Search

This paper presents a neural network predictive control scheme for studying the coagulation process of wastewater treatment in a paper mill. A multi-layer back-propagation neural network is employed to model the nonlinear relationships between the removal rates of pollutants and the chemical dosages, in order to adapt the system to a variety of operating conditions and acquire a more flexible learning ability. The system includes a neural network emulator of the reaction process, a neural network controller, and an optimization procedure based on a performance function that is used to identify desired control inputs. The gradient descent algorithm method is used to realize the optimization procedure. The results indicate that reasonable forecasting and control performances have been achieved through the developed system. [Copyright &y& Elsevier]

Artificial intelligence (AI)-driven fault diagnosis methods are crucial for ensuring rotating machinery's safety and effective operation. The success of most current methods relies on the assumption that sufficient high-quality labeled datasets can be obtained for model training. However, in real-world industrial scenarios, obtaining such datasets is difficult or nearly impossible, thereby hindering the practical implementation of these methods. The integration of virtual modeling and transfer learning offers a powerful approach to meet the above challenge. Abundant virtual data of different fault categories can be acquired in the virtual space with highly flexible and at a low cost, and transfer learning can enhance the practical utility of these virtual data for contributing to the construction of diagnosis models. Therefore, this paper proposes a digital twin-driven partial domain fault diagnosis method based on unlabeled physical data and labeled virtual data. First, a virtual model of rotating machinery is built to generate labeled virtual fault data with enough fault types. Then, an adversarial transfer learning network is developed to leverage the effective knowledge from the virtual and physical data. Meanwhile, a weighting learning module is introduced to reduce the negative effect caused by the redundant fault categories in the virtual space. Finally, the proposed digital twin-driven transfer learning network is trained with the labeled virtual data and unlabeled physical data. Experiments on a light truck transmission system demonstrate that the proposed method achieves satisfactory diagnostic performance even without labeled physical fault data, contributing to the advancement of AI engineering applications. [ABSTRACT FROM AUTHOR]

A new document management system is proposed in this paper. Its kernel is based on a new set of neuro-fuzzy systems of the ART family: FasArt and RFasArt. The first one, FasArt, is used to support a simple Optical Character Recognition (OCR) that inherits fine properties of ART architectures, such as fast and incremental learning, stability and modularity. On the other hand, RFasArt is a new recurrent version of FasArt which efficiently exploits contextual information in the task of logical labeling. The proposed system is extensively tested in two real-world applications, i.e. E-mail of printed business letter and digital library of scientific papers. Experimental results show logical labeling and OCR rates over 90%. The proposed system is better compared to a previous system proposed by the group, where instead of using contextual information in an integrated way, a postprocessing Viterbi-based model was employed. [Copyright &y& Elsevier]

The existing broiler health monitoring technology has problems such as low automation, unstable monitoring results, and low practical value, making it difficult to provide timely and reliable broiler health monitoring results. The broiler sound signal can provide feedback on their health. A widely validated and correct experience is to analyze the frequency of coughs in a segment of broiler sound signal to determine the health of the broiler group. Based on this, in this paper, the authors proposed a new broiler health monitoring technology based on sound detection. The broiler health monitoring problem is cleverly transformed into a multi-classification problem, which can be solved by identifying the sound types in broiler sound signals. Specifically, the audio signal collection system was designed to complete signal collection and preliminary signal filtering. Wiener filtering was used for deep signal filtering. The 60-dimensional sound features with good performance from three aspects, time-frequency domain, Mel-Frequency Cepstral Coefficients, and sparse representation were extracted, and a preliminary data set was created. Min-max normalization was used to align the numerical distribution of the data set, and a high-quality data set was created. Multi-classification models based on different classification algorithms and neural networks were trained, and the best-performing Random Forest was obtained, thus parameter optimization was carried out, and the optimal multi-classification model was obtained, achieving a classification accuracy of 91.14%. The visualization platform was built to process the classification results of the multi-classification model, completing majority voting processing and cough rate calculation, thereby achieving broiler health monitoring. In addition, the definitions of cough rate and prediction accuracy were newly proposed. A large number of experiments have verified the feasibility of the broiler health monitoring technology proposed in this paper, with an average prediction accuracy of 98.97% achieved. • Newly propose a complete broiler health monitoring technology based on sound detection. • Transform the broiler health monitoring problem into the sound type identification problem. • Newly propose an index of cough rate to evaluate the health of broiler groups. • Newly propose a data quality improvement scheme. • Obtain the highest prediction accuracy of broiler health monitoring in this field, currently. [ABSTRACT FROM AUTHOR]

Federated Learning (FL) improves the performance of the training phase of machine learning procedures by distributing the model training to a set of clients and recombining the final models in a server. All clients share the same model, each with a subset of the complete dataset, addressing size issues or privacy concerns. However, having a central server generates a bottleneck and weakens the failure tolerance in truly distributed environments. This work follows the line of applying consensus for FL as a no-centralized approach. Moreover, the paper presents a fully distributed consensus in MAS (multi-agent system) modeling and a new asynchronous consensus in MAS (multi-agent system). The paper also includes some descriptions and tests for implementing such learning algorithms in an actual agent platform, along with simulation results obtained in a case study about electrical production in Australian wind farms. [ABSTRACT FROM AUTHOR]

