Adaptive Space Research Articles

Managing human-AI collaborations within Industry 5.0 scenarios via knowledge graphs: key challenges and lessons learned

In this paper, we discuss technologies and approaches based on Knowledge Graphs (KGs) that enable the management of inline human interventions in AI-assisted manufacturing processes in Industry 5.0 under potentially changing conditions in order to maintain or improve the overall system performance. Whereas KG-based systems are commonly based on a static view with their structure fixed at design time, we argue that the dynamic challenge of inline Human-AI (H-AI) collaboration in industrial settings calls for a late shaping design principle. In contrast to early shaping, which determines the system's behavior at design time in a fine granular manner, late shaping is a coarse-to-fine approach that leaves more space for fine-tuning, adaptation and integration of human intelligence at runtime. In this context we discuss approaches and lessons learned from the European manufacturing project Teaming.AI, https://www.teamingai-project.eu/, addressing general challenges like the modeling of domain expertise with particular focus on vertical knowledge integration, as well as challenges linked to an industrial KG of choice, such as its dynamic population and the late shaping of KG embeddings as the foundation of relational machine learning models which have emerged as an effective tool for exploiting graph-structured data to infer new insights.

Convergent evolution in shape in European lineages of gobies.

During their radiation, certain groups of animals evolved significant phenotypic disparity (morphological diversity), enabling them to thrive in diverse environments. Adaptations to the same type of environment can lead to convergent evolution in function and morphology. However, well-documented examples in repeated adaptations of teleost fishes to different habitats, which are not primarily related to trophic specialization, are still scarce. Gobies are a remarkable fish group, exhibiting a great species diversity, morphological variability, and extraordinary ability to colonize very different environments. A variety of lifestyles and body forms evolved also in European lineages of gobies. We conducted two-dimensional geometric morphometric and phylomorphospace analyses in European lineages of gobies and evaluated the extent of convergent evolution in shape associated with adaptation to various habitats. Our analyses revealed the change in shape along the nektonic-cryptobenthic axis, from very slender head and body to stout body and wide head. We showed convergent evolution related to mode of locomotion in the given habitat in four ecological groups: nektonic, hyperbenthic, cryptobenthic and freshwater gobies. Gobies, therefore, emerge as a highly diversified lineage with unique lifestyle variations, offering invaluable insights into filling of ecomorphological space and mechanisms of adaptation to various aquatic environments with distinct locomotion requirements.

12 tips for integrating the 12 Practitioner Values to improve clinical supervision for neurodiverse learners

With the NHS Long Term Workforce Plan requiring clinical placements to accommodate up to 50% more learners, the pressure on clinical educators to maintain high-quality learning environments is becoming increasingly intense. Neurodiverse learners face significant barriers in busy, fast-paced environments, making the cultivation of supportive and adaptive learning spaces essential to ensure all learners have the opportunity to thrive in a healthcare system under immense demand. This article is aimed at empowering clinical educators to lead inclusive placements through implementation of advanced supervision skills to support neurodiverse learners. These are presented as 12 practical strategies, each aligned with the 12 Practitioner Values, for fostering inclusive professional relationships. By offering actionable ‘tips’, this article addresses both the moral imperative to meet diverse learning needs and the systemic necessity of building a more inclusive workforce.

Feature correlation fusion and feature selection under adaptive neighborhood group approximation space

Feature correlation fusion and feature selection under adaptive neighborhood group approximation space

Building sustainable mitigation through adaptive green open space on tanjung mas sub district

Abstract Mitigation is a step to reduce the risk of disasters in a particular area. Tanjung Mas sub-district is an area that has a high potential for land subsidence and tidal flooding because it is located on the North Coast of Java. Temporary evacuation points are urgently needed to protect residents from the dangers of tidal floods and distribute logistics from volunteers. Based on community preferences, the Green Open Space in Tambak Lorok are used as an evacuation point for flood disasters. The green open space, which was initially used for sustainable water absorption, was converted into an evacuation point as a flood disaster mitigation measure. This research aims to measure the suitability of green open space as a temporary evacuation site. The research method used is a Space Syntax approach and qualitative description analysis. Based on the results of the analysis, almost all the requirements for evacuation places by the green open space location. It is easily accessible because it is on the primary residential route, easily accessible by vehicles, and has building structures higher than the road. However, the area of green open space still needs to be increased for the minimum standard capacity per person. Apart from that, the infrastructure to support evacuation, such as electricity, communication equipment, or rubber boats, needs to be improved. The construction of green open space as a temporary evacuation site needs to be adjusted to minimum standards and the needs of the population. It is also hoped that the development of green open space will be the responsibility of not only the government but also cooperation between stakeholders. Green open space isn’t just for environment impacts, but can also increase the community resilience.

