Sensor infrastructures have become key enablers in collecting massive urban data. While representing an invaluable source of geographic information, high deployment costs of air quality stations relying on a chemical principle of operation leads to geographically imbalanced data. Typically, a minority of districts are equipped with such sensors or benefit from data collection campaigns, while others are data-poor. Moreover, the data available is highly heterogeneous, which adding on uncertainties. We present a methodology called ‘Smart Beestricts’ to improve the resolution of spatiotemporal data through Transfer Learning across districts of smart cities, based on: (i) aggregating spatiotemporal urban data into hexagonal grid representations, (ii) multi-variate clustering of the grid for discovering candidate regions for transfer, and (iii) transferring prediction models from data-rich sectors to data-poor ones. The transferred models are finally utilized to predict missing data across the city, thus improving spatiotemporal resolution. The methodology is validated in predicting missing air quality data in Madrid. The datasets generated are available through an open repository including meteorology, air pollution, and traffic data. Our methodology increased the spatial coverage of NO2 data from approximately 98 km2 to 253 km2, achieving coefficients of determination (R2) of up to 0.70 in the test regions.

Smart solutions increasingly involve the use of sensor data to represent the physical world in the digital world and apply intelligence to such representation. The main approach is a vertical end-to-end solution from sensors to intelligence and back to actuators. Recently, a new holistic approach, the so-called Digital Twin, has emerged. This goes beyond traditional smart solutions by replicating, with high-fidelity cross-domain aspects, a physical object into the digital world. The key differentiation is the inclusion of semantics information in the digital replica in a form of knowledge graph. Further, analytics continuously enrich Digital Twin’s information with predictions and insights. In this article, we adopt the Digital Twin approach for the creation of a digital replica of Espinardo’s campus at the University of Murcia (Spain). The starting point is the existing sensor network deployment and the infrastructure under development of Fog–Edge–Cloud computing based on a 5G private network. The smart campus Digital Twin is formed by the Digital Twins of 23 buildings for which different sets of data features have been thoroughly selected. We implement the concept of Digital Twin by merging sensor data with external open data sources, analytics models implemented, and information processed by these analytics. We report our experience showing the issues encountered handling the data and producing various analytics models for predicting energy consumption, building occupancy, room usage, solar energy, and anomaly detection. From our experience, we highlight some lessons learned and directions toward the full operational smart campus Digital Twin.

The widespread use of pervasive sensing technologies such as wireless sensors and street cameras allows the deployment of crowd estimation solutions in smart cities. However, existing Wi-Fi-based systems do not provide highly accurate crowd size estimation. Furthermore, these systems do not adapt to the dynamic changes in-the-wild, such as unexpected crowd gatherings. This paper presents a new adaptive machine learning system, called CountMeIn, to address the crowd estimation problem using polynomial regression and neural networks. The approach transfers the calibration task from cameras to machine learning after a short training with people counting from stereoscopic cameras, Wi-Fi probe packets, and temporal features. After the training, CountMeIn calibrates Wi-Fi using the trained model and maintains high accuracy for a longer duration without cameras. We test the approach in our pilot study in Gold Coast, Australia, for about five months. CountMeIn achieves 44% and 72% error reductions in minutely and hourly crowd estimations compared to the state-of-the-art methods.

Ontology matching enables harmonizing heterogeneous data models. Existing ontology matching approaches include machine learning. In particular, recent works leverage weak supervision (WS) through programmatic labeling to avoid the intensive hand-labeling for large ontologies. Programmatic labeling relies on heuristics and rules, called Labeling Functions (LFs), that generate noisy and incomplete labels. However, to cover a reasonable portion of the dataset, programmatic labeling might require a significant number of LFs that might be time expensive and not always straightforward to program.

This paper proposes Group-In, a wireless scanning system to detect static or mobile people groups in indoor or outdoor environments. Group-In collects only wireless traces from the Bluetooth-enabled mobile devices for group inference. The key problem addressed in this work is to detect not only static groups but also moving groups with a multi-phased approach based only noisy wireless Received Signal Strength Indicator (RSSIs) observed by multiple wireless scanners without localization support. We propose new centralized and decentralized schemes to process the sparse and noisy wireless data, and leverage graph-based clustering techniques for group detection from short-term and long-term aspects. Group-In provides two outcomes: 1) group detection in short time intervals such as two minutes and 2) long-term linkages such as a month. To verify the performance, we conduct two experimental studies. One consists of 27 controlled scenarios in the lab environments. The other is a real-world scenario where we place Bluetooth scanners in an office environment, and employees carry beacons for more than one month. Both the controlled and real-world experiments result in high accuracy group detection in short time intervals and sampling liberties in terms of the Jaccard index and pairwise similarity coefficient.

