Adaptive Approach Research Articles

Energy-based approach to the assessment of traffic flow

This article focuses on modeling vehicle acceleration noise in different road conditions, emphasizing urban, highway, and rural roads in Ukraine. Acceleration noise, which refers to the fluctuations in a vehicle's acceleration, is a critical factor in vehicle safety, fuel efficiency, and driving comfort. The research aims to improve current vehicle dynamics models by integrating multi-body dynamics and machine learning algorithms, allowing for more precise predictions of acceleration variability in real-time. The study is based on the existing literature, showing that road surface quality significantly affects acceleration noise. With frequent stop-and-go traffic, urban roads produce moderate but irregular noise patterns. Highways show stable acceleration noise at moderate speeds, but noise increases sharply as vehicles approach higher speeds due to aerodynamic forces. Rural roads, especially those in poor condition, exhibit the highest variability in acceleration noise, even at low speeds. The proposed model has been validated using real-world data. It demonstrates a strong correlation between the predictions and actual vehicle behavior on various road types. One of the key innovations in this research is the use of machine learning to adjust model parameters in real-time dynamically. This adaptive approach enhances the model’s accuracy and applicability, especially in intelligent transport systems. The model can inform traffic management strategies, allowing for real-time adjustments to speed limits, traffic signals, and routing decisions based on road conditions. This contributes to safer, more efficient, and sustainable transport systems, particularly in regions with inconsistent road infrastructure. The research concludes that integrating acceleration noise modeling into intelligent transport systems can significantly improve traffic flow and vehicle safety. Future research will expand the dataset to include a broader range of vehicle types and road conditions, further refining the model's predictive capabilities.

Train assignment and handling capacity arrangement in multi-yard railway container terminals: An enhanced adaptive large neighborhood search heuristic approach

Expanding terminal scale and constructing multiple railway handling yards have become popular strategies for leading railway container terminals globally to cope with the ever-increasing handling volume. Although such an approach greatly enhances the terminal’s productivity, it also intensifies handling operations and introduces additional inter-yard interactions, complicating terminal management. To address these challenges, this paper investigates an integrated optimization approach for multi-yard railway container terminals, which feature both rail-road and rail-rail container transshipment operations. The train assignment plan for each yard and the handling capacity arrangement for each train are jointly optimized while considering inter-yard container transits, workload allocation for yards, and safety requirements in train shunting. This problem is formulated as a nonlinear programming model, with the objective to minimize operational delay and service time for each incoming train, and to minimize workload differences and container transit volume among yards. To efficiently solve this problem, this research develops an enhanced adaptive large neighborhood search (EALNS) heuristic, which includes several customized operators and feasibility repair methods, and is further enhanced with a local search method and backtracking mechanism compared to the standard ALNS framework. Computational experiments with different data scales and problem settings demonstrate the superiority of the EALNS in terms of solution quality and stability compared with three other solution methods. Additionally, practical insights for terminal operations are drawn through detailed analysis of different infrastructure configurations, transshipment train characteristics, and unit cost settings.

Load forecasting using fuzzy logic, artificial neural network, and adaptive neuro-fuzzy inference system approaches: application to South-Western Morocco

Load forecasting using fuzzy logic, artificial neural network, and adaptive neuro-fuzzy inference system approaches: application to South-Western Morocco

A Data-Driven Three-Stage Adaptive Pattern Mining Approach for Multi-Energy Loads

A Data-Driven Three-Stage Adaptive Pattern Mining Approach for Multi-Energy Loads

LA-YOLO: Bidirectional Adaptive Feature Fusion Approach for Small Object Detection of Insulator Self-Explosion Defects

LA-YOLO: Bidirectional Adaptive Feature Fusion Approach for Small Object Detection of Insulator Self-Explosion Defects

Accommodating Learners: An Adaptive Approach to Surgical Hand Preparation With Crutches

