Mastergradsoppgaver i informatikk

Image and video processing using graphics hardware

Sat, 01 May 2010 00:00:00 GMT

Lanes, Børge
Graphic Processing Units have during the recent years evolved into inexpensive high-performance many-core computing units. Earlier being accessible only by graphic APIs, new hardware architectures and programming tools have made it possible to program these devices using arbitrary data types and standard languages like C. This thesis investigates the development process and performance of image and video processing algorithms on graphic processing units, regardless of vendors. The tool used for programming the graphic processing units is OpenCL, a rela- tively new specification for heterogenous computing. Two image algorithms are investigated, bilateral filter and histogram. In addition, an attempt have been tried to make a template-based solution for generation and auto-optimalization of device code, but this approach seemed to have some shortcomings to be usable enough at this time.

GeStore : incremental computation for metagenomic pipelines

Fri, 01 Jun 2012 00:00:00 GMT

Pedersen, Edvard
Genomics is the study of the genomes of organisms. Metagenomics is the study of environmental genomic samples. For both genomics and metagenomics DNA sequencing, and the analysis of these sequences, is an important tool. This analysis is done through integration of sequence data with existing meta-data collections. Genomics is the study of the genomes of organisms, and involves cultivating organisms in a lab and analyzing them. Metagenomics is the study of genomic samples collected directly from the environment, allowing researchers to study organisms that are difficult to cultivate in a petri dish. DNA sequencing and the analysis of these sequences is an important tool for both genomics and metagenomics. The integration of the data produced by sequencing with existing meta-data collections is particularly interesting for metagenomics, as a single biological sample can contain thousands of different organisms. The recent developments in DNA sequencing technology mean that the volume of data that can be produced per dollar is increasing faster than the volume of data that can be analyzed and stored per dollar. This data growth means that the initial analysis of these massive data sets becomes increasingly expensive. In addition, there is a need to periodically update old results using new meta-data from the many knowledge bases (meta-data collections) for biological data. Today, this typically requires rerunning the experimental analysis. Such incremental analysis is interesting for metagenomics since environmental samples potentially contain thousands of organisms. In metagenomic analysis, different sets of tools are used depending on the type of information required. These tools are generally arranged in a pipeline, where the output files of one tool acts as the input for the next. The analysis done by some steps is dependent on different meta-data collections. When meta-data is updated, these steps and all subsequent steps typically need to be executed again. Incremental updates can save significant computation time by running these pipelines against the updated segments, rather than the full meta-data collections. We believe that systems for incremental updates for metagenomic analysis pipelines have the following requirements; (i) reduce the computational resource requirements by using incremental update techniques (ii) the meta-data collections should be accessible without the use of proprietary or computationally expensive techniques (iii) do the incremental updates on demand, due to different needs of experiments, through handling meta-data updates and generating arbitrary delta meta-data collections (iv) support most genomic analysis tools and run on most job management systems (v) no changes should be made to the tools that the pipeline is comprised of, since modifying the many available tools is impractical (vi) the changes to the job management and resource allocation system should be minimal, to save implementation time for the pipeline system maintainer (vii) maintain a view of previous meta-data collections, so old experiments can be repeated with the correct meta-data collection version. To our knowledge no existing incremental update systems satisfy all seven requirements. Often they do not support on-demand processing or maintaining views of old data, in addition many systems require computations to be done within a specific framework or programming language. In this thesis we describe the GeStore incremental update system which satisfies all seven requirements. GeStore reduces the size of the meta-data collections, and thus the computational requirements for the pipeline, by leveraging incremental update techniques, satisfying requirements (i) and (iii). In addition it reduces the storage requirements of the meta-data collections, while still maintaining a complete view of the meta-data collection in a plain-text format, fulfilling requirement (ii) and (vii). It also presents a simple interface to the application programmer, so that integrating the system with existing pipeline solutions does not require large changes to the pipeline system or tools, in accordance with requirements (vi), (iv) and (v). GeStore has been implemented using the MapReduce framework, along with HBase, to provide scalable meta-data processing. We demonstrate the system by generating subsets of meta-data collections for use by the widely used genomic tool BLAST. In our evaluation, we have integrated GeStore with an existing pipelining system, GePan; a metagenomic pipeline system developed for a local biotech company in Tromsø, Norway, and used real-world data to evaluate the performance and benefits of GeStore. Our experimental results show that GeStore is able to reduce the runtime of the incremental updates by up to 65\% when compared to unmodified GePan, while introducing a low storage overhead and requiring minimal changes to GePan. We beleive that efficient on-demand updates of metagenomic data, as provided by GeStore, will be useful to our biology collaborators.

