Refine
Year of publication
- 2020 (40) (remove)
Document Type
- Conference Proceeding (40) (remove)
Language
- English (40) (remove)
Has Fulltext
- no (40) (remove)
Keywords
- 3D ship detection (1)
- Accelerometers (1)
- Accessible Tourism (1)
- Actions (1)
- Adaptive (1)
- Assisted living (1)
- Benchmark (1)
- Bernstein coefficient (1)
- Bernstein polynomial (1)
- Binary codes (1)
The IETF, concerned with the evolution of the Internet architecture, nowadays also looks into industrial automation processes. The contributions of a variety of IETF activities, initiated during the last ten years, enable now the replacement of proprietary standards by an open standardized protocol stack. This stack, denoted in the following as 6TiSCH-stack, is tailored for industrial internet of things (IIoTs). The suitability of 6TiSCH-stack for Industry 4.0 is yet to explore. In this paper, we identify four challenges that, in our opinion, may delay or hinder its adoption. As a prime example of that, we focus on the initial 6TiSCHnetwork
formation, highlighting the shortcomings of the default procedure and introducing our current work for a fast and reliable formation of dense network.
The recovery of our body and brain from fatigue directly depends on the quality of sleep, which can be determined from the results of a sleep study. The classification of sleep stages is the first step of this study and includes the measurement of vital data and their further processing. The non-invasive sleep analysis system is based on a hardware sensor network of 24 pressure sensors providing sleep phase detection. The pressure sensors are connected to an energy-efficient microcontroller via a system-wide bus. A significant difference between this system and other approaches is the innovative way in which the sensors are placed under the mattress. This feature facilitates the continuous use of the system without any noticeable influence on the sleeping person. The system was tested by conducting experiments that recorded the sleep of various healthy young people. Results indicate the potential to capture respiratory rate and body movement.
Polysomnography is a gold standard for a sleep study, and it provides very accurate results, but its cost (both personnel and material) are quite high. Therefore, the development of a low-cost system for overnight breathing and heartbeat monitoring, which provides more comfort while recording the data, is a well-motivated challenge. The system proposed in this manuscript is based on the usage of resistive pressure sensors installed under the mattress. These sensors can measure slight pressure changes provoked during breathing and heartbeat. The captured signal requires advanced processing, like applying filters and amplifiers before the analog signal is ready for the next step. Then, the output signal is digitalized and further processed by an algorithm that performs a custom filtering before it can recognize breathing and heart rate in real-time. The result can be directly visualized. Furthermore, a CSV file is created containing the raw data, timestamps, and unique IDs to facilitate further processing. The achieved results are promising, and the average deviation from a reference device is about 4bpm.
Good sleep is crucial for a healthy life of every person. Unfortunately, its quality often decreases with aging. A common approach to measuring the sleep characteristics is based on interviews with the subjects or letting them fill in a daily questionnaire and afterward evaluating the obtained data. However, this method has time and personal costs for the interviewer and evaluator of responses. Therefore, it would be important to execute the collection and evaluation of sleep characteristics automatically. To do that, it is necessary to investigate the level of agreement between measurements performed in a traditional way using questionnaires and measurements obtained using electronic monitoring devices. The study presented in this manuscript performs this investigation, comparing such sleep characteristics as "time going to bed", "total time in bed", "total sleep time" and "sleep efficiency". A total number of 106 night records of elderly persons (aged 65+) were analyzed. The results achieved so far reveal the fact that the degree of agreement between the two measurement methods varies substantially for different characteristics, from 31 minutes of mean difference for "time going to bed" to 77 minutes for "total sleep time". For this reason, a direct exchange of objective and subjective measuring methods is currently not possible.
The evaluation of the effectiveness of different machine learning algorithms on a publicly available database of signals derived from wearable devices is presented with the goal of optimizing human activity recognition and classification. Among the wide number of body signals we choose a couple of signals, namely photoplethysmographic (optically detected subcutaneous blood volume) and tri-axis acceleration signals that are easy to be simultaneously acquired using commercial widespread devices (e.g. smartwatches) as well as custom wearable wireless devices designed for sport, healthcare, or clinical purposes. To this end, two widely used algorithms (decision tree and k-nearest neighbor) were tested, and their performance were compared to two new recent algorithms (particle Bernstein and a Monte Carlo-based regression) both in terms of accuracy and processing time. A data preprocessing phase was also considered to improve the performance of the machine learning procedures, in order to reduce the problem size and a detailed analysis of the compression strategy and results is also presented.
