Sharing databases and data streams imposes the danger of revealing private information in the form of complex events which can comprise individual data elements and their combinations. Identifying these privacy-revealing complex events is crucial for preserving privacy while maintaining data utility. However, data producers often lack the expertise to comprehensively identify these events, which undermines many state-of-the-art privacy-preserving mechanisms that rely on accurate event labeling. To address this challenge, we developed pArborist - a tool that can semi-automatically create a set of queries to identify and label privacy-revealing complex events in both static datasets and dynamic data streams, guided by the privacy requirements of the data producer. pArborist uses the schema of the database or data stream combined with initial input from the data producer, i.e., seed queries. From each seed query, pArborist grows a tree containing all possible syntactically correct queries, constrained by an upper limit on computational resources. Following this growing phase, the tree is refined by eliminating queries that lack correlation to the seed or are conditionally independent of the seed. Our evaluation indicates that pArborist achieves overall recall of \(90\%\) and precision of \(93\%\) in finding privacy-revealing queries, and this significantly surpasses the state-of-the-art approach FQID. In data stream processing experiments, pArborist introduces a delay of approximately 1.3 ms following an average warm-up period of 920 ms. The experiments also show that pArborist can automatically detect privacy-revealing complex events according to GDPR.

This paper presents a novel approach to requirements engineering for responsible explainable AI (rexAI) that pays attention to the broad range of explanation aspects and enforces the consideration of computer science, ethical, legal, and medical requirements. The medical use-case we are investigating is pediatric sleep apnea diagnosis. We analyze the non-functional and functional requirements and explore the multiple relationships and dependencies between the rexAI requirements and principles.

Good training data is a prerequisite to develop useful Machine Learning applications. However, in many domains existing data sets cannot be shared due to privacy regulations (e.g., from medical studies). This work investigates a simple yet unconventional approach for anonymized data synthesis to enable third parties to benefit from such anonymized data. We explore the feasibility of learning implicitly from visually unrealistic, task-relevant stimuli, which are synthesized by exciting the neurons of a trained deep neural network. As such, neuronal excitation can be used to generate synthetic stimuli. The stimuli data is used to train new classification models. Furthermore, we extend this framework to inhibit representations that are associated with specific individuals. Extensive comparative empirical investigation shows that different algorithms trained on the stimuli are able to generalize successfully on the same task as the original model.

Sleep apnea is a common yet severely under-diagnosed sleep related disorder. Unattended sleep monitoring at home with low-cost sensors can be leveraged for condition detection, and Machine Learning offers a generalized solution for this task. However, patient characteristics, lack of sufficient training data, and other factors can imply a domain shift between training and end-user data and reduced task performance. In this work, we address this issue with the aim to achieve personalization based on the patient’s needs. We present an unsupervised domain adaptation (UDA) solution with the constraint that labeled source data are not directly available. Instead, a classifier trained on the source data is provided. Our solution iteratively labels target data sub-regions based on classifier beliefs, and trains new classifiers from the expanding dataset. Experiments with sleep monitoring datasets and various sensors show that our solution outperforms the classifier trained on the source domain, with a kappa coefficient improvement from 0.012 to 0.242. Additionally, we apply our solution to digit classification DA between three well-established datasets, to investigate its generalizability, and allow for related work comparisons. Even without direct access to the source data, it outperforms several well-established UDA methods in these datasets.

Emerging infrastructure-less network architectures such as WSNs consist of devices that perform packet processing in software. General-purpose network simulators do currently not possess models to simulate the intra-node delay of such devices. For example, a TelosB mote with TinyOS spends seven ms on processing packets with a size of 36 bytes and fifteen ms on packets of 124 bytes. The core problem addressed in this work is that simulation does not include such delays, and therefore, the results are inaccurate. To overcome this problem, we create a communication software execution model of TelosB that accounts for its temporal behavior to enable more accurate WSN simulations in the ns-3 simulator. A challenge is to create a tracing framework for TinyOS that can be used to accurately and reliably trace the behavior of a very resource-constrained system. By analyzing the software execution of TelosB running TinyOS in the emulator Cooja/MSPSim and on a real device, we discover discrepancies in the temporal behavior. The evaluation of our model shows that it is scalable and accurate; the simulated intra-OS delay deviates at most 5% from the intra-OS delay in the real mote. When we include the model in simulations, the forwarding capacity of a mote is decreased by 36%. The WSN community can use this model for more realistic simulations, and future WSN mote models will be easier to make with it as a foundation.

