Adaptive Model Research Articles

Adaptive MPC path-tracking controller based on reinforcement learning and preview-based PID controller

Path-tracking control is a crucial process for autonomous vehicles, ensuring that the vehicle drives safely along the reference path, and the suitable controller parameters ensure the accuracy and stability of this process. To enhance the adaptability of traditional path-tracking controller parameters, this paper proposes an adaptive model predictive control (MPC) controller based on a preview-based PID controller and deep deterministic policy gradient (DDPG) algorithm to achieve adaptive tuning of the controller parameters. Starting with the design of the dynamics tracking error model of the vehicle and the MPC controller. Based on the actor-critic reinforcement learning architecture, the DDPG agent is designed to tune the prediction horizon and weight matrix of the MPC controller. A preview-based PID controller is proposed to improve the efficiency and stability of reinforcement learning and compensate for the error in vehicle modeling. The improved algorithm performance is verified through the simulation scenarios of high-speed lane changing and accelerated overtaking scenarios constructed by MATLAB/Simulink. The results show that the improved algorithm significantly improves the adaptive ability of the traditional MPC controller to time-varying conditions and achieves higher tracking accuracy and stability.

Process Management Framework for Health and Safety at Work (SST) Companies

Objective: This study aims to develop and implement a process management framework for Occupational Safety and Health (OSH) companies, seeking to optimize the organization and execution of services, identifying improvement opportunities throughout the customer journey, from contract closure to renewal. The proposal is to offer an adaptable model that meets industry demands and enhances the operational efficiency of companies. Theoretical Framework: The theoretical framework addresses the evolution of Regulatory Standards (NRs) since the 1970s and the importance of complying with labor laws for the safety and health of workers in Brazil. The role of eSocial, created in 2014 to unify and ensure the collection of employer information, is highlighted, as well as its function in alerting them to legal risks. Method: The methodology used was action research, as defined by Oquist (1978). The research involved mapping the operational processes of OSH companies to identify areas for improvement. The first version of the framework was developed, tested, and based on the results, improved into a second version. The improvements were based on tests and validations conducted throughout the process. Results and Discussion: The first version of the framework showed positive results but also highlighted the need for improvements, which were incorporated into the second version. Changes included the restructuring of steps and the addition of a new phase focused on the commercial process. Satisfaction surveys with internal and external clients, as well as accounting firms, indicated positive acceptance but also a lack of systemic vision among professionals, affecting the quality of the work. Research Implications: The research implications are significant for the OSH sector. The developed framework improves the organization and efficiency of service-providing companies. The study also highlights the importance of performance indicators to monitor performance and mitigate risks, such as customer loss. It is recommended that future research explore the adaptation of the framework to new technologies and automation. Originality/Value: The originality of this study lies in the creation of a process management framework specifically for OSH companies, where organization and efficiency are essential for complying with labor regulations and ensuring worker safety. The value of the work resides in its practical contribution to the sector, offering an adaptable model that can be improved based on feedback and technological advancements.

Exploring an adaptive management model for “status-optimization-regulation” of mining city in transition: A case study of Huangshi, China

Mining cities face the challenges of ecological transformation and sustainable development after mineral depletion. Thus, ecological space optimization and adaptive management are pivotal after ecological restoration project, but easily neglected. Taking Huangshi in Hubei Province as an example, a top-down adaptive management model for regional mining ecological space integrating status-optimization-regulation (SOR) was established based on land system resilience (LSR) evaluation, circuit theory, complex network model and community discovery algorithm. The results showed that i) As the LSR increased, the land use structure shifted from non-ecological zones to forest and cropland, indicating that balancing agriculture and forest protection was crucial for increasing LSR in Huangshi. i) The ecological networks (ENs) of Huangshi had an irregular fishnet pattern, with densely intricate corridors in the south and broader, sparser ones in the north, and numerous ecological barriers near the mining area. Furthermore, the distribution of ecological sources and corridors displayed complementarity and hierarchy. iii) The optimized ENs exhibited higher connectivity and efficiency under disturbance, reducing corridor redundancy and migration costs. iv) The ENs clusters were classified into five types based on ecological connectivity: ecological buffer zone, priority restoration zone, moderate restoration zone, natural restoration zone, and moderate development zone, and tailored ecological regulatory strategies were proposed. The findings provide practice-oriented guidance for the sustainable development of mining cities, and offer a direct approach to support conscious, clear, and coherent adaptive management of ecological restoration in rapidly changing environments.

