Thomas Peter Plagemann

• Gu, He; Plagemann, Thomas Peter & Goebel, Vera Hermine (2026). A Seed for Privacy - semi-automatic privacy-revealing data detection in databases and data streams. In Lofstead, Jay & Kirkpatrick, Christine (Ed.), Proceedings of the 38th International Conference on Scalable Scientific Data Management. Association for Computing Machinery (ACM). ISSN 9798400727085. p. 1–12. doi: 10.1145/3828820.3828821. Full text in Research Archive Show summary

  Sharing databases and data streams imposes the danger of revealing private information in the form of complex events which can comprise individual data elements and their combinations. Identifying these privacy-revealing complex events is crucial for preserving privacy while maintaining data utility. However, data producers often lack the expertise to comprehensively identify these events, which undermines many state-of-the-art privacy-preserving mechanisms that rely on accurate event labeling. To address this challenge, we developed pArborist - a tool that can semi-automatically create a set of queries to identify and label privacy-revealing complex events in both static datasets and dynamic data streams, guided by the privacy requirements of the data producer. pArborist uses the schema of the database or data stream combined with initial input from the data producer, i.e., seed queries. From each seed query, pArborist grows a tree containing all possible syntactically correct queries, constrained by an upper limit on computational resources. Following this growing phase, the tree is refined by eliminating queries that lack correlation to the seed or are conditionally independent of the seed. Our evaluation indicates that pArborist achieves overall recall of 90% and precision of 93% in finding privacy-revealing queries, and this significantly surpasses the state-of-the-art approach FQID. In data stream processing experiments, pArborist introduces a delay of approximately 1.3 ms following an average warm-up period of 920 ms. The experiments also show that pArborist can automatically detect privacy-revealing complex events according to GDPR.

• Lopez, Marta Quemada; Plagemann, Thomas Peter; Goebel, Vera Hermine; Adams, Jonathan; Hui, David & Øverland, Britt [Show all 8 contributors for this article] (2024). Requirements Analysis for Responsible Explainable AI for Pediatric Sleep Apnea Diagnosis. In Pesch, Dirk (Eds.), Proceeding IEEE International Conference on Smart Computing 2024. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798350349948. p. 362–367. doi: 10.1109/SMARTCOMP61445.2024.00082. Full text in Research Archive Show summary

  This paper presents a novel approach to requirements engineering for responsible explainable AI (rexAI) that pays attention to the broad range of explanation aspects and enforces the consideration of computer science, ethical, legal, and medical requirements. The medical use-case we are investigating is pediatric sleep apnea diagnosis. We analyze the non-functional and functional requirements and explore the multiple relationships and dependencies between the rexAI requirements and principles.

• Gu, He; Plagemann, Thomas Peter; Goebel, Vera Hermine; Benndorf, Maik & Koldehofe, Boris (2023). Differential Privacy for Protecting Private Patterns in Data Streams. In O´Connor, Lisa (Eds.), 2023 IEEE 39th International Conference on Data Engineering Workshops (ICDEW). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9798350322446. p. 118–124. doi: 10.1109/ICDEW58674.2023.00025. Full text in Research Archive Show summary

  Complex event processing (CEP) is a powerful and increasingly more important tool to analyse data streams for Internet of Things (IoT) applications. These data streams often contain private information that requires proper protection. However, privacy protection in CEP systems is still in its infancy, and most existing privacy-preserving mechanisms (PPMs) are adopted from those designed for data streams. Such approaches undermine the quality of the entire data stream and limit the performance of IoT applications. In this paper, we attempt to break the limitation and establish a new foundation for PPMs of CEP by proposing a novel pattern-level differential privacy (DP) guarantee. We introduce two PPMs that guarantee pattern-level DP. They operate only on data that correlate with private patterns rather than on the entire data stream, leading to higher data quality. One of the PPMs provides adaptive privacy protection and brings more granularity and generalization. We evaluate the performance of the proposed PPMs with two experiments on a real-world dataset and on a synthetic dataset. The results of the experiments indicate that our proposed privacy guarantee and its PPMs can deliver better data quality under equally strong privacy guarantees, compared to multiple well-known PPMs designed for data streams.

• Volnes, Espen; Plagemann, Thomas Peter & Goebel, Vera Hermine (2023). To Migrate or Not to Migrate: An Analysis of Operator Migration in Distributed Stream Processing. IEEE Communications Surveys and Tutorials. 26(1), p. 670–705. doi: 10.1109/COMST.2023.3330953. Full text in Research Archive Show summary

  One of the most important issues in distributed data stream processing systems is using operator migration to handle highly variable workloads cost-efficiently and adapt to the needs at any given time on demand. Operator migration is a complex process involving changes in the state and stream management of a running query, typically without any data loss, and with as little disruption to the execution as possible. This tutorial aims to introduce operator migration, explain the core elements of operator migration, and provide the reader with a good understanding of the design alternatives used in existing solutions. We developed a conceptual model to explain the fundamentals of operator migration and introduce a unified terminology, leading to a taxonomy of existing solutions. The conceptual model separates mechanisms, i.e., how to migrate, and policy, i.e., when to migrate. This separation is further applied to structure the description of existing solutions, offering the reader an algorithmic perspective on various design alternatives. To enhance our understanding of the impact of various design alternatives on migration mechanisms, we also conducted an empirical study that provides quantitative insights. The operator downtime for the naïve migration approach is almost 20 times longer than when applying an incremental checkpoint-based approach.

• Kristiansen, Stein; Nikolaidis, Konstantinos; Plagemann, Thomas Peter; Goebel, Vera Hermine; Traaen, Gunn Marit & Øverland, Britt [Show all 14 contributors for this article] (2023). A clinical evaluation of a low-cost strain gauge respiration belt and machine learning to detect sleep apnea. Smart Health. ISSN 2352-6483. 27. doi: 10.1016/j.smhl.2023.100373. Full text in Research Archive Show summary

  Sleep apnea is a common and severe sleep-related respiratory disorder. Since the symptoms of sleep apnea are often ambiguous, it is difficult for a physician to decide whether to prescribe a clinical diagnosis, i.e., polysomnography (PSG), which results in a large percentage of undiagnosed and very late diagnosed cases. To reduce the time to diagnosis we investigate whether sleep monitoring data collected with a low-cost strain gauge respiration belt (called Flow) and a smartphone can be used to estimate with machine learning (ML) the severity of a patient’s sleep apnea. The Flow belt and the Type III sleep monitor Nox T3 were used together by 29 patients for unattended sleep monitoring at home, resulting each in 235 hours of sleep data. Through experimental analysis, we found that Convolutional Neural Networks are best suited to analyze the Flow data, because they are most robust against the frequently occurring baseline issues and exhibit the best performance with an accuracy of 0.7609, sensitivity of 0.7833, and specificity of 0.7217. These results can be achieved even if the classifier is trained only on high-quality data from the Nox T3. Thus, there are good chances that future ML experiments with data from other low-cost respiration belts can benefit from existing open PSG datasets without new extensive data collection. On a low-end smartphone, the classifier needs approximately one second to analyze the sleep data from one night. The results demonstrate the potential of low-cost strain gauge belts, smartphones, and ML to enable large parts of the population to perform sleep apnea pre-screening at home.

• Volnes, Espen; Plagemann, Thomas Peter; Boris, Koldehofe & Goebel, Vera Hermine (2022). Travel light: state shedding for efficient operator migration. In Yonghuan, Zhou (Eds.), DEBS '22: Proceedings of the 16th ACM International Conference on Distributed and Event-Based Systems. Association for Computing Machinery (ACM). ISSN 9781450393089. p. 79–84. doi: 10.1145/3524860.3539638. Full text in Research Archive Show summary

  Operator migration is a crucial concept to adapt event pro- cessing systems to dynamic changes. When the placement of a stateful operator changes, the operator state must be migrated to the new host. However, operator state size and time constraints can make it impossible to migrate the op- erator without severe Quality of Service (QoS) degradation. As a relief, we propose to perform state shedding in such a situation. The core idea of state shedding is to partition the operator state, assign a utility to each partial state, and use the utility and size of each partial state to identify the most useful partial states that can be migrated in a given time frame. Thus, state shedding can maintain a substantially higher QoS with a lower impact on query results than state- of-the-art solutions targeting consistent state at the old and new host. In this paper, we define this novel approach and in a simulation environment evaluate state shedding in migration scenarios with pattern-matching queries.

