction module’s functionality using Back Propagation (BP) neural networks. We utilize historical simulation data to train the BP network, obtaining a model for correcting abnormal data. Additionally, we integrate the data correction model with density control algorithms to facilitate pedestrian flow management in abnormal evacuation scenarios. Subsequently, we conduct two comparative simulation experiments to verify the algorithm’s effectiveness. One experiment utilizes an abnormal data replacement method, while the other employs a data correction method. The results show that the method of abnormal data replacement is simple, but it cannot improve the control efficiency in abnormal evacuation scenarios. The data correction method proposed in this paper can effectively improve evacuation efficiency and alleviate the congestion at exits caused by abnormal data, which reduces evacuation efficiency. The results are expected to provide insights into improving evacuation systems’ efficiency and personnel safety.

IMAR in Frequency Domain for Separating Speech Signals by STFT

Blind Source Separation is a statistical method for isolating signals coming from unidentified sources that have been picked up by a variety of sensors. In the fields of biological signal analysis and speech analysis technology, it is an active researcher. The quantity of noise that is present in the signal throughout the speech signal separation process is a disadvantage. This noise affects the signal that has been separated, and it is often loud melodic noise. For the purpose of separating speech signals from BSS, the suggested method makes use of a network that is configured with the parameters of Instantaneous Mixing in addition to an Auto Regressive model and a maximum-likelihood function. In order to separate the individual voice signal from the input mixed signals, the Back Propagation Network is put into operation. The Short Time Fourier Transform is then utilized for the purpose of dividing the spoken stream into extremely precise time periods. Next, Maximum-likelihood method is implemented to determine the optimum values of the IMAR model's W and G parameters. This step is done after the ideal values have been estimated. The suggested model was tested using a combination of voice signals and microphone signals, and the results demonstrated that it provided superior execution in comparison to other algorithms that are currently in use.

Tuning the Proportional-Integral-Derivative Control Parameters of Unmanned Aerial Vehicles Using Artificial Neural Networks for Point-to-Point Trajectory Approach.

Nowadays, trajectory control is a significant issue for unmanned micro aerial vehicles (MAVs) due to large disturbances such as wind and storms. Trajectory control is typically implemented using a proportional-integral-derivative (PID) controller. In order to achieve high accuracy in trajectory tracking, it is essential to set the PID gain parameters to optimum values. For this reason, separate gain values are set for roll, pitch and yaw movements before autonomous flight in quadrotor systems. Traditionally, this adjustment is performed manually or automatically in autotune mode. Given the constraints of narrow orchard corridors, the use of manual or autotune mode is neither practical nor effective, as the quadrotor system has to fly in narrow apple orchard corridors covered with hail nets. These reasons require the development of an innovative solution specific to quadrotor vehicles designed for constrained areas such as apple orchards. This paper recognizes the need for effective trajectory control in quadrotors and proposes a novel neural network-based approach to tuning the optimal PID control parameters. This new approach not only improves trajectory control efficiency but also addresses the unique challenges posed by environments with constrained locational characteristics. Flight simulations using the proposed neural network models have demonstrated successful trajectory tracking performance and highlighted the superiority of the feed-forward back propagation network (FFBPN), especially in latitude tracking within 7.52745 × 10-5 RMSE trajectory error. Simulation results support the high performance of the proposed approach for the development of automatic flight capabilities in challenging environments.

A design of power prediction algorithm based on health assessment optimized neural network

Wind power prediction holds significant value for the stability of the electrical grid when wind power is connected to the grid. Using neural networks for wind power prediction may have some limitations, such as slow speed and low accuracy. This paper proposes to enhance the power prediction accuracy and speed by optimizing the neural network through health assessment wind turbines. Firstly, based on wind turbine actual operating data, a health assessment is conducted to obtain a health matrix of wind turbine. Then, by calculating the weights of the matrix, the power prediction strategy of the network is optimized. Following that, matrix approximation hyperparameters are utilized to expedite the optimization process. Finally, some tests are conducted on neural network power prediction, act as optimized back propagation (BP) neural network and whale swarm algorithm–support vector regression (WSA-SVR) neural networks are employed for wind power prediction. Results show noticeable optimization: after optimizing the BP network, power prediction accuracy increased by about 40%, and prediction speed rose by about 20%; after optimizing the WSA-SVR network, power prediction accuracy improved by 10%, and prediction speed surged by about 45%. Further analysis shows that this method can improve the accuracy and speed of most neural network wind power prediction algorithms.

