Environment Layout Research Articles

'Development and Psychometric Testing of the Lean Management Scale for Nursing Services in Hospitals'.

The aim of this study is to develop a new instrument (The Lean Management Scale for Nursing Services in Hospitals- LMS-N) to evaluate the lean levels of nursing services in hospitals and to evaluate its psychometric properties. A three-phase construct was used to develop this scale and to determine its psychometric properties: (1) creating the item pool, (2) preliminarily evaluating items and (3) evaluating psychometric properties. This methodological study evaluated the scale's face, content and construct validities, internal consistency, and temporal stability. The psychometric properties of the scale were tested with a total of 695 nurses in different sample groups. Data were collected between 18 November 2020 and 15 May 2021. The scale's content validity index was 0.75. According to principal component analysis, the scale included 22 items and five subdimensions, and the total variance was 60.32%. In confirmatory factor analysis, the fit indices were good or acceptable for this construct. Its internal consistency was good or acceptable according to reliability analysis. Test-retest showed that the scale had temporal stability. Lean Management Scale in Nursing Services in Hospitals is a valid and reliable tool that can evaluate the level of leanness of nursing services. It provides a comprehensive evaluation with five subdimensions: management support, visual stock management, work environment layout, preventive notification system and waste detection.

Planning of a Single Flow Channel in Valve Blocks Based on Additive Manufacturing and the Ant Colony Algorithm

As electro-hydrostatic actuator (EHA) technology advances towards lightweight and integration, the demand for enhanced internal flow pathways in hydraulic valve blocks intensifies. However, owing to the constraints imposed by traditional manufacturing processes, conventional hydraulic integrated valve blocks fail to satisfy the demands of a more compact channel layout and lower energy dissipation. Notably, the subjectivity in the arrangement of internal passages results in a time-consuming and labor-intensive process. This study employed additive manufacturing technology and the ant colony algorithm and B-spline curves for the meticulous design of internal passages within an aviation EHA valve block. The layout environment for the valve block passages was established, and path optimization was achieved using the ant colony algorithm, complemented by smoothing using B-spline curves. Three-dimensional modeling was performed using SolidWorks software, revealing a 10.03% reduction in volume for the optimized passages compared with the original passages. Computational fluid dynamics (CFD) simulations were performed using Fluent software, demonstrating that the algorithmically optimized passages effectively prevented the occurrence of vortices at right-angled locations, exhibited superior flow characteristics, and concurrently reduced pressure losses by 34.09%–36.36%. The small discrepancy between the experimental and simulation results validated the efficacy of the ant colony algorithm and B-spline curves in optimizing the passage design, offering a viable solution for channel design in additive manufacturing.

VLAI: Exploration and Exploitation based on Visual-Language Aligned Information for Robotic Object Goal Navigation

Object Goal Navigation(ObjectNav) is the task that an agent need navigate to an instance of a specific category in an unseen environment through visual observations within limited time steps. This work plays a significant role in enhancing the efficiency of locating specific items in indoor spaces and assisting individuals in completing various tasks, as well as providing support for people with disabilities. To achieve efficient ObjectNav in unfamiliar environments, global perception capabilities, understanding the regularities of space and semantics in the environment layout are significant. In this work, we propose an explicit-prediction method called VLAI that utilizes visual-language alignment information to guide the agent's exploration, unlike previous navigation methods based on frontier potential prediction or egocentric map completion, which only leverage visual observations to construct semantic maps, thus failing to help the agent develop a better global perception. Specifically, when predicting long-term goals, we retrieve previously saved visual observations to obtain visual information around the frontiers based on their position on the incrementally built incomplete semantic map. Then, we apply our designed Chat Describer to this visual information to obtain detailed frontier object descriptions. The Chat Describer, a novel automatic-questioning approach deployed in Visual-to-Language, is composed of Large Language Model(LLM) and the visual-to-language model(VLM), which has visual question-answering functionality. In addition, we also obtain the semantic similarity of target object and frontier object categories. Ultimately, by combining the semantic similarity and the boundary descriptions, the agent can predict the long-term goals more accurately. Our experiments on the Gibson and HM3D datasets reveal that our VLAI approach yields significantly better results compared to earlier methods. The code is released athttps://github.com/31539lab/VLAI.

