Search

An efficient backend solution is of great importance for any large-scale system, and Smittestopp is no exception. The Smittestopp backend comprises various components for user and device registration, mobile app data ingestion, database and cloud operations, and web interface support. This chapter describes our journey from a vague idea to a deployed system. We provide an overview of the system internals and design iterations and discuss the challenges that we faced during the development process, along with the lessons learned. The Smittestopp backend handled around 1.5 million registered devices and provided various insights and analyses before being discontinued a few months after its launch.

Professional sports achievements combine not only the individual physical abilities of athletes but also many modern technologies in areas such as medicine, equipment production, nutrition, and physical and mental health monitoring. In this work, we address the problem of predicting soccer players’ ability to perform, from subjective self-reported wellness parameters collected using a commercially deployed digital health monitoring system called PmSys. We use 2 years of data from two Norwegian female soccer teams, where players have reported daily ratings for their readiness-to-play, mood, stress, general muscle soreness, fatigue, sleep quality, and sleep duration. We explore various time series models with the goal of predicting readiness, employing both a univariate approach and a multivariate approach. We provide an experimental comparison of different time series models, such as purely recurrent models, models of mixed recursive convolutional types, ensemble of deep CNN models, and multivariate versions of the recurrent models, in terms of prediction performance, with a focus on detecting peaks. We use different input and prediction windows to compare the accuracy of next-day predictions and next-week predictions. We also investigate the potential of using models built on data from the whole team for making predictions about individual players, as compared to using models built on the data from the individual player only. We tackle the missing data problem by various methods, including the replacement of all gaps with zeros, filling in repeated values, as well as removing all gaps and concatenating arrays. Our case study on athlete monitoring shows that a number of time series analysis models are able to predict readiness with high accuracy in near real-time. Equipped with such insight, coaches and trainers can better plan individual and team training sessions, and perhaps avoid over training and injuries.

Blind natural video quality assessment (BVQA), also known as no-reference video quality assessment, is a highly active research topic. In our recent contribution titled "Blind Natural Video Quality Prediction via Statistical Temporal Features and Deep Spatial Features" published in ACM Multimedia 2020, we proposed a two-level video quality model employing statistical temporal features and spatial features extracted by a deep convolutional neural network (CNN) for this purpose. At the time of publishing, the proposed model (CNN-TLVQM) achieved state-of-the-art results in BVQA. In this paper, we describe the process of reproducing the published results by using CNN-TLVQM on two publicly available natural video quality datasets.

This companion paper is to support the replication of paper "Campus3D: A Photogrammetry Point Cloud Benchmark for Outdoor Scene Hierarchical Understanding", which was presented at ACM Multimedia 2020. The supported paper's main purpose was to provide a photogrammetry point cloud-based dataset with hierarchical multilabels to facilitate the area of 3D deep learning. Based on this provided dataset and source code, in this work, we build a complete package to reimplement the proposed methods and experiments (i.e., the hierarchical learning framework and the benchmarks of the hierarchical semantic segmentation task). Specifically, this paper contains the technical details of the package, including file structure, dataset preparation, installation package, and the conduction of the experiment. We also present the replicated experiment results and indicate our contributions to the original implementation.

Electronic version of an article published as International Journal of Semantic Computing, 15(2), 161-187 (2021) https://doi.org/10.1142/S1793351X2140002X. © Copyright World Scientific Publishing Company https://www.worldscientific.com/worldscinet/ijsc. Developing systems for the automatic detection of events in video is a task which has gained attention in many areas including sports. More specifically, event detection for soccer videos has been studied widely in the literature. However, there are still a number of shortcomings in the state-of-the-art such as high latency, making it challenging to operate at the live edge. In this paper, we present an algorithm to detect events in soccer videos in real time, using 3D convolutional neural networks. We test our algorithm on three different datasets from SoccerNet, the Swedish Allsvenskan, and the Norwegian Eliteserien. Overall, the results show that we can detect events with high recall, low latency, and accurate time estimation. The trade-off is a slightly lower precision compared to the current state-of-the-art, which has higher latency and performs better when a less accurate time estimation can be accepted. In addition to the presented algorithm, we perform an extensive ablation study on how the different parts of the training pipeline affect the final results.

