Asad Ali

Asad Ali, Samin Rahman Khan, Sadman Sakib et al.

Multi-Access or Mobile Edge Computing (MEC) is being deployed by 4G/5G operators to provide computational services at lower latencies. Federating MECs across operators expands capability, capacity, and coverage but gives rise to two issues - third-party authentication and application mobility - for continuous service during roaming without re-authentication. In this work, we propose a Federated State transfer and 3rd-party Authentication (FS3A) mechanism that uses a transparent proxy to transfer the information of both authentication and application state across operators to resolve these issues. The FS3A proxy is kept transparent, with virtual counterparts, to avoid any changes to the existing MEC and cellular architectures. FS3A provides users with a token, when authenticated by an MEC, which can be reused across operators for faster authentication. Prefetching of subscription and state is also proposed to further reduce the authentication and application mobility latencies. We evaluated FS3A on an OpenAirInterface (OAI)-based testbed and the results show that token reuse and subscription prefetching reduce the authentication latency by 53-65%, compared to complete re-authentication, while state prefetching reduces application mobility latency by 51-91%, compared to no prefetching. Overall, FS3A reduces the service interruption time by 33%, compared to no token reuse and prefetching.

Asad Ali, Tushin Mallick, Sadman Sakib et al.

Multi-Access Edge computing (MEC) and Fog computing provide services to subscribers at low latency. There is a need to form a federation among 3GPP MEC and fog to provide better coverage to 3GPP subscribers. This federation gives rise to two issues - third-party authentication and application mobility - for continuous service during handover from 3GPP MEC to fog without re-authentication. In this paper, we propose: 1) a proxy-based state transfer and third-party authentication (PS3A) that uses a transparent proxy to transfer the authentication and application state information, and 2) a token-based state transfer and proxy-based third-party authentication (TSP3A) that uses the proxy to transfer the authentication information and tokens to transfer the application state from 3GPP MEC to the fog. The proxy is kept transparent with virtual counterparts, to avoid any changes to the existing 3GPP MEC and fog architectures. We implemented these solutions on a testbed and results show that PS3A and TSP3A provide authentication within 0.345-2.858s for a 0-100 Mbps proxy load. The results further show that TSP3A provides application mobility while taking 40-52% less time than PS3A using state tokens. TSP3A and PS3A also reduce the service interruption latency by 82.4% and 84.6%, compared to the cloud-based service via tokens and prefetching.

Marcus Venzke, Daniel Klisch, Philipp Kubik et al.

In this paper we investigate the usage of machine learning for interpreting measured sensor values in sensor modules. In particular we analyze the potential of artificial neural networks (ANNs) on low-cost micro-controllers with a few kilobytes of memory to semantically enrich data captured by sensors. The focus is on classifying temporal data series with a high level of reliability. Design and implementation of ANNs are analyzed considering Feed Forward Neural Networks (FFNNs) and Recurrent Neural Networks (RNNs). We validate the developed ANNs in a case study of optical hand gesture recognition on an 8-bit micro-controller. The best reliability was found for an FFNN with two layers and 1493 parameters requiring an execution time of 36 ms. We propose a workflow to develop ANNs for embedded devices.

Kamran Kowsari, Rasoul Sali, Lubaina Ehsan et al.

Image classification is central to the big data revolution in medicine. Improved information processing methods for diagnosis and classification of digital medical images have shown to be successful via deep learning approaches. As this field is explored, there are limitations to the performance of traditional supervised classifiers. This paper outlines an approach that is different from the current medical image classification tasks that view the issue as multi-class classification. We performed a hierarchical classification using our Hierarchical Medical Image classification (HMIC) approach. HMIC uses stacks of deep learning models to give particular comprehension at each level of the clinical picture hierarchy. For testing our performance, we use biopsy of the small bowel images that contain three categories in the parent level (Celiac Disease, Environmental Enteropathy, and histologically normal controls). For the child level, Celiac Disease Severity is classified into 4 classes (I, IIIa, IIIb, and IIIC).

Aman Shrivastava, Karan Kant, Saurav Sengupta et al.

Physicians use biopsies to distinguish between different but histologically similar enteropathies. The range of syndromes and pathologies that could cause different gastrointestinal conditions makes this a difficult problem. Recently, deep learning has been used successfully in helping diagnose cancerous tissues in histopathological images. These successes motivated the research presented in this paper, which describes a deep learning approach that distinguishes between Celiac Disease (CD) and Environmental Enteropathy (EE) and normal tissue from digitized duodenal biopsies. Experimental results show accuracies of over 90% for this approach. We also look into interpreting the neural network model using Gradient-weighted Class Activation Mappings and filter activations on input images to understand the visual explanations for the decisions made by the model.

Asad Ali, Maribel Fernández

We propose a new static approach to Role-Based Access Control (RBAC) policy enforcement. The static approach we advocate includes a new design methodology, for applications involving RBAC, which integrates the security requirements into the system's architecture. We apply this new approach to policies restricting calls to methods in Java applications. We present a language to express RBAC policies on calls to methods in Java, a set of design patterns which Java programs must adhere to for the policy to be enforced statically, and a description of the checks made by our static verifier for static enforcement.