Pekka Siirtola

• PhD
• PostDoc Position at University of Oulu

The migraine is a chronic, incapacitating neurovascular disorder, characterized by attacks of severe headache and autonomic nervous system dysfunction. Among the working age population, the costs of migraine are 111 billion euros in Europe alone. The early detection of migraine attacks would reduce these costs, as it would shorten the migraine atta...

This article studies how to detect and explain concept drift. Human activity recognition is used as a case study together with a online batch learning situation where the quality of the labels used in the model updating process starts to decrease. Drift detection is based on identifying a set of features having the largest relevance difference betw...

In this article, regression and classification models are compared for stress detection. Both personal and user-independent models are experimented. The article is based on publicly open dataset called AffectiveROAD, which contains data gathered using Empatica E4 sensor and unlike most of the other stress detection datasets, it contains continuous...

Purpose This study applied machine learning (ML) and explainable artificial intelligence (XAI) to predict changes in HbA1c levels, a critical biomarker for monitoring glycemic control, within 12 months of initiating a new antidiabetic drug in patients diagnosed with type 2 diabetes. It also aimed to identify the predictors associated with these cha...

IntroductionProgress and innovation in artificial intelligence (AI)-based healthcare interventions continue to develop rapidly. However, there are limitations in the published health economic evaluations (HEEs) of AI interventions, including limited reporting on characteristics and development of algorithms. We developed an extension to the existin...

Orphan diseases, exemplified by T-cell prolymphocytic leukemia, present inherent challenges due to limited data availability and complexities in effective care. This study delves into harnessing the potential of machine learning to enhance care strategies for orphan diseases, specifically focusing on allogeneic hematopoietic cell transplantation (a...

Objectives Economic evaluations (EEs) are commonly used by decision makers to understand the value of health interventions. The Consolidated Health Economic Evaluation Reporting Standards (CHEERS 2022) provide reporting guidelines for EEs. Healthcare systems will increasingly see new interventions that use artificial intelligence (AI) to perform th...

Orphan diseases, exemplified by T-cell prolymphocytic leukemia, present inherent challenges due to limited data availability and complexities in effective care. This study delves into harnessing the potential of machine learning to enhance care strategies for orphan diseases, specifically focusing on allogeneic hematopoietic cell transplantation (a...

Introduction: AI interventions for health care are on the rise. Decisions about coverage and reimbursement are often informed by Health Technology Assessment (HTA) bodies, who rely on Health Economic Evaluations (HEEs) to estimate the value for money (cost effectiveness) of interventions. Transparent reporting of HEEs ensures they can be used for d...

This study aims to predict emotions using biosignals collected via wrist-worn sensor and evaluate the performance of different prediction models. Two dimensions of emotions were considered: valence and arousal. The data collected by the sensor were used in conjunction with target values obtained from questionnaires. A variety of classification and...

Purpose To gain an understanding of the heterogeneous group of type 2 diabetes (T2D) patients, we aimed to identify patients with the homogenous long-term HbA1c trajectories and to predict the trajectory membership for each patient using explainable machine learning methods and different clinical-, treatment-, and socio-economic-related predictors....

Clinical data analysis could lead to breakthroughs. However, clinical data contain sensitive information about participants that could be utilized for unethical activities, such as blackmailing, identity theft, mass surveillance, or social engineering. Data anonymization is a standard step during data collection, before sharing, to overcome the ris...

The aim of this paper is to identify the barriers that are specifically relevant to the use of Artificial Intelligence (AI)-based evidence in Central and Eastern European (CEE) Health Technology Assessment (HTA) systems. The study relied on two main parallel sources to identify barriers to use AI methodologies in HTA in CEE, including a scoping lit...

Digital twin (DT) emerges as a key concept of the Industry 4.0 paradigm and beyond. However, the current literature lacks focus on humans and human activities as a part of complex system DTs. Acknowledging human aspects in DTs can enhance work performance, well-being, motivation and personal development of professionals. This study examines emergin...

This study introduces an ensemble-based personalized human activity recognition method relying on incremental learning, which is a method for continuous learning, that can not only learn from streaming data but also adapt to different contexts and changes in context. This adaptation is based on a novel weighting approach which gives bigger weight t...

Smartwatches have rapidly evolved towards capabilities to accurately capture physiological signals. As an appealing application, stress detection attracts many studies due to its potential benefits to human health. It is propitious to investigate the applicability of deep neural networks (DNN) to enhance human decision-making through physiological...

