D. Zeuss, L. Bald, J. Gottwald, et al., “Nature 4.0: A networked sensor system for integrated biodiversity monitoring,” Global Change Biology, Dec. 2023.
@article{zeuss2023nature,
title = {Nature 4.0: A networked sensor system for integrated biodiversity monitoring},
author = {Zeuss, Dirk and Bald, Lisa and Gottwald, Jannis and Becker, Marcel and Bellafkir, Hicham and Bendix, Jörg and Bengel, Phillip and Beumer, Larissa T. and Brandl, Roland and Brändle, Martin and Dahlke, Stephan and Farwig6, Nina and Freisleben, Bernd and Friess, Nicolas and Heidrich, Lea and Heuer, Sven and Höchst, Jonas and Holzmann, Hajo and Lampe, Patrick and Leberecht, Martin and Lindner, Kim and Masello, Juan F. and Möglich, Jonas Mielke and Mühling, Markus and Müller, Thomas and Noskov, Alexey and Opgenoorth, Lars and Peter, Carina and Quillfeldt, Petra and Rösner, Sascha and Royauté, Raphaël and Runge, Christian M. and Schabo, Dana and Schneider, Daniel and Seeger, Bernhard and Shayle, Elliot and Steinmetz, Ralf and Tafo, Pavel and Vogelbacher, Markus and Wöllauer, Stephan and Younis, Sohaib and Zobel, Julian and Nauss, Thomas},
journal = {Global Change Biology},
year = {2023},
month = dec,
publisher = {Wiley Online Library},
keywords = {automated radiotelemetry system, bats, behaviour, birds, generalised additive models, machine learning, Myotis bechsteinii, Nyctalus leisleri, random forest, small animals, tRackIT},
doi = {10.1111/gcb.17056}
}
Ecosystem functions and services are severely threatened by unprecedented global loss in biodiversity. To counteract these trends, it is essential to develop systems to monitor changes in biodiversity for planning, evaluating, and implementing conservation and mitigation actions. However, the implementation of monitoring systems suffers from a trade-off between grain (i.e., the level of detail), extent (i.e., the number of study sites), and temporal repetition. Here, we present an applied and realised networked sensor system for integrated biodiversity monitoring in the Nature 4.0 project as a solution to these challenges, which considers plants and animals not only as targets of investigation, but also as parts of the modular sensor network by carrying sensors. Our networked sensor system consists of three main closely interlinked components with a modular structure: sensors, data transmission, and data storage, which are integrated into pipelines for automated biodiversity monitoring. We present our own real-world examples of applications, share our experiences in operating them, and provide our collected open data. Our flexible, low-cost, and open- source solutions can be applied for monitoring individual and multiple terrestrial plants and animals as well as their interactions. Ultimately, our system can also be applied to area-wide ecosystem mapping tasks, thereby providing an exemplary cost-efficient and powerful solution for biodiversity monitoring. Building upon our experiences in the Nature 4.0 project, we identified ten key challenges that need to be addressed to better understand and counteract the ongoing loss of biodiversity using networked sensor systems. To tackle these challenges, interdisciplinary collaboration, additional research, and practical solutions are necessary to enhance the capability and applicability of networked sensor systems for researchers and practitioners, ultimately further helping to ensure the sustainable management of ecosystems and the provision of ecosystem services.
DetailsA. Sterz, R. Klose, M. Sommer, J. Höchst, J. Link, B. Simon, A. Klein, M. Hollick, and B. Freisleben, “Energy-efficient Broadcast Trees for Decentralized Data Dissemination in Wireless Networks,” in 2023 IEEE 48th Conference on Local Computer Networks (LCN), 2023, pp. 1–4.
@inproceedings{sterz2023energya,
author = {Sterz, Artur and Klose, Robin and Sommer, Markus and Höchst, Jonas and Link, Jakob and Simon, Bernd and Klein, Anja and Hollick, Matthias and Freisleben, Bernd},
booktitle = {2023 IEEE 48th Conference on Local Computer Networks (LCN)},
title = {Energy-efficient Broadcast Trees for Decentralized Data Dissemination in Wireless Networks},
year = {2023},
month = oct,
pages = {1-4},
doi = {10.1109/LCN58197.2023.10223400},
url = {https://ieeexplore.ieee.org/document/10223400}
}
We present a novel multi-hop data dissemination protocol for wireless networks that minimizes the total energy consumption across an entire network by minimizing the transmission power at each hop. It is based on a game-theoretic model, constructs a spanning tree topology in a decentralized manner, and is usable in practice. We evaluate the protocol via simulation and a pratical implementation on a testbed of 75 Raspberry Pis, demonstrating that a total energy reduction of up to 90% can be achieved compared to a simple broadcast protocol.
DetailsV. Salewski, D. Cimiotti, P. Lampe, J. Höchst, and J. Gottwald, “Ein automatisiertes System zur Erfassung der Signale von Radiosendern und seine Anwendung im Rahmen einer Telemetriestudie an Austernfischerküken,” Vogelwarte: Zeitschrift für Vogelkunde, vol. 61, no. 2, pp. 131–146, Sep. 2023.
@article{salewski2023automatisiertes,
author = {Salewski, Volker and Cimiotti, Dominic and Lampe, Patrick and Höchst, Jonas and Gottwald, Jannis},
title = {Ein automatisiertes System zur Erfassung der Signale von Radiosendern und seine Anwendung im Rahmen einer Telemetriestudie an Austernfischerküken},
journal = {Vogelwarte: Zeitschrift für Vogelkunde},
year = {2023},
month = sep,
volume = {61},
number = {2},
pages = {131--146}
}
Research related to species conservation faces a dilemma: High-quality data must be recorded in a sufficient quantity in order to derive successful management measures. However, recording these data can be associated with disturbances that may, for example, negatively affect reproductive success. Automated systems for low-disturbance data collection offer a solution to this dilemma. We present here a system for automated collection of signals from VHF radio transmitters, the tRackIT system, and describe its application to telemetry of oystercatcher chicks Haematopus ostralegus in Schleswig-Holstein, northern Germany. The tRackIT system consists of tRackIT-stations as receiving units of radio signals in the field, an open-source operating system for the stations (tRackIT OS), and the backend provided by tRackIT Systems consisting of a metadatabase (EcoHub), analysis units based on time series databases, and a visualization unit where both, the incoming raw data from the stations and the products from the analysis units are visualized (Grafana). In spring 2022, we set up five tRackIT-stations in Beltring- harder Koog on the west coast of Schleswig-Holstein to automatically record signals from ten tagged Oystercatcher chicks between May and July and to test the suitability of the system for determining survival rates, causes of death and space use of oystercatcher chicks. Of the ten chicks that were tagged, two chicks likely lost the transmitter prematurely, six chicks did not survive the chick stage due to predation or disease, and two chicks fledged. Time of death and first flight could be determined to the minute in some cases. The probability of a chick fledging, estimated with the program MARK, was 35.3 % ± 15.4 %. From seven chicks only a few localizations were available, which could be attributed to an unfavorable spatial relationship of the chicks to the antennas. In three other chicks, 2,333 to 3,571 localizations were available during 18 to 30 days. The tRackIT system proved to be reliable. Storms lasting several days were withstood by the stations and only a few failures occurred, which were always quickly repaired. Precise data on the fate of the chicks could be determined and, in some cases, a high number of localizations could be made. In the following years we will continue the project. We expect that a higher number of tagged chicks and a relocation of the tRackIT-stations carried out after the experiences of the first season will provide extensive data that can be used to better understand the breeding success and population dynamics of oystercatchers in the study area.
