The code performance of industrial robots is typically analyzed through CPU metrics, which overlook the physical impact of code on robot behavior. This study introduces a novel framework for assessing robot program performance from an embodiment perspective by analyzing the robot’s electrical power profile. Our approach diverges from conventional CPU-based evaluations and instead leverages a suite of normalized metrics, namely, the energy utilization coefficient (fU), the energy conversion metric (fC), and the reliability coefficient (fR), to capture how efficiently and reliably energy is used during task execution. Complementing these metrics, the established robot wear metric (α) provides further insight into long-term reliability. Our approach is demonstrated through an experimental case study in machine tending, comparing four programs with diverse strategies using a UR5e robot. The proposed metrics directly compare and categorize different robot programs, regardless of the specific task, by linking code performance to its physical manifestation through power consumption patterns. Our results reveal the strengths and weaknesses of each strategy, offering actionable insights for optimizing robot programming practices. Enhancing energy efficiency and reliability through this embodiment-centric approach not only improves individual robot performance but also supports broader industrial objectives such as sustainable manufacturing and cost reduction.

Given a setup with external cameras and a mobile manipulator with an eye-in-hand camera, we address theproblem of computing a sequence of base poses and grasp choices that allows for clearing objects from atable while minimizing the overall execution time. The first step in our approach is to construct a worldmodel, which is generated by an anchoring process, using information from the external cameras. Next, wedeveloped a planning module which – based on the contents of the world model - is able to create a plausibleplan for reaching base positions and suitable grasp choices keeping execution time minimal. Comparing ourapproach to two baseline methods shows that the average execution cost of plans computed by our approach is40% lower than the naive baseline and 33% lower than the heuristic-based baseline. Furthermore, we integrateour approach in a demonstrator, undertaking the full complexity of the problem.

In many applications, a mobile manipulator robot is required to grasp a set of objects distributed in space. This may not be feasible from a single base pose and the robot must plan the sequence of base poses for grasping all objects, minimizing the total navigation and grasping time. This is a Combinatorial Optimization problem that can be solved using exact methods, which provide optimal solutions but are computationally expensive, or approximate methods, which offer computationally efficient but sub-optimal solutions. Recent studies have shown that learning-based methods can solve Combinatorial Optimization problems, providing near-optimal and computationally efficient solutions.In this work, we present BaSeNet - a learning-based approach to plan the sequence of base poses for the robot to grasp all the objects in the scene. We propose a Reinforcement Learning based solution that learns the base poses for grasping individual objects and the sequence in which the objects should be grasped to minimize the total navigation and grasping costs using Layered Learning. As the problem has a varying number of states and actions, we represent states and actions as a graph and use Graph Neural Networks for learning. We show that the proposed method can produce comparable solutions to exact and approximate methods with significantly less computation time. The code and Reinforcement Learning environments will be made available on the project webpage*.

Improving robot deployment is a central step towards speeding up robot-based automation in manufacturing. A main challenge in robot deployment is how to best place the robot within the workcell. To tackle this challenge, we combine two knowledge sources: robotic knowledge of the system and workcell context awareness of the user, and intersect them with an Augmented Reality interface. RobotGraffiti is a unique tool that empowers the user in robot deployment tasks. One simply takes a 3D scan of the workcell with their mobile device, adds contextual data points that otherwise would be difficult to infer from the system, and receives a robot base position that satisfies the automation task. The proposed approach is an alternative to expensive and time-consuming digital twins, with a fast and easy-to-use tool that focuses on selected workcell features needed to run the placement optimization algorithm. The main contributions of this paper are the novel user interface for robot base placement data collection and a study comparing the traditional offline simulation with our proposed method. We showcase the method with a robot base placement solution and obtain up to 16 times reduction in time.