This paper presents the implementation of deep learning methods for sleep stage detection by using three signals that can be measured in a non-invasive way: heartbeat signal, respiratory signal, and movement signal. Since signals are measurements taken during the time, the problem is seen as time-series data classification. Deep learning methods are chosen to solve the problem are convolutional neural network and long-short term memory network. Input data is structured as a time-series sequence of mentioned signals that represent 30 seconds epoch, which is a standard interval for sleep analysis. The records used belong to the overall 23 subjects, which are divided into two subsets. Records from 18 subjects were used for training the data and from 5 subjects for testing the data. For detecting four sleep stages: REM (Rapid Eye Movement), Wake, Light sleep (Stage 1 and Stage 2), and Deep sleep (Stage 3 and Stage 4), the accuracy of the model is 55%, and F1 score is 44%. For five stages: REM, Stage 1, Stage 2, Deep sleep (Stage 3 and 4), and Wake, the model gives an accuracy of 40% and F1 score of 37%.
This work is a study about a comparison of survey tools and it should help developers in selecting a suited tool for application in an AAL environment. The first step was to identify the basic required functionality of the survey tools used for AAL technologies and to compare these tools by their functionality and assignments. The comparative study was derived from the data obtained, previous literature studies and further technical data. A list of requirements was stated and ordered in terms of relevance to the target application domain. With the help of an integrated assessment method, the calculation of a generalized estimate value was performed and the result is explained. Finally, the planned application of this tool in a running project is explained.
Cardiovascular diseases are directly or indirectly responsible for up to 38.5% of all deaths in Germany and thus represent the most frequent cause of death. At present, heart diseases are mainly discovered by chance during routine visits to the doctor or when acute symptoms occur. However, there is no practical method to proactively detect diseases or abnormalities of the heart in the daily environment and to take preventive measures for the person concerned. Long-term ECG devices, as currently used by physicians, are simply too expensive, impractical, and not widely available for everyday use. This work aims to develop an ECG device suitable for everyday use that can be worn directly on the body. For this purpose, an already existing hardware platform will be analyzed, and the corresponding potential for improvement will be identified. A precise picture of the existing data quality is obtained by metrological examination, and corresponding requirements are defined. Based on these identified optimization potentials, a new ECG device is developed. The revised ECG device is characterized by a high integration density and combines all components directly on one board except the battery and the ECG electrodes. The compact design allows the device to be attached directly to the chest. An integrated microcontroller allows digital signal processing without the need for an additional computer. Central features of the evaluation are a peak detection for detecting R-peaks and a calculation of the current heart rate based on the RR interval. To ensure the validity of the detected R-peaks, a model of the anatomical conditions is used. Thus, unrealistic RR-intervals can be excluded. The wireless interface allows continuous transmission of the calculated heart rate. Following the development of hardware and software, the results are verified, and appropriate conclusions about the data quality are drawn. As a result, a very compact and wearable ECG device with different wireless technologies, data storage, and evaluation of RR intervals was developed. Some tests yelled runtimes up to 24 hours with wireless Lan activated and streaming.
We present source code patterns that are difficult for modern static code analysis tools. Our study comprises 50 different open source projects in both a vulnerable and a fixed version for XSS vulnerabilities reported with CVE IDs over a period of seven years. We used three commercial and two open source static code analysis tools. Based on the reported vulnerabilities we discovered code patterns that appear to be difficult to classify by static analysis. The results show that code analysis tools are helpful, but still have problems with specific source code patterns. These patterns should be a focus in training for developers.
We propose and apply a requirements engineering approach that focuses on security and privacy properties and takes into account various stakeholder interests. The proposed methodology facilitates the integration of security and privacy by design into the requirements engineering process. Thus, specific, detailed security and privacy requirements can be implemented from the very beginning of a software project. The method is applied to an exemplary application scenario in the logistics industry. The approach includes the application of threat and risk rating methodologies, a technique to derive technical requirements from legal texts, as well as a matching process to avoid duplication and accumulate all essential requirements.
