Per Bækgaard

Valentino Servizi, Dan R. Persson, Francisco C. Pereira et al.

Intelligent Transportation Systems (ITS) underpin the concept of Mobility as a Service (MaaS), which requires universal and seamless users' access across multiple public and private transportation systems while allowing operators' proportional revenue sharing. Current user sensing technologies such as Walk-in/Walk-out (WIWO) and Check-in/Check-out (CICO) have limited scalability for large-scale deployments. These limitations prevent ITS from supporting analysis, optimization, calculation of revenue sharing, and control of MaaS comfort, safety, and efficiency. We focus on the concept of implicit Be-in/Be-out (BIBO) smartphone-sensing and classification. To close the gap and enhance smartphones towards MaaS, we developed a proprietary smartphone-sensing platform collecting contemporary Bluetooth Low Energy (BLE) signals from BLE devices installed on buses and Global Positioning System (GPS) locations of both buses and smartphones. To enable the training of a model based on GPS features against the BLE pseudo-label, we propose the Cause-Effect Multitask Wasserstein Autoencoder (CEMWA). CEMWA combines and extends several frameworks around Wasserstein autoencoders and neural networks. As a dimensionality reduction tool, CEMWA obtains an auto-validated representation of a latent space describing users' smartphones within the transport system. This representation allows BIBO clustering via DBSCAN. We perform an ablation study of CEMWA's alternative architectures and benchmark against the best available supervised methods. We analyze performance's sensitivity to label quality. Under the naïve assumption of accurate ground truth, XGBoost outperforms CEMWA. Although XGBoost and Random Forest prove to be tolerant to label noise, CEMWA is agnostic to label noise by design and provides the best performance with an 88\% F1 score.

Valentino Servizi., Dan R. Persson, Francisco C. Pereira et al.

Passenger flow allows the study of users' behavior through the public network and assists in designing new facilities and services. This flow is observed through interactions between passengers and infrastructure. For this task, Bluetooth technology and smartphones represent the ideal solution. The latter component allows users' identification, authentication, and billing, while the former allows short-range implicit interactions, device-to-device. To assess the potential of such a use case, we need to verify how robust Bluetooth signal and related machine learning (ML) classifiers are against the noise of realistic contexts. Therefore, we model binary passenger states with respect to a public vehicle, where one can either be-in or be-out (BIBO). The BIBO label identifies a fundamental building block of continuously-valued passenger flow. This paper describes the Human-Computer interaction experimental setting in a semi-controlled environment, which involves: two autonomous vehicles operating on two routes, serving three bus stops and eighteen users, as well as a proprietary smartphone-Bluetooth sensing platform. The resulting dataset includes multiple sensors' measurements of the same event and two ground-truth levels, the first being validation by participants, the second by three video-cameras surveilling buses and track. We performed a Monte-Carlo simulation of labels-flip to emulate human errors in the labeling process, as is known to happen in smartphone surveys; next we used such flipped labels for supervised training of ML classifiers. The impact of errors on model performance bias can be large. Results show ML tolerance to label flips caused by human or machine errors up to 30%.

Per Bækgaard, Michael Kai Petersen, Jakob Eg Larsen

Using Low Cost Portable Eye Tracking for Biometric Identification Or Verification: Eye tracking technologies have in recent years become available outside of specialised labs, and are starting to become integrated in tablets and virtual reality headsets. This offers new opportunities for use in common office- and home environments, such as for biometric recognition (identification or verification), alone or in combination with other technologies. This paper exposes two fundamentally different approaches that have been suggested, based on spatial and temporal signatures respectively. While deploying different stimulation paradigms for recording, it also proposes an alternative way to analyze spatial domain signatures using Fourier transformation. Empirical data recorded from two subjects over two weeks, three months apart, are found to support previous results. Further, variations and stability of some of the proposed signatures are analyzed over the extended timeframe and under slightly varying conditions.

Per Bækgaard, Michael Kai Petersen, Jakob Eg Larsen

Cognitive processes involved in both allocation of attention during decision making as well as surprise when making mistakes trigger release of the neurotransmitter norepinephrine, which has been shown to be correlated with an increase in pupil dilation, in turn reflecting raised levels of arousal. Extending earlier experiments based on the Attention Network Test (ANT), separating the neural components of alertness and spatial re-orientation from the attention involved in more demanding conflict resolution tasks, we demonstrate that these signatures of attention are so robust that they may be retrieved even when applying low cost eye tracking in an everyday mobile computing context. Furthermore we find that the reaction of surprise elicited when committing mistakes in a decision task, which in the neuroimaging EEG literature have been referred to as a negativity feedback error correction signal, may likewise be retrieved solely based on an increase in pupil dilation.

Per Bækgaard, Michael Kai Petersen, Jakob Eg Larsen

The emergence of mobile eye trackers embedded in next generation smartphones or VR displays will make it possible to trace not only what objects we look at but also the level of attention in a given situation. Exploring whether we can quantify the engagement of a user interacting with a laptop, we apply mobile eye tracking in an in-depth study over 2 weeks with nearly 10.000 observations to assess pupil size changes, related to attentional aspects of alertness, orientation and conflict resolution. Visually presenting conflicting cues and targets we hypothesize that it's feasible to measure the allocated effort when responding to confusing stimuli. Although such experiments are normally carried out in a lab, we are able to differentiate between sustained alertness and complex decision making even with low cost eye tracking "in the wild". From a quantified self perspective of individual behavioral adaptation, the correlations between the pupil size and the task dependent reaction time and error rates may longer term provide a foundation for modifying smartphone content and interaction to the users perceived level of attention.