Hasil untuk "Architectural drawing and design"

B. Blumenthal, J. Gornostaev, C. Unger

Yuqi Hang

Drawing supports learning by externalizing mental models, but providing timely feedback at scale remains challenging. We present Draw2Learn, a system that explores how AI can act as a supportive teammate during drawing-based learning. The design translates learning principles into concrete interaction patterns: AI generates structured drawing quests, provides optional visual scaffolds, monitors progress, and delivers multidimensional feedback. We collected formative user feedback during system development and open-ended comments. Feedback showed positive ratings for usability, usefulness, and user experience, with themes highlighting AI scaffolding value and learner autonomy. This work contributes a design framework for teammate-oriented AI in generative learning and identifies key considerations for future research.

Xudong Zhao, R. Tao, Wei Li et al.

Earth observation using multisensor data is drawing increasing attention. Fusing remotely sensed hyperspectral imagery and light detection and ranging (LiDAR) data helps to increase application performance. In this article, joint classification of hyperspectral imagery and LiDAR data is investigated using an effective hierarchical random walk network (HRWN). In the proposed HRWN, a dual-tunnel convolutional neural network (CNN) architecture is first developed to capture spectral and spatial features. A pixelwise affinity branch is proposed to capture the relationships between classes with different elevation information from LiDAR data and confirm the spatial contrast of classification. Then in the designed hierarchical random walk layer, the predicted distribution of dual-tunnel CNN serves as global prior while pixelwise affinity reflects the local similarity of pixel pairs, which enforce spatial consistency in the deeper layers of networks. Finally, a classification map is obtained by calculating the probability distribution. Experimental results validated with three real multisensor remote sensing data demonstrate that the proposed HRWN significantly outperforms other state-of-the-art methods. For example, the two branches CNN classifier achieves an accuracy of 88.91% on the University of Houston campus data set, while the proposed HRWN classifier obtains an accuracy of 93.61%, resulting in an improvement of approximately 5%.

Yuming HUANG, Hongtao ZHAI, Zhenxing RAO et al.

ObjectiveThe implementation of the strategy for ecological conservation and high-quality development in the Yellow River Basin signifies a new phase of “systematic governance” in China’s ecological civilization efforts. Concurrently, numerous historical legacy issues make mine restoration an urgent priority. Building resilience, as the primary approach to addressing ecological risks and fostering inclusive growth, serves as an effective means to assess and resolve the complex challenges associated with the restoration of historical legacy mines (mine areas). This research aims to bridge this gap by investigating the relationship between ecological restoration strategies and system resilience under both acute and chronic disturbance, thereby enhancing decision-making for ecological restoration in key areas of the Yellow River Basin and to promote harmonious coexistence between humans and the Earth.MethodsThis research uses system dynamics modelling to establish casual relationships between historical mine restoration and the individual subsystems of society, economy, and ecology. By analyzing sample data from Sanmenxia City from 2015 to 2022, including survey and statistical data, the research quantitatively evaluates the impact of three restoration modes — ecological reconstruction, assisted regeneration, and natural recovery — on the resilience of ecological, economic, and social subsystems. Based on relevant research and policy regulations, two scenarios — acute shock and chronic shock — are developed to identify optimal strategies for enhancing resilience in each subsystem. In addition, a policy intervention strategy — balanced synergistic development — is analyzed to assess its impact on subsystem resilience.Results 1) ‌‌Restoration mode efficacy: Under acute and chronic disturbances, ecological reconstruction has the most significant positive impact on the resilience of all three subsystems (ecological, economic, and social subsystems), followed by assisted regeneration, while natural recovery has the weakest impact. It is believed that the greater the intensity of intervention, the greater the positive impact on system resilience. 2) ‌Policy intervention outcomes: Under chronic shock conditions, the strategy ranking from strongest to weakest ecological response capacity is balanced coordination > ecological reconstruction > no intervention. Under acute shock conditions, ecological resilience levels gradually decrease across the three strategies of ecological reconstruction, balanced coordination, and no intervention. The balanced coordination strategy demonstrates strong effects in enhancing resilience across all subsystems and is more likely to achieve a collaborative enhancement effect in composite system resilience. 3) ‌Temporal and scenario-specific optimization: In 2023, the Sanmenxia composite system barely achieved a coordinated state, highlighting the necessity of strengthening the coupling of the three subsystems to effectively implement the ecological restoration strategy for historical legacy mines (mine areas) and enhance the resilience of the composite system. The simulation results reveal that prior to 2027, the resilience of the composite system under the balanced coordination strategy is slightly higher than that of the ecological reconstruction model. However, starting from 2027, the ecological reconstruction model begins to outperform the balanced coordination strategy and maintains this advantage until 2035. This also underscores that ecological restoration should be based on the coordinated unity of the composite system, prioritizing economic development while also balancing ecological and social benefits, so as to achieve sustainable use of resources and promote sustainable development.ConclusionsThis research provides a critical theoretical and practical link between ecological restoration of historical legacy mines (mine areas) and the resilience of the “ecological – economic – social” composite system. Key contributions include: A framework for quantifying resilience responses to restoration strategies, addressing a gap in existing resilience theory. Empirical validation confirms that ecological restoration is the most effective restoration mode for enhancing multi-dimensional resilience, particularly in highly disturbed contexts. Policy recommendations: Advocate selecting restoration strategies based on specific contexts — balancing development with restoration to achieve gradual system adaptation or intensive reconstruction to meet urgent restoration needs. These findings provide actionable guidance for policymakers to align restoration objectives with broader socio-ecological resilience goals, ultimately promoting sustainable post-mining regional development.

