Adaptive Framework Research Articles

Adaptive sensor attack detection and defense framework for autonomous vehicles based on density

The security of autonomous vehicles heavily depends on localization systems that integrate multiple sensors, which are vulnerable to sensor attacks and increase the risk of accidents. Given the diversity of sensor attacks and the dynamic changing of driving scenarios of autonomous vehicles, an adaptive and effective attack detection and defense framework faces a considerable challenge. This paper proposes a novel real-time adaptive attack detection and defense framework based on density, which can detect and identify attacked sensors and effectively recover data. We first develop a reinforcement learning multi-armed Bandit-based Density-Based Spatial Clustering of Applications with Noise (BDBSCAN) algorithm that selects hyperparameters adaptively. The Adaptive Extended Kalman Filter (AEKF) combines with the vehicle dynamic model on the localization system and extracts data features used for the BDBSCAN algorithm to monitor potential sensor attacks. If attack detection indicates possible system compromise, AEKF is further employed on localization sensors with anomalies identified through the BDBSCAN algorithm of the attacked sensors. To ensure precision and reliability, the data recovery incorporates a redundancy mechanism to apply a decision tree to select the optimal state estimation between AEKF and Extended Kalman Filter (EKF) to replace corrupted sensor data. To evaluate the effectiveness and adaptability of the proposed framework, we conducted 15,000 experiments using the real-world KITTI and V2V4Real datasets across various driving and sensor attack scenarios. The results demonstrate that our proposed framework achieves 100% accuracy and 0% false alarm rate in various driving scenarios for attack detection within 0.15 s, with a recovery time of 0.08 s.

Frequency domain adaptive framework for visible-infrared person re-identification

Frequency domain adaptive framework for visible-infrared person re-identification

Evolution of Information Technology: A Comprehensive Review

Pervasive computing, wireless sensor networks, and M2M communication have fuelled the Internet of Things. The IoT connects and interacts with many physical items using unique internet addresses. This article covers the structure and technologies of the Internet of Things (IoT). The Internet of Things (IoT) needs a standard structure. Thus, it begins with a complete explanation of architectural designs and then discusses communication protocols and standards. The article also includes a succinct review of common IoT protocols and standards, helping the reader comprehend the topic. It also provides concrete solutions and tactics for addressing Internet of Things issues. The essay culminates by demonstrating the practical applications of the Internet of Things (IoT). Nolan's Stages Theory offered a new perspective on commercial IT development in 1973. The rapid digital revolution has changed its underlying foundation, despite its continuous use. The initial idea focused on IT in production. Later, it expanded to include the complex relationship between IT and organisational strategy. Since its inception, the methodology has helped business and IT leaders navigate IT adoption without technical details. Nolan's Stages Theory still applies, but cloud computing, artificial intelligence, big data, and the Internet of Things require a more evolved approach. The rapid progress of technology has blurred the barriers between IT and other company functions, requiring a complete digital transformation strategy. Information systems and organisational structures have grown in importance and interconnection. As firms gained independence and flexibility, IT systems developed. IT integration into key company activities has transformed it into a strategic enabler. Nolan's strict methodology provides valuable insights into history, but it limits understanding of the dynamic and transformational forces altering the digital landscape. Contemporary studies emphasise the need for flexible and adaptive frameworks to accommodate the rapid pace of technological advances and their impact on organisational structures and business models. Nolan's Stages Theory is still significant in IT administration, although it has limitations in today's networked and data-driven business contexts. Future research should develop sophisticated and forward-thinking models to help organizations navigate the digital transition.

