Search

In the vehicle-following scenario of autonomous driving, the change of driving style in the front vehicle will directly affect the decision on the rear vehicle. In this paper, a strategy based on a probabilistic neural network (PNN) for front vehicle intention recognition is proposed, which enables the rear vehicle to obtain the driving intention of the front vehicle without communication between the two vehicles. First, real vehicle data with different intents are collected and time—frequency domain variables are extracted. Secondly, Principal Component Analysis (PCA) is performed on the variables in order to obtain comprehensive features. Meanwhile, two cases are classified according to whether the front vehicle can transmit data to the rear vehicle. Finally, two recognition models are trained separately according to a PNN algorithm, and the two models obtained from the training are verified separately. When the front vehicle can communicate with the rear vehicle, the recognition accuracy of the corresponding PNN model reaches 96.39% (simulation validation) and 95.08% (real vehicle validation). If it cannot, the recognition accuracy of the corresponding PNN model reaches 78.18% (simulation validation) and 73.74% (real vehicle validation). [ABSTRACT FROM AUTHOR]

Deep learning has gained widespread interest in the task of building semantic segmentation modelling using remote sensing images; however, neural network models require a large number of training samples to achieve better classification performance, and the models are more sensitive to error patches in the training samples. The training samples obtained in semi-supervised classification methods need less reliable weakly labelled samples, but current semi-supervised classification research puts the generated weak samples directly into the model for applications, with less consideration of the impact of the accuracy and quality improvement of the weak samples on the subsequent model classification. Therefore, to address the problem of generating and optimising the quality of weak samples from training data in deep learning, this paper proposes a semi-supervised building classification framework. Firstly, based on the test results of the remote sensing image segmentation model and the unsupervised classification results of LiDAR point cloud data, this paper quickly generates weak image samples of buildings. Secondly, in order to improve the quality of the spots of the weak samples, an iterative optimisation strategy of the weak samples is proposed to compare and analyse the weak samples with the real samples and extract the accurate samples from the weak samples. Finally, the real samples, the weak samples, and the optimised weak samples are input into the semantic segmentation model of buildings for accuracy evaluation and analysis. The effectiveness of this paper's approach was experimentally verified on two different building datasets, and the optimised weak samples improved by 1.9% and 0.6%, respectively, in the test accuracy mIoU compared to the initial weak samples. The results demonstrate that the semi-supervised classification framework proposed in this paper can be used to alleviate the model's demand for a large number of real-labelled samples while improving the ability to utilise weak samples, and it can be used as an alternative to fully supervised classification methods in deep learning model applications that require a large number of training samples. [ABSTRACT FROM AUTHOR]

This editorial presents a summary of the Special Issue on Artificial Intelligence Solutions and Applications for Distributed Systems in Smart Spaces, presented in the "Computer Science & Engineering" section of I Electronics i (ISSN 2079-9292). The application of artificial intelligence (AI) in distributed environments has become a research area of high-added value and economic potential. The Present Issue This Special Issue consists of seven papers that address pivotal topics in the field of AI solutions for distributed systems and their applications. [Extracted from the article]

In this paper, a fault identification algorithm combining a signal processing algorithm and machine learning algorithm is proposed, using a four-mass vibration MEMS gyroscope (FMVMG) for signal acquisition work, constructing a gyroscope fault dataset, and performing the model training task based on this dataset. Combining the improved EWT algorithm with SEResNeXt-50 reduces the impact of white noise in the signal on the identification task and significantly improves the accuracy of fault identification. The EWT algorithm is a wavelet analysis algorithm with adaptive wavelet analysis, which can significantly reduce the impact of boundary effects, and has a good effect on decomposition of signal segments with short length, but a reconstruction method is needed to effectively separate the noise signal and effective signal, and so this paper uses multiscale permutation entropy for calculation. For the reason that the neural network has a better ability to characterize high-dimensional signals, the one-dimensional signal is reconstructed into a two-dimensional image signal and the signal features are extracted. Then, the constructed image signals are fed into the SEResNeXt-50 network, and the characterization ability of the model is further improved in the network with the addition of the Squeeze-and-Excitation module. Finally, the proposed model is applied to the FMVMG fault dataset and compared with other models. In terms of recognition accuracy, the proposed method improves about 30.25% over the BP neural network and about 1.85% over ResNeXt-50, proving the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

The life expectancy of power transformers is primarily determined by the integrity of the insulating oil and cellulose paper between the conductor turns, phases and phase to earth. During the course of their in-service lifetime, the solid insulating system of windings is contingent on long-standing ageing and decomposition. The decomposition of the cellulose paper insulation is strikingly grievous, as it reduces the tensile strength of the cellulose paper and can trigger premature failure. The latter can trigger premature failure, and to realize at which point during the operational life this may occur is a daunting task. Various methods of estimating the DP have been proposed in the literature; however, these methods yield different results, making it difficult to accurately estimate a reliable DP. In this work, a novel approach based on the Feedforward Backpropagation Artificial Neural Network has been proposed to predict the amount of DP in transformer cellulose insulation. Presently, no ANN model has been proposed to predict the remaining DP using 2FAL concentration. A databank comprising 100 data sets—70 for training and 30 for testing—is used to develop the proposed ANN using 2-furaldehyde (2FAL) as an input and DP as an output. The proposed model yields a correlation coefficient of 0.958 for training, 0.915 for validation, 0.996 for testing and an overall correlation of 0.958 for the model. [ABSTRACT FROM AUTHOR]

This paper aims at evaluating the current state of research into artificial intelligence (AI)-based decision support systems (DSS) for improving construction project sustainability. The literature was systematically reviewed to explore the use of AI in the construction project lifecycle together with the consideration of the economic, environmental, and social goals of sustainability. A total of 2688 research papers were reviewed, and 77 papers were further analyzed, and the major tasks of the DSSs were categorized. Our review results suggest that the main research stream is dedicated to early-stage project prediction (50% of all papers), with artificial neural networks (ANNs) and fuzzy logic (FL) being the most popular AI algorithms in use. Hybrid AI models were used in 46% of all studies. The goal for economic sustainability is the most considered in research, with 87% of all papers considering this goal, and there is evidence given of a trend towards the environmental and social goals of sustainability receiving increasing attention throughout the latter half of the decade. [ABSTRACT FROM AUTHOR]

The rapid development of natural language processing and deep learning techniques has boosted the performance of related algorithms in several linguistic and text mining tasks. Consequently, applications such as opinion mining, fake news detection or document classification that assign documents to predefined categories have significantly benefited from pre-trained language models, word or sentence embeddings, linguistic corpora, knowledge graphs and other resources that are in abundance for the more popular languages (e.g., English, Chinese, etc.). Less represented languages, such as the Kazakh language, balkan languages, etc., still lack the necessary linguistic resources and thus the performance of the respective methods is still low. In this work, we develop a model that classifies scientific papers written in the Kazakh language using both text and image information and demonstrate that this fusion of information can be beneficial for cases of languages that have limited resources for machine learning models' training. With this fusion, we improve the classification accuracy by 4.4499% compared to the models that use only text or only image information. The successful use of the proposed method in scientific documents' classification paves the way for more complex classification models and more application in other domains such as news classification, sentiment analysis, etc., in the Kazakh language. [ABSTRACT FROM AUTHOR]

