Search Results (32)

The address is a key element in the construction of smart cities. When receiving reports from citizens, public security officers need to quickly and accurately locate a crime scene based on the address provided by the reporter. The address from the reporter may be a standard address or it may be a point of interest, abbreviation, or common name. The difficulty in converting the address into a standard address can be solved through the analysis of address elements and address matching. We developed a bidirectional encoder representations from transformers (BERT)-based address feature resolution method and an address-matching algorithm. On this basis, a police force address-matching system for City A was designed and implemented. A Web application system was also developed based on the address database of City A. The developed address resolution and matching method with the database maintenance module successfully matched the reported address to the standard one. Full article

Urban traffic congestion poses persistent challenges to mobility, public safety, and governance efficiency in metropolitan areas. This study proposes an intelligent traffic flow forecasting framework based on an extended Long Short-Term Memory (xLSTM) model, specifically designed for real-time congestion prediction and proactive police dispatch support. Utilizing a real-world dataset collected from over 300 vehicle detector (VD) sensors, the proposed model integrates vehicle volume, speed, and lane occupancy data at five-minute intervals. Methodologically, the xLSTM model incorporates matrix-based memory cells and exponential gating mechanisms to enhance spatio-temporal learning capabilities. Model performance is evaluated using multiple metrics, including congestion classification accuracy, F1-score, MAE, RMSE, and inference latency. The xLSTM model achieves a congestion prediction accuracy of 87.3%, an F1-score of 0.882, and an average inference latency of 41.2 milliseconds—outperforming baseline LSTM, GRU, and Transformer-based models in both accuracy and speed. These results validate the system’s suitability for real-time deployment in police control centers, where timely prediction of traffic congestion enables anticipatory patrol allocation and dynamic signal adjustment. By bridging AI-driven forecasting with public safety operations, this research contributes a validated and scalable approach to intelligent transportation governance, enhancing the responsiveness of urban mobility systems and advancing smart city initiatives. Full article

Sound event detection tasks are rapidly advancing in the field of pattern recognition, and deep learning methods are particularly well suited for such tasks. One of the important directions in this field is to detect the sounds of emotional events around residential buildings in smart cities and quickly assess the situation for security purposes. This research presents a comprehensive study of an ensemble convolutional recurrent neural network (CRNN) model designed for sound event detection (SED) in residential and public safety contexts. The work focuses on extracting meaningful features from audio signals using image-based representation, such as Discrete Cosine Transform (DCT) spectrograms, Cocheagrams, and Mel spectrograms, to enhance robustness against noise and improve feature extraction. In collaboration with police officers, a two-hour dataset consisting of 112 clips related to four classes of emotional sounds, such as harassment, quarrels, screams, and breaking sounds, was prepared. In addition to the crowdsourced dataset, publicly available datasets were used to broaden the study’s applicability. Our dataset contains 5055 audio files of different lengths totaling 14.14 h and strongly labeled data. The dataset consists of 13 separate sound categories. The proposed CRNN model integrates spatial and temporal feature extraction by processing these spectrograms through convolution and bi-directional gated recurrent unit (GRU) layers. An ensemble approach combines predictions from three models, achieving F1 scores of 71.5% for segment-based metrics and 46% for event-based metrics. The results demonstrate the model’s effectiveness in detecting sound events under noisy conditions, even with a small, unbalanced dataset. This research highlights the potential of the model for real-time audio surveillance systems using mini-computers, offering cost-effective and accurate solutions for maintaining public order. Full article

Multirotor drones play an increasingly significant role in smart cities and are among the most widely discussed emerging technologies. They are expected to support various applications such as package delivery, data collection, traffic policing, surveillance, and medicine. As part of their services, future drones should be able to solve the last-mile challenge and land safely in urban areas. This paper addresses the path planning task for an autonomous drone searching for a landing place in an urban environment. Our algorithm uses a novel multi-resolution probabilistic approach in which visual information is collected by the drone at decreasing altitudes. As part of the exploration task, we present the Global Path Planning (GPP) problem, which uses probabilistic information and the camera’s field of view to plan safe trajectories that will maximize the search success by covering areas with high potential for proper landing while avoiding no-fly zones and complying with time constraints. The GPP problem is formulated as a minimization problem and then is shown to be NP-hard. As a baseline, we develop an approximation algorithm based on an exhaustive search, and then we devise a more complex yet efficient heuristic algorithm to solve the problem. Finally, we evaluate the algorithms’ performance using simulation experiments. Simulation results obtained from various scenarios show that the proposed heuristic algorithm significantly reduces computation time while keeping coverage performance close to the baseline. To the best of our knowledge, this is the first work referring to a multi-resolution approach to such search missions; further, in particular, the GPP problem has not been addressed previously. Full article