Data usage control is of utmost importance for federated data analytics across multiple business domains. However, the existing data usage control approaches are limited due to their complexity and inefficiency. This paper proposes an intent-oriented data usage control system for federated data analytics, called IntentKeeper. The system allows users to specify intents for data usage policies and services easily. Thus, it reduces the data sharing complexity for data providers and consumers. Moreover, IntentKeeper enforces preventive and proactive data usage control for better security and efficiency through joint decisions based on policy enforcement and service orchestration. The use case validations for the automotive industry scenario show that IntentKeeper significantly reduces the complexity of policy specification (up to 75% for moderately complex scenarios) compared to the state-of-the-art flow-based approach. Lastly, the experimental results show that the IntentKeeper system provides sufficiently short response times (less than 40ms) with minimal overhead (less than 10ms).

This paper focuses on the application of wireless sensor networks (WSNs) with unmanned aerial vehicle (UAV) for animal tracking problem. The goal of this application is to monitor the target animals in large wild areas without any attachment devices. The WSN includes clusters of sensor nodes and a single UAV that acts as a mobile sink and visits the clusters. We propose a model predictive control (MPC) method that is used to guide the UAV in planning its path. We first build a prediction model to learn the animal appearance patterns from the sensed historical data. Then, based on the real-time predicted animal distributions, we introduce a path planning approach for the UAV that reduces message delay by maximizing the collected rewards. The experimental results show that our approach outperforms the greedy and traveling salesmen problem-based path planning heuristics in terms of collected value of information. We also discuss the results of other performance metrics involving message delay and percentage of events collected.

Crowd mobility has been paid attention for the Internet-of-things (IoT) applications. This paper addresses the crowd estimation problem and builds an IoT service to share the crowd estimation results across different systems. The crowd estimation problem is to approximate the crowd size in a targeted area using the observed information (e.g., Wi-Fi data). This paper exploits Wi-Fi probe request packets ("Wi-Fi probes" for short) broadcasted by mobile devices to solve this problem. However, using only Wi-Fi probes to estimate the crowd size may result in inaccurate results due to various environmental uncertainties which may lead to crowd overestimation or underestimation. Moreover, the ground-truth is unavailable because the coverage of Wi-Fi signals is time-varying and invisible. This paper introduces auxiliary sensors, stereoscopic cameras, to collect the near ground-truth at a specified calibration choke point. Two calibration algorithms are proposed to solve the crowd estimation problem. The key idea is to calibrate the Wi-Fi-only crowd estimation based on the correlations between the two types of data modalities. Then, to share the calibrated results across systems required by different stakeholders, our system is integrated with the FIWARE-based IoT platform. To verify the proposed system, we have launched an indoor pilot study in the Wellington Railway Station and an outdoor pilot study in the Christchurch Re:START Mall in New Zealand. The large-scale pilot studies show that stereoscopic cameras can reach minimum accuracy of 85% and high precision detection for providing the near ground-truth. The proposed calibration algorithms reduce estimation errors by 43.68% on average compared to the Wi-Fi-only approach.

Smart city infrastructure is forming a large scale Internet of Things (IoT) system with widely deployed IoT devices, such as sensors and actuators that generate a huge volume of data. Given this large scale and geo-distributed nature of such IoT systems, fog computing has been considered as an affordable and sustainable computing paradigm to enable smart city IoT services. However, it is still a major challenge for developers to program their services to leverage benefits of fog computing. Developers have to figure out many details, such as how to dynamically configure and manage data processing tasks over cloud and edges and how to optimize task allocation for minimal latency and bandwidth consumption. In addition, most of the existing fog computing frameworks either lack service programming models or define a programming model only based on their own private data model and interfaces; therefore, as a smart city platform, they are quite limited in terms of openness and interoperability. To tackle these problems, we propose a standard-based approach to design and implement a new fog computing-based framework, namelyFogFlow, for IoT smart city platforms. FogFlow’s programming model allows IoT service developers to program elastic IoT services easily over cloud and edges. Moreover, it supports standard interfaces to share and reuse contextual data across services. To showcase how smart city use cases can be realized with FogFlow, we describe three use cases and implement an example application for anomaly detection of energy consumption in smart cities. We also analyze FogFlow’s performance based on microbenchmarking results for message propagation latency, throughput, and scalability.