Analyzing clinical data comes with many challenges. Medical expertise combined with statistical and programming knowledge must go hand-in-hand when applying data mining methods on clinical datasets. This work aims at bridging the gap between clinical expertise and computer science knowledge by providing an application for clinical data analysis wit...

Analyzing clinical data comes with many challenges. Medical expertise combined with statistical and programming knowledge must go hand-in-hand when applying data mining methods on clinical datasets. This work aims at bridging the gap between clinical expertise and computer science knowledge by providing an application for clinical data analysis wit...

Most off-the-shelf wearable devices do not provide reliable synchronization interfaces, causing multi-device sensing and machine learning approaches, e.g. for activity recognition, still to suffer from inaccurate clock sources and unmatched time. Instead of using active online synchronization techniques, such as those based on bidirectional wireles...

This study presents incremental learning based methods to personalize human activity recognition models. Initially, a user-independent model is used in the recognition process. When a new user starts to use the human activity recognition application, personal streaming data can be gathered. Of course, this data does not have labels. However, there...

OpenHAR is a toolbox for Matlab to combine and unify 3D accelerometer data of ten publicly open data sets. This chapter introduces OpenHAR and provides initial experimental results based on it. Moreover, OpenHAR provides an easy access to these data sets by providing them in the same format, and in addition, units, measurement range, sampling rates...

The recognition of complex and subtle human behaviors from wearable sensors will enable next-generation human-oriented computing in scenarios of high societal value (e.g., dementia care). This will require large-scale human activity corpuses and much improved methods to recognize activities and the context in which they occur. This workshop deals w...

Stress detection is becoming a popular field in machine learning and this study focuses on recognizing stress using the sensors of commercially available smartwatches. In most of the previous studies, stress detection is based on partly or fully on electrodermal activity sensor (EDA). However, if the final aim of the study is to build a smartwatch...

Wearable sensors have become more commonly used in everyday basis and powerful in terms of computational capacity and sensing resources, including capability to collect data from different bio-signals. The data collected from everyday wearables offers huge opportunities to monitor people's everyday life without expensive laboratory measurements, in...

In this study, a novel method to obtain user-dependent human activity recognition models unobtrusively by exploiting the sensors of a smartphone is presented. The recognition consists of two models: sensor fusion-based user-independent model for data labeling and single sensor-based user-dependent model for final recognition. The functioning of the...

In this study, the aim is to personalize inertial sensor data-based human activity recognition models using incremental learning. At first, the recognition is based on user-independent model. However, when personal streaming data becomes available, the incremental learning-based recognition model can be updated, and therefore personalized, based on...

This work investigates how context should be taken into account when performing continuous authentication of a smartphone user based on touchscreen and accelerometer readings extracted from swipe gestures. The study is conducted on the publicly available HMOG dataset consisting of 100 study subjects performing pre-defined reading and navigation tas...

In this study, importance of user inputs is studied in the context of personalizing human activity recognition models using incremental learning. Inertial sensor data from three body positions are used, and the classification is based on Learn++ ensemble method. Three different approaches to update models are compared: non-supervised, semi-supervis...

In this study, importance of user inputs is studied in the context of personalizing human activity recognition models using incremental learning. Inertial sensor data from three body positions are used, and the classification is based on Learn++ ensemble method. Three different approaches to update models are compared: non-supervised, semi-supervis...

In the steel plate production process it is important to minimize the wastage piece produced when cutting a mother steel plate to the size ordered by a customer. In this study, we build classi?cation and regression models to recognize the steel plate side edge shape, if it is curved or not and the amount of curvature. This is done based on time ser...

Our article “Recognizing human activities user-independently on smartphones based on accelerometer data” was published in the International Journal of Interactive Multimedia and Artificial Intelligence (IJIMAI) in 2012. In 2018, it was selected as the most outstanding article published in the 10 years of IJIMAI life. To celebrate the 10th anniversa...

This study introduces OpenHAR, a free Matlab toolbox to combine and unify publicly open data sets. It provides an easy access to accelerometer signals of ten publicly open human activity data sets. Data sets are easy to access as OpenHAR provides all the data sets in the same format. In addition, units, measurement range and labels are unified, as...

