| 1. |
- Ahmed, Mobyen Uddin, 1976-
(författare)
-
A Multimodal Approach for Clinical Diagnosis and Treatment
- 2011
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- A computer-aided Clinical Decision Support System (CDSS) for diagnosis and treatment often plays a vital role and brings essential benefits for clinicians. Such a CDSS could function as an expert for a less experienced clinician or as a second option/opinion of an experienced clinician to their decision making task. Nevertheless, it has been a real challenge to design and develop such a functional system where accuracy of the system performance is an important issue. This research work focuses on development of intelligent CDSS based on a multimodal approach for diagnosis, classification and treatment in medical domains i.e. stress and post-operative pain management domains. Several Artificial Intelligence (AI) techniques such as Case-Based Reasoning (CBR), textual Information Retrieval (IR), Rule-Based Reasoning (RBR), Fuzzy Logic and clustering approaches have been investigated in this thesis work. Patient’s data i.e. their stress and pain related information are collected from complex data sources for instance, finger temperature measurements through sensor signals, pain measurements using a Numerical Visual Analogue Scale (NVAS), patient’s information from text and multiple choice questionnaires. The proposed approach considers multimedia data management to be able to use them in CDSSs for both the domains. The functionalities and performance of the systems have been evaluated based on close collaboration with experts and clinicians of the domains. In stress management, 68 measurements from 46 subjects and 1572 patients’ cases out of ≈4000 in post-operative pain have been used to design, develop and validate the systems. In the stress management domain, besides the 68 measurement cases, three trainees and one senior clinician also have been involved in order to conduct the experimental work. The result from the evaluation shows that the system reaches a level of performance close to the expert and better than the senior and trainee clinicians. Thus, the proposed CDSS could be used as an expert for a less experienced clinician (i.e. trainee) or as a second option/opinion for an experienced clinician (i.e. senior) to their decision making process in stress management. In post-operative pain treatment, the CDSS retrieves and presents most similar cases (e.g. both rare and regular) with their outcomes to assist physicians. Moreover, an automatic approach is presented in order to identify rare cases and 18% of cases from the whole cases library i.e. 276 out of 1572 are identified as rare cases by the approach. Again, among the rare cases (i.e. 276), around 57.25% of the cases are classified as ‘unusually bad’ i.e. the average pain outcome value is greater or equal to 5 on the NVAS scale 0 to 10. Identification of rear cases is an important part of the PAIN OUT project and can be used to improve the quality of individual pain treatment.
|
|
| 2. |
- Barua, Shaibal, 1982-
(författare)
-
Multivariate Data Analytics to Identify Driver’s Sleepiness, Cognitive load, and Stress
- 2019
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Driving a vehicle in a dynamic traffic environment requires continuous adaptation of a complex manifold of physiological and cognitive activities. Impaired driving due to, for example, sleepiness, inattention, cognitive load or stress, affects one’s ability to adapt, predict and react to upcoming traffic events. In fact, human error has been found to be a contributing factor in more than 90% of traffic crashes. Unfortunately, there is no robust, objective ground truth for determining a driver’s state, and researchers often revert to using subjective self-rating scales when assessing level of sleepiness, cognitive load or stress. Thus, the development of better tools to understand, measure and monitor human behaviour across diverse scenarios and states is crucial. The main objective of this thesis is to develop objective measures of sleepiness, cognitive load and stress, which can later be used as research tools, either to benchmark unobtrusive sensor solutions or when investigating the influence of other factors on sleepiness, cognitive load, and stress.This thesis employs multivariate data analysis using machine learning to detect and classify different driver states based on physiological data. The reason for using rather intrusive sensor data, such as electroencephalography (EEG), electrooculography (EOG), electrocardiography (ECG), skin conductance, finger temperature, and respiration is that these methods can be used to analyse how the brain and body respond to internal and external changes, including those that do not generate overt behaviour. Moreover, the use of physiological data is expected to grow in importance when investigating human behaviour in partially automated vehicles, where active driving is replaced by passive supervision.Physiological data, especially the EEG is sensitive to motion artifacts and noise, and when recorded in naturalistic environments such as driving, artifacts are unavoidable. An automatic EEG artifact handling method ARTE (Automated aRTifacts handling in EEG) was therefore developed. When used as a pre-processing step in the classification of driver sleepiness, ARTE increased classification performance by 5%. ARTE is data-driven and does not rely on additional reference signals or manually defined thresholds, making it well suited for use in dynamic settings where unforeseen and rare artifacts are commonly encountered. In addition, several machine-learning algorithms have