Forest biomass estimation is undoubtedly one of the most pressing research subjects at present. Combining multi-source remote sensing information can give full play to the advantages of different remote sensing technologies, providing more comprehensive and rich information for aboveground biomass (AGB) estimation research. Based on Landsat 8, Sentinel-2A, and ALOS2 PALSAR data, this paper takes the artificial coniferous forests in the Saihanba Forest of Hebei Province as the object of study, fully explores and establishes remote sensing factors and information related to forest structure, gives full play to the advantages of spectral signals in detecting the horizontal structure and multi-dimensional synthetic aperture radar (SAR) data in detecting the vertical structure, and combines environmental factors to carry out multivariate synergistic methods of estimating the AGB. This paper uses three variable selection methods (Pearson correlation coefficient, random forest significance, and the least absolute shrinkage and selection operator (LASSO)) to establish the variable sets, combining them with three typical non-parametric models to estimate AGB, namely, random forest (RF), support vector regression (SVR), and artificial neural network (ANN), to analyze the effect of forest structure on biomass estimation, explore the suitable AGB of artificial coniferous forests estimation of machine learning models, and develop the method of quantifying saturation value of the combined variables. The results show that the horizontal structure is more capable of explaining the AGB compared to the vertical structure information, and that combining the multi-structure information can improve the model results and the saturation value to a great extent. In this study, different sets of variables can produce relatively superior results in different models. The variable set selected using LASSO gives the best results in the SVR model, with an R 2 values of 0.9998 and 0.8792 for the training and the test set, respectively, and the highest saturation value obtained is 185.73 t/ha, which is beyond the range of the measured data. The problem of saturation in biomass estimation in boreal medium- and high-density forests was overcome to a certain extent, and the AGB of the Saihanba area was better estimated. [ABSTRACT FROM AUTHOR]

This paper introduces a novel one-dimensional convolutional neural network that utilizes clinical data to accurately detect choledocholithiasis, where gallstones obstruct the common bile duct. Swift and precise detection of this condition is critical to preventing severe complications, such as biliary colic, jaundice, and pancreatitis. This cutting-edge model was rigorously compared with other machine learning methods commonly used in similar problems, such as logistic regression, linear discriminant analysis, and a state-of-the-art random forest, using a dataset derived from endoscopic retrograde cholangiopancreatography scans performed at Olive View–University of California, Los Angeles Medical Center. The one-dimensional convolutional neural network model demonstrated exceptional performance, achieving 90.77% accuracy and 92.86% specificity, with an area under the curve of 0.9270. While the paper acknowledges potential areas for improvement, it emphasizes the effectiveness of the one-dimensional convolutional neural network architecture. The results suggest that this one-dimensional convolutional neural network approach could serve as a plausible alternative to endoscopic retrograde cholangiopancreatography, considering its disadvantages, such as the need for specialized equipment and skilled personnel and the risk of postoperative complications. The potential of the one-dimensional convolutional neural network model to significantly advance the clinical diagnosis of this gallstone-related condition is notable, offering a less invasive, potentially safer, and more accessible alternative. [ABSTRACT FROM AUTHOR]

In this paper, the effect evaluation and production prediction of staged fracturing for horizontal wells in tight reservoirs are studied. Firstly, the basic characteristics and value of horizontal wells in tight reservoirs are introduced, their geological characteristics, flow mechanism and permeability model are analyzed and the application of grey theory in effect analysis is discussed. Considering the problems of staged fracturing effect evaluation and the production prediction of horizontal wells in tight reservoirs, a BP neural network model based on deep learning is proposed. Due to the interference of multiple physical parameters and the complex functional relationship in the development of tight reservoir fracturing, the traditional prediction method has low accuracy and it is difficult to establish an accurate mapping relationship. In this paper, a BP neural network is used to simulate multivariable nonlinear mapping by modifying the model, and its advantages in solving the coupling relationship of complex functions are brought into play. A neural network model with fracturing parameters as input and oil and gas production as output is designed. Through the training and testing of data sets, the accuracy and applicability of the proposed model for effect evaluation and yield prediction are verified. The research results show that the model can fit the complex mapping relationship between fracturing information and production and provide an effective evaluation and prediction tool for the development of the staged fracturing of horizontal wells in tight reservoirs. [ABSTRACT FROM AUTHOR]

This paper presents a novel use of a bio-inspired retina model as a scene preprocessing stage for the recognition of letters and numbers on Chilean vehicle license plates. The goal is to improve the effectiveness and ease of pattern recognition. Inspired by the responses of mammalian retinas, this retinal model reproduces both the natural adjustment of contrast and the enhancement of object contours by parvocellular cells. Among other contributions, this paper provides an in-depth exploration of the architecture, advantages, and limitations of the model; investigates the tuning parameters of the model; and evaluates its performance when integrating a convolutional neural network and a spiking neural network into an optical character recognition (OCR) algorithm, using 40 different genuine license plate images as a case study and for testing. The results obtained demonstrate the reduction of error rates in character recognition based on convolutional neural networks (CNNs), spiking neural networks (SNNs), and OCR. It is concluded that this bio-inspired retina model offers a wide spectrum of potential applications to further explore, including motion detection, pattern recognition, and improvement of dynamic range in images, among others. [ABSTRACT FROM AUTHOR]

Human Activity Recognition (HAR) plays an important role in the automation of various tasks related to activity tracking in such areas as healthcare and eldercare (telerehabilitation, telemonitoring), security, ergonomics, entertainment (fitness, sports promotion, human–computer interaction, video games), and intelligent environments. This paper tackles the problem of real-time recognition and repetition counting of 12 types of exercises performed during athletic workouts. Our approach is based on the deep neural network model fed by the signal from a 9-axis motion sensor (IMU) placed on the chest. The model can be run on mobile platforms (iOS, Android). We discuss design requirements for the system and their impact on data collection protocols. We present architecture based on an encoder pretrained with contrastive learning. Compared to end-to-end training, the presented approach significantly improves the developed model's quality in terms of accuracy (F1 score, MAPE) and robustness (false-positive rate) during background activity. We make the AIDLAB-HAR dataset publicly available to encourage further research. [ABSTRACT FROM AUTHOR]

This document serves as an introduction to a special issue on wireless sensor networks (WSNs), explaining their structure and applications in various sectors. It also discusses the challenges faced by WSNs, such as limited energy and data management. The special issue features ten research papers on advanced WSNs. [Extracted from the article]