Joan Casals Pañella, Marta Domènech, Sara Vima Grau et al.

El presente artículo plantea una reflexión en torno al legado arquitectónico residencial en Europa posterior a la Segunda Guerra Mundial, a través del estudio de la rehabilitación del edificio DeFlat Kleiburg, ubicado en el barrio Bijlmermeer de Ámsterdam (2017). En particular, se propone una revisión crítica sobre la obsolescencia de las grandes actuaciones residenciales modernas concebidas como respuesta a la necesidad de provisión masiva de vivienda en el período de posguerra, así como sobre las estrategias y motivaciones contemporáneas para su rehabilitación. El texto profundiza en el estudio de los debates y prácticas que entienden el entorno habitado como un componente crucial del patrimonio construido, subrayando la necesidad de preservar los conjuntos residenciales como instrumento para fortalecer la cohesión social. Asimismo, se analiza en detalle la transformación llevada a cabo en Kleiburg, basada en una estrategia de rehabilitación interior orientada a salvaguardar la composición, los acabados y la estructura original, al tiempo que promueve la flexibilidad funcional y la diversificación tipológica y de usos.

Dawei GAO

Ryosuke Kohita, Akira Kasuga

Cloud architecture design presents significant challenges due to the necessity of clarifying ambiguous requirements and systematically addressing complex trade-offs, especially for novice engineers with limited cloud experience. While recent advances in the use of AI tools have broadened available options, system-driven approaches that offer explicit guidance and step-by-step information management may be especially effective in supporting novices during the design process. This study qualitatively examines the experiences of 60 novice engineers using such a system-driven cloud design support tool. The findings indicate that structured and proactive system guidance helps novices engage more effectively in architectural design, especially when addressing tasks where knowledge and experience gaps are most critical. For example, participants found it easier to create initial architectures and did not need to craft prompts themselves. In addition, participants reported that the ability to simulate and compare multiple architecture options enabled them to deepen their understanding of cloud design principles and trade-offs, demonstrating the educational value of system-driven support. The study also identifies areas for improvement, including more adaptive information delivery tailored to user expertise, mechanisms for validating system outputs, and better integration with implementation workflows such as infrastructure-as-code generation and deployment guidance. Addressing these aspects can further enhance the educational and practical value of system-driven support tools for cloud architecture design.

