Search

We present ElasticHash, a novel approach for high-quality, efficient, and large-scale semantic image similarity search. It is based on a deep hashing model to learn hash codes for fine-grained image similarity search in natural images and a two-stage method for efficiently searching binary hash codes using Elasticsearch (ES). In the first stage, a coarse search based on short hash codes is performed using multi-index hashing and ES terms lookup of neighboring hash codes. In the second stage, the list of results is re-ranked by computing the Hamming distance on long hash codes. We evaluate the retrieval performance of \textit{ElasticHash} for more than 120,000 query images on about 6.9 million database images of the OpenImages data set. The results show that our approach achieves high-quality retrieval results and low search latencies.

Electrocardiogram (ECG) data collection during emergency situations is challenging, making ECG data generation an efficient solution for dealing with highly imbalanced ECG training datasets. In this paper, we propose a novel approach for ECG signal generation using Generative Adversarial Networks (GANs) and statistical ECG data modeling. Our approach leverages prior knowledge about ECG dynamics to synthesize realistic signals, addressing the complex dynamics of ECG signals. To validate our approach, we conducted experiments using ECG signals from the MIT-BIH arrhythmia database. Our results demonstrate that our approach, which models temporal and amplitude variations of ECG signals as 2-D shapes, generates more realistic signals compared to state-of-the-art GAN based generation baselines. Our proposed approach has significant implications for improving the quality of ECG training datasets, which can ultimately lead to better performance of ECG classification algorithms. This research contributes to the development of more efficient and accurate methods for ECG analysis, which can aid in the diagnosis and treatment of cardiac diseases., Comment: 6 figures, 31 pages, under review

Emerging network architectures like Information-centric Networking (ICN) offer 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, known as in-network processing. However, existing ICN architectures are limited in terms of data plane programmability due to the lack 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 a 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). In addition, we provide a CEP query language and facilitate CEP operations while increasing the range of 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 applications: energy forecasting in smart homes and a disaster scenario., Comment: arXiv admin note: text overlap with arXiv:2012.05070

Information-centric Networking (ICN) is an emerging Internet architecture that offers promising features, such as in-network caching and named data addressing, to support the edge computing paradigm, in particular Internet-of-Things (IoT) applications. ICN can benefit from Complex Event Processing (CEP), which is an in-network processing paradigm to specify and perform efficient query operations on data streams. However, integrating CEP into ICN is a challenging task due to the following reasons: (1) typical ICN architectures do not provide support for forwarding and processing continuous data streams; (2) IoT applications often need short response times and require robust event detection, which both are hard to accomplish using existing CEP systems. In this article, we present a novel network architecture, called INetCEP, for efficient CEP-based in-network processing as part of ICN. INetCEP enables efficient data processing in ICN by means of (1) a unified communication model that supports continuous data streams, (2) a meta query language for CEP to specify data processing operations in the data plane, and (3) query processing algorithms to resolve the specified operations. Our experimental results for two IoT use cases and datasets show that INetCEP offers very short response times of up to 73 {\mu}s under high workload and is more than 15X faster in terms of forwarding events than the state-of-the-art CEP system Flink. Furthermore, the delivery and processing of complex queries is around 32X faster than Flink and more than 100X faster than a naive pull-based reference approach, while maintaining 100% accuracy.

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 yet comprehensive 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.