The recognition of complex and subtle human behaviors from wearable sensors will enable next-generation human-oriented computing in scenarios of high societal value (e.g., dementia care). This will require large-scale human activity corpuses and much improved methods to recognize activities and the context in which they occur. This workshop deals w...

In this study, the aim is to personalize inertial sensor data-based human activity recognition models using incremental learning. At first, the recognition is based on user-independent model. However, when personal streaming data becomes available, the incremental learning-based recognition model can be updated, and therefore personalized, based on...

This work investigates how context should be taken into account when performing continuous authentication of a smartphone user based on touchscreen and accelerometer readings extracted from swipe gestures. The study is conducted on the publicly available HMOG dataset consisting of 100 study subjects performing pre-defined reading and navigation tas...

In this article, it is studied how well inertial sensor-based human activity recognition models work when training and testing data sets are collected in different environments. Comparison is done using publicly open human activity data sets. This article has four objectives. Firstly, survey about publicly available data sets is presented. Secondly...

Background: The majority of young people do not meet the recommendations on physical activity for health. New innovative ways to motivate young people to adopt a physically active lifestyle are needed. Objective: The study aimed to study the feasibility of an automated, gamified, tailored Web-based mobile service aimed at physical and social act...

The migraine is a chronic, incapacitating neurovascular disorder, characterized by attacks of severe headache and autonomic nervous system dysfunction, concerning 15% of people in developed countries. It is one of the most understated and incapacitating diseases in the world and costing yearly 111 Billion Euros in Europe only. In our study, we disc...

In this work, it was tested if a computer game and wearable sensors could be used to motivate young men to increase their everyday activity. The game itself was planned so that the possibility to play the game and success in it was dependent of how much activity the subject achieved during his everyday life. A pilot version of a computer game, call...

The activity recognition research has remained popular although the first steps were taken almost two decades ago. While the first ideas were more like a-proof-of-concept studies the area has become a fruitful soil to novel methods of machine learning, to adaptive modeling, signal fusion and several different types of application areas. Nevertheles...

Migraine is a poorly understood disease and it is estimated that 15% of people in Europe alone are affected by it. In this study skin electrodermal activity (EDA) signals of left and right wrists were collected from a migraine patient to see if the asymmetry associated with EDA signals will affect to migraine detection based on wearable sensors. In...

In this paper, a noise injection method to improve personal recognition models is presented. The idea of the method is to build more general recognition models for eHealth using a small original data set and by expanding the area covered by training data using noise injection. This way, it is possible to train models that are less vulnerable to cha...

In this article wearable sensors based human activity recognition is approached with a case where personal data collected has a high inner activity variety. With this kind of approach, the model adaptivity as well as update becomes more important issues for the activity recognition models. In authors' previous article it was shown that with this ki...

In this study, information from wearable sensors is used to recognize human activities. Commonly the approaches are based on accelerometer data while in this study the potential of electromyogram (EMG) signals in activity recognition is studied. The electromyogram data is used in two different scenarios: 1) recognition of completely new activities...

In this study, a novel method to obtain user-dependent human activity recognition models unobtrusively by using the sensors of a smartphone is presented. The recognition consists of two models: sensor fusion-based user-independent model for data labeling and single sensor-based user-dependent model for final recognition. The functioning of the pres...

In this study, a novel user-independent method to recognize activities accurately in situations where traditional accelerometer based classification contains a lot of uncertainty is presented. The method uses two recognition models: one using only accelerometer data and other based on sensor fusion. However, as a sensor fusion-based method is known...

Wearable sensors based activity recognition is a research area where mostly inertial measurement unit based information is used to recognize human activities. Commonly the approaches are based on accelerometer data while in this study the potential of electromyogram signals in activity recognition is studied. The actual research problem tackled is...

Inertial sensors are devices that measure movement, and therefore, when they are attached to a body, they can be used to measure human movements. In this thesis, data from these sensors are studied to recognize human activities user-independently. This is possible if the following two hypotheses are valid: firstly, as human movements are dissimilar...

Many governments and institutions have guidelines for health-enhancing physical activity. Additionally, according to recent studies, the amount of time spent on sitting is a highly important determinant of health and wellbeing. In fact, sedentary lifestyle can lead to many diseases and, what is more, it is even found to be associated with increased...

In this study, every day activities are recognized from data collected using smartphones accelerometer sensors. Offline experiments are made to show that the presented method is user- and body position-independent. In addition, it is shown that the features used in the classification are not dependent on the calibration of the phone. The recognitio...