Sleep apnea is a common and strongly under-diagnosed severe sleep-related respiratory disorder with periods of disrupted or reduced breathing during sleep. To diagnose sleep apnea, sleep data are collected with either polysomnography or polygraphy and scored by a sleep expert. We investigate in this work the use of supervised machine learning to automate the analysis of polygraphy data from the A3 study containing more than 7,400 hours of sleep monitoring data from 579 patients. We conduct a systematic comparative study of classification performance and resource use with different combinations of 27 classifiers and four sleep signals. The classifiers achieve up to 0.8941 accuracy (kappa: 0.7877) when using all four signal types simultaneously and up to 0.8543 accuracy (kappa: 0.7080) with only one signal, i.e., oxygen saturation. Methods based on deep learning outperform other methods by a large margin. All deep learning methods achieve nearly the same maximum classification performance even when they have very different architectures and sizes. When jointly accounting for classification performance, resource consumption and the ability to achieve with less training data high classification performance, we find that convolutional neural networks substantially outperform the other classifiers.

Good training data is a prerequisite to develop useful Machine Learning applications. However, in many domains existing data sets cannot be shared due to privacy regulations (e.g., from medical studies). This work investigates a simple yet unconventional approach for anonymized data synthesis to enable third parties to benefit from such anonymized data. We explore the feasibility of learning implicitly from visually unrealistic, task-relevant stimuli, which are synthesized by exciting the neurons of a trained deep neural network. As such, neuronal excitation can be used to generate synthetic stimuli. The stimuli data is used to train new classification models. Furthermore, we extend this framework to inhibit representations that are associated with specific individuals. We use sleep monitoring data from both an open and a large closed clinical study, and Electroencephalogram sleep stage classification data, to evaluate whether (1) end-users can create and successfully use customized classification models, and (2) the identity of participants in the study is protected. Extensive comparative empirical investigation shows that different algorithms trained on the stimuli are able to generalize successfully on the same task as the original model. Architectural and algorithmic similarity between new and original models play an important role in performance. For similar architectures, the performance is close to that of using the original data (e.g., Accuracy difference of 0.56%-3.82%, Kappa coefficient difference of 0.02-0.08). Further experiments show that the stimuli can provide state-ofthe-art resilience against adversarial association and membership inference attacks.

Supervised machine learning applications in the health domain often face the problem of insufficient training datasets. The quantity of labelled data is small due to privacy concerns and the cost of data acquisition and labelling by a medical expert. Furthermore, it is quite common that collected data are unbalanced and getting enough data to personalize models for individuals is very expensive or even infeasible. This paper addresses these problems by (1) designing a recurrent Generative Adversarial Network to generate realistic synthetic data and to augment the original dataset, (2) enabling the generation of balanced datasets based on heavily unbalanced dataset, and (3) to control the data generation in such a way that the generated data resembles data from specific individuals. We apply these solutions for sleep apnea detection and study in the evaluation the performance of four well-known techniques, i.e., K-Nearest Neighbour, Random Forest, Multi-Layer Perceptron, and Support Vector Machine. All classifiers exhibit in the experiments a consistent increase in sensitivity and a kappa statistic increase by between 0.007 and 0.182.