Non-Intrusive Load Identification Based on Retrainable Siamese Network.

Non-intrusive load monitoring (NILM) can identify each electrical load and its operating state in a household by using the voltage and current data measured at a single point on the bus, thereby behaving as a key technology for smart grid construction and effective energy consumption. The existing NILM methods mainly focus on the identification of pre-trained loads, which can achieve high identification accuracy and satisfying outcomes. However, unknown load identification is rarely involved among those methods and the scalability of NILM is still a crucial problem at the current stage. In light of this, we have proposed a non-intrusive load identification method based on a Siamese network, which can be retrained after the detection of an unknown load to increase the identification accuracy for unknown loads. The proposed Siamese network comprises a fixed convolutional neural network (CNN) and two retrainable back propagation (BP) networks. When an unknown load is detected, the low-dimensional features of its voltage-current (V-I) trajectory are extracted by using the fixed CNN model, and the BP networks are retrained online. The finetuning of BP network parameters through retraining can improve the representation ability of the network model; thus, a high accuracy of unknown load identification can be achieved by updating the Siamese network in real time. The public WHITED and PLAID datasets are used for the validation of the proposed method. Finally, the practicality and scalability of the method are demonstrated using a real-house environment test to prove the ability of online retraining on an embedded Linux system with STM32MP1 as the core.

Defect Recognition Method for Magnetic Leakage Detection in Oil and Gas Steel Pipes Based on Improved Neural Networks

The aging infrastructure of petroleum and natural gas pipelines poses a threat to national economies, necessitating precise defect detection for safety and efficiency. To enhance the accuracy of predicting pipeline defect sizes, this study introduces a magnetic leakage detection system, employing Backpropagation (BP) neural networks optimized with genetic algorithms. Traditional BP networks face challenges, including parameter determination and slow convergence, addressed through genetic algorithms' global search capabilities. Simulated data are generated using ANSYS software by using models of semi-circular defects in steel pipes, producing magnetic leakage signals of varying intensities. MATLAB was used to construct both standard BP and genetically optimized BP neural networks. Results show that the latter significantly reduces computational errors, demonstrating improved accuracy in defect dimension prediction. The approach contributes to overcoming non-uniqueness in the recognition process and the complex nonlinear relationship between magnetic signals and defect size parameters. The study offers a guided approach for selecting BP neural network parameters, enhancing practicality. Simulations validate the method's effectiveness, indicating low workload and high reliability. This research provides a meaningful advancement in the detection of defects in long-distance pipelines, impacting the safety and efficiency of petroleum and natural gas transportation.

A new paradigm for smart packaging: A dual-channel freshness monitoring platform based on aerogels of sodium alginate-anthocyanin complex with high colorimetric sensitivity and stability

Global seafood consumption is estimated at 156 million tons annually, with an economic loss of >25 billion euros annually due to marine fish spoilage. In contrast to traditional smart packaging which can only roughly estimate food freshness, an intelligent platform integrating machine learning and smart aerogel can accurately predict remaining shelf life in food products, reducing economic losses and food waste. In this study, we prepared aerogels based on anthocyanin complexes that exhibited excellent environmental responsiveness, high porosity, high color-rendering properties, high biocompatibility, high stability, and irreversibility. The aerogel showed excellent indication properties for rainbow trout and proved suitable for fish storage environments. Among the four machine learning models, the radial basis function neural network and backpropagation network optimized by genetic algorithm demonstrated excellent monitoring performance. Also, the two-channel dataset provided more comprehensive information and superior descriptive capability. The three-layer structure of the monitoring platform provided a new paradigm for intelligent and sophisticated food packaging. The results of the study might be of great significance to the food industry and sustainable development.

Predicted evaporation in Basrah using artificial neural networks

Abstract Accurate evaporation estimation is crucial for managing hydrologic, hydraulic, and agricultural systems, among many other applications of water resources. Empirical formulae for estimating evaporation exist, but their performance is not always sufficient due to the intricacy of the process and its nonlinear connection with other elements of the hydrological cycle. For this reason, a model of artificial neural networks was developed to estimate the daily potential evaporation in the southern Iraqi city of Basrah. A feedforward backpropagation (BP) network with a single hidden layer has been used to construct the mode. Different networks with various neuron counts were assessed. The developed models have been trained, tested, and validated using daily observations of the average rainfall, wind speed, average temperature, average relative humidity, and evaporation. The final evaporation was predicted using an artificial neural network (ANN) model. The proposed model was found to be more suitable to describe evaporation in any region of the world based on the values of the error analysis and the coefficient of determination, according to the ANN model. The Levenberg–Marquardt algorithm (LMA) was determined to have the lowest mean-squared error (MSE) and highest value of the coefficient of correlation (R) of the six proposed BP algorithms. The LMA’s hidden layer’s ideal neuron count was 30 neurons, with an MSE of 0.00288 and R 2 = 99. As a result, ANN displayed excellent performance in terms of evaporation prediction value. The study’s findings highlight the significance of predicting evaporation as the main metric for evaluating the effects of climate change on water resources.