Mohd Faisal Khan, Mukul Lokhande, Santosh Kumar Vishvakarma

Edge-AI applications still face considerable challenges in enhancing computational efficiency in resource-constrained environments. This work presents RAMAN, a resource-efficient and approximate posit(8,2)-based Multiply-Accumulate (MAC) architecture designed to improve hardware efficiency within bandwidth limitations. The proposed REAP (Resource-Efficient Approximate Posit) MAC engine, which is at the core of RAMAN, uses approximation in the posit multiplier to achieve significant area and power reductions with an impact on accuracy. To support diverse AI workloads, this MAC unit is incorporated in a scalable Vector Execution Unit (VEU), which permits hardware reuse and parallelism among deep neural network layers. Furthermore, we propose an algorithm-hardware co-design framework incorporating approximation-aware training to evaluate the impact of hardware-level approximation on application-level performance. Empirical validation on FPGA and ASIC platforms shows that the proposed REAP MAC achieves up to 46% in LUT savings and 35.66% area, 31.28% power reduction, respectively, over the baseline Posit Dot-Product Unit (PDPU) design, while maintaining high accuracy (98.45%) for handwritten digit recognition. RAMAN demonstrates a promising trade-off between hardware efficiency and learning performance, making it suitable for next-generation edge intelligence.

Yongxiang Liu, Yuchun Ma, Eren Kurshan et al.

Most previous 3D IC research focused on stacking traditional 2D silicon layers, so the interconnect reduction is limited to inter-block delays. In this paper, we propose techniques that enable efficient exploration of the 3D design space where each logical block can span more than one silicon layers. Although further power and performance improvement is achievable through fine grain 3D integration, the necessary modeling and tool infrastructure has been mostly missing. We develop a cube packing engine which can simultaneously optimize physical and architectural design for effective utilization of 3D in terms of performance, area and temperature. Our experimental results using a design driver show 36% performance improvement (in BIPS) over 2D and 14% over 3D with single layer blocks. Additionally multi-layer blocks can provide up to 30% reduction in power dissipation compared to the single-layer alternatives. Peak temperature of the design is kept within limits as a result of thermal-aware floorplanning and thermal via insertion techniques.

Yifei Zhou, Thomas Kämpfe, Kai Ni et al.

Compute-in-memory (CiM) emerges as a promising solution to solve hardware challenges in artificial intelligence (AI) and the Internet of Things (IoT), particularly addressing the "memory wall" issue. By utilizing nonvolatile memory (NVM) devices in a crossbar structure, CiM efficiently accelerates multiply-accumulate (MAC) computations, the crucial operations in neural networks and other AI models. Among various NVM devices, Ferroelectric FET (FeFET) is particularly appealing for ultra-low-power CiM arrays due to its CMOS compatibility, voltage-driven write/read mechanisms and high ION/IOFF ratio. Moreover, subthreshold-operated FeFETs, which operate at scaling voltages in the subthreshold region, can further minimize the power consumption of CiM array. However, subthreshold-FeFETs are susceptible to temperature drift, resulting in computation accuracy degradation. Existing solutions exhibit weak temperature resilience at larger array size and only support 1-bit. In this paper, we propose TReCiM, an ultra-low-power temperature-resilient multibit 2FeFET-1T CiM design that reliably performs MAC operations in the subthreshold-FeFET region with temperature ranging from 0 to 85 degrees Celcius at scale. We benchmark our design using NeuroSim framework in the context of VGG-8 neural network architecture running the CIFAR-10 dataset. Benchmarking results suggest that when considering temperature drift impact, our proposed TReCiM array achieves 91.31% accuracy, with 1.86% accuracy improvement compared to existing 1-bit 2T-1FeFET CiM array. Furthermore, our proposed design achieves 48.03 TOPS/W energy efficiency at system level, comparable to existing designs with smaller technology feature sizes.

Rene Antonio Romero Alvarez

Con el avance urbano mundial generado por la globalización de la economía, de todos los sistemas posibles de acceso a la vivienda en nuestra sociedad, el de la vivienda como «mercancía» prevalece, aunque no exclusivo. En este artículo proponemos una revisión del «mercado de vivienda urbano» en la ciudad contemporánea, especialmente lo sucedido desde 1990 hasta 2020. Creemos necesario abordar sus rasgos identitarios, la disposición de los agentes económicos y su relación en la estructura de fabricación de viviendas, así como la interacción de comercialización y la incidencia del mercado como proceso de transformaciones de materialidades inmobiliarias. Con el propósito de colaborar en la comprensión de tal objeto, se realiza una revisión de antecedentes de distintos autores. 

Yuxuan Yin, Yu Wang, Boxun Xu et al.