• Nikolaidis, Konstantinos; Kristiansen, Stein; Plagemann, Thomas Peter; Goebel, Vera Hermine; Liestøl, Knut & Kankanhalli, Mohan [Show all 11 contributors for this article] (2022). Learning Realistic Patterns from Visually Unrealistic Stimuli: Generalization and Data Anonymization (Extended Abstract). In Raed, Luc de (Eds.), Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence. AAAI Press. ISSN 9781956792003. p. 5762–5766. doi: 10.24963/ijcai.2022/806. Full text in Research Archive Show summary

  Good training data is a prerequisite to develop useful Machine Learning applications. However, in many domains existing data sets cannot be shared due to privacy regulations (e.g., from medical studies). This work investigates a simple yet unconventional approach for anonymized data synthesis to enable third parties to benefit from such anonymized data. We explore the feasibility of learning implicitly from visually unrealistic, task-relevant stimuli, which are synthesized by exciting the neurons of a trained deep neural network. As such, neuronal excitation can be used to generate synthetic stimuli. The stimuli data is used to train new classification models. Furthermore, we extend this framework to inhibit representations that are associated with specific individuals. Extensive comparative empirical investigation shows that different algorithms trained on the stimuli are able to generalize successfully on the same task as the original model.

• Nikolaidis, Konstantinos; Kristiansen, Stein; Plagemann, Thomas Peter; Goebel, Vera Hermine; Liestøl, Knut & Kankanhalli, Mohan [Show all 11 contributors for this article] (2022). My Health Sensor, My Classifier - Adapting a Trained Classifier to Unlabeled End-User Data. ACM Transactions on Computing for Healthcare (HEALTH). ISSN 2691-1957. 3(4), p. 1–24. doi: 10.1145/3559767. Full text in Research Archive Show summary

  Sleep apnea is a common yet severely under-diagnosed sleep related disorder. Unattended sleep monitoring at home with low-cost sensors can be leveraged for condition detection, and Machine Learning offers a generalized solution for this task. However, patient characteristics, lack of sufficient training data, and other factors can imply a domain shift between training and end-user data; and reduced task performance. In this work, we address this issue with the aim to achieve personalization based on the patient’s needs. We present an unsupervised domain adaptation (UDA) solution with the constraint that labeled source data are not directly available. Instead, a classifier trained on the source data is provided. Our solution iteratively labels target data sub-regions based on classifier beliefs, and trains new classifiers from the expanding dataset. Experiments with sleep monitoring datasets and various sensors show that our solution outperforms the classifier trained on the source domain, with a kappa coefficient improvement from 0.012 to 0.242. Additionally, we apply our solution to digit classification DA between three well-established datasets, to investigate its generalizability, and allow for related work comparisons. Even without direct access to the source data, it outperforms several well-established UDA methods in these datasets.

• Lindeberg, Morten Gunnar Bjørner & Plagemann, Thomas Peter (2022). A Study on Migration Scheduling in Distributed Stream Processing Engines, ICDCN '22: Proceedings of the 23rd International Conference on Distributed Computing and Networking. Association for Computing Machinery (ACM). ISSN 9781450395601. p. 50–61. doi: 10.1145/3491003.3491008. Full text in Research Archive
• Nikolaidis, Konstantinos; Plagemann, Thomas Peter; Kristiansen, Stein; Goebel, Vera Hermine & Kankanhalli, Mohan (2021). Using Under-Trained Deep Ensembles to Learn Under Extreme Label Noise: A Case Study for Sleep Apnea Detection. IEEE Access. 9, p. 45919–45934. doi: 10.1109/ACCESS.2021.3067455. Full text in Research Archive Show summary

  Improper or erroneous labelling can pose a hindrance to reliable generalization for supervised learning. This can have negative consequences, especially for critical fields such as healthcare. We propose an effective new approach for learning under extreme label noise for medical applications like sleep apnea, that is based on under-trained deep ensembles. Each ensemble member is trained with a subset of the training data, to acquire a general overview of the decision boundary separation, without focusing on potentially erroneous details. The accumulated knowledge of the ensemble is combined to form new labels, that determine a better class separation than the original labels. A new model is trained with these labels to generalize reliably despite the label noise. We evaluate our approach on the tasks of sleep apnea detection and sleep apnea severity classification, and observe performance improvement in kappa from 0.02 up-to 0.55.

• Kristiansen, Stein; Nikolaidis, Konstantinos; Plagemann, Thomas Peter; Goebel, Vera Hermine; Traaen, Gunn Marit & Øverland, Britt [Show all 14 contributors for this article] (2021). Machine learning for sleep apnea detection with unattended sleep monitoring at home. ACM Transactions on Computing for Healthcare (HEALTH). ISSN 2691-1957. 2(2). doi: 10.1145/3433987. Full text in Research Archive Show summary

  Sleep apnea is a common and strongly under-diagnosed severe sleep-related respiratory disorder with periods of disrupted or reduced breathing during sleep. To diagnose sleep apnea, sleep data are collected with either polysomnography or polygraphy and scored by a sleep expert. We investigate in this work the use of supervised machine learning to automate the analysis of polygraphy data from the A3 study containing more than 7,400 hours of sleep monitoring data from 579 patients. We conduct a systematic comparative study of classification performance and resource use with different combinations of 27 classifiers and four sleep signals. The classifiers achieve up to 0.8941 accuracy (kappa: 0.7877) when using all four signal types simultaneously and up to 0.8543 accuracy (kappa: 0.7080) with only one signal, i.e., oxygen saturation. Methods based on deep learning outperform other methods by a large margin. All deep learning methods achieve nearly the same maximum classification performance even when they have very different architectures and sizes. When jointly accounting for classification performance, resource consumption and the ability to achieve with less training data high classification performance, we find that convolutional neural networks substantially outperform the other classifiers.

• Kristiansen, Stein; Goebel, Vera Hermine; Andersen, Morten Hamborg; Plagemann, Thomas Peter; Traaen, Gunn Marit & Øverland, Britt [Show all 8 contributors for this article] (2021). Evaluating a Low-Cost Strain Gauge Breathing Sensor for Sleep Apnea Detection at Home. In Gedeon, Ibrahim (Eds.), 2021 IEEE International Conference on Communications Workshops (ICC Workshops). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781728194417. doi: 10.1109/ICCWorkshops50388.2021.9473597. Full text in Research Archive Show summary

  We report results and experience from a clinical evaluation of a low-cost strain gauge breathing sensor for sleep apnea detection. We collected from 34 individuals 57 nights of unattended sleep monitoring data at home with the certified Type 3 monitor Nox-T3 and the Flow strain gauge sensor from SweetZpot. The quality of the Flow data does not match the quality of the Nox-T3 data due to the much simpler build of the Flow sensor and issues during data acquisition. The Flow data can still be used to accurately discriminate between normal and disrupted breathing. With appropriate data pre-processing, we achieve a mean breath detection sensitivity of 97.2% and positive prediction value of 94.2%.

• Volnes, Espen; Plagemann, Thomas Peter; Goebel, Vera Hermine & Kristiansen, Stein (2021). EXPOSE: Experimental Performance Evaluation of Stream Processing Engines Made Easy. In Nambiar, Raghunath (Eds.), Performance Evaluation and Benchmarking 12th TPC Technology Conference. Springer. ISSN 9783030849245. p. 18–34. doi: 10.1007/978-3-030-84924-5_2. Full text in Research Archive Show summary

  Experimental performance evaluation of stream processing engines (SPE) can be a great challenge. Aiming to make fair comparisons of different SPEs raises this bar even higher. One important reason for this challenge is the fact that these systems often use concepts that require expert knowledge for each SPE. To address this issue, we present Expose, a distributed performance evaluation framework for SPEs that enables a user through a declarative approach to specify experiments and conduct them on multiple SPEs in a fair way and with low effort. Experimenters with few technical skills can define and execute distributed experiments that can easily be replicated. We demonstrate Expose by defining a set of experiments based on the existing NEXMark benchmark and conduct a performance evaluation of Flink, Beam with the Flink runner, Siddhi, T-Rex, and Esper, on powerful and resource-constrained hardware.

• Volnes, Espen; Kristiansen, Stein & Plagemann, Thomas Peter (2021). Improving the Accuracy of Timing in Scalable WSN Simulations with Communication Software Execution Models. Computer Networks. ISSN 1389-1286. 188. doi: 10.1016/j.comnet.2021.107855. Full text in Research Archive
• Nikolaidis, Konstantinos; Kristiansen, Stein; Plagemann, Thomas Peter; Goebel, Vera Hermine; Liestøl, Knut & Kankanhalli, Mohan [Show all 11 contributors for this article] (2021). Learning realistic patterns from visually unrealistic stimuli: Generalization and data anonymization. The journal of artificial intelligence research. ISSN 1076-9757. 72, p. 1163–1214. doi: 10.1613/JAIR.1.13252. Full text in Research Archive Show summary

  Good training data is a prerequisite to develop useful Machine Learning applications. However, in many domains existing data sets cannot be shared due to privacy regulations (e.g., from medical studies). This work investigates a simple yet unconventional approach for anonymized data synthesis to enable third parties to benefit from such anonymized data. We explore the feasibility of learning implicitly from visually unrealistic, task-relevant stimuli, which are synthesized by exciting the neurons of a trained deep neural network. As such, neuronal excitation can be used to generate synthetic stimuli. The stimuli data is used to train new classification models. Furthermore, we extend this framework to inhibit representations that are associated with specific individuals. We use sleep monitoring data from both an open and a large closed clinical study, and Electroencephalogram sleep stage classification data, to evaluate whether (1) end-users can create and successfully use customized classification models, and (2) the identity of participants in the study is protected. Extensive comparative empirical investigation shows that different algorithms trained on the stimuli are able to generalize successfully on the same task as the original model. Architectural and algorithmic similarity between new and original models play an important role in performance. For similar architectures, the performance is close to that of using the original data (e.g., Accuracy difference of 0.56%-3.82%, Kappa coefficient difference of 0.02-0.08). Further experiments show that the stimuli can provide state-ofthe-art resilience against adversarial association and membership inference attacks.