As a step towards mobile and ubiquitous computing, the TRAMP Real-time Application Mobility Platform (TRAMP) enables secure and user-friendly migration of multimedia application components. The motivating factors are device and user mobility, i.e., to let the user determine where application components should execute at all times. In order to organize and locate roaming devices, a decentralized peer-to-peer overlay is developed. To provide location transparency for application developers and enable efficient data sharing among application components, an API is provided that hides whether shared memory or latency optimized network distribution is used to share data. The problem of open TCP connections to third-party applications is solved with a proxy-based approach. Multimedia applications are especially sensitive to service interruptions that can be caused by migration, and a new approach for check-pointing, state transfer, and resuming an application with minimal freeze time is therefore introduced. The evaluation of TRAMP shows that this optimization for low freeze time has significant effect. For example, migrating the Skype video-conferencing application with TRAMP reduces the average freeze time from 41.1 seconds with legacy approaches to 213 milliseconds. Further results from the empirical evaluation of TRAMP demonstrate that it has no negative impact on the Quality of Experience.

Complex Event Processing (CEP) and Mobile Adhoc networks (MANETs) are two technologies that can be used to enable monitoring applications for Emergency and Rescue missions (ER). MANETs are characterized by energy limitations, and in-network processing or distributed CEP is one possible solution. Operator placement mechanism for distributed CEP has a direct impact on energy consumption. Existing operator placement mechanisms focus on static network topologies and are therefore inappropriate for MANETs scenarios. We propose a novel energy efficient decentralized distributed placement mechanism, designed to achieve fast convergence with minimal data transmission cost while achieving a near optimal placement assignment. We compare our decentralized placement mechanism with a centralized approach under different mobility scenarios. Furthermore, we evaluate the distributed CEP under different workload scenarios in order to gain additional insight into different performance characteristics of the system. Finally, we measure the impact of a simple placement replication scheme on the overall system performance in terms of delay and message overhead. Our decentralized placement mechanism achieves up to almost 50% lower message overhead compared to the centralized approach, and it has lower message overhead across different mobility scenarios compared to the centralized approach. The placement replication scheme achieves up to 51% lower delay compared to the decentralized placement mechanism with no replication.

Network simulation is commonly used to evaluate the performance of distributed systems, but these approaches do not account for the performance impact that protocol execution on nodes has on performance, which may be significant. We propose a methodology to capture execution models from communication software running on real devices where the execution models can be integrated with discrete event network simulators to improve their accuracy. We provide a set of rules to instrument the software to obtain the events of importance, and present techniques to create executable models based on the obtained traces. To make the models scalable, processing stages are reduced to statistical distributions. When the resulting models are executed in a device model with a scheduler simulator, we are able to model the dynamics of multithreading and parallel execution. Our initial results from a proof-of-concept extension to Ns-3 show that our models are able to accurately model protocol execution on the Google Nexus One with low simulation overhead.

There is a rising interest to use sensors of various kinds for human activity recognition. Complex human activities are composed of temporally related simple activities and the concept of complex events is well suited to capture this relationship and to detect complex activities, i.e., complex events. This paper addresses the need for high accuracy of complex activity detection and low battery consumption of the sensors. To achieve this goal, this paper presents a framework to obtain the required accuracy of complex activity detection and minimize the cost of delivering samples from the sensors to the sink. We formalize the problem as an integer-programming problem and solve it by an approximation approach. The goal is to satisfy the user specified accuracy at a minimum cost. We compare the performance of our approximation approach with exact method for complex human activity determination. Evaluation results with a publicly available dataset demonstrate the potential impact of our approach.

Due to the lack of multicast services in the Internet, applications based on single-source, multiple-destination transfers such as video conferencing, IP radio, and IPTV must use unicast. This type of traffic exhibits high redundancy with temporal clustering of duplicated packets. The redundancy originates from multiple transfers of the same data chunk over the same link. We propose CacheCast, a link-layer caching mechanism that eliminates the redundant data transmissions using small caches on links. CacheCast's underlying principles are simplicity and reliability. It is a fully distributed and incrementally deployable architecture. It consists of small caches on links that act independently and a server support that simplifies the link cache operation. Our analysis indicates that transfers of the same data to multiple destinations with CacheCast can achieve near-multicast efficiency in terms of consumed link bandwidth. The implementation of CacheCast proves its feasibility, efficiency, and the improvements of the server.

