Search Results (122)

The increasing frequency and severity of urban crowd disasters underscore a critical need for intelligent surveillance systems capable of real-time crowd anomaly detection and early warning. While deep learning models such as LSTMs, ConvLSTMs, and Transformers have been applied to video-based crowd anomaly detection, they often face limitations in long-term contextual reasoning, computational efficiency, and interpretability. To address these challenges, this paper proposes HiMeLSTM, a crowd anomaly detection framework built around a hippocampal-inspired memory-enhanced LSTM backbone that integrates Long Short-Term Memory (LSTM) networks with an Episodic Memory Unit (EMU). This hybrid design enables the model to effectively capture both short-term temporal dynamics and long-term contextual patterns essential for understanding complex crowd behavior. We evaluate HiMeLSTM on two publicly available crowd-anomaly benchmark datasets (UCF-Crime and ShanghaiTech Campus) and an in-house CrowdSurge-1K dataset, demonstrating that it consistently outperforms strong baseline architectures, including Vanilla LSTM, ConvLSTM, a lightweight spatial–temporal Transformer, and recent reconstruction-based models such as MemAE and ST-AE. Across these datasets, HiMeLSTM achieves up to 93.5% accuracy, 89.6% anomaly detection rate (ADR), and a 0.89 F1-score, while maintaining computational efficiency suitable for real-time deployment on GPU-equipped edge devices. Unlike many recent approaches that rely on multimodal sensors, optical-flow volumes, or detailed digital twins of the environment, HiMeLSTM operates solely on raw CCTV video streams combined with a simple manually defined zone layout. Furthermore, the hippocampal-inspired EMU provides an interpretable memory retrieval mechanism: by inspecting the retrieved episodes and their att ention weights, operators can understand which past crowd patterns contributed to a given decision. Overall, the proposed framework represents a significant step toward practical and reliable crowd monitoring systems for enhancing public safety in urban environments. Full article

Urban green space is essential for ecological functions, environmental quality, and human well-being, yet campus expansion can reduce vegetated areas. This study assessed UGS dynamics at Universitas Padjadjaran’s Jatinangor campus from 2015 to 2025 and evaluated an object-based machine learning approach for fine-scale land cover mapping. High-resolution WorldView-2, WorldView-3, and Legion-03 imagery were pan-sharpened, geometrically corrected, normalized, and used to compute NDVI and NDWI indices. Object-based image analysis segmented the imagery into homogeneous objects, followed by random forest classification into six land cover classes; UGS was derived from dense and sparse vegetation. Accuracy assessment included confusion matrices, overall accuracy 0.810–0.860, kappa coefficients 0.747–0.826, weighted F1 scores 0.807–0.860, and validation with 43 field points. The total UGS increased from 68.89% to 74.69%, bare land decreased from 13.49% to 5.81%, and building areas moderately increased from 10.36% to 11.52%. The maps captured vegetated and developed zones accurately, demonstrating the reliability of the classification approach. These findings indicate that campus expansion has been managed without compromising ecological integrity, providing spatially explicit, reliable data to inform sustainable campus planning and support green campus initiatives. Full article

Objectives: The crime rate in Trinidad and Tobago has increased over the last few years. It is important to understand the impact of rising societal crime on university workplace productivity in order to make meaningful recommendations to mitigate the negative effects of crime. Methods: We conducted semi-structured interviews online via Zoom and face-to-face with both academic and non-academic staff from a university located in Trinidad and Tobago in April 2025. We employed purposive sampling and topics explored included participants’ views on crime, the effect of crime on workplace productivity, the effect of crime on workplace concentration, the effect of crime on participants’ mental health, concerns about safety at the workplace, and desired changes or suggestions to ensure improved safety at the workplace. Data were manually analyzed, and we employed thematic analysis to understand the participants’ data. Results: Analysis included data from 10 participants. Participants represented both academic and non-academic staff, with varied ethnic backgrounds, age range, and were both from Mount Hope and the main campus. Seven of the participants believed that their work productivity had been negatively affected by the crime situation. All the participants agreed that the crime situation was out of control; two of the participants claimed to have been victims of crime. Five of the participants believed they had experienced depressive symptoms, while six participants claimed to have experienced poor concentration on the job. Five participants expressed genuine concerns that something terrible could happen to them within their workplace premises. In order to improve security at the workplace, seven of the participants suggested the employment of more security personnel, while six participants highlighted the need for more surveillance and closed-circuit television (CCTV) cameras. Participants identified four major categories or themes: views on crime and its effects on individuals; effects of crime on workplace productivity; effects of crime on mental well-being; and suggestions and opportunities to improve security at the workplace. Conclusions: From this study, it can be inferred that the majority of the participants were negatively affected by the climate of crime in the country. A comprehensive risk assessment would identify potential risks and vulnerabilities faced by staff, while enhanced surveillance measures and the promotion of the Employee Assistance Program (EAP) can support those impacted. Staff should also be trained to respond effectively to potential threats. Full article

