Data-driven Solutions Research Articles

The data-driven solutions and inverse problems of some nonlinear diffusion convection-reaction equations based on Physics-Informed Neural Network

The Physics-Informed Neural Network (PINN) has achieved remarkable results in solving partial differential equations (PDEs). This paper aims to solve the forward and inverse problems of some specific nonlinear diffusion convection-reaction equations, thereby validating the practical efficacy and accuracy of data-driven approaches in tackling such equations. In the forward problems, four different solutions of the studied equations are reproduced effectively and the approximation errors can be reduced to 10−5. Experiments indicate that the PINNs method based on adaptive activation functions (PINN-AAF), outperforms the standard PINNs in dealing with inverse problems. The unknown parameters are estimated effectively and the approximation errors can lower to 10−4. Additionally, training rules for both PINN and PINN-AAF are summarized. The results of this study validate the exceptional performance of the data-driven approach in solving the complex nonlinear diffusion convection-reaction equation problems, and provide an effective mechanism for dealing with analogous, intricate nonlinear problems.

Spoofing attack recognition for GNSS-based train positioning using a BO-LightGBM method.

Trustworthy positioning is critical in the operational control and management of trains. For a train positioning system (TPS) based on a global navigation satellite system (GNSS), a spoofing attack significantly threatens the trustworthiness of positioning. However, the influence and recognition of GNSS spoofing attacks are not considered in the existing research on GNSS-enabled TPS. Spoofing attacks affect the performance of GNSS observations and the positioning results, allowing the development of data-driven spoofing recognition solutions. This study aims to achieve effective spoofing recognition for active security protection in TPS. Different features were designed to reflect the effects of a spoofing attack, including GNSS observation-related indicators and odometer-enabled parameters, and a novel Bayesian optimization-light gradient boosting machine (BO-LightGBM) solution was proposed. In particular, a Bayesian optimization technique was introduced into the LightGBM framework to improve the hyperparameter determination capability for recognition model training. Using a GNSS spoofing test platform with a specific GNSS signal generator and the SimSAFE spoofing test tool, different spoofing attack modes were tested to collect sample datasets for model training and evaluation. The results of model establishment and comparison of the model performance indicators illustrated the advantages of the proposed solution, its adaptability to different spoofing attack situations, and its superiority over state-of-the-art modeling strategies.

Hybrid data mining and data-driven algorithms for a green logistics transportation network in the post-COVID era: A case study in the USA

This study examines the problem of item allocation in a post-COVID environment with various products and a large customer base. The number of customers has increased due to the rise of internet access and the growing willingness to shop online. Problems such as the timely delivery of goods or services, the selection and destination of orders in decentralized warehouses, and the allocation of warehouses to customers are difficult to overcome with a large variety of items and many customers. It has been proposed that mathematical modeling in combination with meta-heuristic solution techniques solve these problems. However, solving mathematical models is very time-consuming and labor-intensive because there are many different location situations. Due to computing power and memory capacity advances, researchers have been looking at data-driven solutions to these problems. This study aims to tackle the diversity of commodities and the number of consumers in the post-COVID era by proposing a hybrid data-driven approach that combines data mining and mathematical modeling to solve mathematical location models with high accuracy in less time. This paper was implemented based on data from real cases in the USA.

A data-driven maximum entropy method for probability uncertainty analysis based on the B-spline theory

The probability density function (PDF) is quite important for structural reliability analysis; thus, accurate PDF modeling methods draw increasing attention. This paper proposes a novel metaheuristic data-driven paradigm of the maximum entropy method (MEM) based on the B-spline function theory. Firstly, a B-spline proxy of the MEM PDF is proposed for probability uncertainty analysis. We derive the parameter calculation formulation and calculate the undetermined parameters via the raw data of structural responses. Then, to determine the knots of the B-spline functions, we propose a novel data-driven approach with the aid of a powerful metaheuristic algorithm and the response data information. Different from the traditional MEM, the proposed method is a complete data-driven solution approach and does not involve the statistical moment calculation and the nonlinear equations composed of statistical moments. Combining the advantages of the B-spline theory and the MEM, the proposed method can reconstruct the response PDF with a complex shape, such as the PDF with multiple peaks or heavy tails. For verification, two numerical examples and one engineering example are analyzed, and compared with some classical PDF modeling methods. The results show that the proposed method is superior to the compared methods in terms of computational accuracy, when the same sample data is used.

