Florian Grützmacher

Bio: Florian Grützmacher is an academic researcher from University of Rostock. The author has contributed to research in topics: Activity recognition & Gesture recognition. The author has an hindex of 4, co-authored 10 publications receiving 37 citations.

Time and Memory Efficient Online Piecewise Linear Approximation of Sensor Signals.

Abstract: Piecewise linear approximation of sensor signals is a well-known technique in the fields of Data Mining and Activity Recognition. In this context, several algorithms have been developed, some of them with the purpose to be performed on resource constrained microcontroller architectures of wireless sensor nodes. While microcontrollers are usually constrained in computational power and memory resources, all state-of-the-art piecewise linear approximation techniques either need to buffer sensor data or have an execution time depending on the segment’s length. In the paper at hand, we propose a novel piecewise linear approximation algorithm, with a constant computational complexity as well as a constant memory complexity. Our proposed algorithm’s worst-case execution time is one to three orders of magnitude smaller and its average execution time is three to seventy times smaller compared to the state-of-the-art Piecewise Linear Approximation (PLA) algorithms in our experiments. In our evaluations, we show that our algorithm is time and memory efficient without sacrificing the approximation quality compared to other state-of-the-art piecewise linear approximation techniques, while providing a maximum error guarantee per segment, a small parameter space of only one parameter, and a maximum latency of one sample period plus its worst-case execution time.

Activity Recognition using Head Worn Inertial Sensors

Abstract: Human activity recognition using inertial sensors is an increasingly used feature in smartphones or smartwatches, providing information on sports and physical activities of each individual. But while the position a smartphone is worn in varies between persons and circumstances, a smartwatch moves constantly, in rhythm with its user's arms. Both problems make activity recognition less reliable. Attaching an inertial sensor to the head provides reliable information on the movements of the whole body while not being superimposed by many additional movements. This can be achieved by fixing sensors to glasses, helmets, or headphones. In this paper, we present a system using head-mounted inertial sensors for human activity recognition. We compare it to existing research work and show possible advantages or disadvantages of positioning a single sensor on the head to recognize physical activities. Furthermore we evaluate the benefits of using different sensor configurations on activity recognition.

Towards energy efficient sensor nodes for online activity recognition

Abstract: In sensor-based activity recognition often huge amounts of data have to be acquired from multiple sensors, which need to be communicated for further processing. When using wireless sensor nodes, energy efficiency is of outstanding importance, since it directly influences the time until the battery needs to be recharged. However, communicating a huge amount of sensor data over wireless interfaces causes high energy consumption as well. Furthermore, the host controller receiving the sensor data is hindered of using its low power modes, as it needs to be woken up more frequently as well. In the paper at hand, we introduce our approach of reducing energy consumption of sensor nodes in online activity recognition scenarios by calculating the feature extraction on the sensor subsystem itself. By doing so, we can reduce the output rate of the sensor which enables the host controller to stay in its low power modes for longer periods. Additionally, this approach drastically reduces the amount of data to be transmitted over wireless interfaces, which further improves energy consumption. In our experiments, the proposed approach reduces the energy consumption of a sensor node by up to 33 %.

Model-Based Design of Energy-Efficient Human Activity Recognition Systems with Wearable Sensors

Abstract: The advances in MEMS technology development allow for small and thus unobtrusive designs of wearable sensor platforms for human activity recognition. Multiple such sensors attached to the human body for gathering, processing, and transmitting sensor data connected to platforms for classification form a heterogeneous distributed cyber-physical system (CPS). Several processing steps are necessary to perform human activity recognition, which have to be mapped to the distributed computing platform. However, the software mapping is decisive for the CPS’s processing load and communication effort. Thus, the mapping influences the energy consumption of the CPS, and its energy-efficient design is crucial to prolong battery lifetimes and allow long-term usage of the system. As a consequence, there is a demand for system-level energy estimation methods in order to substantiate design decisions even in early design stages. In this article, we propose to combine well-known dataflow-based modeling and analysis techniques with energy models of wearable sensor devices, in order to estimate energy consumption of wireless sensor nodes for online activity recognition at design time. Our experiments show that a reasonable system-level average accuracy above 97% can be achieved by our proposed approach.

Sensor-based online hand gesture recognition on multi-core DSPs

Abstract: In this paper we propose a novel approach for parallelized computation of sensor-based online hand gesture recognition on multi-core DSPs. To this end, we dispatch different windows of sensor data segments to different groups of cores. Within a group of cores, we distribute the template-based recognition on the basis of reference recordings. In order to model different configurations of our approach, we use extended data flow graphs. Our experiments show real time performance making our approach suitable for online hand gesture recognition.

