| 1. |
- Blanch, Krister, 1991
(författare)
-
Beyond-application datasets and automated fair benchmarking
- 2023
-
Licentiatavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Beyond-application perception datasets are generalised datasets that emphasise the fundamental components of good machine perception data. When analysing the history of perception datatsets, notable trends suggest that design of the dataset typically aligns with an application goal. Instead of focusing on a specific application, beyond-application datasets instead look at capturing high-quality, high-volume data from a highly kinematic environment, for the purpose of aiding algorithm development and testing in general. Algorithm benchmarking is a cornerstone of autonomous systems development, and allows developers to demonstrate their results in a comparative manner. However, most benchmarking systems allow developers to use their own hardware or select favourable data. There is also little focus on run time performance and consistency, with benchmarking systems instead showcasing algorithm accuracy. By combining both beyond-application dataset generation and methods for fair benchmarking, there is also the dilemma of how to provide the dataset to developers for this benchmarking, as the result of a high-volume, high-quality dataset generation is a significant increase in dataset size when compared to traditional perception datasets. This thesis presents the first results of attempting the creation of such a dataset. The dataset was built using a maritime platform, selected due to the highly dynamic environment presented on water. The design and initial testing of this platform is detailed, as well as as methods of sensor validation. Continuing, the thesis then presents a method of fair benchmarking, by utilising remote containerisation in a way that allows developers to present their software to the dataset, instead of having to first locally store a copy. To test this dataset and automatic online benchmarking, a number of reference algorithms were required for initial results. Three algorithms were built, using the data from three different sensors captured on the maritime platform. Each algorithm calculates vessel odometry, and the automatic benchmarking system was utilised to show the accuracy and run-time performance of these algorithms. It was found that the containerised approach alleviated data management concerns, prevented inflated accuracy results, and demonstrated precisely how computationally intensive each algorithm was.
|
|
| 2. |
- Homem, Irvin, 1985-
(författare)
-
Advancing Automation in Digital Forensic Investigations
- 2018
-
Doktorsavhandling (övrigt vetenskapligt/konstnärligt)abstract
- Digital Forensics is used to aid traditional preventive security mechanisms when they fail to curtail sophisticated and stealthy cybercrime events. The Digital Forensic Investigation process is largely manual in nature, or at best quasi-automated, requiring a highly skilled labour force and involving a sizeable time investment. Industry standard tools are evidence-centric, automate only a few precursory tasks (E.g. Parsing and Indexing) and have limited capabilities of integration from multiple evidence sources. Furthermore, these tools are always human-driven.These challenges are exacerbated in the increasingly computerized and highly networked environment of today. Volumes of digital evidence to be collected and analyzed have increased, and so has the diversity of digital evidence sources involved in a typical case. This further handicaps digital forensics practitioners, labs and law enforcement agencies, causing delays in investigations and legal systems due to backlogs of cases. Improved efficiency of the digital investigation process is needed, in terms of increasing the speed and reducing the human effort expended. This study aims at achieving this time and effort reduction, by advancing automation within the digital forensic investigation process.Using a Design Science research approach, artifacts are designed and developed to address these practical problems. Summarily, the requirements, and architecture of a system for automating digital investigations in highly networked environments are designed. The architecture initially focuses on automation of the identification and acquisition of digital evidence, while later versions focus on full automation and self-organization of devices for all phases of the digital investigation process. Part of the remote evidence acquisition capability of this system architecture is implemented as a proof of concept. The speed and reliability of capturing digital evidence from remote mobile devices over a client-server paradigm is evaluated. A method for the uniform representation and integration of multiple diverse evidence sources for enabling automated correlation, simple reasoning and querying is developed and tested. This method is aimed at automating the analysis phase of digital investigations. Machine Learning (ML)-based triage methods are developed and tested to evaluate the feasibility and performance of using such techniques to automate the identification of priority digital evidence fragments. Models from these ML methods are evaluated in identifying network protocols within DNS tunneled network traffic. A large dataset is also created for future research in ML-based triage for identifying suspicious processes for memory forensics.From an ex ante evaluation, the designed system architecture enables individual devices to participate in the entire digital investigation process, contributing their processing power towards alleviating the burden on the human analyst. Experiments show that remote evidence acquisition of mobile devices over networks is feasible, however a single-TCP-connection paradigm scales poorly. A proof of concept experiment demonstrates the viability of the automated integration, correlation and reasoning over multiple diverse evidence sources using semantic web technologies. Experimentation also shows that ML-based triage methods can enable prioritization of certain digital evidence sources, for acquisition or analysis, with up to 95% accuracy.The artifacts developed in this study provide concrete ways to enhance automation in the digital forensic investigation process to increase the investigation speed and reduce the amount of costly human intervention needed.
|
|
| 3. |
- Farooqui, Ashfaq, et al.