• Kristiansen, Stein; Traaen, Gunn Marit; Øverland, Britt; Plagemann, Thomas Peter; Gullestad, Lars & Akre, Harriet [Show all 14 contributors for this article] (2020). Comparing manual and automatic scoring of sleep monitoring data from portable polygraphy. Journal of Sleep Research. ISSN 0962-1105. doi: 10.1111/jsr.13036. Full text in Research Archive Show summary

  We used sleep monitoring data from a study that investigated the prevalence, characteristics, risk factors and type of sleep apnea (SA) in 579 patients with paroxysmal atrial fibrillation. Most patients were screened for two nights, resulting in 1,043 sleep recordings that each contained data from one night. SA was diagnosed using the Nox T3 portable sleep monitor. An experienced sleep specialist scored the recordings manually using Noxturnal software. A total of 157 women (27%) and 422 men (73%) were examined; 477 (82.7%) had an apnea–hypopnea index (AHI) ≥ 5/hr, whereas moderate to severe SA (AHI ≥ 15/hr) was diagnosed in 243 patients (42.1%). The AHI derived from automatic and manual scoring showed a good agreement (Pearson's r coefficient of 0.96). The median difference in AHI was very small (i.e., 0.72 [mean difference, 1.06]), but was statistically significant (p < .0001). Automatic scoring classified sleep recordings with more than 90% accuracy into SA categories of mild (AHI ≥ 5/hr), moderate (AHI ≥ 15/hr) and severe (AHI ≥ 30/hr). We found a minor (11%–21%) mis‐estimation of the number of recordings right above and below the boundary separating mild and moderate SA. The accuracy of automatic scoring differed from recording to recording, especially regarding the sensitivity of detecting disrupted breathing events. We found low to moderate agreement for the duration of disrupted breathing events (r = .53), for which the automatic scoring led to a statistically significant overestimation by 5.22 s (p < .0001).

• Nikolaidis, Konstantinos; Kristiansen, Stein; Goebel, Vera Hermine; Plagemann, Thomas Peter; Liestøl, Knut & Kankanhalli, Mohan (2020). Augmenting Physiological Time Series Data: A Case Study for Sleep Apnea Detection. In Koprinska, Irena (Eds.), Workshops of the European Conference on Machine Learning and Knowledge Discovery in Databases (ECML PKDD 2020): SoGood 2020, PDFL 2020, MLCS 2020, NFMCP 2020, DINA 2020, EDML 2020, XKDD 2020 and INRA 2020). Springer. ISSN 9783030659646. doi: 10.1007/978-3-030-46133-1_23. Full text in Research Archive
• Zgheib, Rita; Kristiansen, Stein; Conchon, Emmanuel; Plagemann, Thomas Peter; Goebel, Vera Hermine & Bastide, Rémi (2020). A scalable semantic framework for IoT healthcare applications. Journal of Ambient Intelligence and Humanized Computing. ISSN 1868-5137. doi: 10.1007/s12652-020-02136-2. Full text in Research Archive
• Dale, Øystein; Kristiansen, Stein; Plagemann, Thomas Peter & Volnes, Espen (2019). Many Cores and Still Delays: Simulating Multi-Core Communication Software Execution. In Beydoun, Ghassan (Eds.), Proceedings of The 11th International Conference on Computer Modeling and Simulation (ICCMS 2019). Association for Computing Machinery (ACM). ISSN 9781450366199. p. 171–175. doi: 10.1145/3307363.3307384. Full text in Research Archive Show summary

  The effects of software execution are typically ignored in network simulators. This leads to inaccurate simulation results for new and emerging network technologies where packet processing in software has a significant impact on network performance. In this paper we extend our prior work to develop models that capture the temporal aspects of software execution on both uni- and multi-core devices. When executed in parallel with existing network protocol models in network simulators, they significantly improve the accuracy of the simulation results. We demonstrate the applicability of the extended methodology by modeling the execution of communication software on one multi-core device, the Galaxy Nexus smartphone, and evaluate the resulting models in terms of accuracy and scalability. We find that our models are able to reproduce the behavior of the modeled software, and that the models scale well with the number of nodes, cores, and threads included in the simulation; i.e., the simulation overhead increases linearly with the number of nodes.

• Volnes, Espen; Kristiansen, Stein; Plagemann, Thomas Peter; Goebel, Vera Hermine & Lindeberg, Morten Gunnar Bjørner (2019). Modeling the Software Execution of CEP in DCEP-Sim. In Koldehove, Boris (Eds.), DEBS '19: Proceedings of the 13th ACM International Conference on Distributed and Event-based Systems 2019. ACM Publications. ISSN 9781450367943. p. 244–247. doi: 10.1145/3328905.3332508. Full text in Research Archive
• Volnes, Espen; Kristiansen, Stein & Plagemann, Thomas Peter (2019). Communication Software Execution Model of a WSN Device for More Accurate Simulation in ns-3. In Beydoun, Ghassan (Eds.), Proceedings of The 11th International Conference on Computer Modeling and Simulation (ICCMS 2019). Association for Computing Machinery (ACM). ISSN 9781450366199. p. 184–189. doi: 10.1145/3307363.3307371. Full text in Research Archive
• Kristiansen, Stein; Plagemann, Thomas Peter & Goebel, Vera Hermine (2018). An Activity Rule Based Approach to Simulate ADL Sequences. IEEE Access. 6, p. 12551–12572. doi: 10.1109/ACCESS.2018.2807761. Full text in Research Archive Show summary

  © 2018 IEEE. Translations and content mining are permitted for academic research only. Personal use is also permitted, but republication/redistribution requires IEEE permission. See http://www.ieee.org/publications_standards/publications/rights/index.html for more information. The concept of activities of daily living (ADL) has for many years successfully been used in a broad range of health and health care applications. Recent hardware and software developments suggest that the future use of ADL will not only benefit from the transition from manually created ADL logs to automatic sensor-based activity recognition and logging but also from the transition from manual inspection of ADL sequences to their automatic software-driven analysis. This ADL sequence analysis software will be core part in mission critical systems, like ambient assisted living, to detect for example changing health status. Therefore, proper testing and evaluation of this software is mandatory before its deployment. However, testing requires data sets that include normal ADL sequences, hazards, and various kinds of long term behavioral changes; which means it might require weeks or even months to monitor individuals to capture such ADL sequences. Thus, collecting such data sets is very costly, if feasible at all; and very few data sets are available on-line. Therefore, we present an approach to create the necessary data sets for testing through simulation. The simulation of ADL sequences is based on existing ADL sequences and uses probabilistic activity instigation and durations with a novel concept called activity rules to create data sets for proper testing. Activity rules are used to model how individuals resolve activity conflicts. We implemented these concepts as a discrete event simulator, called ADLSim. The evaluation of ADLsim shows that the simulated ADL sequences are realistic and able to capture the variability and non-predictable behavior found in the real world, and that activity rules can impact simulation results significantly.

• Kristiansen, Stein; Hugaas, Mari Sønsteby; Goebel, Vera Hermine; Plagemann, Thomas Peter; Nikolaidis, Konstantinos & Liestøl, Knut (2018). Data Mining for Patient Friendly Apnea Detection. IEEE Access. 6, p. 74598–74615. doi: 10.1109/ACCESS.2018.2882270. Full text in Research Archive Show summary

  Obstructive sleep apnea (OSA) is a common but severely under-diagnosed sleep disorder that affects the natural breathing cycle during sleep with the periods of reduced respiration or no airflow at all. It is our long-term goal to increase the percentage of diagnosed OSA cases and reduce the time to diagnosis with user friendly and cost-efficient tools for sleep analysis at home. As a first step towards this goal, we study in this paper whether a small subset of those physiological signals that are used in classical OSA diagnosis in combination with automatic classification allows to detect apnea events. We study the performance of five data mining techniques to classify the epochs of data from the Apnea-ECG and MIT-BIH databases from PhysioNet as either disrupted or normal breathing. The data are only slightly preprocessed (rate reduction and normalization). We focus in this paper on respiratory signals from the nose, abdomen, chest, and oxygen saturation. We measure for any combination of these signals the accuracy, sensitivity, specificity, and the Kappa statistics of classification with artificial neural network, support vector machine, decision tree, K-nearest neighbor (KNN), and random forest. For Apnea-ECG, we achieve an accuracy of 96.6% with a combination of respiration data from the chest and nose as input data and an accuracy of more than 90% for all signal combinations. Interestingly, these good results are also achieved with the simple KNN technique. The results for MIT-BIH are lower, because of noise, smaller size, and some class imbalance. The accuracy does not significantly improves with the number of signals included in the signal combinations. We conclude that one signal might be sufficient to detect disrupted breathing, if the data set is of sufficient quality and size, and that respiration from the abdomen is the preferable choice when considering both classification performance and patient comfort.