Simulation of indoor thermal energy radiators and visualization design of indoor environment layout based on genetic algorithm and light sensor

With the increasing attention to comfortable living environment and energy efficiency, indoor thermal energy management has become an important task in architectural design. Reasonable heat dissipation system can not only improve indoor comfort, but also reduce energy consumption. The aim of this study is to optimize the layout of indoor heat radiator by genetic algorithm and visualization design of indoor environment combined with light sensor, so as to improve the efficiency and comfort of space heat utilization. The indoor heat dissipation model is established, and the changes of indoor temperature and light are monitored by light sensor in real time. Then genetic algorithm is used to optimize the layout of the radiator, considering the heat distribution and light intensity at different locations. The impact of different design schemes on indoor environment was evaluated through simulation experiments. After many iterations, the optimized radiator layout shows a more uniform heat distribution and significantly improved indoor comfort, and the data from the light sensor provides real-time feedback on the environmental layout, making the design solution more realistic. Therefore, the optimization method based on genetic algorithm can effectively improve the layout efficiency of indoor heat radiator, combined with the application of light sensor, can achieve a more scientific indoor environment design.

The influence of two and three-dimensional spatial characteristics of industrial parks on the emotional well-being of employees: A case study of Shenzhen

Enhancing the emotions of the workers within industrial parks is crucial for achieving the sustainable development goal (SDG). However, evidence on the impact of industrial park environmental layouts on emotions is limited due to the low attention on the workers in the industrial park. Based on a framework of two-dimensional (2D) industrial park morphology indicators and three-dimensional (3D) spatial objective perception, this study aims to compare and analyze the effect of environmental characteristics in Shenzhen's industrial parks on workers' emotions by using emotional geography and social media data. The potential mechanism that environmental characteristic variables influence the positive emotion index (PEI) is also explored. Using the natural language processing (NLP) to analyze the Weibo check-in data, the study captures the daily emotions of workers in industrial parks. By adopting the linear and spatial regression models, this research reveals the complex relationship between the environmental layout of the total 425 industrial parks in Shenzhen city and the corresponding emotions of the workers. The conclusions are as follows: (1) There is a significant correlation between the environmental layout of the industrial parks and the emotions of the workers, with the correlation among 3D variables being higher than that among 2D variables considering spatial effects. (2) There is a certain degree of coordination and contradiction between the morphological indicators of the industrial parks and the spatial objective perception variables, necessitating the planners to consider both macro-scale and micro-perception environmental characteristics to enhance the workers' emotions. (3) In addition to higher accessibility and more public transportation options, the safer, wider, relatively more open streets, more perceivable green spaces, and richer street life can promote the positive emotions among the workers. On the contrary, the enclosed environments, the dense and overwhelming buildings, and the excessive road density may lead to negative emotions. This study contributes to establish the environmental layouts for the industrial parks that foster positive worker emotions and offer insights for the sustainable development of the industrial parks.

An evaluation of outpatient satisfaction based on the national standard questionnaire: a satisfaction survey conducted in a tertiary hospital in Shenyang, China.

Patient satisfaction survey serves as a pivotal tool in evaluating the quality of healthcare services. China's nationwide standard patient satisfaction measurement tool was introduced in 2019. This study aimed to assess the model fit of the national standard outpatient satisfaction questionnaire in a tertiary hospital and evaluate the outpatient satisfaction levels using this tool. A cross-sectional survey using the national outpatient satisfaction questionnaire was conducted via message links to all hospital outpatients who registered between April and July 2022. The data collected underwent descriptive analysis, comparative analysis, and confirmatory factor analysis (CFA). A total of 6,012 valid responses were received and analyzed during this period, with 52.9% of the participants being women. The confirmatory factor analysis (CFA) model showed a good fit and identified doctor communication as having a positive effect and environmental factors as having a negative effect on outpatients' satisfaction, with standardized regression weights of 0.46 and 0.42, respectively. Despite the remarkably high satisfaction levels, patients' recommendation for using the services of this hospital surpassed the overall evaluation and total satisfaction scores. A disparity was identified between the expectations and real experiences of outpatients, leading to some extent of dissatisfaction. To enhance satisfaction levels, the hospital should improve the communication skills of all clinical staff, simplify the environment layout for first-time visitors, and manage patient overloads.

