Neural Approach Research Articles

DDC: Deep Distribution Classifier, A Convolutional Neural Network-based Approach for Identifying Data Distributions

In domains such as the stock market and manufacturing, there’s a growing demand for faster and more accurate data distribution identification methods due to the rapid generation of vast volumes of data, highlighting the need for enhanced real-time decision-making capabilities. Traditional methods of identifying data distributions often rely on manual inspection, limited statistical tests and time-consuming analysis, leading to inefficiencies and inaccuracies in classification. In this scenario, the presented research offers a novel approach leveraging Deep Learning (DL) models to automate the process. The presented methodology also enables faster and more accurate identification of data distributions by the generation of synthetic data points and training of the DL model for identifying different distribution types. The primary objective of this study is to develop a DL model that categorizes data points into specific distributions based on an input dataset. Moreover, for model training and evaluation, a total of 1000 datasets are generated,each comprising 1000 data points. The study considers five distributions (Normal, Uniform, Exponential, Log-normal and Beta distribution), with 200 datasets generated (with randomly selected parameters) for each distribution. In the study, the DL model is trained first, and later, the model is evaluated on a separate test (unseen) dataset. Then, its performance in classifying the distributions is assessed based on metrics such as accuracy and loss. The study results demonstrate the effectiveness of the proposed approach in accurately classifying the distribution of data points, providing valuable insights into the application of DL for distribution classification tasks. The proposed method enhances scalability, robustness and efficiency by harnessing the power of convolutional neural networks and advanced preprocessing techniques.

A Comparative Study of Data-Driven Prognostic Approaches under Training Data Deficiency

In industrial system health management, prognostics play a crucial role in ensuring safety and enhancing system availability. While the data-driven approach is the most common for this purpose, they often face challenges due to insufficient training data. This study delves into the prognostic capabilities of four methods under the conditions of limited training datasets. The methods evaluated include two neural network-based approaches, Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) networks, and two similarity-based methods, Trajectory Similarity-Based Prediction (TSBP) and Data Augmentation Prognostics (DAPROG), with the last being a novel contribution from the authors. The performance of these algorithms is compared using the Commercial Modular Aero-Propulsion System Simulation (CMAPSS) datasets, which are made by simulation of turbofan engine performance degradation. To simulate real-world scenarios of data deficiency, a small fraction of the training datasets from the original dataset is chosen at random for the training, and a comprehensive assessment is conducted for each method in terms of remaining useful life prediction. The results of our study indicate that, while the Convolutional Neural Network (CNN) model generally outperforms others in terms of overall accuracy, Data Augmentation Prognostics (DAPROG) shows comparable performance in the small training dataset, being particularly effective within the range of 10% to 30%. Data Augmentation Prognostics (DAPROG) also exhibits lower variance in its predictions, suggesting a more consistent performance. This is worth highlighting, given the typical challenges associated with artificial neural network methods, such as inherent randomness, non-intuitive decision-making processes, and the complexities involved in developing optimal models.

Evaluation of advanced control strategies for PMSG in wind turbines: backstepping fuzzy logic control and adaptive neural network control approaches

This study presents a comparative analysis of two advanced control strategies for Permanent Magnet Synchronous Generators (PMSGs) in wind turbines: Backstepping Fuzzy Logic Control and Adaptive Neural Network Control. The aim is to evaluate their effectiveness in handling structured and unstructured uncertainties and enhancing system performance. Backstepping Fuzzy Logic Control integrates backstepping techniques with fuzzy logic regulation to improve flexibility and robustness. This method addresses the limitations of traditional PI controllers by enhancing adaptability to parameter variations and external disturbances. In contrast, Adaptive Neural Network Control employs neural networks with dynamic compensators to address high uncertainties and nonlinearities, aiming to surpass the performance of conventional PI controllers. The study involves simulations to compare these control strategies based on several criteria: robustness in managing parameter changes and external disturbances, flexibility in adapting to dynamic conditions, and overall performance including efficiency and stability. Simulation results indicate that both strategies offer significant improvements over traditional PI controllers. Backstepping Fuzzy Logic Control demonstrates strong adaptability and robustness, while Adaptive Neural Network Control shows superior efficiency and optimality, particularly in high-uncertainty environments. This comparative analysis provides insights into the strengths and limitations of each approach, offering guidance for selecting the most suitable control strategy based on specific operational requirements. The findings contribute to advancing control methodologies in wind energy systems and suggest directions for future research and practical implementation.