Long-Term Comparative Life Cycle Assessment, Cost, and Comfort Analysis of Heavyweight vs. Lightweight Construction Systems in a Mediterranean Climate

Massive construction systems have always characterized traditional architecture and are currently the most prevalent, straightforward, and cost-effective in many Mediterranean countries. However, in recent years, the construction industry has gradually shifted towards using lightweight, dry construction techniques. This study aims to assess the effects on energy consumption, comfort levels, and environmental sustainability resulting from the adoption of five high-performance construction systems in a multi-family residential building: (i) reinforced concrete structure with low-transmittance thermal block infill; (ii) reinforced concrete structure with light-clay bricks and outer thermal insulation; (iii) steel frame; (iv) cross-laminated timber (CLT); (v) timber-steel hybrid structure. To achieve this goal, a multidisciplinary approach was employed, including the analysis of thermal parameters, the evaluation of indoor comfort through the adaptive model and Fanger’s PMV, and the quantification of environmental and economic impacts through life cycle assessment and life cycle cost applied in a long-term analysis (ranging from 30 to 100 years). The results highlight that heavyweight construction systems are the most effective in terms of comfort, cost, and long-term environmental impact (100 years), while lightweight construction systems generally have higher construction costs, provide lower short-term environmental impacts (30 years), and offer intermediate comfort depending on the thermal mass.

The Natural Pattern-based Fuzzy Investment System

Research background: The underlying research problem concerns simplifying nature’s infinite sustainability pattern into a usable system to prove self-care in the financial field. Many disciplines have discovered self-sustaining systems, implying one should also exist in the portfolio- or asset management field. Purpose of the article: This paper models and applies a self-sustaining investment system based on nature’s sustainability pattern to present a usable and easily adaptable financial self-care model that can contribute to societal and individual well-being. Methods: This interdisciplinary research incorporates fractal patterns from nature and integrates these into an innovative investment decision system via a working and utilizable model. The article approaches the problem in three ways. First, it applies an unprecedented, proprietary fuzzy heuristic approach to parse the Mandelbrot set hiding nature’s growth code. Second, it subjects the resulting model system to static, dynamic, and iterative methods. Finally, it tests the above in practice in a focus group research project based on individual decisions in a portfolio collision. Findings & value added: The paper brings manageable order to investment decision processes using a specific econophysics approach to provide a complex whole of frames, alternatives, and dynamic wealth management functions. The paper attempts to demonstrate the self-sustaining power of the natural order in investment portfolio returns, behavioral finance, and wealth management decisions. The theory of an efficient, well-functioning, self-sustaining investment decision system based on heuristic criteria is developable and has been proven. The study made the organizational dominance measurable and – through fuzzy logic – simplified the complexity of the Mandelbrot set. The research also shows the scalability of the fuzzy symmetry framework, implying that it is transferable to other disciplines.

Revisiting the adaptive thermal comfort zone in ISO 17772-1 standard: Insights from four thermal comfort databases

The design and operation of naturally ventilated environments rely on adaptive models. The International standard ISO 17772-1:2017 incorporated an adaptive model into the ISO standards framework, which was based on the SCATs Database for office buildings. To verify whether the adaptive thermal comfort zone of the ISO 17772-1 standard can effectively evaluate naturally ventilated environments across different building types worldwide, the analysis was conducted using 59,478 naturally ventilated environment data selected from the Chinese Thermal Comfort Dataset, ASHRAE Global Thermal Comfort Database II, SCATs Database, and ASHRAE RP-884 Database. The results revealed differences in thermal environments among various building types, with neutral temperatures for occupants in offices, residences, and classrooms being 22.3 ℃, 23.2 ℃, and 21.8 ℃, respectively, directly related to the mean operative temperatures they experienced. The acceptable thermal environment data for offices, residences, and classrooms were 63.4 %, 57.3 %, and 78.8 %, respectively, within the comfort zone of the ISO 17772-1 standard. When the outdoor temperature was 10–30 ℃, the ISO 17772-1 standard evaluated the acceptable thermal environments for offices and classrooms well. However, a significant portion of the acceptable thermal environments in residences exceeded the comfort zone defined by the standard. Additionally, based on these data, adaptive models and corresponding adaptive thermal comfort zones were established for offices (slope: 0.2295), residences (slope: 0.3041), and classrooms (slope: 0.2789). These findings provide references for the establishment and improvement of the adaptive model in ISO 17772-1 standard.

