Search

Facial expression recognition plays an important role in human behaviour, communication, and interaction. Recent neural networks have demonstrated to perform well at its automatic recognition, with different explainability techniques available to make them more transparent. In this work, we propose a facial expression recognition study for people with intellectual disabilities that would be integrated into a social robot. We train two well-known neural networks with five databases of facial expressions and test them with two databases containing people with and without intellectual disabilities. Finally, we study in which regions the models focus to perceive a particular expression using two different explainability techniques: LIME and RISE, assessing the differences when used on images containing disabled and non-disabled people.

Background: Pain assessment in individuals with neurological conditions, especially those with limited self-report ability and altered facial expressions, presents challenges. Existing measures, relying on direct observation by caregivers, lack sensitivity and specificity. In cerebral palsy, pain is a common comorbidity and a reliable evaluation protocol is crucial. Thus, having an automatic system that recognizes facial expressions could be of enormous help when diagnosing pain in this type of patient. Objectives: 1) to build a dataset of facial pain expressions in individuals with cerebral palsy, and 2) to develop an automated facial recognition system based on deep learning for pain assessment addressed to this population. Methods: Ten neural networks were trained on three pain image databases, including the UNBC-McMaster Shoulder Pain Expression Archive Database, the Multimodal Intensity Pain Dataset, and the Delaware Pain Database. Additionally, a curated dataset (CPPAIN) was created, consisting of 109 preprocessed facial pain expression images from individuals with cerebral palsy, categorized by two physiotherapists using the Facial Action Coding System observational scale. Results: InceptionV3 exhibited promising performance on the CP-PAIN dataset, achieving an accuracy of 62.67% and an F1 score of 61.12%. Explainable artificial intelligence techniques revealed consistent essential features for pain identification across models. Conclusion: This study demonstrates the potential of deep learning models for robust pain detection in populations with neurological conditions and communication disabilities. The creation of a larger dataset specific to cerebral palsy would further enhance model accuracy, offering a valuable tool for discerning subtle and idiosyncratic pain expressions. The insights gained could extend to other complex neurological conditions.

Facial expression recognition has gained significance as a means of imparting social robots with the capacity to discern the emotional states of users. The use of social robotics includes a variety of settings, including homes, nursing homes or daycare centers, serving to a wide range of users. Remarkable performance has been achieved by deep learning approaches, however, its direct use for recognizing facial expressions in individuals with intellectual disabilities has not been yet studied in the literature, to the best of our knowledge. To address this objective, we train a set of 12 convolutional neural networks in different approaches, including an ensemble of datasets without individuals with intellectual disabilities and a dataset featuring such individuals. Our examination of the outcomes, both the performance and the important image regions for the models, reveals significant distinctions in facial expressions between individuals with and without intellectual disabilities, as well as among individuals with intellectual disabilities. Remarkably, our findings show the need of facial expression recognition within this population through tailored user-specific training methodologies, which enable the models to effectively address the unique expressions of each user., Comment: This work has been submitted to the IEEE for possible publication

Facial expression recognition is vital for human behavior analysis, and deep learning has enabled models that can outperform humans. However, it is unclear how closely they mimic human processing. This study aims to explore the similarity between deep neural networks and human perception by comparing twelve different networks, including both general object classifiers and FER-specific models. We employ an innovative global explainable AI method to generate heatmaps, revealing crucial facial regions for the twelve networks trained on six facial expressions. We assess these results both quantitatively and qualitatively, comparing them to ground truth masks based on Friesen and Ekman's description and among them. We use Intersection over Union (IoU) and normalized correlation coefficients for comparisons. We generate 72 heatmaps to highlight critical regions for each expression and architecture. Qualitatively, models with pre-trained weights show more similarity in heatmaps compared to those without pre-training. Specifically, eye and nose areas influence certain facial expressions, while the mouth is consistently important across all models and expressions. Quantitatively, we find low average IoU values (avg. 0.2702) across all expressions and architectures. The best-performing architecture averages 0.3269, while the worst-performing one averages 0.2066. Dendrograms, built with the normalized correlation coefficient, reveal two main clusters for most expressions: models with pre-training and models without pre-training. Findings suggest limited alignment between human and AI facial expression recognition, with network architectures influencing the similarity, as similar architectures prioritize similar facial regions., Comment: Multimed Tools Appl (2024)

Explainable artificial intelligence techniques are becoming increasingly important with the rise of deep learning applications in various domains. These techniques aim to provide a better understanding of complex "black box" models and enhance user trust while maintaining high learning performance. While many studies have focused on explaining deep learning models in computer vision for image input, video explanations remain relatively unexplored due to the temporal dimension's complexity. In this paper, we present a unified framework for local agnostic explanations in the video domain. Our contributions include: (1) Extending a fine-grained explanation framework tailored for computer vision data, (2) Adapting six existing explanation techniques to work on video data by incorporating temporal information and enabling local explanations, and (3) Conducting an evaluation and comparison of the adapted explanation methods using different models and datasets. We discuss the possibilities and choices involved in the removal-based explanation process for visual data. The adaptation of six explanation methods for video is explained, with comparisons to existing approaches. We evaluate the performance of the methods using automated metrics and user-based evaluation, showing that 3D RISE, 3D LIME, and 3D Kernel SHAP outperform other methods. By decomposing the explanation process into manageable steps, we facilitate the study of each choice's impact and allow for further refinement of explanation methods to suit specific datasets and models.