This paper proposes a new delivery-centric abstraction. A delivery-centric abstraction allows applications to generate content requests agnostic to location or protocol, with the additional ability to stipulate high-level requirements regarding such things as performance, security, resource consumption and monetary cost. A delivery-centric system therefore constantly adapts to fulfil these requirements, given the constraints of the environment. This abstraction has been realised through a delivery-centric middleware called Juno, which uses a reconfigurable software architecture to (i) discover multiple sources of an item of content, (ii) model each source's ability to provide the content, then (iii) adapt to interact with the source(s) that can best fulfil the application's requirements. Juno therefore utilises existing providers in a backwards compatible way, supporting immediate deployment. This paper evaluates Juno using Emulab to validate its ability to adapt to its environment.

Video streaming is not possible between nodes in different partitions of a Mobile Ad-Hoc Network (MANET). However, ferry nodes can be used to deliver video in this environment. This service is helpful in some application scenarios, like emergencies. An important problem arises when the capacity offered by such a delay-tolerant network is not enough to deliver all the video produced. Then, video adaptation is necessary, but the network capacity is hard to estimate. Dynamic Temporal Scalability (DTS) is a novel technique to solve this problem. DTS schedules frames from a stream stored in a node adapting the frame rate to the available resources. The results of evaluating this technique show that the frame sequence delivered to the user is close to live video and has small quality variations. In addition, video quality scales with the available resources. Finally, the efficiency in the use of network resources is similar with DTS and the default scheduling technique, i.e., FIFO.

This article proposes a new delivery-centric abstraction which extends the existing content-centric networking API. A delivery-centric abstraction allows applications to generate content requests agnostic to location or protocol, with the additional ability to stipulate high-level requirements regarding such things as performance, security, and resource consumption. Fulfilling these requirements, however, is complex as often the ability of a provider to satisfy requirements will vary between different consumers and over time. Therefore, we argue that it is vital to manage this variance to ensure an application fulfils its needs. To this end, we present the Juno middleware, which implements delivery-centric support using a reconfigurable software architecture to: (i) discover multiple sources of an item of content; (ii) model each source’s ability to provide the content; then (iii) adapt to interact with the source(s) that can best fulfil the application’s requirements. Juno therefore utilizes existing providers in a backwards compatible way, supporting immediate deployment. This article evaluates Juno using Emulab to validate its ability to adapt to its environment.

Network simulators typically do not include node models. Our studies show that in networks such as mobile networks, the impact of nodes on performance can be significant. Existing techniques to simulate nodes' are not scalable for network simulations, and require a too large modelling effort to be feasible for network research. In this paper, we propose to capture flexible per-protocol performance profiles from real, running systems using instrumentation and traffic benchmarking techniques. By using the obtained profiles as input into an extended scheduler simulator, the behaviour of the node can be accurately reproduced. Since the processing overhead is represented statistically, we preserve scalability and a low modelling overhead.

In sparse mobile ad hoc networks, placement of services and data is crucial to assure their availability to all nodes because sparse population of nodes can lead to (frequent) network partitions. If these dynamic networks display a fairly stable cluster structure, it is possible to utilize this structure to improve service and data availability. However, clustering in a dynamic network is a very challenging task due to the ever-changing topology and irregular density of such a network. In this paper, we investigate clustering of dynamic networks with the help of community detection mechanisms, using only topology information from the local routing table. The main aim of our approach is to reduce to “zero” the communication overhead needed for cluster management and to dynamically adapt to the size and layout of the network. We have performed extensive experiments to evaluate the consistency, quality, and stability of the clustering returned by our algorithms. The results show that our nonintrusive clustering indeed discovers temporary groups of nodes that form stable clusters in the network. Moreover, even though the local routing tables in general reflect slightly diverging topologies, our results still show only small differences between the communities detected at different nodes.