Strategic investments in mobile and stationary energy storage for low-carbon power systems

The main feature and trend of the distribution system is the integration of renewable energy with high penetration rates. The variability and zero marginal cost characteristics of renewable energy will lead to drastically fluctuating locational marginal prices. In the deregulated electricity market, merchants have incentives to utilize energy storage and price arbitrage. Mobile energy storage has a short capital payback period and is widely recognized for transferring energy in the temporal and spatial dimensions. This paper analyses the interaction between merchants and distribution system operators and presents a hybrid energy storage strategic investment framework using bi-level programming. In the upper-level problem, the merchant formulates the capacity, location, and operation strategy of different energy storage to maximize the market revenue of hybrid energy storage, which is paid for by the locational marginal price. In the lower-level problem, the distribution system operator develops an optimal dispatch strategy considering renewable energy and merchant investments. A joint energy and reserve market clearing procedure is performed to derive the locational marginal prices. In the lower-level problem, a data-driven solution strategy based on machine learning is introduced. It uses deep neural networks to approximate the mapping relationship between distribution system states and locational marginal prices. The presented methodology is implemented in an IEEE-33 node system. The results demonstrate that, compared to the basic case, the hybrid energy storage investment strategy has led to an 8.1 % increase in merchant profits and a 12.9 % reduction in the operational costs of the distribution network. The deep neural network approximator fully avoids the lower-level problem with less than 5 % optimality loss.

Application of the Naïve Bayes Algorithm in Classifying the Reading Interests of Regional Library Visitors

Reading interest is a key indicator in assessing the success of library services. However, manually understanding visitors' preferences poses a challenge for library managers. This study aims to classify the reading interests of regional library visitors by employing the Naïve Bayes algorithm, a widely-used classification method in data mining. The research data includes visit records and book borrowing data from a regional library. Through a quantitative approach, this study analyzes reading interest patterns and evaluates the performance of the Naïve Bayes algorithm in classifying these interests. The analysis results show that the algorithm achieves an accuracy of 65%, with a precision of 62%, recall of 63%, and F1-score of 63%. These findings are expected to assist libraries in formulating better-targeted collection management and service policies, contributing to the overall improvement of reading interest in the community. This study contributes to the field by providing a practical, data-driven solution for libraries to enhance service quality through a better understanding of visitor preferences. Furthermore, it demonstrates the applicability of the Naïve Bayes algorithm in a non-commercial context, encouraging future research on data-driven approaches in library management to support literacy and educational development

An updated landslide susceptibility model and a log-Gaussian Cox process extension for Scotland

AbstractAt the time of its development, GeoSure was created using expert knowledge based on a thorough understanding of the engineering geology of the rocks and soils of Great Britain. The ability to use a data-driven methodology to develop a national-scale landslide susceptibility was not possible due to the relatively small size of the landslide inventory at the time. In the intervening 20 years, the National Landslide Database has grown from around 6000 points to over 18,000 records today and continues to be added to. With the availability of this additional inventory, new data-driven solutions could be utilised. Here, we tested a Bernoulli likelihood model to estimate the probability of debris flow occurrence and a log-Gaussian Cox process model to estimate the rate of debris flow occurrence per slope unit. Scotland was selected as the test site for a preliminary experiment, which could potentially be extended to the whole British landscape in the future. Inference techniques for both of these models are applied within a Bayesian framework. The Bayesian framework can work with the two models as additive structures, which allows for the incorporation of spatial and covariate information in a flexible way. The framework also provides uncertainty estimates with model outcomes. We also explored consideration on how to communicate uncertainty estimates together with model predictions in a way that would ensure an integrated framework for master planners to use with ease, even if administrators do not have a specific statistical background. Interestingly, the spatial predictive patterns obtained do not stray away from those of the previous GeoSure methodology, but rigorous numerical modelling now offers objectivity and a much richer predictive description.

Data-driven soliton solution implementation based on nonlinear adaptive physics-informed neural networks

Data-driven soliton solution implementation based on nonlinear adaptive physics-informed neural networks