Vegetation phenology is an important indicator of climate change and ecosystem productivity. However, the monitoring of vegetation generative phenology through remote sensing techniques does not allow for species-specific retrieval in mixed ecosystems; hence, land surface phenology (LSP) is used instead of traditional plant phenology based on plant organ emergence and development observations. Despite the estimated timing of the LSP parameters being dependent on the vegetation index (VI) used, inadequate attention was paid to the evaluation of the commonly used VIs for LSP of different vegetation covers. We used two years of data from the experimental site in central European peatland, where plots of two peatland vegetation communities are under a climate manipulation experiment. We assessed the accuracy of LSP retrieval by simple remote sensing metrics against LSP derived from gross primary production and canopy chlorophyll content time series. The product of Near-Infrared Reflectance of Vegetation and Photosynthetically Active Radiation (NIRvP) and Green Chromatic Coordinates (GCC) was identified as the best-performing remote sensing metrics for peatland physiological and structural phenology, respectively. Our results suggest that the changes in the physiological phenology due to increased temperature are more prominent than the changes in the structural phenology. This may mean that despite a rather accurate assessment of the structural LSP of peatland by remote sensing, the changes in the functioning of the ecosystem can be underestimated by simple VIs. This ground-based phenological study on peatlands provides the base for more accurate monitoring of interannual variation of carbon sink strength through remote sensing. Full article

With the development of Industry 4.0, collaborative mobile robots are becoming increasingly prevalent in industrial settings, raising important safety considerations in human–robot interaction environments. This study examines the safety issues in collaborative mobile robotics through a case study of a smart factory utilizing quadruped robots. This research aims to contribute to the development of safety management strategies by identifying potential risk factors and analyzing the differences in risk perception among stakeholders. A survey was conducted among 93 operators in the factory to identify the main risk factors, followed by a Delphi study with four groups of experts: robot operators, safety management experts, robot developers, and academic experts. The Kruskal–Wallis and Mann–Whitney U tests were used to analyze the statistical significance of differences in perception between the groups. The results showed that collision and deviation from the path were the most concerning risk factors. Significant differences were found in the perceptions of several hazards between expert groups, with academic experts rating most hazards highly while robot developers rated them relatively low. The findings highlight how background knowledge and experience influence risk perception in collaborative robotics. These varying perspectives should be considered when developing safety management strategies for mobile robots in industrial settings, suggesting the importance of multi-stakeholder collaboration and targeted educational programs. Full article

Rapid urbanization in developing countries poses challenges such as rising crime rates and resource scarcity. Unmanned Aircraft Systems (UAS) offer a promising solution to enhance public safety, but their integration requires addressing specific challenges. This study employs the Systems-Theoretic Accident Model and Processes (STAMP) and System-Theoretic Process Analysis (STPA) methodologies to identify potential hazards and requirements for integrating UAS into public safety systems in urban environments. The research objectives include identifying hazards and challenges, developing safety requirements and guidelines, and proposing strategies for efficient infrastructure investment. The proposed framework, based on STAMP/STPA, includes additional steps to consider early-stage systems and maintain stakeholder traceability. A risk matrix approach is utilized to prioritize risk mitigation measures for cost-effectiveness. The findings of this study provide valuable insights for policymakers and urban planners in developing countries seeking to harness the potential of UAS technology for enhancing public safety while addressing the unique challenges posed by rapid urbanization. Full article

Increasing numbers of public and private locations now have surveillance cameras installed to make those areas more secure. Even though many organizations still hire someone to monitor the cameras, the person hired is more likely to miss some unexpected events in the video feeds because of human error. Several researchers have worked on surveillance data and have presented a number of approaches for automatically detecting aberrant events. To keep track of all the video data that accumulate, a supervisor is often required. To analyze the video data automatically, we recommend using neural networks to identify the crimes happening in the real world. Through our approach, it will be easier for police agencies to discover and assess criminal activity more quickly using our method, which will reduce the burden on their staff. In this paper, we aim to provide anomaly detection using surveillance videos as input specifically for the crimes of arson, burglary, stealing, and vandalism. It will provide an efficient and adaptable crime-detection system if integrated across the smart city infrastructure. In our project, we trained multiple accurate deep learning models for object detection and crime classification for arson, burglary and vandalism. For arson, the videos were trained using YOLOv5. Similarly for burglary and vandalism, we trained using YOLOv7 and YOLOv6, respectively. When the models were compared, YOLOv7 performed better with the highest mAP of 87. In this, we could not compare the model’s performance based on crime type because all the datasets for each crime type varied. So, for arson YOLOv5 performed well with 80% mAP and for vandalism, YOLOv6 performed well with 86% mAP. This paper designed an automatic identification of crime types based on camera or surveillance video in the absence of a monitoring person, and alerts registered users about crimes such as arson, burglary, and vandalism through an SMS service. To detect the object of the crime in the video, we trained five different machine learning models: Improved YOLOv5 for arson, Faster RCNN and YOLOv7 for burglary, and SSD MobileNet and YOLOv6 for vandalism. Other than improved models, we innovated by building ensemble models of all three crime types. The main aim of the project is to provide security to the society without human involvement and make affordable surveillance cameras to detect and classify crimes. In addition, we implemented the Web system design using the built package in Python, which is Gradio. This helps the registered user of the Twilio communication tool to receive alert messages when any suspicious activity happens around their communities. Full article