Capturing real-world 3D spaces as point clouds is efficient and descriptive, but it comes with sensor errors and lacks object parametrization. These limitations render point clouds unsuitable for various real-world applications, such as robot programming, without extensive post-processing (e.g., outlier removal, semantic segmentation). On the other hand, CAD modeling provides high-quality, parametric representations of 3D space with embedded semantic data, but requires manual component creation that is time-consuming and costly. To address these challenges, we propose a novel solution that combines the strengths of both approaches. Our method for 3D workcell sketching from point clouds allows users to refine raw point clouds using an Augmented Reality (AR) interface that leverages their knowledge and the real-world 3D environment. By utilizing a toolbox and an AR-enabled pointing device, users can enhance point cloud accuracy based on the device’s position in 3D space. We validate our approach by comparing it with ground truth models, demonstrating that it achieves a mean error within 1cm — significant improvement over standard LiDAR scanner apps.

Industrial robots have been widely used in diverse activities and industries for more than six decades. However, these robots were initially designed to operate autonomously without human interaction. The emergence of a new generation of manipulators, namely lightweight robots such as collaborative robots, has revolutionized the industry by enabling robots to work alongside humans. In this paper, we qualitatively compare the energy consumption of these two types of robots. First, we propose experimental setups to investigate how specific variables, such as standstill position, motion commands, velocity and acceleration limits, time scaling, and joint temperatures, influence the energy consumption of a Cobot, namely, UR3e. Then, UR3e results are compared to IR experimental results which are mainly based on existing literature. The comparison reveals that the energy signature graph, which depicts the energy consumption versus execution time, differs between these two robots. Furthermore, industrial robots consume a considerably larger amount of mechanical energy compared to their electronic components’ energy, while UR3e consumes a higher proportion of energy in their electronic components. Energy optimization strategies for UR3e should focus on efficient electronic design, such as the distribution of computation tasks among system assets, rather than reducing energy consumption through motion planning.

Compliance with global guidelines for sustainable and responsible production in modern industry requires a comparative analysis of consumer devices' energy consumption (EC). This also holds true for the newly established generation of lightweight industrial robots (LIRs). To identify potential strategies for energy optimization, standardized benchmarking procedures are required. However, to the best of the authors' knowledge, there is currently no standardized method for benchmarking the EC of manipulators. In response to this need, we have developed a comprehensive benchmarking framework to evaluate the EC of various LIR designs, delving into the theoretical power consumption under both static and dynamic conditions. Our analysis has led to the proposal of seven proposed metrics—three static and four dynamic. The static metrics—controller consumption, joint electronics consumption, and mechanical brakes' consumption—evaluate the maintenance EC of the robot. Meanwhile, we suggest three dynamic metrics that gauge the system's energy efficiency during motion, with or without payload. We extend this metrics selection by introducing the cost of transportation map for manipulators. For each of the metrics, we suggest a standardized measurement procedure based on state-of-the-art norms and literature. The metric set and experimental procedures are demonstrated using five manipulators (UR3e, UR5e, FR3, M0609, Gen3). Among the results, we can see interesting trends for future optimization of the electronic components and their architecture, e.g., reducing the robot's EC by decentralizing computation via low-consumption onboard controllers for basic tasks and external servers for complex ones.

The concept of a Digital Twin has proved its worth over the past two decades, establishing itself as a cornerstone of contemporary industry. Augmented Reality, an emerging technology, enhances the interaction between humans and machines, including computers and robots. Today, numerous examples exist of the union of these two technologies to create real-augmented digital-twin models of collaborative robots. However, these models often lack data on motor currents and power consumption. In this study, we propose a real-augmented digital-twin model that accurately estimates energy consumption. This additional energy information equips the tool for various applications such as robot optimization, commissioning, and troubleshooting. We employ our real-augmented digital-twin model to test methods for reducing Cobots’ energy consumption, using the tool to demonstrate and train Cobot practitioners on these techniques’ applications. The model is also useful for anomaly detection (troubleshooting) when the robot’s consumption statistically deviates from the ideal model. Moreover, the model can anticipate the robot’s power consumption during the commissioning phase, prior to its installation. Through a series of experiments and a practical demonstration at a robot fair for practitioners, we illustrate the benefits and training capabilities of our approach.

