Search Results (6,070)

The advent and application of biophilic architecture bring numerous environmental, economic, and energy-efficiency benefits, playing a crucial role in advancing low-carbon, energy-saving, healthy, comfortable, and sustainable development within the construction industry. Thanks to its many advantages—such as aesthetic enhancement, improved microclimates, and negative carbon potential—biophilic architecture has been widely adopted in building design, particularly as a response to the escalating environmental crisis. Integrating plants with various architectural forms can optimize building performance, especially by reducing operational energy consumption. This study uses knowledge mapping tools like CiteSpace 6.1.R3 and VOSviewer 1.6.19 to analyze 2309 research papers from the Web of Science (WoS) published over the past decade on the topic of “energy efficiency in biophilic architecture”. It conducts visual analyses of publication trends, collaborative networks, and key themes. The research categorizes plant–architecture integration methods, focusing on three primary areas: green roofs, vertical green systems, and green photovoltaic systems. Additionally, it reviews the ways in which biophilic architecture contributes to energy savings, the research methodologies employed, energy-saving rates, and the factors influencing these outcomes. Finally, a SWOT framework is constructed to assess the strengths, weaknesses, opportunities, and potential threats of biophilic architecture, as well as its future development prospects. The findings indicate that integrating plants with building roofs is an effective energy-saving strategy, achieving energy savings of up to 70%. Furthermore, combining biophilic elements with photovoltaic systems can enhance the efficiency of solar energy generation. This study offers valuable insights for architects and researchers in designing more energy-efficient and sustainable buildings. Full article

In this paper, we address the modeling, simulation, and control of a rotary inverted pendulum (RIP). The RIP model assembled via the MATLAB (Matlab 2021a)^®/Simulink (Simulink 10.3) Simscape (Simscape 7.3)™ environment demonstrates a high degree of fidelity in its capacity to capture the dynamic characteristics of an actual system, including nonlinear friction. The mathematical model of the RIP is obtained via the Euler–Lagrange approach, and a parameter identification procedure is carried out over the Simscape model for the purpose of validating the mathematical model. The usefulness of the proposed Simscape model is demonstrated by the implementation of a variety of control strategies, including linear controllers as the linear quadratic regulator (LQR), proportional–integral–derivative (PID) and model predictive control (MPC), nonlinear controllers such as feedback linearization (FL) and sliding mode control (SMC), and artificial intelligence (AI)-based controllers such as FL with adaptive neural network compensation (FL-ANC) and reinforcement learning (RL). A design methodology that integrates RL with other control techniques is proposed. Following the proposed methodology, a FL-RL and a proportional–derivative control with RL (PD-RL) are implemented as strategies to achieve stabilization of the RIP. The swing-up control is incorporated into all controllers. The visual environment provided by Simscape facilitates a better comprehension and understanding of the RIP behavior. A comprehensive analysis of the performance of each control strategy is conducted, revealing that AI-based controllers demonstrate superior performance compared to linear and nonlinear controllers. In addition, the FL-RL and PD-RL controllers exhibit improved performance with respect to the FL-ANC and RL controllers when subjected to external disturbance. Full article

K-TIG welding offers the advantages of single-sided welding and double-sided formation, making it widely used for medium/thick-plate welding. The welding quality of K-TIG is closely linked to its penetration state. However, the assembly gap in medium/thick-plate workpieces can easily result in an unstable penetration state. In K-TIG welding, the geometric characteristics of the weld pool are closely related to the penetration state. Compared to arc voltage sensing and acoustic signal sensing, visual sensing is a method capable of obtaining the three-dimensional geometric features of the weld pool. To this end, a K-TIG weld pool three-dimensional monitoring algorithm based on a semantic segmentation network using a stereo vision system with a single High-Dynamic-Range (HDR) camera is proposed in this paper. In order to identify the assembly gap of medium/thick-plate workpieces, a gap width extraction algorithm based on the watershed method is proposed. Subsequently, a penetration state recognition model is constructed, taking the three-dimensional geometric features of the weld pool and the gap width as inputs, with the penetration state as the output. The relationship between the input features and the accuracy of penetration recognition is analyzed through feature ablation experiments. The findings reveal that gap width is the most critical feature influencing the accuracy of penetration recognition, while the area feature negatively affects this accuracy. After removing the area feature, the accuracy of the proposed penetration recognition model reaches 96.7%. Full article