Deep neural helmholtz operators for 3D elastic wave propagation and inversion

Summary Numerical simulations of seismic wave propagation in heterogeneous 3D media are central to investigating subsurface structures and understanding earthquake processes, yet are computationally expensive for large problems. This is particularly problematic for full waveform inversion, which typically involves numerous runs of the forward process. In machine learning there has been considerable recent work in the area of operator learning, with a new class of models called neural operators allowing for data-driven solutions to partial differential equations. Recent works in seismology have shown that when neural operators are adequately trained, they can significantly shorten the compute time for wave propagation. However, the memory required for the 3D time domain equations may be prohibitive. In this study, we show that these limitations can be overcome by solving the wave equations in the frequency domain, also known as the Helmholtz equations, since the solutions for a set of frequencies can be determined in parallel. The 3D Helmholtz neural operator is 40 times more memory-efficient than an equivalent time-domain version. We employ a Helmholtz neural operator for 2D and 3D elastic wave modeling, achieving two orders of magnitude acceleration compared to a baseline spectral element method. The neural operator accurately generalizes to variable velocity structures and can be evaluated on denser input meshes than used in the training simulations. We also show that when solving for wavefields strictly on the surface, the accuracy can be significantly improved via a graph neural operator layer. In leveraging automatic differentiation, the proposed method can serve as an alternative to the adjoint-state approach for 3D full-waveform inversion, reducing the computation time by a factor of 350.

PINN for solving forward and inverse problems involving the integrable two dimensional nonlocal equations

Abstract In this paper, the physics informed neural network (PINN) deep learning method is applied to solve the two dimensional nonlocal equations including partial reverse space y-nonlocal Mel'nikov equation, partial reverse space-time nonlocal Mel'nikov equation and nonlocal two dimensional NLS equation. By PINN method, we successfully derive data-driven two soliton solution, lump solution and rogue wave solution. Numerical simulation results indicate that the error range between the data-driven solution and the exact solution is relatively small, which verifies the effectiveness of the PINN deep learning method for solving high dimensional nonlocal equation.
Moreover, the parameter discovery of the partial reverse space-time nonlocal Mel'nikov equation is analysed in terms of its soliton solution for the first time.

Data-driven bottleneck detection on Tehran highways

In metropolitan areas, traffic congestion has become a prevalent challenge due to rapid urbanization and increased vehicle usage, adversely impacting mobility, productivity, and quality of life. Identifying and mitigating persistent traffic bottlenecks is crucial for developing efficient transportation systems and guiding infrastructure planning decisions. This research proposes an innovative data-driven methodology to pinpoint recurrent traffic bottlenecks in Tehran's extensive highway network, addressing the limitations of traditional traffic monitoring methods. Through data mining and image processing techniques applied to 16 months of traffic flow maps from Google Maps, diverse information is extracted, including traffic nodes, congestion hotspots, and locations with the longest queue lengths. The image processing approach involves color-based segmentation, pixel-level analysis, and machine learning algorithms to determine congestion levels across the highway network. The identified bottlenecks are validated against ground truth data from CCTV cameras, demonstrating a remarkable 92 % correlation for key identified points. The proposed approach leverages the power of advanced analytics to comprehensively analyze all major highways, including areas lacking CCTV infrastructure. The robust validation process reinforces the reliability of this data-driven solution in capturing real-world traffic dynamics. As urban mobility challenges escalate globally, the integration of diverse data sources and cutting-edge techniques will be instrumental in guiding intelligent transportation planning and policy decisions.

AI and Big Data approaches to addressing the opioid crisis: a scoping review protocol

IntroductionThis paper outlines the steps necessary to assess the latest developments in artificial intelligence (AI) as well as Big Data technologies and their relevance to the opioid crisis. Fatal opioid...

Data-driven Solution for Agri-SMEs Optimization in Albania: A Framework Using C# and .NET

The Albanian economy relies heavily on the agricultural sector. However, the lack of comprehensive farm management data reduces Albanian agricultural enterprises’ competitiveness in global markets. The purpose of this article is to propose the building of a data gathering, analysis, and visualization application utilizing the C# programming language and the.NET framework. Big data in agriculture can help businesses improve their efficiency, competitiveness, and performance. Drawing on current challenges in Albanian agri-SMEs, it presents a logical structure for a web application designed to improve small and medium-sized enterprises (SMEs) in the agricultural sector by easing sales and purchase monitoring while optimizing profitability. The study suggests that data-driven solutions are essential for agricultural optimization in Albania, with guidelines for future refinement and implementation.

The role of big data analysis for resources optimization of immunization programmes in Pakistan.