Hubble : a platform for developing apps that manage cloud applications and analyze their performance

Tue, 12 Jun 2012 00:00:00 GMT

Pettersen, Robert Molund
The ability to deliver computing as a metered service has made the cloud an attractive platform for deployment of applications. Using the cloud, enterprises experience a decrease in maintenance overhead, faster deployment, and that cloud elasticity can be exploited to meet fluctuating resource demands.; This thesis presents Hubble, a platform for developing apps that manage cloud applications and analyze their performance. Hubble provides apps with support for persistent storage of performance data, creating secure channels for communication with cloud instrumentation and management software, and interfaces to aid with analytical computations on performance data.; We present and evaluate several apps that have been developed for Hubble. These provide functionality spanning from retrieval of performance data, visualization of performance, and management of cloud services.

Precise video feedback through live annotation of football

Fri, 01 Jun 2012 00:00:00 GMT

Grønvik, Johan
The domain of sports analysis is a huge field in sports science. Several different computer systems are available for doing analysis, both expensive and less expensive. Some specialize in specific sports such as football or ice hockey, while others are sports agnostic. However, a common property of most of these systems is that they try to give in-depth and detailed analysis of the sport in question. This thesis proposes and describes a system that provides the user with the ability to annotate interesting happenings during a live sporting event, through a non-invasive mobile device interface. The device permits focus on important happenings by filtering out unnecessary detail. Our system provides corresponding video of the annotations on the same mobile device, thereby facilitating the process of giving video feedback to the involved coaches and players. We have implemented a prototype of the system that enables evaluation of this idea, and through case studies with Tromsø Idrettslag, a Norwegian Premier League football club, we show its usefulness and applicability.

Harvest : a collaborative system for distributed retrieval of social data

Mon, 11 Jun 2012 00:00:00 GMT

Kreutzer, Tor
In recent years, social network providers has become one of the largest industries in the world. These networks created a new arena for sharing information over the Internet, and thus changed the way people interact with each other. Hundreds of millions of social network users are updating statuses and sending messages to each other every day. These interactions produce vast amounts of social data. This data is the core of the social network providers business model, and it is sold to large companies to perform personalized advertisement, brand monitoring and viral marketing. The price of this data can be intimidating, and some might be unable or unwilling to pay for it because of its price. If the data was freely available, research that could benefit from this data would be derived more freely, leading to new knowledge. This thesis presents Harvest, a collaborative system for retrieving social data. Harvest is a peer-to-peer system consisting of contributing social network users, inspired by public resource computing. Harvest shares social network account-bound resources to retrieve large social data sets. Contribution is achieved by running an application on the contributors computer like other public resource computing system such as the @home systems. The system implements retrieval of data from Twitter. Experiments on real Twitter data show that the system scales with increased contribution. The data retrieval bandwidth per contributing user is quite low, and the number of contributors needed to achieve a considerably large data retrieval bandwidth is high, but there are no associated financial costs with the system. Harvest would benefit greatly by retrieving data from more sources as this would increase its data retrieval bandwidth, in addition to offer more abundant data.

Evaluation of shared tuple spaces as communication model for semi-autonomous robots in a mobile environment

Mon, 11 Jun 2012 00:00:00 GMT

Svendby, Andreas
Robotics can be utilized more in emergency services, and a software platform for controlling many semi-autonomous can make it more alluring to use robots in this area. Using semi-autonomous robots can allow personnel to issue robots to perform complex task, without the need of extensive training, and it allows one person to control many robots alone. One challenging aspect of using robots in emergency situations is handling communication between devices in the system. Since emergency situations can be chaotic it must be assumed that the robots have to work in a segmented network, and devices in the system must be allowed to move. Due to the mobile environment, a spatial and temporal uncoupled communication model can be beneficial; it helps handle much of the complexity acquaint with a mobile environment. A possible architecture for robots in a semi-autonomous robot platform has been discussed, and some features for a semi-autonomous robot control unit was implemented. A shared tuple space was designed and implemented as a communication model for use in a mobile environment. The model is based on the client-server model, consisting of three main components: hosts, clients and name servers. Hosts act as buffers in the form of a tuple space, storing tuples from clients. Hosts can be accessed remotely over a network, and clients can insert, read, and withdraw tuples from hosts, thus providing a mechanism for passing data between devices. Clients provide a interface for processes to access the shared tuple space through. The client is also responsible for combine the content from the available hosts, constructing the shared tuple space as seen from the clients point of view. Name servers simply provide device detection, letting clients locate hosts. The use of this communication model grants the ability for clients to pass messages between each other without knowing which process will retrieve it, or at time the message is retrieved. A set of experiments were performed to evaluate the performance of the implemented shared tuple space. Performance results show that the shared tuple space has good enough performance to be used as a communication model for messages that are not dependent on low latency. It is theorized that the important aspects of a communication model for a semi-autonomous robot platform is not low latency, but services provided by it. Messages requiring low latency should be sent over more efficient communication links, while the communication model should help remedy the complexity introduced by working in a mobile environment.