DetailsJ. Höchst, L. Baumgärtner, F. Kuntke, A. Penning, A. Sterz, M. Sommer, and B. Freisleben, “Mobile Device-to-Device Communication for Crisis Scenarios Using Low-Cost LoRa Modems,” in Disaster Management and Information Technology: Professional Response and Recovery Management in the Age of Disasters, H. J. Scholl, E. E. Holdeman, and F. K. Boersma, Eds. Cham: Springer International Publishing, 2023, pp. 235–268.
@inbook{hoechst2023mobile,
author = {H{\"o}chst, Jonas and Baumg{\"a}rtner, Lars and Kuntke, Franz and Penning, Alvar and Sterz, Artur and Sommer, Markus and Freisleben, Bernd},
editor = {Scholl, Hans Jochen and Holdeman, Eric E. and Boersma, F. Kees},
title = {Mobile Device-to-Device Communication for Crisis Scenarios Using Low-Cost LoRa Modems},
booktitle = {Disaster Management and Information Technology: Professional Response and Recovery Management in the Age of Disasters},
year = {2023},
month = sep,
publisher = {Springer International Publishing},
address = {Cham},
pages = {235--268},
isbn = {978-3-031-20939-0},
doi = {10.1007/978-3-031-20939-0_12}
}
We present an approach to enable long-range device-to-device communication between smartphones in crisis situations. Our approach is based on inexpensive and readily available microcontrollers with integrated LoRa hardware that we empower to receive and forward messages via Bluetooth, Wi-Fi, or a serial connection by means of a dedicated firmware, called rf95modem. The developed firmware cannot only be used in crisis scenarios but also in a variety of other applications, such as providing a communication fallback during outdoor activities, geolocation-based games or broadcasting of local information. We present two applications to show the benefits of our approach. First, we introduce a novel device-to-device LoRa chat application that works on both Android and iOS as well as on traditional computers like notebooks using a console-based interface. Second, we demonstrate how other infrastructure-less technology can benefit from our approach by integrating it into the DTN7 delay-tolerant networking software. Furthermore, we present the results of an in-depth experimental evaluation of approach consisting of (i) real-world device-to-device LoRa transmissions in urban and rural areas and (ii) scalability tests based on simulations of LoRa device-to-device usage in a medium-sized city with up to 1000 active users. The firmware, our device-to-device chat application, our integration into DTN7, as well as our code fragments of the experimental evaluation and the experimental results are available under permissive open-source licenses.
DetailsA. Sterz, R. Klose, M. Sommer, J. Höchst, J. Link, B. Simon, A. Klein, M. Hollick, and B. Freisleben, “Energy-Efficient Decentralized Broadcasting in Wireless Multi-Hop Networks,” Sensors, vol. 23, no. 17, Aug. 2023.
@article{sterz2023energy,
author = {Sterz, Artur and Klose, Robin and Sommer, Markus and Höchst, Jonas and Link, Jakob and Simon, Bernd and Klein, Anja and Hollick, Matthias and Freisleben, Bernd},
title = {Energy-Efficient Decentralized Broadcasting in Wireless Multi-Hop Networks},
journal = {Sensors},
volume = {23},
year = {2023},
month = aug,
number = {17},
article-number = {7419},
url = {https://www.mdpi.com/1424-8220/23/17/7419},
issn = {1424-8220},
doi = {10.3390/s23177419}
}
Several areas of wireless networking, such as wireless sensor networks or the Internet of Things, require application data to be distributed to multiple receivers in an area beyond the transmission range of a single node. This can be achieved by using the wireless medium’s broadcast property when retransmitting data. Due to the energy constraints of typical wireless devices, a broadcasting scheme that consumes as little energy as possible is highly desirable. In this article, we present a novel multi-hop data dissemination protocol called BTP. It uses a game-theoretical model to construct a spanning tree in a decentralized manner to minimize the total energy consumption of a network by minimizing the transmission power of each node. Although BTP is based on a game-theoretical model, it neither requires information exchange between distant nodes nor time synchronization during its operation, and it inhibits graph cycles effectively. The protocol is evaluated in Matlab and NS-3 simulations and through real-world implementation on a testbed of 75 Raspberry Pis. The evaluation conducted shows that our proposed protocol can achieve a total energy reduction of up to 90% compared to a simple broadcast protocol in real-world experiments.
Details
J. Gottwald, R. Royauté, M. Becker, T. Geitz, J. Höchst, P. Lampe, L. Leister, K. Lindner, J. Maier, S. Rösner, D. G. Schabo, B. Freisleben, R. Brandl, T. Müller, N. Farwig, and T. Nauss, “Classifying the activity states of small vertebrates using automated VHF telemetry,” Methods in Ecology and Evolution, Dec. 2022.
