Crowd management is crucial for countries and organizations as it can lead to severe consequences or serious safety concerns. Most of the existing research focus on addressing limited crowd ...management issues, namely crowd counting, density estimation, localization, and behavior monitoring. Furthermore, the generated incidents' alerts are mostly not interpretable and remediable. Therefore, there is no comprehensive solution that addresses all these issues. This research proposes a comprehensive intelligence-based crowd management framework that employs anomaly rules to monitor, predict, and detect crowd accidents and help in providing quick response. The suggested crowd intelligence framework addresses all crowd management issues. The use case chosen for this framework is the management of crowds of pilgrims in Umrah Holy event. The proposed framework is then implemented and evaluated with respect to efficiency, scalability, interpretability, remediability, and the number of false positive, true positive, and false negative alerts. In addition, the suggested framework is compared with other recent related work in terms of supporting crowd management issues. The design of the proposed framework and implementation are then fine-tuned in light of the evaluation results. The results and findings of this research can be extended to manage crowds at any event.
Forecasting crowd congestion is a critical aspect of crowd management, particularly in dynamic and densely populated areas, such as urban centers, events, or pilgrimage sites. In this paper, we ...proposed the first crowd congestion forecasting framework for the pilgrimage of Umrah. We addressed the crowd congestion forecasting problem by clustering the crowd flow trajectory in Masjid Al-Haram (Great Mosque) in the city of Makkah into six zones. The framework consists of two main components: 1) Ensemble forecasting model that aims at forecasting the crowd density of Masjid Al-Haram and its six zones, and 2) decision making algorithm that aims at keeping the crowd density at an acceptable level, and recommends updating the crowd flows when the forecasted crowd density exceeds the crowd density threshold. We built the ensemble learning model in three phases. In the first phase, we selected and evaluated different learning base models, including ARIMA, Sequence to Sequence (Seq2Seq) learning, M-1D-CNN-LSTM, and DeepSTN. In the second phase, the best three models, which performed well in the first phase, are selected to build the stacked ensemble model. The latter is validated using the walk-forward technique in the third phase. To evaluate the framework, we built a crowd dataset based on two temporal properties: 1) hourly context and 2) daily context. We evaluated the three phases of the ensemble forecasting model. In the first phase, DeepSTN performs the best by achieving a Mean Absolute Error (MAE) of 0.281. The results also indicate that DeepSTN is the best fit for five zones, and one variant of Seq2Seq, named Seq2Seq2b is the best fit for one zone under Mean Square Error (MSE) and Root Mean Squared Error (RMSE). Under MAE, DeepSTN and Seq2Seq2b, each of which is the best choice for three zones. In the second phase, the stacked ensemble achieves a MAE of 0.257. In the third phase, the stacked ensemble model is validated using the walk forward technique, which allows to reduce the MAE to 0.253. Although this framework focuses on Umrah, it can be customized for other use cases that involve crowd congestion forecasting.
Organizations are required to implement an information security management system (ISMS) for making a central cybersecurity framework, reducing costs, treating risks, and so on. Several ISMS ...standards have been issued and implemented locally and internationally. In Saudi Arabia, the most widely implemented international ISMS is ISO/IEC 27001. Currently, the Saudi National Cybersecurity Authority (NCA) issued a local framework called Essential Cybersecurity Controls (NCA-ECC). Therefore, many ISO/IEC 27001 certified organizations in Saudi Arabia are trying to convert from ISO/IEC 27001 to NCA-ECC or comply with both frameworks. Nevertheless, cybersecurity experts need to know which cybersecurity controls are already implemented, based on the ISO/IEC 27001, and which are not. This paper first measures the extent to which certified ISO/IEC 27001 Saudi organizations comply with the NCA-ECC. Second, it presents a framework for complying with the required unimplemented or partially implemented NCA-ECC controls. The framework can also help organization to be in compliance with both frameworks, if required. Three ISO/IEC 27001-certified Saudi public universities are selected as samples. The data is collected by interviewing the cybersecurity officers in the selected universities. This research shows that certified ISO/IEC 27001 organizations are approximately 64% in compliance with the NCA-ECC. The presented framework can help any ISO/IEC 27001 certified Saudi organization convert from ISO/IEC 27001 to NCA-ECC in a quick and cost-effective manner by considering only NCA-ECC nonconformities.
Introduction: Internet of things (IoT) compose of million of devices connected together over the internet. IoT plays a vital role now a days and especially in future, the most of the monitoring and ...data collection. The data should be secure while collection and as well in the process of transferring till the destination whether Service Organization Control (SOC) or to cloud for storage. In this paper, a secure IoT based intelligent monitoring system is proposed. Methods: An intelligent IoT station that interacts via cellular connection to relay data to the cloud is constructed using the Waspmote platform. The algorithm is injected to automatically filter and only keep the new data for transfer to avoid redundancy. The advanced encryption standard (AES) 256-bit method is enabled for onboard data encryption and then the generated cipher text is transmitted. The encrypted data is then stored over the cloud to ensure privacy. Moreover, the mobile application (mApp) is developed to be installed on handheld devices for calling the secure data from the cloud, decrypting it, and displaying it as per user input, whether real-time or historical. Results and Discussion: The encryption algortihm helps in securing the proposed monitoring system from brute force, man in the middle, phishing, spoofing, and denial of service (DoS) attacks. The results of the real testbed experimentation demonstrate the complexity evaluation and reliability of IoT monitoring systems with end-to-end data security in terms of encryption algorithm delay and data rate, respectively.
Autonomous vehicles (AVs) offer a wide range of promising benefits by reducing traffic accidents, environmental pollution, traffic congestion and land usage etc. However, to reap the intended ...benefits of AVs, it is inevitable that this technology should be trusted and accepted by the public. The consumer's substantial trust upon AVs will lead to its widespread adoption in the real-life. It is well understood that the preservation of strong security and privacy features influence a consumer's trust on a product in a positive manner. In this paper, we introduce a novel concept of digital labels for AVs to increase consumers awareness and trust regarding the security level of their vehicle. We present an architecture called Cybersecurity Box (CSBox) that leverages digital labels to display and inform consumers and passengers about cybersecurity status of the AV in use. The introduction of cybersecurity digital labels on the dashboard of AVs would attempt to increase the trust level of consumers and passengers on this promising technology.
The Ad hoc pervasive computing provides an attractive vision for future computing and has a great influence on many fields that need to be smart with simple digital devices interacting and sharing ...services seamlessly and transparently. Healthcare is a key area that can benefit from smart digital spaces, especially extending services to out-of-hospital contexts. In this poster, we describe the design of a system, called Personal Smart Space (PSS), which provides an automated method for bootstrapping a personal space. Specifically, PSS will track a person’s health and handle variations that may indicate a risk. The PSS is comprised of several services; namely, discovery management, event, description, and presentation. This poster describes the implementation and verification of this PSS for diabetic patients, which is comprised of 4 devices, 5 services and a coordinator. The PSS utilizes the UPnP protocol and XML standards to describe the devices and services to provide more flexibility. The novelty of this PSS lies in how the coordinator provides an interface to components (GPS, Camera, Glucose sensor, and mobile communication devices) and integrates a notification system as well as finding a backup device in cases of faults in one of the PSS components.