Due to the lack of multicast services in the Internet, applications based on single source multiple destinations transfers such as video conferencing, IP radio, IPTV must use unicast or application layer multicast. This in turn has several well-known drawbacks. A basic insight is that this type of traffic exhibits high redundancy with temporal clustering of duplicated packets. The redundancy originates from multiple transfers of the same data chunk over the same link. We propose CacheCast-a link layer caching mechanism-that eliminates the redundant data transmissions using small caches on links. CacheCast's underlying principles are simplicity and reliability. It is a fully distributed and incrementally deployable architecture. It consists of small caches on links that act independently. A single cache removes redundant data from a packet on the link entry and recovers the data on the link exit. Thus, link caches are transparent to routers. We show through analysis and simulation that CacheCast achieves near multicast efficiency for superposition of unicast connections. We implemented CacheCast in ns-2 and show that it does not violate the current understanding of "fairness" in the Internet.

Using Mobile Ad-hoc Networks (MANETs) for audio and video transmission is very promising for application domains such as emergency and rescue. However, audio/video streaming services are not designed for such dynamic and unstable networks. The problems are even more important in so-called sparse MANETs where the node density is relatively low so that disconnections and network partitions are common. We have designed an architecture that combines MANET routing with caching and delay tolerant store-carry-forward operations in an overlay network to improve the quality of audio/video transmission over sparse MANETs. We have implemented a prototype to evaluate the architecture. The results from the experiments demonstrate that our system clearly outperforms simple client-server solutions when the network has temporal disconnections.

An approach to information sharing in mobile ad-hoc networks (MANETs) used e.g. in rescue operations, is to store on every node a small amount of metadata describing what information resources exist in the network and where they reside, allowing applications to first search locally for information about suitable resources, and next request relevant information from a node that contains the resource. The characteristics of MANETs in general and sparse, delay-tolerant networks in particular, make the task of maintaining and disseminating metadata across all nodes difficult, particularly in the presence of scarce resources. We have designed and implemented three protocols which use different approaches to metadata dissemination: epidemic one-to-one routing, one-to-many broadcasting that utilises the characteristics of the shared radio medium of wireless networks, and the semantic protocol where a group consisting of e.g. rescue team leaders is given priority in the dissemination process and afterwards serves as multiple starting points for further dissemination. In the MIDAS project we produce middleware that speeds up MANET application development. By prototyping the metadata management component of MIDAS and testing the prototype with each of the three protocols in the network emulator environment NEMAN, we have measured bandwidth usage and performance. The implemented broadcast protocol is measured to use substantially less bandwidth than epidemic routing. The semantic protocol shows that the group indeed gets priority; it is comparable to the broadcast protocol in terms of bandwidth usage. The broadcast protocol has been used successfully in field tests of the middleware.

Today's Internet has evolved from an early experimental small-scale network to a world-wide network which infrastructure that is used on a day to day basis by companies, public bodies, governments, individuals etc. Many shortcomings of the Internet have been addressed over the last years as "add-ons", but recently many "Future Internet" initiatives have been started with the challenge to re-design the Internet to meet the future challenges. Since the majority of multimedia systems and applications are depending on the Internet we aim in this tutorial to give an overview on ongoing initiatives, identify new concepts and study how they might be leveraged for multimedia systems and applications.

The Streaming Peer-to-Peer Protocol (SPP) architecture is a hybrid P2P system for interactive Video-on-Demand Streaming. We aim to demonstrate key issues of SPP, i.e., peer selection and incentive management. Through real live demonstration on PlanetLab and through simulated scenarios of interest in NS2, the audience will be able to judge the resulting perceptual Quality-of-Service (QoS) on a large screen connected to a set-top box. Furthermore, we plan to visualize what is happening inside SPP on a Laptop.