@article{gottwald2022classifying,
author = {Gottwald, Jannis and Royauté, Raphaël and Becker, Marcel and Geitz, Tobias and Höchst, Jonas and Lampe, Patrick and Leister, Lea and Lindner, Kim and Maier, Julia and Rösner, Sascha and Schabo, Dana G. and Freisleben, Bernd and Brandl, Roland and Müller, Thomas and Farwig, Nina and Nauss, Thomas},
title = {Classifying the activity states of small vertebrates using automated {VHF} telemetry},
journal = {Methods in Ecology and Evolution},
year = {2022},
month = dec,
keywords = {automated radiotelemetry system, bats, behaviour, birds, generalised additive models, machine learning, Myotis bechsteinii, Nyctalus leisleri, random forest, small animals, tRackIT},
doi = {10.1111/2041-210X.14037}
}
Abstract The most basic behavioural states of animals can be described as active or passive. While high-resolution observations of activity patterns can provide insights into the ecology of animal species, few methods are able to measure the activity of individuals of small taxa in their natural environment. We present a novel approach in which a combination of automatic radiotracking and machine learning is used to distinguish between active and passive behaviour in small vertebrates fitted with lightweight transmitters (<0.4 g). We used a dataset containing >3 million signals from very-high-frequency (VHF) telemetry from two forest-dwelling bat species (Myotis bechsteinii [n = 52] and Nyctalus leisleri [n = 20]) to train and test a random forest model in assigning either active or passive behaviour to VHF-tagged individuals. The generalisability of the model was demonstrated by recording and classifying the behaviour of tagged birds and by simulating the effect of different activity levels with the help of humans carrying transmitters. The model successfully classified the activity states of bats as well as those of birds and humans, although the latter were not included in model training (F1 0.96–0.98). We provide an ecological case-study demonstrating the potential of this automated monitoring tool. We used the trained models to compare differences in the daily activity patterns of two bat species. The analysis showed a pronounced bimodal activity distribution of N. leisleri over the course of the night while the night-time activity of M. bechsteinii was relatively constant. These results show that subtle differences in the timing of species’ activity can be distinguished using our method. Our approach can classify VHF-signal patterns into fundamental behavioural states with high precision and is applicable to different terrestrial and flying vertebrates. To encourage the broader use of our radiotracking method, we provide the trained random forest models together with an R package that includes all necessary data processing functionalities. In combination with state-of-the-art open-source automated radiotracking, this toolset can be used by the scientific community to investigate the activity patterns of small vertebrates with high temporal resolution, even in dense vegetation.
DetailsJ. Höchst, “Smart Distributed Sensing in Adaptive Wireless Networks,” PhD thesis, Philipps-Universität Marburg, 2022.
@phdthesis{hoechst2022smart,
author = {Höchst, Jonas},
title = {Smart Distributed Sensing in Adaptive Wireless Networks},
school = {Philipps-Universität Marburg},
year = {2022},
month = oct
}
In the recent past, great progress has been made in three technological areas of computer science: sensing, softwarization of networks, and machine learning. Currently, a large variety of sensors is available in many devices, and sensors are getting smaller and more energy-efficient. Software-defined networks are becoming more widespread, achieving low latency and high throughput for emerging applications. Machine learning is very successful in creating and improving services in numerous applications at the edge and in the cloud. There is a great potential in the overlap of these areas: (a) smart processing of sensor data using machine learning methods makes potentially huge amounts of data manageable; (b) adaptive networks support the immediate availability of sensor data in several application areas, and (c) sensor data and machine learning methods are already used in the field of adaptive networks to improve the quality of service.
In this thesis, approaches are presented to improve the quality of service, the quality of experience, and the quality of results of algorithms, protocols, and applications using different sensors and sensor sources. The information analysis cost and the achievable quality of different approaches within the same domain are compared, and a novel classification of smart systems is presented. The main challenge is to balance the information analysis cost generated by additional communication, computation, and storage with the quality improvement achievable by the novel methods. This challenge is addressed by presenting different approaches, algorithms, and systems in the areas of environmental monitoring, adaptive disruption-tolerant networking, and transitional wireless networking.
In the area of smart environmental monitoring, flexible single-board computers are used to realize improvements of various sensing tasks, especially spatial movement and visual / acoustic observation of bats, as well as automated recognition of bird species in audio recordings.
In the area of smart adaptive disruption-tolerant networking, different implementations of disruption-tolerant networks, systems for opportunistic execution of functions and workflows, and novel sensor-based routing algorithms are presented.
Insights from the two areas will be used to develop novel approaches in the area of smart transitional wireless networks for classifying network traffic flow using machine learning, for dynamic announcement intervals in service discovery, and for Wi-Fi connection loss prediction to perform seamless Wi-Fi/cellular handovers.
DetailsP. Lampe, M. Sommer, A. Sterz, J. Höchst, C. Uhl, and B. Freisleben, “Unobtrusive Mechanism Interception,” in 2022 IEEE 47th Conference on Local Computer Networks (LCN), Edmonton, Canada, 2022.
@inproceedings{lampe2022unobtrusive,
author = {Lampe, Patrick and Sommer, Markus and Sterz, Artur and {H{\"o}chst}, Jonas and Uhl, Christian and Freisleben, Bernd},
title = {Unobtrusive Mechanism Interception},
booktitle = {2022 IEEE 47th Conference on Local Computer Networks (LCN)},
address = {Edmonton, Canada},
days = {26},
month = sep,
year = {2022},
doi = {10.1109/LCN53696.2022.9843536}
}
Networked systems and applications are often based on proprietary hardware/software components that manufacturers might not be willing to adapt or update if new requirements arise. We present mechanism interception, a novel approach to unobtrusively add or modify functionality to/of an existing networked system or application without touching any proprietary components. Behavioral changes are achieved by functionality-enhancing yet unobtrusive interceptors, i.e., components introduced between systems and their environments adding or updating mechanisms. We illustrate our approach by unobtrusively adding a vertical handover mechanism between Wi-Fi and LTE to a mobile end device without disconnecting TCP sessions. Our results indicate that mechanism interception is a compelling approach to achieve improved service quality and provide previously unavailable functionality.
DetailsP. Lampe, M. Sommer, A. Sterz, J. Höchst, C. Uhl, and B. Freisleben, “ForestEdge: Unobtrusive Mechanism Interception in Environmental Monitoring,” in 2022 IEEE 47th Conference on Local Computer Networks (LCN), Edmonton, Canada, 2022.
@inproceedings{lampe2022forestedge,
author = {Lampe, Patrick and Sommer, Markus and Sterz, Artur and {H{\"o}chst}, Jonas and Uhl, Christian and Freisleben, Bernd},
title = {{ForestEdge:} Unobtrusive Mechanism Interception in Environmental Monitoring},
booktitle = {2022 IEEE 47th Conference on Local Computer Networks (LCN)},
address = {Edmonton, Canada},
days = {26},
month = sep,
year = {2022},
doi = {10.1109/LCN53696.2022.9843426}
}
A network for environmental monitoring typically requires a large number of sensors. If a longer service life is intended, it is essential that the deployed sensor systems can be upgraded without modifying hardware. Often, these networks rely on proprietary hardware/software components tailored to the desired functionality, but these could technically also be used for other applications. We present a demo of mechanism interception, a novel approach to unobtrusively add or modify the functionality of an existing networked system, in our case a TreeTalker, without touching any proprietary components. We demonstrate how a cloud infrastructure can be unobtrusively replaced by an edge infrastructure in a wireless sensor network. Our results indicate that mechanism interception is a compelling approach for our scenario to provide previously unavailable functionality without modifying existing components.