As a crop with significant medicinal value and nutritional components, the market demand for bitter melon continues to grow. The diversity of bitter melon shapes has a direct impact on its market acceptance and consumer preferences, making precise identification of bitter melon germplasm resources crucial for breeding work. To address the limitations of time-consuming and less accurate traditional manual identification methods, there is a need to enhance the automation and intelligence of bitter melon phenotype detection. This study developed a bitter melon phenotype detection model named CSW-YOLO. By incorporating the ConvNeXt V2 module to replace the backbone network of YOLOv8, the model’s focus on critical target features is enhanced. Additionally, the SimAM attention mechanism was introduced to compute attention weights for neurons without increasing the parameter count, further enhancing the model’s recognition accuracy. Finally, WIoUv3 was introduced as the bounding box loss function to improve the model’s convergence speed and positioning capabilities. The model was trained and tested on a bitter melon image dataset, achieving a precision of 94.6%, a recall of 80.6%, a mAP50 of 96.7%, and an F1 score of 87.04%. These results represent improvements of 8.5%, 0.4%, 11.1%, and 4% in precision, recall, mAP50, and F1 score, respectively, over the original YOLOv8 model. Furthermore, the effectiveness of the improvements was validated through heatmap analysis and ablation experiments, demonstrating that the CSW-YOLO model can more accurately focus on target features, reduce false detection rates, and enhance generalization capabilities. Comparative tests with various mainstream deep learning models also proved the superior performance of CSW-YOLO in bitter melon phenotype detection tasks. This research provides an accurate and reliable method for bitter melon phenotype identification and also offers technical support for the visual detection technologies of other agricultural products. Full article

In recent years, the increasing demand for worker safety and workflow efficiency in the construction industry has drawn considerable attention to the application of automated ergonomic technologies. To gain a comprehensive understanding of the current research landscape in this field, this study conducts an in-depth visual analysis of the literature on automated ergonomic risk assessment published between 2001 and 2024 in the Web of Science database using CiteSpace and VOSviewer. The analysis systematically reviews key research themes, collaboration networks, keywords, and citation patterns. Building on this, an SWOT analysis is employed to evaluate the core technologies currently widely adopted in the construction sector. By focusing on the integrated application of wearable sensors, artificial intelligence (AI), big data analytics, virtual reality (VR), and computer vision, this research highlights the significant advantages of these technologies in enhancing worker safety and optimizing construction processes. It also delves into potential challenges related to the complexity of these technologies, high implementation costs, and concerns regarding data privacy and worker health. While these technologies hold immense potential to transform the construction industry, future efforts will need to address these challenges through technological optimization and policy support to ensure broader adoption. Full article

Object detection in remote sensing images is crucial for airport management, hazard prevention, traffic monitoring, and more. The precise ability for object localization and identification enables remote sensing imagery to provide early warnings, mitigate risks, and offer strong support for decision-making processes. While traditional deep learning-based object detection techniques have achieved significant results in single-modal environments, their detection capabilities still encounter challenges when confronted with complex environments, such as adverse weather conditions or situations where objects are obscured. To overcome the limitations of existing fusion methods in terms of complexity and insufficient information utilization, we innovatively propose a Cosine Similarity-based Image Feature Fusion (CSIFF) module and integrate it into a dual-branch YOLOv8 network, constructing a lightweight and efficient target detection network called Multi-Modality YOLO Fusion Network (MMYFNet). This network utilizes cosine similarity to divide the original features into common features and specific features, which are then refined and fused through specific modules. Experimental and analytical results show that MMYFNet performs excellently on both the VEDAI and FLIR datasets, achieving mAP values of 80% and 76.8%, respectively. Further validation through parameter sensitivity experiments, ablation studies, and visual analyses confirms the effectiveness of the CSIFF module. MMYFNet achieves high detection accuracy with fewer parameters, and the CSIFF module, as a plug-and-play module, can be integrated into other CNN-based cross-modality network models, providing a new approach for object detection in remote sensing image fusion. Full article