Adaptive reduced basis trust region methods for parameter identification problems

In this contribution, we are concerned with model order reduction in the context of iterative regularization methods for the solution of inverse problems arising from parameter identification in elliptic partial differential equations. Such methods typically require a large number of forward solutions, which makes the use of the reduced basis method attractive to reduce computational complexity. However, the considered inverse problems are typically ill-posed due to their infinite-dimensional parameter space. Moreover, the infinite-dimensional parameter space makes it impossible to build and certify classical reduced-order models efficiently in a so-called “offline phase”. We thus propose a new algorithm that adaptively builds a reduced parameter space in the online phase. The enrichment of the reduced parameter space is naturally inherited from the Tikhonov regularization within an iteratively regularized Gauß-Newton method. Finally, the adaptive parameter space reduction is combined with a certified reduced basis state space reduction within an adaptive error-aware trust region framework. Numerical experiments are presented to show the efficiency of the combined parameter and state space reduction for inverse parameter identification problems with distributed reaction or diffusion coefficients.

State Space Model Reference Adaptive Control for a Class of Second-Degree Fractional Order Systems with Different Eigenvalues

This study proposes an adaptive control synthesis for a class of second-degree fractional order systems with different eigenvalues in the state-space domain. The proposed fractional order adaptive controller is a generalization of the MRAC controller for the class of scalar fractional order systems. In order to control the fractional order plant, an adaptive state space feedback controller is applied based on the error between the system output and a chosen reference model using a fractional adaptation law to make the fractional order plant track the fractional order reference model. We show that the resulting adaptive regulator is able to stabilize the fractional order second degree system with a satisfying performance. A simulation example illustrating these performance properties is provided along with a comparison with a fractional order sliding mode control (FOSMC) to demonstrate the superiority of the proposed control scheme.

A study on an improved laser speckle contrast blood flow imaging methodology

The laser speckle contrast imaging technique based on the dynamic light scattering theory presents a non-scanning and wide-field method for blood flow imaging. However, its accuracy in biological tissues is limited to the decreased contrast and reduced image clarity as conventional single-exposure approaches are susceptible to static scattering. In this paper, based on the adaptive window space direction contrast (awsdK) imaging method proposed by the laboratory, combined with the optimized single exposure technology, the effect of static scattering under a single exposure is reduced. The experimental results show that the method can effectively correct static scattering and eliminate the effect of system noise on speckle contrast. This method not only improves the imaging quality, but also realizes the rapid monitoring of blood flow changes by using the speckle contrast ratio measured in a single exposure, which provides an effective solution for the further development of laser speckle contrast imaging technology.

Behaviour setting transformation methodology, filling in the gaps of the conventional architectural design process.

This article recounts 6 years of empirical research in a humanitarian context on spatial behaviour using the behaviour settings theory. This research journey details the shortcomings of conventional architectural processes and the subsequent development of a human-centred behaviour setting methodology that drives behaviour change for adaptable spaces. The research work puts Barker's theory of behaviour settings into practice to show its significant methodological abilities in shaping behaviours through spaces. While the original theory was solely an analytical account of existing behaviours in certain settings, this study marks the first pragmatic exploration of the theory into both residential and refugee contexts. The methodology that is subsequently proposed is a complementary tool to account for the deficiencies of conventional architectural design processes. A method that enables one to fully immerse themselves in the environment, recognize specific architectural interventions, assess their effects and reiterate. It is a proposal for humanizing architecture, sympathizing its processes and personalizing its results for the users of any space. This article is part of the theme issue 'People, places, things, and communities: expanding behaviour settings theory in the twenty-first century'.

An adaptive feature mode decomposition-guided phase space feature extraction method for rolling bearing fault diagnosis

Abstract The extraction of fault features from rolling bearings is a challenging and highly important task. Since they have complex operating conditions and are usually under a strong noise background. In this study, a novel approach termed phase space feature extraction guided by an adaptive feature mode decomposition (AFMDPSFE) is proposed to detect subtle faults in rolling bearings. Initially, a new method using Kullback-Leiber divergence is introduced to automatically select the optimal mode number and filter length for the decomposition of vibration signals, facilitating the automatic extraction of optimal components and ensuring efficient screening. This eliminates the need for manual configuration of feature mode decomposition parameters. Furthermore, a criterion that could determine two crucial parameters to capture system dynamics characteristics in phase space reconstruction is embedded into AFMDPSFE algorithm. Subsequently, a series of high-dimensional independent components is derived. The envelope spectrum of the principal component exhibiting the highest kurtosis value is computed to achieve fault identification, consequently enhancing the separation of signal from noise. Both simulations and experimental results confirm the effectiveness of AFMDPSFE approach. A comparison analysis shows the excellent performance of AFMDPSFE in extracting fault features from significant noise interference.

