The veranda buildings (Qi-lou) in Lingnan are important historical and cultural carriers of knowledge of the transformation of cities in Lingnan from traditional to modern forms. However, the restoration and protection of Qi-lou building facades faces challenges such as low efficiency, over-reliance on architects’ experience, and a lack of systematic technical tools. This study adopts computer vision techniques, specifically conditional generative adversarial networks (CGANs), to propose a new framework for generating realistic Qi-lou building facade designs. By collecting and processing 131 Qi-lou building facade samples, this study constructs a database covering various architectural styles, such as Gothic, Baroque, and Nanyang styles, and introduces a building exterior profile (BEP), a functional segmentation layout (FSL), and a three-stage hierarchical modeling approach for building elevation (BE) to achieve stylized facade generation. The main research findings are as follows: (1) The proposed CGAN model can accurately generate functional zoning layouts and effectively improve the design efficiency of Qi-lou building facades. (2) The generated facade images are consistent in style and structure, exhibiting high realism and significantly reducing the need for manual adjustments. (3) The generation quality of the model is significantly optimized as the input complexity (such as the number of windows and colonnades) increases. This shows that the framework proposed in this study can provide effective technical support for the restoration and innovative design of Qi-lou buildings in the Lingnan region.

In practical applications, constrained multi-objective optimization problems (CMOPs) often fail to achieve the desired results when dealing with CMOPs with different characteristics. Therefore, to address this drawback, we designed a constraint multi-objective evolutionary algorithm based on feedback tracking constraint relaxation, referred to as CMOEA-FTR. The entire search process of the algorithm is divided into two stages: In the first stage, the constraint boundaries are adaptively adjusted based on the feedback information from the population solutions, guiding the boundary solutions towards neighboring solutions and tracking high-quality solutions to obtain the complete feasible region, thereby promoting the population to approach the unconstrained Pareto front (UPF). The obtained feasible solutions are stored in an archive and continuously updated to promote the diversity and convergence of the population. In the second stage, the scaling of constraint boundaries is stopped, and a new dominance criterion is established to obtain high-quality parents, thereby achieving the complete constrained Pareto front (CPF). Additionally, we customized an elite mating pool selection, an archive updating strategy, and an elite environmental selection truncation mechanism to maintain a balance between diversity and convergence. To validate the performance of CMOEA-FTR, we conducted comparative experiments on 44 benchmark test problems and 16 real-world application cases. The statistical IGD and HV metrics indicate that CMOEA-FTR outperforms seven other CMOEAs.

Micro-expressions, fleeting and often unnoticed facial cues, hold the key to uncovering concealed emotions, offering significant implications for understanding emotions, cognition, and psychological processes. However, micro-expression information capture presents challenges due to its instantaneous and subtle nature. Furthermore, it is affected by unpredictable degradation factors such as device performance and weather, and model degradation issues persist in real scenarios, and directly training deep networks or introducing image restoration networks yields unsatisfactory results, hindering the development of micro-expression recognition in real-world applications. This study aims to develop an advanced micro-expression recognition algorithm to promote the research of micro-expression applications in psychology. Firstly, Generative Adversarial Networks (GANs) are employed to build high-quality micro-expression generation models, which are then used as prior decoders to model micro-expression features. Subsequently, the GAN priors of deep neural networks are fine-tuned using low-quality facial micro-expression images. The designed micro-expression GAN module ensures that the generation of latent codes and noise inputs suitable for micro-expression GAN blocks from the deep and shallow features of deep neural networks. This approach controls the reconstruction of facial structure, local details, and accurate expressions to enhance the stability of subsequent recognition networks. Additionally, a Multi-Scale Dynamic Cross-Domain (MSCD) module is proposed to dynamically adjust the input of reconstructed features to different task representation layers. Doing so effectively integrates reconstructed features and improves the micro-expression recognition performance. Experimental results demonstrate that our method consistently achieves superior performance on multiple datasets, achieving particularly significant performance improvements in micro-expression recognition for severely degraded facial images in real scenarios.

