Architectural Design Research Articles

Visual Perception of Regularity and the Composition Pattern Type of the Facade

The present study investigates the degree of visual regularity perceived by viewers in architectural compositions, specifically concerning the type of pattern used. The research is grounded in psychological and neuropsychological universal determinants of visual perception, particularly the perception of visual regularity. The study is based on an empirical survey that involved 48 participants who rated various compositions on a Likert scale. The stimuli presented consisted of a typology of compositional patterns of facades of Polish multifamily buildings developed by Malewczyk, Taraszkiewicz, and Czyż in 2022. The survey results were subjected to statistical analyses, which revealed a clear relationship between the type of composition and its perceived regularity. This implies that architects can predict the perceived regularity of a composition based on its type, which is crucial since visual regularity is closely linked to the sense of spatial order and aesthetic value. Both of these aspects are vital for perceiving architecture as a built environment. The study highlights the significance of visual perception in architectural design, particularly how the public perceives composition types.

Design and implementation of power and area efficient architectures of circular symmetry 2-D FIR filters using CSOA-based CSD

Design and implementation of power and area efficient architectures of circular symmetry 2-D FIR filters using CSOA-based CSD

From CNNs to Transformers in Multimodal Human Action Recognition: A Survey

Due to its widespread applications, human action recognition is one of the most widely studied research problems in Computer Vision. Recent studies have shown that addressing it using multimodal data leads to superior performance as compared to relying on a single data modality. During the adoption of deep learning for visual modelling in the last decade, action recognition approaches have mainly relied on Convolutional Neural Networks (CNNs). However, the recent rise of Transformers in visual modelling is now also causing a paradigm shift for the action recognition task. This survey captures this transition while focusing on Multimodal Human Action Recognition (MHAR). Unique to the induction of multimodal computational models is the process of ‘fusing’ the features of the individual data modalities. Hence, we specifically focus on the fusion design aspects of the MHAR approaches. We analyze the classic and emerging techniques in this regard, while also highlighting the popular trends in the adaption of CNN and Transformer building blocks for the overall problem. In particular, we emphasize on recent design choices that have led to more efficient MHAR models. Unlike existing reviews, which discuss Human Action Recognition from a broad perspective, this survey is specifically aimed at pushing the boundaries of MHAR research by identifying promising architectural and fusion design choices to train practicable models. We also provide an outlook of the multimodal datasets from their scale and evaluation viewpoint. Finally, building on the reviewed literature, we discuss the challenges and future avenues for MHAR.

Spatial circulatory networks based on the peripheral medial axis transform

This article presents a method for constructing circulatory networks that intrinsically combine geometric, topological, and semantic spatial attributes. The objective of this work is to generate concise graph representations extracted from spatial geometry that may be used for wayfinding and code compliance analyses to inform architectural design and urban planning. Our approach is based on shape analysis using the Medial Axis Transform skeletonization method. We present a process for the semantic classification of its nodes and edges by constructing an analytical rational piece-wise 3D surface representation. This overcomes the problem of identifying salient or otherwise graph features. Furthermore, we augment the networks with peripheral pathways. This addresses the fundamental limitation of skeletal graphs forcing paths exclusively through the middle of space and thus producing unreasonable detours. We demonstrate that our approach encompasses subtle circulatory features and generates concise graphs for open and free-form spaces that do not exhibit corridor-like structures.

Using virtual and augmented reality to study architectural lighting

This paper presents industry stakeholder insights from the implementation of a dual modality intervention using virtual and augmented reality simulation to study complex lighting theory in architecture design. Using a design based research method the aim is to evaluate these insights and inform a pilot study to educate first year architectural design students on the complexities of lighting the built environment and methods to improve architectural workflow. The aim is to enable learners to experience natural and artificial lighting methods comparatively in real-time through multiple comparative visualisation methods. This is important to make informed evaluations regarding architectural designs in terms of spatial quality, character, performance, and user-comfort levels. This in turn allows architects to rapidly modify their designs to accommodate or mitigate the environmental effects. Outcomes from the initial usability test highlight the ability to switch back and forth between the virtual and augmented reality simulation technology, and between lighting visualisation modes as a huge step forward by the industry stakeholders. Additionally, the idea of representing the physical building where the simulation took place virtually using a detailed mapping gave a real-world anchor that made the simulations easy to navigate, leading to improved satisfaction and engagement. However, the study also highlighted improvements in the delivery of the simulation is required to improve simulation learnability and efficiency.