Equitable stormwater utility fees: an integrated analysis of environmental, socioeconomic and infrastructure factors at the community scale

Abstract Municipalities worldwide implement stormwater management programs to mitigate the hydrological and water quality impacts of stormwater runoff. Stormwater utility fees (SWUF) are often used to fund such important programs by collecting revenue from residential and commercial properties. However, existing SWUFs often solely rely on the estimate of impervious surfaces and do not consider other environmental, infrastructure, and socioeconomic factors in the generation and effects of stormwater runoff. This study is the first attempt to propose a reconstruction of SWUFs from the perspectives of social equity and environmental justice. The method aims to address disparities in fee rates among residential parcels, focusing on helping economically disadvantaged communities. It integrates drainage service, potential contribution to non-point source pollution, and socioeconomic status through two alternative schemes. The two schemes allocate fees based on combined rankings of the three factors at the level of census block groups. The proposed method was applied to 88 180 residential parcels in Corpus Christi, Texas, a mid-sized coastal community. The results suggest that over 70% of the disadvantaged communities would benefit from the reconstructed SWUFs without affecting the targeted funding for stormwater infrastructure. This method builds on publicly available datasets and offers an adaptive framework for other municipalities to incorporate additional factors or datasets, representing an exploratory step toward achieving more equitable stormwater management practices.

Appreciating dyslexic thinking in qualitative research: reflections and recommendations for culturally competent, neuro-inclusive academia

AbstractDyslexia and its associated learning challenges are often misconstrued as intellectual deficits, leading to erroneous assumptions that individuals with dyslexia cannot thrive or contribute meaningfully to academic institutions. However, this article contends that the unique thinking patterns associated with dyslexia are complementary to and can substantially enrich the professional practice of qualitative research. The social model of disability emphasises how Higher Education Institutions, rooted in ableist and neurotypical norms, often marginalise and fail to accommodate dyslexic cognitive profiles. Conversely, cultural competency, as an actionable conceptual framework, calls for transformative changes that promote understanding, build meaningful relationships, and ensure effective communication with neurodivergent individuals. Drawing on my experience as a dyslexic academic, I examine critical discussions on disability, neurodiversity, higher education, and qualitative research. Adopting an autoethnographic methodological approach, I highlight my professional strengths within this context, and propose an adaptable cultural competency framework aimed at cultivating neuro-inclusive—and specifically dyslexic-friendly practices, at the individual and organisational levels within academia.

Direct MultiSearch optimization of TPMS scaffolds for bone tissue engineering

BackgroundScaffolds designed for tissue engineering must consider multiple parameters, namely the permeability of the design and the wall shear stress experienced by the cells on the scaffold surface. However, these parameters are not independent from each other, with changes that improve wall shear stress, negatively impacting permeability and vice versa. This study introduces a novel multi-objective optimization framework using Direct MultiSearch (DMS) to design triply periodic minimal surface (TPMS) scaffolds for bone tissue engineering. MethodThe optimization algorithm focused on maximizing the permeability of the scaffolds and obtaining a desired value of average wall shear stress (which ranges between the values that promote osteogenic differentiation of 0.1 mPa and 10 mPa). Multiple fluid inlet velocities and target wall shear stress were analyzed. The DMS method successfully generated Pareto fronts for each configuration, enabling the selection of optimized scaffolds based on specific structural requirements. ResultsThe findings reveal that increasing the target wall shear stress results in a greater number of non-dominated points on the Pareto front, highlighting a more robust optimization process. Additionally, it was also demonstrated that the tested Schwartz diamond scaffolds had a better permeability-wall shear stress relation when compared to Schoen gyroid geometries. ConclusionsDirect MultiSearch was proven as an effective tool to aid in the design of tissue engineering scaffolds. This adaptable optimization framework has potential applications beyond bone tissue engineering, including cartilage tissue differentiation.

Translation and cultural adaptation of evidence-informed leaflets on the work-health interface: a pragmatic approach to cultural adaptation.

