Matching Items (3)
158273-Thumbnail Image.png
Description
Traumatic injuries are the leading cause of death in children under 18, with head trauma being the leading cause of death in children below 5. A large but unknown number of traumatic injuries are non-accidental, i.e. inflicted. The lack of sensitivity and specificity required to diagnose Abusive Head Trauma (AHT)

Traumatic injuries are the leading cause of death in children under 18, with head trauma being the leading cause of death in children below 5. A large but unknown number of traumatic injuries are non-accidental, i.e. inflicted. The lack of sensitivity and specificity required to diagnose Abusive Head Trauma (AHT) from radiological studies results in putting the children at risk of re-injury and death. Modern Deep Learning techniques can be utilized to detect Abusive Head Trauma using Computer Tomography (CT) scans. Training models using these techniques are only a part of building AI-driven Computer-Aided Diagnostic systems. There are challenges in deploying the models to make them highly available and scalable.

The thesis models the domain of Abusive Head Trauma using Deep Learning techniques and builds an AI-driven System at scale using best Software Engineering Practices. It has been done in collaboration with Phoenix Children Hospital (PCH). The thesis breaks down AHT into sub-domains of Medical Knowledge, Data Collection, Data Pre-processing, Image Generation, Image Classification, Building APIs, Containers and Kubernetes. Data Collection and Pre-processing were done at PCH with the help of trauma researchers and radiologists. Experiments are run using Deep Learning models such as DCGAN (for Image Generation), Pretrained 2D and custom 3D CNN classifiers for the classification tasks. The trained models are exposed as APIs using the Flask web framework, contained using Docker and deployed on a Kubernetes cluster.



The results are analyzed based on the accuracy of the models, the feasibility of their implementation as APIs and load testing the Kubernetes cluster. They suggest the need for Data Annotation at the Slice level for CT scans and an increase in the Data Collection process. Load Testing reveals the auto-scalability feature of the cluster to serve a high number of requests.
ContributorsVikram, Aditya (Author) / Sanchez, Javier Gonzalez (Thesis advisor) / Gaffar, Ashraf (Thesis advisor) / Findler, Michael (Committee member) / Arizona State University (Publisher)
Created2020
161388-Thumbnail Image.png
Description
Blockchain technology is defined as a decentralized, distributed ledger recording the origin of a digital asset and all of its updates without the need of any governing authority. In Supply-Chain Management, Blockchain can be used very effectively, leading to a more open and reliable supply chain. In recent years, different

Blockchain technology is defined as a decentralized, distributed ledger recording the origin of a digital asset and all of its updates without the need of any governing authority. In Supply-Chain Management, Blockchain can be used very effectively, leading to a more open and reliable supply chain. In recent years, different companies have begun to use blockchain to build blockchain-based supply chain solutions. Blockchain has been shown to help provide improved transparency across the supply chain. This research focuses on the supply chain management of medical devices and supplies using blockchain technology. These devices are manufactured by the authorized device manufacturers and are supplied to the different healthcare institutions on their demand. This entire process becomes vulnerable as there is no track of individual product once it gets shipped till it gets used. Traceability of medical devices in this scenario is hardly efficient and not trustworthy. To address this issue, the paper presents a blockchain-based solution to maintain the supply chain of medical devices. The solution provides a distributed environment that can track various medical treatments from production to use. The finished product is stored in the blockchain through its digital thread. Required details are added from time to time which records the entire virtual life-cycle of the medical device forming the digital thread. This digital thread adds traceability to the existing supply chain. Keeping track of devices also helps in returning the expired devices to the manufacturer for its recycling. This blockchain-based solution is mainly composed of two phases. Blockchain-based solution design, this involves the design of the blockchain network architecture, which constitutes the required smart contract. This phase is implemented using the secure network of Hyperledger Fabric (HLF). The next phase includes the deployment of the generated network over the Kubernetes to make the system scalable and more available. To demonstrate and evaluate the performance matrix, a prototype solution of the designed platform is implemented and deployed on the Kubernetes. Finally, this research concludes with the benefits and shortcomings of the solution with future scope to make this platform perform better in all aspects.
ContributorsMhalgi, Kaushal Sanjay (Author) / Boscovic, Dragan (Thesis advisor) / Candan, Kasim Selcuk (Thesis advisor) / Grando, Adela (Committee member) / Arizona State University (Publisher)
Created2021
161996-Thumbnail Image.png
Description
Demand for processing machine learning workloads has grown incredibly over the past few years. Kubernetes, an open-source container orchestrator, has been widely used by public and private cloud providers for building scalable systems for meeting this demand. The data used to train machine learning workloads can be sensitive in nature,

Demand for processing machine learning workloads has grown incredibly over the past few years. Kubernetes, an open-source container orchestrator, has been widely used by public and private cloud providers for building scalable systems for meeting this demand. The data used to train machine learning workloads can be sensitive in nature, and organizations may prefer to be responsible for their data security and governance by housing it on on-premises systems. Hybrid cloud gives organizations the flexibility to use both on-premises and cloud infrastructure together, leveraging the advantages of both. While there is a long list of benefits, Kubernetes has limitations by design that limit a user’s abilities in a hybrid cloud environment. The Kubernetes control plane does not allow for the management of worker nodes across cloud providers. This boundary puts new responsibilities on the end-user when deploying a hybrid cloud workload. The end-user must create their clusters and specify which cluster the workload will be scheduled to ahead of time. The Kubernetes scheduler will not take the capacity of another cluster into account. To address these limitations, this thesis presents a new hybrid cloud Kubernetes scheduler that can create new clusters on-demand and burst machine learning workloads to a public cloud when on-premises resources are insufficient. Workloads begin scheduling on an on-premises Kubernetes cluster. When the on-premises cluster’s capacity is exhausted, a new Kubernetes cluster is created on-demand in a public cloud provider, and machine learning tasks waiting in the Kubernetes scheduling queue are dynamically migrated to the public cloud provider’s Kubernetes cluster. The public Kubernetes cluster is dynamically sized and auto scaled based on the pending tasks’ demand. When migrating tasks, the data dependencies among tasks are considered, and a region is dynamically chosen to reduce migration time and cost. The scheduler is experimentally evaluated with real-world machine learning workloads, including predicting if a subscriber will stay with a subscription service, predicting the discount needed to retain a subscription customer, predicting if a credit card transaction is fraudulent, and simulated real-world job arrival behavior in a real hybrid cloud environment. Results show that the scheduler can substantially reduce the workload execution time by dynamically migrating tasks from on-premises to public cloud and minimizing the cost by dynamically sizing and scaling the public cluster.
ContributorsKieley, James (Author) / Zhao, Ming (Thesis advisor) / Huang, Dijiang (Committee member) / Zou, Jia (Committee member) / Arizona State University (Publisher)
Created2021