Interactive computer systems’ designers emphasize the importance of considering humans, their emotions, and behaviors as first-class entities. Emotions are integral parts of human nature, and ignoring that can lead the interactive systems to failure, low quality, or discomfort. User interfaces (UIs) are increasingly becoming adaptive to users’ various characteristics, intending to improve users’ satisfaction, performance, and decisions. However, the previous approaches proposed for supervising such adaptations are not effectively adopted in real-life problems. This paper proposes the novel approach to adapting UIs to users’ emotions using Model-Free Reinforcement Learning (MFRL). The approach aims to maximize applying the essential adaptations and minimize the unnecessary ones towards users’ task completion and satisfaction. We chose emergency evacuation training as a suitable evaluation domain since people experience intense emotions in potential danger. We performed experiments with a mobile application we developed that acts as a recommender system in emergency training. By taking contextual input of the users’ basic emotions from face recognition, the application intelligently adapts its UI to quickly lead people to safe areas while arousing target emotions. The research includes literature analysis, surveys, and further adopting an iterative process in implementation and experimentation. The evaluation process confirms the efficiency and effectiveness of the MFRL in iterations, as well as compared to other possible UI adaptation techniques, i.e., rule-based and sequential adaptation.

Emotions are integral to human nature, and their existence, duration, and evolution could lead to specific behaviors. If emotions and behaviors are ignored in the design of socio-technical systems, they will fail or cause discomfort. User interfaces (UIs) are elements of interactive systems able to trigger or moderate emotions. UIs are increasingly designed adaptive to users' various characteristics, intending to improve their satisfaction, performance, and decisions. However, previous adaptation supervising approaches are not effectively adopted in real life since they neglect the dynamic behaviors of humans or systems. This paper proposes Emoticontrol, a quality-driven approach to adapting UIs to users' emotions using Model-Free Reinforcement Learning (MFRL). The approach aims to maximize applying the essential adaptations and minimize the unnecessary ones towards users' enhanced quality of experience (QoE). The approach also considers improving the software quality of service (QoS) by designing software architecture alternatives. We chose emergency evacuation training as a suitable evaluation domain since people experience intense emotions in potential danger. We performed experiments with a mobile application we developed that acts as a recommender system in evacuation training. By taking contextual input of the users' basic emotions from face recognition, the application intelligently adapts its UI to quickly lead people to safe areas while keeping them emotionally controlled. We consider software performance a crucial QoS; thus, we adopt and test architectures that facilitate an acceptable level of performance. The evaluation process confirms the efficiency and effectiveness of the MFRL in iterations, as well as compared to other UI adaptation techniques.

The Internet of Behaviors (IoB) puts human behavior at the core of engineering intelligent connected systems. IoB links the digital world to human behavior to integrate human-driven design, development, and adaptation processes. This paper defines the novel IoB concept with a constructed model based on a collective effort interacting with software engineers, human-computer interaction scientists, social scientists, and cognitive science communities. The model for IoB is created based on an exploratory study that synthesizes state-of-the-art analysis and experts interviews. The architecture of a real industry 4.0 manufacturing infrastructure helps to explain the IoB model and its application. The conceptual model was used to successfully implement a socio-technical infrastructure for a crowd monitoring and queue management system for the Uffizi Galleries, Florence, Italy. The experiment, which started in the fall of 2016 and was operational in the fall of 2018, used a data-driven approach to feed the system with real-time sensory data. It also incorporated prediction models on visitors’ mobility behavior. The system’s main objective was to capture human behavior, model it, and build a mechanism that considers changes, adapts in real-time, and continuously learns from repetitive behaviors. In addition to the conceptual model and the real-life evaluation, this paper provides recommendations from experts and gives future directions for IoB to become a significant technological advancement in the coming years.

Human-Robot Interaction (HRI) for collaborative robots has not changed since the introduction of the first cobot. The main interface to communicate with the robot remains a wired display - teach pendant (TP). While attempts are made to make the programming experience better - more intuitive touch-screen displays, it generally remains the same. With the recent rapid development of Augmented Reality (AR), the HRI of the cobot could drastically change. This paper explores AR-based implementations in robotics and categorizes them based on the type of the used device, with the main focus on the least explored category - mobile AR. Furthermore, two experiments are conducted to determine the user’s experience in robot programming using TP with a mobile-based AR interface. For this reason, an AR application prototype is developed as a co-interface to a TP. The results of the experiments are presented: the first examines the user’s needs that are missing in current solutions, while the second one analyses the user’s experience in using the robot with the AR interface. The obtained results suggest that users could benefit from mobile-based AR solutions in the commissioning and troubleshooting phase of the lifetime of the robot. However, at the same time, this solution is not advanced and accurate enough (yet) to encourage users to switch to the new platform and abandon the classical TP, while programming the robot.