Convolutional Neural Networks (CNNs) are a kind of artificial neural network designed to extract features and find out patterns for tasks such as segmentation, recognizing objects, and drawing up classification. Within a CNNs architecture, pooling operations are used until the number of parameters and the computational complexity are reduced. Numerous papers have focused on investigating the impact of pooling on the performance of Convolutional Neural Networks (CNNs), leading to the development of various pooling models. Recently, a fuzzy pooling operation based on type-1 fuzzy sets was introduced to cope with the local imprecision of the feature maps. However, in fuzzy set theory, it is not always accurate to assume that the degree of non-membership of an element in a fuzzy set is simply the complement of the degree of membership. This is due to the potential existence of a hesitation degree, which implies a certain level of uncertainty. To overcome this limitation, intuitionistic fuzzy sets (IFS) were introduced to incorporate the concept of a degree of hesitation. In this paper, we introduce a novel pooling operation based on intuitionistic fuzzy sets to incorporate the degree of hesitation heretofore neglected by a fuzzy pooling operation based on classical fuzzy sets, and we investigate its performance in the context of image classification. Intuitionistic pooling is performed in four steps: bifuzzification (by the transformation of data through the use of membership and non-membership maps), first aggregation (through the transformation of the IFS into a standard fuzzy set, second aggregation (through the transformation and use of a sum operator), and the defuzzification of feature map neighborhoods by using a max operator. IFS pooling is used for the construction of an intuitionistic pooling layer that can be applied as a drop-in replacement for the current, fuzzy (type-1) and crisp, pooling layers of CNN architectures. Various experiments involving multiple datasets demonstrate that an IFS-based pooling can enhance the classification performance of a CNN. A benchmarking study reveals that this significantly outperforms even the most recent pooling models, especially in stochastic environments. [ABSTRACT FROM AUTHOR]

Channel estimation accuracy significantly affects the performance of orthogonal frequency-division multiplexing (OFDM) systems. In the literature, there are quite a few channel estimation methods. However, the performances of these methods deteriorate considerably when the wireless channels suffer from nonlinear distortions and interferences. Machine learning (ML) shows great potential for solving nonparametric problems. This paper proposes ML-based channel estimation methods for systems with comb-type pilot patterns and random pilot symbols, such as ATSC 3.0. We compare their performances with conventional channel estimations in ATSC 3.0 systems for linear and nonlinear channel models. We also evaluate the robustness of the ML-based methods against channel model mismatch and signal-to-noise ratio (SNR) mismatch. The results show that the ML-based channel estimations achieve good mean squared error (MSE) performance for linear and nonlinear channels if the channel statistics used for the training stage match those of the deployment stage. Otherwise, the ML estimation models may overfit the training channel, leading to poor deployment performance. Furthermore, the deep neural network (DNN)-based method does not outperform the linear channel estimation methods in nonlinear channels. [ABSTRACT FROM AUTHOR]

This study presents a numerical approach to the design and optimization of centrifugal impellers used in the pumps of active thermal control systems of spacecraft. Although launch costs have shrunk in the last decade, the performance requirements, such as efficiency and reliability, have increased, as such systems are required to work up to 15 years, depending on the mission. To that effect, our paper deals with the first step in this pump design, namely the hydraulic optimization of the impeller. Constructively, this type of impeller allows for certain balancing systems and labyrinth seals to be applied in a more effective way, as well as allowing for additive manufacturing methods to be used—however, details regarding these aspects are beyond the scope of the current paper. By combining empirical formulas, computational fluid dynamics (CFD) analysis, and artificial neural networks (ANNs), the research focuses on achieving high efficiency and fast manufacturing. A series of geometries have been sized and validated using steady-state RANS (Reynolds Averaged Navier-Stokes) simulations, leading to the identification of the most efficient configuration. Subsequent optimization using an ANN resulted in a refined impeller design with notable improvements in hydraulic performance: a 3.55% increase in efficiency and a 7.9% increase in head. Key parameters influencing impeller performance, including blade number, incidence, and backsweep angles, are identified. This approach offers a comprehensive method to address the evolving requirements of space missions and contributes to the advancement of centrifugal pump technology in the space domain. [ABSTRACT FROM AUTHOR]

Increasing global credit card usage has elevated it to a preferred payment method for daily transactions, underscoring its significance in global financial cybersecurity. This paper introduces a credit card fraud detection (CCFD) system that integrates federated learning (FL) with blockchain technology. The experiment employs FL to establish a global learning model on the cloud server, which transmits initial parameters to individual local learning models on fog nodes. With three banks (fog nodes) involved, each bank trains its learning model locally, ensuring data privacy, and subsequently sends back updated parameters to the global learning model. Through the integration of FL and blockchain, our system ensures privacy preservation and data protection. We utilize three machine learning and deep neural network learning algorithms, RF, CNN, and LSTM, alongside deep optimization techniques such as ADAM, SGD, and MSGD. The SMOTE oversampling technique is also employed to balance the dataset before model training. Our proposed framework has demonstrated efficiency and effectiveness in enhancing classification performance and prediction accuracy. [ABSTRACT FROM AUTHOR]

Utilizing a turnkey approach to deliver a construction project entails significant risks from the contractor's perspective. Essentially, the owner awaits project completion without commitments regarding additional expenditures incurred by the contractor during the project's duration. This paper specifically focuses on estimating and analyzing the contingency value for residential turnkey projects in Saudi Arabia. The contingency value across the project's life cycle is estimated using six Artificial Neural Network (ANN) models, which are compared to identify the best-trained network according to project complexity, contingency factor, and contingency impact during the project phases. The output layer provides the contingency factor percentages for each project phase. A 13-story reinforced concrete (RC) residential building established in one of Saudi Arabia's cities was selected to implement the developed methodology. The contingency estimation, performed using @Risk 7.5 and NeuralTools 7.5, was determined to be 11.34% and was distributed across the five phases of the project's life cycle: 0.30% for predesign, 0.99% for design, 2.61% for preconstruction, 6.33% for construction, and 1.12% for postconstruction. Furthermore, it was found that the estimated contingency varies based on project complexity, which is 7.20% for low complexity, 8.16% for medium complexity, 9.41% for complicated, and 11.34% for very complicated projects. Historical data and peer review approaches are employed to validate the results, both of which are endorsed by professionals in this field. This paper highlights two main contributions: Firstly, it significantly enhances risk management by facilitating a comprehensive understanding and systematic analysis of risks, thus improving the contractors' ability to mitigate potential negative impacts on projects. Secondly, it supports more informed decision-making through the use of advanced techniques to estimate and analyze contingency values. These contributions are critical for contractors engaged in Saudi construction projects, particularly those involving residential buildings. [ABSTRACT FROM AUTHOR]

This paper introduces a numerical methodology for classifying and identifying types of bio-based materials through experimental thermal characterization. In contrast to prevailing approaches that primarily focus on thermal conductivity, our characterization methodology encompasses several thermal parameters. In this paper, the physical characteristics of seven types of bio-based concrete were analyzed, focusing on the thermal properties of palm- and esparto-fiber-reinforced concrete. The proposed method uses artificial intelligence techniques, specifically the k-means clustering approach, to segregate data into homogeneous groups with shared thermal characteristics. This enables the elucidation of insights and recommendations regarding the utilization of bio-based insulation in building applications. The results show that the k-means algorithm is able to efficiently classify the reference concrete (RC) with a performance of up to 71%. Additionally, the technique is more accurate when retaining only six centroids, which, among other things, allows all the characteristics associated with each type of concrete to be grouped and identified. Indeed, whether for k clusters k = 7 or k = 5, the technique was not able to predict the typical characteristics of 2% or 3% esparto concrete (EC). [ABSTRACT FROM AUTHOR]