been developed for sleepiness, cognitive load, and stress classification. Regarding sleepiness classification, the best achieved accuracy was achieved using a Support Vector Machine (SVM) classifier. For multiclass, the obtained accuracy was 79% and for binary class it was 93%. A subject-dependent classification exhibited a 10% improvement in performance compared to the subject-independent classification, suggesting that much can be gained by using personalized classifiers. Moreover, by embedding contextual information, classification performance improves by approximately 5%. In regard to cognitive load classification, a 72% accuracy rate was achieved using a random forest classifier. Combining features from several data sources may improve performance, and indeed, we observed classification performance improvement by 10%-20% compared to using features from a single data source. To classify drivers’ stress, using the Case-based reasoning (CBR) and data fusion approach, the system achieved an 83.33% classification accuracy rate.This thesis work encourages the use of multivariate data for detecting and classifying driver states, including sleepiness, cognitive load, and stress. A univariate data source often presents challenges, since features from a single source or one just aspect of the feature are not entirely reliable; Therefore, multivariate information requires accurate driver state detection. Often, driver states are a subjective experience, in which other contextual data plays a vital role. Thus, the implication of incorporating contextual information in the classification scheme is presented in this thesis work. Although there are several commonalities, physiological signals are modulated differently in different driver states; Hence, multivariate data could help detect multiple driver states simultaneously – for example, cognitive load detection when a person is under the influence of different levels of stress.
|
|
| 3. |
- Idrisoglu, Alper
(författare)
-
Voice for Decision Support in Healthcare Applied to Chronic Obstructive Pulmonary Disease Classification : A Machine Learning Approach
- 2024
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Background: Advancements in machine learning (ML) techniques and voice technology offer the potential to harness voice as a new tool for developing decision-support tools in healthcare for the benefit of both healthcare providers and patients. Motivated by technological breakthroughs and the increasing integration of Artificial Intelligence (AI) and Machine Learning (ML) in healthcare, numerous studies aim to investigate the diagnostic potential of ML algorithms in the context of voice-affecting disorders. This thesis focuses on respiratory diseases such as Chronic Obstructive Pulmonary Disease (COPD) and explores the potential of a decision support tool that utilizes voice and ML. This exploration exemplifies the intricate relationship between voice and overall health through the lens of applied health technology (AHT. This interdisciplinary nature of research recognizes the need for accurate and efficient diagnostic tools.Objective: The objectives of this licentiate thesis are twofold. Firstly, a Systematic Literature Review (SLR) thoroughly investigates the current state of ML algorithms in detecting voice-affecting disorders, pinpointing existing gaps and suggesting directions for future research. Secondly, the study focuses on respiratory health, specifically COPD, employing ML techniques with a distinct emphasis on the vowel "A". The aim is to explore hidden information that could potentially be utilized for the binary classification of COPD vs no COPD. The creation of a new Swedish COPD voice classification dataset is anticipated to enhance the experimental and exploratory dimensions of the research.Methods: In order to have a holistic view of a research field, one of the commonly utilized methods is to scan and analyze the literature. Therefore, Paper I followed the methodology of an SLR where existing journal publications were scanned and synthesized to create a holistic view in the realm of ML techniques employed to experiment on voice-affecting disorders. Based on the results from the SLR, Paper II focused on the data collection and experimentation for the binary classification of COPD, which was one of the gaps identified in the first study. Three distinct ML algorithms were investigated on the collected datasets through voice features, which consisted of recordings collected through a mobile application from participants 18 years old and above, and the most utilized performance measures were computed for the best outcome. Results: The summary of findings from Paper I reveals the dominance of Support Vector Machine (SVM) classifiers in voice disorder research, with Parkinson's Disease and Alzheimer's Disease as the most studied disorders. Gaps in research include underrepresented disorders, limited datasets in terms of number of participants, and a lack of interest in longitudinal studies. Paper II demonstrates promising results in COPD classification using ML and a newly developed dataset, offering insights into potential decision support tools for COPD diagnosis.Conclusion: The studies covered in this dissertation provide a comprehensive literature summary of ML techniques used to support decision-making on voice-affecting disorders for clinical outcomes. The findings contribute to understanding the diagnostic potential of using ML on vocal features and highlight avenues for future research and technology development. Nonetheless, the experiment reveals the potential of employing voice as a digital biomarker for COPD diagnosis using ML.