A global adaptive discretization of velocity space for discrete velocity methods in predictions of rarefied and multi-scale flows

By introducing a discrete velocity space (DVS), deterministic methods in gas-kinetic theory, such as the discrete velocity method (DVM) and unified methods, can accurately capture complex nonequilibrium distribution functions and describe rarefied flow behaviors. However, describing high-speed flows with conventional Cartesian DVS is prohibitively costly due to the large number of discrete velocity points. Therefore, to enable deterministic solvers to handle complex, rarefied, and multi-scale flows effectively, a novel adaptive velocity space (AVS) is proposed. First, a global velocity mesh is intentionally adopted instead of a local velocity mesh to maintain a high level of DVS parallelism and facilitate extension to implicit algorithms. The global AVS is robust as it avoids the instability of information transformation between different cell-local AVS. Second, a new strategy is developed for reconstructing the distribution function in the tree-structured AVS, which is a low-order reconstruction with forced macroscopic conservation. This low-order reconstruction facilitates the direct value assignment between farther and child nodes, avoiding the derivative calculation of the distribution function (which is sometimes discontinuous). Additionally, the integration error of the low-order reconstruction is fixed by the forced macroscopic conservation. With these two important improvements, the proposed global AVS is then integrated into general DVM frameworks, such as the unified gas-kinetic scheme. Finally, a number of numerical tests are carried out to validate the proposed method, including steady and unsteady multi-scale flows.

DEEP NEURAL MULTI WAVELET SEGMENTATION AND RESNET-50 IMAGE CLASSIFICATION (DNMWS-RESNET-50IC) BASED EARLY GLAUCOMA DETECTION

Glaucoma, a leading cause of irreversible blindness worldwide, results from progressive damage to the optic nerve, often linked to elevated Intra Ocular Pressure (IOP). Early detection is critical for preventing vision loss, yet traditional diagnostic methods can be limited in accessibility and effectiveness, particularly in the early stages of the disease. Addressing the need for early detection, we propose the Deep Neural Multi-Wavelet Segmentation and ResNet-50 Image Classification (DNMWS-ResNet-50IC) method, specifically designed to detect glaucoma at an early stage using retinal fundus images. In this work, we apply Anisotropic Gaussian Filtering for the preprocessing of retinal fundus images, effectively reducing image noise while preserving the original quality of the image pixels by creating an adaptive window size and scale space. We then utilize multi- wavelet-based image segmentation, leveraging wavelet transforms to analyze and decompose the image into its various frequency components. This technique is particularly advantageous for managing images with complex structures and textures. Subsequently, the segmented features are classified using the ResNet-50 model, which categorizes the images as normal, abnormal, or indicative of early- stage glaucoma. The effectiveness of the proposed method is assessed by measuring three key performance indicators sensitivity, specificity, and accuracy on digital retinal images from the HRF image database. Additionally, the model's performance is further evaluated on a separate test set, considering metrics such as accuracy, precision, recall, and prediction time.

Visual and acoustic discomfort: A comparative study of impacts on individuals with and without ADHD using electroencephalogram (EEG)

The vision of smart buildings that aim to be inclusive needs to take into consideration the diversity of human needs and the various ways in which individuals interact with and experience built environments. This contribution focuses on neurodiversity, specifically investigating how certain design choices and qualities of indoor environments can have distinct impacts on individuals with Attention-Deficit/Hyperactivity Disorder (ADHD). In a controlled laboratory setting, we created six conditions with modified lighting and sound designs. Participants (14 with and 13 without ADHD) were asked to perform an on-screen activity within these conditions, which were randomly ordered. The collected data includes biosignals from three devices including 32-channel electroencephalogram (EEG), eye-tracker, health monitoring bracelet, as well as task performance and self-reported comfort levels. We observed significant differences in the EEG data, suggesting the activation of a specific brain activity – a defense system – in situations of discomfort, but only for participants without ADHD. Such observed defense system against uncomfortable environmental conditions seems to be lacking, slow, or weak in participants with ADHD. This difference in neuro-responses underscores the necessity to design adaptive spaces that cater to a broad spectrum of sensory experiences. As we navigate the future of smart environment design, our research accentuates the importance of recognizing and accommodating the diverse sensory responses of individuals, thereby progressing towards truly neuro-inclusive built environments.