A Unified Neural Network-Based Approach to Nonlinear Modeling and Digital Predistortion of RF Power Amplifier

A Unified Neural Network-Based Approach to Nonlinear Modeling and Digital Predistortion of RF Power Amplifier

Convolutional neural networks-based multi-sensor data fusion analysis for transmission lines

Abstract With the development of the power system, accurate assessment and fault diagnosis of the health status of transmission lines have become increasingly important. However, the standard data fusion algorithms do not fully exploit the correlation and weight disparity among multiple sensors. This study proposes a technique for analyzing transmission lines using a convolutional neural network-based approach to address this issue. By fusing data collected from multiple sensors in different directions, it can more accurately capture key information about transmission lines and conduct comprehensive analysis to evaluate their health status.

Neural architecture search for image super-resolution: A review on the emerging state-of-the-art

Nowadays, complex and expensive neural architectures are seen by many as a way to improve the performance of existing models in image recognition, voice recognition, translation, and other tasks. Such a perspective caused an increased interest in expert architecture engineering within Deep Learning. Fueled by this interest, neural architecture search originated as a promising way to automate the tedious process of constructing a deep neural network by hand. Over the last five years, we have seen an increasing number of works focusing all efforts on studying the impact of automating deep neural network design. The spotlight has recently turned from automatically discovering classification models to other more complex tasks. Motivated by a desire for high-resolution images in real-world user-centered and expert computer vision applications, architecture search for super-resolution image restoration centers in approaches capable of automatically finding efficient and well-performing models. Here, we present a survey that, beyond delving into an overview of modern approaches to automatic neural network design, focuses on the recollection and study of neural architecture search approaches that have directed their efforts at the super-resolution image restoration tasks and future lines of research found within this emerging area of study.

P2P credit risk management with KG-GNN: a knowledge graph and graph neural network-based approach

Credit risk management is crucial for the credit loan decision-making process on P2P platforms, essential for mitigating credit defaults. The rapid decline of China’s P2P platform market highlights the urgent need for Internet financial institutions to enhance their credit risk management strategies. Previous studies have applied machine learning to assess credit risk; however, their effectiveness is often hampered by a lack of consideration for semantic information and individual correlation. In response, we propose an innovative approach, KG-GNN, which integrates knowledge graph (KG) and graph neural network (GNN). KG-GNN leverages KG to encapsulate semantic information within complex categorical features and explore potential relationships between borrowers. Utilizing GNN, our framework extracts representation features from the KG to build comprehensive and accurate credit risk models. Our findings indicate that KG-GNN not only can predict credit risk more accurately than conventional machine learning models but also improves the stream model performance by over 20% through KG and GNN-based data augmentation techniques. By integrating KG with GNN, our approach enriches the methodologies for credit risk management and can be adapted to other data mining challenges that require processing complex semantic and relational information, thereby enhancing model learning capabilities.

