Search Results (165)

Background/Objectives: Early bystander CPR helps to restore perfusion and improves the likelihood of favorable survival and neurological outcome after out-of-hospital cardiac arrest (OHCA). One strategy to improve bystander CPR is the use of crowd-sourcing mobile CPR applications such as PulsePoint, which notifies bystanders of nearby OHCA. In 2019, PulsePoint was deployed in an urban county. Prior to its deployment, bystander CPR rates were 42.9% in this county. This descriptive analysis seeks to analyze bystander intervention after PulsePoint implementation in an urban county. Methods: This retrospective observational study included all PulsePoint activations in Alachua County from June 2020 to September 2023. Patient characteristics and survey data were extracted from EMS patient care reports, hospital electronic medical records, and Pulsepoint dispatch and responder data. Descriptive statistics were used to analyze patient and responder characteristics, PulsePoint activation circumstances, and patient care. Results: Of 225 PulsePoint activations, 95 (42.2%) were confirmed OHCA. Among these, 54 (56.8%) received bystander CPR prior to EMS arrival. Out of 15 prehospital defibrillations, laypersons defibrillated 9 patients (60.0%). There was an average of 3.3 eligible PulsePoint responders within a 0.25-mile radius of the OHCA victim. A majority of PulsePoint survey respondents were formally trained in CPR and automated defibrillator use. Conclusions: The data from our urban EMS experience demonstrate that bystander CPR rates were higher after PulsePoint deployment (56.8%) than before. Our bystander CPR rate was also higher than the national average. Full article

This study presents the e[kent-im] model, a map-based crowdsourcing initiative that digitizes and safeguards urban memory and cultural heritage through community participation and digital tools. The model facilitates the collection, archiving, and dissemination of urban memories by fostering intergenerational knowledge transfer and encouraging civic engagement in heritage preservation. Implemented in the historical center of Kütahya/Türkiye, the project gathered 150 memories and stories from 12 senior participants aged 50–85, which were linked to 303 historical visuals sourced from personal archives. These materials were integrated into a custom-designed web and mobile interface (Mapotic Pro) enriched with metadata categories such as type, period, and location, enabling users to filter and navigate content effectively and watch the videos enriched with participant narratives. A digital city archive matrix was also developed to systematically organize the collected data and support the web-based platform. To assess the platform’s effectiveness, a pilot study with 15 young participants aged 18–28 was conducted. During a self-guided city tour, participants engaged with historical content on the platform and provided feedback through pre- and post-test evaluations. Results indicated heightened awareness of and interest in cultural heritage, demonstrating the model’s potential as both an interactive archive and a tool facilitating intergenerational heritage awareness. Overall, this study highlights the model’s adaptability, scalability, and capacity to bridge generational and technological divides. Full article

In the evolving landscape of Mobile Crowdsourcing (MCS), ensuring the security and privacy of both stored and transmitted multimedia content has become increasingly challenging. Factors such as human mobility, device heterogeneity, dynamic topologies, and data diversity exacerbate the complexity of addressing these concerns effectively. To tackle these challenges, this paper introduces CSXAI (Crowdsourcing eXplainable Artificial Intelligence)—a novel explainable AI system designed to proactively assess and communicate the security status of multimedia resources downloaded in MCS environments. While CSXAI integrates established attack detection techniques, its primary novelty lies in its synthesis of these methods with a user-centric XAI framework tailored for the specific challenges of MCS frameworks. CSXAI intelligently analyzes potential vulnerabilities and threat scenarios by evaluating website context, attack impact, and user-specific characteristics. The current implementation focuses on the detection and explanation of three major web vulnerability classes: Cross-Site Scripting (XSS), Cross-Site Request Forgery (CSRF), and insecure File Upload. The proposed system not only detects digital threats in advance but also adapts its explanations to suit both technical and non-technical users, thereby enabling informed decision-making before users access potentially harmful content. Furthermore, the system offers actionable security recommendations through clear, tailored explanations, enhancing users’ ability to implement protective measures across diverse devices. The results from real-world testing suggest a notable improvement in users’ ability to understand and mitigate security risks in MCS environments. By combining proactive vulnerability detection with user-adaptive, explainable feedback, the CSXAI framework shows promise in empowering users to enhance their security posture effectively, even with minimal cybersecurity expertise. These findings underscore the potential of CSXAI as a reliable and accessible solution for tackling cybersecurity challenges in dynamic, multimedia-driven ecosystems. Quantitative results showed high user satisfaction and interpretability (SUS = 79.75 ± 6.40; USE subscales = 5.32–5.88). Full article