|
|
| 4. |
- Islam, Mir Riyanul, Doctoral Student, 1991-
(författare)
-
Explainable Artificial Intelligence for Enhancing Transparency in Decision Support Systems
- 2024
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Artificial Intelligence (AI) is recognized as advanced technology that assist in decision-making processes with high accuracy and precision. However, many AI models are generally appraised as black boxes due to their reliance on complex inference mechanisms. The intricacies of how and why these AI models reach a decision are often not comprehensible to human users, resulting in concerns about the acceptability of their decisions. Previous studies have shown that the lack of associated explanation in a human-understandable form makes the decisions unacceptable to end-users. Here, the research domain of Explainable AI (XAI) provides a wide range of methods with the common theme of investigating how AI models reach to a decision or explain it. These explanation methods aim to enhance transparency in Decision Support Systems (DSS), particularly crucial in safety-critical domains like Road Safety (RS) and Air Traffic Flow Management (ATFM). Despite ongoing developments, DSSs are still in the evolving phase for safety-critical applications. Improved transparency, facilitated by XAI, emerges as a key enabler for making these systems operationally viable in real-world applications, addressing acceptability and trust issues. Besides, certification authorities are less likely to approve the systems for general use following the current mandate of Right to Explanation from the European Commission and similar directives from organisations across the world. This urge to permeate the prevailing systems with explanations paves the way for research studies on XAI concentric to DSSs.To this end, this thesis work primarily developed explainable models for the application domains of RS and ATFM. Particularly, explainable models are developed for assessing drivers' in-vehicle mental workload and driving behaviour through classification and regression tasks. In addition, a novel method is proposed for generating a hybrid feature set from vehicular and electroencephalography (EEG) signals using mutual information (MI). The use of this feature set is successfully demonstrated to reduce the efforts required for complex computations of EEG feature extraction. The concept of MI was further utilized in generating human-understandable explanations of mental workload classification. For the domain of ATFM, an explainable model for flight take-off time delay prediction from historical flight data is developed and presented in this thesis. The gained insights through the development and evaluation of the explainable applications for the two domains underscore the need for further research on the advancement of XAI methods.In this doctoral research, the explainable applications for the DSSs are developed with the additive feature attribution (AFA) methods, a class of XAI methods that are popular in current XAI research. Nevertheless, there are several sources from the literature that assert that feature attribution methods often yield inconsistent results that need plausible evaluation. However, the existing body of literature on evaluation techniques is still immature offering numerous suggested approaches without a standardized consensus on their optimal application in various scenarios. To address this issue, comprehensive evaluation criteria are also developed for AFA methods as the literature on XAI suggests. The proposed evaluation process considers the underlying characteristics of the data and utilizes the additive form of Case-based Reasoning, namely AddCBR. The AddCBR is proposed in this thesis and is demonstrated to complement the evaluation process as the baseline to compare the feature attributions produced by the AFA methods. Apart from generating an explanation with feature attribution, this thesis work also proposes the iXGB-interpretable XGBoost. iXGB generates decision rules and counterfactuals to support the output of an XGBoost model thus improving its interpretability. From the functional evaluation, iXGB demonstrates the potential to be used for interpreting arbitrary tree-ensemble methods.In essence, this doctoral thesis initially contributes to the development of ideally evaluated explainable models tailored for two distinct safety-critical domains. The aim is to augment transparency within the corresponding DSSs. Additionally, the thesis introduces novel methods for generating more comprehensible explanations in different forms, surpassing existing approaches. It also showcases a robust evaluation approach for XAI methods.