• Starks, Fabrice; Kristiansen, Stein & Plagemann, Thomas Peter (2018). DCEP-Sim: An Open Simulation Framework for Distributed CEP: Introduction for Users and Prospective Developers. In Hinze, Annika & Eyers, David (Ed.), Proceedings of the 12th ACM International Conference on Distributed and Event-based Systems. Association for Computing Machinery (ACM). ISSN 9781450357821. p. 183–186. doi: 10.1145/3210284.3219501. Full text in Research Archive Show summary

  Evaluation of Distributed Complex Event Processing (CEP) systems is a rather challenging task. To simplify this task, we developed the open simulation framework for Distributed CEP, called DCEP-Sim. The goal of this tutorial is to facilitate the process of using DCEP-Sim. Since DCEP-Sim is designed and implemented in the popular network simulator ns-3 we introduce the most important concepts of ns-3. Simulations in ns-3 are configured and executed though a main program called an ns-3 script. We use a simple example script to explain how simulations with DCEP-Sim are set up and executed. To give an idea how DCEP-Sim can be adjusted to particular needs, we explain how DCEP-Sim can be adapted (e.g., through changing the workload and the network topology) and how new Distributed CEP solutions can be added by explaining how to add a new operator to DCEP-Sim.

• Starks, Fabrice; Goebel, Vera Hermine; Kristiansen, Stein & Plagemann, Thomas Peter (2018). Mobile Distributed Complex Event Processing - Ubi Sumus? Quo Vadimus? In Skourletopoulos, Georgios; Mastorakis, George; Mavromoustakis, Constandinos; Dobre, Ciprian & Pallis, Evangelos (Ed.), Mobile Big Data: A Roadmap from Models to Technologies. Springer. ISSN 9783319679242. p. 147–180. doi: 10.1007/978-3-319-67925-9_7. Full text in Research Archive Show summary

  One important class of applications for the Internet of Things is related to the need to gain timely and continuous situational awareness, like smart cities, automated traffic control or emergency and rescue operations. Events happening in the real-world need to be detected in real-time based on sensor data and other data sources. Complex Event Processing (CEP) is a technology to detect complex (or composite) events in data streams and has been successfully applied in high volume and high velocity applications like stock market analysis. However, these applica- tion domains faced only the challenge of high performance, while the Internet of Things and Mobile Big Data introduce a new set of challenges caused by mobility. This chapter aims to explain these challenges and give an overview how they are solved respectively how far state-of-the-art research has advanced to be useful to solve mobile big data problems. At the infrastructure level the main challenge is to trade performance against resource consumption and energy efficiency and op- erator placement is the most dominant mechanisms to address these problems. At the application and consumer level mobile queries pose a new set of challenges for CEP related to continuously changing positions of consumers and producers and the need to adapt the query processing to these changes. Finally, methods and tools for systematical testing and reproducible performance evaluation for mobile distributed CEP is an open problem.

• Kristiansen, Stein; Goebel, Vera Hermine; Øyri, Karl & Plagemann, Thomas Peter (2018). Event-Based Methodology for Real-Time Data Analysis in Cyber Physical Systems. In Radek, Silhavy; Silhavy, Petr & Prokopova, Zdenka (Ed.), Cybernetics Approaches in Intelligent Systems. Springer. ISSN 9783319676180. p. 184–195. doi: 10.1007/978-3-319-67618-0_17. Full text in Research Archive
• Fredrik, Løberg; Goebel, Vera Hermine & Plagemann, Thomas Peter (2018). Quantifying the Signal Quality of Low-cost Respiratory Effort Sensors for Sleep Apnea Monitoring. In Susanne, Boll; Ramesh, Jain; Noel, O'Connor; Troy, MacDaniel & Jochen, Meyer (Ed.), Proceedings of the 3rd International Workshop on Multimedia for Personal Health and Health Care. ACM Digital Library. ISSN 9781450359825. p. 3–11. doi: 10.1145/3264996.3264998. Full text in Research Archive Show summary

  Obstructive Sleep Apnea (OSA) is a common, but severely under- diagnosed sleep disorder characterized by recurring periods of shallow or paused breathing during sleep. It is our long-term goal to allow people to perform the first step towards a sleep apnea de- tection at home by utilizing smartphones, low-cost consumer-grade sensors, and data mining techniques. In this work, we evaluate the signal quality of four respiratory effort sensors (BITalino, FLOW, RespiBAN, and Shimmer), using a RIP sensor from NOX Medical as the gold standard. We design a sixteen-minute signal capture procedure to simulate epochs of disrupted breathing, and capture data from twelve (BITalino and Shimmer) and eleven (RespiBAN and FLOW) subjects during wakefulness. Our signal quality eval- uation approach is based on the breath detection accuracy met- rics sensitivity and positive predictive value (PPV), along with the breath amplitude accuracy metric weighted absolute percentage er- ror (WAPE). These metrics are closely related to how apneic and hypopneic episodes are scored by medical personnel, making it straightforward to reason about their interpretation. Our results show that false breaths are the primary concern affecting the breath detection accuracy of BITalino, Shimmer, and RespiBAN. Respec- tively, the sensitivity of BITalino, Shimmer, RespiBAN, and FLOW is 99.61%, 98.53%, 98.41%, and 98.91%. Their PPV is 96.28%, 96.58%, 90.81%, and 98.81%. Finally, their WAPE is 13.82%, 16.89%, 13.60%, and 8.75%. The supine (back) position is consistently showing the overall best signal quality compared to the side position.

• Hansen, Hans Vatne; Goebel, Vera Hermine & Plagemann, Thomas Peter (2017). TRAMP Real-Time Application Mobility Platform. IEEE Transactions on Mobile Computing. ISSN 1536-1233. 16(11), p. 3236–3249. doi: 10.1109/TMC.2017.2688421. Full text in Research Archive
• Cabrero, Sergio Cabrero; Pañeda, Xabiel Garcia; Melendi, David; Garcia, Roberto & Plagemann, Thomas Peter (2017). Using Firefighter Mobility Traces to Understand Ad-Hoc Networks in Wildfires. IEEE Access. 6, p. 1331–1341. doi: 10.1109/ACCESS.2017.2778347. Full text in Research Archive
• Starks, Fabrice; Kristiansen, Stein & Plagemann, Thomas Peter (2017). DCEP-Sim: An Open Simulation Framework for Distributed CEP. In Chandy, Mani & Koldehofe, Boris (Ed.), The 11th ACM International Conference on Distributed and Event-Based Systems. ACM Digital Library. ISSN 9781450350655. p. 180–190. doi: 10.1145/3093742.3093919. Full text in Research Archive Show summary

  Distributed Complex Event Processing (CEP) is gaining increasing interest for two reasons: (1) to scale system performance to handle higher workloads in real-time, and (2) to perform in-network processing, e.g., in mobile networks to reduce the amount of data that has to be transferred through the network. System scalability and the complexity of mobile systems are some of the major challenges when evaluating the performance of new Distributed CEP solutions. We propose an open framework for distributed CEP (DCEP-Sim) built on a well-established network simulator, i.e, ns3. e design of DCEP-Sim is based on the engineering principles of separation of concerns and the separation of mechanisms and policies. By leveraging the ns-3 feature of object aggregation it is very easy to add new policies, e.g., placement or selection policies, and evaluate them without changing anything else in the DCEPSim. e fact that ns-3 includes many accurate network models implies that Distributed CEP simulation with DCEP-Sim will also be much more accurate than ad-hoc handcra ed simulations. We demonstrate in a use case how easy it is to con gure performance evaluation experiments and we perform experiments to con rm that the integration of the Distributed CEP in ns-3 is good foundation for large-scale experiments. e evaluation results demonstrate that DCEP-Sim substantially reduces the e ort and costs of Distributed CEP evaluation.

