Remote Patient Monitoring systems (RPMs) are becoming increasingly important as the aging populationstruggles to manage chronic illnesses and secure consistent healthcare access. While these systems excel in tracking physical metrics, integrating emotion recognition can bridge the often-overlooked connection between emotional and physical well-being. By identifying emotional responses such as discomfort, distress, or contentment, RPM systems can provide immediate feedback for care adjustments and reveal long-term trends. Subtle shifts in emotional patterns may act as early indicators of mental health conditions linked to chronic diseases or transient emotional stress. Expanding RPMs to include emotion awareness makes care more adaptive and holistic. This review explores how emotion recognition can enhance RPM systems by addressing both physical and emotional health. It examines methods that leverage physiological and behavioral responses to capture emotional states, assessing the advantages, limitations, and applicability of these modalities in RPM settings. By incorporating emotion-aware tools, RPMs have the potential to deliver more comprehensive, responsive, and personalized care, revolutionizing healthcare delivery for diverse patient groups.

Federated Learning (FL) is a privacy-preserving algorithm that enables multiple clients to collaboratively train a global model without sharing their local data. This learning algorithm is particularly valuable in privacy-sensitive applications such as Human Activity Recognition (HAR), where users are reluctant to share their personal data. However, a conventional FL system suffers from data heterogeneity and communication overhead. To address these issues, we propose an efficient FL algorithm for image-based HAR using optimal server representations (OSR). OSR efficiently selects a representative set of privacy-preserved images for transmission to the server and improves the global model quality by training on privacy-preserved data. Our comprehensive experiments carried out on three public datasets, namely Stanford40, PPMI, and VOC2012, demonstrate the superiority of OSR in terms of performance and bandwidth usage compared to state-of-the-art approaches.

Despite the recent advancements in information retrieval (IR), zero-shot IR remains a significant challenge, especially when dealing with new domains, languages, and newly-released use cases that lack historical query traffic from existing users.For such cases, it is common to use query augmentations followed by fine-tuning pre-trained models on the document data paired with synthetic queries.In this work, we propose a novel Universal Document Linking (UDL) algorithm, which links similar documents to enhance synthetic query generation across multiple datasets with different characteristics.UDL leverages entropy for the choice of similarity models and named entity recognition (NER) for the link decision of documents using similarity scores.Our empirical studies demonstrate the effectiveness and universality of the UDL across diverse datasets and IR models, surpassing state-of-the-art methods in zero-shot cases.The developed code for reproducibility is included in the supplementary material.1

Electroencephalography (EEG) based emotion recognition is gaining substantial interest because of its strong association with the area of brain-computer interface. Even though several works exist in the literature, it is still challenging to find discriminative features that can generalize well to different EEG datasets. In this work, we focus on developing a deep learning model that makes use of the spatial and temporal representations of the EEG signal to generate EEG embeddings for emotion recognition. The proposed model uses a self-attention mechanism along with a feature fusion approach to improve the discrimination power of the learned EEG embeddings. Comprehensive experiments are conducted on the DEAP dataset, which demonstrates the superiority of the proposed work, where the attained accuracies for the arousal and valence classification are 91.17% and 90.73% , respectively.

This paper investigates the employment of photoplethysmography (PPG) for user authentication systems. Time-stable and user-specific features are developed by stretching the signal, designing a convolutional neural network and performing a variation-stable approach with three score fusions. Two evaluation scenarios are explored, namely single-session and two-sessions. In the earlier, the training and testing are done solely on one session data to find the user-specific features, while the second scenario is performed on data from two different sessions to test the time permanence of the features. The verification system was tested on four databases achieving an accuracy of 100% for single-session and 87.3% for two-sessions cases. The simulation results confirm the effectiveness of proposed variation-stable fusion which can be extended to other biometrics. The code is available in [1].

Post-traumatic stress disorder is a major public health concern with a lifetime prevalence rate of 6.1-9.2% in North America. PTSD is known to alter the autonomic nervous system leading to chronic sympathetic arousal including heightened anxiety and hypervigilance. Pupillometry offers a quick and accessible measure of autonomic nervous system imbalances characteristic of PTSD. This study investigates the utility of pupillometry as a biomarker to detect PTSD in a sample of 39 adults with (n = 22) and without (n = 17) PTSD. Participants viewed a 25-minute computer protocol consisting of 5-minute rest phase, 10-minute negative emotionally valent images, and 10-minute guided meditation. We relied on a time-frequency analysis to represent the pupillary responses of two different groups (PTSD-affected individuals and healthy-control subjects). These data were then employed with a CNN network to learn a prediction model. Individuals with PTSD demonstrated increased pupil dilation across the entire protocol. The final outcome revealed an accuracy of 81.09% which indicates the feasibility of using this approach to detecting participants with PTSD in an automated way. Findings from this research have important implications for clinical mental health assessment, diagnostics and treatment.