Artificial intelligence has advanced the applications of sensor-based human motion capture and recognition technology in various engineering fields, such as human–robot collaboration and health monitoring. Deep learning methods can achieve satisfactory recognition results when provided with sufficient labeled data. However, labeling a large dataset is expensive and time-consuming in practical applications. To address this issue, this paper proposes a deep convolutional transformer-based contrastive self-supervised (DCTCSS) model under the bootstrap your own latent (BYOL) framework. The DCTCSS model aims to achieve reliable activity recognition using only a small amount of labeled data. Firstly, a deep convolutional transformer (DCT) model is proposed as the backbone of DCTCSS model, to learn high-level feature representations from unlabeled data in pre-training period. Subsequently, a simple linear classifier is trained with supervised fine-tuning using a limited amount of labeled data to recognize activities. In addition, this paper experimentally formulates a random data augmentation strategy to increase the diversity of input data. The performance of the DCTCSS model is evaluated and compared with several state-of-the-art algorithms on three datasets widely used in daily life, medical monitoring, and intelligent manufacturing. Experimental results show that the DCTCSS model achieves mean F1 scores of 95.64%, 88.39%, and 98.40% on the UCI-HAR, Skoda, and Mhealth datasets, respectively, using only 10% of the labeled data. These results outperform both supervised and unsupervised baseline models. Consequently, the DCTCSS model demonstrates its effectiveness in reducing the dependence on large amounts of labeled data while still achieving competitive activity recognition performance. [ABSTRACT FROM AUTHOR]

Small and medium-sized enterprises (SMEs) play a vital role in economic and social development. Among them, scientific and technological innovation ability and investment choice ability are the key factors to evaluate the competitiveness of SMEs. Aiming at the capability evaluation of SMEs, this paper designs a multi-attribute decision-making (MADM) method with interval type-2 trapezoidal fuzzy information measure, which is driven by trigonometric function. Interval type-2 trapezoidal fuzzy numbers (IT2TrFNs) help us to model fuzzy information. Firstly, this paper discusses the three main concepts of entropy, similarity and cross-entropy, and introduces their properties in IT2TrFNs. Secondly, the information measurement formulas related to IT2TrFNs are constructed by using trigonometric functions: IT2TrF trigonometric information entropy, IT2TrF trigonometric similarity measure and IT2TrF trigonometric cross-entropy. They are used to measure the ambiguity and similarity of decision information. Then, taking into account the interdependence between the different attributes, we use entropy and cross-entropy to determine the unknown attribute weights. IT2TrF trigonometric similarity measure is utilized to determine the optimal alternative. Finally, the numerical example is given to evaluate the scientific and technological innovation ability and investment choice ability of SMEs. The feasibility and effectiveness of the proposed MADM method are verified by comparative analysis. • Axiomatic definitions of information measures of IT2TrFS are introduced. • Trigonometric information measure formulas for IT2TrFS are constructed. • The relationship among the information measures is discussed. • A MADM method is developed. • Two examples are given to illustrate the behavior of the proposed method. [ABSTRACT FROM AUTHOR]

Reinforcement learning-based methods have addressed production scheduling problems with flexible processing constraints. However, delayed rewards arise due to the dynamic arrival of jobs and transportation constraints between two successive operations. The flow time of operations can only be determined after processing due to the possibility that the solution for job sequencing may change if new operations are inserted in dynamic environments. Job sequencing is often overlooked in single-agent-based scheduling methods. The lack of information sharing between multiple agents necessitates that researchers manually design reward functions to fit the relationship between optimization objectives and rewards, thereby reducing the accuracy of the learned policies. Thus, this paper proposes a multi-agent-based scheduling optimization framework that facilitates collaboration between the agents of both machines and jobs to address dynamic flexible job-shop scheduling problems (DFJSP) with transportation time constraints. Then, this paper formulates the Partial Observation Markov Decision Process and constructs a reward-sharing mechanism to tackle the delayed reward issue and facilitate policy learning. Finally, we develop an improved multi-agent dueling double deep Q network algorithm to optimize scheduling policy during long-term training. The results show that, compared with the state-of-the-art methods, the proposed method efficiently shortens the weighted flow time under the trained and unseen scenarios. Additionally, the case study results demonstrate its efficiency and responsiveness. It indicates that the proposed method efficiently addresses production scheduling problems with complex constraints, including the insertion of jobs, transportation time constraints, and flexible processing routes. [ABSTRACT FROM AUTHOR]

Carbon Fiber Reinforced Polymer (CFRP) laminates, prized for their lightweight and high stiffness, are extensively used in aerospace and maritime applications. Bolted joints play a crucial role in connecting these laminates. However, manufacturing variations arise during the assembly process, impacting performance due to material-related factors. Predicting the assembly stress fields of Carbon Fiber Reinforced Polymer bolted joints is of great significance in design optimization, manufacturing process control, and structural health monitoring. The currently prevalent finite element analysis methods incur extremely high computational costs, failing to meet the requirements for real-time prediction of the assembly and multiparametric design of composite bolted joints. Proposing a methodological framework for rapidly predicting the assembly physical field is necessary. This paper introduces a stress prediction framework to enhance analysis and aid material parameter design. The framework is inspired by image processing and artificial intelligence drawing by analogizing the computed physical field results to the generated images. Therefore, the Bolted Tightening Generative Adversarial Network (BT-GAN), a cascaded generative model, is proposed in this paper to predict stress fields of the composite bolted joints during assembly. The model starts with data augmentation of the stress filed results from the finite element analysis in a super-resolution network, which realizes an integral interpolation mapping from coarse-grid to fine-grid results. Then, the results of the data enhancement are fed into the subsequent conditional generative adversarial network for learning. Similar to the text-guided image generation approach, the network learns to understand the physical mapping relationships between different parameters and assembly stress fields. Moreover, the network achieves higher accuracy in stress field prediction by extraction the understanding of multi-scale features through the skip connection and the attention mechanism. This method effectively learns the physical mapping relationship between multiple parameters and the stress field, applying a graph generation approach to end-to-end predictions of the field. Compared to the results of finite element analysis from the coarse-grid, the Structure Similarity Index Measure (SSIM) of the cascaded generative network proposed in this paper has been improved from 0.584 to 0.962 and the Peak Signal-to-Noise Ratio (PSNR) metric has been increased from 17.3 dB to 58.2 dB. What's more, the mean relative error on the maximum values of the stress field has reached 6.9%. The trained model takes only 6.1s to complete a single prediction, significantly improving the prediction efficiency compared with finite element analysis. It is compared with the other networks commonly used for physical field prediction and shows improvement in the metrics proposed in the article. By constructing such an end-to-end stress field prediction framework during assembly, efficient forecasting for the assembly of composite bolted joints can be achieved. This is advantageous for the digital twin modeling of the assembly lines and the effective control of assembly quality, providing a powerful tool for assembly design and analysis. [Display omitted] [ABSTRACT FROM AUTHOR]

