Biblio

With the help of technological advancements in the last decade, it has become much easier to extensively and remotely observe medical conditions of the patients through wearable biosensors that act as connected nodes on Body Area Networks (BANs). Sensitive nature of the critical data captured and communicated via wireless medium makes it extremely important to process it as securely as possible. In this regard, lightweight security mechanisms are needed to overcome the hardware resource restrictions of biosensors. Random and secure cryptographic key generation and agreement among the biosensors take place at the core of these security mechanisms. In this paper, we propose the SKA-PSAR (Augmented Randomness for Secure Key Agreement using Physiological Signals) system to produce highly random cryptographic keys for the biosensors to secure communication in BANs. Similar to its predecessor SKA-PS protocol by Karaoglan Altop et al., SKA-PSAR also employs physiological signals, such as heart rate and blood pressure, as inputs for the keys and utilizes the set reconciliation mechanism as basic building block. Novel quantization and binarization methods of the proposed SKA-PSAR system distinguish it from SKA-PS by increasing the randomness of the generated keys. Additionally, SKA-PSAR generated cryptographic keys have distinctive and time variant characteristics as well as long enough bit sizes that provides resistance against cryptographic attacks. Moreover, correct key generation rate is above 98% with respect to most of the system parameters, and false key generation rate of 0% have been obtained for all system parameters.

With the advancement of Artificial Intelligence technology to make smart devices, understanding how humans develop trust in virtual agents is emerging as a critical research field. Through our research, we report on a novel methodology to investigate user's trust in auditory assistance in a Virtual Reality (VR) based search task, under both high and low cognitive load and under varying levels of agent accuracy. We collected physiological sensor data such as electroencephalography (EEG), galvanic skin response (GSR), and heart-rate variability (HRV), subjective data through questionnaire such as System Trust Scale (STS), Subjective Mental Effort Questionnaire (SMEQ) and NASA-TLX. We also collected a behavioral measure of trust (congruency of users' head motion in response to valid/ invalid verbal advice from the agent). Our results indicate that our custom VR environment enables researchers to measure and understand human trust in virtual agents using the matrices, and both cognitive load and agent accuracy play an important role in trust formation. We discuss the implications of the research and directions for future work.

This paper aims at identifying the neural correlates of human trust in autonomous systems using electroencephalography (EEG) signals. Quantifying the relationship between trust and brain activities allows for real-time assessment of human trust in automation. This line of effort contributes to the design of trusted autonomous systems, and more generally, modeling the interaction in human-autonomy interaction. To study the correlates of trust, we use an investment game in which artificial agents with different levels of trustworthiness are employed. We collected EEG signals from 10 human subjects while they are playing the game; then computed three types of features from these signals considering the signal time-dependency, complexity and power spectrum using an autoregressive model (AR), sample entropy and Fourier analysis, respectively. Results of a mixed model analysis showed significant correlation between human trust and EEG features from certain electrodes. The frontal and the occipital area are identified as the predominant brain areas correlated with trust.

Bluetooth enables excellent mobility in Brain Computer Interface (BCI) research and other use cases including ambulatory care, telemedicine, fitness tracking and mindfulness training. Although significant research exists for an all-encompassing BCI performance rating, almost all the literature addresses performance in terms of brain state or brain function classification accuracy. For the few published experiments that address BCI hardware performance, they too, focused on improving classification accuracy. This paper explores some of the more recent studies and proposes a trusted performance rating for BCI applications based on the enhanced privacy, yet reduced bandwidth needs of mobile EEG-based BCI applications. This paper proposes a set of Bluetooth operating parameters required to meet the performance, usability and privacy requirements of reliable and secure mobile neuro-feedback applications. It presents a rating model, "Trusted Mobile BCI", based on those operating parameters, and validated the model with studies that leveraged mobile BCI technology.

Machine Learning (ML) algorithms, as the core technology in Artificial Intelligence (AI) applications, such as self-driving vehicles, make important decisions by performing a variety of data classification or prediction tasks. Attacks on data or algorithms in AI applications can lead to misclassification or misprediction, which can fail the applications. For each dataset separately, the parameters of ML algorithms should be tuned to reach a desirable classification or prediction accuracy. Typically, ML experts tune the parameters empirically, which can be time consuming and does not guarantee the optimal result. To this end, some research suggests an analytical approach to tune the ML parameters for maximum accuracy. However, none of the works consider the ML performance under attack in their tuning process. This paper proposes an analytical framework for tuning the ML parameters to be secure against attacks, while keeping its accuracy high. The framework finds the optimal set of parameters by defining a novel objective function, which takes into account the test results of both ML accuracy and its security against attacks. For validating the framework, an AI application is implemented to recognize whether a subject's eyes are open or closed, by applying k-Nearest Neighbors (kNN) algorithm on her Electroencephalogram (EEG) signals. In this application, the number of neighbors (k) and the distance metric type, as the two main parameters of kNN, are chosen for tuning. The input data perturbation attack, as one of the most common attacks on ML algorithms, is used for testing the security of the application. Exhaustive search approach is used to solve the optimization problem. The experiment results show k = 43 and cosine distance metric is the optimal configuration of kNN for the EEG dataset, which leads to 83.75% classification accuracy and reduces the attack success rate to 5.21%.

ECG signals are often corrupted by 50 Hz noise, the frequency from the power supply. So it becomes quite necessary to remove Power Line Interference (PLI) from the ECG signal. The reference ECG signal data was taken from the MIT-BIH database. Different filtering techniques comprising of Discrete Wavelet Transform (DWT), Normalized Least Mean Square (NLMS) filter, Finite Impulse Response (FIR) filter and Infinite Impulse Response (IIR) filter were used in this paper for denoising the ECG signal which was corrupted by the PLI. Later, the comparison was made among the methods, to find the best methodology to denoise the corrupted ECG signal. The parameters that were used for the comparison are Mean Square Error (MSE), Mean Absolute Error (MAE), Signal to Noise Ratio (SNR) and Peak Signal to Noise Ratio (PSNR). Higher values of SNR & PSNR and lower values of MSE & MAE define the best denoising algorithm.

