arXiv subjects

Adil Rasheed

Publications and source records attributed to Adil Rasheed.

At least 37 records · Page 2Linked to original sources

arXiv2024

Variational Autoencoders for exteroceptive perception in reinforcement learning-based collision avoidance

Modern control systems are increasingly turning to machine learning algorithms to augment their performance and adaptability. Within this context, Deep Reinforcement Learning (DRL) has emerged as a promising control framework, particularly in the domain of marine transportation. Its potential for autonomous marine applications lies in its ability to seamlessly combine path-following and collision avoidance with an arbitrary number of obstacles. However, current DRL algorithms require disproportionally large computational resources to find near-optimal policies compared to the posed control problem when the searchable parameter space becomes large. To combat this, our work delves into the application of Variational AutoEncoders (VAEs) to acquire a generalized, low-dimensional latent encoding of a high-fidelity range-finding sensor, which serves as the exteroceptive input to a DRL agent. The agent's performance, encompassing path-following and collision avoidance, is systematically tested and evaluated within a stochastic simulation environment, presenting a comprehensive exploration of our proposed approach in maritime control systems.

cs.LG↗

arXiv2024

Privacy Re-identification Attacks on Tabular GANs

Generative models are subject to overfitting and thus may potentially leak sensitive information from the training data. In this work. we investigate the privacy risks that can potentially arise from the use of generative adversarial networks (GANs) for creating tabular synthetic datasets. For the purpose, we analyse the effects of re-identification attacks on synthetic data, i.e., attacks which aim at selecting samples that are predicted to correspond to memorised training samples based on their proximity to the nearest synthetic records. We thus consider multiple settings where different attackers might have different access levels or knowledge of the generative model and predictive, and assess which information is potentially most useful for launching more successful re-identification attacks. In doing so we also consider the situation for which re-identification attacks are formulated as reconstruction attacks, i.e., the situation where an attacker uses evolutionary multi-objective optimisation for perturbing synthetic samples closer to the training space. The results indicate that attackers can indeed pose major privacy risks by selecting synthetic samples that are likely representative of memorised training samples. In addition, we notice that privacy threats considerably increase when the attacker either has knowledge or has black-box access to the generative models. We also find that reconstruction attacks through multi-objective optimisation even increase the risk of identifying confidential samples.

cs.CR↗

arXiv2024

Unveiling Urban Mobility Patterns: A Data-Driven Analysis of Public Transit

The expansion of urban centers necessitates enhanced efficiency and sustainability in their transportation infrastructure and mobility systems. The big data obtainable from various transportation modes potentially offers critical insights for urban planning. This study presents analysis of detailed historical public transit data, enriched with relevant temporal and geospatial metadata, as a precursor to injecting dynamism into digital twins of mobility systems via ML/DL-based predictive modeling. A data preprocessing framework was implemented to refine the raw data for effective historical analysis and predictive modeling. This paper examines public transit data for patterns and trends -- incorporating factors such as time, geospatial elements, external influences, and operational aspects. From a technical standpoint, this research helps to assess the quality of the available transit data and identify important information for use in digital twins. Such digital twins foster educated decisions for efficient, sustainable urban mobility systems by anticipating infrastructure demand, identifying service gaps, and understanding mobility dynamics.

physics.soc-ph↗

arXiv2024

Digital Twin of Autonomous Surface Vessels for Safe Maritime Navigation Enabled through Predictive Modeling and Reinforcement Learning

Autonomous surface vessels (ASVs) play an increasingly important role in the safety and sustainability of open sea operations. Since most maritime accidents are related to human failure, intelligent algorithms for autonomous collision avoidance and path following can drastically reduce the risk in the maritime sector. A DT is a virtual representative of a real physical system and can enhance the situational awareness (SITAW) of such an ASV to generate optimal decisions. This work builds on an existing DT framework for ASVs and demonstrates foundations for enabling predictive, prescriptive, and autonomous capabilities. In this context, sophisticated target tracking approaches are crucial for estimating and predicting the position and motion of other dynamic objects. The applied tracking method is enabled by real-time automatic identification system (AIS) data and synthetic light detection and ranging (Lidar) measurements. To guarantee safety during autonomous operations, we applied a predictive safety filter, based on the concept of nonlinear model predictive control (NMPC). The approaches are implemented into a DT built with the Unity game engine. As a result, this work demonstrates the potential of a DT capable of making predictions, playing through various what-if scenarios, and providing optimal control decisions according to its enhanced SITAW.