Estimating the number of people in rooms and zones within commercial buildings are gaining enormous attention for facilitating various domain applications. However, the deployment of state-of-art counting sensors such as camera technologies can be economically in-viable for individual rooms or zones in large commercial and public buildings. Such sensors are also known to be highly intrusive within building deployments. In this paper, we propose a multi-modal fusion method that leverages the accuracy of camera technologies for estimating building-level counts and the non-intrusive and scalability of wireless fidelity (WiFi) trajectory data to estimate room-level counts. This multi-modal fusion method disaggregates the obtained building-level counts by applying a series of data cleaning methods and a two-step probabilistic method. We evaluate the disaggregation method with datasets from a large teaching building, and we benchmark its performance with a state-of-art estimation algorithm and count estimates from raw WiFi trajectories. The obtained evaluation results highlight that the disaggregation algorithm outperforms other estimation methods by a minimum ratio of 35% for all room cases using the Normalized Root Mean Squared Error (NRMSE) metric.

Sensing accurately the number of occupants in the rooms of a building enables many important applications for smart building operation and energy management. A range of sensor technologies has been studied and applied to the problem. However, it is costly to achieve high accuracy by instrumenting all rooms in a building with dedicated occupant sensors. In this paper, we propose a new concept for estimating accurate room-level counts of occupants. The idea is to disaggregate accurate building-level counts via existing common sensors available at the room level. This solution is cost-effective as it scales to large buildings without requiring dedicated sensors in each room. We propose an algorithm named DCount that implements this concept. Our results document that DCount can provide room-level counts with a low normalized root mean squared error of 0.93. This is a major improvement compared to a state-of-the-art algorithm using common sensors and ventilation rate measurements resulting in a normalized root mean squared error of 1.54 on the same data set. Further more, we demonstrate how the results enable occupant-driven analysis of plug-load consumption which is one out of many applications using accurate room-level counts of occupants we hope to enable by proposing DCount.

In this poster, we present an occupancy count correction method - PreCount that corrects the count errors of camera sensing technologies in real-time. PreCount utilizes supervised machine learning approach to learn error patterns from previous corrections alongside some contextual factors that are responsible for the propagation of these errors. In our evaluation, we compare PreCount with state-of-art methods using the normalized root mean squared error metric (NRMSE) with datasets from four building cases. The obtained evaluation results using ground truth data indicates that PreCount can achieve an error reduction of 68% when compared to raw counts and state-of-art methods.

Cyber-physical systems have enabled the collection of massive amounts of data in an unprecedented level of spatial and temporal granularity. Publishing these data can prosper big data research, which, in turn, helps improve overall system efficiency and resiliency. The main challenge in data publishing is to ensure the usefulness of published data while providing necessary privacy protection. In our previous work (Jia et al. 2017a), we presented a privacy-preserving data publishing framework (referred to as PAD hereinafter), which can guarantee k -anonymity while achieving better data utility than traditional anonymization techniques. PAD learns the information of interest to data users or features from their interactions with the data publishing system and then customizes data publishing processes to the intended use of data. However, our previous work is only applicable to the case where the desired features are linear in the original data record. In this article, we extend PAD to nonlinear features. Our experiments demonstrate that for various data-driven applications, PAD can achieve enhanced utility while remaining highly resilient to privacy threats.

The cooperative, invisible non-clinical work of hospital orderlies is often overlooked. It consists foremost of transferring patients between hospital departments. As the overall efficiency of the hospital is highly dependent on the coordination of the work of orderlies, this study investigates the coordination changes in orderlies' work practices in connection to the implementation of a workflow application at the hospital. By applying a mixed methods approach (both qualitative and quantitative studies), this paper calls for attention to the changes in orderlies' coordination activities while moving from a manual and centralized form to a semi-automatic and decentralized approach after the introduction of the workflow application. We highlight a set of cross-boundary (spatial and organizational) information-sharing breakdowns and the challenges of orderlies in maintaining local and global coordination. We also present design recommendations for future design of coordination tools to support orderlies' work practices.