COVID-19 has changed our lives and continues to have a drastic impact. It forces us to impose restrictive social distancing measures and leads us to rely more on the Internet. Mobile networks become one of the major means to access the Internet for most of us. We investigate the performance of 9 mobile networks in Europe around the time when restrictions were imposed, considering web QoE, throughput, RTT, and signal coverage. Our results show countries' mobile networks are impacted by COVID-19 (as high as 46 % increase in page load time) at different times based on the outbreak timelines in these countries. Moreover, we find that operators responded properly and the network performance is back to the pre-COVID-19 times.

Mobile networks have become ubiquitous and the primary means to access the Internet, and the traffic they generate has rapidly increased over the last years. The technology and service diversity in mobile networks call for extensive and accurate measurements to ensure the proper functioning of the networks and rapidly spot impairments. However, the measurement of mobile networks is complicated by their scale, and, thus, expensive, especially due to the diversity of deployments, technologies, and web services. In this paper, we present and provide access to the largest open international mobile network dataset collected using the MONROE platform spanning six countries, 27 mobile network operators, and 120 measurement nodes. We use them to run measurements targeting several web services from January 2018 to December 2019, collecting millions of TCP and UDP flows using these commercial mobile networks. We illustrate the data collection platforms and describe some of the main experiments. Besides a high-level overview of the dataset, we provide two practical use cases. First, we show how our data can be used as a proxy for web service performance. Second, we study the content delivery infrastructure of Facebook.

Video streaming is one of the top traffic contributors in the Internet and a frequent research subject. It is expected that streaming traffic will grow 4-fold for video globally and 9-fold for mobile video between 2017 and 2022. In this paper, we present an automatized measurement framework for evaluating video streaming QoE in operational broadband networks, using headless streaming with a Docker-based client, and a server-side implementation allowing for the use of multiple video players and adaptation algorithms. Our framework allows for integration with the acsMONROE testbed and Bitmovin Analytics, which bring on the possibility to conduct large-scale measurements in different networks, including mobility scenarios, and monitor different parameters in the application, transport, network, and physical layers in real-time.

We propose a QoE-based analysis approach for real-time adaptive 360-degree video streaming measurements, focusing on the correlation between objective video metrics and subjective end-user scores.

In this article we present a selection from a vast range of experiments run with MONROE, our open experiment as a service (EaaS) platform for measurements and experimentation in Mobile Broadband Networks. We show that the plat- form can be used to benchmark network performance in a repeatable and con- trolled manner thanks to the collection of a rich set of geotagged metadata and the execution of discretionary user experiments. Indeed, with the sheer amount of data collected from 12 commercial mobile operators across Europe, MON- ROE offers an unprecedented opportunity to monitor, analyze and ultimately improve the status of current and future mobile broadband networks. Besides, we show how flexibly the platform allows combining metadata and experimental data series during the experiments or by means of post-processing, and show results produced by our own experiments as well as comment on results obtained by external research groups and developers that have been granted access to our platform. pub

Characterizing and evaluating the performance of Mobile Broadband (MBB) networks is a vital need for today’s societies. Testbed-based measurements are of great significance in this context, since they allow for controlled and longitudinal experimentation. In this work, we focus on “speed” as an important Quality of Service (QoS) indicator for MBB networks, and work with MONROE-Nettest, an open source speedtest tool running as an Experiment as a Service (EaaS) on the Measuring Mobile Broadband Networks in Europe (MONROE) testbed. We conduct an extensive longitudinal measurement campaign spanning 2 countries over 2 years, and provide our experiment results together with rich metadata as an open dataset. We characterize this open dataset in detail, as well as derive insights from it regarding the impact of network context, spatio-temporal effects, roaming, and mobility on network performance. We describe our experiences about conducting speedtest measurements in MBB, and discuss the challenges associated with large scale testbed experimentation in operational MBB networks. Tackling one of the said challenges further, we introduce the notion of adaptive speedtest duration, and leverage a Machine Learning (ML) based algorithm to provide a proof-of-concept implementation called “Speedtest++”. Finally, we describe the lessons we have learned, as well as provide an overall discussion of how open datasets can support MBB research, and comment on open challenges, in the hope that these can serve as discussion points for future work.