@article{ma2022privacy,
  title={Privacy-preserving federated learning based on multi-key homomorphic encryption},
  author={Ma, Jing and Naas, Si-Ahmed and Sigg, Stephan and Lyu, Xixiang},
  journal={International Journal of Intelligent Systems},
  year={2022},
  publisher={Wiley Online Library},
  group = {ambience}
}

@inproceedings{hitz2020Emotion,
  title={Sharing geotagged pictures for an Emotion-based Recommender System},
  author={Andreas Hitz and Si-Ahmed Naas and Stephan Sigg},
  booktitle={The 19th International Conference on Pervasive Computing and Communications (PerCom 2021), adjunct},
  year={2021},
  abstract={Recommender systems are prominently used for movie or app recommendation or in e-commerce by considering profiles, past preferences and increasingly also further personalized measures. We designed and implemented an emotion-based recommender system for city visitors that takes into account user emotion and user location for the recommendation process. We conducted a comparative study between the emotion-based recommender system and recommender systems based on traditional measures. Our evaluation study involved 28 participators and the experiments showed that the emotion-based recommender system increased the average rating of the recommendation by almost 19%. We conclude that the use of emotion can significantly improve the results and especially their level of personalization.
},
  group = {ambience}
}


%%% 2020 %%%

Recommender systems are prominently used for movie or app recommendation or in e-commerce by considering profiles, past preferences and increasingly also further personalized measures. We designed and implemented an emotion-based recommender system for city visitors that takes into account user emotion and user location for the recommendation process. We conducted a comparative study between the emotion-based recommender system and recommender systems based on traditional measures. Our evaluation study involved 28 participators and the experiments showed that the emotion-based recommender system increased the average rating of the recommendation by almost 19%. We conclude that the use of emotion can significantly improve the results and especially their level of personalization.

@inproceedings{naas2020global,
  title={A Global Brain fuelled by Local intelligence: Optimizing Mobile Services and Networks with AI},
  author={Naas, Si-Ahmed and Mohammed, Thaha and Sigg, Stephan},
  booktitle={2020 16th International Conference on Mobility, Sensing and Networking (MSN)},
  pages={23--32},
  year={2020},
  organization={IEEE},
  group={ambience}
}

@inproceedings{Ahmed2020gaze,
  title={Functional Gaze Prediction in Egocentric Video},
  author={Si Ahmed Naas and Xiaolan Jiang and Stephan Sigg and Yusheng Ji},
  booktitle={18th International Conference on Advances in Mobile Computing and Multimedia (MoMM2020)},
  year={2020},
  group = {ambience}
}

@inproceedings{naas2020GlobalBrain,
  title={A Global Brain fuelled by Local intelligence Optimizing Mobile Services and Networks with AI},
  author={Si Ahmed Naas and Thaha Mohammed and Stephan Sigg},
  booktitle={16th International Conference on Mobility, Sensing and Networking (MSN 2020) },
  year={2020},
  group = {ambience}
}

@inproceedings{naas2020RealTime,
  title={Real-time Emotion Recognition for Sales},
  author={Si Ahmed Naas and Stephan Sigg},
  booktitle={16th International Conference on Mobility, Sensing and Networking (MSN 2020) },
  year={2020},
  group = {ambience}
}

@article{Chiang_2020_Viewpoint,
author={Xiaolan Jiang and Si Ahmed Naas and Yi-Han Chiang and Stephan Sigg and Yusheng Ji},
journal={IEEE Access},
title={SVP: Sinusoidal Viewport Predictionfor 360-Degree Video Streaming},
year={2020},
abstract={The rapid growth of user expectations and network technologies has proliferated the service needs of 360-degree video streaming. In the light of the unprecedented bitrates required to deliver entire 360-degree videos, tile-based streaming, which associates viewport and non-viewport tiles with different qualities,  has emerged as a promising way to facilitate 360-degree video streaming in practice. Existing work on viewport prediction primarily targets prediction accuracy, which potentially gives rise to excessive computational overhead and latency. In this paper, we propose a sinusoidal viewport prediction (SVP) system for 360-degree video streaming to overcome the aforementioned issues. In particular, the SVP system leverages 1) sinusoidal values of rotation angles to predict orientation, 2) the relationship between prediction errors, prediction time window and head movement velocities to improve the prediction accuracy, and 3) the normalized viewing probabilities of tiles to further improve adaptive bitrate (ABR) streaming performance. To evaluate the performance of the SVP system, we conduct extensive simulations based on real-world datasets. Simulation results demonstrate that the SVP system outperforms state-of-the-art schemes under various buffer thresholds and bandwidth settings in terms of viewport prediction accuracy and video quality, revealing its applicability to both live and video-on-demand streaming in practical scenarios.},
group = {ambience}, 
volume = {8},
doi = {10.1109/ACCESS.2020.3022062}
}

The rapid growth of user expectations and network technologies has proliferated the service needs of 360-degree video streaming. In the light of the unprecedented bitrates required to deliver entire 360-degree videos, tile-based streaming, which associates viewport and non-viewport tiles with different qualities, has emerged as a promising way to facilitate 360-degree video streaming in practice. Existing work on viewport prediction primarily targets prediction accuracy, which potentially gives rise to excessive computational overhead and latency. In this paper, we propose a sinusoidal viewport prediction (SVP) system for 360-degree video streaming to overcome the aforementioned issues. In particular, the SVP system leverages 1) sinusoidal values of rotation angles to predict orientation, 2) the relationship between prediction errors, prediction time window and head movement velocities to improve the prediction accuracy, and 3) the normalized viewing probabilities of tiles to further improve adaptive bitrate (ABR) streaming performance. To evaluate the performance of the SVP system, we conduct extensive simulations based on real-world datasets. Simulation results demonstrate that the SVP system outperforms state-of-the-art schemes under various buffer thresholds and bandwidth settings in terms of viewport prediction accuracy and video quality, revealing its applicability to both live and video-on-demand streaming in practical scenarios.