Accommodations for injured and disabled surgical providers have to balance an individual's needs with measures that ensure sterility requirements, patient and provider safety. The highly specialized nature of the surgical environment poses challenges when implementing changes in the operating room and literature is limited on adaptive surgical hand preparation techniques necessary to maximize a disabled medical student's active participation in their surgical clerkship. This paper presents a detailed account of the development and implementation of an adaptive surgical hand preparation designed to address mobility needs, enabling a student's active participation and education in the surgical curriculum. This offers a framework for adapting traditional surgical hand preparation techniques for crutches consisting of essential requirements in terms of equipment and personnel, step-by-step guide for implementation, discussion of potential risks related to contamination and safety, and a discussion on future directions for further innovation. An adaptive surgical hand preparation technique was necessary to sterilize forearm crutches for a third-year medical student with a physical disability to ensure accessibility in the operating room and equity in surgical clerkship and medical education. Successful use of this protocol, in over 40 surgical cases throughout an 8-week surgical clerkship, created opportunity for a disabled medical student to access the sterile operating table through collaboration and innovation in the operating room. The adaptive hand preparation and sterile crutch cover solution was necessary for the student to assist in open, laparoscopic, and surgical procedures resulting in high clinical performance marks in the surgical clerkship. Beyond the individual benefit, this protocol promotes the importance of equity in medication education and encourages diversity through adaptive measures in the surgical field. Designing an adaptive sterilization protocol for use of crutches in the operating room serves as an example of educational engineering and adaptable accessibility. The entire collaborative effort involving the medical student, university, surgical providers and operating room staff demonstrates the importance of teamwork in creating access in healthcare settings. Through learned experience, the authors provide insights for future directions for innovation, aiming to enhance access and inclusivity in medical education and surgical practice. This paper reflects on the broader implications of educational engineering and inclusive practices in healthcare.

Sigmoidal learning rate optimizer for deep neural network training using a two-phase adaptation approach

The optimization of machine learning models is an open research question since an optimal procedure to change the learning rate throughout training is still unknown. Manually defining a learning rate schedule involves troublesome, time-consuming try-and-error procedures to determine hyperparameters, such as learning rate decay epochs and learning rate decay rates, in order to navigate the intricate landscape of loss functions. Although adaptive learning rate optimizers automatize this process, recent studies suggest they may produce overfitting and reduce performance compared to fine-tuned learning rate schedules. Considering that the new machine learning loss function approaches present landscapes with much more saddle points than local minima, we proposed the Training Aware Sigmoidal Optimizer (TASO). This automated two-phase learning rate adaptation mechanism significantly reduces the need for manual hyperparameter tuning. The first phase uses a high learning rate to quickly traverse the numerous saddle points in the error surface, while the second phase uses a low learning rate to gradually approach the center of the local minimum previously found. We compared the proposed approach with commonly used adaptive learning rate schedules such as Adam, RMSProp, and Adagrad. The validation experiments were performed in image and text datasets and showed that TASO outperformed all competing methods in optimal (i.e., performing hyperparameter validation) and suboptimal (i.e., using default hyperparameters) scenarios. In our benchmark tests, TASO demonstrated promising performance, achieving an 8.32% increase in accuracy and a significant 46.62% decrease in training loss on average across various datasets and models. This remarkable performance positions TASO ahead of well-established adaptive optimizers, suggesting higher effectiveness and consistency in performance.

Transient gas path fault diagnosis of aero-engine based on domain adaptive offline reinforcement learning

Real-time measurement parameters are crucial for diagnosing faults in aero-engine gas path performance, ensuring engine reliability, and mitigating potential economic losses. Traditional aero-engines performance diagnosis was mainly based on the measurements of steady-state condition and lacked the utilization of data under transient conditions. Gas path diagnosis of aero-engines under transient conditions is crucial for early fault detection and safety of flight within the envelope. The challenge lies in the inconsistent distribution of performance deviations caused by variable operating conditions, especially with complex fault types, which can undermine diagnostic credibility. To improve reliability of gas path diagnosis under transient conditions, an offline reinforcement learning fault diagnosis framework based on a transient aero-engine performance model is proposed. To address the issue of variable operating conditions during transient states, a domain adaptive approach is utilized to reconstruct the measurement baseline and facilitate the transfer of different performance deviation distributions. Additionally, by adding spool acceleration as a measurement parameter, the multi-component fault coupling is solved. Finally, validation with actual operating data simulates fault cases, demonstrating the proposed method's efficacy in quantitatively detecting gradual, sudden, and multiple component faults under transient conditions with high accuracy and efficiency. The method proposed in this study achieves a computational speed improvement by 64% compared to the conventional method, achieving a time of 0.13 seconds, with an average error of less than 0.00389%. Additionally, it demonstrates strong robustness in the presence of noise, with an average error of less than 0.03125%. This proposed method improves real-time fault detection under transient conditions for its higher accuracy and efficiency, and therefore significantly enhance gas path health monitoring and diagnosis capability.