Side Channel Attack Resistance of the Elliptic Curve Point Multiplication using Gaussian Integers
(2020)
Elliptic curve cryptography is a cornerstone of embedded security. However, hardware implementations of the elliptic curve point multiplication are prone to side channel attacks. In this work, we present a new key expansion algorithm which improves the resistance against timing and simple power analysis attacks. Furthermore, we consider a new concept for calculating the point multiplication, where the points of the curve are represented as Gaussian integers. Gaussian integers are subset of the complex numbers, such that the real and imaginary parts are integers. Since Gaussian integer fields are isomorphic to prime fields, this concept is suitable for many elliptic curves. Representing the key by a Gaussian integer expansion is beneficial to reduce the computational complexity and the memory requirements of a secure hardware implementation.
Multi-Dimensional Connectionist Classification is amethod for weakly supervised training of Deep Neural Networksfor segmentation-free multi-line offline handwriting recognition.MDCC applies Conditional Random Fields as an alignmentfunction for this task. We discuss the structure and patterns ofhandwritten text that can be used for building a CRF. Since CRFsare cyclic graphical models, we have to resort to approximateinference when calculating the alignment of multi-line text duringtraining, here in the form of Loopy Belief Propagation. This workconcludes with experimental results for transcribing small multi-line samples from the IAM Offline Handwriting DB which showthat MDCC is a competitive methodology.
A residual neural network was adapted and applied to the Physionet/Computing data in Cardiology Challenge 2020 to detect 24 different classes of cardiac abnormalities from 12-lead. Additive Gaussian noise, signal shifting, and the classification of signal sections of different lengths were applied to prevent the network from overfitting and facilitating generalization. Due to the use of a global pooling layer after the feature extractor, the network is independent of the signal’s length. On the hidden test set of the challenge, the model achieved a validation score of 0.656 and a full test score of 0.27, placing us 15th out of 41 officially ranked teams (Team name: UC_Lab_Kn). These results show the potential of deep neural networks for ap- plication to raw data and a complex multi-class multi-label classification problem, even if the training data is from di- verse datasets and of differing lengths.
In today's volatile world, established companies must be capable of optimizing their core business with incremental innovations while simultaneously developing discontinuous innovations to maintain their long-term competitiveness. Balancing both is a major challenge for companies, since different types of innovation require different organizational structures, operational modes and management styles. Established companies tend to excel in improving their current business through incremental innovations which are closely related to their current knowledge base and competencies. However, this often goes hand in hand with challenges in the exploration of knowledge that is new to the company and that is essential for the development of discontinuous innovations. In this respect, the concept of corporate entrepreneurship is recognized as a way to strengthen the exploration of new knowledge and to support the development of discontinuous innovation. For managing corporate entrepreneurship more effectively, it is crucial to understand which types of knowledge can be created through corporate entrepreneurship and which organizational designs are more suited to gain certain types of knowledge. To answer these questions, this study analyzed 23 semi-structured interviews conducted with established companies that are running such entrepreneurial activities. The results show (1) that three general types of knowledge can be explored through corporate entrepreneurship and (2) that some organizational designs are more suited to explore certain knowledge types than others are.
The ageing infrastructure in ports requires regular inspection. This inspection is currently carried out manually by divers who sense by hand the entire underwater infrastructure. This process is cost-intensive as it involves a lot of time and human resources. To overcome these difficulties, we propose to scan the above and underwater port structure with a Multi-SensorSystem, and -by a fully automated processto classify the obtained point cloud into damaged and undamaged zones. We make use of simulated training data to test our approach since not enough training data with corresponding class labels are available yet. To that aim, we build a rasterised heightfield of a point cloud of a sheet pile wall by cutting it into verticall slices. The distance from each slice to the corresponding line generates the heightfield. This latter is propagated through a convolutional neural network which detects anomalies. We use the VGG19 Deep Neural Network model pretrained on natural images. This neural network has 19 layers and it is often used for image recognition tasks. We showed that our approach can achieve a fully automated, reproducible, quality-controlled damage detection which is able to analyse the whole structure instead of the sample wise manual method with divers. The mean true positive rate is 0.98 which means that we detected 98 % of the damages in the simulated environment.
