There are two main goals of this work:
Goal I) Big data in healthcare include Internet of thing (IoT) or Wearable Body Sensor (WBS) data streams from senior livings/ hospital, with structured data from EMR, unstructured clinical notes and video data of surgeries. To increase the value of data and research, the two important aspects of Big Data: Veracity and Variety of data will play crucial role in futuristic observational studies of healthcare. To ensure veracity, we use semantic enabled mining of data and various other machine learning methods. Our framework will ensure built-in privacy preserved, veracity and semantic enabled querying mechanisms from variety of Big data to extract required data for clinical studies. We are using UMLS and Bio-portal ontologies (e.g SNOMED CT), various video and speech processing techniques, data anonymization techniques, and semantic enrichment techniques to achieve this goal.
Goal II) Prediction of aneurysm rupture Neurosurgeons are in dire need to have decision support system to infer whether aneurysm be operated immediately or not. Our work aims to save lives from sudden death by predicting the rupture of aneurysm using extracting and integrating data features from structured and unstructured EMRs, WBS, MRI, CT Scan and MRA
The use of digital multimedia (audio, video, and images) as evidence in every sector of litigation and criminal justice proceedings is becoming the norm. For digital media to be admitted as evidence into a court of law, its authenticity and integrity must be verified. In this context, our digital audio forensics framework aims to determine the underlying facts about an evidentiary recording and to provide authoritative answers to following questions: I)Does evidentiary recording subject to anti-forensic attack? II)What is the performance of a given audio forensic method in the present of anti-forensic attack?
The automation of traceability links or traceability matrices is important to many software development paradigms. In turn, the efficiency and effectiveness of the recovery of traceability links in distributed software development is becoming increasingly vital due to the complexity of project developments, such as continuous change in requirements, geo- graphically dispersed project teams, and the complexity of managing the elements of a project - time, money, scope, and people. Therefore, the trace- ability links among the requirements artifacts, which fulfill business objectives, is so critical to reduce the risk and ensuring the success of projects. To that end, we proposed Autonomous Decentralized Semantic based Traceability Link Recovery (AD-STLR) architecture that uses autonomous decentralized concept, DBpedia knowledge-base, Bablenet 2.5 multilingual dictionary and semantic network, our domain specific ontology for aerospace for finding similarity among different project artifacts and the automation of the traceability links recovery.
The growing trends in Internet usage for data and knowledge sharing calls for dynamic classification of web contents, particularly at the edges of the Internet. One of the main purpose of this URL classification is to perform web filtering. Rather than considering Linked Data as an integral part of Big Data, we propose Autonomous Decentralized Semantic- based Content Classifier for dynamic classification of unstructured web contents, using Linked Data and web metadata in Content Delivery Network (CDN). The proposed framework ensures efficient categorization of URLs (even overlapping categories) by dynamically mapping the changing user-defined categories to ontologies category/classes.
As per CDC, Autism is the fastest-growing developmental disability in US Children with an increased ratio of approx. 120 percent over the last decade. Early detection and Diagnosis of this condition has been challenging, due to the fact that behavioral symptoms are highly unpredictable which may progress towards autism or regress. We use various semantic web tools and technologies , speech APIs and predictive analytics on samples of speech and clinical data to predict the condition.