Privacy-Preserving Federated Adversarial Domain Adaptation Over Feature Groups for Interpretability

We present a novel privacy-preserving federated adversarial domain adaptation approach ($\textbf{PrADA}$) to address an under-studied but practical cross-silo federated domain adaptation problem, in which the party of the target domain is insufficient in both samples and features. We address the lack-of-feature issue by extending the feature space through vertical federated learning with a feature-rich party and tackle the sample-scarce issue by performing adversarial domain adaptation from the sample-rich source party to the target party. In this work, we focus on financial applications where interpretability is critical. However, existing adversarial domain adaptation methods typically apply a single feature extractor to learn feature representations that are low-interpretable with respect to the target task. To improve interpretability, we exploit domain expertise to split the feature space into multiple groups that each holds relevant features, and we learn a semantically meaningful high-order feature from each feature group. In addition, we apply a feature extractor (along with a domain discriminator) for each feature group to enable a fine-grained domain adaptation. We design a secure protocol that enables performing the PrADA in a secure and efficient manner. We evaluate our approach on two tabular datasets. Experiments demonstrate both the effectiveness and practicality of our approach.

A comprehensive model for ensuring data compliance in cloud computing environment

As organizations increasingly adopt cloud computing, ensuring data compliance has become a critical priority. Cloud environments pose unique challenges in meeting regulatory requirements due to their distributed and often multi-tenant nature. This review presents a comprehensive model for achieving data compliance in cloud computing, addressing essential aspects such as data privacy, security, sovereignty, and governance. The model emphasizes a structured, layered approach to compliance, integrating risk assessment, data governance, continuous monitoring, and incident management to ensure compliance throughout the data lifecycle. Key components of the proposed model include robust data privacy and protection mechanisms aligned with global regulations such as GDPR and CCPA, data security protocols for safeguarding confidentiality and access control, and data sovereignty policies to handle jurisdictional requirements and cross-border data flows. Additionally, continuous monitoring and automated auditing tools enhance real-time compliance management, while incident management procedures prepare organizations to respond promptly to breaches or policy violations. The framework also incorporates advanced technological solutions, including compliance automation, data loss prevention, and blockchain for traceability, to streamline compliance tasks and improve transparency. By addressing both the technical and governance aspects of data compliance, this model supports organizations in navigating complex regulatory landscapes across multi-cloud and hybrid environments. The review highlights best practices for ensuring compliance, such as regular policy updates, employee training, and third-party compliance management, to sustain long-term adherence. As the regulatory landscape evolves and new privacy-preserving technologies emerge, this model offers a scalable and adaptive approach, positioning organizations to manage data compliance effectively within dynamic cloud infrastructures. This comprehensive approach ensures secure, compliant data operations, fostering trust and accountability in cloud computing environments.

Adaptive Learning Systems: Harnessing AI to Personalize Educational Outcomes

This paper explores the transformative power ofAdaptive Learning Systems powered by Artificial Intelligence(ALS) to personalize educational outcomes for diverse learners in a way that adaptive learning approaches have the advantage of meeting the needs of the student’s learning style and pace, which traditional education methods have failed to do. It uses data analytics and machine learning algorithms in real time to tailor content and assessment to the specific needs of each learner. In our work, we break down mechanisms by which AI enables timely feedback, changes learning paths, and raises engagement that makes for a more effective and inclusive learningenvironment. Based on case studies and empirical analysis, the contribution of this research will show the added values and challenges AI adaptive learning solutions bring to different educational settings. The findings put so much importance on continuous assessment, hence integrating and harnessing pedagogical best practices for the maximization of AI effect on personal learning.