WallMon : Interactive distributed monitoring of process-level resource usage on display and compute clusters

Tue, 01 Nov 2011 00:00:00 GMT

Nilsen, Arild
To achieve low overhead, traditional cluster monitoring systems sample data at low frequencies and with coarse granularity. However, interactive monitoring requires frequent (up to 60 Hz) sampling of fine-grained data and visualization tools that can explore and display data in near real-time. This makes traditional cluster monitoring systems unsuited for interactive monitoring of distributed cluster applications, as they fail to capture short-duration events, making understanding the performance relationship between processes on the same or different nodes difficult. To address this issue, WallMon was developed, a tool for interactive visual exploration of performance behaviors in distributed systems. For gathering of data, WallMon is centered around an abstraction of collectors and handlers; collectors gathers data of interest, such as CPU and memory usage, and forwards it to handlers in a push-based fashion, while handlers take action upon the data. WallMon captures and visualizes data for every process on every node, as well as overall node statistics. Data is visualized using a technique inspired by the concept of information flocking. WallMon's design is based on the client-server model, and it is extensible through a module system that encapsulates functionality specific to monitoring (collectors) and visualization (handlers). A set of experiments have been carried out on a cluster of 29 nodes with 180 processes per node. Performance results show 7% (of 100) CPU usage at 64 Hz sampling rate when performing process-level monitoring with WallMon. Using WallMon's interactive visualization, we have observed interesting patterns in different parallel and distributed systems, such as unexpected ratio of user- and kernel-level execution among processes in a particular distributed system.

Context-based image retrieval in Fronter learning environment

Tue, 01 Feb 2011 00:00:00 GMT

Larsen, Jelena N
The Internet has become a natural medium for finding information and resources, and has probably become the most important tool in education and e-learning as well. Many educational institutions use on-line systems for uploading, creating and publishing educational content to students and pupils. Extended use of multimedia files, video, audio and image, as a part of the content is a growing trend and there is ever more a need to search for desired multimedia content. This causing challenges to both the on-line systems and its users. To make multimedia content suited for search and retrieval it is imperative to organize and describe content well. Normally, users do not spend much of their time annotating and organizing content. Text-based search engines that are integrated into the educational on-line systems are normally not very suitable for search of multimedia content. The specific concern of this project is to investigate and suggest solutions to how image context information can be collected and then used in image annotation and retrieval within educational content. The image context in this setting is defined as the image environment in which the image is used. For example it can be a collection of images or documents, the course(s), subtopic(s) and/or assignments where images are used as illustrations. The system that is designed and implemented in this thesis will use image context to describe the images content and its semantics and use this in its image retrieval. If there are multiple versions of an image it will also be used in the description and retrieval processes. The evaluation of the system indicates that usage of the image context is very useful in describing the image content and its semantics. The system finds and retrieves more relevant images to the search than the integrated search engine in on-line educational portal. It has also good retrieval performance compared to the integrated one.

A configuration tool for process oriented UAV programming.

Fri, 25 Jun 2010 00:00:00 GMT

Pettersen, Ørjan
This thesis covers the design, implementation and evaluation of a configuration tool for process oriented Unmanned Aerial Vehicle (UAV) programming. In addition it will examine if and how a process network can be used to control sensors and communication channels on an UAV in flight. NORUT-IT is currently developing a sensor platform based on UAVs. The mission computer software they have at the moment have room for improvement when it comes down to issues regarding routing and prioritizing between available network connections. One issue that has been identified is not being able to route between multiple available networks. They have to predefine which network connection the UAV should use to connect to the ground station when it is in flight. It will use this connection the entire flight even if a faster and/or cheaper network connection is available in some areas of the mission. Together with this issue, having a platform with a number of sensors working together, will be challenging to configure and might require programming skills to some degree to set up correctly. Communicating sequential processing(CSP) have properties that can help in building concurrent, reliable and scalable programs. By using CSP and a process configuration tool, the complexity of configuring the mission computer of an UAV can be reduced. The implementation will demonstrate a tool that are believed to be intuitive and will lower the challenge of configuring a process network intended to control the sensors and communication channels on an UAV. The process network creator tool have a graphical interface and a collection of premade CSP processes. It will also have the ability to convert the graphical representation of the process network into a running CSP process.

A context-aware mobile bus application

Tue, 18 May 2010 00:00:00 GMT

Hansen, Christer Andre
Accessing route information should be easy. Today, most collective transport companies distribute timeta- bles online as electronic documents and in paper format. These solutions are outdated and cumbersome to use. However, systems have been built to make the task of finding route information easy, and to replace these formats. Most of these systems, still, have limitations. They rely on users knowing the name of the bus stops, and the destination is left out when finding information. In this thesis we present a system that is able to find travel alternatives based on two parameters, the user’s current location and the destination. Successful tests and experiments have proved that our system can be useful for people that does not know the following; the name of the bus stops, where the bus stops are located, what route to use, and where to get of the bus. We also suggest an architecture where our system is integrated as part of a personal cloud.