Network programmability will be required to handle future increased network traffic and constantly changing application needs. However, there is currently no way of using a high-level, easy to use programming language to program Wi-Fi firmware. This impedes rapid prototyping and deployment of novel network services/applications and hinders continuous performance optimization in Wi-Fi networks, since expert knowledge is required for both the used hardware platforms and the Wi-Fi domain. In this paper, we present ReactiFi, a high-level reactive programming language to program Wi-Fi chips on mobile consumer devices. ReactiFi enables programmers to implement extensions of PHY, MAC, and IP layer mechanisms without requiring expert knowledge of Wi-Fi chips, allowing for novel applications and network protocols. ReactiFi programs are executed directly on the Wi-Fi chip, improving performance and power consumption compared to execution on the main CPU. ReactiFi is conceptually similar to functional reactive languages, but is dedicated to the domain-specific needs of Wi-Fi firmware. First, it handles low-level platform-specific details without interfering with the core functionality of Wi-Fi chips. Second, it supports static reasoning about memory usage of applications, which is important for typically memory-constrained Wi-Fi chips. Third, it limits dynamic changes of dependencies between computations to dynamic branching, in order to enable static reasoning about the order of computations. We evaluate ReactiFi empirically in two real-world case studies. Our results show that throughput, latency, and power consumption are significantly improved when executing applications on the Wi-Fi chip rather than in the operating system kernel or in user space. Moreover, we show that the high-level programming abstractions of ReactiFi have no performance overhead compared to manually written C code.

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.

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., Comment: 18th International Conference on Ad Hoc Networks and Wireless (AdHoc-Now 2019)

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., Comment: 2019 IEEE Global Humanitarian Technology Conference (GHTC)

Computation offloading is often used in mobile cloud, edge, 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 intermittent or error-prone. In this paper, we present OPPLOAD, a novel framework for offloading computational workflows in opportunistic networks. The individual tasks forming a workflow can be assigned to particular remote execution platforms (workers) either preselected ahead of time or decided just in time where a matching worker will automatically be assigned for the next task. Tasks are only assigned to capable workers that announce their capabilities. Furthermore, tasks of a workflow can be executed on multiple workers that are automatically selected to balance the load. Our Python implementation of OPPLOAD is publicly available as open source software. The results of our experimental evaluation demonstrate the feasibility of our approach.

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., Comment: LCN 2019 Cam Ready Version

Video indexing approaches such as visual concept classification and person recognition are essential to enable fine-grained semantic search in large-scale video archives such as the historical video collection of former German Democratic Republic (GDR) maintained by the German Broadcasting Archive (DRA). Typically, a lexicon of visual concepts has to be defined for semantic search. However, the definition of visual concepts can be more or less subjective due to individually differing judgments of annotators, which may have an impact on annotation quality and subsequently training of supervised machine learning methods. In this paper, we analyze the inter-coder agreement for historical TV data of the former GDR for visual concept classification and person recognition. The inter-coder agreement is evaluated for a group of expert as well as non-expert annotators in order to determine differences in annotation homogeneity. Furthermore, correlations between visual recognition performance and inter-annotator agreement are measured. In this context, information about image quantity and agreement are used to predict average precision for concept classification. Finally, the influence of expert vs. non-expert annotations acquired in the study are used to evaluate person recognition.

The German Broadcasting Archive (DRA) maintains the cultural heritage of radio and television broadcasts of the former German Democratic Republic (GDR). The uniqueness and importance of the video material stimulates a large scientific interest in the video content. In this paper, we present an automatic video analysis and retrieval system for searching in historical collections of GDR television recordings. It consists of video analysis algorithms for shot boundary detection, concept classification, person recognition, text recognition and similarity search. The performance of the system is evaluated from a technical and an archival perspective on 2,500 hours of GDR television recordings., Comment: TPDL 2016, Hannover, Germany. Final version is available at Springer via DOI