One of the key challenges for city authorities is to ensure an adequate quality of life for residents while promoting sustainable urban development. Achieving this balance is closely related to transport management which strongly affects urban quality of life, energy consumption, and resource savings. The aim of this article is to propose a new approach of assessing urban transport management quality, with a view to implement urban energy and resource-saving policies. The assessment procedure is based on the Six Sigma methodology and is illustrated using the example of the city of Szczecin for three selected routes. Travel data were obtained based on actual vehicle traffic using crowdsourcing methods. The capacity processes were assessed based on the potential capacity index and the actual capacity index, which characterise deviations in urban traffic from the best way to save energy and resources. Customer specification limits were set based on surveys assessing residents’ expectations regarding car travel times on the analysed routes. The results show that the methodology proposed in the article can be successfully used to assess urban transport management and to identify areas in need of improvement for sustainable transport panning. Full article

Rapid urban growth in Middle Eastern cities has intensified congestion-related challenges, yet traffic data-based decision making remains limited. This study leverages crowd-sourced travel time data from the Google Maps API to evaluate temporal and spatial patterns of congestion across multiple strategic routes in Jeddah, Saudi Arabia, a coastal metropolis with a complex road network characterized by narrow, high-traffic corridors and limited public transit. A real-time Congestion Index quantifies traffic flow, incorporating free-flow speed benchmarking, dynamic profiling, and temporal classification to pinpoint congestion hotspots. The analysis identifies consistent peak congestion windows and route-specific delays that are critical for travel behavior modeling. In addition to congestion monitoring, the framework contributes to urban sustainability by supporting reductions in traffic-related emissions, enhancing mobility equity, and improving economic efficiency through data-driven transport management. To our knowledge, this is the first study to systematically use the validated, real-time Google Maps API to quantify route-specific congestion in a Middle Eastern urban context. The approach provides a scalable and replicable framework for evaluating urban mobility in other data-sparse cities, especially in contexts where traditional traffic sensors or GPS tracking are unavailable. The findings support evidence-based transport policy and demonstrate the utility of publicly accessible traffic data for smart city integration, real-time traffic monitoring, and assisting transport authorities in enhancing urban mobility. Full article

Speaker profiling systems are often evaluated on a single corpus, which complicates reliable comparison. We present a fully reproducible evaluation pipeline that trains Convolutional Neural Networks (CNNs) and Long-Short Term Memory (LSTM) models independently on three speech corpora representing distinct recording conditions—studio-quality TIMIT, crowdsourced Mozilla Common Voice, and in-the-wild VoxCeleb1. All models share the same architecture, optimizer, and data preprocessing; no corpus-specific hyperparameter tuning is applied. We perform a detailed preprocessing and feature extraction procedure, evaluating multiple configurations and validating their applicability and effectiveness in improving the obtained results. A feature analysis shows that Mel spectrograms benefit CNNs, whereas Mel Frequency Cepstral Coefficients (MFCCs) suit LSTMs, and that the optimal Mel-bin count grows with corpus Signal Noise Rate (SNR). With this fixed recipe, EfficientNet achieves 99.82% gender accuracy on Common Voice (+1.25 pp over the previous best) and 98.86% on VoxCeleb1 (+0.57 pp). MobileNet attains 99.86% age-group accuracy on Common Voice (+2.86 pp) and a 5.35-year MAE for age estimation on TIMIT using a lightweight configuration. The consistent, near-state-of-the-art results across three acoustically diverse datasets substantiate the robustness and versatility of the proposed pipeline. Code and pre-trained weights are released to facilitate downstream research. Full article

