首页期刊导航|Engineering applications of artificial intelligence: The international journal of intelligent real-time automation
期刊信息/Journal information
Engineering applications of artificial intelligence: The international journal of intelligent real-time automation
Elsevier Science Ltd.
Elsevier Science Ltd.
0952-1976
Engineering applications of artificial intelligence: The international journal of intelligent real-time automation/Journal Engineering applications of artificial intelligence: The international journal of intelligent real-time automationSCIISTPEIAHCI
查看更多>>摘要：Accurate wind speed prediction improves power system stability and efficiency. Wind direction contains airflow dynamic information, but existing methods fail to fully capture it. The multi-periodicity of meteorological data causes irregular wind speed fluctuations, complicating the capture of correlations and variances across periods. To address these issues, this paper proposes the Multi-Period Wind Direction Graph Network(MWGN). Gaussian Spatial Module(GSM) calculates the relationship between wind turbines using Gaussian distribution along the crosswind direction, thus enhancing airflow motion capture. Multi-Period Time Series Decoupling Module(MPTSDM) selects the primary periods by analyzing the frequency domain and extracts local correlation and periodic correlation, to better model the changing pattern of time series. Compared with the existing models, MWGN achieves the consistent state-of-the-art in three datasets.
查看更多>>摘要：As glass usage expands across industries, intelligent glass defect detection is essential for ensuring quality. However, the varying shapes and sizes of defects, coupled with numerous subtle defects and the demand for efficient detection, present challenges for existing methods in achieving both accurate and real-time detection. To address these, we propose the lightweight and robust Glass Surface Defect Network (GSDNet) via scale- and shape-aware feature extraction. Specifically, the novel Shape-aware Feature Extraction (SFE) block, which employs deformable convolution with special linear shape-adaptive offset constraints, forms the feature extraction network, enabling the adaptive extraction of local features for defects with irregular shapes. Meanwhile, the Scale-aware (SA) attention is proposed, incorporating spatial attention mechanism to guide the model in focusing on key features across different receptive fields, enhancing defect detection at various scales. Finally, to enhance detection efficiency, the Efficient Bidirectional Path Aggregation Network (EBiPAN) is proposed as the feature aggregation module, integrating high-resolution information through bi-directional concatenation to improve small defect detection while avoiding significant additional computational burden. To validate the effectiveness of GSDNet, we compile the first multi-class glass defect dataset, covering 4 types of glass and 12 defect categories. Extensive experiments demonstrate GSDNet exhibits exceptional accuracy and robustness, consistently outperforming 9 advanced networks, with a 6.8% improvement in mean Average Precision and a notable 10.9% improvement in mean Average Precision small over the You Only Look Once version 8. Moreover, the optimal balance of accuracy and efficiency is achieved, with a detection speed of 68 frames per second. The dataset and code are publicly available at.
Paulo GilMiguel JoaoCarolina CarvalhoLuis Brito Palma...
110672.1-110672.10页
查看更多>>摘要：This study investigates the problem of system identification and control for non-affine nonlinear deterministic systems using a generalised state-space neuro-fuzzy model. The proposed new model consists of a seven-layer neural network, where the consequent part comprises a finite set of discrete-time invariant linear state-space models. For tracking control design, quadratic stabilisers are integrated within a Parallel Distributed Compensation framework. Instead of merely ensuring the closed-loop stability of the state-augmented system, the feedback matrices are computed by solving a region-constrained Linear Matrix Inequality problem, which guarantees that the closed-loop eigenvalues remain within a G-stable region. The proposed generalised neuro-fuzzy model is proven to be a universal approximator on compact sets, with sufficient conditions for closed-loop stability established under the Neuro-Fuzzy-based Parallel Distributed Compensation framework. Experimental results on a nonlinear benchmark system validate the effectiveness and practical feasibility of the proposed neuro-fuzzy tracking control strategy.