Using Generative AI Midjourney to Enhance Divergent and Convergent Thinking in an Architect’s Creative Design Process

Architects use a range of tools, from the traditional pencil to Virtual Reality technologies to prototype and articulate their creative designs. In recent years, Generative Artificial Intelligence (GenAI) software has reached the mainstream and there is an exponential appearance of GenAI images that portray architectural designs. This article documents an architectural design methodology that uses Midjourney, a text-to-image GenAI software, as a design tool that enhances architects’ creativity. Prompted by a design brief, we used Midjourney to accelerate (1) the identification and refinement process of developing a prospective user and (2) the ideation process of creating different desirable spaces for the designed user.

An Investigation on Hardware-Aware Vision Transformer Scaling

Vision Transformer (ViT) has demonstrated promising performance in various computer vision tasks, and recently attracted a lot of research attention. Many recent works have focused on proposing new architectures to improve ViT and deploying it into real-world applications. However, little effort has been made to analyze and understand ViT’s architecture design space and its implication for hardware costs on different devices. In this work, by simply scaling ViT’s depth, width, input size, and other basic configurations, we show that a scaled vanilla ViT model without bells and whistles can achieve comparable or superior accuracy-efficiency trade-off than most of the latest ViT variants. Specifically, compared with DeiT-Tiny, our scaled model achieves a ↑ 1.9% higher ImageNet top-1 accuracy under the same FLOPs and a ↑ 3.7% better ImageNet top-1 accuracy under the same latency on an NVIDIA Edge GPU TX2. Motivated by this, we further investigate the extracted scaling strategies from the following two aspects: (1) can these scaling strategies be transferred across different real hardware devices ? and (2) can these scaling strategies be transferred to different ViT variants and tasks ?. For (1), our exploration, based on various devices with different resource budgets, indicates that the transferability effectiveness depends on the underlying device together with its corresponding deployment tool. For (2), we validate the effective transferability of the aforementioned scaling strategies obtained from a vanilla ViT model on top of an image classification task to the PiT model, a strong ViT variant targeting efficiency as well as object detection and video classification tasks. In particular, when transferred to PiT, our scaling strategies lead to a boosted ImageNet top-1 accuracy of from 74.6% to 76.7% (↑ 2.1%) under the same 0.7G FLOPs. When transferred to the COCO object detection task, the average precision is boosted by ↑ 0.7% under a similar throughput on a V100 GPU.

Research on the Energy Consumption Influence Mechanism and Prediction for the Early Design Stage of University Public Teaching Buildings in Beijing

The public teaching buildings of universities have a large flow of people, high lighting requirements, and large energy consumption, which present significant potential for energy saving. The greatest opportunity for integrating “green” architectural design strategies lies in the design phase, especially the early stage of architectural design. However, current designers often rely on experience or qualitative judgment for decision-making. Thus, there is a pressing need for rational and quantitative green architectural design theories and techniques to guide and support decision-making for the design parameters of teaching buildings. This study, based on field surveys of 40 teaching buildings, constructs building archetypes regarding energy consumption including 28 typical values. Based on the “Rectangle”, “L”, “U”, and “Courtyard” archetypes, through batch energy consumption simulation and multiple regression methods, the influence mechanisms of nine energy consumption influencing factors on four types of building energy consumptions were explored, and energy consumption prediction models were derived. The findings of this research can serve as factor evaluation and selection in the early stage of architectural design for public teaching buildings at universities, and the prediction model can assist in the early estimation of energy consumption. This aims to enrich and supplement green architectural design methods by supporting the design of green public teaching buildings and providing reference and application for relevant engineering practices.