Smart policing refers to the use of advanced technologies such as artificial intelligence to enhance policing activities in terms of crime prevention or crime reduction. Artificial intelligence tools, including machine learning and natural language processing, have widespread applications across various fields, such as healthcare, business, and law enforcement. By means of these technologies, smart policing enables organizations to efficiently process and analyze large volumes of data. Some examples of smart policing applications are fingerprint detection, DNA matching, CCTV surveillance, and crime prediction. While artificial intelligence offers the potential to reduce human errors and biases, it is still essential to acknowledge that the algorithms reflect the data on which they are trained, which are inherently collected by human inputs. Considering the critical role of the police in ensuring public safety, the adoption of these algorithms demands careful and thoughtful implementation. This paper presents a systematic literature review focused on exploring the machine learning techniques employed by law enforcement agencies. It aims to shed light on the benefits and limitations of utilizing these techniques in smart policing and provide insights into the effectiveness and challenges associated with the integration of machine learning in law enforcement practices. Full article

The concept of Smart Cities integrates innovative technologies to improve citizens’ quality of life in towns and cities worldwide. Crisis management is a separate section directly managed by the leadership of municipalities, cities and counties in cooperation between police, fire and municipal police to ensure the safety of residents and safety in public spaces. The purpose of this study is to investigate to which extent publicly available information related to the field of crisis management is unavailable to residents in municipalities, towns and cities through online information systems. The primary aim is to provide suggestions for a general information system structure and content that would highlight and satisfy the need to address the crisis management issue, especially in providing immediate information to the population through an innovative online form. The achievement of this goal is methodologically based on qualitative research analysing and comparing the information published for residents through Smart City information systems in selected towns and municipalities. Document analysis or conceptual design was applied, and evaluation criteria for objective assessment of Smart City information systems were appropriately determined. The comparative analysis based on this set of criteria enabled the development of the proposals of information systems’ content that can be used to keep the information systems for Smart Cities in cities, municipalities and regions, actual and beneficial. From the available resources, two main modules that focused either on citizens or cities were synthesised. Moreover, SWOT analysis or the Smart Regions Rapid Response structure was derived. Acquired results outline generic structures and contents that support the development of the concept of Smart Cities and can be suitably implemented for the development of the modification of information systems containing relevant information for residents, cities and municipalities, focusing on citizen safety. Full article

Multimodal emotion classification (MEC) has been extensively studied in human–computer interaction, healthcare, and other domains. Previous MEC research has utilized identical multimodal annotations (IMAs) to train unimodal models, hindering the learning of effective unimodal representations due to differences between unimodal expressions and multimodal perceptions. Additionally, most MEC fusion techniques fail to consider the unimodal–multimodal inconsistencies. This study addresses two important issues in MEC: learning satisfactory unimodal representations of emotion and accounting for unimodal–multimodal inconsistencies during the fusion process. To tackle these challenges, the authors propose the Two-Stage Conformer-based MEC model (Uni2Mul) with two key innovations: (1) in stage one, unimodal models are trained using independent unimodal annotations (IUAs) to optimize unimodal emotion representations; (2) in stage two, a Conformer-based architecture is employed to fuse the unimodal representations learned in stage one and predict IMAs, accounting for unimodal–multimodal differences. The proposed model is evaluated on the CH-SIMS dataset. The experimental results demonstrate that Uni2Mul outperforms baseline models. This study makes two key contributions: (1) the use of IUAs improves unimodal learning; (2) the two-stage approach addresses unimodal–multimodal inconsistencies during Conformer-based fusion. Uni2Mul advances MEC by enhancing unimodal representation learning and Conformer-based fusion. Full article