As the percentage of elderly people in developed countries increases worldwide, the healthcare of this collective is a worrying matter, especially if it includes the preservation of their autonomy. In this direction, many studies are being published on Ambient Assisted Living (AAL) systems, which help to reduce the preoccupations raised by the independent living of the elderly. In this study, a systematic review of the literature is presented on fall detection and Human Activity Recognition (HAR) for the elderly, as the two main tasks to solve to guarantee the safety of elderly people living alone. To address the current tendency to perform these two tasks, the review focuses on the use of Deep Learning (DL) based approaches on computer vision data. In addition, different collections of data like DL models, datasets or hardware (e.g. depth or thermal cameras) are gathered from the reviewed studies and provided for reference in future studies. Strengths and weaknesses of existing approaches are also discussed and, based on them, our recommendations for future works are provided.

Optical Spectrum as a Service (OSaaS) spanning over multiple transparent optical network domains, can significantly reduce the investment and operational costs of the end-to-end service. Based on the black-link approach, these services are empowered by reconfigurable transceivers and the emerging disaggregation trend in optical transport networks. This work investigates the accuracy aspects of the channel probing method used in Generalized Signal to Noise Ratio (GSNR)-based OSaaS characterization in terrestrial brownfield systems. OSaaS service margins to accommodate impacts from enabling neighboring channels and end-of-life channel loads are experimentally derived in a systematic lab study carried out in the Open Ireland testbed. The applicability of the lab-derived margins is then verified in the HEAnet production network using a 400 GHz wide OSaaS. Finally, the probing accuracy is tested by depleting the GSNR margin through power adjustments utilizing the same 400 GHz OSaaS in the HEAnet live network. A minimum of 0.92 dB and 1.46 dB of service margin allocation is recommended to accommodate the impacts of enabling neighboring channels and end-of-life channel loads. Further 0.6 dB of GSNR margin should be allocated to compensate for probing inaccuracies.

In this paper, we develop spectral and post-spectral estimators for grouped panel data models. Both estimators are consistent in the asymptotics where the number of observations $N$ and the number of time periods $T$ simultaneously grow large. In addition, the post-spectral estimator is $\sqrt{NT}$-consistent and asymptotically normal with mean zero under the assumption of well-separated groups even if $T$ is growing much slower than $N$. The post-spectral estimator has, therefore, theoretical properties that are comparable to those of the grouped fixed-effect estimator developed by Bonhomme and Manresa (2015). In contrast to the grouped fixed-effect estimator, however, our post-spectral estimator is computationally straightforward., Comment: 61 pages

We demonstrate a machine learning-based optical network monitoring system which can integrate fiber monitoring, predictive maintenance of optical hardware, and security information management in a single solution.

Predictive algorithms have a powerful potential to offer benefits in areas as varied as medicine or education. However, these algorithms and the data they use are built by humans, consequently, they can inherit the bias and prejudices present in humans. The outcomes can systematically repeat errors that create unfair results, which can even lead to situations of discrimination (e.g. gender, social or racial). In order to illustrate how important is to count with a diverse training dataset to avoid bias, we manipulate a well-known facial expression recognition dataset to explore gender bias and discuss its implications.

The H2020 METRO-HAUL European project has architected a latency-aware, cost-effective, agile, and programmable optical metro network. This includes the design of semidisaggregated metro nodes with compute and storage capabilities, which interface effectively with both 5G access and multi-Tbit/s elastic optical networks in the core. In this paper, we report the automated deployment of 5G services, in particular, a public safety video surveillance use case employing low-latency object detection and tracking using on-camera and on-the-edge analytics. The demonstration features flexible deployment of network slice instances, implemented in terms of European Telecommunications Standards Institute (ETSI) network function virtualization network services. We summarize the key findings in a detailed analysis of end-to-end quality of service, service setup time, and soft-failure detection time. The results show that the round-trip time over an 80 km link is under 800s and the service deployment time is under 180s., Comment: 10 pages

We report the automated deployment of 5G services across a latency-aware, semidisaggregated, and virtualized metro network. We summarize the key findings in a detailed analysis of end-to-end latency, service setup time, and soft-failure detection time., Comment: The research leading to these results has received funding from the EC and BMBF through the METRO-HAUL project (G.A. No. 761727) and OTB-5G+ project (reference No. 16KIS0979K)

We study discrete panel data methods where unobserved heterogeneity is revealed in a first step, in environments where population heterogeneity is not discrete. We focus on two-step grouped fixed-effects (GFE) estimators, where individuals are first classified into groups using kmeans clustering, and the model is then estimated allowing for group-specific heterogeneity. Our framework relies on two key properties: heterogeneity is a function - possibly nonlinear and time-varying - of a low-dimensional continuous latent type, and informative moments are available for classification. We illustrate the method in a model of wages and labor market participation, and in a probit model with time-varying heterogeneity. We derive asymptotic expansions of two-step GFE estimators as the number of groups grows with the two dimensions of the panel. We propose a data-driven rule for the number of groups, and discuss bias reduction and inference.

We propose a new simulation-based estimation method, adversarial estimation, for structural models. The estimator is formulated as the solution to a minimax problem between a generator (which generates simulated observations using the structural model) and a discriminator (which classifies whether an observation is simulated). The discriminator maximizes the accuracy of its classification while the generator minimizes it. We show that, with a sufficiently rich discriminator, the adversarial estimator attains parametric efficiency under correct specification and the parametric rate under misspecification. We advocate the use of a neural network as a discriminator that can exploit adaptivity properties and attain fast rates of convergence. We apply our method to the elderly's saving decision model and show that our estimator uncovers the bequest motive as an important source of saving across the wealth distribution, not only for the rich., Comment: 56 pages, 3 tables, 11 figures