cs.RO↗

arXiv2024

Nonlinear Model Predictive Control for Enhanced Navigation of Autonomous Surface Vessels

This article proposes an approach for collision avoidance, path following, and anti-grounding of autonomous surface vessels under consideration of environmental forces based on Nonlinear Model Predictive Control (NMPC). Artificial Potential Fields (APFs) set the foundation for the cost function of the optimal control problem in terms of collision avoidance and anti-grounding. Depending on the risk of a collision given by the resulting force of the APFs, the controller optimizes regarding an adapted heading and travel speed by additionally following a desired path. For this purpose, nonlinear vessel dynamics are used for the NMPC. To extend the situational awareness concerning environmental disturbances impacted by wind, waves, and sea currents, a nonlinear disturbance observer is coupled to the entire NMPC scheme, allowing for the correction of an incorrect vessel motion due to external forces. In addition, the most essential rules according to the Convention on the International Regulations for Preventing Collisions at Sea (COLREGs) are considered. The results of the simulations show that the proposed framework can control an autonomous surface vessel under various challenging scenarios, including environmental disturbances, to avoid collisions and follow desired paths.

eess.SY↗

arXiv2024

An environmental disturbance observer framework for autonomous surface vessels

This paper proposes a robust disturbance observer framework for maritime autonomous surface vessels considering model and measurement uncertainties. The core contribution lies in a nonlinear disturbance observer, reconstructing the forces on a vessel impacted by the environment. For this purpose, mappings are found leading to synchronized global exponentially stable error dynamics. With the stability theory of Lyapunov, it is proven that the error converges exponentially into a ball, even if the disturbances are highly dynamic. Since measurements are affected by noise and physical models can be erroneous, an unscented Kalman filter (UKF) is used to generate more reliable state estimations. In addition, a noise estimator is introduced, which approximates the noise strength. Depending on the severity of the measurement noise, the observed disturbances are filtered through a cascaded structure consisting of a weighted moving average (WMA) filter, a UKF, and the proposed disturbance observer. To investigate the capability of this observer framework, the environmental disturbances are simulated dynamically under consideration of different model and measurement uncertainties. It can be seen that the observer framework can approximate dynamical forces on a vessel impacted by the environment despite using a low measurement sampling rate, an erroneous model, and noisy measurements.

eess.SY↗

arXiv2024

Computationally and Memory-Efficient Robust Predictive Analytics Using Big Data

In the current data-intensive era, big data has become a significant asset for Artificial Intelligence (AI), serving as a foundation for developing data-driven models and providing insight into various unknown fields. This study navigates through the challenges of data uncertainties, storage limitations, and predictive data-driven modeling using big data. We utilize Robust Principal Component Analysis (RPCA) for effective noise reduction and outlier elimination, and Optimal Sensor Placement (OSP) for efficient data compression and storage. The proposed OSP technique enables data compression without substantial information loss while simultaneously reducing storage needs. While RPCA offers an enhanced alternative to traditional Principal Component Analysis (PCA) for high-dimensional data management, the scope of this work extends its utilization, focusing on robust, data-driven modeling applicable to huge data sets in real-time. For that purpose, Long Short-Term Memory (LSTM) networks, a type of recurrent neural network, are applied to model and predict data based on a low-dimensional subset obtained from OSP, leading to a crucial acceleration of the training phase. LSTMs are feasible for capturing long-term dependencies in time series data, making them particularly suited for predicting the future states of physical systems on historical data. All the presented algorithms are not only theorized but also simulated and validated using real thermal imaging data mapping a ship's engine.

