SENSORNETS 2021 Abstracts


Area 1 - Intelligent Data Analysis and Processing for Sensor Networks

Full Papers
Paper Nr: 15
Title:

Optimal Sensor Placement for Human Activity Recognition with a Minimal Smartphone–IMU Setup

Authors:

Vincent X. Rahn, Lin Zhou, Eric Klieme and Bert Arnrich

Abstract: Human Activity Recognition (HAR) of everyday activities using smartphones has been intensively researched over the past years. Despite the high detection performance, smartphones can not continuously provide reliable information about the currently conducted activity as their placement at the subject’s body is uncertain. In this study, a system is developed that enables real-time collection of data from various Bluetooth inertial measurement units (IMUs) in addition to the smartphone. The contribution of this work is an extensive overview of related work in this field and the identification of unobtrusive, minimal combinations of IMUs with the smartphone that achieve high recognition performance. Eighteen young subjects with unrestricted mobility were recorded conducting seven daily-life activities with a smartphone in the pocket and five IMUs at different body positions. With a Convolutional Neural Network (CNN) for activity recognition, activity classification accuracy increased by up to 23% with one IMU additional to the smartphone. An overall prediction rate of 97% was reached with a smartphone in the pocket and an IMU at the ankle. This study demonstrated the potential that an additional IMU can improve the accuracy of smartphone-based HAR on daily-life activities.

Short Papers
Paper Nr: 12
Title:

System based Code Evaluation Criteria for CDM Applications in Sensor and Data Transmission Systems

Authors:

Peter Stapf, Marek Götten, Andreas Ahrens and Steffen Lochmann

Abstract: To increase the multiplexing capability of code-division multiplexing (CDM) applied in optical sensor networks, a system based code evaluation is required. This contribution analyses evaluation criteria for sequences applied in CDM systems. A comparison of an optical sensor application and a single user data transmission system is presented. While a detection signal-to-noise ratio and the bit error rate are used to evaluate data transmission systems, the proposed optical sensor application uses a modified signal-to-multiuser-interference ratio (mSMUI). The main difference exists in the handling of interference. In contrary to data transmission, the mSMUI requires a separation of positive and negative interferences. Both applications are simulated for different binary sequences. While the Legendre sequence with a length of 503 chips achieves the over all best results for the optical sensor application, the single user data transmission simulation shows no significant sequence influence.

Paper Nr: 16
Title:

Efficient Flash Indexing for Time Series Data on Memory-constrained Embedded Sensor Devices

Authors:

Scott Fazackerley, Nadir Ould-Khessal and Ramon Lawrence

Abstract: Embedded sensor devices with limited hardware resources must efficiently collect environmental and industrial time series data for analysis. Performing data analysis on the device requires data storage and indexing that minimizes memory, I/O, and energy usage. This paper presents an index structure that is optimized for the constrained use cases associated with sensor time series collection and analysis. By supporting only planned queries and analysis patterns, the storage and indexing implementation is simplified, and outperforms general techniques based on hashing and trees. The indexing technique is analyzed and compared with other indexing approaches and is adapted to all flash memory types including memory that supports overwriting.

Area 2 - Sensor Networks and Architectures

Short Papers
Paper Nr: 21
Title:

System for Supporting Implementation and Monitoring of Smart Campus Applications based on IoT Protocols

Authors:

Franklin M. Venceslau, Ruan D. Gomes and Iguatemi E. Fonseca

Abstract: This paper descbribes a system for monitoring Smart Campus applications based on IoT protocols. The system have as main goals to support the deployment of new sensors, actuators, and gateways in the campus, based on a pre-deployed network infrasctructure, and to monitor the performance of applications along the time. The network architecture considered in this paper provides reliability through the use of diversity techniques at physical and data link layers, based on the IEEE 802.15.4g SUN standard, and it performs the persistence of information based on time series database. In order to support the network infrastructure evolution and the incorporation of new devices and applications, information about the currently running applications and about the quality of the data links and the wireless network’s overload level can be collected by the proposed system. In this position paper, the architecture of the system is described in details, and initial results are discussed.