Human Activity Recognition for Production and Logistics—A Systematic Literature Review

Abstract: This contribution provides a systematic literature review of Human Activity Recognition for Production and Logistics. An initial list of 1243 publications that complies with predefined Inclusion Criteria was surveyed by three reviewers. Fifty-two publications that comply with the Content Criteria were analysed regarding the observed activities, sensor attachment, utilised datasets, sensor technology and the applied methods of HAR. This review is focused on applications that use marker-based Motion Capturing or Inertial Measurement Units. The analysed methods can be deployed in industrial application of Production and Logistics or transferred from related domains into this field. The findings provide an overview of the specifications of state-of-the-art HAR approaches, statistical pattern recognition and deep architectures and they outline a future road map for further research from a practitioner’s perspective.

FinDroidHR: Smartwatch Gesture Input with Optical Heartrate Monitor

Abstract: We present FinDroidHR, a novel gesture input technique for off-the-shelf smartwatches. Our technique is designed to detect 10 hand gestures on the hand wearing a smartwatch. The technique is enabled by analysing features of the Photoplethysmography (PPG) signal that optical heart-rate sensors capture. In a study with 20 participants, we show that FinDroidHR achieves 90.55% accuracy and 90.73% recall. Our work is the first study to explore the feasibility of using optical sensors on the off-the-shelf wearable devices to recognise gestures. Without requiring bespoke hardware, FinDroidHR can be readily used on existing smartwatches.

Online Sensor Drift Compensation for E-Nose Systems Using Domain Adaptation and Extreme Learning Machine

Abstract: Sensor drift is a common issue in E-Nose systems and various drift compensation methods have received fruitful results in recent years. Although the accuracy for recognizing diverse gases under drift conditions has been largely enhanced, few of these methods considered online processing scenarios. In this paper, we focus on building online drift compensation model by transforming two domain adaptation based methods into their online learning versions, which allow the recognition models to adapt to the changes of sensor responses in a time-efficient manner without losing the high accuracy. Experimental results using three different settings confirm that the proposed methods save large processing time when compared with their offline versions, and outperform other drift compensation methods in recognition accuracy.

Easing Power Consumption of Wearable Activity Monitoring with Change Point Detection.

Abstract: Continuous monitoring of complex activities is valuable for understanding human behavior and providing activity-aware services. At the same time, recognizing these activities requires both movement and location information that can quickly drain batteries on wearable devices. In this paper, we introduce Change Point-based Activity Monitoring (CPAM), an energy-efficient strategy for recognizing and monitoring a range of simple and complex activities in real time. CPAM employs unsupervised change point detection to detect likely activity transition times. By adapting the sampling rate at each change point, CPAM reduces energy consumption by 74.64% while retaining the activity recognition performance of continuous sampling. We validate our approach using smartwatch data collected and labeled by 66 subjects. Results indicate that change point detection techniques can be effective for reducing the energy footprint of sensor-based mobile applications and that automated activity labels can be used to estimate sensor values between sampling periods.

DRIVEN: a Framework for Efficient Data Retrieval and Clustering in Vehicular Networks

Abstract: Applications for adaptive (sometimes also called smart) Cyber-Physical Systems are blossoming thanks to the large volumes of data, sensed in a continuous fashion, in large distributed systems. The benefits of these applications come nonetheless with a price: the need for jointly addressing challenges in efficient data communication and analysis (among others). The goal of the DRIVEN framework, presented here, is to address these challenges for a data gathering and distance-based clustering tool in the context of vehicular networks. Because of the limited communication bandwidth (compared to the volume of sensed data) of vehicular networks and the monetary costs of data transmission, the intuition behind DRIVEN is to avoid gathering the data to be clustered in a raw format from each vehicle, but rather to allow for a streaming-based error-bounded approximation, through Piecewise Linear Approximation, to compress the volumes of data to be gathered. At the same time, rather than relying on a batch-based clustering algorithm that requires all the data to be first gathered (and then clustered), DRIVEN relies on and extends a streaming-based clustering algorithm that leverages the inherent ordering of the spatial and temporal data being collected, to perform the clustering in an online fashion, while data is being retrieved. As we show, based on our prototype implementation using Apache Flink and our evaluation with real-world data such as GPS and LiDAR, the accuracy loss for the clustering performed on the reconstructed data can be small, even when the raw data is compressed to 10-35% of its original size, and the transferring of data itself can be completed in up to one-tenth of the duration observed when gathering raw data.