Madam, The significance of Big Data Analysis (BDA) in optimizing immunization programmes in Pakistan emerges within the context of global and regional immunization challenges post the COVID-19 pandemic. Despite recovery efforts, a substantial number of children globally remain under-vaccinated, with 14.3 million zero-dose children in 2022.[1] South Asia, primarily India, has shown notable progress, exceeding pre-pandemic coverage levels.[2] In Pakistan, the Expanded Programme on Immunization (EPI) launched in 1978 aims to combat high under-five mortality rates due to vaccine-preventable diseases.[3] However, vaccine coverage remains suboptimal, with only 66% of children aged 12-23 months receiving basic EPI vaccines.[3] This is compounded by reduced doses administered later in schedules, influenced by limited access, awareness gaps, and insufficient vaccinators, especially in rural areas. [3] Big data analytics can help tackle challenges, improve resource allocation, and optimize immunization in Pakistan. The vital role of BDA in optimizing Pakistan's immunization programmes is rooted in its manifold health benefits. BDA aids disease prevention, identifies health risk factors, and enhances healthcare strategies.[4] Amid health emergencies like COVID-19, BDA leverages information technology to fortify health systems, enhancing decision-making, reducing errors, and conserving resources.[4] BDA's dynamic potential is evident. Its predictive tools swiftly pinpoint high-risk patients, streamlining care and elevating healthcare outcomes.[4] BDA draws insights from vast datasets for informed decisions. A recent study conducted in Sindh, increased vaccinator attendance from 44% to 88%, by factoring in results of BDA of Electronic Immunization Registries into their decision making.[5] BDA of antigen administration during accelerated outreach efforts revealed substantial boosts, compared to routine activities.[5] These findings spurred continued efforts in high-risk areas, showcasing BDA's impact in project acceleration and resource optimization.[5] This case highlights BDA's transformative role, enhancing immunization programs through data-driven insights. To harness the potential of BDA in immunization, Pakistan's healthcare system requires a digital overhaul. This entails prioritizing active patient data collection, storage, and analysis on a national scale. Collected data would facilitate targeted vaccination efforts in vulnerable areas. Storing data supports future research and predictive analysis, offering insights into current measures' efficacy and enabling necessary adjustments. A robust data analysis infrastructure, coupled with healthcare professional training, is essential. Cost-effective data security is vital. Digital registries in tertiary care hospitals and rural centres can aid government analysis. This holistic approach seeks to establish a digital healthcare ecosystem, involve the public, and implement data-driven solutions for improved immunization and overall public health in Pakistan.

Physics-constrained deep learning approach for solving inverse problems in composite laminated plates

The applications of physics-informed neural networks (PINNs) in material parameters identification of composite laminates are currently research highlights. We present an efficient physics-constrained deep learning approach based on PINNs for solving material parameters of composite laminates. We explain the details of incorporating first-order shear deformation theory as physical information into designed loss functions. The performance of proposed approach is demonstrated through a numerical example of idealized composite laminated plates under uniform pressure conditions. The computational errors of material parameters are less than 0.1%. Moreover, the applicability of transfer learning (TL) has been illustrated for inversion of material parameters with few datasets. The ambition is to improve the identification efficiency of carbon and glass fiber reinforced plies material parameters across various loading conditions. Intensive studies are conducted to compare convergence time between with and without TL through a numerical example under thermal-force coupling conditions. The comparison shows PINNs with TL obtain average error of 0.144% and 0.077% in carbon and glass fiber reinforced plies, which is better than without TL of 0.472% and 0.284%, respectively. The proposed work emphasizes the effective application of PINNs-based approach that combines first-order deformation and data-driven solution features for inverse solving material parameters of composite laminates.

Challenges and opportunities to advance manufacturing research for sustainable battery life cycles

Advanced manufacturing research for sustainable battery life cycles is of utmost importance to reach net zero carbon emissions (European Commission, 2023a) as well as several of the United Nations Sustainable Development Goals (UNSDGs), for example: 30% reduction of CO2 emission, 10 million job opportunities and access to electricity for 600 million people (World Economic Forum, 2019). This editorial paper highlights international motivations for pursuing more sustainable manufacturing practices and discusses key research topics in battery manufacturing. Batteries will be central to our sustainable future as generation and storage become key components to on-demand energy supply. Four underlying themes are identified to address industrial needs in this field: 1. Digitalizing and automating production capabilities: data-driven solutions for production quality, smart maintenance, automation, and human factors, 2. Human-centric production: extended reality for operator support and skills development, 3. Circular battery life cycles: circular battery systems supported by service-based and other novel business models, 4. Future topics for battery value chains: increased industrial resilience and transparency with digital product passports, and next-generation battery chemistries. Challenges and opportunities along these themes are highlighted for transforming battery value chains through circularity and more sustainable production, with a particular emphasis on lithium-ion batteries (LIB). The paper concludes with directions for further research to advance a circular and sustainable battery value chain through utilizing the full potential of digitalization realising a cleaner, more energy-efficient society.