This paper presents a novel application of machine learning models to clarify the intricate behaviors of expansive soils, focusing on the impact of sand content, saturation level, and dry density. Departing from conventional methods, this research utilizes a data-centric approach, employing a suite of sophisticated machine learning models to predict soil properties with remarkable precision. The inclusion of a 30% sand mixture is identified as a critical threshold for optimizing soil strength and stiffness, a finding that underscores the transformative potential of sand amendment in soil engineering. In a significant advancement, the study benchmarks the predictive power of several models including extreme gradient boosting (XGBoost), gradient boosting regression (GBR), random forest regression (RFR), decision tree regression (DTR), support vector regression (SVR), symbolic regression (SR), and artificial neural networks (ANNs and proposed ANN-GMDH). Symbolic regression equations have been developed to predict the elasticity modulus and unconfined compressive strength of the investigated expansive soil. Despite the complex behaviors of expansive soil, the trained models allow for optimally predicting the values of unconfined compressive parameters. As a result, this paper provides for the first time a reliable and simply applicable approach for estimating the unconfined compressive parameters of expansive soils. The proposed ANN-GMDH model emerges as the pre-eminent model, demonstrating exceptional accuracy with the best metrics. These results not only highlight the ANN's superior performance but also mark this study as a groundbreaking endeavor in the application of machine learning to soil behavior prediction, setting a new benchmark in the field. [ABSTRACT FROM AUTHOR]

Although deep neural networks have been successfully applied in many fields, research studies show that neural network models are easily disrupted by small malicious inputs, greatly reducing their performance. Such disruptions are known as adversarial attacks. To reduce the impact of adversarial attacks on models, researchers have proposed adversarial training methods. However, compared with standard training, adversarial training results in additional computational overhead and training time. To improve the training effect without significantly increasing the training time, an improved Fast-M adversarial training algorithm based on the fast adversarial training algorithm is proposed in this paper. Extensive comparative experiments are conducted with the MNIST, CIFAR10, and CIFAR100 datasets. The results show that the Fast-M algorithm achieves the same training effect as the commonly used projected gradient descent (PGD) adversarial training method, with a training time that is only one-third of that of PGD and a performance comparable to that of fast adversarial training, demonstrating the proposed algorithm's effectiveness. [ABSTRACT FROM AUTHOR]

This review explores recent advancements in hydrogen gas (H2) safety through the lens of artificial intelligence (AI) techniques. As hydrogen gains prominence as a clean energy source, ensuring its safe handling becomes paramount. The paper critically evaluates the implementation of AI methodologies, including artificial neural networks (ANN), machine learning algorithms, computer vision (CV), and data fusion techniques, in enhancing hydrogen safety measures. By examining the integration of wireless sensor networks and AI for real-time monitoring and leveraging CV for interpreting visual indicators related to hydrogen leakage issues, this review highlights the transformative potential of AI in revolutionizing safety frameworks. Moreover, it addresses key challenges such as the scarcity of standardized datasets, the optimization of AI models for diverse environmental conditions, etc., while also identifying opportunities for further research and development. This review foresees faster response times, reduced false alarms, and overall improved safety for hydrogen-related applications. This paper serves as a valuable resource for researchers, engineers, and practitioners seeking to leverage state-of-the-art AI technologies for enhanced hydrogen safety systems. [ABSTRACT FROM AUTHOR]

Monitoring heart conditions through electrocardiography (ECG) has been the cornerstone of identifying cardiac irregularities. Cardiologists often rely on a detailed analysis of ECG recordings to pinpoint deviations that are indicative of heart anomalies. This traditional method, while effective, demands significant expertise and is susceptible to inaccuracies due to its manual nature. In the realm of computational analysis, Artificial Neural Networks (ANNs) have gained prominence across various domains, which can be attributed to their superior analytical capabilities. Conversely, Spiking Neural Networks (SNNs), which mimic the neural activity of the brain more closely through impulse-based processing, have not seen widespread adoption. The challenge lies primarily in the complexity of their training methodologies. Despite this, SNNs offer a promising avenue for energy-efficient computational models capable of displaying a high-level performance. This paper introduces an innovative approach employing SNNs augmented with an attention mechanism to enhance feature recognition in ECG signals. By leveraging the inherent efficiency of SNNs, coupled with the precision of attention modules, this model aims to refine the analysis of cardiac signals. The novel aspect of our methodology involves adapting the learned parameters from ANNs to SNNs using leaky integrate-and-fire (LIF) neurons. This transfer learning strategy not only capitalizes on the strengths of both neural network models but also addresses the training challenges associated with SNNs. The proposed method is evaluated through extensive experiments on two publicly available benchmark ECG datasets. The results show that our model achieves an overall accuracy of 93.8% on the MIT-BIH Arrhythmia dataset and 85.8% on the 2017 PhysioNet Challenge dataset. This advancement underscores the potential of SNNs in the field of medical diagnostics, offering a path towards more accurate, efficient, and less resource-intensive analyses of heart diseases. [ABSTRACT FROM AUTHOR]

Radio frequency interference (RFI) significantly hampers the target detection performance of frequency-modulated continuous-wave radar. To address the problem and maintain the target echo signal, this paper proposes a priori assumption on the interference component nature in the radar received signal, as well as a method for interference estimation and mitigation via time–frequency analysis. The solution employs Fourier synchrosqueezed transform to implement the radar's beat signal transformation from time domain to time–frequency domain, thus converting the interference mitigation to the task of time–frequency distribution image restoration. The solution proposes the use of image processing based on the dual-tree complex wavelet transform and combines it with the spatial domain-based approach, thereby establishing a dual-domain fusion interference filter for time–frequency distribution images. This paper also presents a convolutional neural network model of structurally improved UNet++, which serves as the interference estimator. The proposed solution demonstrated its capability against various forms of RFI through the simulation experiment and showed a superior interference mitigation performance over other CNN model-based approaches. [ABSTRACT FROM AUTHOR]

Deep learning, a crucial technique for achieving artificial intelligence (AI), has been successfully applied in many fields. The gradual application of the latest architectures of deep learning in the field of time series forecasting (TSF), such as Transformers, has shown excellent performance and results compared to traditional statistical methods. These applications are widely present in academia and in our daily lives, covering many areas including forecasting electricity consumption in power systems, meteorological rainfall, traffic flow, quantitative trading, risk control in finance, sales operations and price predictions for commercial companies, and pandemic prediction in the medical field. Deep learning-based TSF tasks stand out as one of the most valuable AI scenarios for research, playing an important role in explaining complex real-world phenomena. However, deep learning models still face challenges: they need to deal with the challenge of large-scale data in the information age, achieve longer forecasting ranges, reduce excessively high computational complexity, etc. Therefore, novel methods and more effective solutions are essential. In this paper, we review the latest developments in deep learning for TSF. We begin by introducing the recent development trends in the field of TSF and then propose a new taxonomy from the perspective of deep neural network models, comprehensively covering articles published over the past five years. We also organize commonly used experimental evaluation metrics and datasets. Finally, we point out current issues with the existing solutions and suggest promising future directions in the field of deep learning combined with TSF. This paper is the most comprehensive review related to TSF in recent years and will provide a detailed index for researchers in this field and those who are just starting out. [ABSTRACT FROM AUTHOR]