In Turkey, the transportation industry's greenhouse gas (GHG) emissions increased by 147.1% between 1990 and 2019. Today, this transportation industry (i.e., freight and passenger) is among the significant contributors to greenhouse gas emissions in Turkey's megacities. Moreover, 65.43% of short-distance trips between home to work and home to school have been made by private automobiles in Istanbul and increasing concerns about environmental pollution have led practitioners to seek practical, robust, and effective solutions to reduce GHG emissions. Shared electric scooters have rapidly become popular for end-users and practitioners in megacities, depending on their valuable advantages. However, the rapid spread of micro-mobility, characterized by e-scooters, has also raised questions about this system's sustainability, suitability, and applicability. Thus, there are some critical and noteworthy gaps in this issue. This study investigates the factors affecting the suitable e-scooter selection for a sustainable urban transport system. Besides, it aims to develop a methodological framework for assessing the available e-scooter alternatives. For this purpose, a novel negotiation approach, a new form of the Delphi technique, was developed with the help of Fermatean fuzzy sets to identify the influential criteria. Also, the current paper presents a consensus-based MULTIMOORA (Multiple Objective Optimization on the basis of Ratio Analysis plus Full Multiplicative Form) decision-making model based on Fermatean fuzzy sets to address the appraisal problem concerning e-scooter selection. The current paper indicated that economic measures such as acquisition price and upkeep costs affect the e-scooter selection processes. In addition, an optimization model based on cross-entropy and dispersion measures is utilized to compute criteria weights. It highlighted that the costs of e-scooters are still high, and operators consider these criteria instead of the technical and operational features of the e-scooters. Finally, the validity check executed to test the robustness and trustworthiness of the model affirms the model's firmness and trustworthiness. [ABSTRACT FROM AUTHOR]

Heterogeneity and uncertainty in a composite microstructure lead to either computational bottlenecks if modeled rigorously or to solution inaccuracies in the stress field and failure predictions if approximated. Although methods suitable for analyzing arbitrary and non-linear microstructures exist, their computational cost makes them impractical to use in large-scale structural analysis. Surrogate models or Reduced Order Models (ROMs) commonly enhance efficiencies but are typically calibrated with a single microstructure. Homogenization methods, such as the Mori–Tanaka method, offer rapid homogenization for a wide range of constituent properties. However, simplifying assumptions, like stress and strain averaging in phases, render the consideration of both deterministic and stochastic variations in microstructure infeasible. This paper illustrates a transformer neural network architecture that captures the knowledge of various microstructures and constituents, enabling it to function as a computationally efficient homogenization surrogate model. Given an image or an abstraction of an arbitrary composite microstructure of linearly elastic fibers in an elastoplastic matrix, the transformer network predicts the history-dependent, non-linear, and homogenized stress–strain response. Two methods for encoding microstructure features were tested: calculating two-point statistics using Principal Component Analysis (PCA) for dimensionality reduction and employing an autoencoder with a Convolutional Neural Network (CNN). Both methods accurately predict the homogenized material response. The developed transformer neural network offers an efficient means for microstructure-to-property translation, generalizable and extendable to a variety of microstructures. The paper describes the network architecture, training and testing data generation, and performance under cycling and random loadings. [ABSTRACT FROM AUTHOR]

The reliability of bolt connections significantly impacts the operational state and lifespan of industrial equipment. Vision-based noncontact methods exhibit high efficiency in bolt loosening detection. However, limited image features hinder measurement accuracy. To improve bolt loosening detection performance, this paper proposes a novel deep learning backbone, the high-resolution cross-scale transformer, to extract high precision keypoints for bolt three-dimensional model construction. Simultaneously, a monocular vision measurement model is established to get the bolt exposed length and evaluate the connection loosening state. The proposed backbone hybridizes the advantages of high-resolution architecture and transformer, realizing global information aggregation and fine-grained image details. A simplified module, dual-scale multi-head self-attention, is designed to reduce the computational redundancy caused by the implementation of high-resolution multi-branch architecture. In the experiment section, the high-resolution cross-scale transformer outperforms other keypoint detection baselines, achieving the top one performance with 91.6 average precision and 84.9 average recall. The monocular vision measurement model realizes a 0.053 mm error with a 0.028 mm standard deviation, satisfying the industrial implementation requirement. Additionally, the model is tested on different industrial situations and an additional outside dataset, indicating the model's robustness and actual environment adaptability. • A monocular vision measurement method for bolt loosening detection is proposed. • It is the first attempt to introduce the transformer mechanism in bolt keypoint detection. • A new keypoint detection backbone is proposed in this paper for bolt feature extraction. • The 3D exposed length of bolts is calculated with a monocular vision system. • The bolt loosening detection method is validated. [ABSTRACT FROM AUTHOR]

Since 2000, the field of machine scheduling—an integral part of computer science and operations research—has seen significant advancements. This paper explores the dynamic progression of machine scheduling, offering a detailed overview of its past advancements, current practices, and future directions. Anchoring the research in robust data analysis and statistical methodologies, the paper reveals the subtle yet impactful changes that have characterized the field in the last two decades. It examines the prominence of various scheduling problems, identifies leading research journals, and highlights international contributions and collaborations, thereby offering a thorough guide to the machine scheduling ecosystem. The study delves into specific problem characteristics and assesses performance criteria and solution methods to provide an in-depth view of the field's multifaceted nature. Ultimately, this paper captures the essence of machine scheduling's evolution and suggests new paths for exploration. The insights gained contribute significantly to academic discussions and equip practitioners with a comprehensive understanding of the dynamic landscape of machine scheduling. [ABSTRACT FROM AUTHOR]

