Posts

Showing posts from December, 2025

✨ Best Research Article Award

Image
  ✨ Best Research Article Award Celebrating groundbreaking architectural research that pushes boundaries in design, sustainability, technology, and human-centered innovation. This award honors visionary scholars whose work transforms how we shape cities, structures, and future-built environments. A tribute to excellence, impact, and discovery. Architecture Engineers Awards 🔗 Nominate now! 👉  https://architectureengineers.com/awa... 🌐 Visit:  http://architectureengineers.com 📩 Contact:  contact@architectureengineers.com #ArchitectureAwards #ResearchExcellence #BestResearchArticle #DesignInnovation #SustainableArchitecture #BuildingScience #EmergingArchitects #AcademicAwards #FutureOfArchitecture

Sustainability-Integrated Neural Architecture Search with ZEP-NAS

Image
The rising environmental impact of deep learning has made sustainability an essential consideration in model design. While existing sustainable Neural Architecture Search (NAS) methods primarily focus on reducing the computational cost of the search process, they often overlook the substantial emissions generated by the final architectures during training and deployment. This oversight allows carbon-intensive models to persist even after an efficient search. To address this gap, this research emphasizes the need to embed long-term emission awareness directly into NAS objectives. Limitations of Conventional Sustainable NAS Approaches Traditional sustainability efforts in NAS mainly target the efficiency of the search algorithm itself, such as reducing GPU hours or computational overhead during architecture exploration. However, these methods neglect the broader lifecycle emissions of selected models, including training, fine-tuning, and large-scale deployment. This partial optimizati...

Network-Architectured DRTMCs via DED: Achieving Strength–Ductility Synergy through In-Situ Nano-Reinforcement

Image
  Discontinuously reinforced titanium matrix composites (DRTMCs) are gaining traction due to their impressive strength-ductility synergy, yet traditional fabrication routes suffer from scalability limits imposed by matrix powder size and inconsistent reinforcement distribution. Additive manufacturing, particularly directed energy deposition (DED), offers a promising solution but often struggles to balance strength and ductility. This study addresses these challenges by developing in-situ nano-reinforced DRTMCs with a quasi-continuous network architecture, fabricated using pure Ti and LaB₆ as starting materials. The objective is to enhance microstructural control, refine grains, and achieve superior mechanical performance. In-Situ Formation of Nano-Sized Reinforcements The integration of LaB₆ during DED processing enables the in-situ formation of nano-sized TiB and La₂O₃ reinforcements. These particles serve as potent nucleation and strengthening agents, promoting the development ...

A Combined Autotuning and Runtime Resource Management Framework for Dynamic Workload Optimization on Homogeneous Architectures

Image
Modern computing systems operate under highly variable and unpredictable workloads, with performance-critical applications constantly entering and leaving the execution environment. These fluctuations create challenges in meeting strict performance guarantees while maintaining energy efficiency. Traditional approaches typically rely on either application-level autotuning or architecture-level resource management, but these independent strategies often fall short in addressing complex performance–power–quality trade-offs. This study introduces an integrated two-level framework that unifies both mechanisms to improve system responsiveness, efficiency, and reliability on homogeneous architectures. Background and Motivation As computing platforms grow increasingly heterogeneous in their application demands—even on homogeneous hardware—they face the dual challenge of sustaining application performance and minimizing power consumption. Autotuners can optimize software-level parameters suc...

Climate-Adaptive Thermal Comfort Optimization in Architectural Design

Image
Climate change has intensified the challenges associated with maintaining indoor–outdoor thermal comfort, prompting the need for advanced, data-driven design approaches. This study introduces an integrated framework combining Multiobjective optimization (MOO) and explainable machine learning (ML) to analyze how spatial morphology affects indoor–outdoor thermal comfort (IOTC). By merging global optimization capability with transparent interpretability, the framework supports climate-responsive architectural decision-making and delivers insights that improve both design quality and environmental performance. Multiobjective Optimization for Thermal Comfort The framework employs a genetic algorithm (GA)–based MOO model to optimize nine morphological parameters related to building and courtyard forms. These parameters serve as decision variables for the simultaneous optimization of predicted mean vote (PMV) and the universal thermal climate index (UTCI) during contrasting seasonal conditi...

Predictor-Assisted Evolutionary Neural Architecture Search for Spiking Neural Networks

Image
Spiking Neural Networks (SNNs) represent a biologically inspired computing paradigm that transmits information through discrete spikes, offering improved biological interpretability and superior energy efficiency. Despite these advantages, the design of high-performance SNN architectures remains a major challenge, as existing structures rely heavily on manual engineering and expert intuition. This research addresses this issue by proposing a fully automated method to discover optimal SNN architectures using a predictor-assisted evolutionary neural architecture search framework, aiming to enhance performance while reducing computational cost and energy consumption. Limitations of Manual SNN Architecture Design Traditional approaches to SNN architecture development depend largely on manual design strategies, making them inflexible and difficult to scale. These human-crafted architectures often suffer from limited adaptability, restricted search space exploration, and reliance on expe...

A Dual-Aspect Evaluation Framework for Architectural Plan Generation Using pix2pix-Series Algorithms

Image
  Architectural plan generation using pix2pix-series algorithms presents significant challenges, particularly regarding the absence of domain-specific evaluation standards and limited understanding of how training configurations jointly influence performance. Current architectural AI workflows focus heavily on visual output, often overlooking principle adherence, vectorization quality, and the structural logic of predicted plans. Addressing this gap, the proposed framework introduces a systematic experimental design and a dual-aspect evaluation approach specifically tailored for architectural-like plans, establishing a rigorous foundation for AI-enabled generative design in architecture. Limitations of Existing pix2pix Adaptations in Architectural Design Although pix2pix architectures are widely adopted for map translation and image-to-image tasks, their adaptation to architectural plan generation remains underdeveloped due to the lack of domain-centered evaluation benchmarks. A...