|
|
| 5. |
- Barua, Shaibal, 1982-
(författare)
-
Intelligent Driver Mental State Monitoring System Using Physiological Sensor Signals
- 2015
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Driving a vehicle involves a series of events, which are related to and evolve with the mental state (such as sleepiness, mental load, and stress) of the driv- er. These states are also identified as causal factors of critical situations that can lead to road accidents and vehicle crashes. These driver impairments need to be detected and predicted in order to reduce critical situations and road accidents. In the past years, physiological signals have become conven- tional measures in driver impairment research. Physiological signals have been applied in various studies to identify different levels of mental load, sleepiness, and stress during driving.This licentiate thesis work has investigated several artificial intelligence algorithms for developing an intelligent system to monitor driver mental state using physiological signals. The research aims to measure sleepiness and mental load using Electroencephalography (EEG). EEG signals, if pro- cessed correctly and efficiently, have potential to facilitate advanced moni- toring of sleepiness, mental load, fatigue, stress etc. However, EEG signals can be contaminated with unwanted signals, i.e., artifacts. These artifacts can lead to serious misinterpretation. Therefore, this work investigates EEG arti- fact handling methods and propose an automated approach for EEG artifact handling. Furthermore, this research has also investigated how several other physiological parameters (Heart Rate (HR) and Heart Rate Variability (HRV) from the Electrocardiogram (ECG), Respiration Rate, Finger Tem- perature (FT), and Skin Conductance (SC)) to quantify drivers’ stress. Dif- ferent signal processing methods have been investigated to extract features from these physiological signals. These features have been extracted in the time domain, in the frequency domain as well as in the joint time-frequency domain using wavelet analysis. Furthermore, data level signal fusion has been proposed using Multivariate Multiscale Entropy (MMSE) analysis by combining five physiological sensor signals. Primarily Case-Based Reason- ing (CBR) has been applied for drivers’ mental state classification, but other Artificial intelligence (AI) techniques such as Fuzzy Logic, Support Vector Machine (SVM) and Artificial Neural Network (ANN) have been investigat- ed as well.For drivers’ stress classification, using the CBR and MMSE approach, the system has achieved 83.33% classification accuracy compared to a human expert. Moreover, three classification algorithms i.e., CBR, an ANN, and a SVM were compared to classify drivers’ stress. The results show that CBR has achieved 80% and 86% accuracy to classify stress using finger tempera- ture and heart rate variability respectively, while ANN and SVM reached an accuracy of less than 80%.