Analog circuit design requires substantial human expertise and involvement, which is a significant roadblock to design productivity. Bayesian Optimization (BO), a popular machine learning based optimization strategy, has been leveraged to automate analog design given its applicability across various circuit topologies and technologies. Traditional BO methods employ black box Gaussian Process surrogate models and optimized labeled data queries to find optimization solutions by trading off between exploration and exploitation. However, the search for the optimal design solution in BO can be expensive from both a computational and data usage point of view, particularly for high dimensional optimization problems. This paper presents ADO-LLM, the first work integrating large language models (LLMs) with Bayesian Optimization for analog design optimization. ADO-LLM leverages the LLM's ability to infuse domain knowledge to rapidly generate viable design points to remedy BO's inefficiency in finding high value design areas specifically under the limited design space coverage of the BO's probabilistic surrogate model. In the meantime, sampling of design points evaluated in the iterative BO process provides quality demonstrations for the LLM to generate high quality design points while leveraging infused broad design knowledge. Furthermore, the diversity brought by BO's exploration enriches the contextual understanding of the LLM and allows it to more broadly search in the design space and prevent repetitive and redundant suggestions. We evaluate the proposed framework on two different types of analog circuits and demonstrate notable improvements in design efficiency and effectiveness.

Zekang Yang, Wang Zeng, Sheng Jin et al.

Designing effective neural architectures poses a significant challenge in deep learning. While Neural Architecture Search (NAS) automates the search for optimal architectures, existing methods are often constrained by predetermined search spaces and may miss critical neural architectures. In this paper, we introduce NADER (Neural Architecture Design via multi-agEnt collaboRation), a novel framework that formulates neural architecture design (NAD) as a LLM-based multi-agent collaboration problem. NADER employs a team of specialized agents to enhance a base architecture through iterative modification. Current LLM-based NAD methods typically operate independently, lacking the ability to learn from past experiences, which results in repeated mistakes and inefficient exploration. To address this issue, we propose the Reflector, which effectively learns from immediate feedback and long-term experiences. Additionally, unlike previous LLM-based methods that use code to represent neural architectures, we utilize a graph-based representation. This approach allows agents to focus on design aspects without being distracted by coding. We demonstrate the effectiveness of NADER in discovering high-performing architectures beyond predetermined search spaces through extensive experiments on benchmark tasks, showcasing its advantages over state-of-the-art methods. The codes will be released soon.

Sadhbh Kenny, Alissa N. Antle

As Artificial Intelligence ecosystems become increasingly entangled within our everyday lives, designing systems that are ethical, inclusive and socially just is more vital than ever. It is well known that AI can algorithmic biases that reflect, extend and exacerbate our existing systemic injustices. Yet, despite most teenagers interacting with AI daily, only few have the opportunity to learn how it works and its socio-technical complexities. This is a particularly salient issue for marginalized communities. BIPOC teens are often misrepresented throughout AI development and implementation, but they are also less likely to receive STEM education.In response to these unprecedented socio-technical challenges and calls for more critical approaches to child-centered AI design and education, we explore how we can leverage co-speculative design practices to help scaffold BIPOC youth (ages 14-17) critiques of existing AI systems and support the re-imagining of more just AI futures. Drawing on Harway's Situated Knowledges and Speculative Fabulations, these workshops highlight the unique ways marginalized youth perceive AI as having social and ethical implications and how they envision alternative worlds with AI. Our case study describes three 2 hour sessions of a larger 8 week black-led AI STEM program. Analysis includes, data from pre-post surveys, workshop recordings, focus group discussions, learning artifacts, and field notes. We contribute 1) a discussion of how youth perceive AI as having social and ethical implications, 2) a nuanced understanding of how speculative approaches can be leveraged to support youth engagement with complex socio-technical issues and 3) enable youth to open up new AI possibilities in a world absent of techno-capitalist values.