(författare)
-
On Active Learning for Supervisor Synthesis
- 2024
-
Ingår i: IEEE Transactions on Automation Science and Engineering. - : Institute of Electrical and Electronics Engineers Inc.. - 1545-5955 .- 1558-3783. ; 21, s. 78-
-
Tidskriftsartikel (refereegranskat)abstract
- Supervisory control theory provides an approach to synthesize supervisors for cyber-physical systems using a model of the uncontrolled plant and its specifications. These supervisors can help guarantee the correctness of the closed-loop controlled system. However, access to plant models is a bottleneck for many industries, as manually developing these models is an error-prone and time-consuming process. An approach to obtaining a supervisor in the absence of plant models would help industrial adoption of supervisory control techniques. This paper presents, an algorithm to learn a controllable supervisor in the absence of plant models. It does so by actively interacting with a simulation of the plant by means of queries. If the obtained supervisor is blocking, existing synthesis techniques are employed to prune the blocking supervisor and obtain the controllable and non-blocking supervisor. Additionally, this paper presents an approach to interface the with a PLC to learn supervisors in a virtual commissioning setting. This approach is demonstrated by learning a supervisor of the well-known example simulated in Xcelgo Experior and controlled using a PLC. interacts with the PLC and learns a controllable supervisor for the simulated system. Note to Practitioners—Ensuring the correctness of automated systems is crucial. Supervisory control theory proposes techniques to help build control solutions that have certain correctness guarantees. These techniques rely on a model of the system. However, such models are typically unavailable and hard to create. Active learning is a promising technique to learn models by interacting with the system to be learned. This paper aims to integrate active learning and supervisory control such that the manual step of creating models is no longer needed, thus, allowing the use of supervisory control techniques in the absence of models. The proposed approach is implemented in a tool and demonstrated using a case study.
|
|
| 4. |
- Crnkovic, Ivica, et al.
(författare)
-
Is software engineering training enough for software engineers?
- 2003
-
Ingår i: Software Engineering Education Conference, Proceedings. - 0769518699 ; , s. 140-147
-
Konferensbidrag (refereegranskat)abstract
- Most software engineering courses focus exclusively on the software development process, often referring to problems related to the complexity of software products and processes. In practice, however, many problems of a complex nature arise in which system engineering and other engineering disciplines are important in the development of systems. In such cases software engineers may have difficulty in coping with the entire problem, in the same way that engineers in other fields may have difficulty in understanding the software part. This suggests that the software engineering education of today is inadequate in certain respects. This paper presents a case study of a software engineering course and discusses the difficulty for computer science students to understand and to develop a system which also requires skills in engineering of a non-software nature.
|
|
| 5. |
- Yanggratoke, Rerngvit, 1983-, et al.
(författare)
-
Predicting real-time service-level metrics from device statistics
- 2015
-
Ingår i: Proceedings of the 2015 IFIP/IEEE International Symposium on Integrated Network Management, IM 2015. - : Institute of Electrical and Electronics Engineers Inc.. - 9783901882760 ; , s. 414-422
-
Konferensbidrag (refereegranskat)abstract
- While real-time service assurance is critical for emerging telecom cloud services, understanding and predicting performance metrics for such services is hard. In this paper, we pursue an approach based upon statistical learning whereby the behavior of the target system is learned from observations. We use methods that learn from device statistics and predict metrics for services running on these devices. Specifically, we collect statistics from a Linux kernel of a server machine and predict client-side metrics for a video-streaming service (VLC). The fact that we collect thousands of kernel variables, while omitting service instrumentation, makes our approach service-independent and unique. While our current lab configuration is simple, our results, gained through extensive experimentation, prove the feasibility of accurately predicting client-side metrics, such as video frame rates and RTP packet rates, often within 10-15% error (NMAE), also under high computational load and across traces from different scenarios.
|
|
| 6. |
|
|
| 7. |
- Lian, Mengke, et al.
(författare)
-
What Can Machine Learning Teach Us about Communications
- 2018
-
Ingår i: IEEE International Symposium on Information Theory - Proceedings. - 2157-8095. ; 15 January 2019
-
Konferensbidrag (refereegranskat)abstract
- Rapid improvements in machine learning over the past decade are beginning to have far-reaching effects. For communications, engineers with limited domain expertise can now use off-the-shelf learning packages to design high-performance systems based on simulations. Prior to the current revolution in machine learning, the majority of communication engineers were quite aware that system parameters (such as filter coefficients) could be learned using stochastic gradient descent. It was not at all clear, however, that more complicated parts of the system architecture could be learned as well. In this paper, we discuss the application of machine-learning techniques to two communications problems and focus on what can be learned from the resulting systems. We were pleasantly surprised that the observed gains in one example have a simple explanation that only became clear in hindsight. In essence, deep learning discovered a simple and effective strategy that had not been considered earlier.
|
|
| 8. |
|
|
| 9. |
- Lv, Zhihan, Dr. 1984-, et al.
(författare)
-
Editorial : 5G for Augmented Reality
- 2022
-
Ingår i: Mobile Networks and Applications. - : Springer. - 1383-469X .- 1572-8153.
-
Tidskriftsartikel (refereegranskat)
|
|
| 10. |
- Bengtsson, Lars, 1963
(författare)
-
Mikrodatorteknik
- 1995
-
Bok (övrigt vetenskapligt/konstnärligt)abstract
- Första delen behandlar Microchips "Base-line"-kretsar och andra delen behandlar "Midrange"-kretsarna. De flesta funktioner belyses med konstruktionsexempel. Exempel och övningar är mycket hårdvarunära och boken behandlar konstruktion av mikrodatorer från grunden. Boken är avsedd för kurser i mikrodatorteknik på högskolan eller annan högre teknisk utbildning, men kan även användas som självstudiematerial eftersom de flesta exempel ges med detaljerade och verifierade lösningar av såväl hård- som mjukvaran. Tidigare erfarenhet av assemblerprogrammering är inte nödvändig men grundläggande kunskaper i digitalteknik förutsätts. Boken kan med fördel också läsas av rutinerade assemblerprogrammerare som vill veta hur prestanda hos de nya RISC-baserade PIC-controllerna står sig i konkurrensen med de mer etablerade enchipscontrollerna, t ex HC11 och 8751, som bygger på traditionell CISC-arkitektur.
|
|
