864 research outputs found
Deep learning in gene expression modeling
No full textDeveloping computational intelligence algorithms for learning insights from data has been a growing intellectual challenge. Much advances have already been made through data mining but there is an increasing research focus on deep learning to exploit the massive improvement in computational power. This chapter presents recent advancements in deep learning research and identifies some remaining challenges as drawn from using deep learning in the application area of gene expression modelling. It highlights deep learning (DL) as a branch of Machine Learning (ML), the various models and theoretical foundations, its motivations as to why we need deep learning in the context of evolving Big Data, particularly in the area of gene expression level classification. We present a review, and strengths and weaknesses of various DL models and their computational power to specific to gene expression modeling. Deep learning models are efficient feature selectors and therefore work best in high dimension datasets. We present major research challenges in feature extraction and selection using different deep models. Our case studies are drawn from gene expression datasets. Hence we report some of the key formats of gene expression datasets used for deep learning. As ongoing research we will discuss the future prospects of deep learning for gene expression modelling.</p
Data Extraction for Improved Prediction Outcomes in Organ Transplantation - A Hybrid Approach
No full text
Constraint-directed search in knowledge-based planning environments / Dharmendra Prakash Sharma
Full text linkUse of Artificial Neural Networks in the Prediction of Kidney Transplant Outcomes
No full textTraditionally researchers have used statistical methods to predict medical outcomes. However, statistical techniques do not provide sufficient in-formation for solving problems of high complexity. Recently more attention has turned to a variety of artificial intelligence modeling techniques such as Artificial Neural Networks (ANNs), Case Based Reasoning (CBR) and Rule Induction (RI). In this study we sought to use ANN to predict renal transplantation outcomes. Our results showed that although this was possible, the positive predictive power of the trained ANN was low, indicating a need for improvement if this approach is to be useful clinically. We also highlight potential problems that may arise when using incomplete clinical datasets for ANN train-ing including the danger of pre-processing data in such a way that misleading high predictive value is obtaine
Multimodal Fuzzy Fusion for Biometric Identity Management
No full textBiometric identity management based only on the single biometric modality is not accurate or robust enough to be used in uncontrolled environments. This paper describes a fusion of face and voice biometric traits, based on fuzzy logic approach for speaker identity verification. In this approach, a scheme based on membership function and fuzzy integral is proposed to fuse information from the two modalities. Equal Error rate is used to evaluate the fusion scheme. Experimental results show the fusion scheme improves identity verification performance substantially and makes the system robust to environmental degradations such as acoustic noise and visual compression artefact
Advances in smart, multimedia and computer gaming technologies
No full textThe chapter summarizes the contents of this book highlighting recent advances in smart systems, multimedia, and serious gaming technologies through a fusion of these approaches. Such fusion is a nascent area that potentially can hybridize the features and advantages of the relevant areas, and, as a result, provide users with advanced and enhanced functionality and features, which currently does not exist.</p
Recommended from our members
Leveraging Mobile Value Added Services (MVAS) for the Growth of Women Micro-Entrepreneurs (WMEs) in Fiji (IMTFI Blog)
Full text linkThe ever-increasing penetration of mobile phones presents enormous opportunities for women micro-entrepreneurs (WMEs) in developing countries, including Pacific island countries such as Fiji, to grow their businesses. Existing research by organizations such as the GSMA suggests that mobile services are being utilized by women to empower their lives.A team consisting of Prof. Milind Sathye, Prof. Biman Prasad, Prof. Dharmendra Sharma, Dr. Parmendra Sharma, and Dr. Suneeta Sathye proposed to study the unexplored situation in Fiji and identify the challenges faced by WMEs in the use of MVAS so that suitable policy initiatives could be taken by the Fijian government for faster growth of this sector. 
- …