In emergency and rescue operations MANETs can help to increase the efficiency of the collaborative work. The goal is to increase the availability of services and information through resource awareness. The work described in this paper, presents our approach towards prediction of current and future resources available on remote devices. Our solution is based on information extracted from the node's routing protocol. The advantage of our approach is that resource management is not intrusive, does not need location information, and is independent of the routing protocol. We are using simulations to analyze for how far into the future we can make valid predictions.

In the ad-hoc InfoWare project we investigate middleware solutions for mobile ad-hoc networks (MANETs) used in emergency and rescue situations. One goal in the project is to increase availability of services and information through resource awareness. In this context we regard the ability to predict with a certain confidence the future resource availability as very helpful. The work described in this paper, presents our current progress towards prediction of future connectivity between nodes using information about a node's neighborhood extracted from the routing protocol. The simple idea is that if two nodes have been close to each other for a certain time, there is a high probability that they will be close also in the immediate future. The advantage with our approach is that the nodes do not need location information. We are using simulation to analyze for how far into the future we can make valid predictions

No abstract available.

No abstract available.

Data servers for multimedia applications like news-on-demand represent a severe bottleneck, because a potentially (very) high number of users concurrently retrieve data with high data rates. In the Intermediate Storage Node Concept (INSTANCE) project, we develop a new architecture for media-on-demand servers that maximizes the number of concurrent clients a single server can support. Traditional bottlenecks, like copy operations, multiple copies of the same data element in main memory, and checksum calculation in communication protocols are avoided by applying three orthogonal techniques: zero-copy-one-copy memory architecture, network level framing, and integrated error management. We describe the design, implementation, and evaluation of our integrated error management mechanism. Our results show that the reuse of parity information from a RAID system as forward error correction information in the transport protocol reduces the server workload and enables smooth playout at the client.

Article Techniques to increase disk access locality in the Minorca multimedia file system Share on Authors: Chuanbao Wang University of Oslo, UniK - Center for Technology at Kjeller Granaveien 33, P.B. 70 N-2027 Kjeller, Norway University of Oslo, UniK - Center for Technology at Kjeller Granaveien 33, P.B. 70 N-2027 Kjeller, NorwayView Profile , Vera Goebel University of Oslo, UniK - Center for Technology at Kjeller Granaveien 33, P.B. 70 N-2027 Kjeller, Norway University of Oslo, UniK - Center for Technology at Kjeller Granaveien 33, P.B. 70 N-2027 Kjeller, NorwayView Profile , Thomas Plagemann University of Oslo, UniK - Center for Technology at Kjeller Granaveien 33, P.B. 70 N-2027 Kjeller, Norway University of Oslo, UniK - Center for Technology at Kjeller Granaveien 33, P.B. 70 N-2027 Kjeller, NorwayView Profile Authors Info & Claims MULTIMEDIA '99: Proceedings of the seventh ACM international conference on Multimedia (Part 2)October 1999 Pages 147–150https://doi.org/10.1145/319878.319917Online:01 October 1999Publication History 6citation202DownloadsMetricsTotal Citations6Total Downloads202Last 12 Months1Last 6 weeks1 Get Citation AlertsNew Citation Alert added!This alert has been successfully added and will be sent to:You will be notified whenever a record that you have chosen has been cited.To manage your alert preferences, click on the button below.Manage my AlertsNew Citation Alert!Please log in to your account Save to BinderSave to BinderCreate a New BinderNameCancelCreateExport CitationPublisher SiteGet Access

Da CaPo provides an environment for the dynamic configuration of protocols. Configuration is done with respect to application requirements, properties of the offered network services, and the available resources in the end systems. The goal of the configuration is to provide a service with minimal necessary functionality for each request, i.e., to diminish protocol complexity and so to increase protocol performance. Modules serve as basic building blocks for the protocol configuration. Common software engineering principles like encapsulation and information hiding as well as a unified module interface allow the unconstrained configuration of modules to protocols. The Da CaPo runtime environment links modules to protocols in one UNIX process and realizes an efficient data transport inside the end systems because performance reducing operations like data copying or process switches are minimized.>