查看更多>>摘要：Model Predictive Control (MPC) is a powerful tool for planning the local trajectory of autonomous mobile robots. The paper considers a new algorithm for trajectory planning and obstacle avoidance based on the MPC technique known in Artificial Intelligence (AI) planning and robotics. We have proposed an original method for decomposing obstacles to form a potential field, which in turn is used as an additional component in MPC. Thus, we propose a new intelligent trajectory planning method that takes into account the special shape of obstacles, which in turn significantly improves the metrics of intelligent agent movement on the well-known Moving AI benchmark. The challenging aspect of MPC planning is collision avoidance on large and complicated grid maps. We propose the Polygon Segmentation for obtaining Artificial Potential Field (PolySAP). This local planner approximates the obstacles on the map with a set of polygons. We address the question of how to partition a map with polygons to make it fast and effective for a practical MPC planner. We propose a decomposition algorithm based on Straight Skeleton. Our algorithm returns a set of polygons, which are then convexified. Numerical experiments show that our method outperforms basic algorithms in performance and provides sufficient partition quality for effective planning. We propose an artificial potential function calculated for polygonal obstacles and added to the MPC objective for collision avoidance. We evaluate our approach on city map dataset and on a real robotic platform. Numerical experiments show that PolySAP allows for polygon decomposition that is five times faster than Interior Extensions. Our MPC solver provides a fast solution for the MPC task compared to the state-of-the-art MPC planners. Our planner ensured the safe motion of the real mobile robot through a narrow indoor environment. Our code is available at.
查看更多>>摘要：This work focuses on the Supplier Selection and Order Allocation (SSOA) problem with prominent features namely resiliency, circular economy, and customer-based dimensions. In this regard, this work proposes a novel data-driven approach based on the data mining and decision-making methods. In the current work, in the first step, the weights of the indicators are computed using the Fuzzy Best-Worst Method (FBWM). Then, the performance of the potential Raw Material Providers (RMPs) is assessed using the Decision Tree Regressor (DTR), and Data Envelopment Analysis (DEA) methods. In the next step, the best RMPs is identified and also the number of orders is specified by proposing a multi-objective mathematical model. In the next step, to deal with the mixed uncertainty, a hybrid data-driven method by combining the Robust Possibilistic-Stochastic Optimization (RPSO) and Prophet methods is proposed. Finally, to achieve the optimal solution, a new method called the Lexicographic Chebyshev Multi-Choice Goal Programming with Utility Function (LCMCGP-UF) is proposed. The achieved outputs demonstrate that cost, quality, waste management, service level, and robustness are determined as the most desirable indicators. The proposed model determines the best suppliers and also specifies the optimal location to establish the facilities. Additionally, the results confirm the efficiency and validity of the developed data-driven approach. Moreover, the results of the sensitivity analysis show that the total cost and non-resiliency of the supply chain have increased by increasing the demand parameter while the service level has decreased.
查看更多>>摘要：In many applications that involve prediction of a large number of variables, such as energy consumption or portfolio construction, it is common to employ a single model for predicting multiple target variables at once. Under this "monolithic" approach, the model is necessarily optimized on average across targets, and not for any one target in particular. Thus, the resulting predictions are likely to be underwhelming for a significant subset of targets. At the other end of the spectrum, optimizing and maintaining a separate prediction model for each of hundreds or thousands of targets, is unrealistic. This work proposes a novel model selection approach, termed max-one, that sits between these two extremes. Our methodology takes advantage of the standard hyperparameter tuning process used with most machine learning models and assigns to each target its own optimal model-hyperparameter combination, based on the criterion of one's choice. In the context of portfolio optimization, which we use as a concrete example, the resulting family of models generates stock predictions which can then be used to construct a portfolio. Applying our suggested framework to an extensive 35-year data set with thousands of United States' stocks, leads to an impressive 7x capital increase after transaction costs. This surpasses the performance of the "single model" approach and that of major global stock indices and compares favorably with recent relevant works, without sacrificing computational efficiency. Although our domain-specific application involves equities, our proposed approach could be used in settings where a model is tuned to predict multiple target variables.
查看更多>>摘要：The uncertain cooperative task assignment (CTA) problem based on uncertainty theory is a complex combinatorial optimization problem that cannot be effectively addressed using probability theory due to insufficient samples. In light of this limitation, this paper initially proposes an uncertain multiobjective CTA (UMCTA) problem, taking into account the uncertainties present in the battlefield environment. Consequently, the expected-value standard-deviation UMCTA model (Eσ-UMCTA) model, which emphasize the minimization of expected returns and stability of the objective functions, is developed. Nonetheless, this approach may yield suboptimal assignment schemes under predetermined risk levels. To address this issue, a minimum-risk model for the UMCTA problem is introduced by maximizing the belief degree that the objective functions do not exceed the predefined risk levels, and the concept of the minimum-risk efficient assignment scheme is delineated. Given the challenges in solving the minimum-risk model due to uncertain variables, two scenarios for addressing these uncertainties in the UMCTA problem are contemplated, and the minimum-risk model is transformed into a deterministic multiobjective programming problem. Subsequently, recognizing the combinational nature and complexity of the resulting deterministic multiobjective programming problem, an enhanced discrete particle swarm optimization (PSO) algorithm with non-dominated sorting is devised, where the crossover and mutation operators are employed to sustain diversity and avert premature convergence. Finally, a simulation study is conducted to substantiate the practicability of the proposed model and assess the efficacy of the designed algorithm.