Machine vision-based online detection method for color characteristics of cobalt extraction solution

Cobalt, as a rare metal, plays an important role in strategic resources due to its physical, chemical, and mechanical properties in applications. In order to achieve automatic control of the cobalt extraction process, it is necessary to conduct online detection of the color characteristics of the cobalt extraction solution. Unfortunately, due to the lack of online automatic detection methods for the color of cobalt extraction solution, the automatic control of the extraction process has not yet been achieved. Currently, the color of cobalt extraction solution needs to be observed and judged by operators based on experience. This will result in significant detection errors and time lag. To change this situation, an online detection method for color features of cobalt extraction solution based on machine vision is proposed in this article. Firstly, we establish a real-time image acquisition environment for detecting object colors, and then use the Gaussian filters and K-means algorithm to denoise and segment the image. In order to correct color distortion in images caused by ambient light, we measure the color feature values of a set of standard color cards using the machine vision system and a standard spectrophotometer. Based on this test data, we establish chromaticity correction models for the extraction solution using back propagation (BP) network and radial basis function (RBF) network, respectively. The models can correct the color characteristic values of the extraction solution, overcome environmental interference, and thus obtain more accurate color characteristic values of the extraction solution. The established model can be used for online automatic color detection of cobalt extraction solution. The modeling results indicate that in the established color measurement environment, the RBF network model outperforms the BP network model in color feature detection accuracy.

IMAR in Frequency Domain for Separating Speech Signals by STFT

Blind Source Separation is a statistical method for isolating signals coming from unidentified sources that have been picked up by a variety of sensors. In the fields of biological signal analysis and speech analysis technology, it is an active researcher. The quantity of noise that is present in the signal throughout the speech signal separation process is a disadvantage. This noise affects the signal that has been separated, and it is often loud melodic noise. For the purpose of separating speech signals from BSS, the suggested method makes use of a network that is configured with the parameters of Instantaneous Mixing in addition to an Auto Regressive model and a maximum-likelihood function. In order to separate the individual voice signal from the input mixed signals, the Back Propagation Network is put into operation. The Short Time Fourier Transform is then utilized for the purpose of dividing the spoken stream into extremely precise time periods. Next, Maximum-likelihood method is implemented to determine the optimum values of the IMAR model's W and G parameters. This step is done after the ideal values have been estimated. The suggested model was tested using a combination of voice signals and microphone signals, and the results demonstrated that it provided superior execution in comparison to other algorithms that are currently in use.

Machine learning backpropagation network analysis of permeability, Forchheimer coefficient, and effective thermal conductivity of macroporous foam–fluid systems

Macroporous materials exhibit outstanding properties in heat and mass transfer due to their high pore volume, high surface area, and high Young's modulus. Consequently, understanding their thermofluidic properties is crucial in the design, synthesis, and optimal application of these materials. Therefore, this study, premieres, the use of a machine learning (ML) backpropagation network to develop and train a series of datasets for permeability, Forchheimer coefficient, and effective thermal conductivity of variable macroporous foam–fluid systems with respect to degrees of interstices, fluid and solid properties. To account for permeability values for flowing fluids in the Darcy regime, numerical simulations of slow–moving fluids were implemented over the materials' interstices. In comparison to similarly substantiated values of permeability in the Forchheimer regime, these values were a bit lower. The ML-based backpropagation algorithm was used to analyze data, which produced predictions (output signals) that are more than 90 % in correlation to CFD datasets. This provided insight into the effect of porosity and reduced mean pore openings on macroporous structures' thermofluidic behaviour. Material porosity was observed to play a dominant role in estimating Forchheimer coefficients and effective thermal conductivities for these foam-fluid systems. However, reduced mean pore openings were observed to be more critical for estimating permeability. The contributory effects of reduced mean pore openings on the effective thermal conductivity for these macroporous foam–fluid systems were determined to vary between 5.8 and 13.2 percent. Furthermore, the effective thermal conductivity of macroporous foam–fluid systems was also evaluated in relation to changes in the interstitial fluid and solid matrix thermal conductivity.