Being aware of activities of co-workers is a basic and vital mechanism for efficient work in highly distributed work settings. Thus, automatic recognition of the task phases the mobile workers are currently (or have been) in has many applications, e.g., efficient coordination of tasks by visualizing co-workers' task progress, automatic notifications based on context awareness, and record filing of task statuses and completions. This paper presents methods to sense and detect highly mobile workers' tasks phases in large building complexes. Large building complexes restrict the technologies available for sensing and recognizing the activities and task phases the workers currently perform as such technologies have to be easily deployable and maintainable at a large scale. The methods presented in this paper consist of features that utilize data from sensing systems which are common in large-scale indoor work environments, namely from a WiFi infrastructure providing coarse grained indoor positioning, from inertial sensors in the workers' mobile phones, and from a task management system yielding information about the scheduled tasks' start and end locations. The methods presented have low requirements on the accuracy of the indoor positioning, and thus come with low deployment and maintenance effort in real-world settings. We evaluated the proposed methods in a large hospital complex, where the highly mobile workers were recruited among the non-clinical workforce. The evaluation is based on manually labelled real-world data collected over 4 days of regular work life of the mobile workforce. The collected data yields 83 tasks in total involving 8 different orderlies from a major university hospital with a building area of 160, 000 m2. The results show that the proposed methods can distinguish accurately between the four most common task phases present in the orderlies' work routines, achieving Fi-Scores of 89.2%.

Industrial buildings are responsible for a large share of the worldwide electricity consumption. Disaggregated information about electricity consumption enables decision- making and feedback tools to reduce and optimize the electricity consumption. In industrial settings, electrical load comes from a variety of equipment and machinery which can be awkward and expensive to monitor individually. We believe that Non-Intrusive Load Monitoring (NILM) can ease the burden of such a monitoring infrastructure. This hypothesis has been evaluated by collecting a rich data set from more than forty sensors measuring power consumption for six months at an industrial cold store. Their electrical equipments includes compressors, industrial fans, evaporators etc. which by earlier work have been hypothesised as too difficult to detect by NILM algorithms. This paper provides a detailed study of how industrial equipment and machinery challenge NILM algorithms. We consider how NILM can be used with different levels of sub- metering for providing breakdowns of the power consumption in an industrial setting. Our results show that changing the level of sub- metering increased the test accuracy(F1 score) with a third from 0.4 to 0.6. We introduce FHMM with day specific training, meaning having a model for each day in the week. The FHMM with day specific training reduced by half the mean normalized error from 0.7 to 0.3. These results thereby open up for the use of NILM in an industrial setting.

The widespread presence of motion sensors on users' personal mobile devices has spawned a growing research interest in human activity recognition (HAR). However, when deployed at a large-scale, e.g., on multiple devices, the performance of a HAR system is often significantly lower than in reported research results. This is due to variations in training and test device hardware and their operating system characteristics among others. In this paper, we systematically investigate sensor-, device- and workload-specific heterogeneities using 36 smartphones and smartwatches, consisting of 13 different device models from four manufacturers. Furthermore, we conduct experiments with nine users and investigate popular feature representation and classification techniques in HAR research. Our results indicate that on-device sensor and sensor handling heterogeneities impair HAR performances significantly. Moreover, the impairments vary significantly across devices and depends on the type of recognition technique used. We systematically evaluate the effect of mobile sensing heterogeneities on HAR and propose a novel clustering-based mitigation technique suitable for large-scale deployment of HAR, where heterogeneity of devices and their usage scenarios are intrinsic.