Side Channel Attack Resistance of the Elliptic Curve Point Multiplication using Eisenstein Integers
(2020)
Asymmetric cryptography empowers secure key exchange and digital signatures for message authentication. Nevertheless, consumer electronics and embedded systems often rely on symmetric cryptosystems because asymmetric cryptosystems are computationally intensive. Besides, implementations of cryptosystems are prone to side-channel attacks (SCA). Consequently, the secure and efficient implementation of asymmetric cryptography on resource-constrained systems is demanding. In this work, elliptic curve cryptography is considered. A new concept for an SCA resistant calculation of the elliptic curve point multiplication over Eisenstein integers is presented and an efficient arithmetic over Eisenstein integers is proposed. Representing the key by Eisenstein integer expansions is beneficial to reduce the computational complexity and the memory requirements of an SCA protected implementation.
The reliability of flash memories suffers from various error causes. Program/erase cycles, read disturb, and cell to cell interference impact the threshold voltages and cause bit errors during the read process. Hence, error correction is required to ensure reliable data storage. In this work, we investigate the bit-labeling of triple level cell (TLC) memories. This labeling determines the page capacities and the latency of the read process. The page capacity defines the redundancy that is required for error correction coding. Typically, Gray codes are used to encode the cell state such that the codes of adjacent states differ in a single digit. These Gray codes minimize the latency for random access reads but cannot balance the page capacities. Based on measured voltage distributions, we investigate the page capacities and propose a labeling that provides a better rate balancing than Gray labeling.
Soft-input decoding of concatenated codes based on the Plotkin construction and BCH component codes
(2020)
Low latency communication requires soft-input decoding of binary block codes with small to medium block lengths.
In this work, we consider generalized multiple concatenated (GMC) codes based on the Plotkin construction. These codes are similar to Reed-Muller (RM) codes. In contrast to RM codes, BCH codes are employed as component codes. This leads to improved code parameters. Moreover, a decoding algorithm is proposed that exploits the recursive structure of the concatenation. This algorithm enables efficient soft-input decoding of binary block codes with small to medium lengths. The proposed codes and their decoding achieve significant performance gains compared with RM codes and recursive GMC decoding.
This paper proposes a novel transmission scheme for generalized multistream spatial modulation. This new approach uses one Mannheim error correcting codes over Gaussian or Eisenstein integers as multidimensional signal constellations. These codes enable a suboptimal decoding strategy with near maximum likelihood performance for transmission over the additive white Gaussian noise channel. In this contribution, this decoding algorithm is generalized to the detection for generalized multistream spatial modulation. The proposed method can outperform conventional generalized multistream spatial modulation with respect to decoding performance, detection complexity, and spectral efficiency.
Despite the importance of Social Life Cycle Sustainability Assessment (S-LCSA), little research has addressed its integration into Product Lifecycle Management (PLM) systems. This paper presents a structured review of relevant research and practice. Also, to address practical aspects in more detail, it focuses on challenges and potential for adoption of such an integrated system at an electronics company.
We began by reviewing literature on implementations of Social-LCSA and identifying research needs. Then we investigated the status of Social-LCSA within the electronics industry, both by reviewing literature and interviewing decision makers, to identify challenges and the potential for adopting S-LCSA at an electronics company. We found low maturity of Social-LCSA, particularly difficulty in quantifying social sustainability. Adoption of Social-LCSA was less common among electronics industry suppliers, especially mining & smelting plants. Our results could provide a basis for conducting case studies that could further clarify issues involved in integrations of Social-LCSA into PLM systems.
Modeling a suitable birth density is a challenge when using Bernoulli filters such as the Labeled Multi-Bernoulli (LMB) filter. The birth density of newborn targets is unknown in most applications, but must be given as a prior to the filter. Usually the birth density stays unchanged or is designed based on the measurements from previous time steps.