Utilizing digital footprint analysis for end-to-end risk-based authentication in medical billing systems

Healthcare systems face escalating challenges in securing sensitive financial and patient data due to sophisticated fraud tactics and unauthorized access. This study presents a dynamic risk-based authentication (RBA) framework that leverages digital footprint analysis, including behavior monitoring, device recognition, and location-based anomaly detection, to strengthen security. The framework utilizes machine learning models, Isolation Forest for outlier detection, and recurrent neural networks for sequential behavior analysis, to assess risk in real-time, dynamically adjusting authentication requirements based on risk profiles. Privacy-preserving technologies such as homomorphic encryption and federated learning are integrated to comply with HIPAA and GDPR standards, ensuring secure data handling without centralization. Findings show that the proposed RBA framework effectively reduces false positives, improves detection accuracy, and provides a scalable solution for securing medical billing systems. This adaptive approach supports both user experience and stringent privacy compliance, laying the groundwork for more resilient healthcare data security systems. Future studies could extend this framework by incorporating blockchain to enhance data transparency and auditability across transactions.

Image-based weight estimation and grading of post-harvested Indian potato (Solanum tuberosum) using dimensional analysis integrated with adaptive neuro fuzzy inference system approach

ABSTRACT The current study builds a model of the link between the image-based weights of Indian Potatoes extracted using the built computer vision system using a dimensional analysis integrated with the adaptive neuro-fuzzy inference system. An atomized sorting system must be developed to enhance the exportation quality. A soft computing method is applied to nonlinear data training. The features include size (dimensions, area, and volumes), shapes, and gravimetric properties were chosen. As per standards and export criteria, potatoes should be divided into three groups (small, medium, and big) based on their estimated weight. A self-build image-based system was designed for capturing an image. The experimental outcomes were contrasted with the presented integrated predicted outcomes. A respectable level of agreement is noted with good competency and dependability by the strong correlation coefficient (0.9975). Hence, the presented approach is strongly recommended for image-based weight estimation and classification. Code: https://colab.research.google.com/drive/1g-B81q8284Hw1QFwAJjqpmDEV35KsNzV

Calibrated Adaptive Teacher for Domain-Adaptive Intelligent Fault Diagnosis

Intelligent fault diagnosis (IFD) based on deep learning can achieve high accuracy from raw condition monitoring signals. However, models usually perform well on the training distribution only, and experience severe performance drops when applied to a different distribution. This is also observed in fault diagnosis, where assets are often operated in working conditions different from the ones in which the labeled data have been collected. The scenario where labeled data are available in a source domain and only unlabeled data are available in a target domain has been addressed recently by unsupervised domain adaptation (UDA) approaches for IFD. Recent methods have relied on self-training with confident pseudo-labels for the unlabeled target samples. However, the confidence-based selection of pseudo-labels is hindered by poorly calibrated uncertainty estimates in the target domain, primarily due to over-confident predictions, which limits the quality of pseudo-labels and leads to error accumulation. In this paper, we propose a novel method called Calibrated Adaptive Teacher (CAT), where we propose to calibrate the predictions of the teacher network on target samples throughout the self-training process, leveraging post hoc calibration techniques. We evaluate CAT on domain-adaptive IFD and perform extensive experiments on the Paderborn University (PU) benchmark for fault diagnosis of rolling bearings under varying operating conditions, using both time- and frequency-domain inputs. We compare four different calibration techniques within our framework, where temperature scaling is both the most effective and lightweight one. The resulting method—CAT+TempScaling—achieves state-of-the-art performance on most transfer tasks, with on average 7.5% higher accuracy and 4 times lower calibration error compared to domain-adversarial neural networks (DANNs) across the twelve PU transfer tasks.

Human-Centered Design to Respond to Public Health Crises: Maintaining Canine Rabies Vaccination during the COVID-19 Pandemic in Peru.