Deep learning-aided respiratory motion compensation in PET/CT: addressing motion induced resolution loss, attenuation correction artifacts and PET-CT misalignment.

Respiratory motion (RM) significantly impacts image quality in thoracoabdominal PET/CT imaging. This study introduces a unified data-driven respiratory motion correction (uRMC) method, utilizing deep learning neural networks, to solve all the major issues caused by RM, i.e., PET resolution loss, attenuation correction artifacts, and PET-CT misalignment. In a retrospective study, 737 patients underwent [18F]FDG PET/CT scans using the uMI Panorama PET/CT scanner. Ninety-nine patients, who also had respiration monitoring device (VSM), formed the validation set. The remaining data of the 638 patients were used to train neural networks used in the uRMC. The uRMC primarily consists of three key components: (1) data-driven respiratory signal extraction, (2) attenuation map generation, and (3) PET-CT alignment. SUV metrics were calculated within 906 lesions for three approaches, i.e., data-driven uRMC (proposed), VSM-based uRMC, and OSEM without motion correction (NMC). RM magnitude of major organs were estimated. uRMC enhanced diagnostic capabilities by revealing previously undetected lesions, sharpening lesion contours, increasing SUV values, and improving PET-CT alignment. Compared to NMC, uRMC showed increases of 10% and 17% in SUVmax and SUVmean across 906 lesions. Sub-group analysis showed significant SUV increases in small and medium-sized lesions with uRMC. Minor differences were found between VSM-based and data-driven uRMC methods, with the SUVmax was found statistically marginal significant or insignificant between the two methods. The study observed varied motion amplitudes in major organs, typically ranging from 10 to 20mm. A data-driven solution for respiratory motion in PET/CT has been developed, validated and evaluated. To the best of our knowledge, this is the first unified solution that compensates for the motion blur within PET, the attenuation mismatch artifacts caused by PET-CT misalignment, and the misalignment between PET and CT.

Enhancing Prediction Accuracy of Vessel Arrival Times Using Machine Learning

Marine transportation accounts for approximately 90% of the total trade managed in international logistics and plays a vital role in many companies’ supply chains. However, en-route factors like weather conditions or piracy incidents often delay scheduled arrivals at destination ports, leading to downstream inefficiencies. Due to the maritime industry’s digital transformation, smart ports and vessels generate vast amounts of data, creating an opportunity to use the latest technologies, like machine and deep learning (ML/DL), to support terminals in their operations. This study proposes a data-driven solution for accurately predicting vessel arrival times using ML/DL techniques, including Deep Neural Networks, K-Nearest Neighbors, Decision Trees, Random Forest, and Extreme Gradient Boosting. This study collects real-world AIS data in the Eastern Mediterranean Sea from a network of public and private AIS base stations. The most relevant features are selected for training and evaluating the six ML/DL models. A comprehensive comparison is also performed against the estimated arrival time provided by shipping agents, a simple calculation-based approach, and four other ML/DL models proposed recently in the literature. The evaluation has revealed that Random Forest achieves the highest performance with an MAE of 99.9 min, closely followed by XGBoost, having an MAE of 105.0 min.

A data-driven control method for ground locomotion on sloped terrain of a hybrid aerial-ground robot

In this work, we present a data-driven solution for the attitude control of DoubleBee on slopes. DoubleBee is a novel hybrid aerial-ground robot with two rotors and two active wheels. Inspired by the physcics modeling of the system, we add a channel-separated attention head to a deep ReLU neural network to predict disturbances from ground effects, motor torques and rotation axis shift. The proposed neural network is Lipschitz continuous, has fewer parameters and performs better for disturbance estimation than the baseline deep ReLU neural network. Then, we design a sliding mode controller using these predictions and establish its input-to-state stability and error bounds. Experiments show improvements of the proposed neural network in training speed and robustness over a baseline ReLU network, and a 40% reduction in tracking error compared to a baseline PID controller.

Data-Driven Insights and Solutions for the Health and Human Resource Crisis in Canada.

Canada's healthcare system is experiencing a health and human resource (HHR) crisis. The available evidence of the scope of the problem and potential solutions, however, is not commensurate with the scale and urgency of the crisis. The use of linked health administrative data to study the health, well-being and work patterns of the health workforce offers critical insights into how the workforce is functioning at a population level. Efforts to rapidly expand the use of these data are needed to understand the scope of the HHR crisis, find opportunities for improvement and drive change.