This paper proposes a novel approach for detecting groups of people that walk “together” (group mobility) as well as the people who walk “alone” (individual movements) using wireless signals. We exploit multiple wireless sniffers to pervasively collect human mobility data from people with mobile devices and identify similarities and the group mobility based on the wireless fingerprints. We propose a method which initially converts the wireless packets collected by the sniffers into people's wireless fingerprints. The method then determines group mobility by finding the statuses of people at certain times (dynamic/static) and the space correlation of dynamic people. To evaluate the feasibility of our approach, we conduct real world experiments by collecting data from 10 participants carrying Bluetooth Low Energy (BLE) beacons in an office environment for a two-week period. The proposed approach captures space correlation with 95% and group mobility with 79% accuracies on average. With the proposed approach we successfully 1) detect the groups and individual movements and 2) generate social networks based on the group mobility characteristics.

Crowd behaviour analytics focuses on behavioural characteristics of groups of people instead of individuals' activities. This work considers human queuing behaviour which is a specific crowd behavior of groups. We design a plug-and-play system solution to the queue detection problem based on Wi-Fi/Bluetooth Low Energy (BLE) received signal strength indicators (RSSIs) captured by multiple signal sniffers. The goal of this work is to determine if a device is in the queue based on only RSSIs. The key idea is to extract features not only from individual device's data but also mobility similarity between data from multiple devices and mobility correlation observed by multiple sniffers. Thus, we propose single-device feature extraction, cross-device feature extraction, and cross-sniffer feature extraction for model training and classification. We systematically conduct experiments with simulated queue movements to study the detection accuracy. Finally, we compare our signal-based approach against camera-based face detection approach in a real-world social event with a real human queue. The experimental results indicate that our approach can reach minimum accuracy of 77% and it significantly outperforms the camera-based face detection because people block each other's visibility whereas wireless signals can be detected without blocking.

In this paper, we propose an infrastructure-independent opportunistic mobile social networking strategy for efficient message broadcasting in campus environments. Specifically, we focus on the application scenario of university campuses. In our model, the students' smart-phones forward messages to each other. The messages are created spontaneously as independent events in various places of the campus. The events can be either urgent security alerts or private announcements to the students currently on the campus. Our proposed state- based campus routing (SCR) protocol is based on the idle and active states of the students in indoor and outdoor places. The proposed model is analyzed through extensive network simulations using mobility datasets collected from students on University of Milano and University of Cambridge campuses. The opportunistic network model and the SCR protocol are compared with epidemic, epidemic with TTS (Times To Send), PROPHET, and random routing protocols. The message delivery performance of SCR is close to Epidemic and PROPHET while SCR reduces the amount of message transmissions.

In times of natural or man-made disasters, missions such as safe evacuation of people from the disaster areas have critical importance. Considering large areas with limited vehicle use such as theme parks and state fairs, search and rescue of the pedestrians is a major challenge. Moreover, as an effect of disaster, damages to infrastructure may disrupt the use of Internet services. Therefore, alternative communication systems with disaster resilience are necessary for evacuation planning and guidance. In this paper, we develop a method for tracking pedestrians using smart-phones during disasters. In the network model, sensors store and carry messages to a limited number of mobile sinks. We propose physical force based (PF), grid allocation based (GA) and road allocation based (RA) approaches for sink placement and mobility. The proposed approaches are analyzed through extensive network simulations using real theme park maps and a theme park pedestrian mobility model for disaster scenarios.

In this paper, we focus on an application of wireless sensor networks (WSNs) with unmanned aerial vehicle (UAV). The aim of the application is to detect the locations of endangered species in large-scale wildlife areas or monitor movement of animals without any attachment devices. We first define the mathematical model of the animal monitoring problem in terms of the value of information (VoI) and rewards. We design a network model including clusters of sensor nodes and a single UAV that acts as a mobile sink and visits the clusters. We propose a path planning approach based on a Markov decision process (MDP) model that maximizes the VoI while reducing message delays. We used real-world movement dataset of zebras. Simulation results show that our approach outperforms greedy and random heuristics as well as the path planning based on the solution of the traveling salesman problem.