This paper delivers an exhaustive analysis of the fusion of multi-sensor technologies, including traditional sensors such as cameras, Light Detection and Ranging(LiDAR), Radio Detection and Ranging(RADAR), and ultrasonic sensors, with Artificial Intelligence(AI) powered methodologies in obstacle detection for Autonomous Vehicles(AVs). With the growing momentum in AVs adoption, a heightened need exists for versatile and resilient obstacle detection systems. Our research delves into study of literatures, where proposed approaches assimilate data from this diverse sensor suite, integrated through Deep Learning(DL) techniques, to refine AV performance. Recent advancements and prevailing challenges within the domain are thoroughly examined, with particular focus on the integration of sensor fusion techniques, the facilitation of real-time processing via edge and fog computing, and the implementation of advanced artificial intelligence architectures, including Convolutional Neural Networks(CNNs), Recurrent Neural Networks(RNNs), and Generative Adversarial Networks(GANs), to enhance data interpretation efficacy. In conclusion, the paper underscores the critical contribution of multi-sensor arrays and deep learning in enhancing the safety and reliability of autonomous vehicles, offering significant perspectives for future research and technological progress. [ABSTRACT FROM AUTHOR]

Current failure prediction methods of bearings have less uncertainty analysis with interpretability, less correlation analysis between degradation characteristics and prediction error. Moreover, there are multiple degradation stages in entire life cycle and prediction performance cannot meet practical demands. Therefore, this paper proposes a new approach for failure prediction of bearings. The change point detection method achieves multi-stage division of degradation data. The improved hybrid deep forest with best dissimilarity sequence (BDS) is studied and a new pretrained algorithm with pruning operation is developed. The convergence theorem is proved. A novel multi-stage failure prediction algorithm based on improved hybrid deep forest, hypothesis testing and interpretability analysis, is developed to get better prediction result. The time complexity of proposed algorithm is analyzed. The datasets of NASA and FEMTO-ST institute are utilized and experimental results show that: 1) Our approach with model interpretability has better prediction performances than support vector machine (SVR), recurrent neural network (RNN), long short-term memory (LSTM), and deep forest (DF); 2) The non-normal distribution characteristics, monotonic degradation trend and effect size of multiple stages are analyzed based on hypothesis testing methods; 3) The positive and inverse relation analysis achieves the correlation interpretability between multi-stage degradation characteristics and failure prediction results. • EWMA, CUSUM, and K-means clustering are used to obtain real change points for multi-stage division. • An improved hybrid deep forest model with BDS is presented to improve prediction performance. • This paper proposes a new pretrained algorithm to achieve a better tradeoff between accuracy and runtime cost. • A multi-stage failure prediction algorithm with model interpretability is developed. • Hypothesis testing and correlation analysis are utilized to enhance the interpretability of degradation characteristics. [ABSTRACT FROM AUTHOR]

Multi-target stance detection is the detection of the stance of multiple targets in text. Currently, most multi-target stance detection methods only detect the stance of two targets individually and do not make the two targets complement each other to take full advantage of the relevant semantic information between the two targets. In this paper, we propose a comparative learning based stance agreement detection framework. We applied contrastive learning to stance agreement detection, it enabled the model to learn more information about the features of the target and to strengthen the links between the semantic information of the targets so that they assist each other in stance detection. In addition, we fine-tuned a new model as our encoder to more fully exploit the semantic information between hidden contexts. We also apply joint training as a multi-task learning approach, allowing models to share domain-specific information based on the dataset. By comparing different methods, experimental results show that our method achieves state-of-the-art results on multi-target benchmark datasets. In the concluding sections of our paper, we conducted error analysis experiments on the proposed methodology, elucidating its inherent limitations and furnishing invaluable insights conducive to future enhancements. [ABSTRACT FROM AUTHOR]

Quality function deployment (QFD) is an effective method to convert customer requirements (CRs) into design requirements (DRs) by constructing house of quality (HOQ). With the rapid growth of the e-commerce market, it is a new challenge to utilize the available online reviews to facilitate the implementation of QFD. Therefore, this paper proposes a novel QFD model from the perspective of group decision making (GDM) and social network analysis (SNA), then applies the proposed model to product design under Chinese e-commerce scene. Firstly, this paper extracts CRs from online reviews on e-commerce platforms, and the initial HOQs can be constructed. Then a bilateral negotiation GDM method based on SNA is carried out to generate a consensus-based HOQ, and therefore the final priorities of DRs can be obtained. Finally, a case study is provided to illustrate the applicability, and some discussions and comparative analysis are also conducted. The result indicates that the proposed method can generate effective and stable results for QFD implementation in real-world e-commerce scenario. [ABSTRACT FROM AUTHOR]

In recent years, decomposition-based combination models have been widely used in wind power prediction. This type of method decomposes the highly volatile wind power into some relatively smooth subsequences, which reduces the difficulty of modeling. However, this might use information from future data in advance, creating the illusion of high prediction accuracy. Therefore, this paper proposes a wind power ultra-short-term prediction model based on fixed scale dual mode decomposition (FSDMD) and deep learning networks. First, the wind power series after fixed scale blocking is decomposed using ensemble empirical mode decomposition (EEMD), and use the improved variational mode decomposition (VMD) based on Spearman rank order correlation coefficient (SROCC) to decompose the obtained high-frequency components twice. Then, the appropriate mode components were selected by calculating the SROCC and experimental analysis, and combined with the convolutional neural network (CNN) and the bidirectional long short-term memory (BiLSTM) network to train the model. Finally, the historical data of wind turbines in a wind farm in Northwest China is used for example verification, and the comparison with other models in the two scenarios of sufficient and insufficient features. The results show that the proposed FSDMD–CNN–BiLSTM model has high prediction accuracy in both scenarios. Especially in the scenario of insufficient features, compared with CNN-BiLSTM model, RMSE, MAE and MAPE are reduced by 8.20,14.24 and 0.15, respectively. In addition, this paper verifies that mode decomposition can improve the performance of prediction model without using future features, which provides ideas for solving similar problems. [ABSTRACT FROM AUTHOR]