Real-time human activity recognition on a mobile phone is presented in this article. Unlike in most other studies, not only the data were collected using the accelerometers of a smartphone, but also models were implemented to the phone and the whole classification process (preprocessing, feature extraction and classification) was done on the device...

Real-time human activity recognition on a mobile phone is pre-sented in this article. Unlike in most other studies, not only the data were collected using the accelerometers of a smartphone, but also models were implemeted to the phone and the whole classification process (preprocessing, feature extraction and classification) was done on the device...

In this study an approach to an imperceptible and reliable worker monitoring system for industrial assembly lines is presented. A single wrist-worn inertial measurement unit is attached to the active wrist of the worker and by using acceleration and angular speed information, the behavior of the worker is recognized. The recognition is done in two...

The classification accuracy of time series is highly dependent on the quality of used features. In this study, features of new type, called SAX (Symbolic Aggregate approXimation) similarity features, are presented. SAX similarity features are a combination of the traditional statistical number-based and the template-based classification. SAX simila...

Towards persuasive system for efficient use of water resource, we propose a method to detect "water waste" among water-related activities based on water sound analysis. We supposed two types of water-wastes: inter-activity water waste and intra-activity water waste. An evaluation with a variety of experimental conditions presents that the aggregate...

In this paper, water tap usage is examined based on water sound analysis. We focus on detecting "water waste" to make persuasion of water savings effective, where two types of water waste are defined: inter-activity water waste and intra- activity water waste. Based on a preliminary user survey, four types of basin-related activities are identified...

The study concentrates on tracking swimming exercises based on the data of 3D accelerometer and shows that human activities can be tracked accurately using low sampling rates. The tracking of swimming exercise is done in three phases: first the swimming style and turns are recognized, secondly the number of strokes are counted and thirdly the inten...

A novel method to classify long-term human activi- ties is presented in this study. The method consists of two parts: quick test and periodic classification. The quick test uses temporal information to improve recognition accuracy, while the periodic classification is based on the assumption that recognized activities are long-term. Periodic quick...

This study concentrated on real-time monitoring of a worker using wearable-sensor-based activity recognition. An inertial measurement unit was attached to both wrists of the worker and, by using acceleration and angle speed information, the activities performed by the worker were recognized. Online recognition was done using the sliding window meth...

This study presents a method for recognizing six predefined gestures using data collected with a wrist-worn tri-axial accelerometer. The aim of the study is to design a gesture recognition-based control system for a simple user interface. The recognition is done by matching the shapes that user's movements cause to acceleration signals to predefine...

As wearable sensors are becoming more common, their utilization in real-world applications is also becoming more attractive. In this study, a single wrist-worn inertial measurement unit was attached to the active wrist of a worker and acceleration and angular speed information was used to decide what activity the worker was performing at certain ti...

The mining of meaningful shapes of time series is done widely in order to find shapes that can be used, for example, in classification problems or in summarizing signals. Normally, shapes that summarize periodic signals have to be mined visually, and in order to find a shape of high quality, several tests haves to be made. This makes visual mining...

Automatic recognition of activities using time series data collected from exercise can facilitate development of applications that motivate people to exercise more frequently and actively. This article presents a method for recognizing nine different everyday sport activities, such as running, walking, aerobics and Nordic walking, using only two-di...

This paper introduces a novel algorithm for estimating energy expenditure during physical activity. The estimation is based on acceleration data measured from a wrist-worn accelerometer. Simultaneous measurements of acceleration and oxygen consumption using a biaxial accelerometer and a breath gas analyzer were made during four different activities...

This article presents a method for the calculating simi- larity of two trajectories. The method is especially design ed for a situation where the points of the trajectories are dis- tributed sparsely and at non-equidistant intervals. The pr o- posed method is based on giving different weights to differ- ent points: points that are close to each oth...

Graphical presentation of long time series signals is chal-lenging because the resolution of a computer screen in pix-els is usually smaller than the length of the signal in points. However, visualizing signals at a glance is highly impor-tant because analysing data in graphical form can be much more productive than it is in numerical or written fo...

Time series data is usually stored and processed in the form of discrete trajectories of multidimensional measurement points. In order to compare the measurements of a query trajectory to a set of stored trajectories, one needs to calc u- late similarity between two trajectories. In this paper an e f- ficient algorithm for calculating the similarit...