Advances in drift compensation algorithms for electronic nose technology

Purpose This paper aims to explore recent advances in drift compensation algorithms for Electronic Nose (E-nose) technology and addresses sensor drift challenges through offline, online and neural network-based strategies. It offers a comprehensive review and covers causes of drift, compensation methods and future directions. This synthesis provides insights for enhancing the reliability and effectiveness of E-nose systems in drift issues. Design/methodology/approach The article adopts a comprehensive approach and systematically explores the causes of sensor drift in E-nose systems and proposes various compensation strategies. It covers both offline and online compensation methods, as well as neural network-based approaches, and provides a holistic view of the available techniques. Findings The article provides a comprehensive overview of drift compensation algorithms for E-nose technology and consolidates recent research insights. It addresses challenges like sensor calibration and algorithm complexity, while discussing future directions. Readers gain an understanding of the current state-of-the-art and emerging trends in electronic olfaction. Originality/value This article presents a comprehensive review of the latest advancements in drift compensation algorithms for electronic nose technology and covers the causes of drift, offline drift compensation algorithms, online drift compensation algorithms and neural network drift compensation algorithms. The article also summarizes and discusses the current challenges and future directions of drift compensation algorithms in electronic nose systems.

Enhancing Breast Cancer Detection Through a Tailored Convolutional Neural Network Deep Learning Approach

Enhancing Breast Cancer Detection Through a Tailored Convolutional Neural Network Deep Learning Approach

Semantic Segmentation of Urban Remote Sensing Images Based on Deep Learning

In the realm of urban planning and environmental evaluation, the delineation and categorization of land types are pivotal. This study introduces a convolutional neural network-based image semantic segmentation approach to delineate parcel data in remote sensing imagery. The initial phase involved a comparative analysis of various CNN architectures. ResNet and VGG serve as the foundational networks for training, followed by a comparative assessment of the experimental outcomes. Subsequently, the VGG+U-Net model, which demonstrated superior efficacy, was chosen as the primary network. Enhancements to this model were made by integrating attention mechanisms. Specifically, three distinct attention mechanisms—spatial, SE, and channel—were incorporated into the VGG+U-Net framework, and various loss functions were evaluated and selected. The impact of these attention mechanisms, in conjunction with different loss functions, was scrutinized. This study proposes a novel network model, designated VGG+U-Net+Channel, that leverages the VGG architecture as the backbone network in conjunction with the U-Net structure and augments it with the channel attention mechanism to refine the model’s performance. This refinement resulted in a 1.14% enhancement in the network’s overall precision and marked improvements in MPA and MioU. A comparative analysis of the detection capabilities between the enhanced and original models was conducted, including a pixel count for each category to ascertain the extent of various semantic information. The experimental validation confirms the viability and efficacy of the proposed methodology.

Understanding Narratives of Uncertainty in Fertility Intentions of Dutch Women: A Neural Topic Modeling Approach

Understanding Narratives of Uncertainty in Fertility Intentions of Dutch Women: A Neural Topic Modeling Approach

A two-stage spatial prediction modeling approach based on graph neural networks and neural processes

Spatial prediction models hold significant application value in fields such as environmental science, economic development, and geological exploration. With advancements in deep learning technology, graph neural networks (GNNs) offer a powerful and scalable solution for spatial data modeling. In these models, each spatial location is represented as a vertex, with the explanatory variables at each point converted into vertex features, and the vertex label corresponding to the target value at that point. GNNs utilize this representation to predict vertex labels, thereby performing spatial prediction. However, the residuals of GNN predictions are found to still exhibit spatial autocorrelation, indicating that traditional GNNs only achieve suboptimal results in terms of capturing complex spatial relationships. In this paper, we propose a two-stage spatial prediction method called Location Embedded Graph Neural Networks-Residual Neural Processes (LEGNN-RNP) to address this challenge. In the first stage, we employ LEGNNs, a new framework that integrates location features into GNNs through an attention mechanism, enhancing the learning of complex spatial models by considering both spatial context and attribute features. In the second stage, we model the residuals from LEGNN predictions to further extract spatial patterns from the data. Specifically, we introduce RNP, a neural process-based approach to model the Gaussian Process (GP) distribution of residuals. The distribution parameters (i.e., mean and covariance) are parameterized by a neural network, where the mean estimates the residual and the variance quantifies the prediction uncertainty. Experiments on four datasets demonstrate that our proposed two-stage method achieves state-of-the-art results by effectively extracting spatial relationships and significantly improving spatial prediction accuracy.