The global elderly population continues to increase, and the demand for leisure programs that support active aging is growing. In particular, group-based outdoor activities for seniors are often conducted in large public areas such as parks, ecological gardens, and cultural sites. As many of these spaces are now being integrated into smart city infrastructures equipped with IoT-based sensing and location-aware services, opportunities for data-driven safety support are expanding. However, in these wide and crowded environments, a small number of social workers are responsible for supervising many elderly participants, which creates monitoring blind spots. In addition, age-related cognitive and physical decline increases the risk of wandering and sudden health deterioration, making timely detection and response difficult. To address this problem, we propose a safety monitoring system for seniors. The system is based on a cloud platform that collects location data from GPS modules and motion information from embedded sensors on mobile devices. It provides real-time tracking of each participant and periodically evaluates their safety state. When abnormal conditions are detected, alerts are delivered to both social workers and the corresponding senior. A prototype implementation, consisting of a cloud server and mobile applications for social workers and elderly users, has been developed. The system is evaluated through a field test conducted on a university campus. Full article

Campus stairwells, characterized by their crowded nature during certain short periods of time, present a high risk for falls that can lead to dangerous stampedes. Accurate fall detection is crucial for preventing such accidents. However, existing research lacks a detection model that balances high precision with lightweight design and lacks on-site experimental validation to assess practical feasibility. This study addresses these gaps by proposing an enhanced fall recognition model based on YOLOv7, validated through on-site experiments. A dataset on campus stairwell falls was established, capturing diverse stairwell personnel behaviors. Four YOLOv7 improvement schemes were proposed, and numerical comparison experiments identified the best-performing model, combining DO-DConv and Slim-Neck modules. This model achieved an average precision (mAP) of 88.1%, 2.41% higher than the traditional YOLOv7, while reducing GFLOPs from 105.2 to 38.2 and cutting training time by 4 h. A field experiment conducted with 22 groups of participants under small-scale populations and varying lighting conditions preliminarily confirmed that the model’s accuracy is within an acceptable range. The experimental results also analyzed the changes in detection confidence across different population sizes and lighting conditions, offering valuable insights for further model improvement and its practical applications. Full article