This paper proposes a new approach for reconstructing high-resolution images from low-resolution inputs using Denoising Diffusion Probabilistic Models (DDPMs). Existing DDPMs, while promising, face two issues: one is detail discrepancies due to the uncertain degradation factors in low-resolution images, the other is slow sampling speeds. To address these, a multimodal approach based on reversible guidance and cyclical knowledge distillation (MRKD) is introduced. This method is based on the concept where prior and posterior probabilities can assist in comprehending and predicting future events from available data and information. In the MRKD method, text and image information are separately encoded, and novel constraints are applied on prior and posterior distributions, optimizing the detailed features of the reconstructed image. In addition, due to the uncertainty of degradation factors in low-resolution images, a 'one-to-many' mapping issue arises in single-image super-resolution tasks. In response to this, the paper redefines constraints on the posterior distribution using the log-likelihood. Specifically, the Bayesian transformation of the input and output of the observation model is employed to effectively guide the diffusion process. To boost the slow sampling speed of DDPM, a cyclical knowledge distillation strategy is proposed, allowing iterative transfer of learned parameters from a high-step DDPM to a low-step model, thereby accelerating the sampling process while preserving image quality. The experimental results demonstrate that these strategies enable the model to effectively comprehend the high-level semantics and contextual information within images. Additionally, they address challenges associated with mode collapse, the loss of high-frequency details, and the complexities of long-tail data. [ABSTRACT FROM AUTHOR]

The load data features of some electricity-theft consumers during the theft period are similar to those of normal consumers, making these electricity-theft consumers outliers from the cluster of electricity-theft. The current classification method, which uses the mean value to determine the cluster centers, is vulnerable to the influence of outliers. Therefore, this paper proposes a self-decision ant colony clustering algorithm for electricity theft detection method that is targeted to self-decision which samples are used to update the cluster centers. The method constructs a dynamic weighting approach to determine the cluster centers based on the idea of Backpropagation, and updates the weights of each sample in the clusters to reflect the different importance of different samples, thus reducing the influence of outlier samples. A new activation function, Odd, is proposed to enhance the ability of the proposed method to solve linearly indistinguishable problems. A self-decision dropout mechanism is proposed which evolves the mechanism of randomly stopping the work of samples in clusters into a targeted and self-decision mechanism that stops the work of redundant or non-active samples as well as improves the contribution of outlier samples with positive effects. In this paper, the proposed method is tested by the electricity consumption data provided by the State Grid Corporation of China (SGCC) and the Smart* Data Set for Sustainability (SDSS) provided by the UMass Trace Repository, and the experimental results show that the proposed method effectively solves the above problems with higher detection accuracy, it has certain advantages over other current studies. [ABSTRACT FROM AUTHOR]

Accurate detection of pavement markings at the pixel level is crucial for enhancing traffic safety. The majority of current advanced deep-learning networks predominantly focus on localized features, neglecting the global context of pavement image. Such networks often result in discontinuous segmentation outcomes and suboptimal recovery of local details. In this paper, a robust model named C-Transformer is proposed to provide an effective solution to this challenge. The contributions of this paper primarily involve two aspects. Firstly, the proposed C-Transformer is designed to succinctly integrate convolution operations and self-attention, facilitating a comprehensive understanding of essential features. Secondly, an efficient Feed-Forward Network called Inverse Residual Feed-Forward Network is also proposed in this paper and deployed in C-Transformer to improve latent representations. Experimental results demonstrate that, compared to other state-of-the-art networks, the proposed C-Transformer achieves a performance enhancement of 0.93% in F-measure and a 1.64% improvement in Intersection-Over-Union. In particular, the robustness and effectiveness of the C-Transformer in accurate pavement marking detection are proved through field test results. This paper illustrates the feasibility of employing a hybrid Convolutional neural network-Transformer-based network for automatic robust pavement marking detection under noisy conditions. [ABSTRACT FROM AUTHOR]

This paper proposes a new linguistic model called Linguistic q-Rung Orthopair fuzzy Z-number (LqROFZN), which combines the advantages of linguistic variables, Z-number and q-Rung Orthopair Fuzzy numbers. It can be used as a powerful tool for uncertain decision-making, which can effectively improve the accuracy and reliability of the decision-making results, and has a notable application prospect for the fields of information decision-making, risk assessment, diagnosis and so on. In this paper, firstly, the definition of LqROFZN and its operational rules are given, a new distance measure and the concept of entropy are given under LqROFZN, and the entropy of LqROFZN can assess the credibility situation of LqROFZN. Next, two aggregation operators under LqROFZN are given, namely the Linguistic q-Rung Orthopair fuzzy Z-number weighted aggregation (LqROFZWA) operator and the Linguistic q-Rung Orthopair fuzzy Z-number weighted Geometric aggregation (LqROFZWGA) operator. Finally, the MCDM method under LqROFZN is given and the credibility of the evaluation results is assessed using the entropy of LqROFZN. In a set of actual airline aircraft selection cases, the feasibility and advantages of the proposed method are verified through comparative analysis with other methods. [ABSTRACT FROM AUTHOR]