DetailsJ. Höchst, H. Bellafkir, P. Lampe, M. Vogelbacher, M. Mühling, D. Schneider, K. Lindner, S. Rösner, D. G. Schabo, N. Farwig, and B. Freisleben, “Bird@Edge: Bird Species Recognition at the Edge,” in International Conference on Networked Systems (NETYS), 2022.
@inproceedings{hoechst2022birdedge,
title = {{Bird@Edge: Bird Species Recognition at the Edge}},
author = {H{\"o}chst, Jonas and Bellafkir, Hicham and Lampe, Patrick and Vogelbacher, Markus and M{\"u}hling, Markus and Schneider, Daniel and Lindner, Kim and R{\"o}sner, Sascha and Schabo, Dana G. and Farwig, Nina and Freisleben, Bernd},
booktitle = {International Conference on Networked Systems (NETYS)},
year = {2022},
month = may,
organization = {Springer},
keywords = {Bird Species Recognition, Edge Computing, Passive Acoustic Monitoring, Biodiversity},
doi = {10.1007/978-3-031-17436-0_6},
meta_key = {Talk Recording},
meta_val = {https://www.youtube.com/watch?v=reAm4HSyQl8}
}
We present Bird@Edge, an Edge AI system for recognizing bird species in audio recordings to support real-time biodiversity monitoring. Bird@Edge is based on embedded edge devices operating in a distributed system to enable efficient, continuous evaluation of soundscapes recorded in forests. Multiple ESP32-based microphones (called Bird@Edge Mics) stream audio to a local Bird@Edge Station, on which bird species recognition is performed. The results of several Bird@Edge Stations are transmitted to a backend cloud for further analysis, e.g., by biodiversity researchers. To recognize bird species in soundscapes, a deep neural network based on the EfficientNet-B3 architecture is trained and optimized for execution on embedded edge devices and deployed on a NVIDIA Jetson Nano board using the DeepStream SDK. Our experiments show that our deep neural network outperforms the state-of-the-art BirdNET neural network on several data sets and achieves a recognition quality of up to 95.2% mean average precision on soundscape recordings in the Marburg Open Forest, a research and teaching forest of the University of Marburg, Germany. Measurements of the power consumption of the Bird@Edge components highlight the real-world applicability of the approach. All software and firmware components of Bird@Edge are available under open source licenses.
DetailsM. Sommer, J. Höchst, A. Sterz, A. Penning, and B. Freisleben, “ProgDTN: Programmable Disruption-tolerant Networking,” in International Conference on Networked Systems (NETYS), 2022.
@inproceedings{sommer2022progdtn,
title = {{ProgDTN: Programmable Disruption-tolerant Networking}},
author = {Sommer, Markus and Höchst, Jonas and Sterz, Artur and Penning, Alvar and Freisleben, Bernd},
booktitle = {International Conference on Networked Systems (NETYS)},
year = {2022},
month = may,
organization = {Springer},
doi = {10.1007/978-3-031-17436-0_13},
meta_key = {Talk Recording},
meta_val = {https://www.youtube.com/watch?v=u9lgwYoCZEE}
}
Existing routing algorithms for disruption-tolerant networking (DTN) have two main limitations: (a) a particular DTN routing algorithm is typically designed to achieve very good performance in a specific scenario, but has limited performance in other scenarios, and (b) DTN routing algorithms do not take advantage of network programmability to profit from its benefits. We present ProgDTN, a novel approach to support programmable disruption-tolerant networking by allowing network operators to implement and adapt routing algorithms without knowledge of a router’s interior workings using the popular JavaScript language. To consider the specific properties of a particular application scenario, network operators can incorporate context information of DTN bundles and nodes in their routing algorithms. ProgDTN is based on DTN7, a flexible and efficient open-source, platform-independent implementation of the Bundle Protocol version 7. Our experimental evaluation demonstrates that using ProgDTN to tailor a routing algorithm to a particular scenario achieves excellent results of up to 99.9% delivery ratio while reducing unnecessary transmissions by 92.9%. ProgDTN’s implementation, our tailored scenario-specific routing algorithm, and code/data fragments for our experiments are released under permissive open-source licenses
Details
J. Höchst, J. Gottwald, P. Lampe, J. Zobel, T. Nauss, R. Steinmetz, and B. Freisleben, “tRackIT OS: Open-source Software for Reliable VHF Wildlife Tracking,” in 51. Jahrestagung der Gesellschaft für Informatik, Digitale Kulturen, INFORMATIK 2021, Berlin, Germany, 2021.
@inproceedings{hoechst2021tRackIT,
title = {{tRackIT OS: Open-source Software for Reliable VHF Wildlife Tracking}},
author = {Höchst, Jonas and Gottwald, Jannis and Lampe, Patrick and Zobel, Julian and Nauss, Thomas and Steinmetz, Ralf and Freisleben, Bernd},
booktitle = {51. Jahrestagung der Gesellschaft f{\"{u}}r Informatik, Digitale Kulturen, {INFORMATIK} 2021, Berlin, Germany},
series = {{LNI}},
publisher = {{GI}},
month = sep,
year = {2021},
doi = {10.18420/informatik2021-035}
}
We present tRackIT OS, open-source software for reliable VHF radio tracking of (small) animals in their wildlife habitat. tRackIT OS is an operating system distribution for tRackIT stations that receive signals emitted by VHF tags mounted on animals and are built from low-cost commodity-off-the-shelf hardware. tRackIT OS provides software components for VHF signal processing, system monitoring, configuration management, and user access. In particular, it records, stores, analyzes, and transmits detected VHF signals and their descriptive features, e.g., to calculate bearings of signals emitted by VHF radio tags mounted on animals or to perform animal activity classification. Furthermore, we provide results of an experimental evaluation carried out in the Marburg Open Forest, the research and teaching forest of the University of Marburg, Germany. All components of tRackIT OS are available under a GNU GPL 3.0 open source license at https://github.com/nature40/tRackIT-OS.
DetailsJ. Zobel, P. Frommelt, P. Lieser, J. Höchst, P. Lampe, B. Freisleben, and R. Steinmetz, “Energy-efficient Mobile Sensor Data Offloading via WiFi using LoRa-based Connectivity Estimations,” in 51. Jahrestagung der Gesellschaft für Informatik, Digitale Kulturen, INFORMATIK 2021, Berlin, Germany, 2021.