Enhancing E-Learning Platform for Higher Education

The use of e-learning platforms in higher education has grown in popularity in recent years. Systematic study into the efficiency and improvement of these platforms is still necessary, though. This report does a thorough analysis of e-learning websites for higher education in an effort to close this gap. Utilizing both qualitative and quantitative techniques, such as literature reviews, data analysis, and user surveys, we examine the main features of e-learning websites and how they affect students' educational experiences in higher education settings. The research's conclusions offer insightful information about the layout, operation, and usability of e-learning environments, with potential applications in raising student happiness, learning results, and engagement levels. Keywords—E-Learning, Higher Education, Educational Technology, Learning Management Systems, User Experience, E-Learning Platforms, Student Engagement, Online Learning

Determining future scenarios of urban areas with cellular automata/Markov Chain Model method; example of Ereğli District Konya-Türkiye (2030–2040)

As a result of the rapid increase in the world population, the earth surface has started to be damaged due to natural and artificial effects. The extent of the damage to nature can be determined by examining the temporal changes of land use and land cover (LULC). In order to offer healthier and more sustainable living spaces, scientists have produced many studies on the changes in nature. Within the scope of this study, 5 basic training classes were created with the help of Landsat satellite images and CORINE data, covering the period of 1985–2018 for Ereğli-Bor Sub-Basin, which is one of the 9 sub-basins of Konya Closed Basin located in the Central Anatolian Region of Türkiye. Landsat Satellite images, Google Earth Program and CORINE data were overlaid to create a basic training class as artificial areas, agricultural areas—pasture areas—forest areas and wetlands and these areas were classified by supervised classification method. The study was carried out on an area of approximately 331057 ha in and around Ereğli district. Modeling was carried out with the Cellular Automata (CA) Markov Chain Model to determine the urban development potential in the region. In order to estimate the modeling accuracy, the 2018 prediction model was created according to the 2018 reference map, and the validation between the two data was analyzed with the kappa statistics. According to kappa statistics values, it was determined that K_location and K_standard values were 0.9301 and 0.8935, respectively. As a result of the validation in sufficient standards, future prediction models were applied; future models and result maps were prepared for the years 2030–2040. According to the modeling results, it is estimated that the artificial area class in Ereğli district will reach 122.74 km2 by 2030 and 142.24 km2 in 2040. In addition, it was expressed in detail with the prediction results and maps that there will be a decrease in pasture, forest and agricultural areas in the region until 2030 and 2040. As a result, it is predicted that the ecological balance in the region will change and agricultural production may decrease as a result of the decline in agricultural pasture and forest areas. For this reason, it has been revealed that it is important for the future of humanity that plans such as environmental layout and master development plans to be made by regional manager in the region for the future should be planned in line with the results to be obtained as a result of future prediction models.

Toward Better Pedestrian Trajectory Predictions: The Role of Density and Time-to-Collision in Hybrid Deep-Learning Algorithms.

Predicting human trajectories poses a significant challenge due to the complex interplay of pedestrian behavior, which is influenced by environmental layout and interpersonal dynamics. This complexity is further compounded by variations in scene density. To address this, we introduce a novel dataset from the Festival of Lights in Lyon 2022, characterized by a wide range of densities (0.2-2.2 ped/m2). Our analysis demonstrates that density-based classification of data can significantly enhance the accuracy of predictive algorithms. We propose an innovative two-stage processing approach, surpassing current state-of-the-art methods in performance. Additionally, we utilize a collision-based error metric to better account for collisions in trajectory predictions. Our findings indicate that the effectiveness of this error metric is density-dependent, offering prediction insights. This study not only advances our understanding of human trajectory prediction in dense environments, but also presents a methodological framework for integrating density considerations into predictive modeling, thereby improving algorithmic performance and collision avoidance.