Analyzing Neuroarchitecture to Enhance User Experience in Sacred Spaces

This paper explores the analysis of neuroarchitecture principles to enhance the user experience in sacred spaces, aiming to deepen spiritual engagement, emotional resonance, and overall well-being. Sacred paces play a pivotal role in human societies, serving as places for worship, contemplation, and community gathering. By integrating insights from neuroscience into architectural design, it is possible to optimize spatial layouts, sensory stimuli, and environmental factors to foster a deeper sense of connection, tranquility, and spiritual fulfillment. Through a multidisciplinary approach encompassing neuroscience, architecture, and environmental psychology, this research examines the impact of architectural elements on neural processes and subjective experiences within sacred environments. Case studies of sacred spaces from diverse cultural and religious traditions are analyzed to elucidate effective design strategies and best practices. The effectiveness of neuroarchitecture principles in enhancing the user experience and promoting a sense of connection, reverence, and transcendence in sacred environments is assessed through empirical studies and user feedback. The findings highlight the potential of neuroarchitecture to enrich the design of sacred spaces, offering insights that contribute to the creation of environments that inspire awe, foster contemplation, and deepen the human spirit.

A review on regular clocking scheme in quantum dot cellular automata

Quantum-dot cellular automata (QCA) is a novel and emerging nanotechnology that explores the potential of using quantum dots as information carriers in computing devices. The information transfer, as well as timing synchronization of the QCA circuit, is controlled by clocks. Despite this, most of the work done in QCA does not consider the proper layout of the underlying clocking circuit required. Hence, it ends up with QCA circuits with irregular clock zones, which is not suitable for fabrication. However, for efficient design and to provide proper routing options within the clock zones, a regular, scalable clocking scheme is needed. Without a well-defined and regular clocking zone, the QCA circuit designs are incomplete and not a standard fabrication candidate. In this regard, several regular clocking schemes in QCA are discussed in the literature. In this survey, a systematic review of those clocking schemes will be investigated. A detailed comparison of these schemes is also discussed based on design architecture and fabrication point of view.

Full‐Color Electrochromics with Donor‐Gradient Architectures for Chameleon‐Like Adaptive Camouflage

AbstractMulticolor electrochromics have emerged as a promising solution for achieving active color modulation akin to chameleon‐like adaptive camouflage. However, the development of electrochromics with full‐color tunability still remains challenging, given the weak molecular polarity of inherent active materials and the difficulty in forming polarizer orbitals under varying applied voltages. Employing molecular polarity adjustments, a novel electrochromic polymer is successfully developed with a donor‐gradient design of molecular architecture, enabling comprehensive full‐color tunability. The polymer demonstrates outstanding overall electrochromic performance, including fast switching (around 1.4 s), high coloration efficiency (395.1 cm2 C−1@550 nm) and excellent reversibility (over 92% retention after 5000 cycles). Leveraging the full‐color tunability and rapid response, the electrochromic polymer is further integrated with sensing and control modules to create an environmental adaptive camouflage prototype system capable of seamlessly blending colors with dynamic background environments. This work is expected to provide a straightforward approach for developing full‐color electrochromics for electrochromic camouflage applications.

Automated Code Review Tool

As software development undergoes continual evolution, the assurance of code quality remains paramount in the development lifecycle. This research paper introduces an innovative Automated Code Review Tool engineered to augment and streamline the code review process. The tool capitalizes on advanced static code analysis, machine learning algorithms, and industry best practices to automate the detection of code quality issues, security vulnerabilities, and compliance with coding standards. The Automated Code Review Tool addresses the inherent challenges of manual code reviews, including human error, time constraints, and inconsistencies. Through automation, developers can expedite the identification and resolution of potential issues, thereby enhancing overall code quality and software reliability. Key features of the tool encompass intelligent pattern recognition, real-time feedback, and customizable rule sets, enabling development teams to tailor the tool to their project-specific requirements. Leveraging machine learning algorithms facilitates the tool's continuous learning from past reviews, thereby adapting to evolving coding practices and emerging security threats. This paper presents the architectural framework and design principles underpinning the Automated Code Review Tool, emphasizing its capacity to foster collaboration among development teams, reduce time-to-market, and ultimately contribute to the development of more robust and secure software. A comprehensive evaluation of the tool's efficacy across diverse development environments is conducted, offering insights into the practical implications of embracing automated solutions in real-world contexts. Keywords: Automated Code Review Tool, Code quality, Static code analysis, Machine learning algorithms, Coding standards, Manual code reviews, Human error, Time constraints, etc.