• Hansen, Hans Vatne; Goebel, Vera Hermine & Plagemann, Thomas Peter (2016). DevCom: Device communities for user-friendly and trustworthy communication, sharing, and collaboration. Computer Communications. ISSN 0140-3664. 85, p. 14–27. doi: 10.1016/j.comcom.2016.02.001. Full text in Research Archive
• Kristiansen, Stein; Plagemann, Thomas Peter & Goebel, Vera Hermine (2016). Smooth and crispy - integrating continuous event proximity calculation and discrete event detection. In Gal, Avigdor; Weidlich, Matthias; Kalogeraki, Vana & Venkasubramanian, Nalini (Ed.), Proceedings of the 10th ACM International Conference on Distributed and Event-based Systems, DEBS '16, Irvine, CA,USA, June 20 -24. ACM Publications. ISSN 9781450340212. p. 153–160. doi: 10.1145/2933267.2933302. Full text in Research Archive
• Drugan, Ovidiu Valentin; Plagemann, Thomas Peter & Munthe-Kaas, Ellen (2015). Dynamic clustering in Sparse MANETs. Computer Communications. ISSN 0140-3664. 59, p. 84–97. doi: 10.1016/j.comcom.2014.12.005. Full text in Research Archive
• Starks, Fabrice & Plagemann, Thomas Peter (2015). Operator placement for efficient distributed complex event processing in MANETs. IEEE International Conference on Wireless and Mobile Computing, Networking, and Communications. ISSN 2160-4886. p. 83–90. doi: 10.1109/WiMOB.2015.7347944. Full text in Research Archive
• Kristiansen, Stein; Plagemann, Thomas Peter & Goebel, Vera Hermine (2015). A Methodology to Model the Execution of Communication Software for Accurate Network Simulation. ACM Transactions on Modeling and Computer Simulation. ISSN 1049-3301. 26(1). doi: 10.1145/2746233. Full text in Research Archive Show summary

  Network simulation is commonly used to evaluate the performance of distributed systems, but these approaches do not account for the performance impact that protocol execution on nodes has on performance, which can be significant. We provide a methodology to extract from real devices models of communication software execution that can be used to extend network simulators to improve their accuracy. The models are obtained by instrumenting the target devices to obtain the events necessary to describe software execution. We specify which events must be captured, how to capture them, and how to transform the event traces into models that can be used to extend network simulators. The obtained models are based on high-level abstractions that can be used to describe the execution of a wide range of communication software, and the design principles to extend network simulators are not restricted to any specific network simulator. The same model of communication software execution can be used without modification in all discrete event-based network simulators that are extended according to our principles. The models are represented in a human-readable format that is suitable for modification and can therefore be used to predict how software modifications impact performance. We evaluate our models with two proof-of-concept extensions of Ns-3 that execute the models of two modern smartphones: the Google Nexus One (GN1) and the Nokia N900. We measure the accuracy of our models by comparing results from real experiments with those from simulations with our models and analyze the simulation overhead of our approach.

• Srebrny, Piotr; Sørbø, Dag Henning Liodden & Plagemann, Thomas Peter (2015). Tiny network caches with large performance gains for popular downloads. Lecture Notes in Computer Science (LNCS). ISSN 0302-9743. 9071, p. 197–210. doi: 10.1007/978-3-319-22572-2_14. Full text in Research Archive
• Dahl, Aage Andre Håland; Zaher, Ali & Plagemann, Thomas Peter (2015). Android Based Toolset for NFC Tag Testing and Performance Evaluation. In Badia, Leonardo (Eds.), European Wireless 2015; 21th European Wireless Conference; Proceedings of. VDE Verlag GmbH. ISSN 9783800739769. p. 1–8. Full text in Research Archive
• Srebrny, Piotr; Sørbø, Dag Henning Liodden; Plagemann, Thomas Peter; Goebel, Vera Hermine & Mauthe, Andreas (2014). CacheCast: A Single-Source Multiple-Destination Caching Mechanism, Advanced Content Delivery, Streaming, and Cloud Services. Wiley. ISSN 9781118575215. p. 385–411. doi: 10.1002/9781118909690.ch20. Full text in Research Archive
• Nguyen, Viet Hoang; Munthe-Kaas, Ellen & Plagemann, Thomas Peter (2014). Energy saving for activity recognition through sensor selection, scheduling and sampling rate tuning, 2014 7th IFIP Wireless and Mobile Networking Conference (WMNC). IEEE Press. ISSN 9781479930609. doi: 10.1109/WMNC.2014.6878873. Full text in Research Archive
• Velazquez-Garcia, Francisco Javier; Andersen, Håvard Stigen; Hansen, Hans Vatne; Goebel, Vera Hermine & Plagemann, Thomas Peter (2013). SOCKMAN: Socket Migration for Multimedia Applications. In Pripužić, Krešimir & Banek, Marko (Ed.), Proceedings of the 12th International Conference on Telecommunications. University of Zagreb. ISSN 9789531841757. p. 115–122. Full text in Research Archive
• Kamisinski, Piotr; Goebel, Vera Hermine & Plagemann, Thomas Peter (2013). A reconfigurable distributed CEP middleware for diverse mobility scenarios. In Indulska, Jadwiga & Bisdikian, Chatschik (Ed.), 2013 IEEE International Conference on Pervasive Computing and Communications Workshops. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781467350778. p. 617–620. doi: 10.1109/PerComW.2013.6529568. Full text in Research Archive Show summary

  Sensor nodes and complex event processing (CEP) are important and powerful means for gathering data and detecting phenomena of interest in mission-critical pervasive systems, e.g. for emergency and rescue operations. However, the dynamic network does not allow using centralized CEP. To address this issue, we present a component-based distributed CEP middleware. Its main goal is easy reconfigurability to different mobility scenarios. This is achieved by providing an extensible collection of algorithms that are tailored for specific scenarios. The middleware makes it possible to select on demand the algorithms that are most suitable for the current scenario. Our evaluation shows that the middleware works in a broad spectrum of mobility scenarios. We also investigate the trade-off between efficiency and reliability of distributed CEP. Copyright 2013 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

• Kristiansen, Stein; Plagemann, Thomas Peter & Goebel, Vera Hermine (2013). Modeling communication software execution for accurate simulation of distributed systems, Proceedings of the 2013 ACM SIGSIM conference on Principles of advanced discrete simulation. Association for Computing Machinery (ACM). ISSN 9781450319201. p. 67–78. doi: 10.1145/2486092.2486102. Full text in Research Archive
• Nguyen, Viet Hoang; Munthe-Kaas, Ellen & Plagemann, Thomas Peter (2013). Towards quality and energy aware complex event processing, Wireless and Mobile Computing, Networking and Communications (WiMob), 2013 IEEE 9th International Conference on. IEEE Press. ISSN 9781479904266. p. 352–359. doi: 10.1109/WiMOB.2013.6673384. Full text in Research Archive
• Kristiansen, Stein; Plagemann, Thomas Peter & Goebel, Vera Hermine (2013). Extending network simulators with communication software execution models, 2013 Fifth International Conference on Communication Systems and Networks (COMSNETS). IEEE Press. ISSN 9781467353304. p. 1–10. doi: 10.1109/COMSNETS.2013.6465549. Full text in Research Archive
• Nguyen, Viet Hoang; Munthe-Kaas, Ellen & Plagemann, Thomas Peter (2013). Quality and energy aware data acquisition for activity and locomotion recognition, Pervasive Computing and Communications Workshops (PERCOM Workshops), 2013 IEEE International Conference on. IEEE Press. ISSN 9781467350754. p. 493–498. doi: 10.1109/PerComW.2013.6529547. Full text in Research Archive
• Plagemann, Thomas Peter; Goebel, Vera Hermine; Mauthe, Andreas & Srebrny, Piotr (2013). No more Déjà Vu - Eliminating Redundancy with CacheCast: Feasibility and Performance Gains. IEEE/ACM Transactions on Networking. ISSN 1063-6692. 21(6), p. 1736–1749. doi: 10.1109/TNET.2012.2236104. Full text in Research Archive
• Tyson, Gareth; Mauthe, Andreas; Kaune, Sebastian; Grace, Paul; Taweel, Adel & Plagemann, Thomas Peter (2012). Juno: a middleware platform for supporting delivery-centric applications. ACM Transactions on Internet Technology (TOIT). ISSN 1533-5399. 12(2). doi: 10.1145/2390209.2390210. Full text in Research Archive
• Lindeberg, Morten Gunnar Bjørner; Haavet, Jan Erik; Barros, Sergio Cabrero; Goebel, Vera Hermine & Plagemann, Thomas Peter (2012). Message lost or message taken - on message ferry selection in DTNs -. In Fitzpatrick, John M. (Eds.), Wireless Days (WD) 2012 Conference Publications. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781467344029. p. 1–7. doi: 10.1109/wd.2012.6402815. Full text in Research Archive
• Lindeberg, Morten Gunnar Bjørner; Goebel, Vera Hermine & Plagemann, Thomas Peter (2012). CLiSuite: Simplifying the development of cross-layer adaptive applications. In Göschka, Karl M.; Tosic, Vladimir; Pereira, José Orlando & Hung, Patrick C. K. (Ed.), Proceedings of the 7th Workshop on Middleware for Next Generation Internet Computing (MW4NG '12). Association for Computing Machinery (ACM). ISSN 9781450316071. p. 1–6. doi: 10.1145/2405178.2405180. Full text in Research Archive
• Nguyen, Viet Hoang; Munthe-Kaas, Ellen & Plagemann, Thomas Peter (2012). Energy-balanced sensor selection for social context detection. In Giordano, Silvia; Langheinrich, Marc & Schmidt, Albrecht (Ed.), 2012 IEEE International Conference on Pervasive Computing and Communications Workshops. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781467309059. p. 32–37. Full text in Research Archive
• Cabrero, Sergio; Paneda, Xabiel G.; Gracia, Roberto; Melendi, David & Plagemann, Thomas Peter (2012). Dynamic Temporal Scalability: Video adaptation in sparse Mobile Ad-Hoc Networks. In Barcelo-Ordinas, Jose M.; Chen, Wen & Quintero, Alejandro (Ed.), Wireless and Mobile Computing, Networking and Communications (WiMob), 2012 IEEE 8th International Conference on. IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781467314299. p. 349–356. doi: 10.1109/wimob.2012.6379097. Full text in Research Archive
• Tyson, Gareth; Mauthe, Andreas; Kaune, Sebastian; Grace, Paul; Taweel, Adel & Plagemann, Thomas Peter (2012). Juno: An Adaptive Delivery-Centric Middleware. In Shirazi, Behrooz (Eds.), Consumer Communications and Networking Conference (CCNC), 2012 IEEE. IEEE Sarnoff Symposium. ISSN 9781457720710. p. 587–591. doi: 10.1109/ccnc.2012.6181010. Full text in Research Archive
• Rodriguez-Fernandez, Daniel; Martinez-Yelmo, Isaias; Munthe-Kaas, Ellen & Plagemann, Thomas Peter (2012). ILORIN: Identifier-LOcator Resolution for Infrastructure-less Networks. In Pujolle, Guy; Duarte, Otto & Boutaba, Raouf (Ed.), Proceedings of the 2012 International Conference on the Network of the Future (NoF'12). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781467352659. doi: 10.1109/nof.2012.6463992. Full text in Research Archive Show summary