Detecting defects in complex urban sewer scenes is crucial for urban underground structure health monitoring. However, most image-based sewer defect detection models are complex, have high resource consumption, and fail to provide detailed damage information. To increase defect detection efficiency, visualize pipelines, and enable deployment on edge devices, this paper proposes a computer vision-based robotic defect detection framework for sewers. The framework encompasses positioning, defect detection, model deployment, 3D reconstruction, and the measurement of realistic pipelines. A lightweight Sewer-YOLO-Slim model is introduced, which reconstructs the YOLOv7-tiny network by adjusting its backbone, neck, and head. Channel pruning is applied to further reduce the model’s complexity. Additionally, a multiview reconstruction technique is employed to build a 3D model of the pipeline from images captured by the sewer robot, allowing for accurate measurements. The Sewer-YOLO-Slim model achieves reductions of 60.2%, 60.0%, and 65.9% in model size, parameters, and floating-point operations (FLOPs), respectively, while improving the mean average precision (mAP) by 1.5%, reaching 93.5%. Notably, the pruned model is only 4.9 MB in size. Comprehensive comparisons and analyses are conducted with 12 mainstream detection algorithms to validate the superiority of the proposed model. The model is deployed on edge devices with the aid of TensorRT for acceleration, and the detection speed reaches 15.3 ms per image. For a real section of the pipeline, the maximum measurement error of the 3D reconstruction model is 0.57 m. These results indicate that the proposed sewer inspection framework is effective, with the detection model exhibiting advanced performance in terms of accuracy, low computational demand, and real-time capability. The 3D modeling approach offers valuable insights for underground pipeline data visualization and defect measurement. Full article

Red sour soup (RSS) is a traditional food with rich cultural connotations and nutritional value, unique to the Kaili region of Guizhou Province, China. However, the existing packaging design lacks cultural characteristics and visual appeal, which greatly limits its market potential. This study proposes a systematic research framework for RSS packaging design by integrating NLP, Kansei engineering, and semiotics. First, we mined consumers’ dual requirements by analyzing online reviews from e-commerce and tourism platforms using NLP and LDA. Second, we used Kansei engineering to construct a mapping model between consumers’ requirements and design elements. Notably, in the semantic space, we innovatively introduced the concept of a semantic network, considering the relationships between Kansei words for the first time. Finally, we proposed integrating the four dimensions of semiotics into the four stages of design, guiding the application of batik culture in packaging design. Based on this framework, we created a set of RSS packaging designs that integrate modern design concepts and traditional Miao cultural elements. The new design showed significant attractiveness in testing, with 100% of subjects preferring it, fully demonstrating the effectiveness and consumer acceptance of our approach. This study provides new methods and ideas for packaging in the food industry, which has positive significance for the modernized marketing of traditional foods. Full article