cs.LG↗

arXiv2024

Digital Twin for Wind Energy: Latest updates from the NorthWind project

NorthWind, a collaborative research initiative supported by the Research Council of Norway, industry stakeholders, and research partners, aims to advance cutting-edge research and innovation in wind energy. The core mission is to reduce wind power costs and foster sustainable growth, with a key focus on the development of digital twins. A digital twin is a virtual representation of physical assets or processes that uses data and simulators to enable real-time forecasting, optimization, monitoring, control and informed decision-making. Recently, a hierarchical scale ranging from 0 to 5 (0 - Standalone, 1 - Descriptive, 2 - Diagnostic, 3 - Predictive, 4 - Prescriptive, 5 - Autonomous has been introduced within the NorthWind project to assess the capabilities of digital twins. This paper elaborates on our progress in constructing digital twins for wind farms and their components across various capability levels.

cs.CY↗

arXiv2024

CasTGAN: Cascaded Generative Adversarial Network for Realistic Tabular Data Synthesis

Generative adversarial networks (GANs) have drawn considerable attention in recent years for their proven capability in generating synthetic data which can be utilised for multiple purposes. While GANs have demonstrated tremendous successes in producing synthetic data samples that replicate the dynamics of the original datasets, the validity of the synthetic data and the underlying privacy concerns represent major challenges which are not sufficiently addressed. In this work, we design a cascaded tabular GAN framework (CasTGAN) for generating realistic tabular data with a specific focus on the validity of the output. In this context, validity refers to the the dependency between features that can be found in the real data, but is typically misrepresented by traditional generative models. Our key idea entails that employing a cascaded architecture in which a dedicated generator samples each feature, the synthetic output becomes more representative of the real data. Our experimental results demonstrate that our model is capable of generating synthetic tabular data that can be used for fitting machine learning models. In addition, our model captures well the constraints and the correlations between the features of the real data, especially the high dimensional datasets. Furthermore, we evaluate the risk of white-box privacy attacks on our model and subsequently show that applying some perturbations to the auxiliary learners in CasTGAN increases the overall robustness of our model against targeted attacks.

cs.LG↗

arXiv2024

Data Integration Framework for Virtual Reality Enabled Digital Twins

Digital twins are becoming increasingly popular across many industries for real-time data streaming, processing, and visualization. They allow stakeholders to monitor, diagnose, and optimize assets. Emerging technologies used for immersive visualization, such as virtual reality, open many new possibilities for intuitive access and monitoring of remote assets through digital twins. This is specifically relevant for floating wind farms, where access is often limited. However, the integration of data from multiple sources and access through different devices including virtual reality headsets can be challenging. In this work, a data integration framework for static and real-time data from various sources on the assets and their environment is presented that allows collecting and processing of data in Python and deploying the data in real-time through Unity on different devices, including virtual reality headsets. The integration of data from terrain, weather, and asset geometry is explained in detail. A real-time data stream from the asset to the clients is implemented and reviewed, and instructions are given on the code required to connect Python scripts to any Unity application across devices. The data integration framework is implemented for a digital twin of a floating wind turbine and an onshore wind farm, and the potential for future research is discussed.

eess.SP↗

arXiv2023

Digital Twins in Wind Energy: Emerging Technologies and Industry-Informed Future Directions

This article presents a comprehensive overview of the digital twin technology and its capability levels, with a specific focus on its applications in the wind energy industry. It consolidates the definitions of digital twin and its capability levels on a scale from 0-5; 0-standalone, 1-descriptive, 2-diagnostic, 3-predictive, 4-prescriptive, 5-autonomous. It then, from an industrial perspective, identifies the current state of the art and research needs in the wind energy sector. The article proposes approaches to the identified challenges from the perspective of research institutes and offers a set of recommendations for diverse stakeholders to facilitate the acceptance of the technology. The contribution of this article lies in its synthesis of the current state of knowledge and its identification of future research needs and challenges from an industry perspective, ultimately providing a roadmap for future research and development in the field of digital twin and its applications in the wind energy industry.

