Explore the vast range of titles available.

The wide spread usage of wearable sensors such as in smart watches has provided continuous access to valuable user generated data such as human motion that could be used to identify an individual based on his/her motion patterns such as, gait. Several methods have been suggested to extract various heuristic and high-level features from gait motion data to identify discriminative gait signatures and distinguish the target individual from others. However, the manual and hand crafted feature extraction is error prone and subjective. Furthermore, the motion data collected from inertial sensors have complex structure and the detachment between manual feature extraction module and the predictive learning models might limit the generalization capabilities. In this paper, we propose a novel approach for human gait identification using time-frequency (TF) expansion of human gait cycles in order to capture joint 2 dimensional (2D) spectral and temporal patterns of gait cycles. Then, we design a deep convolutional neural network (DCNN) learning to extract discriminative features from the 2D expanded gait cycles and jointly optimize the identification model and the spectro-temporal features in a discriminative fashion. We collect raw motion data from five inertial sensors placed at the chest, lower-back, right hand wrist, right knee, and right ankle of each human subject synchronously in order to investigate the impact of sensor location on the gait identification performance. We then present two methods for early (input level) and late (decision score level) multi-sensor fusion to improve the gait identification generalization performance. We specifically propose the minimum error score fusion (MESF) method that discriminatively learns the linear fusion weights of individual DCNN scores at the decision level by minimizing the error rate on the training data in an iterative manner. 10 subjects participated in this study and hence, the problem is a 10-class identification task. Based on our experimental results, 91% subject identification accuracy was achieved using the best individual IMU and 2DTF-DCNN. We then investigated our proposed early and late sensor fusion approaches, which improved the gait identification accuracy of the system to 93.36% and 97.06%, respectively.

One of the main reasons for fatal accidents on the road is distracted driving. The continuous attention of an individual driver is a necessity for the task of driving. While driving, certain levels of distraction can cause drivers to lose their attention, which might lead to an accident. Thus, the number of accidents can be reduced by early detection of distraction. Many studies have been conducted to automatically detect driver distraction. Although camera-based techniques have been successfully employed to characterize driver distraction, the risk of privacy violation is high. On the other hand, physiological signals have shown to be a privacy preserving and reliable indicator of driver state, while the acquisition technology might be intrusive to drivers in practical implementation. In this study, we investigate a continuous measure of phasic Galvanic Skin Responses (GSR) using a wristband wearable to identify distraction of drivers during a driving experiment on-the-road. We first decompose the raw GSR signal into its phasic and tonic components using Continuous Decomposition Analysis (CDA), and then the continuous phasic component containing relevant characteristics of the skin conductance signals is investigated for further analysis. We generated a high resolution spectro-temporal transformation of the GSR signals for non-distracted and distracted (calling and texting) scenarios to visualize the associated behavior of the decomposed phasic GSR signal in correlation with distracted scenarios. According to the spectrogram observations, we extract relevant spectral and temporal features to capture the patterns associated with the distracted scenarios at the physiological level. We then performed feature selection using support vector machine recursive feature elimination (SVM-RFE) in order to: (1) generate a rank of the distinguishing features among the subject population, and (2) create a reduced feature subset toward more efficient distraction identification on the edge at the generalization phase. We employed support vector machine (SVM) to generate the 10-fold cross validation (10-CV) identification performance measures. Our experimental results demonstrated cross-validation accuracy of 94.81% using all the features and the accuracy of 93.01% using reduced feature space. The SVM-RFE selected set of features generated a marginal decrease in accuracy while reducing the redundancy in the input feature space toward shorter response time necessary for early notification of distracted state of the driver.

