Using slisemap to interpret physical data.

Manifold visualisation techniques are commonly used to visualise high-dimensional datasets in physical sciences. In this paper, we apply a recently introduced manifold visualisation method, slisemap, on datasets from physics and chemistry. slisemap combines manifold visualisation with explainable artificial intelligence. Explainable artificial intelligence investigates the decision processes of black box machine learning models and complex simulators. With slisemap, we find an embedding such that data items with similar local explanations are grouped together. Hence, slisemap gives us an overview of the different behaviours of a black box model, where the patterns in the embedding reflect a target property. In this paper, we show how slisemap can be used and evaluated on physical data and that it is helpful in finding meaningful information on classification and regression models trained on these datasets.

Exploring the mammalian sensory space: co-operations and trade-offs among senses.

The evolution of a particular sensory organ is often discussed with no consideration of the roles played by other senses. Here, we treat mammalian vision, olfaction and hearing as an interconnected whole, a three-dimensional sensory space, evolving in response to ecological challenges. Until now, there has been no quantitative method for estimating how much a particular animal invests in its different senses. We propose an anatomical measure based on sensory organ sizes. Dimensions of functional importance are defined and measured, and normalized in relation to animal mass. For 119 taxonomically and ecologically diverse species, we can define the position of the species in a three-dimensional sensory space. Thus, we can ask questions related to possible trade-off vs. co-operation among senses. More generally, our method allows morphologists to identify sensory organ combinations that are characteristic of particular ecological niches. After normalization for animal size, we note that arboreal mammals tend to have larger eyes and smaller noses than terrestrial mammals. On the other hand, we observe a strong correlation between eyes and ears, indicating that co-operation between vision and hearing is a general mammalian feature. For some groups of mammals we note a correlation, and possible co-operation between olfaction and whiskers.

Visual Data Exploration as a Statistical Testing Procedure: Within-View and Between-View Multiple Comparisons.

A fundamental problem in visual data exploration concerns whether observed patterns are true or merely random noise. This problem is especially pertinent in visual analytics, where the user is presented with a barrage of patterns, without any guarantees of their statistical validity. Recently this problem has been formulated in terms of statistical testing and the multiple comparisons problem. In this paper, we identify two levels of multiple comparisons problems in visualization: the within-view and the between-view problem. We develop a statistical testing procedure for interactive data exploration that controls the family-wise error rate on both levels. The procedure enables the user to determine the compatibility of their assumptions about the data with visually observed patterns. We present use-cases where we visualize and evaluate patterns in real-world data.

Dental functional traits of mammals resolve productivity in terrestrial ecosystems past and present.

We have recently shown that rainfall, one of the main climatic determinants of terrestrial net primary productivity (NPP), can be robustly estimated from mean molar tooth crown height (hypsodonty) of mammalian herbivores. Here, we show that another functional trait of herbivore molar surfaces, longitudinal loph count, can be similarly used to extract reasonable estimates of rainfall but also of temperature, the other main climatic determinant of terrestrial NPP. Together, molar height and the number of longitudinal lophs explain 73 per cent of the global variation in terrestrial NPP today and resolve the main terrestrial biomes in bivariate space. We explain the functional interpretation of the relationships between dental function and climate variables in terms of long- and short-term demands. We also show how the spatially and temporally dense fossil record of terrestrial mammals can be used to investigate the relationship between biodiversity and productivity under changing climates in geological time. The placement of the fossil chronofaunas in biome space suggests that they most probably represent multiple palaeobiomes, at least some of which do not correspond directly to any biomes of today's world.

Finding statistically significant high accident counts in exploration of occupational accident data.

INTRODUCTION: Finnish companies are legally required to insure their employees against occupational accidents. Insurance companies are then required to submit information about occupational accidents to the Finnish Workers' Compensation Center (TVK), which then publishes occupational accident statistics in Finland together with Statistics Finland. Our objective is to detect silent signals, by which we mean patterns in the data such as increased occupational accident frequencies for which there is initially only weak evidence, making their detection challenging. Detecting such patterns as early as possible is important, since there is often a cost associated with both reacting and not reacting: not reacting when an increased accident frequency is noted may lead to further accidents that could have been prevented. METHOD: In this work we use methods that allow us to detect silent signals in data sets and apply these methods in the analysis of real-world data sets related to important societal questions such as occupational accidents (using the national occupational accidents database). RESULTS: The traditional approach to determining whether an effect is random is statistical significance testing. Here we formulate the described exploration workflow of contingency tables into a principled statistical testing framework that allows the user to query the significance of high accident frequencies. CONCLUSIONS: Our results show that we can use our iterative workflow to explore contingency tables and provide statistical guarantees for the observed frequencies. PRACTICAL APPLICATIONS: Our method is useful in finding useful information from contingency tables constructed from accident databases, with statistical guarantees, even when we do not have a clear a priori hypothesis to test.

Randomization algorithms for large sparse networks.

In many domains it is necessary to generate surrogate networks, e.g., for hypothesis testing of different properties of a network. Generating surrogate networks typically requires that different properties of the network are preserved, e.g., edges may not be added or deleted and edge weights may be restricted to certain intervals. In this paper we present an efficient property-preserving Markov chain Monte Carlo method termed CycleSampler for generating surrogate networks in which (1) edge weights are constrained to intervals and vertex strengths are preserved exactly, and (2) edge and vertex strengths are both constrained to intervals. These two types of constraints cover a wide variety of practical use cases. The method is applicable to both undirected and directed graphs. We empirically demonstrate the efficiency of the CycleSampler method on real-world data sets. We provide an implementation of CycleSampler in R, with parts implemented in C.