Area 3 - Sensor Networks Applications

Full Papers
Paper Nr: 11
Title:

Real-Time Range Query Approximation by Means of Adaptive Quad Streaming

Authors:

Simon Keller and Rainer Mueller

Abstract: Continuous range queries are a common means to handle mobile clients in high-density areas. Most existing approaches focus on settings in which the range queries for location-based services are mostly static whereas the mobile clients in the ranges move. We focus on a category called Dynamic Real-Time Range Queries (DRRQ) assuming that both, clients requested by the query and the inquirers, are mobile. In consequence, the query parameters results continuously change. This leads to two requirements: the ability to deal with an arbitrary high number of mobile nodes (scalability) and the real-time delivery of range query results. In this paper we present the highly decentralized solution Adaptive Quad Streaming (AQS) for the requirements of DRRQs. AQS approximates the query results in favor of a controlled real-time delivery and guaranteed scalability. While prior works commonly optimizes data structures on servers, we use AQS to focus on a highly distributed cell structure without data structures automatically adapting to changing client distributions. Instead of the commonly used request-response approach, we apply a lightweight streaming method in which no bidirectional communication and no storage or maintenance of queries are required at all.

Paper Nr: 14
Title:

Wireless Sensor Network for in situ Soil Moisture Monitoring

Authors:

Jianing Fang, Chuheng Hu, Nour Smaoui, Doug Carlson, Jayant Gupchup, Razvan Musaloiu-E., Chieh-Jan M. Liang, Marcus Chang, Omprakash Gnawali, Tamas Budavari, Andreas Terzis, Katalin Szlavecz and Alexander S. Szalay

Abstract: We discuss the history and lessons learned from a series of deployments of environmental sensors measuring soil parameters and CO2 fluxes over the last fifteen years, in an outdoor environment. We present the hardware and software architecture of our current Gen-3 system, and then discuss how we are simplifying the user facing part of the software, to make it easier and friendlier for the environmental scientist to be in full control of the system. Finally, we describe the current effort to build a large-scale Gen-4 sensing platform consisting of hundreds of nodes to track the environmental parameters for urban green spaces in Baltimore, Maryland.

Paper Nr: 20
Title:

Linoc: A Prototyping Platform for Capacitive and Passive Electrical Field Sensing

Authors:

Julian Von Wilmsdorff, Malte Lenhart, Florian Kirchbuchner and Arjan Kuijper

Abstract: In this paper the Linoc prototyping toolkit is presented. It is a sensor toolkit that focuses on fast prototyping of sensor systems, especially on capacitive ones. The toolkit is built around two capacitive and two Electric Potential Sensing (EPS) groups providing unobtrusive proximity detection in the field of Human Computer Interface (HCI). The toolkits focus lies on its usability and connectivity in order to be adapted in future research and novel use cases. A common obstacle in the beginning of a project is the time required to familiarize with present tools and systems, before the actual project can be attended to. Another obstacle while tackling new tasks is the actual physical connection of sensors to the processing unit. This situation can be even worse due to dependencies on previous work, most of the times not fully documented and missing knowledge even if the the original designer is involved. Good toolkits can help to overcome this problem by providing a layer of abstraction and allowing to work on a higher level. If the toolkit however requires too much time to familiarize or behaves too restrictive, its goal has been missed and no benefits are generated. To assess the quality of the Linoc prototyping toolkit, it was evaluated in terms of three different aspects: demonstration, usage and technical performance. The usage study found good reception, a fast learning curve and an interest to use the toolkit in the future. Technical benchmarks for the capacitive sensors show a detectable range equal to its predecessors and several operational prototypes prove that the toolkit can actually be used in projects.

Short Papers
Paper Nr: 6
Title:

An Efficient Low-power Wake-up Receiver Architecture for Power Saving for Transmitter and Receiver Communications

Authors:

Robert Fromm, Lydia Schott and Faouzi Derbel

Abstract: For power-limited wireless sensor networks, energy efficiency is a critical concern. Receiving packages is proven to be one of the most power-consuming tasks in a WSN. To address this problem the asynchronous communication is based on wake-up receivers. The proposed receiver circuit can detect carrier signals inside the 868 MHz band. Reliable signal detection at 10 m was achieved with a total power consumption of 4.2 µW. Two use cases of this low-power receiver were introduced. First the wake-up receiver and second as a collision avoidance circuit. Because of its low power consumption savings of factor 7000 can be estimated compared to integrated solutions of commercially available radio transceivers.