Numerous Artificial Intelligence (AI) solutions are available for achieving thermal comfort. They were either trained with limited datasets or using personalized training with limited field studies. This work assessed the model that used the ASHRAE multiple databases as the shallow supervised learning dataset for an Artificial Neural Network (ANN) based controller suitable for the residential dwellings' node. The learning accuracy can be increased to 96.1%. This paper presented the field studies to show the model performances for the common UK dwellings: the prior 1970s, the new, modular, refurbished, and the use of new materials to improve indoor thermal performance. The result shows that the model was able to perform in different environments and able to acknowledge adaptive human comfort. This was shown by the ability to represent 98.90% of the ASHRAE Standard 55 data, 6.06% improvement from the previous research. As a result, the broader comfort zone acknowledgement can lead to energy saving whilst maintaining comfort by the possibility of lowering the temperature set point. This study also proves that further energy savings can be acquired from the occupants' presence, scheduling, and activities. These factors can increase the comfort probability to more than 10%. [Display omitted] • This paper addresses the gap between the physiology and the psychology thermal comfort approach, dominated by AI solutions. • The work shows a wider comfort zone which has been identified to become progressively narrower over the past several decades. • The field studies represent major UK-dwelling cases that weren't addressed in the previous Artificial Intelligence approach. • The occupant presence and scheduling can contribute to more than a 10% increase in comfort which impacts energy saving. • This work highlights the possibility of achieving indoor thermal comfort with less energy for more sustainable dwellings. [ABSTRACT FROM AUTHOR]

Emotion recognition is an aspect of human-computer interaction, affective computing, and social robotics. Conventional unimodal approaches for emotion recognition, depending on single data sources such as facial expressions or speech signals often fall short in capturing the complexity and context-dependent nature of emotions. Multimodal Emotion Recognition (MER), which integrates information from multiple modalities, has emerged as a promising solution to overcome these limitations. In recent years, Transformers-based approaches have gathered significant attention in the fields of natural language processing and computer vision, highlighting their ability to capture long-range dependencies and semantic representations. These models have rapidly achieved the MER state-of-the-art. However, current survey papers that cover MER lack a specific focus on Transformer-based techniques. To bridge this research gap, this review paper provides a comprehensive investigation of Transformers-based approaches for MER. It explores various Transformer architectures and proposes several scenarios for using Transformers at different stages of MER process. In addition, it examines datasets suitable for MER, discusses fusion mechanisms, and introduces novel taxonomies in both MER and Transformer technologies. The review also addresses challenges and future research directions. Through this review, we aim to provide researchers with an inclusive understanding of the current state-of-the-art in Transformers-based approaches for MER, paving the way for further advancements in this rapidly developing field. • First specialized survey in transformer-based Multimodal Emotion Recognition. • Organized taxonomy of fusion techniques based on discerning criteria. • Transformers taxonomy categorized by structural and operational distinctions. • Diverse scenarios of applying transformers at different stages of MER process. • Meticulous analysis identifies trends and challenges across multimodal datasets. [ABSTRACT FROM AUTHOR]

Gathering pipelines are one of the key upstream infrastructures in the gas industry that link production well to the processing plant. Leak detection is critical for ensuring the safety of pipeline transmission. The detection of small leakage in gathering pipelines consistently poses a formidable challenge. In this paper, a process model is built based on health data of supervisory control and data acquisition system from the actual operating pipeline. In the model structure, the convolutional neural network is used to extract the spatial features, the bi-directional long short-term memory is used to extract the temporal features, and the attention mechanism is employed to allocate the model's attention resources reasonably. Next, the residual between the entity pipeline's output data and the process model's output data is used as a monitoring indicator of the operating state of the pipeline. A clustering-based boundary determination method is proposed to recognize the centroid of normal and small leak conditions, and pipeline leak detection is performed by the Euclidean distance between the monitoring indicator and the centroid. This paper explores the feasibility of fast modeling and leak detection with limited hardware. Field tests for the validation of the proposed methods were implemented in two in-service natural gas gathering pipeline. The experimental results demonstrate that the proposed method significantly enhances the detection performance of small-size leak. The leak detection rates of 94.06% and 92.16% evinces the potency of the proposed method applied in the leak detection of gathering pipelines across diverse real-world scenarios. [ABSTRACT FROM AUTHOR]

The paper investigates the application of machine learning (ML) for voltage sag source localization (VSSL) in electrical power systems. To overcome feature-selection challenges for traditional ML methods and provide more meaningful sequential features for deep learning methods, the paper proposes three time-sample-based feature forms, and evaluates an existing feature form. The effectiveness of these feature forms is assessed using k-means clustering with k = 2 referred to as downstream and upstream classes, according to the direction of voltage sag origins. Through extensive voltage sag simulations, including noises in a regional electrical power network, k-means identifies a sequence involving the multiplication of positive-sequence current magnitude with the sine of its angle as the most prominent feature form. The study develops further traditional ML methods such as decision trees (DT), support vector machine (SVM), random forest (RF), k-nearest neighbor (KNN), an ensemble learning (EL), and a designed one-dimensional convolutional neural network (1D-CNN). The results found that the combination of 1D-CNN or SVM with the most prominent feature achieved the highest accuracies of 99.37% and 99.13%, respectively, with acceptable/fast prediction times, enhancing VSSL. The exceptional performance of the CNN was also approved by field measurements in a real power network. However, selecting the best ML methods for deployment requires a trade-off between accuracy and real-time implementation requirements. The research findings benefit network operators, large factory owners, and renewable energy park producers. They enable preventive maintenance, reduce equipment downtime/damage in industry and electrical power systems, mitigate financial losses, and facilitate the assignment of power-quality penalties to responsible parties. • Comprehensive study on enhanced voltage sag source localization assisted by ML. • Proposing three new time sample-based feature forms, effective for ML methods. • Identifying the most influential feature form (form 4) utilizing k-means clustering. • Developing diverse supervised models, including a designed one-dimensional CNN. • CNN-Feature form 4 achieved 99.37% accuracy with an acceptable prediction speed. [ABSTRACT FROM AUTHOR]