Today’s cities are facing the challenges of increasing traffic congestion, emissions, and the need to improve road safety. The solution to these problems is the use of artificial intelligence (AI) and the Internet of Things (IoT) in intelligent traffic management. The purpose of the article is to analyze and evaluate AI- and IoT-based solutions implemented in Polish cities and to identify innovative proposals that can improve traffic management. The study uses a mixed-method approach, including the analysis of crowdsourced mobility data (from GPS, smartphones, and municipal reports), GIS tools for mapping congestion, big data analytics, and machine learning algorithms, to evaluate trends and predict traffic scenarios. The evaluation focused on seven major Polish cities—Warsaw, Krakow, Wroclaw, Gdansk, Poznan, Katowice, and Lodz—where intelligent transportation systems such as dynamic traffic lights, intelligent pedestrian crossings, accident prediction systems, and parking space management have been implemented. The effectiveness of these solutions was assessed using the following six key indicators: waiting time at intersections, travel time, congestion level, CO₂ emissions, energy consumption, and number of traffic incidents. The article provides a comprehensive analysis of these solutions’ impacts on traffic flow, emissions, energy efficiency, and road safety. A key contribution of the paper is the presentation of new proposals for improvements, such as the inclusion of behavioral data in traffic modeling, integration with GPS navigation, and dynamic emergency and public transport priority management. The article also discusses further digitization and interoperability needs. The findings show that the implementation of intelligent transportation systems not only improves urban mobility and safety but also enhances environmental sustainability and residents’ quality of life. Full article

In complex indoor and outdoor scenarios, traditional GPS-based ranging technology faces limitations in availability due to signal occlusion and user privacy issues. Wireless signal ranging technology based on 5G base stations has emerged as a potential alternative. However, existing methods are limited by low efficiency in constructing static signal databases, poor environmental adaptability, and high resource overhead, restricting their practical application. This paper proposes a 5G wireless signal ranging framework that integrates mobile edge computing (MEC) and crowdsourced intelligence to systematically address the aforementioned issues. This study designs a progressive solution by (1) building a crowdsourced data collection network, using mobile terminals equipped with GPS technology to automatically collect device signal features, replacing inefficient manual drive tests; (2) developing a progressive signal update algorithm that integrates real-time crowdsourced data and historical signals to optimize the signal fingerprint database in dynamic environments; (3) establishing an edge service architecture to offload signal matching and trajectory estimation tasks to MEC nodes, using lightweight computing engines to reduce the load on the core network. Experimental results demonstrate a mean positioning error of 5 m, with 95% of devices achieving errors within 10 m, as well as building and floor prediction error rates of 0.5% and 1%, respectively. The proposed framework outperforms traditional static methods by 3× in ranging accuracy while maintaining computational efficiency, achieving significant improvements in environmental adaptability and service scalability. Full article

Background: The rapid rise of e-commerce has intensified last-mile logistics challenges, fueling the need for sustainable, efficient solutions. Parcel locker crowdshipping systems, integrated with public transport networks, show promise in reducing congestion, emissions, and delivery costs. However, operational and physical constraints (e.g., crowded stations) and liability complexities remain significant barriers to broad adoption. This study investigates the demographic and operational factors that influence the adoption and scalability of these systems. Methods: A mixed-methods design was employed, incorporating survey data from 368 participants alongside insights from 20 semi-structured interviews. Quantitative analysis identified demographic trends and operational preferences, while thematic analysis offered in-depth contextual understanding. Results: Younger adults (18–34), particularly gig-experienced males, emerged as the most engaged demographic. Females and older individuals showed meaningful potential if safety and flexibility concerns were addressed. System efficiency depended on locating parcel lockers within 1 km of major origins and destinations, focusing on moderate parcel weights (3–5 kg), and offering incentives for minor route deviations. Interviews emphasized ensuring that lockers avoid station congestion, clearly defining insurance/liability protocols, and allowing task refusals during peak passenger hours. Conclusions: By leveraging public transport infrastructure, parcel locker crowdshipping requires robust policy frameworks, strategic station-space allocation, and transparent incentives to enhance feasibility. Full article