@inproceedings{zobel2021energy,
title = {{Energy-efficient Mobile Sensor Data Offloading via WiFi using LoRa-based Connectivity Estimations}},
author = {Zobel, Julian and Frommelt, Paul and Lieser, Patrick and Höchst, Jonas and Lampe, Patrick and Freisleben, Bernd and Steinmetz, Ralf},
booktitle = {51. Jahrestagung der Gesellschaft f{\"{u}}r Informatik, Digitale Kulturen, {INFORMATIK} 2021, Berlin, Germany},
series = {{LNI}},
publisher = {{GI}},
month = sep,
year = {2021},
doi = {10.18420/informatik2021-037}
}
Long-term animal monitoring in natural habitats provides significant insights into the animals’ behavior, interactions, health, or external influences. However, the sizes of monitoring devices attachable to animals strongly depends on the animals’ sizes, and thus the range of possible sensors including batteries is severely limited. Gathered data can be offloaded from monitoring devices to data sinks in a wireless sensor network using available radio access technologies, but this process also needs to be as energy-efficient as possible. This paper presents an approach to combine the benefits of high-throughput WiFi and robust low-power LoRa communication for energy-efficient data offloading. WiFi is only used when connectivity between mobile devices and data sinks is available, which is determined by LoRa-based distance estimations without the need for additional GPS sensors. A prototypical implementation on low-end commodity-off-the-shelf hardware is used to evaluate the proposed approach in a German mixed forest using a simple path loss model for distance estimation. The system provides an offloading success rate of 87%, which is similar to that of a GPS-based approach, but with around 37% less power consumption.
DetailsJ. Gottwald, P. Lampe, J. Höchst, N. Friess, J. Maier, L. Leister, B. Neumann, T. Richter, B. Freisleben, and T. Nauss, “BatRack: An open-source multi-sensor device for wildlife research,” Methods in Ecology and Evolution, Jul. 2021.
@article{gottwald2021batrack,
title = {{BatRack: An open-source multi-sensor device for wildlife research}},
author = {Gottwald, Jannis and Lampe, Patrick and H{\"o}chst, Jonas and Friess, Nicolas and Maier, Julia and Leister, Lea and Neumann, Betty and Richter, Tobias and Freisleben, Bernd and Nauss, Thomas},
journal = {Methods in Ecology and Evolution},
publisher = {Wiley Online Library},
month = jul,
year = {2021},
keywords = {Automatic Radio Tracking, Bats, Behavioural Ecology, Camera Traps, Multi-Sensor, Passive Acoustic Monitoring},
doi = {10.1111/2041-210X.13672}
}
Bats represent a highly diverse group of mammals and are essential for ecosystem functioning. However, knowledge about their behavior, ecology, and conservation status is limited. Direct observation of marked individuals (commonly applied to birds) is not possible for bats due to their small size, rapid movement, and nocturnal lifestyle, while neither popular observation methods such as camera traps nor conventional tracking technologies sufficiently capture the behavior of individuals. The combination and networking of different sensors in a single system can overcome these limitations, but this potential has been explored only to a limited extent.
We present BatRack, a multi-sensor device that combines ultrasonic audio recordings, automatic radio telemetry, and video camera recordings in a single modular unit. BatRack facilitates the individual or combined scheduling of sensors and includes a mutual triggering mode. It consists of off-the-shelf hardware and both its hardware blueprints and the required software have been published under an open license to allow scientists and practitioners to replicate the system.
We tested the suitability of radio telemetry and audio sensors as camera triggers and evaluated the detection of individuals in video recordings compared to radio telemetry signals. Specifically, BatRack was used to monitor the individual swarming behavior of six members of a maternity colony of Bechstein’s bat. Preliminary anecdotal results indicate that swarming intensity is related to reproductive state and roost switching..
BatRack allows researchers to recognize individual bats and monitor their behavioral patterns using an easily deployed and scalable system. BatRack is thus a promising approach to obtaining detailed insights into the behavioral ecology of bats.
DetailsJ. Nguyen, K. Kesper, G. Kräling, et al., “Repurposing CPAP machines as stripped-down ventilators,” Scientific reports, vol. 11, no. 1, pp. 1–9, Jun. 2021.
@article{nguyen2021repurposing,
title = {Repurposing CPAP machines as stripped-down ventilators},
author = {Nguyen, Johnny and Kesper, Karl and Kräling, Gunter and Birk, Christian and Mross, Peter and Hofeditz, Nico and Höchst, Jonas and Lampe, Patrick and Penning, Alvar and Leutenecker-Twelsiek, Bastian and Schindler, Carsten and Buchenauer, Helwig and Geisel, David and Sommer, Caroline and Henning, Ronald and Wallot, Pascal and Wiesmann, Thomas and Beutel, Björn and Schneider, Gunter and Castro-Camus, Enrique and Koch, Martin},
journal = {Scientific reports},
volume = {11},
number = {1},
pages = {1--9},
month = jun,
year = {2021},
publisher = {Nature Publishing Group},
doi = {10.1038/s41598-021-91673-7}
}
The worldwide shortage of medical‐grade ventilators is a well‐known issue, that has become one of the central topics during the COVID‐19 pandemic. Given that these machines are expensive and have long lead times, one approach is to vacate them for patients in critical conditions while patients with mild to moderate symptoms are treated with stripped‐down ventilators. We propose a mass‐ producible solution that can create such ventilators with minimum effort. The central part is a module that can be attached to CPAP machines and repurpose them as low‐pressure ventilators. Here, we describe the concept and first measurements which underline the potential of our solution. Our approach may serve as a starting point for open‐access ventilator technologies.
Details
L. Baumgärtner, A. Dmitrienko, B. Freisleben, A. Gruler, J. Höchst, J. Kühlberg, M. Mezini, R. Mitev, M. Miettinen, A. Muhamedagic, T. D. Nguyen, A. Penning, D. Pustelnik, F. Roos, A.-R. Sadeghi, M. Schwarz, and C. Uhl, “Mind the GAP: Security & Privacy Risks of Contact Tracing Apps,” in 2020 IEEE 19th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom), 2020, vol. 1, pp. 458–467.
@inproceedings{baumgaertner2020mind,
author = {Baumgärtner, Lars and Dmitrienko, Alexandra and Freisleben, Bernd and Gruler, Alexander and Höchst, Jonas and Kühlberg, Joshua and Mezini, Mira and Mitev, Richard and Miettinen, Markus and Muhamedagic, Anel and Nguyen, Thien Duc and Penning, Alvar and Pustelnik, Dermot and Roos, Filipp and Sadeghi, Ahmad-Reza and Schwarz, Michael and Uhl, Christian},
title = {{Mind the GAP: Security & Privacy Risks of Contact Tracing Apps}},
booktitle = {2020 IEEE 19th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)},
organization = {IEEE},
year = {2020},
month = dec,
volume = {1},
pages = {458-467},
doi = {10.1109/TrustCom50675.2020.00069},
keywords = {Contact Tracing Apps, Exposure Notification API}
}
Google and Apple have jointly provided an API for exposure notification in order to implement decentralized contract tracing apps using Bluetooth Low Energy, the so-called "Google/Apple Proposal", which we abbreviate by "GAP". We demonstrate that in real-world scenarios the current GAP design is vulnerable to (i) profiling and possibly de-anonymizing infected persons, and (ii) relay-based wormhole attacks that basically can generate fake contacts with the potential of affecting the accuracy of an app-based contact tracing system. For both types of attack, we have built tools that can easily be used on mobile phones or Raspberry Pis (e.g., Bluetooth sniffers). The goal of our work is to perform a reality check towards possibly providing empirical real-world evidence for these two privacy and security risks. We hope that our findings provide valuable input for developing secure and privacy-preserving digital contact tracing systems.