Driven by the global energy transition and carbon-neutrality goals, virtual power plants (VPPs) are expected to aggregate distributed energy resources and participate in multiple electricity markets while achieving economic efficiency and low carbon emissions. However, the strong volatility of wind and photovoltaic generation, together with the coupling between electric and thermal loads, makes real-time VPP scheduling challenging. Existing deep reinforcement learning (DRL)-based methods still suffer from limited predictive awareness and insufficient handling of physical and carbon-related constraints. To address these issues, this paper proposes an improved model, termed SAC-LAx, based on the Soft Actor–Critic (SAC) deep reinforcement learning algorithm for intelligent VPP scheduling. The model integrates an Attention–xLSTM prediction module and a Linear Programming (LP) constraint module: the former performs multi-step forecasting of loads and renewable generation to construct an extended state representation, while the latter projects raw DRL actions onto a feasible set that satisfies device operating limits, energy balance, and carbon trading constraints. These two modules work together with the SAC algorithm to form a closed perception–prediction–decision–control loop. A campus integrated-energy virtual power plant is adopted as the case study. The system consists of a gas–steam combined-cycle power plant (CCPP), battery storage, a heat pump, a thermal storage unit, wind turbines, photovoltaic arrays, and a carbon trading mechanism. Comparative simulation results show that, at the forecasting level, the Attention–xLSTM (Ax) module reduces the day-ahead electric load Mean Absolute Percentage Error (${\mathrm{M}}_{\mathrm{A}\mathrm{P}\mathrm{E}}$) from 4.51% and 5.77% obtained by classical Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) models to 2.88%, significantly improving prediction accuracy. At the scheduling level, the SAC-LAx model achieves an average reward of approximately 1440 and converges within around 2500 training episodes, outperforming other DRL algorithms such as Deep Deterministic Policy Gradient (DDPG), Twin Delayed Deep Deterministic Policy Gradient (TD3), and Proximal Policy Optimization (PPO). Under the SAC-LAx framework, the daily net operating cost of the VPP is markedly reduced. With the carbon trading mechanism, the total carbon emission cost decreases by about 49% compared with the no-trading scenario, while electric–thermal power balance is maintained. These results indicate that integrating prediction enhancement and LP-based safety constraints with deep reinforcement learning provides a feasible pathway for low-carbon intelligent scheduling of VPPs. Full article

This study explores how outdoor environments in cold-region university campuses influence students’ physical and mental health, addressing the lack of research on health-oriented campus design under cold climatic conditions. Drawing on Evidence-Based Design (EBD) theory and the Socio-Ecological Model (SEM), a Multi-Factor Analysis (MFA) framework integrating theoretical analysis, data mining, and empirical validation was developed to reveal the mechanisms linking campus environmental factors and student health. Through a systematic literature review and Latent Dirichlet Allocation (LDA) topic modeling, six key factors—climate adaptability, architectural layout, infrastructure, natural landscape, safety, and transportation accessibility—were identified and further verified through questionnaire data (N = 480) for reliability and validity. The Delphi method was then used to refine the indicator system and determine factor weights, while case studies of representative cold-region universities proposed optimization strategies from the dimensions of built environment, climatic adaptation, and perceived environment. The findings enrich the application of socio-ecological theory in health-oriented campus research and provide scientific and practical guidance for planning and promoting healthy university environments in cold regions. Full article

Campus buildings often present hidden safety risks such as falls and wheelchair instabilities, which are closely related to architectural layout, material selection, and accessibility design. This study develops YOLOv11-Safe, an attention-enhanced and geometry-aware framework that functions as both a detection model and a spatial diagnostic tool for building safety assessment. The framework integrates a modified SimAM attention mechanism and a normalized Wasserstein distance (NWD) loss to improve detection accuracy in complex indoor environments, trained on a dataset of 1000 annotated images covering fall and wheelchair accident scenarios. To interpret spatial risk patterns, a Random Forest classifier combined with SHAP analysis was applied to quantify the contribution of five architectural–behavioral variables: body–ground contact ratio (BGCR), accessibility index (AI), event duration (D), body posture angle (PA), and spatial density (SD). Results show that BGCR and AI dominate the risk-level prediction, while D, PA, and SD refine boundary conditions. Scene-based verification further demonstrated that the framework accurately localized unsafe features—such as uneven drainage edges and discontinuous handrails—and translated them into actionable design feedback. The proposed approach thus links deep-learning detection with interpretable spatial analysis, offering a quantitative foundation for evidence-based architectural safety optimization in university campuses. Full article