Pattern recognition systems always misclassify anomalies, which can be dangerous for uninformed users. Therefore, anomalies must be filtered out from each classification. The main challenge for the anomaly filter design is the huge number of possible anomaly samples compared with the number of samples in the training set. Tailoring the filter for the given classifier is just the first step in this reduction. Paper tests the hypothesis that the filter trained in avoiding "near" anomalies will also refuse the "far" anomalies, and the anomaly detector is then just a classifier distinguishing between "far real" and "near anomaly" samples. As a "far real" samples generator was used, a Generative Adversarial Network (GAN) fake generator that transforms normally distributed random seeds into fakes similar to the training samples. The paper proves the assumption that seeds unused in fake training will generate anomalies. These seeds are distinguished according to their Chebyshev norms. While the fakes have seeds within the hypersphere with a given radius, the near anomalies have seeds within the sphere near cover. Experiments with various anomaly test sets have shown that GAN-based anomaly detectors create a reliable anti-anomaly shield using the abovementioned assumptions. The proposed anomaly detector is tailored to the given classifier, but its limitation is due to the need for the availability of the database on which the classifier was trained. [ABSTRACT FROM AUTHOR]

The accurate prediction of heavy precipitation in convective environments is crucial because such events, often occurring in Italy during the summer and fall seasons, can be a threat for people and properties. In this paper, we analyse the impact of satellite-derived surface-rainfall-rate data assimilation on the Weather Research and Forecasting (WRF) model's precipitation prediction, considering 15 days in summer 2022 and 17 days in fall 2022, where moderate to intense precipitation was observed over Italy. A 3DVar realised at CNR-ISAC (National Research Council of Italy, Institute of Atmospheric Sciences and Climate) is used to assimilate two different satellite-derived rain rate products, both exploiting geostationary (GEO), infrared (IR), and low-Earth-orbit (LEO) microwave (MW) measurements: One is based on an artificial neural network (NN), and the other one is the operational P-IN-SEVIRI-PMW product (H60), delivered in near-real time by the EUMETSAT HSAF (Satellite Application Facility in Support of Operational Hydrology and Water Management). The forecast is verified in two periods: the hours from 1 to 4 (1–4 h phase) and the hours from 3 to 6 (3–6 h phase) after the assimilation. The results show that the rain rate assimilation improves the precipitation forecast in both seasons and for both forecast phases, even if the improvement in the 3–6 h phase is found mainly in summer. The assimilation of H60 produces a high number of false alarms, which has a negative impact on the forecast, especially for intense events (30 mm/3 h). The assimilation of the NN rain rate gives more balanced predictions, improving the control forecast without significantly increasing false alarms. [ABSTRACT FROM AUTHOR]

Giga-casting, a revolutionary approach for manufacturing large, single-piece car body components from aluminium, has emerged as a potential game-changer in the automotive industry. However, these large, thin-walled castings are prone to distortions during solidification and heat treatment processes. Straightening these distortions is crucial to ensure structural integrity, facilitate downstream assembly, and maintain aesthetic qualities. This paper proposes a novel method for straightening giga-cast components using a multi-pin straightening machine. The machine's versatility stems from its ability to adapt to various geometries through multiple strategically controlled straightening pins. This paper introduces the concept of a "straightening stroke decision algorithm" to achieve precise straightening and overcome the challenges of complex shapes. This algorithm determines the stroke length for each pin, combining a polynomial model representing the global stiffness of the component with a machine learning model that captures the stiffness changes arising from the current geometry. The effectiveness of the proposed approach is evaluated through comprehensive numerical experiments using finite element analyses. The straightening performance is assessed for the straightening algorithm with different machine learning models (deep neural network and XGBoost) and compared to a traditional optimisation method. The proposed surrogate models decided the straightening strokes so that the maximum remaining distortion became 0.02% of the largest dimension of each target geometry. The results of the numerical experiment showed that the proposed straightening method is suitable for straightening distortion in large thin-walled components. [ABSTRACT FROM AUTHOR]

The research on baggage flow plays a pivotal role in achieving the efficient and intelligent allocation and scheduling of airport service resources, as well as serving as a fundamental element in determining the design, development, and process optimization of airport baggage handling systems. This paper examines baggage checked in by departing passengers at airports. The crrent state of the research on baggage flow demand is first reviewed and analyzed. Then, using examples of objective data, it is concluded that while there is a significant correlation between airport passenger flow and baggage flow, an increase in passenger flow does not necessarily result in a proportional increase in baggage flow. According to the existing research results on the influencing factors of baggage flow sorting and classification, the main influencing factors of baggage flow are divided into two categories: macro-influencing factors and micro-influencing factors. When studying the relationship between the economy and baggage flow, it is recommended to use a comprehensive analysis that includes multiple economic indicators, rather than relying solely on GDP. This paper provides a brief overview of prevalent transportation flow prediction methods, categorizing algorithmic models into three groups: based on mathematical and statistical models, intelligent algorithmic-based models, and combined algorithmic models utilizing artificial neural networks. The structures, strengths, and weaknesses of various transportation flow prediction algorithms are analyzed, as well as their application scenarios. The potential advantages of using artificial neural network-based combined prediction models for baggage flow forecasting are explained. It concludes with an outlook on research regarding the demand for baggage flow. This review may provide further research assistance to scholars in airport management and baggage handling system development. [ABSTRACT FROM AUTHOR]

Stance information has a significant influence on market strategy, government policy, and public opinion. Users differ not only in their polarity but also in the degree to which they take a stand. The traditional classification of stances is quite simple and cannot fully depict the diversity of stances. At the same time, traditional approaches ignore user sentiment features when expressing their stances. As a result, this paper develops a multi-stance detection model by fusing sentiment features. First, a five-category stance indicator system is built based on the LDA model, then sentiment features are extracted from the reviews using the sentiment lexicon, and finally, stance detection is implemented using a hybrid neural network model. The experiment shows that the proposed method can classify stances into five categories and perform stance detection more accurately. [ABSTRACT FROM AUTHOR]