DetailsJ. Höchst, A. Penning, P. Lampe, and B. Freisleben, “PIMOD: A Tool for Configuring Single-Board Computer Operating System
Images,” in 2020 IEEE Global Humanitarian Technology Conference (GHTC 2020), Seattle, USA, 2020, pp. 1–8.
@inproceedings{hoechst2020pimod,
author = {{Höchst}, Jonas and Penning, Alvar and Lampe, Patrick and Freisleben, Bernd},
title = {{PIMOD: A Tool for Configuring {Single-Board} Computer Operating System
Images}},
booktitle = {{2020 IEEE Global Humanitarian Technology Conference (GHTC 2020)}},
address = {Seattle, USA},
days = {29},
month = oct,
pages = {1-8},
doi = {10.1109/GHTC46280.2020.9342928},
year = {2020},
keywords = {Single-Board Computer; Operating System Image; System Provisioning},
meta_key = {Talk Recording},
meta_val = {https://www.youtube.com/watch?v=j-R7PTJvMEg}
}
Computer systems used in the field of humanitarian technology are often based on general-purpose single-board computers, such as Raspberry Pis. While these systems offer great flexibility for developers and users, configuration and deployment either introduces overhead by executing scripts on multiple devices or requires deeper technical understanding when building operating system images for such small computers from scratch.
In this paper, we present PIMOD, a software tool for configuring operating system images for single-board computer systems. We propose a simple yetcomprehensive configuration language. In a configuration profile, called Pifile, a small set of commands is used to describe the configuration of an operating system image. Virtualization techniques are used during the execution of the profile in order to be distribution and platform independent. Commands can be issued in the guest operating system, providing access to the distribution specific tools, e.g., to configure hardware parameters. The implementation of PIMOD is made public under a free and open source license. PIMOD is evaluated in terms of user benefits, performance compared to on-system configuration, and applicability across different hardware platforms and operating systems.
DetailsJ. Höchst, L. Baumgärtner, F. Kuntke, A. Penning, A. Sterz, and B. Freisleben, “LoRa-based Device-to-Device Smartphone Communication for Crisis Scenarios,” in 17th International Conference on Information Systems for Crisis Response and Management (ISCRAM 2020), Blacksburg, Virginia, USA, 2020.
@inproceedings{hoechst2020lora,
author = {{Höchst}, Jonas and {Baumgärtner}, Lars and Kuntke, Franz and Penning, Alvar and Sterz, Artur and Freisleben, Bernd},
title = {{LoRa-based Device-to-Device Smartphone Communication for Crisis Scenarios}},
booktitle = {{17th International Conference on Information Systems for Crisis Response and Management (ISCRAM 2020)}},
address = {Blacksburg, Virginia, USA},
month = may,
year = {2020},
keywords = {LoRa, Disaster Communication, Device-To-Device Communication}
}
In this paper, we present an approach to facilitate long-range device-to-device communication via smartphones in crisis scenarios. Through a custom firmware for low-cost LoRa capable micro-controller boards, called rf95modem, common devices for end users can be enabled to use LoRa through a Bluetooth, Wi-Fi, or serial connection. We present two applications utilizing the flexibility provided by the proposed firmware. First, we introduce a novel device-to-device LoRa chat application that works a) on the two major mobile platforms Android and iOS and b) on traditional computers like notebooks using a console-based interface. Second, we demonstrate how other infrastructure-less technology can benefit from our approach by integrating it into the DTN7 delay-tolerant networking software. The firmware, the device-to-device chat application, the integration into DTN7, as well as the experimental evaluation code fragments are available under permissive open-source licenses.
Details
L. Baumgärtner, J. Höchst, and T. Meuser, “B-DTN7: Browser-based Disruption-tolerant Networking via Bundle Protocol 7,” in 2019 International Conference on Information and Communication Technologies
for Disaster Management (ICT-DM’19), Paris, France, 2019.
@inproceedings{baumgaertner2019bdtn7,
author = {{Baumgärtner}, Lars and {Höchst}, Jonas and Meuser, Tobias},
title = {{B-DTN7: Browser-based Disruption-tolerant Networking via Bundle Protocol 7}},
booktitle = {{2019 International Conference on Information and Communication Technologies
for Disaster Management (ICT-DM'19)}},
address = {Paris, France},
days = {17},
month = dec,
year = {2019},
keywords = {DTN; wasm; emergency communication},
doi = {10.1109/ICT-DM47966.2019.9032944}
}
During and after the event of a crisis, means of communication are vital for civilians and professional responders alike. In particular, technologies such as disruption-tolerant networking (DTN) can play a key role to distribute data even under challenging network conditions. Such networks benefit from an increased number of mobile participants, since they help distribute messages to remote places. Unfortunately, it is unrealistic to assume that smartphone vendors will ship the necessary software or users will be prepared with the needed apps installed before the crisis happens. Currently, smartphone apps usually need Internet connections to be installed from an app store and/or are very platform specific, i.e., there is no general device-to-device app distribution. We present a novel solution to let any user with a web browser persistently participate in a DTN network. By leveraging a newly written Bundle Protocol 7 draft implementation in the programming language Rust and deploying to WebAssembly, we provide a secure and efficient way for backend and frontend DTN networks.
The presented solution incorporates classic DTN daemons and access points for web app distribution and bundle synchronisation. Through benchmarks we show the efficient processing of bundles and the feasibility of bundle handling in browsers. All code is available as open-source under a permissive license.
DetailsA. Penning, L. Baumgärtner, J. Höchst, A. Sterz, M. Mezini, and B. Freisleben, “DTN7: An Open-Source Disruption-tolerant Networking Implementation of Bundle Protocol 7,” in 18th International Conference on Ad Hoc Networks and Wireless (ADHOC-NOW 2019), Esch-sur-Alzette, Luxemburg, 2019.