Synthetic data in generalizable, learning-based neuroimaging

Abstract Synthetic data has emerged as an attractive option for developing machine learning methods in human neuroimaging, particularly in magnetic resonance imaging (MRI)— a modality where image contrast depends enormously on acquisition hardware and parameters. This retrospective paper reviews a family of recently proposed methods, based on synthetic data, for generalizable machine learning in brain MRI analysis. Central to this framework is the concept of domain randomization, which involves training neural networks on a vastly diverse array of synthetically generated images with random contrast properties. This technique has enabled robust, adaptable models that are capable of handling diverse MRI contrasts, resolutions, and pathologies, while working out-of-the-box, without retraining. We have successfully applied this method to tasks such as whole brain segmentation (SynthSeg), skull-stripping (SynthStrip), registration (SynthMorph, EasyReg), super-resolution and MR contrast transfer (SynthSR). Beyond these applications, the paper discusses other possible use cases and future work in our methodology. Neural networks trained with synthetic data enable the analysis of clinical MRI, including large retrospective datasets, while greatly alleviating (and sometimes eliminating) the need for substantial labeled datasets, and offer enormous potential as robust tools to address various research goals.

An adaptive hexagonal deployment model for resilient wireless sensor networks in precision agriculture

This study presents an innovative hexagonal deployment model designed specifically for wireless sensor networks (WSNs) with a primary application in precision agriculture. The proposed protocol integrates advanced features, notably an adaptive frequency-hopping spread spectrum (AFHSS) mechanism and a decentralized real-time adaptation strategy to optimize data transmission in dynamic agricultural environments. The simulation study, conducted in diverse terrains with realistic sensor node distributions, meticulously evaluates the protocol’s performance using comprehensive Quality of Service (QoS) metrics. The hexagonal deployment model operates by strategically positioning sensor nodes in a hexagonal grid pattern, ensuring uniform coverage of the agricultural field. The AFHSS mechanism dynamically adjusts frequency channels, mitigating interference and fortifying the network’s robustness against external disruptions. Complementing this, the decentralized real-time adaptation empowers individual nodes to autonomously respond to the ever-changing environmental conditions, optimizing data transmission efficiency. Quantitative results from the simulations exhibit outstanding performance metrics. The protocol achieves an average latency of 50 milliseconds, a packet loss rate below 2%, a success rate exceeding 95%, and highly efficient obstacle management, with adjusted nodes accounting for less than 5%. These compelling outcomes underscore the protocol’s exceptional ability to deliver responsive and reliable data transmission, positioning it as a promising solution for enhancing environmental monitoring in precision agriculture. This study provides quantitative evidence of the protocol’s prowess and delves into the nuanced working mechanisms, offering a deeper understanding of its potential impact. The findings contribute significant insights to the field, serving as a robust foundation for researchers and practitioners engaged in designing and implementing resilient WSNs tailored for precision agriculture applications.

A Cloud-Edge Collaborative Framework for Adaptive Quality Prediction Modeling in IIoT

A Cloud-Edge Collaborative Framework for Adaptive Quality Prediction Modeling in IIoT

An Adaptive CSI Feedback Model Based on BiLSTM for Massive MIMO-OFDM Systems

An Adaptive CSI Feedback Model Based on BiLSTM for Massive MIMO-OFDM Systems

The Effectiveness of Asset Pricing Models Under Special Conditions: Evidence from the COVID-19 Pandemic, Emerging Markets, and Financial Crises

Asset pricing models are important tools in finance. However, special market conditions can make them highly ineffective. This paper evaluates the performance of classical asset pricing models (that is, CAPM and Fama-French models) under three specific scenarios: the COVID-19 pandemic, emerging markets, and financial crises. Recent research and market data are reviewed to conclude that these models have very low efficiency in times of extreme occurrences for capturing proper asset valuations. Our findings reveal that standard models lose a substantial part of their explanatory power in periods of crises while new context-specific risk factors come into existence in other exceptional conditions. This work argues for the inclusion of liquidity and tail risk considerations, especially during market stress, as we also observe a greater need for more dynamic and adaptive modeling approaches that capture time-varying risk premia and factor loadings. The findings drive home the point that standard asset pricing models cannot be applied across the board in all market conditions and stress the need for developing more flexible and situation-specific valuation tools. Therefore, this research lies in its dual contribution, both in academic terms and practical finance, by providing an understanding of the behavior of asset pricing models in extreme markets and giving indications for future model development.

Automatic kidney stone identification: an adaptive feature-weighted LSTM model based on urine and blood routine analysis.