In visual tracking, the Transformer architecture is widely used because it can capture the global dependencies of sequence data without inductive bias. However, the attention mechanism of Transformer will bring ultra-high computational complexity and space occupancy, so that the tracking task cannot meet the real-time requirements. In this paper, we explore a sparsity region-aware attention mechanism. The sparse attention mechanism retains the regions with semantic relevance, and performs fine-grained attention calculation in this region. In the region-aware attention mechanism, a DropKey technique is introduced to reduce model over-fitting and improve the generalization ability of the model. Using region-aware attention as the basic building block, we design a dynamic region-aware Transformer backbone for visual tracking. This backbone network can effectively reduce the computational complexity while exploring global context dependencies. Based on the region-aware Transformer backbone network, this paper proposes a dynamic region-aware Transformer backbone visual tracking algorithm, which uses an optimization based model predictor to fully fuse object appearance and background information, so as to achieve more robust object tracking. The proposed tracker is trained in an end-to-end manner and experimentally evaluated on eight tracking benchmarks. Experimental results show that the algorithm has good tracking performance, especially in the application of unmanned aerial vehicle (UAV) tracking, our proposed tracker achieves an area under curve (AUC) score of 66.5% on the UAV123 dataset. Code is available at https://github.com/YSGFF/RTDiMP. [ABSTRACT FROM AUTHOR]

Pipe wall-thinning is a phenomenon whereby the thickness of pipes in a nuclear power plant decreases over time owing to extended operational years. This thickness reduction is caused by various long-term thermal aging mechanisms such as Flow-Accelerated Corrosion, Liquid Droplet Impingement Erosion, cavitation, and flashing. Reducing the thickness of the secondary system pipes to the point of rupture can lead to severe human casualties and significant economic losses. Consequently, domestic power plant operators regularly manage the power plant pipes. Ongoing research focuses on the identification and management of pipe wall-thinning. However, previous studies have encountered problems in accurately judging the decrease in pipe wall-thinning in the presence of noise. To overcome this, Convolutional Neural Network (CNN) models based on image feature analysis have been used. This approach allows for the differentiation of pipe wall-thinning feature from small-sized noise in a single image. However, there were difficulties in making accurate judgments for large-sized noise that resembled the feature of pipe wall-thinning. This paper aims to analyze the limitations of the current pipe wall-thinning evaluation methods and to achieve accurate pipe wall-thinning discrimination through time-series analysis of continuous pipe wall-thinning data. The proposed method employs a Convolutional Recurrent Neural Network (CRNN) model, integrating the Recurrent Neural Network(RNN) model with the CNN model. The image feature of the pipes, extracted using CNN, are utilized as inputs for the RNN. This enables the observation of how the image features of the pipes change over time. This feature differentiates from the time-series feature of noise that occurs suddenly. Through this method, the paper proposes a new approach for effectively identifying the gradual decrease in pipe wall-thinning, enabling precise assessment of pipe wall-thinning progression. [ABSTRACT FROM AUTHOR]

This paper focuses on action recognition tasks oriented to the field of human–robot interaction, which is one of the major challenges in the robotic video understanding field. Previous approaches focus on designing temporal models, lack the ability to capture motion information and build contextual correlation models. This may result in robots being unable to effectively understand long-term video actions. To solve these two problems, this paper propose a novel video understanding framework including: an Adaptive Temporal Sensitivity and Motion Capture Network (ATSMC-Net) and a contextual scene reasoning module called Knowledge Function Graph Module (KFG-Module). The proposed ATSMC-Net can adaptively adjust the frame-level and pixel-level sensitive regions of temporal features to effectively capture motion information. To fuse contextual scene information for cross-temporal inference, the KFG-Module is introduced to achieve fine-grained video understanding based on the relationship between objects and actions. We evaluate the method using three public video understanding benchmarks, including Something-Something-V1&V2 and HMDB51. In addition, we present a dataset with real-world application scenarios of human–robot interactions to verify the effectiveness of our approach on mobile robots. The experimental results show that the proposed method can significantly improve the video understanding of the robots. [ABSTRACT FROM AUTHOR]

Due to the non-homology problem and the simple structural characteristics, a grey prediction model will have defects in modeling. In this paper, the structure of the GM (1 , 1 , x (1) ) model is deformed, and additional parameters are added. A novel four-parameter grey prediction model NFGM(1,1) is established to avoid the non-homology problem. The accumulation order of the NFGM(1,1) model is optimized to enhance its performance. This paper first introduces a nonlinear term and a linear term into the GM (1 , 1 , x (1) ) model to compensate for its structural defects, which can enhance the accuracy of the model in modeling complex modeling sequences. Secondly, a simplified basic formula of the model is proposed to estimate its parameters and iteratively establish the model, which can avoid the problem of non-homologous errors during modeling. Then a novel four-parameter grey prediction model NFGM(1,1) is constructed. Thirdly, the unbiasedness of NFGM(1,1) is proved and verified by matrix theory. Fourthly, by optimizing the order of the NFGM(1,1) model, the model is more flexible and adjustable, and a novel fractional-order four-parameter grey prediction model FNFGM(1,1) can be obtained. Finally, the FNFGM(1,1) model is applied to the prediction of natural gas production in China. The model results show that the FNFGM(1,1) model exhibits superior performance compared to the NFGM(1,1), TWGM(1,1), TDGM(1,1), DGM(1,1), and GM(1,1) models, with the mean relative simulation/prediction/comprehensive percentage errors of 0.92%/1.42%/1.07%, respectively. According to the predicted results, China's natural gas production will reach 3542.9 × 108 m3 in 2027 and some relevant policy recommendations are put forwarded. • On the basis of GM (1 , 1 , x (1) ) , a nonlinear term and a linear term are introduced to expand the model structure, and a novel four-parameter grey prediction model is proposed. • In order to avoid the non-homology problem of the differential equation and difference equation in traditional modeling, this paper uses the simplified basic formula of the model to estimate parameters, and does not directly derive the time response, but directly uses the iterative recurrence method to model. • The new model is proved to be unbiased by the matrix theory method and verified by arithmetic examples. • According to the objective function and constraints of fractional-order solving, PSO algorithm is used to optimize the order of the new model, which makes the model parameters changeable and improves the model performance. • The comprehensive performance of the new model is verified by a case study, the new model is applied to forecast China's natural gas production in the context of Xi Jinping's new era, and the results show that the new model has better accuracy, and the results obtained can help the government to formulate relevant policies. [ABSTRACT FROM AUTHOR]