Multi-User Redirected Walking in Separate Physical Spaces for Online VR Scenarios.

With the recent rise of Metaverse, online multiplayer VR applications are becoming increasingly prevalent worldwide. However, as multiple users are located in different physical environments, different reset frequencies and timings can lead to serious fairness issues for online collaborative/competitive VR applications. For the fairness of online VR apps/games, an ideal online RDW strategy must make the locomotion opportunities of different users equal, regardless of different physical environment layouts. The existing RDW methods lack the scheme to coordinate multiple users in different PEs, and thus have the issue of triggering too many resets for all the users under the locomotion fairness constraint. We propose a novel multi-user RDW method that is able to significantly reduce the overall reset number and give users a better immersive experience by providing a fair exploration. Our key idea is to first find out the "bottleneck" user that may cause all users to be reset and estimate the time to reset given the users' next targets, and then redirect all the users to favorable poses during that maximized bottleneck time to ensure the subsequent resets can be postponed as much as possible. More particularly, we develop methods to estimate the time of possibly encountering obstacles and the reachable area for a specific pose to enable the prediction of the next reset caused by any user. Our experiments and user study found that our method outperforms existing RDW methods in online VR applications.

Stress affects navigation strategies in immersive virtual reality

There are known individual differences in both the ability to learn the layout of novel environments and the flexibility of strategies for navigating known environments. However, it is unclear how navigational abilities are impacted by high-stress scenarios. Here we used immersive virtual reality (VR) to develop a novel behavioral paradigm to examine navigation under dynamically changing situations. We recruited 48 participants (24 female; ages 17–32) to navigate a virtual maze (7.5 m × 7.5 m). Participants learned the maze by moving along a fixed path past the maze’s landmarks (paintings). Subsequently, participants experienced either a non-stress condition, or a high-stress condition tasking them with navigating the maze. In the high-stress condition, their initial path was blocked, the environment was darkened, threatening music was played, fog obstructed more distal views of the environment, and participants were given a time limit of 20 s with a countdown timer displayed at the top of their screen. On trials where the path was blocked, we found self-reported stress levels and distance traveled increased while trial completion rate decreased (as compared to non-stressed control trials). On unblocked stress trials, participants were less likely to take a shortcut and consequently navigated less efficiently compared to control trials. Participants with more trait spatial anxiety reported more stress and navigated less efficiently. Overall, our results suggest that navigational abilities change considerably under high-stress conditions.

Autonomous port management based AGV path planning and optimization via an ensemble reinforcement learning framework

The rapid development of shipping trade pushes automated container terminals toward the direction of intelligence, safety and efficiency. In particular, the formulation of AGV scheduling tasks and the safety and stability of transportation path is an important part of port operation and management, and it is one of the basic tasks to build an intelligent port. Existing research mainly focuses on collaborative operation between port equipment and path optimization under environmental perception, while there is relatively little research on optimization of path smoothness and safety. Therefore, we propose a path optimization model based on the artificial potential field and twin delayed deep deterministic policy gradient (APF-TD3) framework for the port environment. Firstly, we obtain the scheduling task plan of a single AGV by enumeration. Secondly, according to the artificial potential field (APF) algorithm to generate repulsion for obstacles in the harbor and attraction for container storage at the target point with the position information of the AGV as the input data of the reinforcement learning algorithm is inputted into the twin delayed deep deterministic policy gradient algorithm (TD3). Then TD3 selects the optimal action strategy for the AGV according to the input AGV state information and the designed reward mechanism as well as executes the action. Through repeated execution, the optimal action for the next step is selected at each point to generate a path with start and end points. We validate the model by simulating the scale of containerized cargo in the port i.e. small scale, medium scale and large scale scenes. The experimental results show that the method has the shortest path length of 27.519 m, 270.847 m, and 496.389 m compared to artificial potential field and deep deterministic policy gradient (APF-DDPG), APF, and rapidly-exploring random tree (RRT) algorithms, which also have significant advantages in terms of path security and path smoothness. This framework could respond to the scheduling and transportation tasks of single AGV in different environmental layouts and guarantee the smoothness and safety of the path based on the optimization of the path, which promotes the efficient operation and management of ports.