Bikes and bike networks are for younger fit bicyclists, and the U.S. continues to not serve older individuals, with and without dementia, and caregivers. Biking is a sustainable form of transportation, and expanding the biking population would address climate change while improving health. To our knowledge, research has not been conducted in which seniors indicate their preferences for bike styles and networks, health concerns, and desires to bike. Conducted in four senior-living communities in New England, the Visual and Verbal Preference Survey involved 178 participants (female—50%/male—29.8%; age 20–85 52.8%; age > 85 41.6% with 19.6% missing gender and 5.6% missing age). Bike test riding in two senior communities involved 50 participants (female—50%/male—40%; age 66–75 14%; 76–85 60%; age 86–95 16% with 10% missing gender and age). Seniors preferred the adult tricycle, followed by the three- and four-wheeled two-seated bikes, and to bicycle for 30 min 2 days a week, have a bathroom break every hour, and have a bicycle loop. Balance and fear of falling were major concerns, but they wanted to bicycle with family, children, and grandchildren. In two of the communities, seniors test rode three senior-friendly Van Raam bikes. The results mirrored the pre-test survey responses, where the adult tricycle (Easy Rider) was most preferred, followed by the three-wheeled two-seater bike (Fun2Go) and the low-step regular bike (Balance Bike). One community purchased the Fun2Go. Full article

As the significance of meticulous and precise map creation grows in modern Geographic Information Systems (GISs), urban planning, disaster response, and other domains, the necessity for sophisticated map generation technology has become increasingly evident. In response to this demand, this paper puts forward a technique based on Generative Adversarial Networks (GANs) for converting aerial imagery into high-quality maps. The proposed method, comprising a generator and a discriminator, introduces novel strategies to overcome existing challenges; namely, the use of a Canny edge detector and Residual Blocks. The proposed loss function enhances the generator’s performance by assigning greater weight to edge regions using the Canny edge map and eliminating superfluous information. This approach enhances the visual quality of the generated maps and ensures the accurate capture of fine details. The experimental results demonstrate that this method generates maps of superior visual quality, achieving outstanding performance compared to existing methodologies. The results show that the proposed technology has significant potential for practical applications in a range of real-world scenarios. Full article

Guide dogs play a crucial role in enhancing independence and mobility for people with visual impairment, offering invaluable assistance in navigating daily tasks and environments. However, the extensive training required for these dogs is costly, resulting in a limited availability that does not meet the high demand for such skilled working animals. Towards optimizing the training process and to better understand the challenges these guide dogs may be experiencing in the field, we have created a multi-sensor smart collar system. In this study, we developed and compared two supervised machine learning methods to analyze the data acquired from these sensors. We found that the Convolutional Long Short-Term Memory (Conv-LSTM) network worked much more efficiently on subsampled data and Kernel Principal Component Analysis (KPCA) on interpolated data. Each attained approximately 40% accuracy on a 10-state system. Not needing training, KPCA is a much faster method, but not as efficient with larger datasets. Among various sensors on the collar system, we observed that the inertial measurement units account for the vast majority of predictability, and that the addition of environmental acoustic sensing data slightly improved performance in most datasets. We also created a lexicon of data patterns using an unsupervised autoencoder. We present several regions of relatively higher density in the latent variable space that correspond to more common patterns and our attempt to visualize these patterns. In this preliminary effort, we found that several test states could be combined into larger superstates to simplify the testing procedures. Additionally, environmental sensor data did not carry much weight, as air conditioning units maintained the testing room at standard conditions. Full article

Currently, research on peg-in-hole (PiH) compliant assembly is predominantly limited to circular pegs and holes, with insufficient exploration of various complex-shaped PiH tasks. Furthermore, the degree of freedom for rotation about the axis of the circular peg cannot be constrained after assembly, and few studies have covered the complete process from autonomous hole-searching to insertion. Based on the above problems, a novel cross-shaped peg and hole design has been devised. The center coordinates of the cross-hole are obtained during the hole-searching process using the three-dimensional reconstruction theory of a binocular stereo vision camera. During the insertion process, 26 contact states of the cross-peg and the cross-hole were classified, and the mapping relationship between the force-moment sensor and relative errors was established based on a backpropagation (BP) neural network, thus completing the task of autonomous PiH assembly. This system avoids hand-guiding, completely realizes the autonomous assembly task from hole-searching to insertion, and can be replaced by other structures of pegs and holes for repeated assembly after obtaining the accurate relative pose between two assembly platforms, which provides a brand-new and unified solution for complex-shaped PiH assembly. Full article