Many mobile location-aware applications require the sampling of trajectory data accurately over an extended period of time. However, continuous trajectory tracking poses new challenges to the overall battery life of the device, and thus novel energy-efficient sensor management strategies are necessary for improving the lifetime of such applications. Additionally, such sensor management strategies are required to provide a high and application-adjustable level of robustness regardless of the user’s transportation mode. In this article, we extend and further analyze the sensor management strategies of the EnTracked$_{T}$system that intelligently determines when to sample different on-device sensors (e.g., accelerometer, compass and GPS) for trajectory tracking. Specifically, we propose the concept of situational bounding to improve and parameterize the robustness of sensor management strategies for trajectory tracking. We demonstrate the effectiveness of our proposed approach by performing a series of emulation experiments on real world data sets collected from different modes of transportation (including walking, running, biking and commuting by car) on mobile devices from two different platforms. Thorough experimental analyses indicate that our system can save significant amounts of battery power compared to the state-of-the-art position tracking systems, while simultaneously maintaining robustness and accuracy bounds as required by diverse location-aware applications.

Accurate information about how people commonly travel in a given large-scale building environment and which routes they take for given start and destination points is essential for applications such as indoor navigation, route prediction, and mobile work planning and logistics. In this paper, we propose methods for detecting commonly used routes by robust aggregation, clustering, and merging of indoor position traces. The developed methods overcome three specific challenges for detecting commonly used routes in an indoor setting based on position data: i) a high ratio between path-density and positioning-accuracy, ii) a flat path hierarchy, and iii) providing cost-effective scalability. Through an evaluation based on data collected by staff members at a hospital covering more than 10 hectare over three floors, we show that the proposed methods detect routes that are representative of the commonly used routes between locations. These methods are sufficiently efficient to provide common routes based on real-time data from thousands of devices simultaneously. Furthermore, we show that the methods operate robustly even on basis of noisy and coarse-grained position estimates as provided by large-scale deployable indoor Wi-Fi positioning systems, and with no prior information on building layout.

Existing methods for transportation mode detection (TMD) using mobile sensing make it generally possible to distinguish between walking, cycling, and motorized transport. However, our means of transport evolve and we develop radically new ways of transporting ourselves, thus new TMD sub-classification methods are needed to distinguish these new transport forms. As we transition from fossil-fueled cars to electric vehicles, switch to bikes with electric motors, ride in hybrid buses, or do city sightseeing on Segways, new challenges arise in distinguishing these from a mobile sensing perspective. Distinguishing electric vehicles (EVs) from fossil-fueled vehicles (FFVs) is a challenge, where traditional methods based on features such as GPS speed, or statistics on raw accelerometer data, are insufficient. In this paper, we present methods for distinguishing EVs from FFVs using smartphones with built-in inertial sensors, by reliably identifying idle-engine motor vibrations through features built on frequency analysis. We provide an extensive analysis of the challenges involved in making the EV/FFV distinction, as well as practical tools based on the methods. This includes analyzing the measurable similarities and differences between EVs and FFVs, and developing methods of reliably separating them. The presented tools implement the methods as classifiers built using machine learning. The analysis of our experiments shows that we can achieve an accuracy of 89-95% distinguishing EVs from FFVs, even with on-body phones.

The ability to accurately estimate indoor travel times is crucial for enabling improvements within application areas such as indoor navigation, logistics for mobile workers, and facility management. In this paper, we study the challenges inherent in indoor travel time estimation, and we propose th

The optimization of logistics in large building complexes with many resources, such as hospitals, require realistic facility management and planning. Current planning practices rely foremost on manual observations or coarse unverified assumptions and therefore do not properly scale or provide realistic data to inform facility planning. In this paper, we propose analysis methods to extract knowledge from large sets of network collected WiFi traces to better inform facility management and planning in large building complexes. The analysis methods, which build on a rich set of temporal and spatial features, include methods for noise removal, e.g., labeling of beyond building-perimeter devices, and methods for quantification of area densities and flows, e.g., building enter and exit events, and for classifying the behavior of people, e.g., into user roles such as visitor, hospitalized or employee. Spatio-temporal visualization tools built on top of these methods enable planners to inspect and explore extracted information to inform facility-planning activities. To evaluate the methods, we present results for a large hospital complex covering more than 10 hectares. The evaluation is based on WiFi traces collected in the hospital's WiFi infrastructure over two weeks observing around 18000 different devices recording more than a billion individual WiFi measurements. For the presented analysis methods we present quantitative performance results, e.g., demonstrating over 95% accuracy for correct noise removal of beyond building perimeter devices. We furthermore present detailed statistics from our analysis regarding people's presence, movement and roles, and example types of visualizations that both highlight their potential as inspection tools for planners and provide interesting insights into the test-bed hospital.