Subicular neurons encode concave and convex geometries

Animals in the natural world constantly encounter geometrically complex landscapes. Successful navigation requires that they understand geometric features of these landscapes, including boundaries, landmarks, corners and curved areas, all of which collectively define the geometry of the environment1–12. Crucial to the reconstruction of the geometric layout of natural environments are concave and convex features, such as corners and protrusions. However, the neural substrates that could underlie the perception of concavity and convexity in the environment remain elusive. Here we show that the dorsal subiculum contains neurons that encode corners across environmental geometries in an allocentric reference frame. Using longitudinal calcium imaging in freely behaving mice, we find that corner cells tune their activity to reflect the geometric properties of corners, including corner angles, wall height and the degree of wall intersection. A separate population of subicular neurons encode convex corners of both larger environments and discrete objects. Both corner cells are non-overlapping with the population of subicular neurons that encode environmental boundaries. Furthermore, corner cells that encode concave or convex corners generalize their activity such that they respond, respectively, to concave or convex curvatures within an environment. Together, our findings suggest that the subiculum contains the geometric information needed to reconstruct the shape and layout of naturalistic spatial environments.

GREEN PATH: an expert system for space planning and design by the generation of human trajectories

Public space is usually conceived as where people live, perceive, and interact with other people. The environment affects people in several different ways as well. The impact of environmental problems on humans is significant, affecting all human activities, including health and socio-economic development. Thus, there is a need to rethink how space is used. Dealing with the important needs raised by climate emergency, pandemic and digitization, the contributions of this paper consist in the creation of opportunities for developing generative approaches to space design and utilization. It is proposed GREEN PATH, an intelligent expert system for space planning. GREEN PATH uses human trajectories and deep learning methods to analyse and understand human behaviour for offering insights to layout designers. In particular, a Generative Adversarial Imitation Learning (GAIL) framework hybridised with classical reinforcement learning methods is proposed. An example of the classical reinforcement learning method used is continuous penalties, which allow us to model the shape of the trajectories and insert a bias, which is necessary for the generation, into the training. The structure of the framework and the formalisation of the problem to be solved allow for the evaluation of the results in terms of generation and prediction. The use case is a chosen retail domain that will serve as a demonstrator for optimising the layout environment and improving the shopping experience. Experiments were assessed on shoppers’ trajectories obtained from four different stores, considering two years.

Construction and characteristic analysis of landscape gene maps of traditional villages along ancient Qin-Shu roads, Western China