The photoplethysmography (PPG) is a non-invasive physiological signal that captures the changes in blood volume resulted from heart activity. It carries unique person-specific characteristics that can be utilized for biometric systems. Currently, the use of a biometric system is crucial to ensure the security of the user’s identity. Due to the high sensitivity of the PPG signal, it suffers from extreme variations within the same subject when obtained at different time instances. These variations impose a challenge to employ the PPG signal and hinder the algorithm generalization for many applications including verification and identification systems. In this work, we propose a PPG Biometric Generative Adversarial Network (PBGAN) to create synthetic person-specific and time-stable PPG signals for genuine samples. Two types of classification models are employed with the PBGAN where the focus is on verification scenarios. In addition, we expand our previously recorded PPG dataset from 100 to 170 participants where the new size guarantees the generalization capability of the proposed system. This database along with three public ones are employed to evaluate the performances in terms of uniqueness and time stability. Furthermore, we consider three different training strategies to simulate practical scenarios. The best results acquired from our collected database in terms of Equal Error Rate (EER) is 1.3% for the single-session and 11.5% for the two-sessions scenarios which demonstrate the effectiveness of the proposed method in improving the verification system’s performance. Compared to our previous work, we achieve 1.3% and 1.4% EER improvements in two-sessions’ databases with small computational times which reveals the superiority of our proposed approach for real applications.

In this work, we demonstrates the feasibility of employing the biometric photoplethysmography (PPG) signal for human verification applications. The PPG signal has dominance in terms of accessibility and portability which makes its usage in many applications such as user access control very appealing. Therefore, we developed robust time-stable features using signal analysis and deep learning models to increase the robustness and performance of the verification system with the PPG signal. The proposed system focuses on utilizing different stretching mechanisms namely Dynamic Time Warping, zero padding and interpolation with Fourier transform, and fuses them at the data level to be then deployed with different deep learning models. The designed deep models consist of Convolutional Neural Network (CNN) and Long-Short Term Memory (LSTM) which are considered to build a user specific model for the verification task. We collected a dataset consisting of 100 participants and recorded at two different time sessions using Plux pulse sensor. This dataset along with another two public databases are deployed to evaluate the performance of the proposed verification system in terms of uniqueness and time stability. The final result demonstrates the superiority of our proposed system tested on the built dataset and compared with other two public databases. The best performance achieved from our collected two-sessions database in terms of accuracy is 98% for the single-session and 87.1% for the two-sessions scenarios.

In this paper, we propose a multi-modal mesh surface representation by fusing texture and geometric data. Our approach defines an inverse mapping between different geometric descriptors computed on the mesh surface, and the corresponding 2D texture image of the mesh, allowing the construction of fused geometrically augmented images. This new fused modality enables us to learn feature representations from 3D data in a highly efficient manner by employing standard convolutional neural networks in a transfer-learning mode. In contrast to existing methods, the proposed approach is both computationally and memory efficient, preserves intrinsic geometric information and learns highly discriminative feature representations by effectively fusing shape and texture information at the data level. The efficacy is demonstrated on the task of facial expression classification, showing competitive performance with state-of-the-art methods.

In this paper, we propose an approach to learn generic multi-modal mesh surface representations using a novel scheme for fusing texture and geometric data. Our approach defines an inverse mapping between different geometric descriptors computed on the mesh surface or its down-sampled version, and the corresponding 2D texture image of the mesh, allowing the construction of fused geometrically augmented images (FGAI). This new fused modality enables us to learn feature representations from 3D data in a highly efficient manner by simply employing standard CNNs in a transfer-learning mode. The proposed approach is both computationally and memory efficient, preserves intrinsic geometric information and learns highly discriminative feature representations by effectively fusing shape and texture information at data level. The efficacy of our approach is demonstrated for the tasks of facial action unit detection and expression classification. The extensive experiments conducted on the Bosphorus and BU-4DFE datasets show that our method produces a significant boost in the performance when compared to state-of-the-art solutions.

Colorectal cancer is one of the major causes of cancer deaths worldwide. To achieve early cancer screening, detecting the presence of polyps in the colon tract is the preferred technique. In this paper, a deep learning approach for identifying polyps in colonoscopy images is proposed. The novelty of our technique stems from the fact that it fully employs a pre-trained Convolutional Neural Network (CNN) architecture as a feature extractor. Contrary to the conventional methods which either perform fine-tuning or train the CNN from scratch, we utilize the CNN output features as an input to train the Support Vector Machine (SVM) Classifier. The efficiency of the presented framework is demonstrated on the public CVC ColonDB, in which the experimental results indicate that our methodology significantly outperforms other competitive paradigms.

In order to exploit the inherent sparsity of an OFDM multipath wireless channel, this paper presents a novel estimation technique based on the ℓ1-LS criterion that relies on the selection of the optimal regularization parameter. This term is proven in the paper to be intimately related to the Signal to Noise Ratio (SNR) and Sparsity Degree (ρ) of the channel. Therefore, in order to take full advantage of the ℓ1-LS framework, an ad-hoc technique for estimating blindly the SNR and ρ of the problem is also introduced. The performance of the novel algorithm is compared to a number of reference techniques. Two standard measures, namely the Mean Square Error (MSE) of the estimated channel and the Symbol Error Rate (SER) of the OFDM system validate the robustness of the proposed algorithm. Indeed, this novel technique achieves better estimation along with better spectrum efficiency.

Embedding a sparse penalty in conventional Least Mean Square (LMS) adaptive algorithms is an established strategy to enhance the performance and robustness against noise in the estimation of sparse plants, such as wireless mul-tipath channels. In this paper we review the most prominent NLMS-based algorithms with ℓp-norm constraint, discussing the underlying mechanisms that lead to improvement gains in sparse scenarios. Simulation results validate the analysis and comparative discussion. Given that adaptive algorithms operating in time domain deteriorate with correlated signals, we propose hereby a novel frequency-domain (FD) ℓp-NLMS that performs in such situations. Simulation results indicate that the proposed method outperforms its time-domain counterparts not only in convergence rate but more importantly in residual misalignment. This important result has not been echoed so far.