Emotion recognition is critical to understanding students’ emotional states. However, problems such as crowded classroom environments, changing light, and occlusion often affect the accuracy of recognition. This study proposes an emotion recognition algorithm specifically for classroom environments. Firstly, the study adds the self-made MCC module and the Wise-IoU loss function to make object detection in the YOLOv8 model more accurate and efficient. Compared with the native YOL0v8x, it reduces the parameters by 16% and accelerates the inference speed by 20%. Secondly, in order to address the intricacies of the classroom setting and the specific requirements of the emotion recognition task, a multi-channel emotion recognition network (MultiEmoNet) has been developed. This network fuses skeletal, environmental, and facial information, and introduces a central loss function and an attention module AAM to enhance the feature extraction capability. The experimental results show that MultiEmoNet achieves a classification accuracy of 91.4% on a homemade classroom student emotion dataset, which is a 10% improvement over the single-channel classification algorithm. In addition, this study also demonstrates the dynamic changes in students’ emotions in the classroom through visual analysis, which helps teachers grasp students’ emotional states in real time. This paper validates the potential of multi-channel information-fusion deep learning techniques for classroom teaching analysis and provides new ideas and tools for future improvements to emotion recognition techniques. Full article

Catheter ablation therapy, which is a treatment for atrial fibrillation (AF), has a higher recurrence rate as AF duration increases. Compared to paroxysmal AF (PAF), sustained AF is known to cause progressive anatomic remodeling of the left atrium, resulting in enlargement and shape changes. In this study, we used contrast-enhanced computed tomography (CT) to classify atrial fibrillation (AF) into paroxysmal atrial fibrillation (PAF) and long-term persistent atrial fibrillation (LSAF), which have particularly different recurrence rates after catheter ablation. Contrast-enhanced CT images of 30 patients with PAF and 30 patients with LSAF were input into six pretrained convolutional neural networks (CNNs) for the binary classification of PAF and LSAF. In this study, we propose a method that can recognize information regarding the body axis direction of the left atrium by inputting five slices near the left atrium. The classification was visualized by obtaining a saliency map based on score-class activation mapping (CAM). Furthermore, we surveyed cardiologists regarding the classification of AF types, and the results of the CNN classification were compared with the results of physicians’ clinical judgment. The proposed method achieved the highest correct classification rate (81.7%). In particular, models with shallow layers, such as VGGNet and ResNet, are able to capture the overall characteristics of the image and therefore are likely to be suitable for focusing on the left atrium. In many cases, patients with an enlarged left atrium tended to have long-lasting AF, confirming the validity of the proposed method. The results of the saliency map and survey of physicians’ basis for judgment showed that many patients tended to focus on the shape of the left atrium in both classifications, suggesting that this method can classify atrial fibrillation more accurately than physicians, similar to the judgment criteria of physicians. Full article

The objective of hyperspectral pansharpening is to fuse low-resolution hyperspectral images (LR-HSI) with corresponding panchromatic (PAN) images to generate high-resolution hyperspectral images (HR-HSI). Despite advancements in hyperspectral (HS) pansharpening using deep learning, the rich spectral details and large data volume of HS images place higher demands on models for effective spectral extraction and processing. In this paper, we present HyperGAN, a hyperspectral image fusion approach based on Generative Adversarial Networks. Unlike previous methods that deepen the network to capture spectral information, HyperGAN widens the structure with a Wide Block for multi-scale learning, effectively capturing global and local details from upsampled HSI and PAN images. While LR-HSI provides rich spectral data, PAN images offer spatial information. We introduce the Efficient Spatial and Channel Attention Module (ESCA) to integrate these features and add an energy-based discriminator to enhance model performance by learning directly from the Ground Truth (GT), improving fused image quality. We validated our method on various scenes, including the Pavia Center, Eastern Tianshan, and Chikusei. Results show that HyperGAN outperforms state-of-the-art methods in visual and quantitative evaluations. Full article