Kidney stones are the most common urinary system diseases, and early identification is of great significance. The purpose of this study was to use routine urine and blood detection indices to build a deep learning (DL) model to identify the presence of kidney stones in the early stage. A retrospective analysis was conducted on patients with kidney stones who were treated at West China Hospital of Sichuan University from January 2020 to June 2023. A total of 1130 individuals presenting with kidney stones and 1230 healthy subjects were enrolled. The first blood and urine laboratory data of participants at our hospital were collected, and the data were divided into a training dataset (80%) and a verification dataset (20%). Additionally, a long short-term memory (LSTM)-based adaptive feature weighting model was trained for the early identification of kidney stones, and the results were compared with those of other models. The performance of the model was evaluated by the area under the subject working characteristic curve (AUC). The important predictive factors are determined by ranking the characteristic importance of the predictive factors. A total of 17 variables were screened; among the top 4 characteristics according to the weight coefficient in this model, urine WBC, urine occult blood, qualitative urinary protein, and microcyte percentage had high predictive value for kidney stones in patients. The accuracy of the kidney stone (KS-LSTM) learning model was 89.5%, and the AUC was 0.95. Compared with other models, it has better performance. The results show that the KS-LSTM model based on routine urine and blood tests can accurately identify the presence of kidney stones. And provide valuable assistance for clinicians to identify kidney stones in the early stage.

The Application of a Modified Adaptive CS Model in Tracking and Predicting Maneuvering Targets on the Airport Surface

The Application of a Modified Adaptive CS Model in Tracking and Predicting Maneuvering Targets on the Airport Surface

Adaptive isogeometric gear contact analysis: Geometry generation, truncated hierarchical B-Spline refinement and validation

Gears are one of the most widely used transmission components. Their operation relies on the contact between mating gear teeth flanks for the transmission of power. Accurate prediction of the contact stresses at these regions, is crucial for the design and dimensioning of these systems. Gear design is centered around highly smooth involute curves that greatly influence their contact behaviour. In this paper, a fully adaptive isogeometric contact modelling scheme, based on hierarchical splines, is presented and applied to the simulation of gear contact problems. In particular, isogeometric simulation is performed for the modelling of mating pair of gear teeth, regarded as linearly elastic bodies. A boundary fitted B-Spline representation of the teeth is automatically generated from engineering design parameters and is used to define the initial discretisation basis. The numerical integration over the contact region is addressed using the so called, Gauss-Point to Surface formulation and a closest point projection procedure. Truncated hierarchical B-Splines are used to capture the highly localised nature of contact, while effectively reducing the number of degrees of freedom. The adaptivity is driven by the strain energy density gradient, which allows to automatically localise the mesh without a priori knowledge of the contact region between the teeth flanks. In our experiments we justify the choices made in different steps of our algorithm and we assess the performance of our adaptive solver with respect to classical tensor product B-Splines.

Adaptive interacting multiple model particle filter based on a dual-pattern bat algorithm for maneuvering target tracking

The interacting multiple model particle filter (IMM-PF) is a filtering method commonly used for nonlinear non-Gaussian radar systems. Its transfer probabilities are usually fixed and dependent on prior information. When tracking maneuvering targets, the IMM-PF may cause excessive tracking errors due to the model switching lag. In addition, the particle impoverishment caused by the resampling of the particle filter seriously affects the filtering accuracy. Therefore, the IMM-PF has difficulty meeting the accuracy and speed requirements of modern high-performance radar target tracking systems. To address these problems, an adaptive interacting multiple model particle filter based on the dual-pattern bat algorithm (ADIMM-DPBA-PF) is proposed for tracking maneuvering targets under nonlinear and non-Gaussian conditions. First, the adaptive model switching mechanism is established to adjust the transition probabilities using the model probability posterior information at consecutive times, improving the model switching efficiency. Second, a particle filter based on the dual-pattern bat algorithm (DPBA-PF) is proposed. The filter exploits global search and local search strategies to optimize the particles and intelligently move the particles to the high likelihood region. Finally, a particle filter based on the dual-pattern bat algorithm is used to form the adaptive interacting multiple model method. The experimental results show that the proposed algorithm has better comprehensive performance than the IMM-PF.

Enhanced Abandoned Object Detection through Adaptive Dual-Background Modeling and SAO-YOLO Integration