AI-driven interior design generation offers promising applications. However, current AI-based diffusion models struggle to generate indoor layouts in pixel-level alignment with the indoor structure. This study proposes a new stable diffusion-based interior design workflow with an Interior Design Control Network (IDCN). IDCN ensures that the batch-generated creative interior designs based on an input image of an unfurnished room match the indoor structure. Generating innovative designs and rendering images directly with the proposed method eliminates the tedious creative design and drawing work in traditional design practices. The results indicate that the proposed method with the new design approach achieves nearly real-time design generation and modification and significantly enhances design creativity and efficiency. Moreover, the proposed method can be generalized to other design generation tasks, thereby promoting the transformation toward intelligent design.

Emergency events pose critical challenges to national and social stability, requiring efficient and timely responses to mitigate their impact. In the initial stages of an emergency, decision-makers face the dual challenge of minimizing transportation costs while adhering to stringent rescue time constraints. To address these issues, this study proposes a two-stage optimization model aimed at ensuring the equitable distribution of disaster relief materials across multiple distribution centers. The model seeks to minimize the overall cost, encompassing vehicle dispatch expenses, fuel consumption, and time window penalty costs, thereby achieving a balance between efficiency and fairness. To solve this complex optimization problem, a hybrid algorithm combining genetic algorithms and particle swarm optimization was designed. This hybrid approach leverages the global exploration capability of genetic algorithms and the fast convergence of particle swarm optimization to achieve superior performance in solving real-world logistics challenges. Case studies were conducted to evaluate the feasibility and effectiveness of both the proposed model and the algorithm. Results indicate that the model accurately reflects the dynamics of emergency logistics operations, while the hybrid algorithm exhibits strong local optimization capabilities and robust performance in handling diverse and complex scenarios. Experimental findings underscore the potential of the proposed approach in optimizing emergency response logistics. The hybrid algorithm consistently achieves significant reductions in total cost while maintaining fairness in material distribution. These results demonstrate the algorithm’s applicability to a wide range of disaster scenarios, offering a reliable and efficient tool for emergency planners. This study not only contributes to the body of knowledge in emergency logistics optimization but also provides practical insights for policymakers and practitioners striving to improve disaster response strategies.

The core issue in handling constrained multi-objective optimization problems (CMOP) is how to maintain a balance between objectives and constraints. However, existing constrained multi-objective evolutionary algorithms (CMOEAs) often fail to achieve the desired performance when confronted with complex feasible regions. Building upon this theoretical foundation, a two-stage archive-based constrained multi-objective evolutionary algorithm (CMOEA-TA) based on genetic algorithms(GA) is proposed. In CMOEA-TA, First stage: The archive appropriately relaxes constraints based on the proportion of feasible solutions and constraint violations,compelling the population to explore more search space. Second stage: Sharing valuable information between the archive and the population, while embedding constraint dominance principles to enhance the feasibility of solutions. In addition an angle-based selection strategy was used to select more valuable solutions to increase the diversity of the population. To verify its effectiveness, CMOEA-TA was tested on 54 CMOPs in 4 benchmark suites and 7 state-of-the-art algorithms were compared. The experimental results show that it is far superior to seven competitors in inverse generation distance (IGD) and hypervolume (HV) metrics.

The interior design suffers from inefficiency and a lack of aesthetic appeal. With the development of artificial intelligence diffusion models, using text descriptions to generate aesthetically pleasing designs has emerged as a new approach to address these issues. In this study, we propose a novel method based on the aesthetic diffusion model, which can quickly generate visually appealing interior design based on input text descriptions while allowing for the specification of decorative styles and spatial functions. The method proposed in this study creates creative designs and drawings by computer instead of from designers, thus improving the design efficiency and aesthetic appeal. We demonstrate the potential of this approach in the field of interior design through our research. The results indicate that: (1) The method efficiently provides designers with aesthetically pleasing interior design solutions; (2) By modifying the text descriptions, the method allows for the rapid regeneration of design solutions; (3) Designers can apply this highly flexible method to other design fields through fine-tuning. (4) The method optimizes the workflow of interior design.