Genetic modification optimization technique: A neural network multi-objective energy management approach

In this study, a Neural Network-Enhanced Gene Modification Optimization Technique was introduced for multi-objective energy resource management. Addressing the need for sustainable energy solutions, this technique integrated neural network models as fitness functions, representing an advancement in artificial intelligence-driven optimization. Data collected in the European Union covered greenhouse gas emissions, energy consumption by sources, energy imports, and Levelized Cost of Energy. Since different configurations of energy consumption by sources lead to varying greenhouse gas emissions, costs, and imports, neural network prediction models were used to project the effect of new energy combinations on these variables. The projections were then fed into the gene modification optimization process to identify optimal configurations. Over 28 generations, simulations demonstrated a 46 percent reduction in energy costs and a 9 percent decrease in emissions. Human bias and subjectivity were mitigated by automating parameter settings, enhancing the objectivity of results. Benchmarking against traditional methods, such as Euclidean Distance, validated the superior performance of this approach. Furthermore, the technique's ability to visualize chromosomes and gene values offered clarity in optimization processes. These results suggest significant advancements in the energy sector and potential applications in other industries, contributing to the global effort to combat climate change.

Enhancing air pollution prediction: A neural transfer learning approach across different air pollutants

Air pollution stands out as one of the most alarming environmental challenges. It poses significant risks to human health and the environment. Accurate forecasting of air pollutant concentration levels is crucial for effective air quality management and timely implementation of mitigation strategies. In this paper, the transfer learning technique is investigated using the artificial neural network (ANN), also called multi-layer perception (MLP), to transfer knowledge across different air pollutants forecasting, and therefore, to generalize over a large set of air pollutants in the same air monitoring station. By leveraging the knowledge learned from a source forecasting task, transfer learning allows us to reduce the data requirements, speed up the training of the models, and enhance the predictive performance for different air pollutants for the target forecasting task. We present a comprehensive analysis of the transfer learning across different air pollutants in the same air monitoring station on a large dataset of air quality measurements. Our results demonstrate that transfer learning significantly improves forecasting accuracy with fewer fine-tuning data, particularly when limited labeled data is available for the target task. The findings of this study contribute to the advancement of air pollution forecasting methodologies, facilitating better decision-making processes and proactive air quality management.

Retraction Note: Classification of rubberized coir fibres using deep learning-based neural fuzzy decision tree approach

Retraction Note: Classification of rubberized coir fibres using deep learning-based neural fuzzy decision tree approach

Neural network-based distributed consensus tracking control for uncertain Euler–Lagrange systems over directed topologies

This paper proposes a neural network-based robust control approach for driving disturbed Euler–Lagrange systems (e.g., robot manipulator) in a directed network to perform consensus tracking of a heterogeneous leader’s output signal. The parameter matrices and external disturbances in each follower’s Euler–Lagrange dynamics are unmeasurable, thus we unify them into one lumped uncertainty term. Neural networks are then employed to online estimate these uncertainties, with adaptive update laws ensuring the boundedness of the estimation errors. Subsequently, a set of distributed observers are developed to adaptively estimate the leader’s states as well as the unidentified parameter vector and output matrix in the leader’s model. With their help, the robust cooperative controller is designed. Its efficacy on directed networks is theoretically justified by designing a Lyapunov function with a special structure. This function produces symmetric positive definite matrices when its first derivative terms interact with the specified parameters in the observer and Laplacian matrices for directed graphs. Finally, numerical simulations based on two-link robot manipulators are carried out to verify that the tracking errors converge to zero when applying the neural network-based robust controller.