Abandoned object detection is a critical task in the field of public safety. However, existing methods perform poorly when detecting small and occluded objects, leading to high false detection and missed detection rates. To address this issue, this paper proposes an abandoned object detection method that integrates an adaptive dual-background model with SAO-YOLO (Small Abandoned Object YOLO). The goal is to reduce false and missed detection rates for small and occluded objects, thereby improving overall detection accuracy. First, the paper introduces an adaptive dual-background model that adjusts according to scene changes, reducing noise interference in the background model. When combined with an improved PFSM (Pixel-based Finite State Machine) model, this enhances detection accuracy and robustness. Next, a network model called SAO-YOLO is designed. Key improvements within this model include the SAO-FPN (Small Abandoned Object FPN) feature extraction network, which fully extracts features of small objects, and a lightweight decoupled head, SODHead (Small Object Detection Head), which precisely extracts local features and enhances detection accuracy through multi-scale feature fusion. Finally, experimental results show that SAO-YOLO increases mAP@0.5 and mAP@0.5:0.95 by 9.0% and 5.1%, respectively, over the baseline model. It outperforms other advanced detection models. Ultimately, after a series of experiments on the ABODA, PETS2006, and AVSS2007 datasets, the proposed method achieved an average detection precious of 91.1%, surpassing other advanced methods. It significantly outperforms other advanced detection methods. This approach notably reduces false and missed detections, especially for small and occluded objects.

WRF-HEATS coupling: Incorporating human behaviors and city topography into urban heat stress evaluation

Urban human thermal stress can be inaccurately estimated along with less-understood heat heterogeneity due to the absence of high-resolution meteorological information and realistic human behavior representation. To this end, we coupled a regional climate model (weather research and forecasting model, WRF) and a human energy balance model (human-environment adaptive thermal stress model, HEATS) to predict pedestrian's dynamic thermal stress at a neighborhood scale. The WRF-human coupling system resolves human-environment heat exchanges based on meteorological and topographical information with the consideration of dynamic human activities. The coupling system has been tested and utilized to study dynamic heat stress in a typical hot, humid, and mountainous city, Hong Kong. Our results revealed widespread heat heterogeneity with up to 7 °C difference in Physiological Subjective Temperature (PST) in the core urban area, and extreme heat exposure (up to 45 °C PST) in calm-wind zones at noon. Heat stress can be further aggregated considering realistic human behaviors such as extra clothing (e.g., protective facemask during pandemics) and physical exercise (e.g., walking along inclined terrain). Optimal-thermal-comfort routes have been designed and suggested based on the simulated neighborhood-scale heat stress map.

RNN-based linear parameter varying adaptive model predictive control for autonomous driving

Autonomous driving is a complex and highly dynamic process that ensures controlling the coupled longitudinal and lateral vehicle dynamics. Model predictive control, distinguished by its predictive feature, optimal performance, and ability to handle constraints, makes it one of the most promising tools for this type of control application. The content of this article handles the problem of autonomous driving by proposing an adaptive linear parameter varying model predictive controller (LPV-MPC), where the controller's prediction model is adaptive by means of a recurrent neural network. The proposed LPV-MPC is further optimised by a hybrid Genetic and Particle Swarm Optimization Algorithm (GA-PSO). The developed controller is tested and evaluated on a challenging track under variable wind disturbance.

Dual-level adaptive incongruity-enhanced model for multimodal sarcasm detection

Multimodal sarcasm detection leverages multimodal information, such as image, text, etc. to identify special instances whose superficial emotional expression is contrary to the actual emotion. Existing methods primarily focused on the incongruity between text and image information for sarcasm detection. Existing sarcasm methods in which the tendency of image encoders to encode similar images into similar vectors, and the introduction of noise in graph-level feature extraction due to negative correlations caused by the accumulation of GAT layers and the lack of representations for non-neighboring nodes. To address these limitations, we propose a Dual-Level Adaptive Incongruity-Enhanced Model (DAIE) to extract the incongruity between the text and image at both token and graph levels. At the token level, we bolster token-level contrastive learning with patch-based reconstructed image to capture common and specific features of images, thereby amplifying incongruities between text and images. At the graph level, we introduce adaptive graph contrast learning, coupled with negative pair similarity weights, to refine the feature representation of the model’s textual and visual graph nodes, while also enhancing the information exchange among neighboring nodes. We conduct experiments using a publicly available sarcasm detection dataset. The results demonstrate the effectiveness of our method, outperforming several state-of-the-art approaches by 3.33% and 4.34% on accuracy and F1 score, respectively.

Pulsar Signal Adaptive Surrogate Modeling

As the number of spacecraft heading beyond Earth’s orbit increased in recent years, autonomous navigation solutions have become increasingly important. One such solution is pulsar-based navigation. The availability of pulsar signals for simulations and HIL testing is essential for the development of pulsar-based navigation. This study proposes a method to develop a surrogate model of pulsar signals based on radio pulsar observations. The selection of suitable pulsars for the radio telescope is discussed, and a series of observations are conducted. The collected data are processed using the PRESTO software, and the pulsar parameters for the model are derived. Unlike current pulsar signal models, the proposed model anticipates pulsar signal parameters to change over time. It can provide dynamic input parameters for known synthetic pulsar signal generators, resulting in a more realistic signal.