Building a Banking Management System with Full Stack Java

The system encompasses a comprehensive range of functionalities crucial for efficient banking operations, including account management, transaction processing, customer relationship management, and security features. Leveraging Java's versatility, the system employs Spring Boot for backend development, Angular for frontend user interfaces, and Hibernate for database interaction, ensuring scalability, flexibility, and maintainability. Key aspects addressed in this paper include architectural design, database modeling, user interface development, security measures, and integration of essential banking features. Through a rigorous development process and adherence to industry standards, the resulting banking management system demonstrates reliability, performance, and adaptability to evolving banking needs. This paper contributes a valuable resource for developers and researchers interested in building modern, robust banking solutions using full stack Java technologies.

A Physics-based Model Assisted by Machine-Learning for Sodium-ion Batteries with both Liquid and Solid Electrolytes

Abstract In the absence of experimental data of a fully developed hierarchical 3D sodium solid state batteries, we developed an improved continuum model by relying on Machine Learning-assisted parameter fitting to uncover the intrinsic material properties that can be transferred into different battery models. The electrochemical system simulated has sodium metal P2-type Na2/3[Ni1/3Fe1/12Mn7/12]O2 (NNFMO) as the cathode, paired with two types of electrolytes have been modeled viz, the organic liquid electrolyte and a solid polymer electrolyte. We implemented a 1D continuum model in COMSOL to suit both liquid and solid electrolytes, then used a Gaussian Process Regressor to fit and evaluate the electrochemical parameters in both battery systems. To enhance the generalizability of our model, the liquid cell and solid cell models share the same OCV input for the cathode materials. The resulting parameters are well aligned with their physical meaning and literature values. The continuum model is then used to understand the effect of increasing the thickness of the cathode and current density by analysing the cathode utilization, and the overpotentials arising from transport and charge transfer. This 1D model and the parameter set are ready to be used in a 3D battery architecture design.

Deep Learning Model for COVID-19 Classification Using Fine Tuned ResNet50 on Chest X-Ray Images

Amid the COVID-19 pandemic, extensive research has focused on deep learning methodologies for accurately diagnosing the virus from chest X-ray images. Various models, including Convolutional Neural Networks (CNNs) and pre-trained models, have achieved accuracies ranging from 85.20% to 99.66%. However, the proposed Fine-Tuned ResNet50 model consistently outperforms others with an impressive accuracy of 98.20%. By leveraging on transfer learning and careful architectural design the proposed model demonstrates superior performance compared to previous studies using DarkNet, ResNet50, and pre-trained models. Graphical comparisons highlight its competitive edge, emphasizing its effectiveness in COVID-19 classification tasks. The ResNet50 architecture, known for its deep residual layers and skip connections, facilitates robust feature extraction and classification, especially in medical imaging. Data pre-processing techniques, like noise reduction and contrast enhancement, ensure input data quality and reliability, enhancing the model's predictive abilities. Training results reveal the model's steady accuracy improvement and loss reduction over 20 epochs, aligning closely with validation metrics. Evaluation on a test set of COVID-19 chest X-ray images confirms exceptional accuracy (98.20%), precision (99.00%), recall (98.82%), and F1-score (98.91%), highlighting its proficiency in identifying COVID-19 cases while minimizing false positives and negatives. Comparative analyses against prior studies further validate its superior performance, establishing the Fine-Tuned ResNet50 model as a reliable tool for COVID-19 diagnosis. Future research should focus on exploring ensemble learning techniques, interpretability methods, and stakeholder collaboration to ensure safe AI deployment in clinical settings. Moreover, larger and diverse datasets are crucial for validating model performance and improving generalization, ultimately enhancing patient care and public health outcomes in the mitigating COVID-19 and future pandemics.

Photo-Stimulated Zn-based Batteries: Progress, Challenges, and Perspectives.

Solar energy, as a renewable energy source, dominates the vast majority of human energy, which can be harvested and converted by photovoltaic solar cells. However, the intermittent availability of solar energy restricts the actual utilization circumstances of solar cells. Integrating photo-responsive electrodes into an energy storage device emerges as a dependable and executable strategy, fostering the creation of photo-stimulated batteries that seamlessly amalgamate the process of solar energy collection, conversion, and storage in one system. Endowed by virtues such as cost-effectiveness, facile manufacturing, safety, and environmental friendliness, photo-stimulated Zn-based batteries have attracted considerable attention. The progress report furnishes a brief overview, summarizing various photo-stimulated Zn-based batteries. Their configurations, operational principles, advancements, and the intricate engineering of photoelectrode designs are introduced, respectively. Through rigorous architectural design, photo-stimulated Zn-based batteries exhibit the ability to initiate charging by saving electricity usage, and in certain instances, even without the need for external electrical grids under illumination. Furthermore, the compensation of solar energy can be explored to improve the output electric energy. At last, opportunities and challenges toward photo-stimulated Zn-based batteries in the process of development are proposed and discussed in the hope of expanding their application scenarios and accelerating the commercialization progress.