A Production Prediction Model of Tight Gas Well Optimized with a Back Propagation (BP) Neural Network Based on the Sparrow Search Algorithm

The production of tight gas wells decreases rapidly, and the traditional method is difficult to accurately predict the production of tight gas wells. At present, intelligent algorithms based on big data have been applied in oil and gas well production prediction, but there are still some technical problems. For example, the traditional error back propagation neural network (BP) still has the problem of finding the local optimal value, resulting in low prediction accuracy. In order to solve this problem, this paper establishes the output prediction method of BP neural network optimized with the sparrow search algorithm (SSA), and optimizes the hyperparameters of BP network such as activation function, training function, hidden layer, and node number based on examples, and constructs a high-precision SSA-BP neural network model. Data from 20 tight gas wells, the SSA-BP neural network model, Hongyuan model, and Arps model are predicted and compared. The results indicate that when the proportion of the predicted data is 20%, the SSA-BP model predicts an average absolute mean percentage error of 20.16%. When the proportion of forecast data is 10% of the total data, the SSA-BP algorithm has high accuracy and high stability. When the proportion of predicted data is 10%, the mean absolute average percentage error is 3.97%, which provides a new method for tight gas well productivity prediction.

Swarm intention identification via dynamic distribution probability image

In the realm of decision-making for defense and security applications, it is paramount to swiftly and accurately identify the intentions of incoming swarms. Conventional identification methods predominantly focus on single-target applications and overlook the perturbations introduced by measurement noise. In this study, we propose a novel concept: the Dynamic Distribution Probability (DDP) image, which is constructed using the estimated state and its covariance matrix. Each grayscale pixel value within the image signifies the probability of the presence of the agent within the swarm. Our proposed identification scheme integrates the use of Extended Kalman Filter (EKF), Convolutional Neural Network (CNN), Back Propagation (BP) network, and Gated Recurrent Unit (GRU) network. Specifically, the DDP image is processed through a CNN to distill the formation characteristics, and the estimated swarm state from EKF is inputted into a BP network to deduce the kinematic information. The outputs from both networks are summed and subsequently channeled into a GRU network to capture temporal dynamics. Extensive numerical simulations and flight experiments are presented to demonstrate the robust anti-noise capability of the proposed scheme compared with conventional methods, as well as its superior training efficiency.

Virtual analysis of machine learning models for diseases prediction in muskmelon

Muskmelon, a crop prized for its economic potential, has a relatively brief growth cycle. Disease susceptibility during this period can have a profound impact on yields, posing challenges for farmers. Environmental conditions are pivotal in disease occurrence. Unfavorable conditions reduce the likelihood of pathogens infecting vulnerable host plants as temperature and humidity influence pathogen behavior, including toxin synthesis, virulence protein production, and reproduction. Pathogens can lie dormant in the soil until suitable conditions activate them. When the right environment and host plants align, these dormant pathogens can cause outbreaks. Disease prediction becomes possible by analyzing environmental variables. Real-time data collected via strategically placed sensors focused on viral, fungal, and bacterial infections. Results indicated that the extreme gradient boosting (XGBoost) algorithm, with a maximum tree depth of 4 and 30 trees per iteration, achieved remarkable performance, yielding an accuracy of 97%. For comparison, the XGBoost model outperformed an 8-layer Backpropagation network with 7 nodes per layer, which achieved 95% accuracy. These findings underscore XGBoost's efficacy in forecasting and mitigating muskmelon plant diseases, offering the potential for improved crop yields and agricultural sustainability.

Prediction of hydrological and water quality data based on granular-ball rough set and k-nearest neighbor analysis.

Hydrological and water quality datasets usually encompass a large number of characteristic variables, but not all of these significantly influence analytical outcomes. Therefore, by wisely selecting feature variables with rich information content and removing redundant features, it not only can the analysis efficiency be improved, but the model complexity can also be simplified. This paper considers introducing the granular-ball rough set algorithm for feature variable selection and combining it with the k-nearest neighbor method and back propagation network to analyze hydrological and water quality data, thus promoting overall and fused inspection. The results of hydrological water quality data analysis show that the proposed method produces better results compared to using a standalone k-nearest neighbor regressor.