SMTRI: A deep learning-based web service for predicting small molecules that target miRNA-mRNA interactions

Mature microRNAs are short, single-stranded RNAs that bind to target mRNAs and induce translational repression and gene silencing. Many microRNAs discovered in animals have been implicated in diseases and have recently been pursued as therapeutic targets. However, conventional pharmacological screening for candidate small-molecule drugs can be time-consuming and labor-intensive. Therefore, developing a computational program to assist mature microRNA-targeted drug discovery in silico is desirable. Our previous work (https://doi.org/10.1002/advs.201903451) revealed that the unique functional loops formed during Argonaute-mediated microRNA-mRNA interactions have stable structural characteristics and may serve as potential targets for small molecule drug discovery. Developing drugs specifically targeting disease-related mature microRNAs and their target mRNAs would avoid affecting unrelated ones. Here, we presented SMTRI, a convolutional neural network-based approach for efficiently predicting small molecules that target RNA secondary structural motifs formed by interactions between microRNAs and their target mRNAs. Measured on three additional testing sets, SMTRI outperformed state-of-the-art algorithms by 12.9-30.3% in AUC and 2.0-18.4% in Accuracy. Moreover, four case studies on the published experimentally validated RNA-targeted small molecules also revealed the reliability of SMTRI. Our method is available as a user-friendly web server at http://smtri.net.

Artificial Neural Network-based Approach for Inverse Kinematics of PUMA 260 Robot

Artificial Neural Network-based Approach for Inverse Kinematics of PUMA 260 Robot

Neural-Symbolic Methods for Knowledge Graph Reasoning: A Survey

Neural symbolic knowledge graph (KG) reasoning offers a promising approach that combines the expressive power of symbolic reasoning with the learning capabilities inherent in neural networks. This survey provides a comprehensive overview of advancements, techniques, and challenges in the field of neural symbolic KG reasoning. The survey introduces the fundamental concepts of KGs and symbolic logic, followed by an exploration of three significant KG reasoning tasks: knowledge graph completion, complex query answering, and logical rule learning. For each task, we thoroughly discuss three distinct categories of methods: pure symbolic methods, pure neural approaches, and the integration of neural networks and symbolic reasoning methods known as neural-symbolic. We carefully analyze and compare the strengths and limitations of each category of methods to provide a comprehensive understanding. By synthesizing recent research contributions and identifying open research directions, this survey aims to equip researchers and practitioners with a comprehensive understanding of the state-of-the-art in neural symbolic KG reasoning, fostering future advancements in this interdisciplinary domain.

Predictive modeling of combined cycle power plant performance using a digital twin-based neural ODE approach

This study presents a novel digital twin-based predictive modeling approach to enhance the operation, maintenance, and management of combined cycle power plants. The research aimed to accurately forecast the combined cycle power (CCP) output, a critical performance indicator, to support intelligent decision-making for plant operators and engineers. The proposed framework leverages a neural ordinary differential equation (NODE) model integrated within a digital twin architecture to capture the complex, nonlinear dynamics of combined cycle gas turbine unit (CCGU) system. The predictive model was trained and validated using multivariate time-series data collected from a CCGU, achieving high accuracy with an R2_score of 0.993, a mean absolute percentage error of 0.325 %, and a root mean squared error of 1.518. Importantly, the NODE model demonstrated superior forecasting capabilities compared to traditional machine learning techniques. The digital twin (DT) concept enables seamless real-time data integration, physics-based models, and advanced data analytics to facilitate comprehensive CCGU lifecycle management. This novel approach provides operators with reliable, real-time insights to optimize plant performance, reduce maintenance costs, and improve overall sustainability. The generalization of the NODE model to an independent CCGU unit validated its applicability across diverse power plant configurations, highlighting the originality and practical value of the research. The key contribution of this work is the development of a digital twin-based predictive modeling framework centered on the innovative use of neural ordinary differential equations to enhance the operation and maintenance of critical energy infrastructure. This research advances the state-of-the-art in intelligent asset management for the built environment.