Our aim was to translate and culturally adapt three evidence-informed leaflets on the work-health interface from English into Norwegian. Integral to this aim was the exploration of the quality and acceptability of each of the adapted leaflets to Norwegian-speaking stakeholders; general practitioners, people who deal with health issues in the workplace, and the general population. Common health problems, such as musculoskeletal pain, account for most workdays lost and disability benefits in Norway. To facilitate return to work, it may be important to have access to evidence-informed information on the work-health interface for stakeholders involved in sickness absence processes. However, there is limited information material available in Norwegian that is tailored for the different stakeholders. Cultural adaptation is an emerging strategy for implementing health information across different populations and regions. Guidelines on cultural adaptation are not well-suited for translating and adapting evidence-informed health information material. We conducted a pragmatic cultural adaptation process informed by existing guidelines. Our conceptual framework for adaptation is situated between adaptation and translation and comprises appraisal, forward- and back-translation, review in multiple steps, sense checking, and re-designing using a transcreation approach. Using an online survey, we aimed to evaluate the overall quality, value, acceptability, and clarity of each of the adapted leaflets to a total of 30 end-users. We translated and culturally adapted three leaflets from English to Norwegian. Adapted leaflets were found to be clearly presented, acceptable, and valued by 45 Norwegian end-users. No differences in key concepts between original and back-translated leaflets emerged through the review process by the original author and forward translators. We used a pragmatic approach in this study that might be useful to others culturally adapting evidence-informed health information material.

Improved phenology-based rice mapping algorithm by integrating optical and radar data

Information on rice planting areas is critically important for food and water security, as well as for adapting to climate change. Mapping rice globally remains challenging due to the diverse climatic conditions and various rice cropping systems worldwide. Synthetic Aperture Radar (SAR) data, which is immune to climatic conditions, plays a vital role in rice mapping in cloudy, rainy, low-latitude regions but it suffers from commission errors in high-latitude regions. Conversely, optical data performs well in high-latitude regions due to its high observation frequency and less cloud contamination but faces significant omission errors in low-latitude regions. An effective integrated method that combines both data types is key to global rice mapping. Here, we propose a novel adaptive rice mapping framework named Rice-Sentinel that combines Sentinel-1 and Sentinel-2 data. First, we extracted key phenological phases of rice (e.g., the flooding and transplanting phase and the rapid growth phase), by analyzing the characteristic V-shaped changes in the Sentinel-1 VH curve. Second, we identified potential flooding signals in rice pixels by integrating the VH time series from Sentinel-1 with the Land Surface Water Index (LSWI) and Enhanced Vegetation Index (EVI) from Sentinel-2, utilizing the generated phenology phases. Third, the rapid growth signals of rice following its flooding phase were identified using Sentinel-2 data. Finally, rice fields were identified by integrating flooding and rapid growth signals. The resultant rice maps in six different case regions of the world (Northeast and South China, California, USA, Mekong Delta of Vietnam, Sakata City in Japan, and Mali in Africa) showed overall accuracies over 90 % and F1 scores over 0.91, outperforming the existing methods and products. This algorithm combines the strengths of both optical and SAR time series data and leverages biophysical principles to generate robust rice maps without relying on any prior ground truth samples. It is well-positioned for global applications and is expected to contribute to global rice monitoring efforts.

SkipNet: an adaptive neural network equalization algorithm for future passive optical networking

In this paper, we propose an original adaptive neural network equalizer (NNE) algorithm named SkipNet, which is suitable for rapid training on a packet-by-packet basis for burst-mode non-linear equalization in upstream PON transmission. SkipNet uses the simple LMS algorithm and avoids complex neural network training algorithms such as backpropagation and mini-batch training. We demonstrate SkipNet on captured continuous mode 100 Gbit/s PAM4 signals using an SOA preamplifier to achieve the challenging 29 dB PON optical loss budget. The adaptive SkipNet equalizer is shown to overcome combinations of severe SOA patterning effects and fiber dispersion impairments to achieve >29dB dynamic range back-to-back and >22.9dB dynamic range for up to 81.6 ps/nm accumulated dispersion. It can adapt in as little as 250 training symbols to each impairment scenario, which is equivalent to existing FFE/DFE solutions, while matching the non-linear performance of previously proposed static NNE solutions. To the best of our knowledge, SkipNet is the first ever adaptive NNE framework that can realistically be trained and adapted on a packet-by-packet basis and within strict PON packet preamble lengths.