@inproceedings{penning2019dtn,
author = {Penning, Alvar and Baumgärtner, Lars and Höchst, Jonas and Sterz, Artur and Mezini, Mira and Freisleben, Bernd},
title = {DTN7: An Open-Source Disruption-tolerant Networking Implementation of Bundle Protocol 7},
booktitle = {18th International Conference on Ad Hoc Networks and Wireless (ADHOC-NOW 2019)},
address = {Esch-sur-Alzette, Luxemburg},
days = {01},
month = oct,
year = {2019},
doi = {10.1007/978-3-030-31831-4_14},
url = {https://dtn7.github.io/#adhoc-now-2019-conference}
}
In disruption-tolerant networking (DTN), data is transmitted in a store-carry-forward fashion from network node to network node. In this paper, we present an open source DTN implementation, called DTN7, of the recently released Bundle Protocol Version 7 (draft version 13). DTN7 is written in Go and provides features like memory safety and concurrent execution. With its modular design and interchangeable components, DTN7 facilitates DTN research and application development. Furthermore, we present results of a comparative experimental evaluation of DTN7 and other DTN systems including Serval, IBR-DTN, and Forban. Our results indicate that DTN7 is a flexible and efficient open-source multi-platform implementation of the most recent Bundle Protocol Version 7.
DetailsJ. Höchst, A. Sterz, A. Frömmgen, D. Stohr, R. Steinmetz, and B. Freisleben, “Learning Wi-Fi Connection Loss Predictions for Seamless Vertical
Handovers Using Multipath TCP,” in 2019 IEEE 44th Conference on Local Computer Networks (LCN), Osnabrück, Germany, 2019.
@inproceedings{hoechst2019learning,
author = {H{\"o}chst, Jonas and Sterz, Artur and {Fr{\"o}mmgen}, Alexander and Stohr, Denny and Steinmetz, Ralf and Freisleben, Bernd},
title = {{Learning Wi-Fi Connection Loss Predictions for Seamless Vertical
Handovers Using Multipath TCP}},
booktitle = {{2019 IEEE 44th Conference on Local Computer Networks (LCN)}},
address = {Osnabr{\"u}ck, Germany},
days = {13},
month = oct,
year = {2019},
url = {https://umr-ds.github.io/seamcon/},
doi = {10.1109/LCN44214.2019.8990753},
meta_key = {Talk Recording},
meta_val = {https://www.youtube.com/watch?v=vpD3yTvSpD4}
}
We present a novel data-driven approach to perform smooth Wi-Fi/cellular handovers on smartphones. Our approach relies on data provided by multiple smartphone sensors (e.g., Wi-Fi RSSI, acceleration, compass, step counter, air pressure) to predict Wi-Fi connection loss and uses Multipath TCP to dynamically switch between different connectivity modes. We train a random forest classifier and an artificial neural network on real-world sensor data collected by five smartphone users over a period of three months. The trained models are executed on smartphones to reliably predict Wi-Fi connection loss 15 seconds ahead of time, with a precision of up to 0.97 and a recall of up to 0.98. Furthermore, we present results for four DASH video streaming experiments that run on a Nexus 5 smartphone using available Wi-Fi/cellular networks. The neural network predictions for Wi-Fi connection loss are used to establish MPTCP subflows on the cellular link. The experiments show that our approach provides seamless wireless connectivity, improves quality of experience of DASH video streaming, and requires less cellular data compared to handover approaches without Wi-Fi connection loss predictions.
DetailsA. Sterz, L. Baumgärtner, J. Höchst, P. Lampe, and B. Freisleben, “OPPLOAD: Offloading Computational Workflows in Opportunistic Networks,” in 2019 IEEE 44th Conference on Local Computer Networks (LCN), Osnabrück, Germany, 2019.
@inproceedings{sterz2019oppload,
author = {Sterz, Artur and {Baumg{\"a}rtner}, Lars and {H{\"o}chst}, Jonas and Lampe, Patrick and Freisleben, Bernd},
title = {{OPPLOAD: Offloading Computational Workflows in Opportunistic Networks}},
booktitle = {{2019 IEEE 44th Conference on Local Computer Networks (LCN)}},
address = {Osnabr{\"u}ck, Germany},
days = {13},
month = oct,
year = {2019},
doi = {10.1109/LCN44214.2019.8990775}
}
Computation offloading is often used in mobile cloud computing, edge computing, and/or fog computing to cope with resource limitations of mobile devices in terms of computational power, storage, and energy. Computation offloading is particularly challenging in situations where network connectivity is periodic, intermittent, or error-prone. In this paper, we present OPPLOAD, a novel framework designed for offloading computational workflows in opportunistic networks that provide support for communication in such situations. The individual tasks forming a workflow can be assigned to particular remote execution platforms, called workers, either preselected ahead of time or decided just in time where a matching worker will automatically be assigned for the next task in the workflow. Workers announce their capabilities, i.e., tasks are only assigned to capable workers. Furthermore, tasks of a workflow can be executed on multiple workers that are automatically selected to balance the overall load. OPPLOAD also offers the ability to handle several types of error and exceptions appropriately. Our Python implementation of OPPLOAD, which uses the Serval Mesh to handle networking and routing, is publicly available as open source software. The results of our experimental evaluation demonstrate the feasibility of our approach.
DetailsL. Baumgärtner, P. Lampe, J. Höchst, R. Mogk, A. Sterz, P. Weisenburger, M. Mezini, and B. Freisleben, “Smart Street Lights and Mobile Citizen Apps for Resilient Communication in a Digital City,” in 2019 IEEE Global Humanitarian Technology Conference (GHTC 2019), Seattle, USA, 2019.
@inproceedings{baumgaertner2019smart,
author = {{Baumg{\"a}rtner}, Lars and Lampe, Patrick and {H{\"o}chst}, Jonas and Mogk, Ragnar and Sterz, Artur and Weisenburger, Pascal and Mezini, Mira and Freisleben, Bernd},
title = {Smart Street Lights and Mobile Citizen Apps for Resilient Communication in a Digital City},
booktitle = {{2019 IEEE Global Humanitarian Technology Conference (GHTC 2019)}},
address = {Seattle, USA},
days = {17},
month = oct,
year = {2019},
doi = {10.1109/GHTC46095.2019.9033134}
}
Currently, nearly four billion people live in urban areas. Since this trend is increasing, natural disasters or terrorist attacks in such areas affect an increasing number of people. While information and communication technology is crucial for the operation of urban infrastructures and the well-being of its inhabitants, current technology is quite vulnerable to disruptions of various kinds. In future smart cities, a more resilient urban infrastructure is imperative to handle the increasing number of hazardous situations. We present a novel resilient communication approach based on smart street lights as part of the public infrastructure. It supports people in their everyday life and adapts its functionality to the challenges of emergency situations. Our approach relies on various environmental sensors and in-situ processing for automatic situation assessment, and a range of communication mechanisms (e.g., public WiFi hotspot functionality and mesh networking) for maintaining a communication network. Furthermore, resilience is not only achieved based on infrastructure deployed by a digital city’s municipality, but also based on integrating citizens through software that runs on their mobile devices (e.g., smartphones and tablets). Web-based zero-installation and platform-agnostic apps can switch to device-to-device communication to continue benefiting people even during a disaster situation. Our approach, featuring a covert channel for professional responders and the zero-installation app, is evaluated through a prototype implementation based on a commercially available street light.