Paper Nr: 9
Title:

Low Energy ECG Features Extraction for Atrial Fibrillation Detection in Wearable Sensors

Authors:

Manan AlMusallam and Adel Soudani

Abstract: The Internet of Health Things plays a key role in the transformation of health care systems as it enables wearable health monitoring systems to ensure continuous and non-invasive tracking of vital body parameters. To successfully detect the cardiac problem of Atrial Fibrillation (AF) wearable sensors are required to continuously sense and transmit ECG signals. The traditional approach of ECG streaming over energy-consuming wireless links can overwhelm the limited energy resources of wearable sensors. This paper proposes a low-energy features’ extraction method that combines the RR interval and P wave features for higher AF detection accuracy. In the proposed scheme, instead of streaming raw ECG signals , local AF features extraction is executed on the sensors. Results have shown that combining time-domain features with wavelet extracted features, achieved a sensitivity of 98.59% and a specificity of 97.61%. In addition, compared to ECG streaming, on-sensor AF detection achieved a 92% gain in energy savings.

Paper Nr: 17
Title:

On-site Sensor Noise Evaluation and Detectability in Low Cost Accelerometers

Authors:

Marco Manso and Mourad Bezzeghoud

Abstract: Seismic networks help understanding the phenomena related with seismic events. These networks are employing low-cost accelerometers in order to achieve high-density deployments enabling accurate characterisation (high resolution) of strong earthquake motion and early warning capabilities. In order to assess the applicability of low-cost accelerometers in seismology, it is essential to evaluate their noise characteristics and identify their detectability thresholds. In this paper, a method is proposed that provides an indication of sensor noise, being demonstrated on different sensors. The method is designed to adapt to a sensor’s characteristics while on-site and in-operation, thus removing potentially related logistical and maintenance bottlenecks.

Paper Nr: 13
Title:

Mirror Mosaicking: A Novel Approach to Achieve High-performance Classification of Gases Leveraging Convolutional Neural Network

Authors:

S. N. Chaudhri and N. S. Rajput

Abstract: Limited dimensionality of the dataset obtained from an electronic nose (EN) is due to the number of elements in the sensor array used generally in the range of 4-8 elements only. Further, large number of sensor data can be generated by sampling the sensor responses both during the transient and steady states. The lower-dimensionality of sensor data prohibits the use of a convolutional neural network (CNN)-based pattern recognition techniques because the kernels of a CNN cannot be used on the obtained sample vectors to extract the features. In this paper, we have proposed a novel approach to enhance the data dimensionality keeping the sensor response characteristics absolutely unaltered. By leveraging the concept of mirror mosaicking technique, we have upscaled the input sample vectors into a 6×6 2-D input arrays to train the shallow CNN. Using the proposed approach, all the 16-unknown steady-state test samples classified accurately which are not used during the training. Moreover, the parameters of the classification report viz., Precision, Recall, and F1 score also obtained with a fraction value of 1.00. The proposed technique is a generic approach that can be used to classify various low-dimensional datasets obtained from various sensor arrays in various fields.

Paper Nr: 18
Title:

PAIoT Network: A Unique Regional IoT Network for Very Different Applications

Authors:

Stefania Nanni and Gianluca Mazzini

Abstract: LepidaSpa, the ICT in-house company of the Public Administrations of the Emilia Romagna region, has realized a regional IoT public network‡, based on the LoRaWan§ technology, free of charge for all public administrations, as well as to private citizens, potentially enabling the collection of relevant data from thousands of new sensors and making them accessible to both the owners of the sensors and, limitedly to institutional or public interest scopes, to every PA entity. The innovative aspects of the proposed solution mainly concern the extreme simplicity of the sensors installation, the low entry costs for stakeholders, both public and private, who want to deploy their own sensors, a centralized service that collects and makes data available in the cloud, the replicability of IoT projects on a regional scale.

Paper Nr: 22
Title:

Genetic Programming based Iterative Improvement Algorithm for HW/SW Cosynthesis of Distributted Embedded Systems

Authors:

Adam Górski and Maciej Ogorzałek

Abstract: In this work we present a novel genetic programming based iterative improvement approach for hardware/software cosynthesis of distributed embedded systems. The approach starts from a ready solution which is an embryo of a genotype. Other nodes in the genotypes are chromosomes. The chromosomes contain system refinement options. The final solution is obtained after evolution process and mapping genotype to phenotype. Unlike existing genetic programming iterative improvement methodologies our algorithm starts from randomly generated system. Therefore the search space is not constrained by any initial condition. It is also easier for the algorithm to escape local minima of optimizing parameters.