查看更多>>摘要：Differential Architecture Search (DARTS) has become a prominent technique for neural architecture search in recent years. Despite its merits, the issue of discretization discrepancy within DARTS still necessitates further exploration, as it can degrade in performance. In this paper, we introduce a novel algorithm termed Continuous-Discrete Alignment Optimization (DARTS-CDAO), designed to address the discretization discrepancy and thereby enhance the robustness and generalization capabilities of the discovered neural architectures. Our proposed DARTS-CDAO algorithm seamlessly integrates the discretization process into the training phase of the architecture parameters, thereby bolstering the search algorithm's adaptability to the inherent discretization processes. Specifically, our methodology commences by formalizing the process of architecture parameter discretization. Subsequently, we introduce a coarse gradient weighting algorithm that is employed to update the architecture parameters, effectively minimizing the divergence between the representation of continuous and discrete parameters. Rigorous theoretical analysis, coupled with extensive experimental outcomes, substantiates that our proposed approach can elevate the performance of the searched models. Notably, this enhancement is achieved without incurring additional search time, rendering DARTS more robust and endowed with a heightened capacity for generalization.
查看更多>>摘要：Accurate anomaly detection and localization in sheet metal glue line applications are crucial for quality assurance in automotive manufacturing. Most current vision-based inspection systems that rely on geometric deviations from a predefined shape often suffer from high false-positive rates, leading to unnecessary interventions and operational inefficiencies. This research investigates the potential of unsupervised deep learning models to significantly reduce false positives in the analysis of sheet metal glue line images, even with limited datasets. We conducted a comparative evaluation of 17 unsupervised deep learning models covering different categories with 28 backbones on datasets of approximately 300 industrial glue line images per part from a Swedish vehicle manufacturer. A data synthesis method was applied to balance the glue line dataset, further enhancing the reliability of the models. To address the challenge of limited training data and improve model generalization, we incorporated data augmentation techniques and performed robustness experiments to ensure applicability to real-world industrial conditions. Our findings demonstrate that deep learning approaches can effectively detect and localize anomalies, significantly reducing false positives and gluing machine downtimes compared to the existing system. Moreover, we proposed a multi-criteria decision-making based approach for model selection, enabling decision-makers to achieve optimal trade-offs between accuracy and inference time, thus improving operational efficiency. These advancements highlight that even with limited training data, unsupervised deep learning models can enhance anomaly detection reliability, streamline the automotive production process, and reduce unnecessary resource expenditures.
查看更多>>摘要：Large-scale layout-conditioned text-to-image diffusion models have made significant progress and achieved remarkable results in generating diverse and high-quality images, realizing objects appearing in specific regions simultaneously. However, existing methods still fail with attribute coupling, unreasonable spatial relationships expressions and missing objects when the prompt is complex with multiple objects containing multiple attributes. In addition, it is difficult for users to give precise layout conditions for complex prompts. To address the above issues, we propose MirrorDiff, a novel training-free grounded text-to-image-to-text framework by redescription to correct inaccurate content expressions of synthetic images iteratively. Specifically, we first utilize large language models as layout generator which have the ability to understand visual concepts and support plausible arrangements to generate scene layout for complex prompts to help users obtain precision layout more conveniently. Subsequently, to solve small object missing, we design a layout-guided attention modulation strategy to properly adjust attention maps during diffusion generation process, which effectively increases attention of small objects. Additionally, semantic text regeneration supervision is proposed to constrain the redescription to keep consistent with the given text semantically, which aims to mitigate attribute coupling and failures of spatial relationships expressions. We conduct extensive experiments on four benchmarks and our method achieves the best results in all categories on the Holistic, Reliable and Scalable benchmark, which shows that our proposed MirrorDiff achieves state-of-the-art results both quantitatively and qualitatively compared with current superior models.
NETL
NSTL
Elsevier