Leakage in water supply pipelines remains a significant challenge. It leads to resource and economic waste. Researchers have developed several leak detection methods, including the use of embedded sensors and pressure prediction. The former approach involves pre-installing detectors inside pipelines to detect leaks. This method allows for the precise localization of leak points. The stability is compromised because of the wireless signal strength. The latter approach, which relies on pressure measurements to predict leak events, does not achieve precise leak point localization. To address these challenges, in this paper, a coherent optical time-domain reflectometry (φ-OTDR) system is employed to capture vibration signal phase information. Subsequently, two pre-trained neural network models based on CNN and Resnet18 are responsible for processing this information to accurately identify vibration events. In an experimental setup simulating water pipelines, phase information from both leaking and non-leaking pipe segments is collected. Using this dataset, classical CNN and ResNet18 models are trained, achieving accuracy rates of 99.7% and 99.5%, respectively. The multi-leakage point experiment results indicate that the Resnet18 model has better generalization compared to the CNN model. The proposed solution enables long-distance water-pipeline precise leak point localization and accurate vibration event identification. [ABSTRACT FROM AUTHOR]

Existing research in metasurface design was based on trial-and-error high-intensity iterations and requires deep acoustic expertise from the researcher, which severely hampered the development of the metasurface field. Using deep learning enabled the fast and accurate design of hypersurfaces. Based on this, in this paper, an integrated learning approach was first utilized to construct a model of the forward mapping relationship between the hypersurface physical structure parameters and the acoustic field, which was intended to be used for data enhancement. Then a dual-feature fusion model (DFCNN) based on a convolutional neural network was proposed, in which the first feature was the high-dimensional nonlinear features extracted using a data-driven approach, and the second feature was the physical feature information of the acoustic field mined using the model. A convolutional neural network was used for feature fusion. A genetic algorithm was used for network parameter optimization. Finally, generalization ability verification was performed to prove the validity of the network model. The results showed that 90% of the integrated learning models had an error of less than 3 dB between the real and predicted sound field data, and 93% of the DFCNN models could achieve an error of less than 5 dB in the local sound field intensity. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs) are increasingly important in the medical diagnosis of electrocardiogram (ECG) signals. However, research has shown that DNNs are highly vulnerable to adversarial examples, which can be created by carefully crafted perturbations. This vulnerability can lead to potential medical accidents. This poses new challenges for the application of DNNs in the medical diagnosis of ECG signals. This paper proposes a novel network Channel Activation Suppression with Lipschitz Constraints Net (CASLCNet), which employs the Channel-wise Activation Suppressing (CAS) strategy to dynamically adjust the contribution of different channels to the class prediction and uses the 1-Lipschitz's ℓ∞ distance network as a robust classifier to reduce the impact of adversarial perturbations on the model itself in order to increase the adversarial robustness of the model. The experimental results demonstrate that CASLCNet achieves A C C r o b u s t scores of 91.03% and 83.01% when subjected to PGD attacks on the MIT-BIH and CPSC2018 datasets, respectively, which proves that the proposed method in this paper enhances the model's adversarial robustness while maintaining a high accuracy rate. [ABSTRACT FROM AUTHOR]

This paper investigates a method for precise mapping of human arm movements using sEMG signals. A multi-channel approach captures the sEMG signals, which, combined with the accurately calculated joint angles from an Inertial Measurement Unit, allows for action recognition and mapping through deep learning algorithms. Firstly, signal acquisition and processing were carried out, which involved acquiring data from various movements (hand gestures, single-degree-of-freedom joint movements, and continuous joint actions) and sensor placement. Then, interference signals were filtered out through filters, and the signals were preprocessed using normalization and moving averages to obtain sEMG signals with obvious features. Additionally, this paper constructs a hybrid network model, combining Convolutional Neural Networks and Artificial Neural Networks, and employs a multi-feature fusion algorithm to enhance the accuracy of gesture recognition. Furthermore, a nonlinear fitting between sEMG signals and joint angles was established based on a backpropagation neural network, incorporating momentum term and adaptive learning rate adjustments. Finally, based on the gesture recognition and joint angle prediction model, prosthetic arm control experiments were conducted, achieving highly accurate arm movement prediction and execution. This paper not only validates the potential application of sEMG signals in the precise control of robotic arms but also lays a solid foundation for the development of more intuitive and responsive prostheses and assistive devices. [ABSTRACT FROM AUTHOR]

In modern warfare, frequency-hopping communication serves as the primary method for battlefield information transmission, with its significance continuously growing. Fighting for the control of electromagnetic power on the battlefield has become an important factor affecting the outcome of war. As communication electronic warfare evolves, jammers employing deep neural networks (DNNs) to decode frequency-hopping communication parameters for smart jamming pose a significant threat to communicators. This paper proposes a method to generate adversarial samples of frequency-hopping communication signals using adaptive whitening and feature gradient smoothing. This method targets the DNN cognitive link of the jammer, aiming to reduce modulation recognition accuracy and counteract smart interference. First, the frequency-hopping signal is adaptively whitened. Subsequently, rich spatiotemporal features are extracted from the hidden layer after inputting the signal into the deep neural network model for gradient calculation. The signal's average feature gradient replaces the single-point gradient for iteration, enhancing anti-disturbance capabilities. Simulation results show that, compared with the existing gradient symbol attack algorithm, the attack success rate and migration rate of the adversarial samples generated by this method are greatly improved in both white box and black box scenarios. [ABSTRACT FROM AUTHOR]

As a core component of new energy vehicles, accurate estimation of the State of Health (SOH) of lithium-ion power batteries is essential. Correctly predicting battery SOH plays a crucial role in extending the lifespan of new energy vehicles, ensuring their safety, and promoting their sustainable development. Traditional physical or electrochemical models have low accuracy in measuring the SOH of lithium batteries and are not suitable for the complex driving conditions of real-world vehicles. This study utilized the black-box characteristics of deep learning models to explore the intrinsic correlations in the historical cycling data of lithium batteries, thereby eliminating the need to consider the internal chemical reactions of lithium batteries. Through Pearson correlation analysis, this study selects health indicators (HIs) from lithium battery cycling data that significantly impact SOH as input features. In the field of lithium batteries, this paper applies ABC-BiGRU for the first time to SOH prediction. Compared with other recursive neural network models, ABC-BiGRU demonstrates superior predictive performance, with maximum root mean square error and mean absolute error of only 0.016799317 and 0.012626847, respectively. [ABSTRACT FROM AUTHOR]

Within a river catchment, the relationship between pollutant load migration and its related factors is nonlinear generally. When neural network models are used to identify the nonlinear relationship, data scarcity and random weight initialization might result in overfitting and instability. In this paper, we propose an averaged weight initialization neural network (AWINN) to realize the multi-index integrated prediction of a pollutant load under data scarcity. The results show that (1) compared with the particle swarm optimization neural network (PSONN) and AdaboostR models that prevent overfitting, AWINN improved simulation accuracy significantly. The R2 in test sets of different pollutant load models reached 0.51–0.80. (2) AWINN is effective in overcoming instability. With more hidden layers, the stability of the models' outputs was stronger. (3) Sobol sensitivity analysis explained that the main influencing factors of the whole process were the flows of the catchment inlet and outlet, and main factors changed across seasons. The algorithm proposed in this paper can realize stably integrated prediction of pollutant load in the catchment under data scarcity and help to understand the mechanism that influences pollutant load migration. [ABSTRACT FROM AUTHOR]