The vast availability of mobile phones with built-in movement and location sensors enables the collection of detailed information about human movement even indoors. As mobility is a key element of many processes and activities, an interesting class of information to extract is movement patterns that quantify how humans move, interact and group. In this paper we propose methods for detecting two common pedestrian movement patterns, namely individual following relations and group leadership. The proposed methods for identifying following patterns employ machine learning on features derived using similarity analysis on time-lagged sequences of WiFi measurements containing either raw signal strength values or derived locations. To detect leadership we combine the individual following relations into directed graphs and detect leadership within groups by graph link analysis. Methods for detecting these movement patterns open up new possibilities in–amongst others–computational social science, reality mining, marketing research and location-based gaming. We provide evaluation results that show error rates down to 7%, improving over state-of-the-art methods with up to eleven percentage points for following patterns and up to twenty percentage points for leadership patterns. Furthermore, we provide an analysis of the computational efficiency of the proposed methods and present visualizations for the analysis of detected patterns. Our methods are, contrary to state of the art, also applicable in challenging indoor environments, e.g., multi-story buildings. This implies that even quite small samples allow us to detect information such as how events and campaigns in multi-story shopping malls may trigger following in small groups, or which group members typically take the lead when triggered by e.g. commercials, or how rescue or police forces act during training exercises.

The vast availability of mobile phones with built-in movement and location sensors enable the collection of detailed information about human movement even indoors. As mobility is a key element of many processes and activities, an interesting class of information to extract is movement patterns that quantify how humans move, interact and group. In this paper we propose methods for detecting two common pedestrian movement patterns, namely individual following relations and group leadership. The proposed methods for identifying following patterns employ machine learning on features derived using similarity analysis on time lagged sequences of WiFi measurements containing either raw signal strength values or derived locations. To detect leadership we combine the individual following relations into directed graphs and detect leadership within groups by graph link analysis. Methods for detecting these movement patterns open up new possibilities in — amongst others — computational social science, reality mining, marketing research and location-based gaming. We provide evaluation results that show error rates down to 7%, improving over state of the art methods with up to eleven percentage points for following patterns and up to twenty percentage points for leadership patterns. Our method is, contrary to state of the art, also applicable in challenging indoor environments, e.g., multi-story buildings. This implies that even quite small samples allow us to detect information such as how events and campaigns in multistory shopping malls may trigger following in small groups, or which group members typically take the lead when triggered by e.g. commercials, or how rescue or police forces act during training exercises.

Previous work on the recognition of human movement patterns has mainly focused on movements of individuals. This paper addresses the joint identification of the indoor movement of multiple persons forming a cohesive whole - specifically a flock - with clustering approaches operating on features derived from multiple sensor modalities of modern smartphones. Automatic detection of flocks has several important applications, including evacuation management and socially aware computing. The novelty of this paper is, firstly, to use data fusion techniques to combine several sensor modalities (WiFi, accelerometer and compass) to improve recognition accuracy over previous unimodal approaches. Secondly, improve the recognition of flocks using hierarchical clustering. We use a dataset comprising 16 subjects forming one to four flocks walking in a building on single and multiple floors. With the best settings, we achieve a F-score accuracy of up to 87 percent an improvement of up to twelve percent points over existing approaches.

Fingerprinting-based localization methods relying on WiFi and GSM information provide sufficient localization accuracy for many mobile phone applications. Most of the existing approaches require a training set consisting of geo-referenced fingerprints to build a reference database. We propose a collaborative, semi-supervised WiFi+GSM fingerprinting method where only a small fraction of all fingerprints needs to be geo-referenced. Our approach enables indexing of areas in the absence of GPS reception as often found in urban spaces and indoors without manual labeling of fingerprints. The method takes advantage of the characteristic that the similarity of two fingerprints correlates to the distance between their corresponding location. By applying multidimensional scaling, a topology estimation is generated and with the help of a small set of geo-referenced fingerprints anchored to physical locations. An evaluation with an urban-scale data set shows that we can locate a mobile device with a median error of 30m. While normally all fingerprints of the training set need to be geo-referenced, with our method, only 8% require geo-referencing. We further show that the localization error decreases as new fingerprints are added and converges to an accuracy comparable to related work.