|
|
| 6. |
- Aghanavesi, Somayeh, 1981-
(författare)
-
Sensor-based knowledge- and data-driven methods : A case of Parkinson’s disease motor symptoms quantification
- 2020
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The overall aim of this thesis was to develop and evaluate new knowledge- and data-driven methods for supporting treatment and providing information for better assessment of Parkinson’s disease (PD).PD is complex and progressive. There is a large amount of inter- and intravariability in motor symptoms of patients with PD (PwPD). The current evaluation of motor symptoms that are done at clinics by using clinical rating scales is limited and provides only part of the health status of PwPD. An accurate and clinically approved assessment of PD is required using frequent evaluation of symptoms.To investigate the problem areas, the thesis adopted the microdata analysis approach including the stages of data collection, data processing, data analysis, and data interpretation. Sensor systems including smartphone and tri-axial motion sensors were used to collect data from advanced PwPD experimenting with repeated tests during a day. The experiments were rated by clinical experts. The data from sensors and the clinical evaluations were processed and used in subsequent analysis.The first three papers in this thesis report the results from the investigation, verification, and development of knowledge- and data-driven methods for quantifying the dexterity in PD. The smartphone-based data collected from spiral drawing and alternate tapping tests were used for the analysis. The results from the development of a smartphone-based data-driven method can be used for measuring treatment-related changes in PwPD. Results from investigation and verification of an approximate entropy-based method showed good responsiveness and test-retest reliability indicating that this method is useful in measuring upper limb temporal irregularity.The next two papers, report the results from the investigation and development of motion sensor-based knowledge- and data-driven methods for quantification of the motor states in PD. The motion data were collected from experiments such as leg agility, walking, and rapid alternating movements of hands. High convergence validity resulted from using motion sensors during leg agility tests. The results of the fusion of sensor data gathered during multiple motor tests were promising and led to valid, reliable and responsive objective measures of PD motor symptoms.Results in the last paper investigating the feasibility of using the Dynamic Time-Warping method for assessment of PD motor states showed it is feasible to use this method for extracting features to be used in automatic scoring of PD motor states.The findings from the knowledge- and data-driven methodology in this thesis can be used in the development of systems for follow up of the effects of treatment and individualized treatments in PD.
|
|
| 7. |
- Rahman, Hamidur, 1984-
(författare)
-
An Intelligent Non-Contact based Approach for Monitoring Driver’s Cognitive Load
- 2018
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- The modern cars have been equipped with advanced technical features to help make driving faster, safer and comfortable. However, to enhance transport security i.e. to avoid unexpected traffic accidents it is necessary to consider a vehicle driver as a part of the environment and need to monitor driver’s health and mental state. Driving behavior-based and physiological parameters-based approaches are the two commonly used approaches to monitor driver’s health and mental state. Previously, physiological parameters-based approaches using sensors are often attached to the human body. Although these sensors attached with body provide excellent signals in lab conditions it can often be troublesome and inconvenient in driving situations. So, physiological parameters extraction based on video images offers a new paradigm for driver’s health and mental state monitoring. This thesis report presents an intelligent non-contact-based approach to monitor driver’s cognitive load based on physiological parameters and vehicular parameters. Here, camera sensor has been used as a non-contact and pervasive methods for measuring physiological parameters.The contribution of this thesis is in three folds: 1) Implementation of a camera-based method to extract physiological parameters e.g., heart rate (HR), heart rate variability (HRV), inter-bit-interval (IBI), oxygen saturation (SpO2) and respiration rate (RR) considering several challenging conditions e.g. illumination, motion, vibration and movement. 2) Vehicular parameters e.g. lateral speed, steering wheel angle, steering wheel reversal rate, steering wheel torque, yaw rate, lanex, and lateral position extraction from a driving simulator. 3) Investigation of three machine learning algorithms i.e. Logistic Regression (LR), Support Vector Machine (SVM) and Linear Discriminant Analysis (LDA) to classify driver’s cognitive load. Here, according to the results, considering the challenging conditions, the highest correlation coefficient achieved for both HR and SpO2 is 0.96. Again, the Bland Altman plots shows 95% agreement between camera and the reference sensor. For IBI, the quality index (QI) is achieved 97.5% considering 100 ms R-peak error. For cognitive load classification, two separate studies are conducted, study1 with 1-back task and study2 with 2-back task and both time domain and frequency domain features are extracted from the facial videos. Finally, the achieved average accuracy for the classification of cognitive load is 91% for study1 and 83% for study2. In future, the proposed approach should be evaluated in real-road driving environment considering other complex challenging situations such as high temperature, complete dark/bright environment, unusual movements, facial occlusion by hands, sunglasses, scarf, beard etc.
|
|