In this paper, we assume that the true initial state of new objects is normally distributed. The expected value and covariance of the underlying density are unknown parameters. Using the estimated multi-object state of the LMB and the Rauch-Tung-Striebel (RTS) recursion, these parameters are recursively estimated and adapted after a target is detected.
The main contribution of this paper is an algorithm to estimate the parameters of the birth density and its integration into the LMB framework. Monte Carlo simulations are used to evaluate the detection driven adaptive birth density in two scenarios. The approach can also be applied to filters that are able to estimate trajectories.
Methods based exclusively on heart rate hardly allow to differentiate between physical activity, stress, relaxation, and rest, that is why an additional sensor like activity/movement sensor added for detection and classification. The response of the heart to physical activity, stress, relaxation, and no activity can be very similar. In this study, we can observe the influence of induced stress and analyze which metrics could be considered for its detection. The changes in the Root Mean Square of the Successive Differences provide us with information about physiological changes. A set of measurements collecting the RR intervals was taken. The intervals are used as a parameter to distinguish four different stages. Parameters like skin conductivity or skin temperature were not used because the main aim is to maintain a minimum number of sensors and devices and thereby to increase the wearability in the future.
Spatial modulation is a low-complexity multipleinput/ multipleoutput transmission technique. The recently proposed spatial permutation modulation (SPM) extends the concept of spatial modulation. It is a coding approach, where the symbols are dispersed in space and time. In the original proposal of SPM, short repetition codes and permutation codes were used to construct a space-time code. In this paper, we propose a similar coding scheme that combines permutation codes with codes over Gaussian integers. Short codes over Gaussian integers have good distance properties. Furthermore, the code alphabet can directly be applied as signal constellation, hence no mapping is required. Simulation results demonstrate that the proposed coding approach outperforms SPM with repetition codes.
The Montgomery multiplication is an efficient method for modular arithmetic. Typically, it is used for modular arithmetic over integer rings to prevent the expensive inversion for the modulo reduction. In this work, we consider modular arithmetic over rings of Gaussian integers. Gaussian integers are subset of the complex numbers such that the real and imaginary parts are integers. In many cases Gaussian integer rings are isomorphic to ordinary integer rings. We demonstrate that the concept of the Montgomery multiplication can be extended to Gaussian integers. Due to independent calculation of the real and imaginary parts, the computation complexity of the multiplication is reduced compared with ordinary integer modular arithmetic. This concept is suitable for coding applications as well as for asymmetric key cryptographic systems, such as elliptic curve cryptography or the Rivest-Shamir-Adleman system.
The expansion of a given multivariate polynomial into Bernstein polynomials is considered. Matrix methods for the calculation of the Bernstein expansion of the product of two polynomials and of the Bernstein expansion of a polynomial from the expansion of one of its partial derivatives are provided which allow also a symbolic computation.
Multi-dimensional spatial modulation is a multipleinput/ multiple-output wireless transmission technique, that uses only a few active antennas simultaneously. The computational complexity of the optimal maximum-likelihood (ML) detector at the receiver increases rapidly as more transmit antennas or larger modulation orders are employed. ML detection may be infeasible for higher bit rates. Many suboptimal detection algorithms for spatial modulation use two-stage detection schemes where the set of active antennas is detected in the first stage and the transmitted symbols in the second stage. Typically, these detection schemes use the ML strategy for the symbol detection. In this work, we consider a suboptimal detection algorithm for the second detection stage. This approach combines equalization and list decoding. We propose an algorithm for multi-dimensional signal constellations with a reduced search space in the second detection stage through set partitioning. In particular, we derive a set partitioning from the properties of Hurwitz integers. Simulation results demonstrate that the new algorithm achieves near-ML performance. It significantly reduces the complexity when compared with conventional two-stage detection schemes. Multi-dimensional constellations in combination with suboptimal detection can even outperform conventional signal constellations in combination with ML detection.
