Kaikki aineistot
Lisää
Abstract Real-world data streams pose a unique challenge to the implementation of machine learning (ML) models and data analysis. A notable problem that has been introduced by the growth of Internet of Things (IoT) deployments across the smart city ecosystem is that the statistical properties of data streams can change over time, resulting in poor prediction performance and ineffective decisions. While concept drift detection methods aim to patch this problem, emerging communication and sensing technologies are generating a massive amount of data, requiring distributed environments to perform computation tasks across smart city administrative domains. In this article, we implement and test a number of state-of-the-art active concept drift detection algorithms for time series analysis within a distributed environment. We use real-world data streams and provide critical analysis of results retrieved. The challenges of implementing concept drift adaptation algorithms, along with their applications in smart cities, are also discussed.
Abstract Substantial ongoing research now uses smartphones as a research platform for various studies and interventions. With the aging population becoming a frequent focus of research, an increasing number of studies and projects attempt to develop technological interventions for the elderly population. The extent to which the elderly population (i.e., seniors) adopts and uses smartphones is not clear. Many studies acknowledge that today’s seniors are not particularly keen on using smartphones, but in the near future we can expect this trend to change.
Abstract Advances in technology equip traffic domain with instruments to gather and analyze data for safe and fuel efficient traveling. This article elaborates on the effects from taxi drivers route selection on fuel efficiency. We fuse real driving behavior data from taxi cabs, weather, and digital map information for fuel consumption prediction. That way we compare actually driven trips and their quickest and shortest counterparts for fuel efficiency.
Abstract Advances in technology equip traffic domain with instruments to gather and analyse data for safe and fuel-efficient traveling. In this article, we elaborate on the effects that taxi drivers’ route selection has on fuel efficiency. For this purpose, we fuse real driving behaviour data from taxi cabs, weather, digital map, and traffic situation information to gain understanding of how the routes are selected and what are the effects in terms of fuel-efficiency. Analysis of actually driven trips and their quickest and shortest counterparts is conducted to find out the fuel-efficiency consequences on route selection. The judgments are used for developing a fuel-consumption model, exploring further the route characteristics and external factors affecting fuel consumption.
Abstract A Smart Campus is a protected area within Smart Cities (Cities 2.0) where physical security of assets is vital for the continuous operation of the university. Concretely, there are specific mission-critical areas on the campus, which should be protected from unauthorized and malicious individuals. This paper describes a sustainable Smart Campus system architecture based on individuals’ spatiotemporal authentication fingerprint, generated by fusing data from mobile GPS devices and CCTV cameras infrastructure to detect malicious user behavior. The system incorporates unobtrusive monitoring to collect data from such individuals. While the system monitors for unauthorized access to restricted locations within the campus area, data are analyzed by an intrusion detection algorithm that sets off alarms and prompts physical evacuation. The efficiency of the proposed system is evaluated by gauging the prediction accuracy of alarms triggered and response time to the actual incidents on the campus. Results are promising for the adoption of the proposed system architecture by universities in Cities 2.0.
Abstract Researchers who analyse smartphone usage logs often make the assumption that users who lock and unlock their phone for brief periods of time (e.g., less than a minute) are continuing the same "session" of interaction. However, this assumption is not empirically validated, and in fact different studies apply different arbitrary thresholds in their analysis. To validate this assumption, we conducted a field study where we collected user-labelled activity data through ESM and sensor logging. Our results indicate that for the majority of instances where users return to their smartphone, i.e., unlock their device, they in fact begin a new session as opposed to continuing a previous one. Our findings suggest that the commonly used approach of ignoring brief standby periods is not reliable, but optimisation is possible. We therefore propose various metrics related to usage sessions and evaluate various machine learning approaches to classify gaps in usage.
Abstract Brain-computer interfaces (BCIs) can use data from non-invasive electroencephalogram (EEG) to transform different brain signals into binary code, often aiming to gain control utility of an end-effector (e.g mouse cursor). In the past several years, advances in wearable and immersive technologies have made it possible to integrate EEG with virtual reality (VR) headsets. These advances have enabled a new generation of user studies that help researchers improve understanding of various issues in current VR design (e.g. cybersickness and locomotion). The main challenge for integrating EEG-based BCIs into VR environments is to develop communication architectures that deliver robust, reliable and lossless data flows. Furthermore, user comfort and near real-time interactivity create additional challenges. We conducted two experiments in which a consumer-grade EEG headband (Muse2) was utilized to assess the feasibility of an EEG-based BCI in virtual environments. We first conducted a pilot experiment that consisted of a simple task of object re-scaling inside the VR space using focus values generated from the user’s EEG. The subsequent study experiment consisted of two groups (control and experimental) performing two tasks: telekinesis and teleportation. Our user research study shows the viability of EEG for real-time interactions in non-serious applications such as games. We further suggest that a simplified way of calculating the mean EEG values is adequate for this type of use. We, in addition, discuss the findings to help improve the design of user research studies that deploy similar EEGbased BCIs in VR environments.
