Jean-Charles Grégoire

Nasif Muslim, Jean-Charles Grégoire

Consent-Based Access Control (CBAC) is a foundational mechanism for enforcing patient autonomy in modern healthcare information systems. Many CBAC frameworks are built on the eXtensible Access Control Markup Language (XACML) and inherit its \emph{lazy evaluation} model, in which policy interactions are resolved only at request time. This design allows contradictory consent directives to accumulate within the repository, creating a semantic gap between patient intent and system behavior while burdening high-frequency runtime decisions with complex conflict resolution. This paper presents an extended CBAC framework that enforces semantic correctness at consent creation time rather than during access evaluation. The framework introduces a pre-commit validation workflow centered on a Consent Conflict Analysis Module (CCAM), which proactively detects modality conflicts and redundancies before directives become active. In addition, immutable system invariants are formalized to guarantee baseline access for record authors and patients, preserving clinical continuity and professional accountability. Finally, the framework incorporates a context-aware emergency mediation mechanism that enables controlled \emph{break-the-glass} access driven by real-time physiological evidence, with disclosure strictly bounded by an Emergency Disclosure Control Function (EDCF). Simulation-based evaluation using controlled synthetic workloads demonstrates that pre-commit conflict resolution yields low and stable runtime decision latency and consistently outperforms standard XACML-based baselines as policy repositories scale. Emergency access experiments further demonstrate strong restrictions on data access, pruning the majority of non-relevant record elements while preserving clinically essential information.

Nasif Muslim, Jean-Charles Grégoire

Effective healthcare delivery depends on accurate longitudinal health records and addressing patients' concerns regarding the privacy of their information. While patient authentication is essential, reusing patient identifiers exposes individuals to linkability (associating multiple visits) and traceability (tying visits to real-world identities) risks. This paper presents a privacy-preserving, patient-centric identity management framework specifically tailored to the operational and regulatory requirements of healthcare. The framework balances operational reliability with strong privacy protections through a rooted trust anchor, anonymous pseudonyms, and a conditional traceability mechanism. It is formally specified, and its security and privacy properties are evaluated through MSRA-based architectural analysis and complementary formal verification. Simulation-based evaluation demonstrates that the framework's identity workflows are operationally feasible within the latency bounds typical of clinical environments.

Edip Demirbilek, Jean-Charles Grégoire

Our objective is to build machine learning based models that predict audiovisual quality directly from a set of correlated parameters that are extracted from a target quality dataset. We have used the bitstream version of the INRS audiovisual quality dataset that reflects contemporary real-time configurations for video frame rate, video quantization, noise reduction parameters and network packet loss rate. We have utilized this dataset to build bitstream perceived quality estimation models based on the Random Forests, Bagging, Deep Learning and Genetic Programming methods. We have taken an empirical approach and have generated models varying from very simple to the most complex depending on the number of features used from the quality dataset. Random Forests and Bagging models have overall generated the most accurate results in terms of RMSE and Pearson correlation coefficient values. Deep Learning and Genetic Programming based bitstream models have also achieved good results but that high performance was observed only with a limited range of features. We have also obtained the epsilon-insensitive RMSE values for each model and have computed the significance of the difference between the correlation coefficients. Overall we conclude that computing the bitstream information is worth the effort it takes to generate and helps to build more accurate models for real-time communications. However, it is useful only for the deployment of the right algorithms with the carefully selected subset of the features. The dataset and tools that have been developed during this research are publicly available for research and development purposes.

Edip Demirbilek, Jean-Charles Grégoire

We make an intensive use of multimedia frameworks in our research on modeling the perceived quality estimation in streaming services and real-time communications. In our preliminary work, we have used the VLC VOD software to generate reference audiovisual files with various degree of coding and network degradations. We have successfully built machine learning based models on the subjective quality dataset we have generated using these files. However, imperfections in the dataset introduced by the multimedia framework we have used prevented us from achieving the full potential of these models. In order to develop better models, we have re-created our end-to-end multimedia pipeline using the GStreamer framework for audio and video streaming. A GStreamer based pipeline proved to be significantly more robust to network degradations than the VLC VOD framework and allowed us to stream a video flow at a loss rate up to 5\% packet very easily. GStreamer has also enabled us to collect the relevant RTCP statistics that proved to be more accurate than network-deduced information. This dataset is free to the public. The accuracy of the statistics eventually helped us to generate better performing perceived quality estimation models. In this paper, we present the implementation of these VLC and GStreamer-based multimedia communication quality assessment testbeds with the references to their publicly available code bases.

Edip Demirbilek, Jean-Charles Grégoire

We have developed reduced reference parametric models for estimating perceived quality in audiovisual multimedia services. We have created 144 unique configurations for audiovisual content including various application and network parameters such as bitrates and distortions in terms of bandwidth, packet loss rate and jitter. To generate the data needed for model training and validation we have tasked 24 subjects, in a controlled environment, to rate the overall audiovisual quality on the absolute category rating (ACR) 5-level quality scale. We have developed models using Random Forest and Neural Network based machine learning methods in order to estimate Mean Opinion Scores (MOS) values. We have used information retrieved from the packet headers and side information provided as network parameters for model training. Random Forest based models have performed better in terms of Root Mean Square Error (RMSE) and Pearson correlation coefficient. The side information proved to be very effective in developing the model. We have found that, while the model performance might be improved by replacing the side information with more accurate bit stream level measurements, they are performing well in estimating perceived quality in audiovisual multimedia services.