With the deepening of modernization and industrialization, the issues of water pollution and scarcity have become more pressing. To address these issues, many wastewater treatment factories have been built to improve the reuse of water resources. However, the control of the wastewater treatment process (WWTP) is a complex task due to the highly nonlinear and strongly coupled nature. It is challenging to develop the accurate mechanism models of the wastewater treatment system. The improvement of the efficiency for the WWTP is crucial to safeguard the urban ecological environment. In this paper, adaptive critic with weight allocation (ACWA) is developed to address the optimal control problem in the WWTP. Different from the previous methods of the WWTP, system modeling is not adopted in this paper, which meets the actual physical background of the wastewater treatment system to a great extent. In addition, the actor-critic algorithm in reinforcement learning is used as the basic structure in the ACWA. It is worth noting that a novel weighted action-value function and the advantage function are introduced in the weight updating process of the action network and the critic network. The experimental results show that the control accuracy of the ACWA is greatly improved compared with the previous control methods. [ABSTRACT FROM AUTHOR]

Over the past decades, deep learning techniques have attracted increased attention from various research and industrial domains aligned with the development of Industry Internet-of-Things(IIoT). Specifically, with the advantage of data-driven methods, industrial organizations are seeking novel proactive strategies supported by analytic models to guarantee the quality of their production by observing degradation or predicting failure ahead of the occurrence of the component or asset. Predictive strategies are expected to promise the influence of unnecessary maintenance interruptions and mitigate the consequence of that, hence, extending the remaining useful life of products. This paper conducts a survey of the utilization of deep learning technologies on engineering applications where they provide satisfactory solutions with respect to specific data types or input signals. 106 primary papers are reviewed on deep learning–driven approaches which mainly explore five of the most popular architectures in the application of predictive maintenance. The main content of this paper summarizes the common advantages of each architecture and, accordingly, points out their limitations, as well as describes the application scopes of fully connected deep neural networks, convolutional neural networks, stacked autoencoders, deep belief networks, and deep recurrent neural networks. Based on the technique discussion for each of them, we intend to provide a comprehensive understanding and guidance of the appropriate usage of deep learning architectures to devise an effective predictive maintenance strategy for the scientific and industrial developers whose expertise lies in the prior domain knowledge of multi-source isomerization data. Moreover, the main content demonstrated the summarization of the decisive factor by which the incremental stages of the approaches were determined, fundamentally including the dataset specification, feature extraction, and the integration of deep learning approaches. [ABSTRACT FROM AUTHOR]

Fruits and vegetables are major sources of nutrients for the majority of the population across the globe. With the rapid increase in population, the objectives of the future agro-industry are to reduce product loss while increasing product quality and productivity considerably. Consequently, farmers need to be assisted with cutting-edge technologies for sustainable, eco-friendly, and efficient farming. Smart farming for early disease recognition and control is the current hot-spot research objective in the fruitage domain. The precision agriculture era has been revolutionized by federating cutting-edge technologies like machine learning, deep learning, and, the Internet-of-Things. However, the existing studies focused on the impact of individual technology on single or multiple cultivars of edible fruits or vegetables. Limited areas of the fruitage disease remain explored, necessitating further investigation into the research gaps and challenges identified for implementing the smart practices in real-field farmlands. In this paper, a comprehensive survey of recent advancements in fruit and vegetable disease identification and classification is presented. The technology-wise state-of-the-art findings, gaps, challenges, and future opportunities for fruitage disease recognition have been presented, covering 99 research articles. Moreover, the corpus of publicly available fruit and vegetable datasets has been investigated, with the existing gaps, improvements, and future requirements. The research paper concludes with challenges and a future outlook that promises to be a very significant and valuable resource for researchers working in the area of agronomic disease monitoring. [ABSTRACT FROM AUTHOR]

The advancement of deep learning and neural networks has led to the widespread adoption of neural word embeddings as a prominent lexical representation method in natural language processing. With the help of the neural language model trained by the contextual information of large scale text, the neural word embedding obtained by the neural language model captures more semantic correlation in the semantic space, while ignoring the semantic similarity. It will incur high computational cost and time costs during the training process of the model. To better inject semantic similarity into the distribution space and reduce time cost, we perform post processing learning of neural word embeddings using deep metric learning. This paper proposes a lexical enhancement method based on flexible margins and multiple samples learning. In this method, we embed the lexical entailment constraint relations into neural word embeddings. By categorizing the set of lexical constraints and penalizing the negative samples to different degrees according to the gap between categories, and allowing the positive and negative samples to learn from each other in the distributed space. The method we propose significantly improves neural word embeddings. By evaluating neural word embedded vocabulary similarity, the benchmark accuracy is improved to 75%. The method shows great competitiveness in text similarity tasks and text categorization tasks. These findings summarize research results and provide strong support for further applications. • This paper proposes the LexFMSL model to optimize word embeddings. • This paper enhances LEAR model performance through flexible margins and learning methods. • The LexFMSL model achieves good results on different word embedding datasets. [ABSTRACT FROM AUTHOR]