Multimedia Presentation Databases

Subrahmanian, V. S.; Martínez, María Vanina; Recupero, Diego Reforgiato

doi:10.1007/978-1-4899-7993-3_236-2

Cited by 2 publications

(3 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, ML training data may also include other common types such as images, audio, and videos. The challenge of data multi-modality is non-trivial, and stretches beyond simply utilizing technologies such as multimedia databases [139] and polystores.…”

Section: Data Lakes Meet Machine Learningmentioning

confidence: 99%

Data Lakes: A Survey of Functions and Systems

Hai

Koutras

Quix

et al. 2023

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

Data lakes are becoming increasingly prevalent for big data management and data analytics. In contrast to traditional 'schema-on-write' approaches such as data warehouses, data lakes are repositories storing raw data in its original formats and providing a common access interface. Despite the strong interest raised from both academia and industry, there is a large body of ambiguity regarding the definition, functions and available technologies for data lakes. A complete, coherent picture of data lake challenges and solutions is still missing. This survey reviews the development, architectures, and systems of data lakes. We provide a comprehensive overview of research questions for designing and building data lakes. We classify the existing approaches and systems based on their provided functions for data lakes, which makes this survey a useful technical reference for designing, implementing and deploying data lakes. We hope that the thorough comparison of existing solutions and the discussion of open research challenges in this survey will motivate the future development of data lake research and practice.

show abstract

Section: Data Lakes Meet Machine Learningmentioning

confidence: 99%

Data Lakes: A Survey of Functions and Systems

Hai

Koutras

Quix

et al. 2023

IEEE Trans. Knowl. Data Eng.

View full text Add to dashboard Cite

show abstract

“…To speed up the CBR retrieval process, researchers have applied indexing methods, such as X‐trees (Berchtold et al. 2001), R‐trees (Guttman 1984), LCS‐trees (Sánchez‐Ruiz and Ontanón 2014) and TV‐trees (Subrahmanian 1998), while Bach et al. (2014) implemented cluster‐based methods.…”

Section: Related Workmentioning

confidence: 99%

“…To speed up the CBR retrieval process, researchers have applied indexing methods, such as X-trees (Berchtold et al 2001), R-trees (Guttman 1984), LCS-trees (Sánchez-Ruiz and Ontan ón 2014) and TV-trees (Subrahmanian 1998), while Bach et al (2014) implemented cluster-based methods. Due to the presence of more than one million CBR cases, we use qualitative features (e.g., comorbidities) to filter out the less relevant CBR cases from further consideration; and the similarities between the target and the remaining cases are subsequently assessed.…”

Section: Case Based Reasoning Literaturementioning

confidence: 99%

Chronic Disease Progression Prediction: Leveraging Case‐Based Reasoning and Big Data Analytics

Nenova

Shang

2022

Production and Operations Management

View full text Add to dashboard Cite

Physicians caring for chronically ill individuals need to predict patients' disease progression, as accurate disease projections can facilitate better treatment decisions. The power of prediction is prevention, as it is easier to prevent than to reverse. In this research, we propose a data‐driven model for accurate and fast disease trajectory prediction, using electronic health records (EHRs) from Veterans Affairs Hospitals. EHRs contain tremendous amount of frequently updated, highly dimensional and not equally spaced data in diverse formats (e.g., numeric, textual, images, and videos). We propose an intelligent case‐based reasoning (iCBR) approach to better predict kidney disease progression, which can help prevent patients' health deterioration and prolong lives. Our iCBR contributes to the literature by enhancing the automation and personalization capabilities of the conventional case‐based reasoning (CBR). Through the iCBR, we advance the utilization of patient's laboratory data, vital sign, clinic visit, and comorbidity information. We examine (1) if the number of cases chosen for predicting the new patient's disease progression should be tailored, and (2) what the best number of prediction cases should be if customization is warranted. We link the number of cases selected for disease prediction with patient's disease characteristics. By comparing the results of the iCBR and popular machine learning and statistics models adapted to our problem, we find that the iCBR outperforms other methods. While the proposed model is applied to patients with chronic kidney disease, it can be readily applied to other chronic diseases such as diabetes, due to its similar data structure.

show abstract

Multimedia Presentation Databases

Cited by 2 publications

References 13 publications

Data Lakes: A Survey of Functions and Systems

Data Lakes: A Survey of Functions and Systems

Chronic Disease Progression Prediction: Leveraging Case‐Based Reasoning and Big Data Analytics

Contact Info

Product

Resources

About