Recent research has revealed that subtle imperceptible perturbations can deceive well-trained neural network models, leading to inaccurate outcomes. These instances, known as adversarial examples, pose significant threats to the secure application of machine learning techniques in safety-critical systems. In this paper, we delve into the study of one-pixel attacks in deep neural networks, recently reported as a kind of adversarial examples. To identify such one-pixel attacks, most existing methodologies rely on the differential evolution method, which utilizes random selection from the current population to escape local optima. However, the differential evolution technique might waste search time and overlook good solutions if the number of iterations is insufficient. Hence, in this paper, we propose a gradient ascent with momentum approach to efficiently discover good solutions for the one-pixel attack problem. As our method takes a more direct route to the goal compared to existing methods relying on blind random walks, it can effectively identify one-pixel attacks. Our experiments conducted on popular CNNs demonstrate that, in comparison with existing methodologies, our technique can detect one-pixel attacks significantly faster. [ABSTRACT FROM AUTHOR]

This correction notice provides updates and corrections to a research paper on deep machine learning model-based cyber-attacks detection in smart power systems. The paper proposes a deep learning-based attack detection model that addresses system disturbances caused by natural events and cyber-attacks. It discusses the use of principal component analysis (PCA) for feature selection and the potential of deep learning-based and decision tree classifiers for detecting cyber-attacks in intelligent energy grids. The notice also includes updates to references, clarifications on the experimental data set, and feature selection based on PCA. The study evaluates the effectiveness of the proposed model using various assessment indexes and compares it to conventional methods, concluding that the proposed model is effective in detecting cyber-attacks and demonstrates good performance in detecting destructive attacks. [Extracted from the article]

Electricity consumption in buildings is one of the major causes of energy usage and knowledge of this can help building owners and users increase energy efficiency and conservation efforts. For Pacific Island countries, building electricity demand data is not readily accessible or available for constructing models to predict electricity demand. This paper starts to fill this gap by studying the case of schools in Fiji. The aim of the paper is to assess the factors affecting electricity demand for grid-connected Fijian schools and use this assessment to build mathematical models (multiple linear regression (MLR) and artificial neural network (ANN)) to predict electricity consumption. The average grid-connected electricity demand in kWh/year was 1411 for early childhood education schools, 5403 for primary schools, and 23,895 for secondary schools. For predicting electricity demand (ED) for all grid-connected schools, the stepwise MLR model shows that taking logarithm transformations on both the dependent variable and independent variables (number of students, lights, and air conditioning systems) yields statistically significant independent variables with an R2 value of 73.3% and RMSE of 0.2248. To improve the predicting performance, ANN models were constructed on both the natural form of variables and transformed variables. The optimum ANN model had an R2 value of 95.3% and an RMSE of 59.4 kWh/year. The findings of this study can assist schools in putting measures in place to reduce their electricity demand, associated costs, and carbon footprint, as well as help government ministries make better-informed policies. [ABSTRACT FROM AUTHOR]

Simple Summary: The research of this paper can be applied in the compaction parameter prediction of soil-filling materials, which can significantly reduce the amount of laboratory work and improve the efficiency of optimizing design for soil resource utilization in engineering construction. Maximum Dry Density (MDD) and Optimum Moisture Content (OMC) are two important parameters of soil filling, which affect the soil stability and bearing capacity, and thus the reliability and durability of facilities such as highways and bridges. Therefore, it is important to make reasonable predictions of OMC and MDD. Four machine learning algorithms, namely, Support Vector Machine (SVM), Artificial Neural Network (ANN), Random Forest (RF), and Extreme Gradient Boosting Tree (XGBoost), are adopted in this paper to establish MDD and OMC prediction models. After training and testing, the best models of the four algorithms are compared. The results show that, as an ensemble learning algorithm, XGBoost is the best model for predicting MDD and OMC, with an R2 of 0.9234 for OMC, and an R2 of 0.9098 for MDD. Finally, the feature importance analysis concludes that the plastic limit (PL) and the liquid limit (LL) are the two features that affect OMC and MDD the most. The prediction of soil compaction parameters using machine learning models, especially ensemble learning, can significantly reduce the amount of laboratory work and improve the efficiency of optimizing design for soil resource utilization in engineering construction. [ABSTRACT FROM AUTHOR]

The implementation of energy storage system (ESS) technology with an appropriate control system can enhance the resilience and economic performance of power systems. However, none of the storage options available today can perform at their best in every situation. As a matter of fact, an isolated storage solution's energy and power density, lifespan, cost, and response time are its primary performance constraints. Batteries are the essential energy storage component used in electric mobility, industries, and household applications nowadays. In general, the battery energy storage systems (BESS) currently available on the market are based on a homogeneous type of electrochemical battery. However, a hybrid energy storage system (HESS) based on a mixture of various types of electrochemical batteries can potentially provide a better option for high-performance electric cars, heavy-duty electric vehicles, industries, and residential purposes. A hybrid energy storage system combines two or more electrochemical energy storage systems to provide a more reliable and efficient energy storage solution. At the same time, the integration of multiple energy storage systems in an HESS requires advanced control strategies to ensure optimal performance and longevity of the system. This review paper aims to provide a comprehensive overview of the control systems used in HESSs for a wide range of applications. An overview of the various control strategies used in HESSs is offered, including traditional control methods such as proportional–integral–derivative (PID) control, and advanced control methods such as model predictive control (MPC), droop control (DC), sliding mode control (SMC), rule-based control (RBC), fuzzy logic control (FLC), and artificial neural network (ANN) control are discussed. The paper also highlights the recent developments in HESS control systems, including the use of machine learning techniques such as deep reinforcement learning (DRL) and genetic algorithms (GA). The paper provides not only a description and classification of various control approaches but also a comparison between control strategies from the evaluation of performance point of view. The review concludes by summarizing the key findings and future research directions for HESS control systems, which is directly linked to the research on machine learning and the mix of different control type strategies. [ABSTRACT FROM AUTHOR]

The Special Issue on "Application of Big Data Analysis and Advanced Analytics in Sustainable Production Process" received several state-of-the-art research papers related to the application of big data analysis and advanced analytics in three different areas of sustainable production processes: prognostics and health management (PHM), supply chain management (SCM), and safety policy in the workplace. On a similar subject, in the paper "A Time-Series Data Generation Method to Predict Remaining Useful Life" [[5]], a time series generation method, which is useful when there are not enough fault-labeled data available, is presented by Ahn, Yun, and Hur. We live in the big data era, in which a large amount of information is continuously created, registering all kinds of events, such as those generated in the design, planning, control, and execution of manufacturing, logistics, and supply chain processes. [Extracted from the article]