No abstract available.

In Pervasive Computing research, substantial work has been directed towards radio-based sensing of human movement patterns. This research has, however, mainly been focused on movements of individuals. This paper addresses the joint identification of the movement indoors of multiple persons forming a cohesive whole - specifically flocks - with clustering approaches operating on three different feature sets derived from WiFi signals which are comparatively analysed. Automatic detection of flocks has several important applications, including social and psychological sensing and emergency research studies. We use a dataset comprising 16 subjects forming one to four flocks walking in a building on single and multiple floors. For the detection of flocks we achieved an average F-measure accuracy of up to 85 percent. We report on the advantages and drawbacks of the three different types of feature sets considering their suitability for use “in the wild” or in well-defined environments.

Today, power consumption is a main limitation for mobile phones. To minimize the power consumption of popular and traditionally power-hungry location-based services requires knowledge of how individual phone features consume power, so that those features can be utilized intelligently for optimal power savings while at the same time maintaining good quality of service. This paper proposes an unsupervised API-level method for power profiling mobile phones based on genetic algorithms. The method enables accurate profiling of the power consumption of devices and thereby provides the information needed by methods that aim to minimize the power consumption of location-based and other services.

Emergent location-aware applications often require tracking trajectories of mobile devices over a long period of time. To be useful, the tracking has to be energy-efficient to avoid having a major impact on the battery life of the mobile device. Furthermore, when trajectory information needs to be sent to a remote server, on-device simplification of the trajectories is needed to reduce the amount of data transmission. While there has recently been a lot of work on energy-efficient position tracking, the energy-efficient tracking of trajectories has not been addressed in previous work. In this paper we propose a novel on-device sensor management strategy and a set of trajectory updating protocols which intelligently determine when to sample different sensors (accelerometer, compass and GPS) and when data should be simplified and sent to a remote server. The system is configurable with regards to accuracy requirements and provides a unified framework for both position and trajectory tracking. We demonstrate the effectiveness of our approach by emulation experiments on real world data sets collected from different modes of transportation (walking, running, biking and commuting by car) as well as by validating with a real-world deployment. The results demonstrate that our approach is able to provide considerable savings in the battery consumption compared to a state-of-the-art position tracking system while at the same time maintaining the accuracy of the resulting trajectory, i.e., support of specific accuracy requirements and different types of applications can be ensured.

An important feature of a modern mobile device is that it can position itself. Not only for use on the device but also for remote applications that require tracking of the device. To be useful, such position tracking has to be energy-efficient to avoid having a major impact on the battery life of the mobile device. Furthermore, tracking has to robustly deliver position updates when faced with changing conditions such as delays due to positioning and communication, and changing positioning accuracy.

Using 802.11 concurrently for communications and positioning is problematic, especially if location-based services (e.g., indoor navigation) are concurrently executed with real-time applications (e.g., VoIP, video conferencing). Periodical scanning for measuring the signal strength interrupts the data flow. Reducing the scan frequency is no option because it hurts the position accuracy. For this reason, we need an adaptive technique to mitigate this problem.

Differences in signal strength among wireless network cards, phones and tags are a fundamental problem for location fingerprinting. Current solutions require manual and error-prone calibration for each new client to address this problem. This paper proposes hyperbolic location fingerprinting, which records fingerprints as signal-strength ratios between pairs of base stations instead of absolute signal-strength values. The proposed solution has been evaluated by extending two well-known location fingerprinting techniques to hyperbolic location fingerprinting. The extended techniques have been tested on ten-hour-long signal-strength traces collected with five different IEEE 802.11 network cards. The evaluation shows that the proposed solution solves the signal-strength difference problem without requiring extra manual calibration and provides a performance equal to that of existing manual solutions.