Many resource-constrained systems still rely on symmetric cryptography for verification and authentication. Asymmetric cryptographic systems provide higher security levels, but are very computational intensive. Hence, embedded systems can benefit from hardware assistance, i.e., coprocessors optimized for the required public key operations. In this work, we propose an elliptic curve cryptographic coprocessors design for resource-constrained systems. Many such coprocessor designs consider only special (Solinas) prime fields, which enable a low-complexity modulo arithmetic. Other implementations support arbitrary prime curves using the Montgomery reduction. These implementations typically require more time for the point multiplication. We present a coprocessor design that has low area requirements and enables a trade-off between performance and flexibility. The point multiplication can be performed either using a fast arithmetic based on Solinas primes or using a slower, but flexible Montgomery modular arithmetic.
In this work, we investigate a hybrid decoding approach that combines algebraic hard-input decoding of binary block codes with soft-input decoding. In particular, an acceptance criterion is proposed which determines the reliability of a candidate codeword. For many received codewords the stopping criterion indicates that the hard-decoding result is sufficiently reliable, and the costly soft-input decoding can be omitted. The proposed acceptance criterion significantly reduces the decoding complexity. For simulations we combine the algebraic hard-input decoding with ordered statistics decoding, which enables near maximum likelihood soft-input decoding for codes of small to medium block lengths.
The ballistocardiography is a technique that measures the heart rate from the mechanical vibrations of the body due to the heart movement. In this work a novel noninvasive device placed under the mattress of a bed estimates the heart rate using the ballistocardiography. Different algorithms for heart rate estimation have been developed.
This document presents a new complete standalone system for a recognition of sleep apnea using signals from the pressure sensors placed under the mattress. The developed hardware part of the system is tuned to filter and to amplify the signal. Its software part performs more accurate signal filtering and identification of apnea events. The overall achieved accuracy of the recognition of apnea occurrence is 91%, with the average measured recognition delay of about 15 seconds, which confirms the suitability of the proposed method for future employment. The main aim of the presented approach is the support of the healthcare system with the cost-efficient tool for recognition of sleep apnea in the home environment.
This paper examines the corporate organisational aspects of the implementation of Industry 4.0. Industry 4.0 builds on new technologies and appears as a disruptive innovation to manufacturing firms. Although we do have a good understanding of the technical components, the implementation of the management and organisational aspects of Industry 4.0 is under-researched. It is challenging to find qualitative empirical evidence which provides comprehensive insights about real implementation cases. Based on a case study in a German high value manufacturing firm, we explore the corporate organisation and implementation of Industry 4.0. By using the framework of Complex Adaptive System (CAS), we have identified three key factors which facilitate the implementation of Industry 4.0 namely 1.) Organisational structure changes such as the foundation of a central department for digital transformation, 2.) The election of a Chief Digital Officer as a personnel change, and 3.) Corporate opening up towards cooperating with partners as a cultural change. We have furthermore found that Lean Management is an important enabler that ensures readiness for the adoption of Industry 4.0.
Uncertainty about the future requires companies to create discontinuous innovations. Established companies, however, struggle to do so; whereas independent startups seem to better cope with this. Consequently, established companies set up entrepreneurial initiatives to make use of startups' benefits. Consequently, this led-amongst others-to great interest in socalled corporate entrepreneurship (CE) programs and to the development and characterization of several different forms. Their processes to achieve certain objectives, yet, are still rather ineffective. Thus, considerations of the actions performed in preparation for and during CE programs could be one approach to improve this but are still absent today. Furthermore, the increasing use of several CE programs in parallel seems to bear the potential for synergies and, thus, more efficient use of resources. Aiming to provide insights to both issues, this study analyzes actions of CE programs, by looking at interviews with managers of seven corporate incubators and accelerator programs of five established German tech-companies.
Digitalization is one of the most frequently discussed topics in industry. New technologies, platform concepts and integrated data models do enable disruptive business models and drive changes in organization, processes, and tools. The goal is to make a company more efficient, productive and ultimately profitable. However, many companies are facing the challenge of how to approach digital transformation in a structured way and to realize these potential benefits. What they realize is that Product Lifecycle Management plays a key role in digitalization intends, as object, structure and process management along the life cycle is a foundation for many digitalization use cases. The introduced maturity model for assessing a firm’s capabilities along the product lifecycle has been used almost two hundred times. It allows a company to compare its performance with an industry specific benchmark to reveal individual strengths and weaknesses. Furthermore, an empirical study produced multidimensional correlation coefficients, which identify dependencies between business model characteristics and the maturity level of capabilities.