  In order to overcome the limitations of the current Internet addressing, it is generally accepted that the Future Internet needs a separation between identifiers and network locators. Such identifier-locator split is also needed in infrastructure-less networks, such as Mobile ad hoc Networks (MANETs) and Delay Tolerant Networks, since they are an integral part of the Future Internet. Despite the amount of work in infrastructure-based networks, only a few proposals have considered how to apply this identifier-locator split in infrastructure-less networks. The contribution of this paper is an identifier-locator resolution system that can work in sparse MANETs, which are prone to network partitions. Our approach is an identifier-locator association discovery system, which uses periodic beacons to exchange the resolution information, avoiding the establishment of shared state between nodes. Our system exploits the broadcast nature of the wireless medium, opportunistic encounters, and information replication to disseminate identifier-locator associations across the network. The results of our extensive experiments demonstrate that our solution outperforms the related work, achieving a higher identifier-locator association discovery rate. association discovery system, which uses periodic beacons to exchange the resolution information, avoiding the establishment of shared state between nodes. Our system exploits the broadcast nature of the wireless medium, opportunistic encounters, and information replication to disseminate identifier-locator associations across the network. The results of our extensive experiments demonstrate that our solution outperforms the related work, achieving a higher identifier-locator association discovery rate.

• Rodriguez-Fernandez, Daniel; Martinez-Yelmo, Isaias; Munthe-Kaas, Ellen & Plagemann, Thomas Peter (2012). Always best (dis-)connected: challenges to interconnect highly heterogeneous networks. Journal of Internet Engineering. ISSN 1791-177X. 5(1), p. 299–309. Full text in Research Archive Show summary

  Wireless networks enable mobility, multihoming, and Delay Tolerant Networks. In such networking environments, the principles of the Internet, i.e., the end-to-end principle and the combination of identity and location in IP addresses, cannot be applied. In this paper, we propose a scalable application centric approach for supporting mobility, multihoming, and interconnecting highly heterogeneous networks where the networks may belong to different networking paradigms, e.g., IP based and Delay Tolerant Networks. Applications and users that want to communicate, use communities. These communities are application specific overlays formed by entities (nodes or other communities) that want to support the application. Community members might together have several network technologies available, and the community manages internetworking information for the members to seamlessly integrate them. This integration is assisted by a community support layer that coordinates the communities with the available networks. An underlay layer common interface is used to access the different networks, allowing an implementation that considers its specific characteristics and challenges. We propose a global cryptographic based namespace for entities to enable internetworking across heterogeneous networks with different locator schemes. Identifiers are resolved to locators using a late binding approach. Furthermore, we analyse the communication challenges present in emergency and rescue operations and describe how to deal with them using our proposal.

• Hansen, Hans Vatne; Velazquez, Francisco Javier; Goebel, Vera Hermine & Plagemann, Thomas Peter (2012). Efficient Data Sharing for Multi-device Multimedia Applications. In Fuhrhop, Christian; Steglich, Stephan & Jaokar, Ajit (Ed.), Proceedings of the Workshop on Multi-device App Middleware, Multi-Device '12. Association for Computing Machinery (ACM). ISSN 9781450316170. doi: 10.1145/2405172.2405174. Full text in Research Archive
• Hansen, Hans Vatne; Velazquez-Garcia, Francisco Javier; Goebel, Vera Hermine; Munthe-Kaas, Ellen & Plagemann, Thomas Peter (2012). Migration of Fine-grained Multimedia Applications. In Wohlstadter, Eric (Eds.), Proceedings of the Posters and Demo Track, Middleware '12. Association for Computing Machinery (ACM). ISSN 9781450316125. doi: 10.1145/2405153.2405165. Full text in Research Archive
• Rodriguez-Fernandez, Daniel; Martinez-Yelmo, Isaias; Munthe-Kaas, Ellen & Plagemann, Thomas Peter (2011). Always Best (dis-)Connected: Challenges to Interconnect Highly Heterogeneous Networks. Lecture Notes in Computer Science (LNCS). ISSN 0302-9743. 6649, p. 410–421. Full text in Research Archive
• Mondet, Sebastien; Alberdi, Ion & Plagemann, Thomas Peter (2011). Generating Optimised and Formally Checked Packet Parsing Code, Future Challenges in Security and Privacy for Academia and Industry 26th IFIP TC 11 International Information Security Conference. Springer. ISSN 9783642214233. p. 173–184. doi: 10.1007/978-3-642-21424-0_14. Full text in Research Archive
• Kristiansen, Stein; Plagemann, Thomas Peter & Goebel, Vera Hermine (2011). Towards Scalable and Realistic Node Models for Network Simulators. Computer communication review. ISSN 0146-4833. 41(4), p. 418–419. doi: 10.1145/2043164.2018498. Full text in Research Archive
• Kristiansen, Stein; Plagemann, Thomas Peter & Goebel, Vera (2011). Towards scalable and realistic node models for network simulators. In Keshav, Srinivasan; Liebeherr, Jörg; Byers, John & Mogul, Jeffrey (Ed.), Proceedings of the ACM SIGCOMM 2011 conference on SIGCOMM. Association for Computing Machinery (ACM). ISSN 9781450307970. p. 418–419. doi: 10.1145/2043164.2018498. Full text in Research Archive
• Puzar, Matija & Plagemann, Thomas Peter (2011). Data sharing in mobile ad-hoc networks – a study of replication and performance in the MIDAS data space. International Journal of Space-Based and Situated Computing (IJSSC). ISSN 2044-4893. 1(2-3), p. 137–150. doi: 10.1504/IJSSC.2011.04034. Full text in Research Archive
• Søberg, Jarle; Goebel, Vera Hermine & Plagemann, Thomas Peter (2011). Deviation detection in automated home care using CommonSens, 2011 IEEE International Conference on Pervasive Computing and Communications Workshops (PERCOM Workshops). IEEE (Institute of Electrical and Electronics Engineers). ISSN 9781612849386. p. 668–673. doi: 10.1109/percomw.2011.5766972. Full text in Research Archive Show summary

  Automated home care uses sensors to report about the well-being of monitored persons. Our complex event processing (CEP) system CommonSens simplifies the work of the application programmers, i.e., those who write the complex queries, by facilitating reuse of queries, sensor instances and environments. We have observed that many automated home care systems focus on detecting alarming behaviour, e.g., falls and heart attacks. However, it is impossible to predict and describe everything that can go wrong. In this paper we define deviation detection in CommonSens, which means that the application programmer only needs to state queries that define correct behaviour. If something happens that does not correspond to the query, this is interpreted as a deviation and a notification or alarm is sent. We believe that this approach further simplifies the work of the application programmer. Deviation detection is implemented in our CommonSens prototype, and we show that our prototype detects deviations as expected by running a set of functionality tests and an experiment based on real-world trace files.