As a diagnostic monitoring approach, electroencephalogram (EEG) signals can be decoded by signal processing methodologies for various health monitoring purposes. However, EEG recordings are contaminated by other interferences, particularly facial and ocular artifacts generated by the user. This is specifically an issue during continuous EEG recording sessions, and is therefore a key step in using EEG signals for either physiological monitoring and diagnosis or brain–computer interface to identify such artifacts from useful EEG components. In this study, we aim to design a new generic framework in order to process and characterize EEG recording as a multi-component and non-stationary signal with the aim of localizing and identifying its component (e.g., artifact). In the proposed method, we gather three complementary algorithms together to enhance the efficiency of the system. Algorithms include time–frequency (TF) analysis and representation, two-dimensional multi-resolution analysis (2D MRA), and feature extraction and classification. Then, a combination of spectro-temporal and geometric features are extracted by combining key instantaneous TF space descriptors, which enables the system to characterize the non-stationarities in the EEG dynamics. We fit a curvelet transform (as a MRA method) to 2D TF representation of EEG segments to decompose the given space to various levels of resolution. Such a decomposition efficiently improves the analysis of the TF spaces with different characteristics (e.g., resolution). Our experimental results demonstrate that the combination of expansion to TF space, analysis using MRA, and extracting a set of suitable features and applying a proper predictive model is effective in enhancing the EEG artifact identification performance. We also compare the performance of the designed system with another common EEG signal processing technique—namely, 1D wavelet transform. Our experimental results reveal that the proposed method outperforms 1D wavelet.

Human-in-the-loop (HITL) IoT systems merge artificial intelligence, automation, and user interaction, enabling IoT environments to adapt dynamically based on human feedback. These systems are pivotal in applications requiring real-time responsiveness, user-specific customization, and privacy preservation, such as smart homes, healthcare monitoring, and advanced driver assistance systems. This thesis investigates the design principles, challenges, and privacy implications of HITL IoT systems, with a focus on enhancing personalization, efficiency, and trust. We present four key contributions addressing privacy challenges in HITL IoT systems. First, ERUDITE, a wearable neurotechnology platform, uses EEG data to personalize adaptive learning environments, demonstrating a 26% improvement in learning outcomes. Second, ada-PARL introduces adaptive privacy-aware reinforcement learning, reducing privacy leakage by 23% while enhancing utility by 57% in smart home simulations. Third, adaEXPARL proposes a novel early-exit strategy for Deep Q-Networks, achieving a 31% improvement in privacy with minimal utility trade-offs. Finally, we develop a privacy control mechanism for Microsoft HoloLens, incorporating real-time data masking and anonymization, establishing a benchmark for privacy-preserving IoT systems. Through these contributions, this thesis provides a comprehensive framework for designing HITL IoT systems that balance user adaptability, privacy, and utility, laying the foundation for their application in sensitive and user-driven environments.

In the evolving landscape of human-centric systems, personalized privacy solutions are becoming increasingly crucial due to the dynamic nature of human interactions. Traditional static privacy models often fail to meet the diverse and changing privacy needs of users. This paper introduces PEaRL, a system designed to enhance privacy preservation by tailoring its approach to individual behavioral patterns and preferences. While incorporating reinforcement learning (RL) for its adaptability, PEaRL primarily focuses on employing an early-exit strategy that dynamically balances privacy protection and system utility. This approach addresses the challenges posed by the variability and evolution of human behavior, which static privacy models struggle to handle effectively. We evaluate PEaRL in two distinct contexts: Smart Home environments and Virtual Reality (VR) Smart Classrooms. The empirical results demonstrate PEaRL's capability to provide a personalized tradeoff between user privacy and application utility, adapting effectively to individual user preferences. On average, across both systems, PEaRL enhances privacy protection by 31%, with a corresponding utility reduction of 24%.

Reinforcement learning (RL) presents numerous benefits compared to rule-based approaches in various applications. Privacy concerns have grown with the widespread use of RL trained with privacy-sensitive data in IoT devices, especially for human-in-the-loop systems. On the one hand, RL methods enhance the user experience by trying to adapt to the highly dynamic nature of humans. On the other hand, trained policies can leak the user's private information. Recent attention has been drawn to designing privacy-aware RL algorithms while maintaining an acceptable system utility. A central challenge in designing privacy-aware RL, especially for human-in-the-loop systems, is that humans have intrinsic variability and their preferences and behavior evolve. The effect of one privacy leak mitigation can be different for the same human or across different humans over time. Hence, we can not design one fixed model for privacy-aware RL that fits all. To that end, we propose adaPARL, an adaptive approach for privacy-aware RL, especially for human-in-the-loop IoT systems. adaPARL provides a personalized privacy-utility trade-off depending on human behavior and preference. We validate the proposed adaPARL on two IoT applications, namely (i) Human-in-the-Loop Smart Home and (ii) Human-in-the-Loop Virtual Reality (VR) Smart Classroom. Results obtained on these two applications validate the generality of adaPARL and its ability to provide a personalized privacy-utility trade-off. On average, for the first application, adaPARL improves the utility by \\(57\\%\\) over the baseline and by \\(43\\%\\) over randomization. adaPARL also reduces the privacy leak by \\(23\\%\\) on average. For the second application, adaPARL decreases the privacy leak to \\(44\\%\\) before the utility drops by \\(15\\%\\).