Social Type-Aware Navigation Framework for Mobile Robots in Human-Shared Environments.

As robots become increasingly common in human-populated environments, they must be perceived as social beings and behave socially. People try to preserve their own space during social interactions with others, and this space depends on a variety of factors, such as individual characteristics or their age. In real-world social spaces, there are many different types of people, and robots need to be more sensitive, especially when interacting with vulnerable subjects such as children. However, the current navigation methods do not consider these differences and apply the same avoidance strategies to everyone. Thus, we propose a new navigation framework that considers different social types and defines appropriate personal spaces for each, allowing robots to respect them. To this end, the robot needs to classify people in a real environment into social types and define the personal space for each type as a Gaussian asymmetric function to respect them. The proposed framework is validated through simulations and real-world experiments, demonstrating that the robot can improve the quality of interactions with people by providing each individual with an adaptive personal space. The proposed costmap layer is available on GitHub.

Deep hyperbolic convolutional model for knowledge graph embedding

Recent advancements in knowledge graph embedding have enabled the representation of entities and relations in continuous vector spaces. Performing link prediction on incomplete knowledge graphs using these embeddings has emerged as a challenging task, drawing considerable research interest. Knowledge graphs in the real world typically exhibit a natural hierarchical structure. Hyperbolic embedding methods have shown promising results in modeling hierarchical data, especially in low-dimensional representations. However, existing hyperbolic models for knowledge graph embedding are generally shallow, resulting in limited expressiveness. Additionally, some deep hyperbolic models exist but are often constrained to fixed curvature spaces, which may not optimally capture varying hierarchical structures. In this work, we propose DeER, a novel multi-layer hyperbolic model that leverages a trainable curvature space, marking an advancement in the depth and adaptability of hyperbolic modeling for knowledge graph embeddings. We specifically design a hyperbolic convolutional neural network to learn the heterogeneous interactions between entities and relations within this adaptable hyperbolic space. Additionally, we introduce a hyperbolic feedforward neural network to transform hyperbolic features across multiple layers, enhancing the model’s ability to capture complex hierarchical relationships. Experimental results on three benchmark datasets demonstrate that DeER significantly enhances expressiveness and hierarchical modeling performance when compared to both shallow and other deep baseline approaches.

Surrogate-based integrated design optimization for aerodynamic/stealth performance enhancements

The shape optimization considering both aerodynamic and radar stealth performances has been a considerable attention area for next-generation aircraft, with challenges involving balancing design contradictions and improving optimization efficiency. This paper develops a surrogate-based integrated design optimization method coupling Computational Fluid Dynamics (CFD) and Computational Electromagnetics (CEM) for aerodynamic/stealth performance enhancements. The topology-based 3D hexahedral mesh generation and 2D triangular mesh generation with adaptive refinement provide efficient preprocessing for CFD/CEM solvers. The surrogate-based optimization algorithm with parallel infill-sampling strategy and adaptive design space expansion is employed to search the global optimum and improve optimization efficiency while filtering out numerical noise. The Weighted Sum method is employed to address design contradictions in different disciplines. Optimizations considering aerodynamic, stealth, and aerodynamic/stealth performance of a flying wing aircraft are conducted to verify the effectiveness of the developed method. The optimization results indicate that exclusive consideration of a singular discipline leads to a significant deterioration in the performance of the other discipline. Balanced performance is achieved through coupling optimization. The numerical noise in the stealth discipline is markedly higher than in the aerodynamics discipline. The results demonstrate that the developed method is capable of addressing aerodynamic/stealth design optimization problems and significantly reducing the number of CFD/CEM evaluations while maintaining global optimization effectiveness.

Categorisation of urban open spaces for heat adaptation: A cluster based approach

In the context of climate change, adapting a city's open spaces to heat waves and extreme heat is crucial for mitigating the Urban Heat Island effect and ensuring the wellbeing of its inhabitants. However, the heat adaptation potential of open spaces varies within a city. This study develops an objective and replicable method to categorise urban areas based on their open spaces' adaptive capacity and improvement potential to heat waves at the micro-scale. This is achieved using a clustering approach, eliminating manual operations, using openly available data, employing indicators suitable for every urban fabric type, and using the urban block as the analysis unit. The validation of the method in the case study of Bilbao (Spain) demonstrates its capacity to obtain meaningful insights regarding open space heat adaptation potential. An analysis of the resulting categories reveals significant open space improvement potential throughout the city and a varying adaptive capacity that depends on urban density. Categories with the lowest adaptive capacity have median open space ratios between 0.35 and 0.65 and median tree cover ratios between 0.07 and 0.15. Those with the highest adaptive capacity present median open space ratios between 0.8 and 1 and median tree cover ratios between 0.05 and 0.25. The method can aid local policymakers in identifying opportunity spots for hosting adaptation solutions and understanding the challenges the city may face in planning adaptation action. The method's replicability enables it to be applied in other cities, contributing to a broader exploration of climate change adaptation potential.