In this paper we present an efficient algorithm for the segmentation of the inner and outer boundary of thoratic and abdominal aortic aneurysms (TAA & AAA) in computed tomography angiography (CTA) acquisitions. The aneurysm segmentation includes two steps: first, the inner boundary is segmented based on a grey level model with two thresholds; then, an adapted active contour model approach is applied to the more complicated outer boundary segmentation, with its initialization based on the available inner boundary segmentation. An opacity image, which aims at enhancing important features while reducing spurious structures, is calculated from the CTA images and employed to guide the deformation of the model. In addition, the active contour model is extended by a constraint force that prevents intersections of the inner and outer boundary and keeps the outer boundary at a distance, given by the thrombus thickness, to the inner boundary. Based upon the segmentation results, we can measure the aneurysm size at each centerline point on the centerline orthogonal multiplanar reformatting (MPR) plane. Furthermore, a 3D TAA or AAA model is reconstructed from the set of segmented contours, and the presence of endoleaks is detected and highlighted. The implemented method has been evaluated on nine clinical CTA data sets with variations in anatomy and location of the pathology and has shown promising results., Comment: 7 pages, 7 figures, 1 table, 12 references, Proc. SPIE 6918, Medical Imaging 2008: Visualization, Image-Guided Procedures, and Modeling, 69181F (17 March 2008)

In this paper a method is introduced, to visualize bifurcated stent grafts in CT-Data. The aim is to improve therapy planning for minimal invasive treatment of abdominal aortic aneurysms (AAA). Due to precise measurement of the abdominal aortic aneurysm and exact simulation of the bifurcated stent graft, physicians are supported in choosing a suitable stent prior to an intervention. The presented method can be used to measure the dimensions of the abdominal aortic aneurysm as well as simulate a bifurcated stent graft. Both of these procedures are based on a preceding segmentation and skeletonization of the aortic, right and left iliac. Using these centerlines (aortic, right and left iliac) a bifurcated initial stent is constructed. Through the implementation of an ACM method the initial stent is fit iteratively to the vessel walls - due to the influence of external forces (distance- as well as balloonforce). Following the fitting process, the crucial values for choosing a bifurcated stent graft are measured, e.g. aortic diameter, right and left common iliac diameter, minimum diameter of distal neck. The selected stent is then simulated to the CT-Data - starting with the initial stent. It hereby becomes apparent if the dimensions of the bifurcated stent graft are exact, i.e. the fitting to the arteries was done properly and no ostium was covered., Comment: 6 pages, 5 figures, 5 equations, 9 references in Proc. SPIE 6509, Medical Imaging 2007: Visualization and Image-Guided Procedures, 65091N (22 March 2007)

The most common sellar lesion is the pituitary adenoma, and sellar tumors are approximately 10-15% of all intracranial neoplasms. Manual slice-by-slice segmentation takes quite some time that can be reduced by using the appropriate algorithms. In this contribution, we present a segmentation method for pituitary adenoma. The method is based on an algorithm that we have applied recently to segmenting glioblastoma multiforme. A modification of this scheme is used for adenoma segmentation that is much harder to perform, due to lack of contrast-enhanced boundaries. In our experimental evaluation, neurosurgeons performed manual slice-by-slice segmentation of ten magnetic resonance imaging (MRI) cases. The segmentations were compared to the segmentation results of the proposed method using the Dice Similarity Coefficient (DSC). The average DSC for all datasets was 75.92% +/- 7.24%. A manual segmentation took about four minutes and our algorithm required about one second., Comment: 7 pages, 6 figures, 1 table, 16 references in Proc. SPIE 7963, Medical Imaging 2011: Computer-Aided Diagnosis, 79632T (9 March 2011). arXiv admin note: text overlap with arXiv:1103.1778

In this article, we present a graph-based method using a cubic template for volumetric segmentation of vertebrae in magnetic resonance imaging (MRI) acquisitions. The user can define the degree of deviation from a regular cube via a smoothness value Delta. The Cube-Cut algorithm generates a directed graph with two terminal nodes (s-t-network), where the nodes of the graph correspond to a cubic-shaped subset of the image's voxels. The weightings of the graph's terminal edges, which connect every node with a virtual source s or a virtual sink t, represent the affinity of a voxel to the vertebra (source) and to the background (sink). Furthermore, a set of infinite weighted and non-terminal edges implements the smoothness term. After graph construction, a minimal s-t-cut is calculated within polynomial computation time, which splits the nodes into two disjoint units. Subsequently, the segmentation result is determined out of the source-set. A quantitative evaluation of a C++ implementation of the algorithm resulted in an average Dice Similarity Coefficient (DSC) of 81.33% and a running time of less than a minute., Comment: 23 figures, 2 tables, 43 references, PLoS ONE 9(4): e93389