Data on pedestrian infrastructure is essential for improving the mobility environment and for planning efficiency. Although governmental agencies are responsible for capturing data on pedestrian infrastructure mostly by field audits, most have not completed such audits. In recent years, virtual auditing based on street view imagery (SVI), specifically through geo-crowdsourcing platforms, offers a more inclusive approach to pedestrian movement planning, but concerns about the quality and reliability of opensource geospatial data pose barriers to use by governments. Limited research has compared opensource data in relation to traditional government approaches. In this study, we compare pedestrian infrastructure data from an opensource virtual sidewalk audit platform (Project Sidewalk) with government data. We focus on neighborhoods with diverse walkability and income levels in the city of Seattle, Washington and in DuPage County, Illinois. Our analysis shows that Project Sidewalk data can be a reliable alternative to government data for most pedestrian infrastructure features. The agreement for different features ranges from 75% for pedestrian signals to complete agreement (100%) for missing sidewalks. However, variations in measuring the severity of barriers challenges dataset comparisons. Full article

Vibration-based bridge modal identification is a crucial tool in monitoring and managing transportation infrastructure. Traditionally, this entails deploying a fixed array of sensors to measure bridge responses such as accelerations, determine dynamic characteristics, and subsequently infer bridge conditions that will facilitate prognosis and decision-making. However, such a paradigm is not scalable, possesses limited spatial resolution, and typically entails high effort and cost. Recently, mobile sensing-based paradigms have demonstrated promise in laboratory and field settings as an alternative. These methods can leverage big data from crowdsourcing vibration data acquired from smartphone devices belonging to pedestrians and passengers traveling over a bridge, constituting a significantly large data stream of indirectly sensed bridge response. Although the efficacy of such a paradigm has been demonstrated for a limited set of case studies, ubiquitous implementation requires analyzing the impact of vehicle dynamics and quantifying data sources that can be used for the purpose of bridge modal identification. This paper presents a road map for achieving this through dynamically diverse datastreams such as passenger cars, buses, bikes, and scooters. Existing datastreams point towards the implementation of crowdsourced mobile sensing paradigms in urban settings, which would facilitate effective decision-making for enhanced transportation infrastructure resilience. Full article

The increasing frequency and severity of disasters in urban areas demand sustainable, smart disaster management strategies to leverage technological advancements. This study provides a comprehensive review of mobile apps for disaster awareness available in the Google Play Store, with a particular emphasis on addressing flood disaster readiness and response. Mobile apps have become indispensable tools for disseminating immediate notifications, facilitating emergency communication, and coordinating response activities. A total of 77 mobile apps in the Google Play Store were identified and evaluated using a systematic search. The evaluation criteria included user ratings, download counts, and key crisis management functionalities such as real-time alerts, emergency contact directories, preparedness checklists, and user reporting capabilities. The findings emphasised the following: (a) the importance of integrating cutting-edge technologies, i.e., AI and IoT, to enhance functionality, accuracy, and capacity in mobile applications; (b) the use of crowdsourcing as a valuable mechanism for enriching inclusive and responsible data; (c) enabling timely updates and fostering community engagement; and (d) establishing agency engagements, gamified elements, and real-time reciprocal communication tools, i.e., push-to-talk features to ensure the long-term sustainability of mobile apps. By incorporating these insights, disaster management apps can significantly enhance community resilience and improve the effectiveness of responding to natural disasters in this digital age. Full article

