Computing and Information Systems - Theses

Permanent URI for this collection

Search Results

Now showing 1 - 3 of 3
  • Item
    Thumbnail Image
    Machine Learning-based Energy and Thermal Efficient Resource Management Algorithms for Cloud Data Centres
    Ilager, Shashikant Shankar ( 2021)
    Cloud data centres are the backbone infrastructures of modern digital society and the economy. Data centres have witnessed tremendous growth, consuming enormous energy to power IT equipment and cooling system. It is estimated that the data centres consume 2% of global electricity generated, and the cooling system alone consumes up to 50% of it. Therefore, to save significant energy and provide reliable services, workloads should be managed in both an energy and thermal efficient manner. However, existing heuristics or static rule-based resource management policies often fail to find an optimal solution due to the massive complexity and non-linear characteristics of the data centre and its workloads. In this thesis, we focus on machine learning-based resource management algorithms for energy and thermal efficiency in Cloud data centres which are proven to be efficient in capturing non-linearity between interdependent parameters. We explore how these techniques can be adapted to resource management problems to increase the energy and thermal efficiency of Cloud data centres while simultaneously satisfying application QoS requirements. In particular, we propose algorithms for workload placement, consolidation, application scheduling, and configuring efficient frequencies of resources in Cloud data centres. The proposed solutions are evaluated using various simulation toolkits and prototype systems implemented on real testbeds.
  • Item
    Thumbnail Image
    A Robust and Reliable Tele-medical data Security and Authentication System using Spread Spectrum Steganography
    Eze, Peter Uchenna ( 2020)
    An emerging area with unique security challenges is the area of automated diagnosis (autodiagnosis) in teleradiology. In teleradiology, patients’ scans and associated electronic medical records(EMR) are transmitted to a remote location (rural-urban or urban-urban) for image analysis, classification, and diagnosis. The major challenge with this approach is that these scans and EMR are often fragmented and sent out to different users, such as requesting hospitals, independent specialists, patients, external artificial intelligence(AI) systems, and image archives. This occurrence makes it difficult to control the security and privacy of these health information. Therefore, new methods for tamper detection on the image and secrecy preservation of patient’s health records are now necessary in this new setting. Steganography and digital watermarking, collectively known as information hiding (IH) techniques, are among the methods of providing robust security for multimedia (image, video, audio, and text) data. In particular, Spread Spectrum(SS) Steganography and watermarking are hiding techniques that provide secret and robust information hiding, respectively, by using secret keys that are known only to the authorized parties. However, due to the non-standardisation of IH techniques, coupled with the issues of diagnostic quality after data hiding in medical images, the adoption of IH methods in medical practice is currently low. Hence, we are also faced with the challenges of validation and adoption of IH-based algorithms for practical use. Therefore, we are faced with two major challenges in this thesis: (i)how to improve tamper detection and data hiding capacity of spread spectrum steganography while retaining its robustness and secrecy and(ii)how to increase the adoption of data hiding security techniques in teleradiology for autodiagnosis. The goal of solving these challenges is to improve global healthcare with maximum security but at a low cost. The quest to achieve this objective led to the following contributions in this thesis: 1. Firstly, we design a new algorithm known as the Spread Spectrum-based Constant Correlation Compression Coding Scheme (C4S) for cover data Integrity and zero Bit Error Rate (BER) covert message detection. The goal is to allow both accurate and robust detection of secret message in the form of EMR, and content integrity verification by a third-party remote application. 2. Secondly, by leveraging the method developed above and the amplitude modulation techniques, we improved SS Steganographic data hiding capacity. We increased the number of bits that can be embedded in each 8x8 image sub-block from the classical 1 bit to 12 bits for 16-bit DICOM and 9 bits for 8-bit natural images. This steganographic capacity was achieved by both increasing the number of unique sequences and the number of frequency channels used for transmission. 3. The predictors and features (known as image biomarkers in medicine) used for remote autodiagnosis, are not usually considered while evaluating medical image IH algorithms. Thus, in this contribution, the effect of IH in computer-aided diagnosis is evaluated based on statistical significance testing of the feature changes, and Machine Learning classification (Support Vector Machine) of Chest X-ray scans of Normal and Pneumonia patients. The results imply that attention should be paid to the specific biomarkers that are sensitive to embedded information but are also relevant in autodiagnosis. 