HierCGRA: A Novel Framework for Large-scale CGRA with Hierarchical Modeling and Automated Design Space Exploration

Coarse-grained reconfigurable arrays (CGRAs) are promising design choices in computation-intensive domains, since they can strike a balance between energy efficiency and flexibility. A typical CGRA comprises processing elements (PEs) that can execute operations in applications and interconnections between them. Nevertheless, most CGRAs suffer from the ineffectiveness of supporting flexible architecture design and solving large-scale mapping problems. To address these challenges, we introduce HierCGRA, a novel framework that integrates hierarchical CGRA modeling, Chisel-based Verilog generation, LLVM-based data flow graph (DFG) generation, DFG mapping, and design space exploration (DSE). With the graph homomorphism (GH) mapping algorithm, HierCGRA achieves a faster mapping speed and higher PE utilization rate compared with the existing state-of-the-art CGRA frameworks. The proposed hierarchical mapping strategy achieves 41× speedup on average compared with the ILP mapping algorithm in CGRA-ME. Furthermore, the automated DSE based on Bayesian optimization achieves a significant performance improvement by the heterogeneity of PEs and interconnections. With these features, HierCGRA enables the agile development for large-scale CGRA and accelerates the process of finding a better CGRA architecture.

Harnessing Deep Learning and Reinforcement Learning Synergy as a Form of Strategic Energy Optimization in Architectural Design: A Case Study in Famagusta, North Cyprus

This study introduces a novel framework that leverages artificial intelligence (AI), specifically deep learning and reinforcement learning, to enhance energy efficiency in architectural design. The goal is to identify architectural arrangements that maximize energy efficiency. The complexity of these models is acknowledged, and an in-depth analysis of model selection, their inherent complexity, and the hyperparameters that govern their operation is conducted. This study validates the scalability of these models by comparing them with traditional optimization techniques like genetic algorithms and simulated annealing. The proposed system exhibits superior scalability, adaptability, and computational efficiency. This research study also explores the ethical and societal implications of integrating AI with architectural design, including potential impacts on human creativity, public welfare, and personal privacy. This study acknowledges it is in its preliminary stage and identifies its potential limitations, setting the stage for future research to enhance and expand the effectiveness of the proposed methodology. The findings indicate that the model can steer the architectural field towards sustainability, with a demonstrated reduction in energy usage of up to 20%. This study also conducts a thorough analysis of the ethical implications of AI in architecture, emphasizing the balance between technological advancement and human creativity. In summary, this research study presents a groundbreaking approach to energy-efficient architectural design using AI, with promising results and wide-ranging applicability. It also thoughtfully addresses the ethical considerations and potential societal impacts of this technological integration.

Music and Religion in the Spiritual World of the Hungarian Aristocracy: The Case of Count Anton Erdődy (1714–1769)

This study deals with the forms and expressions of the Christian piety of the Hungarian aristocracy in the early modern period on the example of Anton Erdődy (1714–1769), a representative of one of the most influential and most ancient Hungarian–Croatian noble families. The personal piety of this socially high-ranking aristocrat was shaped by familial, social, and spiritual traditions, which determined the nature of his artistic patronage. The unique Baroque organ preserved in the chapel of his no longer existing mansion in Trenčianske Bohuslavice, Slovakia (former Bohuslavice, Upper Hungary) is a magnificent manifestation of this patronage. The reconstruction of Anton Erdődy’s idea of the spiritual world and of his piety enables us to formulate a hypothesis that the atypical architectural and structural design of this organ did not result only from the aesthetic requirements of its commissioner, but also had a theological foundation and religious essence in addition to its visual effect. This study is the result of extensive heuristic research and analysis of sources and extant artefacts using the methods of music historiography.

Co-creation Processes to Rethink Architectural Design

Co-creation Processes to Rethink Architectural Design