Achieving fairness in sequential-decision making systems within Human-in-the-Loop (HITL) environments is a critical concern, especially when multiple humans with different behavior and expectations are affected by the same adaptation decisions in the system. This human variability factor adds more complexity since policies deemed fair at one point in time may become discriminatory over time due to variations in human preferences resulting from inter- and intra-human variability. This paper addresses the fairness problem from an equity lens, considering human behavior variability, and the changes in human preferences over time. We propose FAIRO, a novel algorithm for fairness-aware sequential-decision making in HITL adaptation, which incorporates these notions into the decision-making process. In particular, FAIRO decomposes this complex fairness task into adaptive sub-tasks based on individual human preferences through leveraging the Options reinforcement learning framework. We design FAIRO to generalize to three types of HITL application setups that have the shared adaptation decision problem. Furthermore, we recognize that fairness-aware policies can sometimes conflict with the application's utility. To address this challenge, we provide a fairness-utility tradeoff in FAIRO, allowing system designers to balance the objectives of fairness and utility based on specific application requirements. Extensive evaluations of FAIRO on the three HITL applications demonstrate its generalizability and effectiveness in promoting fairness while accounting for human variability. On average, FAIRO can improve fairness compared with other methods across all three applications by 35.36%.

Thanks to the rapid growth in wearable technologies and recent advancement in machine learning and signal processing, monitoring complex human contexts becomes feasible, paving the way to develop human-in-the-loop IoT systems that naturally evolve to adapt to the human and environment state autonomously. Nevertheless, a central challenge in designing many of these IoT systems arises from the requirement to infer the human mental state, such as intention, stress, cognition load, or learning ability. While different human contexts can be inferred from the fusion of different sensor modalities that can correlate to a particular mental state, the human brain provides a richer sensor modality that gives us more insights into the required human context. This paper proposes ERUDITE, a human-in-the-loop IoT system for the learning environment that exploits recent wearable neurotechnology to decode brain signals. Through insights from concept learning theory, ERUDITE can infer the human state of learning and understand when human learning increases or declines. By quantifying human learning as an input sensory signal, ERUDITE can provide adequate personalized feedback to humans in a learning environment to enhance their learning experience. ERUDITE is evaluated across \\(15\\) participants and showed that by using the brain signals as a sensor modality to infer the human learning state and providing personalized adaptation to the learning environment, the participants' learning performance increased on average by \\(26\\%\\). Furthermore, we showed that ERUDITE can be deployed on an edge-based prototype to evaluate its practicality and scalability.

A new deep learning-based electroencephalography (EEG) signal analysis framework is proposed. While deep neural networks, specifically convolutional neural networks (CNNs), have gained remarkable attention recently, they still suffer from high dimensionality of the training data. Two-dimensional input images of CNNs are more vulnerable to be redundant versus one-dimensional input time-series of conventional neural networks. In this study, we propose a new dimensionality reduction framework for reducing the dimension of CNN inputs based on the tensor decomposition of the time-frequency representation of EEG signals. The proposed tensor decomposition-based dimensionality reduction algorithm transforms a large set of slices of the input tensor to a concise set of slices which are called super-slices. Employing super-slices not only handles the artifacts and redundancies of the EEG data but also reduces the dimension of the CNNs training inputs. We also consider different time-frequency representation methods for EEG image generation and provide a comprehensive comparison among them. We test our proposed framework on HCB-MIT data and as results show our approach outperforms other previous studies.