/pdf/a-break-in-the-clouds-towards-a-cloud-definition-svovsw1r5a.pdf

A Break in the Clouds: Towards a Cloud Definition

http://homepage.cs.latrobe.edu.au/sloke/papers/1-s2.0-S0167739X12001318-main.pdf

Mobile cloud computing

Normal accidents. Living with high-risk technologies

A systematic literature review of blockchain-based applications: Current status, classification and open issues

On blockchain and its integration with IoT. Challenges and opportunities

Breast cancer is one of the most common causes of cancer-related death in women worldwide. Early and accurate diagnosis of breast cancer may significantly increase the survival rate of patients. In this study, we aim to develop a fully automatic, deep learning-based, method using descriptor features extracted by Deep Convolutional Neural Network (DCNN) models and pooling operation for the classification of hematoxylin and eosin stain (H#E) histological breast cancer images provided as a part of the International Conference on Image Analysis and Recognition (ICIAR) 2018 Grand Challenge on BreAst Cancer Histology (BACH) Images. Different data augmentation methods are applied to optimize the DCNN performance. We also investigated the efficacy of different stain normalization methods as a pre-processing step. The proposed network architecture using a pre-trained Xception model yields 92.50% average classification accuracy.

Breast Cancer Diagnosis with Transfer Learning and Global Pooling

The use of mobile devices such as smartphones and tablets, and other ICT tools to facilitate healthcare delivery in the medical landscape, known as mHealth, has witnessed a phenomenal rise recently. In most mHealth systems, mobile devices are employed as services and health information client consumers. Thus, healthcare professionals use these devices to consume services which are running on back-end platforms. However, in a research collaboration with the Geriatrics Ward of the City Hospital in Saskatoon, Canada, we have identified a huge potential in facilitating the mobile device as a service hosting node. Hence, we developed a physically distributed information infrastructure, called SOPHRA, which aids the healthcare professionals to securely access and share patients' medical information which are hosted on their mobile devices. Since mobile devices establish communication over wireless channels which can sometimes be unavailable, the proposed mobile hosting framework faces the challenge of reliable and real-time message propagation to the mobile participants. This paper presents the adopted methodologies employed in implementing SOPHRA to address the aforementioned challenges. A cloud-oriented middleware is implemented which enables the mobile participants to reliably communicate in soft real-time. Furthermore, the records of the patients are modeled as Web Services (WS) which aids medical information to be passed across the system components; and these WS are independently replicated on the middleware to ensure high information availability. Currently, SOPHRA supports both SOAP and RESTful Web Services protocols and facilitates information exchanges over Wi-Fi.

SOPHRA: A Mobile Web Services Hosting Infrastructure in mHealth

We propose a new platform for user modelling with blockchains that allows users to share data without losing control and ownership of it and applied it to the domain of travel booking. Our platform provides solution to three important problems: ensuring privacy and user control, and incentives for sharing. It tracks who shared what, with whom, when, by what means and for what purposes in a verifiable fashion. The paper presents a case study of applying the framework for a hotel reservation system as one of the enterprise nodes of Multichain which collects users’ profile data and allows users to receive rewards while sharing their data with other travel service providers according to their privacy preferences expressed in smart contracts. The user data from the repository is converted into an open data format and shared via stream in the blockchain so that other nodes can efficiently process and use the data. The smart contract verifies and executes the agreed terms of use of the data and transfers digital tokens as a reward to the user. The smart contract imposes double deposit collateral to ensure that all participants act honestly. The paper also presents a performance evaluation of the platform by analyzing latency and memory consumption with selected three test-scenarios and measuring the transaction cost for smart contracts deployment. The results show that the node responded quickly in all our cases with a befitting transaction cost.

/pdf/a-blockchain-platform-for-user-data-sharing-ensuring-user-44x27hlnfa.pdf

A Blockchain Platform for User Data Sharing Ensuring User Control and Incentives

Breast cancer is one of the leading causes of death across the world in women. Early diagnosis of this type of cancer is critical for treatment and patient care. Computer-aided detection (CAD) systems using convolutional neural networks (CNN) could assist in the classification of abnormalities. In this study, we proposed an ensemble deep learning-based approach for automatic binary classification of breast histology images. The proposed ensemble model adapts three pre-trained CNNs, namely VGG19, MobileNet, and DenseNet. The ensemble model is used for the feature representation and extraction steps. The extracted features are then fed into a multi-layer perceptron classifier to carry out the classification task. Various pre-processing and CNN tuning techniques such as stain-normalization, data augmentation, hyperparameter tuning, and fine-tuning are used to train the model. The proposed method is validated on four publicly available benchmark datasets, i.e., ICIAR, BreakHis, PatchCamelyon, and Bioimaging. The proposed multi-model ensemble method obtains better predictions than single classifiers and machine learning algorithms with accuracies of 98.13%, 95.00%, 94.64% and 83.10% for BreakHis, ICIAR, PatchCamelyon and Bioimaging datasets, respectively.

Ralph Deters

Papers

Breast Cancer Diagnosis with Transfer Learning and Global Pooling

SOPHRA: A Mobile Web Services Hosting Infrastructure in mHealth

A Blockchain Platform for User Data Sharing Ensuring User Control and Incentives

Classification of Histopathological Biopsy Images Using Ensemble of Deep Learning Networks

Classification of histopathological biopsy images using ensemble of deep learning networks.