This study presents a comprehensive methodological framework that encompasses all stages required to evaluate the structural response to potential seismic motions. The proposed approach involves the estimation of seismic hazard at the site of interest, the disaggregation and definition of control earthquakes, the characterization of local site effects, the assessment of possible resonance phenomena, and the comparison between response spectra derived from probable seismic scenarios and the design spectra of the buildings, leading to conclusions regarding structural safety. The methodology integrates instrumental measurements of soil and building vibration periods with analytical procedures to define response spectra consistent with expected seismic scenarios. It was applied to buildings of special importance located in Guatemala City, particularly within the University of San Carlos of Guatemala (USAC) campus, with the aim of evaluating their structural safety and developing retrofitting criteria when necessary. The implementation began with a probabilistic seismic hazard analysis (PSHA) to identify control earthquakes that make the largest contribution to hazard for a 475-year return period, followed by the estimation of rock response spectra. A seismic microzonation study was then conducted to characterize local site conditions. Instrumental vibration measurements of the soil and structures were obtained, and a soil–structure interaction analysis was carried out to evaluate potential resonance effects. The results showed no evidence of resonance. Finally, soil response spectra derived from the control earthquakes were compared with the design spectra defined by the AGIES 2024 structural safety standards. The results confirmed that the design spectra adequately envelope the computed response spectra for all soil–structure combinations. The proposed methodology is replicable and can be used to assess the seismic design adequacy of other buildings, providing a rational basis for retrofitting decisions when design spectra do not fully encompass the expected seismic response. Full article

This paper presents a comparative analysis of pedestrian behavior and perceived safety among university students at two signalized intersections near the campus premises of the Aristotle University of Thessaloniki, Greece. Although both intersections include pedestrian crosswalks and traffic lights, one permits vehicle left turns during pedestrian phases via flashing yellow arrows, while the other restricts all vehicle movement. Two questionnaire-based surveys (n₁ = 304 and n₂ = 303) recorded demographic information, crossing behavior, perceived risk, and preferred safety interventions. Results indicate that the intersection permitting vehicle conflict is associated with significantly lower levels of perceived safety and higher instances of risk-taking, such as crossing “at any time”. Conversely, the vehicle-restricted intersection fosters greater compliance with pedestrian signals and a stronger sense of security. Key factors influencing crossing decisions included vehicle speed, signal duration, pedestrian group presence, and urgency. Respondents prioritized safety improvements such as pedestrian countdown timers, enhanced signage, and enforcement cameras. These findings underscore the critical role of signal phasing in shaping pedestrian behavior and safety perceptions. Evidence-based recommendations are offered to urban planners and policymakers to enhance pedestrian safety through targeted infrastructure upgrades and enforcement strategies. Full article

Global road safety reports identify human factors as the leading causes of traffic accidents, particularly behaviors such as speeding, drunk driving, and driver distraction, emphasizing the need for autonomous driving technologies to enhance transport safety. This research aims to provide a practical model for the development of autonomous driving systems as part of an autonomous transportation system for inter-building passenger mobility, intended to enable safe and efficient short-distance transport between buildings in semi-open environments such as university campuses. This work presents a fully integrated autonomous platform combining LiDAR, cameras, and IMU sensors for mapping, perception, localization, and control within a drive-by-wire framework, achieving superior coordination in driving, braking, and obstacle avoidance and validated under real campus conditions. The electric golf cart prototype achieved centimeter-level mapping accuracy (0.32 m), precise localization (0.08 m), and 2D object detection with an mAP value exceeding 70%, demonstrating accurate perception and positioning under real-world conditions. These results confirm its reliable performance and suitability for practical autonomous operation. Field tests showed that the vehicle maintained appropriate speeds and path curvature while performing effective obstacle avoidance. The findings highlight the system’s potential to improve safety and reliability in short-distance autonomous mobility while supporting scalable smart mobility development. Full article

A university campus is a composite built environment integrating research, daily life, culture, and ecological green space. Its landscape elements shape environmental perception and overall spatial quality. This study assesses spatial quality by identifying key features and optimizing their joint effects across three perceptions: safety, comfort, and belonging. Using a Chinese campus, we captured street-view images, applied semantic segmentation to quantify elements (grass, trees, buildings, roads, sidewalks), and used explainable machine learning with data augmentation to identify the features most relevant to these perceptions. This study then employed fuzzy-set Qualitative Comparative Analysis (fsQCA) to reveal configuration pathways that enhance spatial quality. Results show that data augmentation mitigates class imbalance and improves prediction accuracy. Key features include sky, river, bridge, people, grass, and sidewalks, and path analysis indicates that greater sky openness and higher densities of people, roads, sidewalks, and grass, together with fewer buildings, cars, and bare earth, enhance safety, comfort, and belonging. This study delivers globally transferable design rules and a replicable, policy-ready workflow that enables evidence-based campus upgrades across diverse regions. Full article

