Search results

This study aims to present a novel Genetic Algorithm-Based Design Model (GABDM) to provide reduced-risk areas, namely, a “safe footprint,” in interior spaces during earthquakes. This study focuses on housing interiors as the space where inhabitants spend most of their daily lives.

The GABDM uses the genetic algorithm as a method, the Nondominated Sorting Genetic Algorithm II algorithm, and the Wallacei X evolutionary optimization engine. The model setup, including inputs, constraints, operations and fitness functions, is presented, as is the algorithmic model’s running procedure. Following the development phase, GABDM is tested with a sample housing interior designed by the authors based on the literature related to earthquake risk in interiors. The implementation section is organized to include two case studies.

The implementation of GABDM resulted in optimal “safe footprint” solutions for both case studies. However, the results show that the fitness functions achieved in Case Study 1 differed from those achieved in Case Study 2. Furthermore, Case Study 2 has generated more successful (higher ranking) “safe footprint” alternatives with its proposed furniture system.

This study presents an original approach to dealing with earthquake risks in the context of interior design, as well as the development of a design model (GABDM) that uses a generative design method to reduce earthquake risks in interior spaces. By introducing the concept of a “safe footprint,” GABDM contributes explicitly to the prevention of earthquake risk. GABDM is adaptable to other architectural typologies that involve footprint and furniture relationships.

We propose in this paper a novel reliable detection method to recognize forged inpainting images. Detecting potential forgeries and authenticating the content of digital images is extremely challenging and important for many applications. The proposed approach involves developing new probabilistic support vector machines (SVMs) kernels from a flexible generative statistical model named “bounded generalized Gaussian mixture model”. The developed learning framework has the advantage to combine properly the benefits of both discriminative and generative models and to include prior knowledge about the nature of data. It can effectively recognize if an image is a tampered one and also to identify both forged and authentic images. The obtained results confirmed that the developed framework has good performance under numerous inpainted images.

Recently, deep learning (DL) has been widely applied in various aspects of human endeavors. However, studies have shown that DL models may also be a primary cause of data leakage, which raises new data privacy concerns. Membership inference attacks (MIAs) are prominent threats to user privacy from DL model training data, as attackers investigate whether specific data samples exist in the training data of a target model. Therefore, the aim of this study is to develop a method for defending against MIAs and protecting data privacy.

One possible solution is to propose an MIA defense method that involves adjusting the model’s output by mapping the output to a distribution with equal probability density. This approach effectively preserves the accuracy of classification predictions while simultaneously preventing attackers from identifying the training data.

Experiments demonstrate that the proposed defense method is effective in reducing the classification accuracy of MIAs to below 50%. Because MIAs are viewed as a binary classification model, the proposed method effectively prevents privacy leakage and improves data privacy protection.

The method is only designed to defend against MIA in black-box classification models.

The proposed MIA defense method is effective and has a low cost. Therefore, the method enables us to protect data privacy without incurring significant additional expenses.

This study aims to present a twofold machine learning (ML) model, namely, EDU-AI, and its implementation in educational buildings. The specific focus is on classroom layout design, which is investigated regarding implementation of ML in the early phases of design.

This study introduces the framework of the EDU-AI, which adopts generative adversarial networks (GAN) architecture and Pix2Pix method. The processes of data collection, data set preparation, training, validation and evaluation for the proposed model are presented. The ML model is trained over two coupled data sets of classroom layouts extracted from a typical school project database of the Ministry of National Education of the Republic of Turkey and validated with foreign classroom boundaries. The generated classroom layouts are objectively evaluated through the structural similarity method (SSIM).

The implementation of EDU-AI generates classroom layouts despite the use of a small data set. Objective evaluations show that EDU-AI can provide satisfactory outputs for given classroom boundaries regardless of shape complexity (reserved for validation and newly synthesized).

EDU-AI specifically contributes to the automation of classroom layout generation using ML-based algorithms. EDU-AI’s two-step framework enables the generation of zoning for any given classroom boundary and furnishing for the previously generated zone. EDU-AI can also be used in the early design phase of school projects in other countries. It can be adapted to the architectural typologies involving footprint, zoning and furnishing relations.