In response to the challenge of accurately assessing age-friendly design requirements during the improvement phase of smart products, a novel evaluation model is proposed. This model is grounded in the technology acceptance model and considers the interplay between user weights and requirements. The aim is to establish precise product indicators and development strategies, thereby maximizing user satisfaction and market competitiveness. Initially, design evaluation indicators are derived from the technology acceptance model. Subsequently, the TextRank algorithm and grounded theory are employed to determine the initial weights of these indicators. The DEMATEL method is utilized to analyze the weight of influence relationships between indicators, while the Kano model determines importance coefficients for adjusting weights. Through normalization, final weights are assigned, and the TOPSIS method implements sorting and significance analysis of age-friendly design requirements. Five age-friendly smartphone samples serve as case studies to evaluate and analyze the five age-friendly design requirement indicators. Method comparison and advantage/disadvantage sorting analyses are conducted to validate the effectiveness and feasibility of the proposed approach.

Interior design requires designer creativity and significant workforce investments. Meanwhile, Artificial Intelligence (AI) is crucial for enhancing the creativity and efficiency of interior design. Therefore, this study proposes an innovative method to generate multistyle interior design and videos with AI. First, this study created a new indoor dataset to train an AI that can generate a specified design style. Subsequently, video generation and super-resolution modules are integrated to establish an end-to-end workflow that generates interior design videos from texture-free 3D models. The proposed method utilizes AI to produce diverse interior design videos directly, thus replacing the tedious tasks of texture selection, lighting arrangement, and video rendering in traditional design processes. The research results indicate that the proposed method can effectively provide diverse interior design videos, thereby enriching design presentation and improving design efficiency. Additionally, the proposed workflow is versatile and scalable, thus holding significant reference value for transforming traditional design toward intelligence.

The key problem to solving constrained multi-objective optimization problems (CMOPs) is how to achieve a balance between objectives and constraints. Unfortunately, most existing methods for CMOPs still cannot achieve the above balance. To this end, this paper proposes an adaptive constraint relaxation-based evolutionary algorithm (ACREA) for CMOPs. ACREA adaptively relaxes the constraints according to the iteration information of population, whose purpose is to induce infeasible solutions to transform into feasible ones and thus improve the ability to explore the unknown regions. Completely ignoring constraints can cause the population to waste significant resources searching for infeasible solutions, while excessively satisfying constraints can trap the population in local optima. Therefore, balancing constraints and objectives is a crucial approach to improving algorithm performance. By appropriately relaxing the constraints, it induces infeasible solutions to be transformed into feasible ones, thus obtaining more information from infeasible solutions. At the same time, it also establishes an archive for the storage and update of solutions. In the archive update process, a diversity-based ranking is proposed to improve the convergence speed of the algorithm. In the selection process of the mating pool, common density selection metrics are incorporated to enable the algorithm to obtain higher-quality solutions. The experimental results show that the proposed ACREA algorithm not only achieved the best Inverse Generation Distance (IGD) value in 54.6% of the 44 benchmark test problems and the best Hyper Volume (HV) value in 50% of them, but also obtained the best results in seven out of nine real-world problems. Clearly, CP-TSEA outperforms its competitors.

Introduction: Urban spatial planning is critical for the development of sustainable and livable cities. However, traditional planning methods often face challenges in handling complex planning scenarios and large-scale data.Methods: This paper introduces UrbanGenoGAN, a novel algorithm that integrates generative adversarial networks (GANs), genetic optimization algorithms (GOAs), and geographic information system (GIS) to address these challenges. Leveraging the generative power of GANs, the optimization capabilities of genetic algorithms, and the spatial analysis capabilities of GIS, UrbanGenoGAN is designed to generate optimized urban plans that cater to various urban planning challenges. Our methodology details the algorithm’s design and integration of its components, data collection and preprocessing, and the training and implementation processes.Results: Through rigorous evaluation metrics, comparative analysis with existing methodologies, and case studies, the proposed algorithm demonstrates significant improvement in urban planning outcomes. The research also explores the technical and practical considerations for implementing UrbanGenoGAN, including scalability, computational efficiency, data privacy, and ethical considerations.Discussion: The findings suggest that the integration of advanced machine learning and optimization techniques with spatial analysis offers a promising approach to enhancing decision-making in urban spatial planning. This work contributes to the growing field of AI applications in urban planning and paves the way for more efficient and sustainable urban development.

