ORCID Profile
0000-0002-9984-5374
Current Organisations
Aston University
,
Indian Institute of Technology Madras
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
Publisher: Cold Spring Harbor Laboratory
Date: 06-2023
DOI: 10.1101/2023.05.31.542682
Abstract: The emerging field of Genome-NLP (Natural Language Processing) aims to analyse biological sequence data using machine learning (ML), offering significant advancements in data-driven diagnostics. Three key challenges exist in Genome-NLP. First, long biomolecular sequences require “tokenisation” into smaller subunits, which is non-trivial since many biological “words” remain unknown. Second, ML methods are highly nuanced, reducing interoperability and usability. Third, comparing models and reproducing results are difficult due to the large volume and poor quality of biological data. To tackle these challenges, we developed the first automated Genome-NLP workflow that integrates feature engineering and ML techniques. The workflow is designed to be species and sequence agnostic. In this workflow: a) We introduce a new transformer-based model for genomes called genomicBERT , which empirically tokenises sequences while retaining biological context. This approach minimises manual preprocessing, reduces vocabulary sizes, and effectively handles out-of-vocabulary “words”. (b) We enable the comparison of ML model performance even in the absence of raw data. To facilitate widespread adoption and collaboration, we have made genomicBERT available as part of the publicly accessible conda package called genomeNLP . We have successfully demonstrated the application of genomeNLP on multiple case studies, showcasing its effectiveness in the field of Genome-NLP. We provide a comprehensive classification of genomic data tokenisation and representation approaches for ML applications along with their pros and cons. We infer k-mers directly from the data and handle out-of-vocabulary words. At the same time, we achieve a significantly reduced vocabulary size compared to the conventional k-mer approach reducing the computational complexity drastically. Our method is agnostic to species or biomolecule type as it is data-driven. We enable comparison of trained model performance without requiring original input data, metadata or hyperparameter settings. We present the first publicly available, high-level toolkit that infers the grammar of genomic data directly through artificial neural networks. Preprocessing, hyperparameter sweeps, cross validations, metrics and interactive visualisations are automated but can be adjusted by the user as needed.
Publisher: Emerald
Date: 04-2014
DOI: 10.1108/IJMPB-03-2013-0007
Abstract: – The purpose of the paper was to conduct an empirical investigation to explore the impact of project management maturity models (PMMMs) on improving project performance. – The investigation used a cross-case analysis involving over 90 in iduals in seven organisations. – The findings of the empirical investigation indicate that PMMMs demonstrate very high levels of variability in in idual's assessment of project management maturity. Furthermore, at higher levels of maturity, the type of performance improvement adopted following their application is related to the type of PMMM used in the assessment. The paradox of the unreliability of PMMMs and their widespread acceptance is resolved by calling upon the “wisdom of crowds” phenomenon which has implications for the use of maturity model assessments in other arena. – The investigation does have the usual issues associated with case research, but the steps that have been taken in the cross-case construction and analysis have improved the overall robustness and extendibility of the findings. – The tendency for PMMMs to shape improvements based on their own inherent structure needs further understanding. – The use of empirical methods to investigate the link between project maturity models and extant changes in project management performance is highly novel and the findings that result from this have added resonance.
Publisher: Routledge
Date: 15-11-2010
Publisher: Informa UK Limited
Date: 07-2009
Publisher: Emerald
Date: 20-04-2010
DOI: 10.1108/14637151011035606
Abstract: The purpose of this paper is to help managers to successfully plan, implement, and operate enterprise resource planning (ERP) projects using a risk management framework. This paper adopted a combined literature review and case study method. Using literature review, the paper first identified major issues of managing ERP projects and develops a risk management framework for managing those issues. The proposed risk management framework was then applied to a ERP implementation project of a UK‐based energy services group and its effectiveness for managing ERP projects implementation had been demonstrated. Additionally, the risk factors as identified from the case application are compared with the risk factors from the previous researches so as to suggest mitigating measures. All the risk factors are categorized into planning, implementation and operations phases along with project processes, organizational transformation and information technology (IT) perspectives. Project implementation phase is the most vulnerable to failure. The case study results reveal that the effect of other projects on on‐going ERP project, management of overall IT architecture and non‐availability of resources for organizational transformation are most critical from likelihood and impact perspectives. Managing risk across various phases of project and equal emphasize to effective project management, organizational transformation and IT adoption are the key to success in ERP implementation. The risk factors, which were identified using literature review and the case study, have great significance as mitigating measures of those risks may result successful implementation of ERP projects in the industry. Additionally, proposed risk management framework could be customized to implement ERP projects elsewhere. ERP projects are risky as they are capital intensive, technically complex, and call for organizational transformation. There are both success and failure stories. However, both researchers and practitioners agree, that if it can be implemented and operated successfully and benefits should be achievable. Although there are many studies on ERP implementation, little has been discussed on managing risks of ERP projects. Therefore, this paper bridges the gap.
Location: United Kingdom of Great Britain and Northern Ireland
No related grants have been discovered for Prasanta Dey.