• Cabrero, Sergio; Pañeda, Xabiel Garcia; Plagemann, Thomas Peter; Melendi, David & Garcia, Roberto (2011). Towards reliable video transmission over sparse MANETs in emergencies. Informática na educação: teoria & prática. ISSN 1516-084X. 14(1), p. 61–77. doi: 10.22456/1982-1654.21937. Full text in Research Archive
• Rodriguez-Fernandez, Daniel; Akø, Per-Arne Holtmon & Plagemann, Thomas Peter (2011). Leveraging self-description to visualise autonomic networks. In Schmeck, Hartmut; Rosenstiel, Wolfgang; Abdelzaher, Tarek & Hellerstein, Joseph (Ed.), ICAC '11 8th International Conference on Autonomic Computing Karlsruhe, Germany — June 14 - 18, 2011. Association for Computing Machinery (ACM). ISSN 9781450306072. p. 183–184. doi: 10.1145/1998582.1998619. Full text in Research Archive Show summary

  The ANA (Autonomic Networking Architecture) project provides a framework to design, create, and federate different network architectures. ANA considers that different network paradigms require their own network architecture and internal policies. The present work describes how the self-description property of autonomic systems is used by the ANA Browser visualisation tool to allow a human user to inspect how an ANA network works internally. The ANA BrowseThe ANA (Autonomic Networking Architecture) project provides a framework to design, create, and federate different network architectures. ANA considers that different network paradigms require their own network architecture and internal policies. The present work describes how the self-description property of autonomic systems is used by the ANA Browser visualisation tool to allow a human user to inspect how an ANA network works internally. The ANA Browser extends the classical network visualisation with a description of the functional configuration which may vary considerably amongst different ANA networks and also might vary at run-time on such polymorphic networks.r extends the classical network visualisation with a description of the functional configuration which may vary considerably amongst different ANA networks and also might vary at run-time on such polymorphic networks.

• Kristiansen, Stein & Plagemann, Thomas Peter (2011). Accuracy and scalability of ns-2's distributed emulation extension. Simulation. ISSN 0037-5497. 87(1-2), p. 45–65. doi: 10.1177/0037549710370215. Full text in Research Archive
• Lindeberg, Morten Gunnar Bjørner; Kristiansen, Stein; Plagemann, Thomas Peter & Goebel, Vera (2011). Challenges and techniques for video streaming over mobile ad hoc networks. Multimedia Systems. ISSN 0942-4962. 17(1), p. 51–82. doi: 10.1007/s00530-010-0187-8. Full text in Research Archive
• Rodriguez-Fernandez, Daniel; Martinez, Isaias; Munthe-Kaas, Ellen & Plagemann, Thomas Peter (2011). Always Best (dis-)Connected: Challenges to Interconnect Highly Heterogeneous Networks. In Masip-Bruin, Xavier; Verchere, Dominique; Tsaoussidis, Vassilis & Yannuzzi, Marcelo (Ed.), Wired/Wireless Internet Communications: 9th IFIP TC 6 International Conference, WWIC 2011, Vilanova i la Geltrú, Spain, June 15-17, 2011, Proceedings. Springer. ISSN 9783642215599. p. 410–421. doi: 10.1007/978-3-642-21560-5_34. Full text in Research Archive Show summary

  Wireless networks enable mobility, multihoming, and Delay Tolerant Networks. In such networking environments, the principles of the Internet, i.e., the end-to-end principle and the combination of location and identification in IP addresses, cannot be applied. In this paper, we propose a scalable application centric approach for mobility and multihoming that is able to interconnect highly heterogeneous networks where the networks may belong to different networking paradigms, e.g., IP based and Delay Tolerant Networks. Applications and users that aim to communicate, form communities. Community members might together have several network technologies available, and the community layer manages internetworking information for the members to seamlessly integrate these. Networking adaptation layers are used to provide a common interface for the different networks to the community layer. Addressing is based on names, cryptographic identifiers, and network locators and such that identifiers can also be created in infrastructure-less and disconnected situations.

• Drugan, Ovidiu Valentin; Plagemann, Thomas Peter & Munthe-Kaas, Ellen (2011). Detecting Communities in Sparse MANETs. IEEE/ACM Transactions on Networking. ISSN 1063-6692. 19(5), p. 1434–1447. doi: 10.1109/TNET.2011.2112376. Full text in Research Archive

View all works in NVA

• Hui, David; Akre, Harriet; Goebel, Vera Hermine; Plagemann, Thomas Peter & Arnesen, Lars Andre Strøm (2025). Bruk av KI-verktøy på fastlegekontoret. doi: 10.4045/tidsskr.25.0432. Full text in Research Archive
• Hui, David; Akre, Harriet; Goebel, Vera Hermine; Plagemann, Thomas Peter & Arnesen, Lars Andre Strøm (2025). Use of AI in general practice. 145. doi: 10.4045/tidsskr.25.0432. Full text in Research Archive
• Plagemann, Thomas Peter & Gu, He (2025). Data Sharing and Privacy - An Empirical Study. Full text in Research Archive
• Plagemann, Thomas Peter (2025). Parrot Project. Full text in Research Archive
• Melteig, Elina; Plagemann, Thomas Peter; Goebel, Vera Hermine; Akre, Harriet; Øverland, Britt & Hui, David (2025). Noen barn slutter å puste om natten. Ofte har barnet sovet dårlig i flere år. Titan.uio.no. doi: https:/www.titan.uio.no/innovasjon/2025/noen-barn-slutter-a-puste-om-natten.html. Full text in Research Archive
• Melteig, Elina; Allgot, Marte Skogstad; Noori, Farzan Majeed & Plagemann, Thomas Peter (2024). Kunstig «pust» skal gjøre behandlingen bedre for dem med pusteutfordringer. Titan.uio.no. Full text in Research Archive
• Plagemann, Thomas Peter (2024). Lazy Migration - Semantic and utility aware operator migration for Distributed Stream Processing. Full text in Research Archive
• Plagemann, Thomas Peter (2024). EXPOSE: Experimental Performance Evaluation of Stream Processing Engines Made Easy. Full text in Research Archive
• Lopez, Marta Quemada; Plagemann, Thomas Peter; Goebel, Vera Hermine; Adams, Jonathan; Hui, David & Øverland, Britt [Show all 8 contributors for this article] (2024). Requirements Analysis for Responsible Explainable AI for Pediatric Sleep Apnea Diagnosis. Full text in Research Archive
• Plagemann, Thomas Peter (2023). Opportunities and Challenges of using Smart Devices and Machine Learning for Health Applications. Full text in Research Archive
• Plagemann, Thomas Peter (2023). Responsible Explainable Machine Learning for Sleep-related Respiratory Disorders. Full text in Research Archive
• Plagemann, Thomas Peter (2023). Respire - planlegging og gjennomføring av internasjonale samarbeidsprosjekter, Full text in Research Archive
• Plagemann, Thomas Peter (2023). Semantic and utility aware operator migration for Distributed Stream Processing. Full text in Research Archive
• Goebel, Vera Hermine & Plagemann, Thomas Peter (2022). Respire - Responsible Explainable Machine Learning for Sleep-related Respiratory Disorders. Full text in Research Archive
• Dale, Øystein; Kristiansen, Stein; Plagemann, Thomas Peter & Volnes, Espen (2019). Many Cores and Still Delays: Simulating Multi-Core Communication Software Execution. Full text in Research Archive Show summary

  The effects of software execution are typically ignored in network simulators. This leads to inaccurate simulation results for new and emerging network technologies where packet processing in software has a significant impact on network performance. In this paper we extend our prior work to develop models that capture the temporal aspects of software execution on both uni- and multi-core devices. When executed in parallel with existing network protocol models in network simulators, they significantly improve the accuracy of the simulation results. We demonstrate the applicability of the extended methodology by modeling the execution of communication software on one multi-core device, the Galaxy Nexus smartphone, and evaluate the resulting models in terms of accuracy and scalability. We find that our models are able to reproduce the behavior of the modeled software, and that the models scale well with the number of nodes, cores, and threads included in the simulation; i.e., the simulation overhead increases linearly with the number of nodes.

• Volnes, Espen; Kristiansen, Stein; Plagemann, Thomas Peter; Goebel, Vera Hermine & Lindeberg, Morten Gunnar Bjørner (2019). Modeling the Software Execution of CEP in DCEP-Sim. Full text in Research Archive
• Volnes, Espen; Kristiansen, Stein & Plagemann, Thomas Peter (2019). Communication Software Execution Model of a WSN Device for More Accurate Simulation in ns-3. Full text in Research Archive
• Nikolaidis, Konstantinos; Kristiansen, Stein; Goebel, Vera Hermine; Plagemann, Thomas Peter & Liestøl, Knut (2019). Augmenting Physiological Time Series Data: A Case study for Sleep Apnea Detection. Full text in Research Archive
• Plagemann, Thomas Peter (2019). Special issues on “User-Centric Social Multimedia Computing” and “Multimedia Cloud Computing for Smarter Cities”. Multimedia Systems. ISSN 0942-4962. 25(5), p. 449–449. doi: 10.1007/s00530-019-00634-8. Full text in Research Archive
• Wang, Meng; Tie, Yun; Tian, Qi; Saddik, Abdulmotaleb Ei; Gong, Yihong & Plagemann, Thomas Peter [Show all 8 contributors for this article] (2016). Preface. Lecture Notes in Computer Science (LNCS). ISSN 0302-9743. 9917 LNCS, p. V–VI. Full text in Research Archive
• Wang, Meng; Tie, Yun; Tian, Qi; Saddik, Abdulmotaleb Ei; Gong, Yihong & Plagemann, Thomas Peter [Show all 8 contributors for this article] (2016). Preface. Lecture Notes in Computer Science (LNCS). ISSN 0302-9743. 9916 LNCS, p. V–VI. Full text in Research Archive
• Fabrice, Bigirimana; Goebel, Vera Hermine & Plagemann, Thomas Peter (2014). Investigation of contradicting optimization goals for event processing overlays in MANETs. Full text in Research Archive
• Cabrero, Sergio; Xabiel, Paneda; Plagemann, Thomas Peter; Melendi, David & Garcia, Roberto (2011). An Overlay Routing Protocol for Video over sparse MANETs in Emergencies. Full text in Research Archive
• Gu, He; Plagemann, Thomas Peter; Goebel, Vera Hermine; Benndorf, Maik & Koldehofe, Boris (2026). Pattern-level Differential Privacy for High-utility Complex Event Processing. arxiv.org. doi: 10.48550/ARXIV.2609.23827. Full text in Research Archive Show summary