DetailsM. Luthra, B. Koldehofe, J. Höchst, P. Lampe, A. H. Rizvi, and B. Freisleben, “INetCEP: In-Network Complex Event Processing for Information-Centric Networking,” in 15th ACM/IEEE Symposium on Architectures for Networking and Communications Systems (ANCS 2019), Cambridge, UK, 2019.
@inproceedings{luthra2019inetcep,
author = {Luthra, Manisha and Koldehofe, Boris and Höchst, Jonas and Lampe, Patrick and Rizvi, Ali Haider and Freisleben, Bernd},
title = {INetCEP: In-Network Complex Event Processing for Information-Centric Networking},
booktitle = {15th ACM/IEEE Symposium on Architectures for Networking and Communications Systems (ANCS 2019)},
address = {Cambridge, UK},
days = {24},
month = sep,
year = {2019},
doi = {10.1109/ANCS.2019.8901877},
url = {https://www.kom.tu-darmstadt.de/research-results/publications/publications-details/?pub_id=LKH\%2B19-1}
}
Emerging network architectures like Information-Centric Networking (ICN) offer inherent simplicity in the data plane by addressing named data. Such flexibility opens up the possibility to move data processing inside network elements for high-performance computation, widely known as in-network processing. However, existing ICN architectures are limited in terms of (i) in-network processing and (ii) data plane programming abstractions. Such architectures can benefit from Complex Event Processing (CEP), an in-network processing paradigm to efficiently process data inside the data plane. Yet, it is extremely challenging to integrate CEP because the current communication model of ICN is limited to consumer-initiated interaction that comes with significant overhead in number of requests to process continuous data streams. In contrast, a change to producer-initiated interaction, as favored by CEP, imposes severe limitations for request-reply interactions.
In this paper, we propose an in-network CEP architecture, INetCEP that supports unified interaction patterns (consumer- and producer-initiated) over ICN. In addition, we provide a CEP query language and facilitate CEP operations while increasing the range of Internet-of-Things (IoT) applications that can be supported by ICN. We provide an open source implementation and evaluation of INetCEP over an ICN architecture, Named Function Networking and two IoT applications: energy forecasting in smart homes and a disaster scenario.
Details
J. Höchst, L. Baumgärtner, M. Hollick, and B. Freisleben, “Unsupervised Traffic Flow Classification Using a Neural Autoencoder,” in 42nd Annual IEEE Conference on Local Computer Networks (LCN), Singapore, 2017.
@inproceedings{hoechst2017unsupervised,
author = {{H{\"o}chst}, Jonas and {Baumg{\"a}rtner}, Lars and Hollick, Matthias and Freisleben, Bernd},
title = {{Unsupervised Traffic Flow Classification Using a Neural Autoencoder}},
booktitle = {42nd Annual IEEE Conference on Local Computer Networks (LCN)},
address = {Singapore},
days = {10},
month = oct,
year = {2017},
url = {https://ieeexplore.ieee.org/document/8109399/},
doi = {10.1109/LCN.2017.57},
keywords = {Autoencoder; Traffic flow classification; Unsupervised learning}
}
The delay and bandwidth requirements of today’s mobile applications differ widely depending on the functionality provided and the data transferred, such as uploading user generated multimedia content, playing online games, or streaming live videos. To perform resource management, mobile wireless networks can particularly profit from classifying and predicting mobile application traffic. State-of-the-art traffic classification approaches have various disadvantages: port-based classification methods can be circumvented by choosing non-standard ports, protocol fingerprinting can be confused by the use of encryption, and current supervised learning methods for analyzing the statistical properties of network flows try to detect predefined classes, such as e-mail or FTP traffic, learned during training. In this paper, we present a novel approach to unsupervised traffic flow classification using statistical properties of flows and clustering based on a neural autoencoder. In contrast to previous work, the neural autoencoder is used to automatically cluster traffic flows, for example, into downloads, uploads, or voice calls, independent of the particular network protocols, such as FTP or HTTP(S), used for performing these tasks. A novel time interval based feature vector construction and a semi-automatic cluster labeling method facilitate traffic flow classification independent of known traffic classes or classification constraints. An experimental evaluation of the proposed approach on real data captured from about 25 mobile devices performing daily work over a period of 4 months is presented. The obtained results show that 7 different classes of mobile traffic flows are detected with an average precision of 80% and an average recall of 75%, indicating the feasibility of our approach.
DetailsL. Baumgärtner, P. Graubner, J. Höchst, A. Klein, and B. Freisleben, “Speak Less, Hear Enough: On Dynamic Announcement Intervals in Wireless On-demand Networks,” in 13th Conference on Wireless On-demand Network Systems and Services (WONS 2017), Jackson Hole, USA, 2017.
@inproceedings{baumgaertner2017speak,
author = {{Baumg{\"a}rtner}, Lars and Graubner, Pablo and {H{\"o}chst}, Jonas and Klein, Anja and Freisleben, Bernd},
title = {{Speak Less, Hear Enough: On Dynamic Announcement Intervals in Wireless On-demand Networks}},
booktitle = {13th Conference on Wireless On-demand Network Systems and Services (WONS 2017)},
address = {Jackson Hole, USA},
days = {21},
month = feb,
year = {2017},
doi = {10.1109/WONS.2017.7888768},
url = {http://2017.wons-conference.org/Papers/1570315160.pdf}
}
Several protocols used in wireless networks rely on nodes announcing information to other nodes. This can be illustrated by service announcements sent in ZeroConf, routing announcements used in OLSR, and peer announcements in wireless peer-to-peer or delay-tolerant networking systems such as Forban and Serval. The main problem is that these protocols use fixed time intervals between subsequent broadcast announcements. Fixed intervals can either lead to high network load (if the announcement interval is too short) or delay the distribution of information between peers (if the announcement interval is too long). Repeatedly broadcasting announcements after fixed intervals also has a significant impact on the energy consumption of mobile devices operating in wireless networks. In this paper, we present several approaches to realize dynamic announcement intervals that facilitate fast reception from at least one other node while trying to keep the overall communication overhead as low as possible. Experimental results in terms of performance properties and energy consumption are presented to illustrate the benefits of dynamic announcement intervals in wireless on-demand networks.
Details