Biosignals reflect pair-dynamics in collaborative work: EDA and ECG study of pair-programming in a classroom environment.

Collaboration is a complex phenomenon, where intersubjective dynamics can greatly affect the productive outcome. Evaluation of collaboration is thus of great interest, and can potentially help achieve better outcomes and performance. However, quantitative measurement of collaboration is difficult, because much of the interaction occurs in the intersubjective space between collaborators. Manual observation and/or self-reports are subjective, laborious, and have a poor temporal resolution. The problem is compounded in natural settings where task-activity and response-compliance cannot be controlled. Physiological signals provide an objective mean to quantify intersubjective rapport (as synchrony), but require novel methods to support broad deployment outside the lab. We studied 28 student dyads during a self-directed classroom pair-programming exercise. Sympathetic and parasympathetic nervous system activation was measured during task performance using electrodermal activity and electrocardiography. Results suggest that (a) we can isolate cognitive processes (mental workload) from confounding environmental effects, and (b) electrodermal signals show role-specific but correlated affective response profiles. We demonstrate the potential for social physiological compliance to quantify pair-work in natural settings, with no experimental manipulation of participants required. Our objective approach has a high temporal resolution, is scalable, non-intrusive, and robust.

Seriation in paleontological data using markov chain Monte Carlo methods.

Given a collection of fossil sites with data about the taxa that occur in each site, the task in biochronology is to find good estimates for the ages or ordering of sites. We describe a full probabilistic model for fossil data. The parameters of the model are natural: the ordering of the sites, the origination and extinction times for each taxon, and the probabilities of different types of errors. We show that the posterior distributions of these parameters can be estimated reliably by using Markov chain Monte Carlo techniques. The posterior distributions of the model parameters can be used to answer many different questions about the data, including seriation (finding the best ordering of the sites) and outlier detection. We demonstrate the usefulness of the model and estimation method on synthetic data and on real data on large late Cenozoic mammals. As an example, for the sites with large number of occurrences of common genera, our methods give orderings, whose correlation with geochronologic ages is 0.95.

Probabilistic Approach to Robust Wearable Gaze Tracking.

This paper presents a method for computing the gaze point using camera data captured with a wearable gaze tracking device. The method utilizes a physical model of the human eye, advanced Bayesian computer vision algorithms, and Kalman filtering, resulting in high accuracy and low noise. Our C++ implementation can process camera streams with 30 frames per second in realtime. The performance of the system is validated in an exhaustive experimental setup with 19 participants, using a self-made device. Due to the used eye model and binocular cameras, the system is accurate for all distances and invariant to device movement. We also test our system against a best-in-class commercial device which is outperformed for spatial accuracy and precision. The software and hardware instructions as well as the experimental data are published as open source.

Cognitive Collaboration Found in Cardiac Physiology: Study in Classroom Environment.

It is known that periods of intense social interaction result in shared patterns in collaborators' physiological signals. However, applied quantitative research on collaboration is hindered due to scarcity of objective metrics of teamwork effectiveness. Indeed, especially in the domain of productive, ecologically-valid activity such as programming, there is a lack of evidence for the most effective, affordable and reliable measures of collaboration quality. In this study we investigate synchrony in physiological signals between collaborating computer science students performing pair-programming exercises in a class room environment. We recorded electrocardiography over the course of a 60 minute programming session, using lightweight physiological sensors. We employ correlation of heart-rate variability features to study social psychophysiological compliance of the collaborating students. We found evident physiological compliance in collaborating dyads' heart-rate variability signals. Furthermore, dyads' self-reported workload was associated with the physiological compliance. Our results show viability of a novel approach to field measurement using lightweight devices in an uncontrolled environment, and suggest that self-reported collaboration quality can be assessed via physiological signals.

Heart rate variability for evaluating vigilant attention in partial chronic sleep restriction.

STUDY OBJECTIVES: Examine the use of spectral heart rate variability (HRV) metrics in measuring sleepiness under chronic partial sleep restriction, and identify underlying relationships between HRV, Karolinska Sleepiness Scale ratings (KSS), and performance on the Psychomotor Vigilance Task (PVT). DESIGN: Controlled laboratory study. SETTING: Experimental laboratory of the Brain Work Research Centre of the Finnish Institute of Occupational Health, Helsinki, Finland. PARTICIPANTS: Twenty-three healthy young males (mean age ± SD = 23.77 ± 2.29). INTERVENTIONS: A sleep restriction group (N = 15) was subjected to chronic partial sleep restriction with 4 h sleep for 5 nights. A control group (N = 8) had 8 h sleep on all nights. MEASUREMENTS AND RESULTS: Based on a search over all HRV frequency bands in the range [0.00, 0.40] Hz, the band [0.01, 0.08] Hz showed the highest correlation for HRV-PVT (0.60, 95% confidence interval [0.49, 0.69]) and HRV-KSS (0.33, 95% confidence interval [0.16, 0.46]) for the sleep restriction group; no correlation was found for the control group. We studied the fraction of variance in PVT explained by HRV and a 3-component alertness model, containing circadian and homeostatic processes coupled with sleep inertia, respectively. HRV alone explained 33% of PVT variance. CONCLUSIONS: The findings suggest that HRV spectral power reflects vigilant attention in subjects exposed to partial chronic sleep restriction. CITATION: Henelius A, Sallinen M, Huotilainen M, Müller K, Virkkala J, Puolamäki K. Heart rate variability for evaluating vigilant attention in partial chronic sleep restriction.