United Voices Group-Singing Intervention to Address Loneliness and Social Isolation Among Older People With HIV During the COVID-19 Pandemic: Intervention Adaption Study.

People living with HIV experience HIV stigma alongside a spectrum of aging-related health conditions that accelerate their vulnerability to the ill effects of loneliness and social isolation. Group-singing interventions are efficacious in improving psychosocial well-being among older people in the general population; however, the social curative effects of group singing have not been explored in relation to HIV stigma. By promoting group identification, bonding, and pride, group singing may reduce loneliness, social isolation, and other negative impacts of HIV stigma among older people living with HIV. Access to group-singing programs may be enhanced by technology. While group singing has been extensively studied in older adults, group-singing interventions have not been adapted for older people living with HIV to target loneliness and social isolation in the context of HIV stigma. The objective of this study was to describe the systematic development of a group-singing intervention to reduce loneliness and social isolation among older people living with HIV. In the San Francisco Bay Area between February 2019 and October 2019, we engaged older people living with HIV in a rigorous, 8-stage, community-engaged intervention adaptation process using the Assessment, Decision, Adaptation, Production, Topical Experts, Integration, Training, and Testing (ADAPT-ITT) framework. On the basis of a formative assessment of the needs and preferences of older people living with HIV, we selected an evidence-based group-singing intervention for older adults and systematically adapted the intervention components by administering them to a community advisory council (n=13). The result was United Voices, a 12-week hybrid (web-based and in-person) group-singing intervention for older people living with HIV. United Voices comprises 12 web-based (ie, via Zoom [Zoom Video Communications]) rehearsals, web-based and in-person drop-in helpdesk sessions, and a professionally produced final concert recording. Through an iterative process and in consultation with stakeholders and topic experts, we refined and manualized United Voices and finalized the design of a pilot randomized controlled trial to evaluate the feasibility and acceptability of the intervention protocol and procedures. The findings provide insights into the barriers and facilitators involved in culturally tailoring interventions for older people living with HIV, implementing intervention adaptations within web-based environments, and the promise of developing hybrid music-based interventions for older adults with HIV.

AWDP-FL: An Adaptive Differential Privacy Federated Learning Framework

Data security and user privacy concerns are receiving increasing attention. Federated learning models based on differential privacy offer a distributed machine learning framework that protects data privacy. However, the noise introduced by the differential privacy mechanism may affect the model’s usability, especially when reasonable gradient clipping is absent. Fluctuations in the gradients can lead to issues like gradient explosion, compromising training stability and potentially leaking privacy. Therefore, gradient clipping has become a crucial method for protecting both model performance and data privacy. To balance privacy protection and model performance, we propose the Adaptive Weight-Based Differential Privacy Federated Learning (AWDP-FL) framework, which processes model gradient parameters at the neural network layer level. First, by designing and recording the change trends of two-layer historical gradient sequences, we analyze and predict gradient variations in the current iteration and calculate the corresponding weight values. Then, based on these weights, we perform adaptive gradient clipping for each data point in each training batch, which is followed by gradient momentum updates based on the third moment. Before uploading the parameters, Gaussian noise is added to protect privacy while maintaining model accuracy. Theoretical analysis and experimental results validate the effectiveness of this framework under strong privacy constraints.

Active Learning of Boltzmann Samplers and Potential Energies with Quantum Mechanical Accuracy.

Extracting consistent statistics between relevant free energy minima of a molecular system is essential for physics, chemistry, and biology. Molecular dynamics (MD) simulations can aid in this task but are computationally expensive, especially for systems that require quantum accuracy. To overcome this challenge, we developed an approach combining enhanced sampling with deep generative models and active learning of a machine learning potential (MLP). We introduce an adaptive Markov chain Monte Carlo framework that enables the training of one normalizing flow (NF) and one MLP per state, achieving rapid convergence toward the Boltzmann distribution. Leveraging the trained NF and MLP models, we compute thermodynamic observables such as free energy differences and optical spectra. We apply this method to study the isomerization of an ultrasmall silver nanocluster belonging to a set of systems with diverse applications in the fields of medicine and catalysis.

