Relying on physiological or behavioral traits for identity recognition, biometric technologies offer several advantages over conventional possession- and knowledge-based approaches and are now widely used in diverse applications. However, as most biometrics (e.g., fingerprints, irises, etc.) in use are extrinsic, susceptible to replay attacks, and could result in the disclosure of individuals’ physiological and pathological conditions, security and privacy concerns must be considered. In this paper, several electrocardiogram (ECG)-based cancelable biometric schemes are proposed to mitigate such concerns. The intrinsic and dynamic nature of ECGs and their inherent indication of life make them extremely difficult to steal or counterfeit. Using the concept of “signal subspace collapsing,” distinct biometric templates associated with an individual’s ECGs can be constructed such that it is possible to revoke a compromised template like a password. By incorporating different strategies for common subspace suppression, the well-known multiple signal classification (MUSIC) method can effectively determine the identity of any individual just via his/her ECGs. Unlike existing cancelable biometrics, the recognition can be accomplished without knowledge of the distortion transformation, which further increases the difficulty of recovering the original ECGs from their templates. Various experiments with real ECGs from 285 subjects are conducted to illustrate the efficacy of the proposed schemes.

Security is a primary concern in Internet of Things (IoT) applications, and biometric recognition is considered to be a promising solution. In this paper, we propose a novel electrocardiogram (ECG)-based biometric recognition scheme that can potentially strengthen the security of IoT-based patient monitoring systems. A biometric system is designed to operate in either verification or identification mode, and we concentrate on applying the proposed approach to the latter due to its difficulty and popularity in existing studies. Through the concept of “subspace oversampling”, we are able to create distinct and irreversible templates for an enrollee to avoid the cross-matching problem and privacy invasion. With the help of “subspace matching”, the identity of unknown subjects can be determined using only their beat bundles without any additional information required for template construction. Moreover, the proposed scheme includes a method for unregistered subject exclusion to avoid falsely linking an initially unidentifiable subject to someone in the database, further strengthening its security. The performance of the proposed scheme was evaluated using the ECGs of 287 subjects from the PTB dataset. The experimental results demonstrated linkability of the constructed templates as low as 0.0938, and beat bundles reconstructed from the templates of a given subject were more likely to be identified as those from another user. An identification rate of 99.02% was obtained even when the proposed exclusion scheme was incorporated; meanwhile, the corresponding false-positive identification error rate was 0.44% under a dictionary attack with real ECGs.

State-of-charge (SOC) is a relative quantity that describes the ratio of the remaining capacity to the present maximum available capacity. Accurate SOC estimation is essential for a battery-management system. In addition to informing the user of the expected usage until the next recharge, it is crucial for improving the utilization efficiency and service life of the battery. This study focuses on applying deep-learning techniques, and specifically convolutional residual networks, to estimate the SOC of lithium-ion batteries. By stacking the values of multiple measurable variables taken at many time instants as the model inputs, the process information for the voltage or current generation, and their interrelations, can be effectively extracted using the proposed convolutional residual blocks, and can simultaneously be exploited to regress for accurate SOCs. The performance of the proposed network model was evaluated using the data obtained from a lithium-ion battery (Panasonic NCR18650PF) under nine different driving schedules at five ambient temperatures. The experimental results demonstrated an average mean absolute error of 1.260%, and an average root-mean-square error of 0.998%. The number of floating-point operations required to complete one SOC estimation was 2.24 × 10⁶. These results indicate the efficacy and performance of the proposed approach.

Resting-state fMRI has been widely used in investigating the pathophysiology of late-life depression (LLD). Unlike the conventional linear approach, cross-sample entropy (CSE) analysis shows the nonlinear property in fMRI signals between brain regions. Moreover, recent advances in deep learning, such as convolutional neural networks (CNNs), provide a timely application for understanding LLD. Accurate and prompt diagnosis is essential in LLD; hence, this study aimed to combine CNN and CSE analysis to discriminate LLD patients and non-depressed comparison older adults based on brain resting-state fMRI signals. Seventy-seven older adults, including 49 patients and 28 comparison older adults, were included for fMRI scans. Three-dimensional CSEs with volumes corresponding to 90 seed regions of interest of each participant were developed and fed into models for disease classification and depression severity prediction. We obtained a diagnostic accuracy > 85% in the superior frontal gyrus (left dorsolateral and right orbital parts), left insula, and right middle occipital gyrus. With a mean root-mean-square error (RMSE) of 2.41, three separate models were required to predict depressive symptoms in the severe, moderate, and mild depression groups. The CSE volumes in the left inferior parietal lobule, left parahippocampal gyrus, and left postcentral gyrus performed best in each respective model. Combined complexity analysis and deep learning algorithms can classify patients with LLD from comparison older adults and predict symptom severity based on fMRI data. Such application can be utilized in precision medicine for disease detection and symptom monitoring in LLD.