The present study discusses the design and development of a digital repository for the preservation and dissemination of the cultural and natural heritage of Zakynthos Island (Greece). Following a crowdsourcing approach, the platform allows users to actively contribute to its content while aiming to integrate scattered information from other relative initiatives. The platform is based on a popular Content Management System (CMS) to provide the core functionality, extended with the use of the CMS’s API to provide additional, personalized functionality for end-users, such as organizing content into thematic routes. The system also features a web application, mainly targeting users visiting the island of Zakynthos, and is developed exclusively with open web technologies and JavaScript frameworks. The web application is an alternative, map-centered, mobile-optimized front-end for the platform’s content featured in the CMS. A RESTful API is also provided, allowing integration with third-party systems and web applications, thereby expanding the repository’s reach and capabilities. Content delivery is personalized, based on users’ profiles, location, and preferences, enhancing engagement and usability. By integrating these features, the repository effectively preserves and makes accessible the unique cultural and natural heritage of Zakynthos to both local and global audiences. Full article

Outdoor jogging plays a critical role in active mobility and transport-related physical activity (TPA), contributing to both urban health and sustainability. While existing studies have primarily focused on jogging participation volumes through survey data, they often overlook the real-time dynamics that shape jogging experiences. This study seeks to provide a data-driven analysis of both jogging volume and speed, exploring how environmental factors influence these behaviors. Utilizing a dataset of over 1000 crowd-sourced jogging trajectories in Shenzhen, we spatially linked these trajectories to road-section-level units to map the distribution of jogging volume and average speed. By depicting a bivariate map of both behavioral characteristics, we identified spatial patterns in jogging behavior, elucidating variations in the distribution of volume and speed. A random forest regression model was validated and employed to capture nonlinear relationships and assess the differential impacts of various environmental factors on jogging volume and speed. The results reveal distinct jogging patterns across the city, where jogging volume is shaped by the mixed interplay of natural, visual, and built environment factors, while jogging speed is primarily influenced by visual factors. Additionally, the analysis highlights nonlinear effects, particularly identifying a threshold beyond which incremental environmental improvements provide diminishing returns in jogging speed. These findings clarify the distinct roles of environmental factors in influencing jogging volume and speed, offering insights into the dynamics of active mobility. Ultimately, this study provides data-informed implications for urban planners seeking to create environments that support TPA and promote active lifestyles. Full article

Earth science education can be enriched by adding technological knowledge to enable monitoring human earth impacts by using soil science as an example. Modern sensing technologies and a mobile mapping platform can enhance an existing field laboratory exercise to expand students’ knowledge beyond the core subject matter. This multi-year study’s objectives were to enrich laboratory exercise content on soil compaction using a soil penetration resistance (PR) tester (penetrometer) with the concepts of direct (soil PR) and proximal remote sensing (cellphone photos of the sample area), and crowdsourcing of field data using a GPS-enabled mobile phone application in an introductory soil science course at Clemson University, South Carolina (SC), United States of America (USA). Students from multiple Science, Technology, Engineering, and Mathematics (STEM) disciplines (forestry, wildlife biology, and environmental and natural resources) participated in the study. They completed a set of reusable learning objects (RLOs) in the following sequence: pre-testing questionnaire, laboratory video, quiz, and post-testing questionnaire. Students had increased familiarity with the concepts from this exercise, as demonstrated by the post-assessment survey. The quiz, which was taken by 113 students online, had an average total correct score of 9 out of a possible 10. A post-assessment survey indicated that the laboratory exercise was an effective way to learn about field soil PR data, direct and proximal remote sensing, and crowdsourcing with a GPS-enabled cellphone application. Results from the two study years (2022 and 2024) were consistent, indicating validity and confidence in the findings. Full article