Typical techniques for tracking vital signs require body contact and most of these techniques are intrusive in nature. Body-contact methods might irritate the patient's skin and he/she might feel uncomfortable while sensors are touching his/her body. In this study, we present a new wireless (non-contact) method for monitoring human vital signs (breathing and heartbeat). We have demonstrated for the first time1 that vitals signs can be measured wirelessly through visible light signal reflected from a human subject, also referred to as visible light sensing (VLS). In this method, the breathing and heartbeat rates are measured without any body-contact device, using only a simple photodetector and a light source (e.g., LED). The light signal reflected from human subject is modulated by the physical motions during breathing and heartbeats. Signal processing tools such as filtering and Fourier transform are used to convert these small variations in the received light signal power to vitals data.We implemented the VLS-based non-contact vital signs monitoring system by using an off-the-shelf light source, a photodetector and a signal acquisition and processing unit. We observed more than 94% of accuracy as compared to a contact-based FDA (The Food and Drug Administration) approved devices. Additional evaluations are planned to assess the performance of the developed vitals monitoring system, e.g., different subjects, environments, etc. Non-contact vitals monitoring system can be used in various areas and scenarios such as medical facilities, residential homes, security and human-computer-interaction (HCI) applications.

This study proposes a method for ECG signals quality assessment (SQA) by using temporal feature, and heuristic rule. The ECG signal will be classified as acceptable or unacceptable. Seven types of noise were able to be detected by the prosed method. The noises are: FL, TVN, BW, AB, MA, PLI and AWGN. The proposed method is aimed to have better performance for SQA than classical machine learning method. The experiment is conducted by using 1000 instances ECG signal. The experiment result shows that db8 has the best performance with 0.86, 0.85 and 85.6% on lead-1 signal and 0.69, 0.79, and 74% on lead-5 signal for specificity, sensitivity and accuracy respectively. Compared to the classical machine learning, the proposed heuristic method has same accuracy but has 48% and 31% better specificity for lead-1 and lead-5. It means that the proposed method has far better ability to detect noise.

Smartwatches are expected to become the world's best-selling electronic product after smartphones. Various smart-watches have been released to the private consumer market, but the data on smartwatches is not well protected. In this paper, we show for the first time that photoplethysmography (PPG)signals influenced by hand gestures can be used to authenticate users on smartwatches. The insight is that muscle and tendon movements caused by hand gestures compress the arterial geometry with different degrees, which has a significant impact on the blood flow. Based on this insight, novel approaches are proposed to detect the starting point and ending point of the hand gesture from raw PPG signals and determine if these PPG signals are from a normal user or an attacker. Different from existing solutions, our approach leverages the PPG sensors that are available on most smartwatches and does not need to collect training data from attackers. Also, our system can be used in more general scenarios wherever users can perform hand gestures and is robust against shoulder surfing attacks. We conduct various experiments to evaluate the performance of our system and show that our system achieves an average authentication accuracy of 96.31 % and an average true rejection rate of at least 91.64% against two types of attacks.

Wearable and mobile medical devices provide efficient, comfortable, and economic health monitoring, having a wide range of applications from daily to clinical scenarios. Health data security becomes a critically important issue. Electrocardiogram (ECG) has proven to be a potential biometric in human recognition over the past decade. Unlike conventional authentication methods using passwords, fingerprints, face, etc., ECG signal can not be simply intercepted, duplicated, and enables continuous identification. However, in many of the studies, algorithms developed are not suitable for practical application, which usually require long ECG data for authentication. In this work, we introduce a two-phase authentication using artificial neural network (NN) models. This algorithm enables fast authentication within only 3 seconds, meanwhile achieves reasonable performance in recognition. We test the proposed method in a controlled laboratory experiment with 50 subjects. Finger ECG signals are collected using a mobile device at different times and physical statues. At the first stage, a ``General'' NN model is constructed based on data from the cohort and used for preliminary screening, while at the second stage ``Personal'' NN models constructed from single individual's data are applied as fine-grained identification. The algorithm is tested on the whole data set, and on different sizes of subsets (5, 10, 20, 30, and 40). Results proved that the proposed method is feasible and reliable for individual authentication, having obtained average False Acceptance Rate (FAR) and False Rejection Rate (FRR) below 10% for the whole data set.

As a plethora of wearable devices are being introduced, significant concerns exist on the privacy and security of personal data stored on these devices. Expanding on recent works of using electrocardiogram (ECG) as a modality for biometric authentication, in this work, we investigate the possibility of using personal ECG signals as the individually unique source for physical unclonable function (PUF), which eventually can be used as the key for encryption and decryption engines. We present new signal processing and machine learning algorithms that learn and extract maximally different ECG features for different individuals and minimally different ECG features for the same individual over time. Experimental results with a large 741-subject in-house ECG database show that the distributions of the intra-subject (same person) Hamming distance of extracted ECG features and the inter-subject Hamming distance have minimal overlap. 256-b random numbers generated from the ECG features of 648 (out of 741) subjects pass the NIST randomness tests.

In this paper, the principle of the kernel extreme learning machine (ELM) is analyzed. Based on that, we introduce a kind of multi-scale wavelet kernel extreme learning machine classifier and apply it to electroencephalographic (EEG) signal feature classification. Experiments show that our classifier achieves excellent performance.