cs.HC↗

arXiv2023

Enhancing Elasticity Models: A Novel Corrective Source Term Approach for Accurate Predictions

With the recent wave of digitalization, specifically in the context of safety-critical applications, there has been a growing need for computationally efficient, accurate, generalizable, and trustworthy models. Physics-based models have traditionally been used extensively for simulating and understanding complex phenomena. However, these models though trustworthy and generalizable to a wide array of problems, are not ideal for real-time. To address this issue, the physics-based models are simplified. Unfortunately, these simplifications, like reducing the dimension of the problem (3D to 2D) or linearizing the highly non-linear characteristics of the problem, can degrade model accuracy. Data-driven models, on the other hand, can exhibit better computational efficiency and accuracy. However, they fail to generalize and operate as blackbox, limiting their acceptability in safety-critical applications. In the current article, we demonstrate how we can use a data-driven approach to correct for the two kinds of simplifications in a physics-based model. To demonstrate the methodology's effectiveness, we apply the method to model several elasticity problems. The results show that the hybrid approach, which we call the corrective source term approach, can make erroneous physics-based models more accurate and certain. The hybrid model also exhibits superior performance in terms of accuracy, model uncertainty, and generalizability when compared to its end-to-end data-driven modeling counterpart.

math.NA↗

arXiv2023

Standalone, Descriptive, and Predictive Digital Twin of an Onshore Wind Farm in Complex Terrain

In this work, a digital twin with standalone, descriptive, and predictive capabilities is created for an existing onshore wind farm located in complex terrain. A standalone digital twin is implemented with a virtual-reality-enabled 3D interface using openly available data on the turbines and their environment. Real SCADA data from the wind farm are used to elevate the digital twin to the descriptive level. The data are complemented with weather forecasts from a microscale model nested into Scandinavian meteorological forecasts, and wind resources are visualized inside the human-machine interface. Finally, the weather data are used to infer predictions on the hourly power production of each turbine and the whole wind farm with a 61 hours forecasting horizon. The digital twin provides a data platform and interface for power predictions with a visual explanation of the prediction, and it serves as a basis for future work on digital twins.

eess.SP↗

arXiv2023

Sparse neural networks with skip-connections for identification of aluminum electrolysis cell

Neural networks are rapidly gaining interest in nonlinear system identification due to the model's ability to capture complex input-output relations directly from data. However, despite the flexibility of the approach, there are still concerns about the safety of these models in this context, as well as the need for large amounts of potentially expensive data. Aluminum electrolysis is a highly nonlinear production process, and most of the data must be sampled manually, making the sampling process expensive and infrequent. In the case of infrequent measurements of state variables, the accuracy and open-loop stability of the long-term predictions become highly important. Standard neural networks struggle to provide stable long-term predictions with limited training data. In this work, we investigate the effect of combining concatenated skip-connections and the sparsity-promoting $\ell_1$ regularization on the open-loop stability and accuracy of forecasts with short, medium, and long prediction horizons. The case study is conducted on a high-dimensional and nonlinear simulator representing an aluminum electrolysis cell's mass and energy balance. The proposed model structure contains concatenated skip connections from the input layer and all intermittent layers to the output layer, referred to as InputSkip. $\ell_1$ regularized InputSkip is called sparse InputSkip. The results show that sparse InputSkip outperforms dense and sparse standard feedforward neural networks and dense InputSkip regarding open-loop stability and long-term predictive accuracy. The results are significant when models are trained on datasets of all sizes (small, medium, and large training sets) and for all prediction horizons (short, medium, and long prediction horizons.)

eess.SY↗

arXiv2023

Demonstration of a Standalone, Descriptive, and Predictive Digital Twin of a Floating Offshore Wind Turbine