The need for a risk management framework for data science projects: a systematic literature review

Many data science endeavors encounter failure, surfacing at any project phase. Even after successful deployments, data science projects grapple with ethical dilemmas, such as bias and discrimination. Current project management methodologies prioritize efficiency and cost savings over risk management. The methodologies largely overlook the diverse risks of sociotechnical systems and risk articulation inherent in data science lifecycles. Conversely, while the established risk management framework (RMF) by NIST and McKinsey aims to manage AI risks, there is a heavy reliance on normative definitions of risk, neglecting the multifaceted subjectivities of data science project failures. This paper reports on a systematic literature review that identifies three main themes: Big Data Execution Issues, Demand for a Risk Management Framework tailored for Large-Scale Data Science Projects, and the need for a General Risk Management Framework for all Data Science Endeavors. Another overarching focus is on how risk is articulated by the institution and the practitioners. The paper discusses a novel and adaptive data science risk management framework – “DS EthiCo RMF” – which merges project management, ethics, and risk management for diverse data science projects into one holistic framework. This agile risk management framework DS EthiCo RMF can bridge the current divide between normative risk standards and the multitude of data science requirements, offering a human-centric method to navigate the intertwined sociotechnical risks of failure in data science projects.

Towards enhanced metamaterials via shape memory alloy-embedded nonlinear resonators

Standard acoustic metamaterials create an attenuation around specific frequency bands. Finite structures, with distinct boundary conditions and a limited number of unit cells, present less attenuation and narrower bands than those predicted by idealized infinite systems. A critical engineering goal is enhancing performance to motivate practical applications. To that aim, this work incorporates shape memory alloys into a quasi-zero stiffness resonator design, allowing the tuning of each cell's internal resonance. Such a feature enables the system reconfiguration to achieve different purposes, from following a disturbance frequency fluctuation to realizing graded nonlinear metamaterials. While the former can work under an adaptive framework, the latter can result in time-invariant locally resonant metamaterials with wideband vibration attenuation. The proposed design combines a frame that axially compresses an SMA beam in the vicinity of its buckling. The critical buckling force changes by thermally activating the SMA, affecting the residual stiffness, hence the unit cell resonant frequency. The unit cell concept is developed analytically and via finite elements, then built and validated experimentally. The promising results indicate the viability of the proposed concept. Preliminary numerical simulations and experiments show the advantages of the proposed smart resonator over a linear time-invariant counterpart.

Test time adaptation for cross-domain sleep stage classification

Domain shift is a serious problem with existing cross-domain sleep stage classification methods. However, most existing domain adaptation methods require access to a large amount of source domain data containing patient information, which may lead to infringement of patient privacy. At the same time, existing methods require collecting all information in advance when processing target data, which cannot meet the situation where test data arrives in batches or in order in actual scenarios. To this end, we propose a test time adaptation framework based on knowledge distillation for cross-domain sleep stage classification. This teacher-student network framework uses pre-trained model to learn variant features and robust representations. We evaluate our framework in the cross domain scenario composed of three datasets and validate its superiority, real time performance and privacy protection capability.

MetaFollower: Adaptable personalized autonomous car following

Car-following (CF) modeling, a fundamental component in microscopic traffic simulation, has attracted increasing research interest in recent decades. In this study, we propose an adaptable personalized car-following framework —– MetaFollower, by leveraging the power of meta-learning. Specifically, we first utilize Model-Agnostic Meta-Learning (MAML) to extract common driving knowledge from various CF events. Afterward, the pre-trained model can be fine-tuned on new drivers with only a few CF trajectories to achieve personalized CF adaptation. We additionally combine Long Short-Term Memory (LSTM) and Intelligent Driver Model (IDM) to reflect temporal heterogeneity with high interpretability. MetaFollower can accurately capture and simulate the intricate dynamics of car-following behavior while considering the unique driving styles of individual drivers. We demonstrate the versatility and adaptability of MetaFollower by showcasing its ability to adapt to new drivers with limited training data quickly. To evaluate the performance of MetaFollower, we conduct rigorous experiments comparing it with both data-driven and physics-based models. The results reveal that our proposed framework outperforms baseline models in predicting car-following behavior with higher accuracy and safety. To the best of our knowledge, this is the first car-following model aiming to achieve fast adaptation by considering both driver and temporal heterogeneity based on meta-learning.