Nowadays, the unmanned aerial vehicle (UAV) has a wide application in transportation. For instance, by leveraging it, we are able to perform accurate and real-time vehicle speed detection in an IoT-based smart city. Although numerous vehicle speed estimation methods exist, most of them lack real-time detection in different situations and scenarios. To fill the gap, this paper introduces a novel low-altitude vehicle speed detector system using UAVs for remote sensing applications of smart cities, forging to increase traffic safety and security. To this aim, (1) we have found the best possible Raspberry PI’s field of view (FOV) camera in indoor and outdoor scenarios by changing its height and degree. Then, (2) Mobile Net-SSD deep learning model parameters have been embedded in the PI4B processor of a physical car at different speeds. Finally, we implemented it in a real environment at the JXUST university intersection by changing the height (0.7 to 3 m) and the camera angle on the UAV. Specifically, this paper proposed an intelligent speed control system without the presence of real police that has been implemented on the edge node with the configuration of a PI4B and an Intel Neural Computing 2, along with the PI camera, which is armed with a Mobile Net-SSD deep learning model for the smart detection of vehicles and their speeds. The main purpose of this article is to propose the use of drones as a tool to detect the speeds of vehicles, especially in areas where it is not easy to access or install a fixed camera, in the context of future smart city traffic management and control. The experimental results have proven the superior performance of the proposed low-altitude UAV system rather than current studies for detecting and estimating the vehicles’ speeds in highly dynamic situations and different speeds. As the results showed, our solution is highly effective on crowded roads, such as junctions near schools, hospitals, and with unsteady vehicles from the speed level point of view. Full article

In this paper, a conventional camera modified to capture multispectral images, has been used to locate latent forensic traces with a smart combination of wavelength filters, capturing angle, and illumination sources. There are commercial multispectral capture devices adapted to the specific tasks of the police, but due to their high cost and operation not well adapted to the field work in a crime scene, they are not currently used by forensic units. In our work, we have used a digital SLR camera modified to obtain a nominal sensitivity beyond the visible spectrum. The goal is to obtain forensic evidences from a crime scene using the multispectral camera by an expert in the field knowing which wavelength filters and correct illumination sources should be used, making visible latent evidences hidden from the human-eye. In this paper, we show a procedure to retrieve from latent forensic traces, showing the validity of the system in different real cases (blood stains, hidden/erased tattoos, unlocking patterns on mobile devices). This work opens the possibility of applying multispectral inspections in the forensic field specially for operational units for the location of latent through non-invasive optical procedures. Full article

Public governance has evolved in terms of safety and security management, incorporating digital innovation and smart-analytics-based tools to visualize abundant data collections. Urban safety and security are vital social problems that have many branches to be solved, simplified, and improved. Currently, we can see that data-driven insights have often been incorporated into planning, forecasting, and fighting such challenges. The literature has extensively indicated several aspects of solving urban safety problems, i.e., social, technological, administrative, urban, and societal. We have a keen interest in the data analysis and smart analytics options that can be deployed to enhance the presentation, promotional analysis, planning, forecasting, and fighting of these problems. For this, we chose to focus on crime statistics and public surveys regarding victimization and perceptions of crime. As we found through a review, many studies have indicated the vitality of crime rates but not public perceptions in decision-making and planning regarding security. There is always a need for the integration of widespread data insights into unified analyses. This study aimed to answer (1) how effectively we can utilize the crime rates and statistics, and incorporate community perceptions and (2) how promising these two ways of seeing the same phenomena are. For the data analysis, we chose four neighboring countries in Central Europe. We selected CECs, i.e., Hungary, Poland, Czech Republic, and Slovakia, known collectively as the Visegrád Group or V4. The data resources were administrative police statistics and ESS (European Social Survey) statistical datasets. The choice of this region helped us reduce variability in regional dynamics, regime changes, and social control practices. Full article

As part of the project EDDA+ (Early Detection of Dangerous Areas in road traffic using smart data), a web-based crowdsourcing platform has been launched on which road users can report danger spots they face in everyday traffic. Whereas official police collision data can only be used reactively, these user reports are intended to warn other road users and provide road safety stakeholders with detailed information for proactive measures. Since this approach is relatively novel, the present pilot study aimed to evaluate the validity of these subjective road user reports. A quasi-randomized sample of N = 77 danger spots distributed over four major German cities was audited using a 70-item objective road safety deficit inventory to identify infrastructural deficits. Based on these items, an overall rating of objective hazardousness for each danger spot was derived. In more than half of the audited danger spots, infrastructural deficits were identified in the audit (=confirmed hazard). In another quarter of audited dangers spots, the reported hazard could not be identified without any doubt due to a lack of infrastructural deficit or detailed information about the nature of the hazard (=uncertain, no certain match between audit and report). Our analysis further revealed that an increased number of road user interactions for the respective danger spot yielded a higher likelihood of confirmation of a danger spot’s hazardousness. Descriptively, pedestrians and bicyclists were most often mentioned as exposed to danger, with the most prevalent nature of danger being areas with poor visibility and misconduct by drivers. The results were blended with police collision data in the next step. We did not find a significant relationship between our danger spots’ rating and the number of collisions at the respective spot. Our results indicate that reports of danger spots and the increased user related activity can serve as an indicator for the early detection of road traffic hazards. Full article