The progress in machinelearning and advancements in measurement and computational capabilities in modern wave control systems has spurred interest in learning-based control techniques, including model predictive cont...
详细信息
ISBN:
(纸本)9798350376357;9798350376340
The progress in machinelearning and advancements in measurement and computational capabilities in modern wave control systems has spurred interest in learning-based control techniques, including model predictive control. The primary challenge in model predictive control lies in addressing the inherent uncertainty in complex and dynamic system models. This paper explores the effectiveness of online system model learning to use Gaussian processes. Recent years have witnessed significant results by combining non-parametric learning models with Gaussian processes and model-based predictive control. This research focuses on assessing the effectiveness of Gaussian processes, considering a stochastic model predictive controller (SMPC). To evaluate the proposed method, simulations on a quadruple tank process are conducted, aiming to regulate liquid levels. Gaussian processes are utilized for real-time estimation of system hyperparameters, incorporated into the predictive control cost function, and account for input and output constraints. The results show the stability and efficacy of the proposed control system.
The use of optimization techniques in modern agriculture is growing, and these methods frequently introduce dangerous substances into the food chain, posing serious health hazards. In an effort to fulfill the rising d...
详细信息
Phishing attacks are a common and under-protected security hazard in today's digital ecosystem. Phishing, which first surfaced in 1996, has grown into an extremely severe and dangerous kind of cybercrime on the in...
详细信息
Diabetes is the serious and widespread disease worldwide. Common ingredients in modern diets, like sugar and fat, increase the risk of diabetes. Recognizing the symptoms is essential to predict and prevent the disease...
详细信息
Paper builds a next-day traffic forecasting system using machinelearning. By the use of historical information, it can correctly predict what will happen in the case of traffic conditions. It also provides dynamic ro...
详细信息
In many settings, fleets of assets must perform series of missions with in-between finite breaks. For such fleets, a widely used maintenance strategy is the fleet selective maintenance (FSM). Under resource constraint...
详细信息
In many settings, fleets of assets must perform series of missions with in-between finite breaks. For such fleets, a widely used maintenance strategy is the fleet selective maintenance (FSM). Under resource constraints, the FSM problem selects an optimal subset of feasible maintenance actions to be performed on a subset of components to minimise the maintenance cost while ensuring high system reliability during the upcoming mission. The majority of extant FSMP models are focussed on traditional physics-based reliability models. With recent advances in machinelearning (ML) and Deep learning (DL) algorithms, data-driven methods have shown accuracy in predicting remaining useful life (RUL). This paper proposes a predictive FSM strategy for fleets of complex and large multicomponent systems. It relies on a concurrent ML/DL and optimisation approach where a clustering algorithm is used to determine the health states of components and a probabilistic RUL prognostics model is used for component reliability assessment. An optimisation model is developed to solve the predictive FSM problem to ensure high reliability of all systems within the fleet. An efficient two-phase solution approach is developed to solve this complex optimisation problem. Numerical experiments show the validity of the approach and highlight the improved maintenance plans achieved.
Novelty Detection (ND) plays a crucial role in machinelearning by identifying new or unseen data during model inference. This capability is especially important for the safe and reliable operation of automated system...
详细信息
ISBN:
(纸本)9798350344868;9798350344851
Novelty Detection (ND) plays a crucial role in machinelearning by identifying new or unseen data during model inference. This capability is especially important for the safe and reliable operation of automated systems. Despite advances in this field, existing techniques often fail to maintain their performance when subject to adversarial attacks. Our research addresses this gap by marrying the merits of nearest-neighbor algorithms with robust features obtained from models pretrained on ImageNet. We focus on enhancing the robustness and performance of ND algorithms. Experimental results demonstrate that our approach significantly outperforms current state-of-the-art methods across various benchmarks, particularly under adversarial conditions. By incorporating robust pretrained features into the k-NN algorithm, we establish a new standard for performance and robustness in the field of robust ND. This work opens up new avenues for research aimed at fortifying machinelearningsystems against adversarial vulnerabilities.
The telecommunications business is one of the key industries with a higher risk of revenue loss owing to client turnover and environmental impact. Thus, efficient and effective churn management includes targeted marke...
详细信息
In a wide array of engineering disciplines, modular designs serve as a fundamental approach for constructing intricate systems from simpler constituent modules. Domain-specific knowledge about the resulting structures...
详细信息
ISBN:
(纸本)9798350363029;9798350363012
In a wide array of engineering disciplines, modular designs serve as a fundamental approach for constructing intricate systems from simpler constituent modules. Domain-specific knowledge about the resulting structures can be formalized, paving the way for informed machinelearning, a methodology that leverages prior knowledge to augment data-driven techniques with symbolic insights. One of many possible ways to include prior knowledge into a machinelearning pipeline is through incorporation into the design of neural network architectures. We propose a novel algorithm for the learning of modular neural networks on modular cyber-physical systems where structural knowledge is used to build network architectures which resemble technical modules and the information flow is based on semantic relations between data and modules. We investigate potential benefits of modular neural networks compared to classical monolithic approaches based on anomaly detection experiments on data sets of mechanical pendulums with variable numbers of joints which are provided with this research. We define and investigate different levels of knowledge integration and modularity and show that modular designs can have a positive impact on anomaly detection performance. All models and code are published as open source.
Lumpy skin disease (LSD), a contagious ailment that can swiftly disseminate within cattle populations, presents a serious risk to the cattle industry's finances. Timely identification and precise recognition of af...
详细信息
暂无评论