Universities face continuous challenges in ensuring rapid and efficient communication during emergencies due to outdated, fragmented, and manual notification systems. This research presents the design, development, and implementation of a multiplatform mobile application to optimize emergency notifications at the Escuela Superior Politécnica de Chimborazo (ESPOCH). The application, developed using the Flutter framework, offers real-time alert dispatch, geolocation services, and seamless integration with ESPOCH’s Security Unit through Application Programming Interfaces (APIs). A descriptive and applied research methodology was adopted, analyzing existing notification workflows and evaluating agile development methodologies. MOBILE-D was selected for its rapid iteration capabilities and alignment with small development teams. The application’s architecture incorporates a Node.js backend, Firebase Realtime Database, Google Maps API, and the ESPOCH Digital ID API for robust and scalable performance. Efficiency metrics were evaluated using ISO/IEC 25010 standards, focusing on temporal behavior. The results demonstrated a 53.92% reduction in response times compared to traditional notification processes, enhancing operational readiness and safety across the campus. This study underscores the importance of leveraging mobile technologies to streamline emergency communication and provides a scalable model for educational institutions seeking to modernize their security protocols. Full article

Building maintenance is a critical component of ensuring long-term performance, safety, and cost-efficiency in both conventional and critical infrastructures. While traditional contracting approaches have often led to inefficiencies and rigid procurement systems, recent developments in performance-based maintenance, digital technologies, and multi-objective optimization provide opportunities to enhance both operational reliability and energy performance. From a resilience perspective, the ability to sustain functionality, adapt maintenance intensity, and recover performance under resource or operational stress is essential for ensuring infrastructure continuity and resilience. This study develops and validates an optimization model for the operation and maintenance of large campus infrastructures, addressing the persistent imbalance between over-maintenance, where costs exceed optimal levels by up to 300%, and under-maintenance, which compromises performance continuity and weakens resilience over time. The model integrates maintenance efficiency indicators, building performance indices, and energy-efficiency retrofits, particularly LED-based lighting upgrades, within a multi-choice goal programming framework. Using datasets from 15 campuses comprising over 2000 buildings, the model was tested through case studies, sensitivity analyses, and simulations under varying facility life cycle expectancies. The facilities were analyzed for alternative life cycles of 25, 50, 75, and 90 years, and the design life cycle was set for 50 years. The results show that the optimized approach can reduce maintenance costs by an average of 34%, with savings ranging from 1% to 55% across campuses. Additionally, energy retrofit strategies such as LED replacement yielded significant economic and environmental benefits, with payback periods of approximately 2–2.5 years. The findings demonstrate that integrated maintenance and energy-efficiency planning can simultaneously enhance building performance, reduce costs, and support sustainability objectives, offering a practical decision-support tool for managing large-scale campus infrastructures. Full article

As smart campus construction continues to advance, traditional safety monitoring and environmental sensing systems are increasingly showing limitations in sensitivity, anti-interference capability, and deployment flexibility. Optical fiber sensing (OFS) technology, with its advantages of high sensitivity, passive operation, immunity to electromagnetic interference, and long-distance distributed sensing, provides a novel solution for real-time monitoring and early warning of critical campus infrastructure. This review systematically examines representative applications of OFS technology in smart campus scenarios, including structural health monitoring of academic buildings, laboratory environmental sensing, and intelligent campus security. By analyzing the technical characteristics of various types of optical fiber sensors, the paper explores emerging developments and future potential of OFS in supporting intelligent campus construction. Finally, the feasibility of building data acquisition, transmission, and visualization platforms based on OFS systems is discussed, highlighting their promising roles in campus safety operations, the integration of teaching and research, and intelligent equipment management. Full article