This article proposes a proactive crowdsourced monitoring and sensing (PCMS) framework with the designed Smart iBeacon device to accurately recognize the activities of an equipped target, exclusively customize the recognition model of a specific target, and actively trigger cooperative tracking of nearby smartphones for an abnormal target based on Internet of Things (IoT) localization. According to our review of relevant research, PCMS is the first framework that provides the following features: 1) coarse-grained and fine-grained features can be extracted to accurately recognize target activities through densely connected convolutional networks with improvement design; 2) crowdsourced monitoring and sensing can be actively triggered for a target as the abnormal activity of the target is detected; and 3) deep learning model of target activity recognition can be exclusively customized for a specific target to improve the recognition accuracy based on the dedicated activity data of the target. An Android-based prototype with stationary iBeacon nodes and the Smart iBeacon is implemented to verify the feasibility and superiority of our PCMS framework. Experimental results show that our framework outperforms existing methods and can accurately recognize target activities for abnormal event detection and proactive crowdsourced tracking in a real-time manner.

In this article, we propose a mobile crowdsourced guiding and finding (MCGF) framework using smartphones to guide indoor people and find missing targets through Internet-of-Things (IoT) localization. The MCGF framework can cooperatively find lost/stolen targets equipped with mobile iBeacon nodes through participatory sensing networks formed by mobile users using smartphones in places with static iBeacon nodes. To precisely localize the missing target, fundamental target localization cases in distinct crowdsourced environments are formally classified and efficiently addressed to reduce the positioning errors with different numbers of smartphones detecting the missing target and different numbers of fixed iBeacon nodes nearby these target-detecting smartphones. According to our review of relevant research, this is the first solution that can provide the crowdsourced guiding path to a missing target with high localization accuracy for all densities of participating smartphones and iBeacon nodes. In particular, an Android-based prototype with static and mobile iBeacon nodes is implemented to verify the feasibility and superiority of our framework. Experimental results show that MCGF outperforms the existing methods and can significantly reduce the localization errors of mobile users and missing targets.

In this paper, we propose a time-efficient indoor navigation and evacuation (TINE) framework to minimize moving time for mobile users based on Internet of Things (IoT) technologies. In normal time, the proposed TINE framework can estimate the density of mobile users in each area and determine the moving speeds to pass through different areas. Based on the determined moving speed of each area, an indoor navigation path can be planned to provide the shortest moving time for a mobile user. In emergent time, TINE can accurately estimate the escaping time for groups of mobile users by jointly considering the length and moving time of passageways, the capacity of passageways/doors/exits, the present distribution and parallel moving of mobile users, and the possible congestion caused by other groups. Based on the estimated escaping time, TINE can efficiently alleviate the congestion of all passageways/exits and evenly distribute the evacuation load among exits to minimize the total escaping time. According to our review of relevant research, this is the first solution that can both provide the fastest navigation path to arbitrary target places and evacuate all groups of mobile users to safe places in the shortest escaping time. Simulation results show that TINE outperforms existing schemes and can significantly reduce the total walking and escaping times of indoor navigation and evacuation, respectively. In particular, an Android-based prototype with iBeacon IoT localization is implemented to verify the feasibility of our TINE system.

This paper proposes a smartphone-based indoor navigation and evacuation system, called EasyGO, to minimize moving time for mobile users through Internet of Things (IoT) technologies. In normal time, EasyGO can estimate the density of indoor people in each area and determine the moving speeds to pass through different areas. Based on the determined moving speed of each area, an indoor navigation path can be planned to provide the shortest moving time for EasyGO users. In emergent time, EasyGO can accurately estimate the escaping time for each EasyGO user by considering the capacity and length of passageways, the capacity of exits, and the current distribution and parallel moving of indoor people. Based on the estimated escaping time, EasyGO can evenly distribute the evacuation load among exits and alleviate the congestion of all passageways and exits to minimize the total escaping time. An Android-based prototype with iBeacon indoor localization is implemented to verify the feasibility of our EasyGO system.

This paper proposes a group-based emergency guiding system for mobile users using smartphones, called Go FAST, which can model the spatiotemporal mobility of indoor people. A dedicated path can be determined to provide the shortest evacuation time for each group of nearby people. The Go FAST system considers the corridor capacities and lengths, exit capacities, concurrent motion, distribution of indoor people, and dedicated escape path to accurately estimate the evacuation time for each group. Based on the estimated evacuation time, the evacuation load can evenly distributed among exits to minimize the total evacuation time. Go FAST can alleviate the congestion of all corridors and exits to reduce the total evacuation time as much as possible. An Android-based prototype with iBeacon indoor localization is implemented to verify the feasibility of our Go FAST system. Simulation results show that Go FAST outperforms existing schemes and can achieve the shortest evacuation time for group-based emergency guiding.