The landscape of traditional villages reflects specific geographical and cultural environments, with distinct regional cultural and living space characteristics. An exploration of the deep genetic core of traditional villages from the perspective of “cultural landscape genes” can help reveal the mechanism of historical evolution of regional settlements and provide a reference for maintaining the regional characteristics of traditional villages today. This study focuses on 23 nationally recognized traditional villages along the northern roads of the ancient Qin-Shu roads. The “landscape-gene” theory, centred on both artificial construction and cultural inheritance in traditional villages, was used to develop a method for identifying and extracting the northern roads of the ancient Qin-Shu roads landscape genes in “architecture culture”. Then, a genome of the cultural landscape of traditional villages was constructed. Six different dimensions with identified genes, including environmental layout, landscape, architectural landscape, material culture, behavioural culture and mentality culture, were analysed. The results showed the following: (1) the traditional villages on the northern roads of the ancient Qin–Shu roads have 8 genes in the constructed landscape, including ‘location layout mainly along mountains and ancient roads, supplemented by water and pictographic patterns’, ‘orderly, flexible and changeable spatial form’, ‘natural landscape surrounded by mountains and rivers, culture and scenery blend’, ‘water in the south and drought in the north’, ‘agricultural main forest auxiliary production landscape’, ‘single north section, complex south section courtyard layout’, ‘load-bearing diversity, good utilization of the gable building structure’, ‘combination of earth, stone and bamboo, recycled and reused building materials’ and ‘atmospheric regularity, exquisite and gorgeous building decoration’. (2) There were six cultural landscape genes, such as ‘strong personalities and regional customs’, ‘preference for flavourful and spicy foods, wine and meat’, which characterized material culture. ‘Romantic history and thrifty values’, and a ‘combination of elegance and vulgarity’ characterized behavioural culture. The mentality of the region was characterized by ‘Xiangtu and Shengxing’, ‘open and inclusive values’, and ‘varied’ beliefs. (3) Philosophical and cosmological underpinnings such as the ‘unity of heaven and humanity’ and the ‘yin-yang and five-element’ theory guide human settlements in traditional villages along the northern roads. This study aims to clarify the characteristics of cultural landscapes in traditional villages through the analysis of cultural landscape genes and a resulting mapped genome, which will provide a scientific basis for the sustainable development of cultural landscapes in traditional villages. Cultural genes can protect the inheritance of regional culture and provide a new perspective for the study of traditional villages along linear cultural heritage zones.

Spatial learning using Google Streetview in an online wayfinding task

The use of navigation applications changed the way people find their way in an unfamiliar environment. A combination of maps, images and textual route instructions shown (or with audio) on one screen guides the user to the destination but may sometimes be overwhelming. This article investigated the spatial knowledge participants acquired after being presented with different types of route instructions, human and computer-generated, in an online wayfinding task using Google Streetview (without the 2D map) of an unfamiliar environment. The results showed a significant difference in the wayfinding performance for deviations from computer-generated instructions, whilst there was no difference in the time spent and the scene recall. Sketch maps revealed both route-like and survey-like characteristics. But most sketch maps are characterised by high route-likeness. Furthermore, this study showed a significant effect of the environmental layout on the participant’s performance based on deviations incurred during wayfinding. The results of this study have implications for improving navigation system instructions and design as well as for learning with geospatial technologies.

Simulating staff activities in healthcare environments: An empirical multi-agent modeling approach

The layout of the healthcare environment profoundly impacts healthcare efficiency, safety, employee satisfaction, and the sustainability of operations, mainly based on occupant behavior analysis. However, due to the increase in professionalism and interprofessional collaboration among healthcare practitioners and the complexity of the physical environment, existing research tools face challenges in describing and analyzing diverse occupant behaviors. This study aims to offer an empirically grounded multi-agent modeling approach as a research tool to simulate and reproduce occupant behavior within healthcare settings. Employing a design science research method, the proposed approach encompasses four stages: empirical data collection, development of behavioral rules, agent-based modeling, and validation. A continuous 24-h observational study involving doctors, nurses, and auxiliary staff within a trauma intensive care unit is conducted to demonstrate the development and application process. Results show that the proposed modeling approach achieves a simulation deviation of 8.31 % in individual walking distances and a 16.26 % deviation in overall staff spatial visitation frequency compared to real-world observations. We believe that using simple if-then rules to represent events and probability rules to describe other basic activities can simulate complex staff activities in a healthcare environment. Interdisciplinary expert evaluation acknowledged the utility of this approach. This study offers a comprehensive dataset of behaviors and contributes methodologically to evaluating the efficiency of built environment layouts. The innovation in this study lies in its scalability, extending from events and individuals to encompass the all staff in levels of modeling and validation, ensuring a consistent alignment with empirical data at each stage.

F-RDW: Redirected Walking With Forecasting Future Position.