Strategies for the Design and Construction of Nature-Inspired & Living Laboratory (NILL 1.0)TM Buildings.

This article explores the growing prominence of nature-inspired design philosophies in the context of sustainability and human well-being within the built environment and focuses on their application within laboratory buildings. Biomimicry and biophilic design are highlighted as key nature-inspired design approaches, with biomimicry drawing inspiration from nature for innovations and biophilic design promoting human health through enhancing the connection with the surrounding natural elements. This paper further discusses living building strategy as an emerging method for creating dynamic and adaptable spaces by prioritizing user experience through co-creation and focusing on sustainable and regenerative structures. The potential of integrating these approaches is emphasized using laboratory buildings as an example, with nature-inspired and living laboratories serving as models for future built environments that promote both environmental responsibility and a positive human experience. Accordingly, this work aims to investigate the design and construction of laboratory buildings based on nature-inspired design strategies and the living building concept. Moreover, the paper discusses the application of biomimicry and living building concepts within laboratory buildings as a novel contribution to the body of knowledge, and concludes by proposing the Nature-inspired & Living Laboratory (NILL 1.0)TM Building Assessment index to serve as a guideline for the design and construction of laboratory buildings using nature as an inspiration and the analogy of human body systems.

Development Pathways and the Political Economy of Maladaptation: The Case of Bioenergy as a Climate Strategy in Brazil

AbstractAlthough it is well known that large-scale bioenergy expansion erodes different environmental, social, and economic dimensions of sustainable development, in countries like Brazil, bioenergy is institutionalized as a flagship climate strategy aimed to cut down CO2 emissions in transport. These trade-offs have serious implications for climate change governance and sustainable development; however, conventional approaches have not yet properly explained this seeming paradox. This article addresses this gap from a critical development pathways approach to bioenergy as a maladaptive strategy in Brazil. I propose an analytical framework to observe how different ideas, interests, and institutions interplay in the historical institutionalization of bioenergy as a climate strategy. The analysis shows that bioenergy institutionalization has been driven by the endemic economic crisis in the sugar sector and governmental interests associated with security and developmental imperatives. The unsustainable co-evolution of development pathways and bioenergy, marked by deforestation, land colonization, and agricultural expansion, has narrowed the adaptation space in agriculture, gearing current climate policy towards path-dependent maladaptive strategies like bioenergy. Paradoxically, framing bioenergy as a climate strategy has been useful to justify more expansive policies in favor of the sugarcane industry, and to greenwash the Brazilian climate policy in the international arena of climate governance.

Formal education as a contested pastoral adaptation pathway: insights from southern Kenya

In dryland pastoral environments, political and geographical marginalization has historically led to development strategies that poorly account for individual and communities’ spatial and socio-economic realities. These development legacies, including long-standing epistemic biases in defining what should be adapted, are often insufficiently considered within adaptation research and practice. This article sets out to analyze the historical emergence and enactment of formal education as a contested adaptation pathway in southern Kenya. For this, I combine the strengths of the historically situated analyses of the pathways scholarship and feminist political ecology’s attention to the performance of intersectional relations of power in everyday livelihood practices. I bring together both archival data and qualitative primary data from focus group discussions (n = 16) and individual interviews (n = 122) conducted in three pastoral communities. The results exemplify the ways that non-climatic factors, such as increased formal school enrolment, (re)shape everyday livelihood practices and social aspirations, molding the current adaptation space. Notably, enacting formal education as an adaptation pathway requires one to navigate increasing cash pressures, mobility, and labor constraints. Wealth disparities, gendered norms, and geographies intersect to shape patterns of vulnerability, with poorer pastoralists residing further away from school centers facing difficult trade-offs on their time and resources. Understanding pathways enactments contributes to problematizing current logics of development and adaptation needs, while yielding important information on socio-spatial differentiation processes in pastoral systems. It also opens the space for further research to use these critical insights to identify alternative adaptation pathways that support more just transformations towards sustainability.