Interior designers are suffering from a lack of intelligent design methods. This study aims to enhance the accuracy and efficiency of retrieval textures for interior design, which is a crucial step toward intelligent design. Currently, interior designers rely on repetitive tasks to obtain textures from websites, which is ineffective as a interior design often requires hundreds of textures. To address this issue, this study proposes a hybrid deep learning approach, HyNet, which boosts retrieval efficiency by recommending similar textures instead of blindly searching. Additionally, a new indoor texture dataset is created to support the application of artificial intelligence in this field. The results demonstrate that the proposed method’s ten recommended images achieve a high accuracy rate of 91.41%. This is a significant improvement in efficiency, which can facilitate the design industry’s progression towards intelligence. Overall, this study offers a promising solution to the challenges facing interior designers, and it has the potential to significantly enhance the industry’s productivity and innovation.

The exceptional architecture designed by master architects is a shared treasure of humanity, which embodies their design skills and concepts not possessed by common architectural designers. To help ordinary designers improve the design quality, we propose a new artificial intelligence (AI) method for generative architectural design, which generates designs with specified styles and master architect quality through a diffusion model based on textual prompts of the design requirements. Compared to conventional methods dependent on heavy intellectual labor for innovative design and drawing, the proposed method substantially enhances the creativity and efficiency of the design process. It overcomes the problem of specified style difficulties in generating high-quality designs in traditional diffusion models. The research results indicated that: (1) the proposed method efficiently provides designers with diverse architectural designs; (2) new designs upon easily altered text prompts; (3) high scalability for designers to fine-tune it for applications in other design domains; and (4) an optimized architectural design workflow.

The construction industry consumes a great deal of energy and causes environmental pollution, especially the interior design of the construction industry because the lower degree of automation brings more ecological problems. Thus, intelligent design and automated manufacturing are essential for interior design, as they can increase efficiency and reduce environmental pollution for sustainable development. This study proposes a new method of intelligent design and automatic manufacturing based on Grasshopper (GH) and proves its effectiveness in interior design through practice. The proposed method automatically generates suitable drawings and three-dimensional models by GH instead of manual drawing, thus improving design efficiency and quality. The construction cost calculation is conducted simultaneously with the design while the cost control is completed in the design stage. Then the design is handed over to the computer numerical control factory to realize high-precision automatic manufacturing. Automatically manufactured components are installed on-site instead of manufactured, making the process more environmentally friendly and reducing the construction period. The results show that the application of this method in interior design helps improve design efficiency and quality and has cost-saving and sustainability advantages.

Because interior design is subject to inefficiency, more creativity is imperative. Due to the development of artificial intelligence diffusion models, the utilization of text descriptions for the generation of creative designs has become a novel method for solving the aforementioned problem. Herein, we build a unique interior decoration style dataset. Thus, we solve the problem pertaining to the need for datasets, propose a new loss function that considers the decoration style, and retrain the diffusion model using this dataset. The trained model learns interior design knowledge and can generate an interior design through text. The proposed method replaces the designer's drawing with computer-generated creative design, thereby enhancing the design efficiency and creative generation. Specifically, the proposed diffusion model can generate interior design images of specific decoration styles and spatial functions end to end from text descriptions, and the generated designs are easy to modify. This novel and creative design method can efficiently generate various interior designs, promote the generation of creative designs, and enhance the design and decision-making efficiency.