In previous studies, we used a method for detecting stress that was based exclusively on heart rate and ECG for differentiation between such situations as mental stress, physical activity, relaxation, and rest. As a response of the heart to these situations, we observed different behavior in the Root Mean Square of the Successive differences heartbeats (RMSSD). This study aims to analyze Virtual Reality via a virtual reality headset as an effective stressor for future works. The value of the Root Mean Square of the Successive Differences is an important marker for the parasympathetic effector on the heart and can provide information about stress. For these measurements, the RR interval was collected using a breast belt. In these studies, we can observe the Root Mean Square of the successive differences heartbeats. Additional sensors for the analysis were not used. We conducted experiments with ten subjects that had to drive a simulator for 25 minutes using monitors and 25 minutes using virtual reality headset. Before starting and after finishing each simulation, the subjects had to complete a survey in which they had to describe their mental state. The experiment results show that driving using virtual reality headset has some influence on the heart rate and RMSSD, but it does not significantly increase the stress of driving.
Three-dimensional ship localization with only one camera is a challenging task due to the loss of depth information caused by perspective projection. In this paper, we propose a method to measure distances based on the assumption that ships lie on a flat surface. This assumption allows to recover depth from a single image using the principle of inverse perspective. For the 3D ship detection task, we use a hybrid approach that combines image detection with a convolutional neural network, camera geometry and inverse perspective. Furthermore, a novel calculation of object height is introduced. Experiments show that the monocular distance computation works well in comparison to a Velodyne lidar. Due to its robustness, this could be an easy-to-use baseline method for detection tasks in navigation systems.
This paper presents the goals, service design approach, and the results of the project “Accessible Tourism around Lake Constance”, which is currently run by different universities, industrial partners and selected hotels in Switzerland, Germany and Austria. In the 1st phase, interviews with different persons with disabilities and elderly persons have been conducted to identify the barriers and pains faced by tourists who want to spend their holidays in the region of Lake Constance as well as possible assistive technologies that help to overcome these barriers. The analysis of the interviews shows that one third of the pains and barriers are due to missing, insufficient, wrong or inaccessible information about the
accessibility of the accommodation, surroundings, and points of interests during the planning phase of the holidays. Digital assistive technologies hence play a
major role in bridging this information gap. In the 2nd phase so-called Hotel-Living-Labs (HLL) have been established where the identified assistive technologies
can be evaluated. Based on these HLLs an overall service for accessible holidays has been designed and developed. In the last phase, this service has been implemented
based on the HLLs as well as the identified assistive technologies and is currently field tested with tourists with disabilities from the three participated countries.
Location-aware mobile devices are becoming increasingly popular and GPS sensors are built into nearly every portable unit with computational capabilities. At the same time, the emergence of location-aware virtual services and ideas calls for new efficient spatial real-time queries. Communication latency in mobile environments interacting with high decentralization and the need of scalability in high-density systems with immense client counts leads to major challenges. In this paper we describe a decentralized architecture for continuous range queries in settings in which both, the requested and the requesting clients, are mobile. While prior works commonly use a request-response approach we provide a stream-based adaptive grid solution dealing with arbitrary high client counts and improving communication latency that meets given hard real-time constraints.
Deep neural networks (DNNs) are known for their high prediction performance, especially in perceptual tasks such as object recognition or autonomous driving. Still, DNNs are prone to yield unreliable predictions when encountering completely new situations without indicating their uncertainty. Bayesian variants of DNNs (BDNNs), such as MC dropout BDNNs, do provide uncertainty measures. However, BDNNs are slow during test time because they rely on a sampling approach. Here we present a single shot MC dropout approximation that preserves the advantages of BDNNs without being slower than a DNN. Our approach is to analytically approximate for each layer in a fully connected network the expected value and the variance of the MC dropout signal. We evaluate our approach on different benchmark datasets and a simulated toy example. We demonstrate that our single shot MC dropout approximation resembles the point estimate and the uncertainty estimate of the predictive distribution that is achieved with an MC approach, while being fast enough for real-time deployments of BDNNs.