Digital Twins bring several benefits for planning, operation, and maintenance of remote offshore assets. In this work, we explain the digital twin concept and the capability level scale in the context of wind energy. Furthermore, we demonstrate a standalone digital twin, a descriptive digital twin, and a prescriptive digital twin of an operational floating offshore wind turbine. The standalone digital twin consists of the virtual representation of the wind turbine and its operating environment. While at this level the digital twin does not evolve with the physical turbine, it can be used during the planning-, design-, and construction phases. At the next level, the descriptive digital twin is built upon the standalone digital twin by enhancing the latter with real data from the turbine. All the data is visualized in virtual reality for informed decision-making. Besides being used for data bundling and visualization, the descriptive digital twin forms the basis for diagnostic, predictive, prescriptive, and autonomous tools. A predictive digital twin is created through the use of weather forecasts, neural networks, and transfer learning. Finally, digital twin technology is discussed in a much wider context of ocean engineering.

eess.SP↗

arXiv2023

Artificial intelligence-driven digital twin of a modern house demonstrated in virtual reality

A digital twin is a powerful tool that can help monitor and optimize physical assets in real-time. Simply put, it is a virtual representation of a physical asset, enabled through data and simulators, that can be used for a variety of purposes such as prediction, monitoring, and decision-making. However, the concept of digital twin can be vague and difficult to understand, which is why a new concept called "capability level" has been introduced. This concept categorizes digital twins based on their capability and defines a scale from zero to five, with each level indicating an increasing level of functionality. These levels are standalone, descriptive, diagnostic, predictive, prescriptive, and autonomous. By understanding the capability level of a digital twin, we can better understand its potential and limitations. To demonstrate the concepts, we use a modern house as an example. The house is equipped with a range of sensors that collect data about its internal state, which can then be used to create digital twins of different capability levels. These digital twins can be visualized in virtual reality, allowing users to interact with and manipulate the virtual environment. The current work not only presents a blueprint for developing digital twins but also suggests future research directions to enhance this technology. Digital twins have the potential to transform the way we monitor and optimize physical assets, and by understanding their capabilities, we can unlock their full potential.

cs.CV↗

arXiv2023

Deep active learning for nonlinear system identification

The exploding research interest for neural networks in modeling nonlinear dynamical systems is largely explained by the networks' capacity to model complex input-output relations directly from data. However, they typically need vast training data before they can be put to any good use. The data generation process for dynamical systems can be an expensive endeavor both in terms of time and resources. Active learning addresses this shortcoming by acquiring the most informative data, thereby reducing the need to collect enormous datasets. What makes the current work unique is integrating the deep active learning framework into nonlinear system identification. We formulate a general static deep active learning acquisition problem for nonlinear system identification. This is enabled by exploring system dynamics locally in different regions of the input space to obtain a simulated dataset covering the broader input space. This simulated dataset can be used in a static deep active learning acquisition scheme referred to as global explorations. The global exploration acquires a batch of initial states corresponding to the most informative state-action trajectories according to a batch acquisition function. The local exploration solves an optimal control problem, finding the control trajectory that maximizes some measure of information. After a batch of informative initial states is acquired, a new round of local explorations from the initial states in the batch is conducted to obtain a set of corresponding control trajectories that are to be applied on the system dynamics to get data from the system. Information measures used in the acquisition scheme are derived from the predictive variance of an ensemble of neural networks. The novel method outperforms standard data acquisition methods used for system identification of nonlinear dynamical systems in the case study performed on simulated data.

cs.AI↗

arXiv2023

A novel corrective-source term approach to modeling unknown physics in aluminum extraction process

With the ever-increasing availability of data, there has been an explosion of interest in applying modern machine learning methods to fields such as modeling and control. However, despite the flexibility and surprising accuracy of such black-box models, it remains difficult to trust them. Recent efforts to combine the two approaches aim to develop flexible models that nonetheless generalize well; a paradigm we call Hybrid Analysis and modeling (HAM). In this work we investigate the Corrective Source Term Approach (CoSTA), which uses a data-driven model to correct a misspecified physics-based model. This enables us to develop models that make accurate predictions even when the underlying physics of the problem is not well understood. We apply CoSTA to model the Hall-Héroult process in an aluminum electrolysis cell. We demonstrate that the method improves both accuracy and predictive stability, yielding an overall more trustworthy model.

cs.LG↗