  Current privacy-preserving mechanisms (PPMs) in Complex Event Processing (CEP) systems are unnecessarily restrictive, reducing the utility of data received by data consumers. This article presents a novel approach to preserve privacy in CEP systems, improving the utility of detected event patterns by dynamically adapting the noise added to an unprotected data stream. We introduce a new guarantee named pattern-level differential privacy (DP), which enables us to apply and compare the strength of PPMs at the pattern level. We propose new pattern-level PPMs yielding pattern-level DP and analyze different trust settings of these PPMs and their requirements for context knowledge in the CEP system, e.g., the deployed queries. Our evaluation is based on three datasets (two real-world, one synthetic) and shows that the proposed PPMs increase data utility while preserving the same privacy level as the state-of-the-art PPMs. We use simulations to study the performance of our proposed PPMs in various practical scenarios. Furthermore, we demonstrate that computational complexity is not an obstacle to deployment.

• Qian, Trond Victor & Plagemann, Thomas Peter (2025). Uncertainty Quantification for Deep Learning in Sleep Apnea Detection: A Comparative Evaluation of Monte Carlo Dropout and Deep Ensembles using a 1D-CNN Model. Universitetet i Oslo. Full text in Research Archive
• Testad, Maja Kvikstad; Foldal, Tobias Myren & Plagemann, Thomas Peter (2024). Developing Health Oriented Crowdsensing Platforms for Modern Android Wearables. Universitetet i Oslo. Full text in Research Archive
• Adul, Ahad; Hui, Chak Kwan & Plagemann, Thomas Peter (2024). Garu - A gamified running application for better physical health. University of Oslo. Full text in Research Archive
• Volnes, Espen; Plagemann, Thomas Peter & Goebel, Vera Hermine (2022). To Migrate or not to Migrate: An Analysis of Operator Migration in Distributed Stream Processing. arXiv2022. Full text in Research Archive Show summary

  One of the most important issues in data stream processing systems is to use operator migration to handle highly variable workloads in a cost-efficient manner and adapt to the needs at any given time on demand. Operator migration is a complex process that involves changes in the state and stream management of a running query, typically without any loss of data, and with as little disruption to the execution as possible. This survey provides an overview of solutions for operator migration from a historical perspective as well as the perspective of the goal of migration. It introduces a conceptual model of operator migration to establish a unified terminology and classify existing solutions. Existing work in the area is analyzed to separate the mechanism of migration from the decision to migrate the data. In case of the latter, a cost-benefit analysis is emphasized that is important for operator migration but is often only implicitly addressed, or is neglected altogether. A description of the available solutions provides the reader with a good understanding of the design alternatives from an algorithmic viewpoint. We complement this with an empirical study to provide quantitative insights on the impact of different design alternatives on the mechanisms of migration

• Plagemann, Thomas Peter; Goebel, Vera Hermine; Hollick, Matthias & Koldehofe, Boris (2022). Towards Privacy Engineering for Real-Time Analytics in the Human-Centered Internet of Things. arXiv. Full text in Research Archive Show summary

  Big data applications offer smart solutions to many urgent societal challenges, such as health care, traffic coordination, energy management, etc. The basic premise for these applications is "the more data the better". The focus often lies on sensing infrastructures in the public realm that produce an ever-increasing amount of data. Yet, any smartphone and smartwatch owner could be a continuous source of valuable data and contribute to many useful big data applications. However, such data can reveal a lot of sensitive information, like the current location or the heart rate of the owner of such devices. Protection of personal data is important in our society and for example manifested in the EU General Data Protection Regulation (GDPR). However, privacy protection and useful big data applications are hard to bring together, particularly in the human-centered IoT. Implementing proper privacy protection requires skills that are typically not in the focus of data analysts and big data developers. Thus, many individuals tend to share none of their data if in doubt whether it will be properly protected. There exist excellent privacy solutions between the "all or nothing" approach. For example, instead of continuously publishing the current location of individuals one might aggregate this data and only publish information of how many individuals are in a certain area of the city. Thus, personal data is not revealed, while useful information for certain applications like traffic coordination is retained. The goal of the Parrot project is to provide tools for real-time data analysis applications that leverage this "middle ground". Data analysts should only be required to specify their data needs, and end-users can select the privacy requirements for their data as well as the applications and end-users they want to share their data with.

• Kristiansen, Stein; Goebel, Vera Hermine; Øyri, Karl & Plagemann, Thomas Peter (2017). Event Modeling and Processing to Simplify Real-Time Analysis of Physiological Signals. Universitetet i Oslo. ISSN 9788273684288. Full text in Research Archive Show summary

  Recent developments in wireless sensors to measure physiological parameters and environmental parameters enable a new generation of applications for health monitoring. However, the complexity of many physiological signals and the need to process sensor data in real-time makes programming such applications a challenging task. This chapter motivates the need to step-wise reduce the complexity of sensor data to enable medical experts to tailor and develop (parts of) applications without having in depth programming skills. To achieve this goal, a methodology for application development with real-time sensor data processing is presented. The methodology is based on the concepts of physical and logical sensors, which can detect atomic and composite events. The combination of using the declarative approach of Complex Event Processing and modularization allows processing most data in the event space instead of signal processing. A use case for a home care application demonstrates the strength of this methodology.

• Starks, Fabrice; Goebel, Vera Hermine; Kristiansen, Stein & Plagemann, Thomas Peter (2017). Mobile Distributed Complex Event Processing - Ubi Sumus? Quo Vadimus? Universitetet i Oslo. ISSN 9788273684295. Full text in Research Archive Show summary

  One important class of applications for the Internet of Things is related to the need to gain timely and continuous situational awareness, like smart cities, automated traffic control, or emergency and rescue operations. Events happening in the real-world need to be detected in real-time based on sensor data and other data sources. Complex Event Processing (CEP) is a technology to detect complex (or composite) events in data streams and has been successfully applied in high volume and high velocity applications like stock market analysis. However, these application domains faced only the challenge of high performance, while the Internet of Things and Mobile Big Data introduce a new set of challenges caused by mobility. This chapter aims to explain these challenges and to give an overview on how they are solved respectively how far state-of-the-art research has advanced to be useful to solve Mobile Big Data problems. At the infrastructure level the main challenge is to trade performance against resource consumption and energy efficiency and operator placement is the most dominant mechanism to address these problems. At the application and consumer level, mobile queries pose a new set of challenges for CEP related to continuously changing positions of consumers and data sources, and the need to adapt the query processing to these changes. Finally, proper methods and tools for systematical testing and reproducible performance evaluation for mobile distributed CEP are needed but not yet available.

• Rodriguez-Fernandez, Daniel; Kristiansen, Stein; Lindeberg, Morten Gunnar Bjørner; Drugan, Ovidiu Valentin; Cabrero, Sergio & Plagemann, Thomas Peter [Show all 10 contributors for this article] (2012). Delay Tolerant Streaming in Rescue Scenarios: Requirements Analysis and Resulting Industrial Issues - Version 2. Universitetet i Oslo. ISSN 9788273683823. Full text in Research Archive Show summary

  In emergency intervention and rescue operations, the coordination and collaboration of the rescue personnel is highly important for the success of the mission. Data networks formed between the devices carried by the rescue personnel can provide the means for collaboration and coordination on the operation scene. Unfortunately, the unforeseeable conditions and characteristics (e.g., size of the scene, availabilities of access ways for the rescue personnel, availability and status of the infrastructure) of the rescue operations can hinder (e.g., intermittently unavailable network infrastructure) and disrupt (e.g., network partitions) communication of data networks. Even in these adverse conditions coordination and collaboration need to be enabled between the participants of the rescue operation. In this technical report we analyse the usage of streaming services (data, audio and video) to improve coordination and collaboration tasks in rescue and emergency operations. We present a detailed requirement analysis for middleware services that support streaming of data, imposed by this application domain from a research and an industrial perspective. For this purpose, we present two rescue scenarios, which helped us perform the requirements analysis for supporting streaming in intermittently connected networks. Additionally, we also present an example from a middleware for streaming voice traffic within large organizations with multiple working sites. Although these examples might seem different, they have similar requirements considering the availability and awareness of network resources.

View all works in NVA