Semantic Integration of Heterogeneous Data Sources Using Ontology-Based Domain Knowledge Modeling for Early Detection of COVID-19.

The enormous outbreak of biomedical knowledge, the aim of reducing computation and processing costs and the widespread availability of internet connection have created a profuse amount of electronic data. Such data are stored across the globe in various data sources that are semantically, structurally and syntactically different. This decentralized nature of biomedical data has made it difficult to obtain a unified view of the data. Data integration plays a crucial role in enhancing access to heterogeneous data making the retrieval easier and faster. A variety of ontology, machine learning, deep learning and fuzzy logic-based solutions are being developed for heterogeneous data integration. The proposed model concentrates on the automatic ontology-based data integration method that can be effectively deployed and used in the healthcare domain. The proposed model is divided into three phases. The first phase includes the automatic mapping of data and generation of local ontology across heterogeneous data sources, the second phase combines the local ontology models developed in the first phase to create a root global schema mapping and the third phase queries diverse databases to retrieve semantically analogous records. The model is created based on the medical records, chest X-ray details and COVID-19 symptom questionnaire data of various patients distributed across three data sources (SQL, mongodb and excel). Based on the data, the patients who have moderate/higher risk of developing serious illness from COVID-19 are retrieved.

Utility-Based Differentially Private Recommendation System.

The Recommendation system relies on feedback and personal information collected from users for effective recommendation. The success of a recommendation system is highly dependent on storing and managing sensitive customer information. Users refrain from using the application if there is a threat to user privacy. Several works that were performed to protect user privacy have paid little attention to utility. Hence, there is a need for a robust recommendation system with high accuracy and privacy. Model-based approaches are more prevalent and commonly used in recommendation. The proposed work improvises the existing private model-based collaborative filtering algorithm with high privacy and utility. We identified that data sparsity is the primary reason for most of the threats in a recommender framework through an extensive literature survey. Hence, our approach combines the l injection for imputing the missing ratings, which are deemed low, with differential privacy. We additionally introduce a random differential privacy approach to alternating least square (ALS) for improved utility. Experimental results on benchmarked datasets confirm that the performance of our private noisy Random ALS algorithm outperforms the non-noisy ALS for all datasets.

A novel approach to multiple sequence alignment using hadoop data grids.

Multiple alignment of protein sequences helps to determine evolutionary linkage and to predict molecular structures. The factors to be considered while aligning multiple sequences are speed and accuracy of alignment. Although dynamic programming algorithms produce accurate alignments, they are computation intensive. In this paper we propose a time efficient approach to sequence alignment that also produces quality alignment. The dynamic nature of the algorithm coupled with data and computational parallelism of hadoop data grids improves the accuracy and speed of sequence alignment. The principle of block splitting in hadoop coupled with its scalability facilitates alignment of very large sequences.