In order to serve better VR experiences to users, existing predictive methods of Redirected Walking (RDW) exploit future information to reduce the number of reset occurrences. However, such methods often impose a precondition during deployment, either in the virtual environment's layout or the user's walking direction, which constrains its universal applications. To tackle this challenge, we propose a mechanism F-RDW that is twofold: (1) forecasts the future information of a user in the virtual space without any assumptions by using the conventional method, and (2) fuse this information while maneuvering existing RDW methods. The backbone of the first step is an LSTM-based model that ingests the user's spatial and eye-tracking data to predict the user's future position in the virtual space, and the following step feeds those predicted values into existing RDW methods (such as MPCRed, S2C, TAPF, and ARC) while respecting their internal mechanism in applicable ways. The results of our simulation test and user study demonstrate the significance of future information when using RDW in small physical spaces or complex environments. We prove that the proposed mechanism significantly reduces the number of resets and increases the traveled distance between resets, hence augmenting the redirection performance of all RDW methods explored in this work. Our project and dataset are available at https://github.com/YonseiCGnA-VR/F-RDW.

Self-Organizing Memory Based on Adaptive Resonance Theory for Vision and Language Navigation

Vision and Language Navigation (VLN) is a task in which an agent needs to understand natural language instructions to reach the target location in a real-scene environment. To improve the model ability of long-horizon planning, emerging research focuses on extending the models with different types of memory structures, mainly including topological maps or a hidden state vector. However, the fixed-length hidden state vector is often insufficient to capture long-term temporal context. In comparison, topological maps have been shown to be beneficial for many robotic navigation tasks. Therefore, we focus on building a feasible and effective topological map representation and using it to improve the navigation performance and the generalization across seen and unseen environments. This paper presents a S elf-organizing Memory based on Adaptive Resonance Theory (SMART) module for incremental topological mapping and a framework for utilizing the SMART module to guide navigation. Based on fusion adaptive resonance theory networks, the SMART module can extract salient scenes from historical observations and build a topological map of the environmental layout. It provides a compact spatial representation and supports the discovery of novel shortcuts through inferences while being explainable in terms of cognitive science. Furthermore, given a language instruction and on top of the topological map, we propose a vision–language alignment framework for navigational decision-making. Notably, the framework utilizes three off-the-shelf pre-trained models to perform landmark extraction, node–landmark matching, and low-level controlling, without any fine-tuning on human-annotated datasets. We validate our approach using the Habitat simulator on VLN-CE tasks, which provides a photo-realistic environment for the embodied agent in continuous action space. The experimental results demonstrate that our approach achieves comparable performance to the supervised baseline.

Impact of the environmental layout of the neonatal intensive care unit on clinical outcomes and neurological development in very/extremely preterm infants

To investigate the impact of the environmental layout of the neonatal intensive care unit (NICU) on clinical outcomes and neurological development in very/extremely preterm infants. A total of 304 very/extremely preterm infants admitted to Children's Hospital of Chongqing Medical University between January 2021 and June 2022 within 24 hours after birth were included in this retrospective cohort study. Based on different environmental layouts in the NICU, the infants were divided into two groups: centralized layout group (n=157) and decentralized layout group (n=147). The clinical outcomes and Test of Infant Motor Performance (TIMP) scores at corrected gestational age between 34 to 51+6 weeks were compared between the two groups. The decentralized layout group had lower incidence rates of bronchopulmonary dysplasia (44.9% vs 62.4%, P<0.05) and intracranial hemorrhage (17.7% vs 28.0%, P<0.05) than the centralized layout group. The cure rate was higher in the decentralized layout group compared to the centralized layout group (68.7% vs 56.7%, P<0.05). The decentralized layout group had higher TIMP scores than the centralized layout group at corrected gestational age between 34 to 51+6 weeks (P<0.05). The decentralized layout of the NICU exhibits positive effects on the clinical outcomes and early neurological development compared to the centralized layout in very/extremely preterm infants.