Realistic human mobility modeling is critical for accurate performance evaluation of mobile wireless networks. Movements of visitors in theme parks affect the performance of systems which are designed for various purposes including urban sensing and crowd management. Previously proposed human mobility models are mostly generic while some of them focus on daily movements of people in urban areas. Theme parks, however, have unique characteristics in terms of very limited use of vehicles, crowd's social behavior, and attractions. Human mobility is strongly tied to the locations of attractions and is synchronized with major entertainment events. Hence, realistic human mobility models must be developed with the specific scenario in mind. In this paper, we present a novel model for human mobility in theme parks. In our model, the nondeterminism of movement decisions of visitors is combined with deterministic behavior of attractions in a theme park. The attractions are categorized as rides, restaurants, and live shows. The time spent at these attractions are computed using queueing-theoretic models. The realism of the model is evaluated through extensive simulations and compared with the mobility models SLAW, RWP and the GPS traces of theme park visitors. The results show that our proposed model provides a better match to the real-world data compared to the existing models.

In this paper, we propose a scenario-specific human mobility model (TP-D) in theme parks. We focus on the disaster scenarios which have significant differences compared to the ordinary mobility behavior of the theme park visitors. The main goal of the theme park operation in disaster scenarios is the evacuation of the visitors from the disaster areas. We first model theme park as a combination of roads, obstacles, lands, and disaster events. We use real theme park maps for generating the theme park models. We incorporate the macro and micro mobility behaviors of the visitors in theme park models. We use the social force concept to model the impact of social interactions on the micro mobility of the visitors. Macro mobility decisions are based on the local knowledge of the visitors, the waypoints, and the disaster events. We analyze and compare the results of the simulation of our model with simulations of currently used models and real-world GPS traces of visitor movement.

Theme parks are large crowded areas with unique characteristics in terms of movement behavior of visitors, attractions in different locations and walking paths connecting the attractions. Wireless sensor networks (WSNs) with mobile sinks can be used for various purposes including security and emergency issues as major challenges in such environments. Modeling of human mobility in theme parks allows us to consider scenario-specific applications of WSNs in these entertainment areas for event coverage purposes. In this paper, we propose a WSN model with mobile sinks and provide a novel approach to cover the events occurring in the environment. Furthermore, we propose new strategies for mobile sink positioning and event handling decision problems. We evaluate the benefits of our approach through extensive simulations using two sophisticated human mobility models for visitor movement.

Advances in unmanned aerial vehicle (UAV) technology and wireless sensor and actor networks (WSAN) made it possible to equip small UAVs with sensors and deploy aerial sensor and actor networks. Aerial sensor networks enable high quality observation of events while reducing the number of requirements. Positioning of UAVs with actor nodes is critical in these systems for effective data collection. In this paper we propose an actor positioning strategy for aerial WSANs considering the scenario of toxic plume observation after a volcanic eruption. The positioning algorithm utilizes the Valence Shell Electron Pair Repulsion (VSEPR) theory of chemistry, which is based on the correlation between molecular geometry and the number of atoms in a molecule. The limitations of the basic VSEPR theory are eliminated by extending the approach for multiple central data collectors. The simulations show that the proposed system provides high connectivity and coverage for the aerial sensor network.

Realistic modeling of the movement of people in an environment is critical for evaluating the performance of mobile wireless systems such as urban sensing or mobile sensor networks. Existing human movement models are either fully synthetic or rely on traces of actual human movement. There are many situations where we cannot perform an accurate simulation without taking into account what the people are actually doing. For instance, in theme parks, the movement of people is strongly tied to the locations of the attractions and is synchronized with major external events. For these situations, we need to develop scenario specific models. In this paper, we present a model of the movement of visitors in a theme park. The nondeterministic behavior of the human walking pattern is combined with the deterministic behavior of attractions in the theme park. The attractions are divided into groups of rides, restaurants and live shows. The time spent by visitors at different attractions is calculated using specialized queuing-theoretic models. We compare the realism of the model by comparing its simulations to the statistics of the theme parks and to real-world GPS traces of visitor movement. We found that our model provides a better match to the real-world data compared to current state-of-the-art movement models.