Sleep monitoring has become a prevalent area of research where body position and physiological data, such as heart rate and respiratory rate, are monitored. Numerous critical health problems are associated with poor sleep, such as pressure sore development, sleep disorders, and low sleep quality, which can lead to an increased risk of falls, cardiovascular diseases, and obesity. Current monitoring systems can be costly, laborious, and taxing on hospital resources. This paper reviews the most recent solutions for contactless textile technology in the form of bed sheets or mats to monitor body positions, vital signs, and sleep, both commercially and in the literature. This paper is organized into four categories: body position and movement monitoring, physiological monitoring, sleep monitoring, and commercial products. A detailed performance evaluation was carried out, considering the detection accuracy as well as the sensor types and algorithms used. The areas that need further research and the challenges for each category are discussed in detail. [ABSTRACT FROM AUTHOR]

The task of fine-grained named entity recognition is to locate entities in text and classify them into predefined fine-grained categories. At present, Chinese fine-grained NER only uses the pretrained language model to encode the characters in the sentence and lacks the ability to extract the deep semantic, sequence, and position information. The sequence annotation method is character-based and lacks the processing of entity boundaries. Fine-grained entity categories have a high degree of similarity, which makes it difficult to distinguish similar categories. To solve the above problems, this paper constructs the BILTAR deep semantic extraction module and adds the GlobalPointer module to improve the accuracy of Chinese fine-grained named entity recognition. The BILTAR module is used to extract deep semantic features from the coding information of pretrained language models and use higher-quality features to improve the model performance. In the GlobalPointer module, the model first adds the rotation position encoding information to the feature vector, using the position information to achieve data enhancement. Finally, the model considers all possible entity boundaries through the GlobalPointer module and calculates the scores for all possible entity boundaries in each category. In this paper, all possible entity boundaries in the text are considered by the above method, and the accuracy of entity recognition is improved. In this paper, the corresponding experiments were carried out on CLUENER 2020 and the micro Chinese fine-grained NER dataset, and the F1 scores of the model in this paper reached 80.848% and 75.751%, respectively. In ablation experiments, the proposed method outperforms the most advanced baseline model and improves the performance of the basic model. [ABSTRACT FROM AUTHOR]

With the rapid growth in the proportion of renewable energy access and the structural complexity of distributed energy systems, traditional microgrid (MG) scheduling methods that rely on mathematical optimization models and expert experience are facing significant challenges. Therefore, it is essential to present a novel scheduling technique with high intelligence and fast decision-making capacity to realize MGs' automatic operation and regulation. This paper proposes an optimal scheduling decision-making method for MGs based on deep neural networks (DNN). Firstly, a typical mathematical scheduling model used for MG operation is introduced, and the limitations of current methods are analyzed. Then, a two-stage optimal scheduling framework comprising day-ahead and intra-day stages is presented. The day-ahead part is solved by mixed integer linear programming (MILP), and the intra-day part uses a convolutional neural network (CNN)—bidirectional long short-term memory (Bi LSTM) for high-speed rolling decision making, with the outputs adjusted by a power correction balance algorithm. Finally, the validity of the model and algorithm of this paper are verified by arithmetic case analysis. [ABSTRACT FROM AUTHOR]

This paper studies the problem of linkage-bar synthesis by means of multiple deep neural networks (DNNs), which requires the inverse solution of linkage parameters based on a desired trajectory curve. This problem is highly complex due to the fact that the solution space is nonlinear and may contain multiple solutions, while a good quality of learning cannot be obtained by a single neural network approach. Therefore, this paper proposes employing Fourier descriptors to represent trajectory curves in a systematic and normalized form, developing a multi-solution distribution evaluation by random restart local searches (MDE-RRLS) to examine a better solution-space partitioning scheme, utilizing multiple DNNs to learn subspace regions separately, and creating a multi-facet query (MFQuery) to cooperatively predict multiple solutions. The experiments demonstrate that the proposed approach can obtain better or at least competitive outcomes compared to previous work in the literature. Furthermore, to verify the effectiveness and applicability, this paper investigates the design problem of an industrial six-linkage-bar ladle mechanism used in a die-casting system, and the proposed method can obtain several superior design solutions and offer alternatives in a short period of time when faced with redesign requirements. [ABSTRACT FROM AUTHOR]

The propulsion system for an aircraft is one of its most crucial systems; therefore, its reliable work must be ensured during all operational conditions and regimes. Modern materials, techniques and methods are used to ensure this goal; however, there is still room for improvement of this complex system. The proposed manuscript describes a progressive approach for the mechanical properties prediction of the turbine section during jet engine operation using an artificial neural network, and it illustrates its application on a small experimental jet engine. The mechanical properties are predicted based on the measured temperature, pressure and rpm during the jet engine operation, and targets for the artificial neural network are finite element analyses results. The artificial neural network (ANN) is trained using training data from the experimental measurements (temperatures, pressure and rpm) and the results from finite element analyses of the small experimental engine turbine section proposed in the paper. The predicted mechanical stress by ANN achieved high accuracy in comparison to the finite element analyses results, with an error of 1.38% for predicted mechanical stress and correlation coefficients higher than 0.99. Mechanical stress and deformation prediction of the turbine section is a time-consuming process when the finite element method is employed; however, the method with artificial neural network application presented in this paper decreased the solving time significantly. Mechanical structural analyses performed in ANSYS software using finite element modeling take around 30–40 min for one load step. In contrast, the artificial neural network presented in this paper predicts the stress and deformation for one load step in less than 0.00000044 s. [ABSTRACT FROM AUTHOR]

Building automation systems installed in large commercial buildings record sub-hourly measurements from hundreds of sensors. The use of such large datasets are challenging because of missing and erroneous data, which can prevent the development of accurate prediction models of the performance of heating, ventilation, and air-conditioning equipment. The use of the transfer learning (TL) method for building applications attracted researchers to solve the problems created by small and incomplete datasets. This paper verifies the hypothesis that the deep neural network models that are pre-trained for one chiller (called the source chiller) with a small dataset of measurements from July 2013 could be applied successfully, by using TL strategies, for the prediction of the operation performance of another chiller (called the target chiller) with different datasets that were recorded during the cooling season of 2016. Measurements from a university campus are used as a case study. The results show that the initial hypothesis of this paper is confirmed. [ABSTRACT FROM AUTHOR]

Knowledge Question Answering is one of the important research directions in the field of robot intelligence. It is mainly based on background knowledge to analyze users' questions and generate answers. It is one of the important application methods of knowledge graph technology. Compared with the traditional expert system of question and answer, it has the advantage of a large-scale background knowledge base and the traceability and interpretability of the question-answering process. Compared with the current ChatGPT (Chat Generative Pre-trained Transformer) technology, it has advantages in the proprietary segmentation field. Aiming at the problem of the accuracy of existing knowledge question-answering methods being low, this paper studies the method of semantic analysis for knowledge question-answering under the support of a knowledge database, proposes a knowledge question-answering method based on the superposition of multiple neural network models, and conducts experimental verification on the publicly available NLPCC2016KBQA(Knowledge Q&A Tasks in the 2016 Natural Language Processing and Chinese Computing Conference) data set. The experimental results show that the F1 value of this method is higher than that of the baseline model. [ABSTRACT FROM AUTHOR]