Abstract This paper investigates the precision of rapid clock synchronisation for ubiquitous sensing services which consist of multiple smartphones. Specifically, we consider scenarios where multiple smartphones are used to sense physical phenomena, and subsequently the sensor data from multiple distributed devices is aggregated. We observe that the accumulated clock drift for smartphones can be more than 150ms per day in the worst case. We show that solutions using the public Network Time Protocol (NTP) can be noisy with errors up to 1800ms in one request. We describe a rapid clock synchronisation technique that reduces drift to 10ms on average (measured by linear regression) and achieves pair-wise synchronisation between smartphones with an average of 27ms (measured by accelerometer), following a Gaussian-like distribution. Our results provide a lower bound for rapid clock synchronisation as a guide when developing ubiquitous sensing services using multiple smartphones.
Abstract A Smart Campus is a miniature of a Smart City with a more demanding framework that enables learning, social interaction and creativity. To ensure a Smart Campus uninterruptible secure operation, a key requirement is that daily routines and activities are performed protected in an environment monitored unobtrusively by a robust surveillance system. The various components that compose such an environment, buildings, labs, public spaces, smart lighting, smart parking, or even smart traffic lights, require us to focus on surveillance systems, and recognize which detection activities to establish. In this paper, we perform a comparative assessment in the area of surveillance systems for Smart Campuses. A proposed taxonomy for IoT-enabled Smart Campus unfold five research dimensions: (1) physical infrastructure; (2) enabling technologies; (3) software analytics; (4) system security; and (5) research methodology. By applying this taxonomy and by adopting a weighted scoring model on the surveyed systems, we first present the state-of-the-art, and then we make a comparative assessment and classify the systems. We extract valuable conclusions and inferences from this classification, providing insights and directions towards required services offered by surveillance systems for Smart Campus.
Abstract IoT services hosted by low-power devices rely on the cloud infrastructure to propagate their ubiquitous presence over the Internet. A critical challenge for IoT systems is to ensure continuous provisioning of IoT services by overcoming network breakdowns, hardware failures, and energy constraints. To overcome these issues, we propose a cloud-based framework namely SensorClone, which relies on virtual devices to improve IoT resilience. A virtual device is the digital counterpart of a physical device that has learned to emulate its operations from sample data collected from the physical one. SensorClone exploits the collected data of low-power devices to create virtual devices in the cloud. SensorClone then can opportunistically migrate virtual devices from the cloud into other devices, potentially underutilized, with higher capabilities and closer to the edge of the network, e.g., smart devices. Through a real deployment of our SensorClone in the wild, we identify that virtual devices can be used for two purposes, 1) to reduce the energy consumption of physical devices by duty cycling their service provisioning between the physical device and the virtual representation hosted in the cloud, and 2) to scale IoT services at the edge of the network by harnessing temporal periods of underutilization of smart devices. To evaluate our framework, we present a use case of a virtual sensor created from an IoT service of temperature. From our results, we verify that it is possible to achieve unlimited availability up to 90% and substantial power efficiency under acceptable levels of quality of service. Our work makes contributions towards improving IoT scalability and resilience by using virtual devices.
Abstract We investigate the predictability of the next unlock event on smartphones, using machine learning and smartphone contextual data. In a 2-week field study with 27 participants, we demonstrate that it is possible to predict when the next unlock event will occur. Additionally, we show how our approach can improve accuracy and energy efficiency by solely relying on software-related contextual data. Based on our findings, smartphone applications and operating systems can improve their energy efficiency by utilising short-term predictions to minimise unnecessary executions, or launch computation-intensive tasks, such as OS updates, in the locked state. For instance, by inferring the next unlock event, smartphones can pre-emptively collect sensor data or prepare timely content to improve the user experience during the subsequent phone usage session.