Diffusion Tensor Imaging (DTI) is a non-invasive imaging technique that allows estimation of the location of white matter tracts in-vivo, based on the measurement of water diffusion properties. For each voxel, a second-order tensor can be calculated by using diffusion-weighted sequences (DWI) that are sensitive to the random motion of water molecules. Given at least 6 diffusion-weighted images with different gradients and one unweighted image, the coefficients of the symmetric diffusion tensor matrix can be calculated. Deriving the eigensystem of the tensor, the eigenvectors and eigenvalues can be calculated to describe the three main directions of diffusion and its magnitude. Using DTI data, fiber bundles can be determined, to gain information about eloquent brain structures. Especially in neurosurgery, information about location and dimension of eloquent structures like the corticospinal tract or the visual pathways is of major interest. Therefore, the fiber bundle boundary has to be determined. In this paper, a novel ray-based approach for boundary estimation of tubular structures is presented., Comment: 5 pages, 2 figures, 7 references

In this contribution, a novel method for stent simulation in preoperative computed tomography angiography (CTA) acquisitions of patients is presented where the sealing zones are automatically calculated and visualized. The method is eligible for non-bifurcated and bifurcated stents (Y-stents). Results of the proposed stent simulation with an automatic calculation of the sealing zones for specific diseases (abdominal aortic aneurysms (AAA), thoracic aortic aneurysms (TAA), iliac aneurysms) are presented. The contribution is organized as follows. Section 2 presents the proposed approach. In Section 3, experimental results are discussed. Section 4 concludes the contribution and outlines areas for future work., Comment: 4 pages, 2 figures, 10 references

We present the integration of the OpenIGTLink network protocol for image-guided therapy (IGT) with the medical prototyping platform MeVisLab. OpenIGTLink is a new, open, simple and extensible network communication protocol for IGT. The protocol provides a standardized mechanism to connect hardware and software by the transfer of coordinate transforms, images, and status messages. MeVisLab is a framework for the development of image processing algorithms and visualization and interaction methods, with a focus on medical imaging. The integration of OpenIGTLink into MeVisLab has been realized by developing a software module using the C++ programming language. As a result, researchers using MeVisLab can interface their software to hardware devices that already support the OpenIGTLink protocol, such as the NDI Aurora magnetic tracking system. In addition, the OpenIGTLink module can also be used to communicate directly with Slicer, a free, open source software package for visualization and image analysis. The integration has been tested with tracker clients available online and a real tracking system., Comment: 18 pages, 5 figures, 1 table, 30 references

Volumetric change in glioblastoma multiforme (GBM) over time is a critical factor in treatment decisions. Typically, the tumor volume is computed on a slice-by-slice basis using MRI scans obtained at regular intervals. (3D)Slicer - a free platform for biomedical research - provides an alternative to this manual slice-by-slice segmentation process, which is significantly faster and requires less user interaction. In this study, 4 physicians segmented GBMs in 10 patients, once using the competitive region-growing based GrowCut segmentation module of Slicer, and once purely by drawing boundaries completely manually on a slice-by-slice basis. Furthermore, we provide a variability analysis for three physicians for 12 GBMs. The time required for GrowCut segmentation was on an average 61% of the time required for a pure manual segmentation. A comparison of Slicer-based segmentation with manual slice-by-slice segmentation resulted in a Dice Similarity Coefficient of 88.43 +/- 5.23% and a Hausdorff Distance of 2.32 +/- 5.23 mm., Comment: 7 pages, 6 figures, 2 tables, 1 equation, 43 references