This paper aims mainly at introducing applied statisticians and econometricians to the current research methodology with non-Euclidean data sets. Specifically, it provides the basis and rationale for statistics in Wasserstein space, where the metric on probability measures is taken as a Wasserstein metric arising from optimal transport theory.

The authors spell out the basis and rationale for using Wasserstein metrics on the data space of (random) probability measures.

In elaborating the new statistical analysis of non-Euclidean data sets, the paper illustrates the generalization of traditional aspects of statistical inference following Frechet's program.

Besides the elaboration of research methodology for a new data analysis, the paper discusses the applications of Wasserstein metrics to the robustness of financial risk measures.

The “chiralisation” of Euclidean polygonal tessellations is a novel, recent method which has been used to design new auxetic metamaterials with complex topologies and improved geometric versatility over traditional chiral honeycombs. This paper aims to design and manufacture chiral honeycombs representative of four distinct classes of 2D Euclidean tessellations with hexagonal rotational symmetry using fused-deposition additive manufacturing and experimentally analysed the mechanical properties and failure modes of these metamaterials.

Finite Element simulations were also used to study the high-strain compressive performance of these systems under both periodic boundary conditions and realistic, finite conditions. Experimental uniaxial compressive loading tests were applied to additively manufactured prototypes and digital image correlation was used to measure the Poisson’s ratio and analyse the deformation behaviour of these systems.

The results obtained demonstrate that these systems have the ability to exhibit a wide range of Poisson’s ratios (positive, quasi-zero and negative values) and stiffnesses as well as unusual failure modes characterised by a sequential layer-by-layer collapse of specific, non-adjacent ligaments. These findings provide useful insights on the mechanical properties and deformation behaviours of this new class of metamaterials and indicate that these chiral honeycombs could potentially possess anomalous characteristics which are not commonly found in traditional chiral metamaterials based on regular monohedral tilings.

To the best of the authors’ knowledge, the authors have analysed for the first time the high strain behaviour and failure modes of chiral metamaterials based on Euclidean multi-polygonal tessellations.

The purpose of this paper is to identify the potential and the challenges for different firms in adopting an AI-first strategy. The study attempts to discern if any company can prioritize AI at the forefront of their strategic plans.

Drawing from illustrative examples from well-known AI-leaders like Netflix and Spotify, as well as from upcoming AI startups and industry incumbents, the paper explores the strategic role of AI in core business processes and customer value creation. It also discusses the advent and implications of generative AI tools since late 2022 to firms’ business strategies.

The authors identify three types of AI-first strategies, depending on firms’ starting points: digital tycoon, niche carver and asset augmenter. The authors discuss how each strategy can aim to achieve data, algorithmic and execution advantages, and what the strategic bottlenecks and risks are within each strategy.

To the best of the authors’ knowledge, this paper is the first to systematically describe how companies can form “AI-first” strategies from different starting points. This study includes actionable examples from known industry players to more emerging startups and industrial incumbents.

The paper aims to investigate the comfort-related performances of an innovative solar shading solution based on a new composite patented material that consists of a cement-based matrix coupled with a stretchable three-dimensional textile. The paper’s aim is, through a performance-based generative design approach, to develop a high-performance static shading system able to guarantee adequate daylit spaces, a connection with the outdoors and a glare-free environment in the view of a holistic and occupant-centric daylight assessment.

The paper describes the design and simulation process of a complex static shading system for digital manufacturing purposes. Initially, the optical material properties were characterized to calibrate radiance-based simulations. The developed models were then implemented in a multi-objective genetic optimization algorithm to improve the shading geometries, and their performance was assessed and compared with traditional external louvres and overhangs.

The system developed demonstrates, for a reference office space located in Milan (Italy), the potential of increasing useful daylight illuminance by 35% with a reduced glare of up to 70%–80% while providing better uniformity and connection with the outdoors as a result of a topological optimization of the shape and position of the openings.

The paper presents the innovative nature of a new composite material that, coupled with the proposed performance-based optimization process, enables the fabrication of optimized shading/cladding surfaces with complex geometries whose formability does not require ad hoc formworks, making the process fast and economic.