D. Ververidis, S. Nikolopoulos, I. Kompatsiaris

In this paper, we focus on interdisciplinary collaboration using intuitive virtual reality interfaces and building information models in the architecture, engineering, and construction industries. These systems have been a topic of research and development for the past ten years; however, there is still no widely open standard format, related software platform, or guidelines that are sufficiently mature; the complexity of such systems is very high. We review existing state-of-the-art interdisciplinary collaborative virtual reality systems, proposing solutions and standards. Thirteen state-of-the-art systems are reviewed and compared to illustrate emerging trends and insufficiencies. It is found that these systems differ significantly with respect to drawing capabilities, photorealism, construction simulation, and interdisciplinary communication. We discover trends in user interfaces that could be evolved to better standards, and provide future guidelines to developers. Combining the best aspects of existing systems, we provide a blueprint for an ideal system that combines the most advanced features for collaborative design.

Rike Neuhoff

As humans we are urged to imagine and realise radically different, more desirable, and most importantly more sustainable futures (Hulme 2020; Pereira et al. 2019). However, the dominance of dystopian scenarios of irreversible environmental and social collapse, along with business- as-usual scenarios, hinder progress and contribute to a gap in futures literature relating to imagining desirable visions for humanity and how to reach them (Bennett et al. 2016; Rana et al. 2020). In this short paper, I share an experiential, meditation-inspired visioning exercise that can aid in enhancing people’s capacity to envision desirable and motivational futures.

Gioacchino Piras, Silvia Mazzaglia

Since their origins, our cities have been conceived and are still imagined and planned according to cultural and urban schemes that reproduce geometries complicit with the patriarchal and neoliberal system. City governments assume a central role in this process through the promotion of corporate policies and rules, on the one hand, and exclusionary urban planning projects on the other. In both cases, the ideal user of the city remains the white, cisgender, heterosexual, able-bodied man or, otherwise, households which reproduce the cisheteropatriarchal norm. After tracing the approaches of some authors who have analysed and problematised the issue of contemporary urban space through the lens of a intersectional perspective, the case study of CHEAP, a Bolognese urban art collective that, through the practice of poster art, questions the normativisation of public space, will be presented.

Serena Curzel, Fabrizio Ferrandi, Leandro Fiorin et al.

Given their increasing size and complexity, the need for efficient execution of deep neural networks has become increasingly pressing in the design of heterogeneous High-Performance Computing (HPC) and edge platforms, leading to a wide variety of proposals for specialized deep learning architectures and hardware accelerators. The design of such architectures and accelerators requires a multidisciplinary approach combining expertise from several areas, from machine learning to computer architecture, low-level hardware design, and approximate computing. Several methodologies and tools have been proposed to improve the process of designing accelerators for deep learning, aimed at maximizing parallelism and minimizing data movement to achieve high performance and energy efficiency. This paper critically reviews influential tools and design methodologies for Deep Learning accelerators, offering a wide perspective in this rapidly evolving field. This work complements surveys on architectures and accelerators by covering hardware-software co-design, automated synthesis, domain-specific compilers, design space exploration, modeling, and simulation, providing insights into technical challenges and open research directions.

Renan C.V.S. Rolim, Laura Gilabert-Sansalvador, María José Viñals

The Mosteirinho de São Francisco was built around 1635, in a period when the Dutch dominated the northeast of Brazil. It is a building of simple architecture but representative of this singular historical context. It was declared as national heritage in 1966, but today it is abandoned, in an advanced state of degradation, and involved in a judicial process regarding its property. This paper presents the main results of the architectural and conservation studies on the building, as well as the methodology to create a 3D model of its current state as a basis for designing an adaptive reuse proposal that seeks to rescue its heritage values.

Jen Lee

As an unforeseen pandemic disturbs our livelihoods and forces us to change our boundaries, small talks arise and disperse in fleeting moments within and beyond physical perimeters. The notion of singular truth (metanarrative : Lyotard 1984) has evidently been overridden in this time. Small stories (Bamberg 2004, 2006; Georgakopoulou 2006; 2007) are heavily embedded as part of the trajectory of social interactions. As fragments of talk-in-interactions, they are recontextualised and reaffirmed as narratives along multiple threads of conversations across time. Presented in this article is a microstudy implementing the lens of small stories on communication activities taking place among members of a specific location-based community. This is a part of the ongoing PhD research on bottom-up community organisation through the alignment of community-specific narratives and positioning of socially engaged art practitioners. The microstudy on communal conversations on an instant messaging app looks into how multiple realities are reconfigured by virtue of multiple tellers and modes of telling.