4. Finally, to bring together several algorithms, evaluation mechanisms, and medical image watermarking into practical use, a unified software framework was designed. This unified framework intends to standardise the validation and adoption all IH algorithms for medical image security applications. In conclusion, this thesis has developed and evaluated new spread spectrum steganography security algorithms for both EMR extraction in the face of attacks and semi-fragile medical image tamper detection, thereby achieving both accuracy and integrity checks, unlike in the basic SS steganography. It also allows higher capacity, especially in the region of non-interest (RONI) of medical images. To enable the adoption of medical image IH techniques in autodiagnosis, a new software framework for unifying algorithms' testing and validation is designed. These contributions are believed to have advanced knowledge in the area of IH and informed practice in the area of medical data security.
  • Item
    Thumbnail Image
    Mapping the structural connectome and predicting functional connectivity with deep learning methods
    Sarwar, Tabinda ( 2020)
    Mapping the human connectome is a major goal in neuroscience, where connectome refers to a comprehensive network description of the brain. This network is often represented as a graph, where nodes denote brain regions and edges represent white matter pathways. Tractography is a computational reconstruction method based on diffusion-weighted magnetic resonance imaging (dMRI) that estimates millions of streamlines that trace out the trajectories of white matter fiber bundles. The number of streamlines interconnecting each pair of regions comprising a predefined cortical parcellation is computed to yield a structural connectivity matrix. Network analyses of these connectivity matrices have yielded new insights into brain disorders (such as Schizophrenia, Alzheimer’s disease), cognition and neurodevelopmental processes. Moreover, the temporal dependence of neuronal activity patterns of different brain regions (functional connectivity) is also associated with underlying neuronal pathways (structural connectivity). In this thesis, we analyse the capabilities of state-of-the-art tractography algorithms (deterministic and probabilistic) for mapping connectomes and develop algorithms that overcome the limitations of conventional tractography algorithms for connectome mapping. Also, we utilize the structure-functional coupling for training Deep Neural Nets to predict the functional connectivity from structural connectivity. In the first part of the thesis, we develop numerical connectome phantoms that feature realistic network topologies and match to the fiber complexity of in vivo dMRI. The connectivity between pairs of regions was predefined for these phantoms. The phantoms are utilized to evaluate the performance of tensor-based and multi-fiber implementations of deterministic and probabilistic tractography. We found that multi-fiber deterministic tractography yields the most accurate connectome reconstructions, whereas probabilistic algorithms are hampered by an abundance of spurious connections. It is essential to omit connections with the fewest number of streamlines (thresholding) when using probabilistic algorithms for mapping connectomes. The study suggests that multi-fiber deterministic tractography is well suited for connectome mapping, regardless of the streamline threshold. In the second part, we propose a novel framework to map structural connectomes using deep learning. This framework not only enables connectome mapping with a convolutional neural network (CNN) but can also be straightforwardly incorporated into conventional connectome mapping pipelines (using tractography) to enhance accuracy. This framework involves decomposing the entire brain volume into overlapping blocks. Blocks are sufficiently small to ensure that a CNN can be efficiently trained to predict each block’s internal connectivity architecture. Later, a block stitching algorithm is proposed to rebuild the full brain volume from these blocks and thereby map end-to-end connectivity matrices. Performance is evaluated using simulated dMRI data generated from numerical connectome phantoms with known ground truth connectivity. Due to the redundancy achieved by allowing blocks to overlap, block decomposition and stitching steps can enhance the accuracy of probabilistic and deterministic tractography algorithms by up to 20-30%. Various studies have reported that functional brain connectivity is associated with underlying structural characteristics. In the third part of the thesis, we utilize this structure-functional coupling to develop a novel framework using deep learning that predicts functional connectivity from structural connectivity. The framework predicts functional connectivity without explicitly modelling the biophysical characteristics of the brain. We have demonstrated that a neural network can predict functional connectivity with high accuracy while preserving the inter-subject functional differences. Furthermore, we also demonstrated that functional connectivity could be used to predict human behavior, namely cognition. Altogether, the analyses and frameworks presented in this thesis aid in extracting structural connectivity and understanding the complex relationships between functional and structural connectivity in the human brain.