Risk Zoning Method of Potential Sudden Debris Flow Based on Deep Neural Network

With the continuous increase in global climate change and human activities, the risk of sudden debris flow disasters is becoming increasingly severe. In order to effectively evaluate and zone the potential hazards of debris flows, this paper proposes a method for zoning the potential sudden hazards of debris flows based on deep neural networks. According to hazard identification, ten risk indicators of potential sudden debris flows are determined. The risk indicators of a potential sudden debris flow in each region were used as the input factors of a deep trust network (DBN) composed of a back propagation (BP) neural network and a restricted Boltzmann machine (RBM). The DBN is pre-trained using the contrast divergence method to obtain the optimal value of the parameter set of the DBN model, and a BP network is set at the last layer of the DBN for fine-tuning to make the network optimal. Using the DBN model with the best parameters, the risk probability of debris flows corresponding to each region is taken as an output. The risk grade is divided, the risk degree of potential sudden debris flow in each region is analyzed, and the potential sudden debris flow risk in each region is divided individually. The results show that this method can effectively complete the risk zoning of sudden debris flow. Moreover, the cumulative contribution of the indicators selected by this method is significant, and the correlation of indicators is not significant, which can play a role in the risk assessment of potential sudden debris flow. This study not only provides new ideas and methods for risk assessment of sudden debris flow disasters, but also fills a gap in the field of geological hazard susceptibility mapping.

A channel state information and geomagnetic fused fingerprint localisation algorithm based on multi‐input convolutional neural network

AbstractNumerous applications require indoor localisation, and one of the current research areas is how to leverage low‐cost ubiquitous signals for indoor localisation. This research designs a multi‐input convolutional neural network (Multi‐CNN) localisation approach to combine natural geomagnetic signals and universal 5G communication signals. To create the location fingerprint data, the geomagnetic three‐component data and channel state information (CSI) must first undergo independent preprocessing. Subsequently, the rebuilt CSI amplitude and geomagnetic intensity are employed for separate offline training to efficiently extract the corresponding data features. Lastly, Multi‐CNN is used to estimate the user's location online. The localisation outcomes for the conference room and hall demonstrate that the Multi‐CNN algorithm can achieve average localisation accuracies of 1.41 and 2.66 m, respectively. These are higher than the single‐input CNN algorithms by 21% and 15%, and higher than backpropagation network (BPNN) algorithm by 24% and 17%, and higher than the weighted K‐nearest neighbour algorithm by 34% and 28%. The Multi‐CNN‐based localisation approach successfully fuses the diverse data, potentially satisfying most indoor localisation applications.

Investigation of Hydrodynamics Characteristics of Fluidized Bed with back propagation Artificial Neural Network (BPANN)

Correlations have also been developed with system parameters by using dimensional analysis and an artificial neural network approach. The paper describes an investigation for the thermal design of a fluidized bed cooler and prediction of heat transfer rate among the media categories. It is devoted to the thermal design of such equipment and their application in the industrial fields. In the present work, an extensive ANN by using back propagation (BP) has been carried out to correlate the expansion ratio, fluctuation ratio in gas-solid fluidized bed. Back propagation network is the most well-known and widely used among the current types of neural network system, several applications of ANN for modeling of nonlinear process systems and subsequent control were reported. In back-propagation, different ANN structures (I×H×O) with varying number of neurons in the hidden layer were used as a tool for training input and output data for prediction value of hydrodynamic characteristics of the bed system. It was noted that ring models are the best ones in reducing bed expansion ratio and fluctuation ratio around (25%) and (23.22%).

Application of a long short-term memory neural network algorithm fused with Kalman filter in UWB indoor positioning

Ultra-wideband technology has good anti-interference capabilities and development prospects in indoor positioning. Since ultra-wideband will be affected by random errors in indoor positioning, to exploit the advantages of the Kalman filter (KF) and the long short-term memory (LSTM) network, this paper proposes a long short-term memory neural network algorithm fused with the Kalman filter (KF–LSTM) to improve UWB positioning. First, the ultra-wideband data is processed through KF to weaken the noise in the data, and then the data is fed into the LSTM network for training, and the capability of the LSTM network to process time series features is employed to obtain more accurate label positions. Finally, simulation and measurement results show that the KF–LSTM algorithm achieves 71.31%, 37.28%, and 49.31% higher average positioning accuracy than the back propagation (BP) network, (back propagation network fused with the Kalman filter (KF-BP), and LSTM network algorithms, respectively, and the KF–LSTM algorithm performs more stably. Meanwhile, the more noise the data contains, the more obvious the stability contrast between the four algorithms.