Application of a multi-source multi-task weight adaptation framework for cross-domain EEG emotion recognition(MS-MWA)

Application of a multi-source multi-task weight adaptation framework for cross-domain EEG emotion recognition(MS-MWA)

Adaptive scaled boundary finite element method for hydrogen assisted cracking with phase field model

This study introduces a numerical framework for analysing hydrogen assisted cracking, employing the scaled boundary finite element method. This is the first instance where the scaled boundary finite element method is employed to model hydrogen embrittlement. The phase field model is utilized to simulate defects, complemented by adaptive meshing using polytree mesh. The ability of the scaled boundary finite element method to treat polygonal elements assists in mitigating the problem of hanging nodes that arises from polytree decomposition. The adaptive framework is developed to predict crack propagation using an initial unstructured quadrilateral mesh generated from any commercial software. The hydrogen atom concentration depends on the hydrostatic stress gradient, which is calculated by interpolating nodal hydrostatic stress with scaled boundary shape functions and taking the gradient. A staggered solution approach is adopted to concurrently tackle hydrogen transport, elasticity, and phase field equations. The methodology is validated using Mode-I edge notch specimens and analysing crack propagation from corrosion pits, with results demonstrating close agreement with existing data. Subsequently, the framework is extended to address more intricate scenarios, such as crack propagation in X-shaped plates and hydrogen transmission in tanks. As the last example, more advanced image based fracture analysis of weld structure is investigated. This example studies the possibility of analysing the hydrogen diffusion directly from TEM imagery. Moreover, we investigate how hydrogen concentration influences structural failure.

Finite-time output-feedback fault tolerant adaptive fuzzy control framework for a class of MIMO saturated nonlinear systems

This paper presents a finite-time fault-tolerant fuzzy adaptive controller for uncertain interconnected nonlinear systems in strict-feedback form. The controller addresses input saturation, state-dependent actuator faults, external disturbances, and unavailable states for measurement. To avoid any unexpected alteration due to failures, the proposed control scheme design addresses all types of actuator faults that are bias, drift, and loss of accuracy as additive faults, as well as a multiplicative fault that results in loss of effectiveness with nonaffine state-dependency. Restrictions on control gains and unmatched interconnections are eliminated, and the explosion complexity caused by recursive back-stepping designs is avoided. Fuzzy Systems approximate the unknown ideal control laws along side the acutator faults and disturbances. The stability analysis guarantees that tracking errors converge to a small compact set around the origin in finite time. Simulation results on a quad-rotor UAV and a mathematical system confirm the effectiveness of the proposed approach.

Learn Then Adapt: A Novel Test-Time Adaptation Method for Cross-Domain Fault Diagnosis of Rolling Bearings

Cross-domain fault diagnosis enhances the generalization capability of diagnostic models across different operating conditions and machines. Current studies tackle the domain shift problem by adapting the model during training with data from the target domain or multiple source domains. However, a more realistic and less explored scenario is automatically adapting a trained (developed) model at test time (deployment period) using limited normal-condition data. To bridge this research gap, we propose a novel test-time adaptation framework to rapidly and effectively adapt the trained model, which only requires mini-batch test data (normal condition). Specifically, we first transform input signals to informative signal embedding and mitigate its noise with a reconstruction loss. Then, we decompose the signal embedding to the domain-related healthy component and the domain-invariant faulty component to better leverage the normal-condition data. Finally, we adapt the model by re-identifying the normal signals of the target domain during the test stage. Extensive experiments verify the effectiveness of our method, demonstrating performance improvements across public and private datasets.