In the early coronavirus disease 2019 pandemic, limited understanding of severe acute respiratory syndrome coronavirus 2 transmission and fears of infection hindered mass dog vaccination efforts in dog rabies-affected areas. Interruption of dog rabies vaccination campaigns could lead to a rapid increase in the risk of human rabies. To address these challenges, we applied human-centered design (HCD) principles to develop a vaccination strategy that prioritizes safety while ensuring dog rabies vaccination continuity in Arequipa, Peru, a rabies-affected area. We describe the process of rapid prototyping and testing undertaken by our research team to adapt the vaccination process in response to a health crisis. A multidisciplinary team met twice a week to prototype a fixed-point vaccination campaign that ensured distancing and reduction of fomite transmission while allowing for the continuation of dog vaccination. Field notes and videos informed successive meetings. The final prototype was used in rabies hotspots. In 4 weeks, six prototypes of safe booths and supporting safety protocols were designed, and two copies of each prototype were field tested. During testing, additional innovations were identified and implemented, including virtual vaccine certificates and online data collection forms. The final prototype was implemented across 251 sites, and 17,876 dogs were vaccinated. Using HCD principles, we swiftly developed a mass vaccination strategy that provided safety and enabled the maintenance of rabies vaccination programs. This work highlights the importance of innovative and adaptive approaches to address public health challenges in times of crisis.

Going with the Grain of the Landscape: rethinking our approach to environmental policy

There are doubts about whether the current approach to regulating the impacts of land use in rural Aotearoa is making a difference. This article starts by outlining four challenges policymakers face when designing policies to protect the environment while balancing social, cultural and economic interests. We then discuss some of the barriers landowners encounter when contemplating land use change to address environmental degradation. Finally, we sketch out an adaptive approach to rethinking how we do environmental policy, including by devolving some decision making to communities, providing better environmental information, being explicit about the costs and trade-offs, and reforming the New Zealand Emissions Trading Scheme.

Advanced digital control strategies for switching buck converters: A modeling perspective

Advanced digital control strategies for switching buck converters: A modeling perspective

Book review: U. Chatterjee, A. O. Akanwa, S. Kumar, S. K. Singh, and A. D. Roy (Eds.), Ecological Footprints of Climate Change: Adaptive Approaches and Sustainability

U. Chatterjee, A. O. Akanwa, S. Kumar, S. K. Singh, and A. D. Roy (Eds.), Ecological Footprints of Climate Change: Adaptive Approaches and Sustainability (Cham: Springer Climate, 2022), 776 pp., €149.79 (hardback); €149.79 (paperback); €117.69 (eBook), ISBN: 978-3-031-15500-0.

Resilient Multi-Robot Coverage Path Redistribution Using Boustrophedon Decomposition for Environmental Monitoring

This study introduces a resilient and adaptive multi-robot coverage path planning approach based on the Boustrophedon Cell Decomposition algorithm, designed to dynamically redistribute coverage tasks in the event of robot failures. The proposed method ensures minimal disruption and maintains a balanced workload across operational robots through a propagation-based redistribution strategy. By iteratively reallocating the failed robot’s coverage path to neighboring robots, the method prevents any single robot from becoming overburdened, ensuring efficient task distribution and continuous environmental monitoring. Simulations conducted in five distinct environments, ranging from simple open areas to complex, obstacle-rich terrains, demonstrate the method’s robustness and adaptability. A key strength of the proposed approach is its fast and efficient task reallocation process, achieved with minimal propagation cycles, making it suitable for real-time applications even in complex scenarios. The approach reduces task variance and maintains balanced coverage throughout the mission.

Towards 3D Reconstruction of Multi-Shaped Tunnels Utilizing Mobile Laser Scanning Data

Using digital twin models of tunnels has become critical to their efficient maintenance and management. A high-precision 3D tunnel model is the prerequisite for a successful digital twin model of tunnel applications. However, constructing high-precision 3D tunnel models with high-quality textures and structural integrity based on mobile laser scanning data remains a challenge, particularly for tunnels of different shapes. This study addresses this problem by developing a novel method for the 3D reconstruction of multi-shaped tunnels based on mobile laser scanning data. This method does not require any predefined mathematical models or projection parameters to convert point clouds into 2D intensity images that conform to the geometric features of tunnel linings. This method also improves the accuracy of 3D tunnel mesh models by applying an adaptive threshold approach that reduces the number of pseudo-surfaces generated during the Poisson surface reconstruction of tunnels. This method was experimentally verified by conducting 3D reconstruction tasks involving tunnel point clouds of four different shapes. The superiority of this method was further confirmed through qualitative and quantitative comparisons with related approaches. By automatically and efficiently constructing a high-precision 3D tunnel model, the proposed method offers an important model foundation for digital twin engineering and a valuable reference for future tunnel model construction projects.