Sort by
Assessing Information Security Governance in Public Sector Banks of India

Purpose of the study: This study aims to investigate and analyze the Information Security governance practices within banks. Design/methodology/approach: This is a Survey-based study. Employees of State Bank of India in Delhi region were the participants of the study. Findings: The findings of the study will contribute to the existing body of knowledge on information security governance in the banking sector. Research limitations: Small sample size and lack of funds for performing comprehensive quantitative study are the limitations of the study. Practical implications: Regulatory compliance, incident response, and data recovery are all a part of this process, as well as risk assessment and management, policy and procedure creation, security awareness and training, security controls and technology, and more. Public sector organizations may improve their security posture and better secure their information assets by adopting a systematic approach to information security governance. Social implications: Data protection, service protection, privacy, fighting cybercrime, public trust, and economic impact are only few of the societal effects of researching information security governance in public sector organizations. Organizations in the public sector can reduce the risk of financial and reputational damage as well as secure sensitive information by employing best practices in information security. Originality/value: The research outcomes will help identify areas of improvement, highlight effective practices, and provide recommendations for enhancing information security governance within banks. Ultimately, this study contributes to the development of robust Information Security governance frameworks that can protect sensitive data, mitigate risks, ensure regulatory compliance, and maintain the trust and confidence of customers and stakeholders in the banking industry.

Open Access
Relevant
Exploring Word Embeddings for Text Classification: A Comparative Analysis

For language tasks like text classification and sequence labeling, word embeddings are essential for providing input characteristics in deep models. There have been many word embedding techniques put out in the past ten years, which can be broadly divided into classic and context-based embeddings. In this study, two encoders—CNN and BiLSTM—are used in a downstream network architecture to analyze both forms of embeddings in the context of text classification. Four benchmarking classification datasets with single-label and multi-label tasks and a range of average sample lengths are selected in order to evaluate the effects of word embeddings on various datasets. CNN routinely beats BiLSTM, especially on datasets that don't take document context into account, according to the evaluation results with confidence intervals. CNN is therefore advised above BiLSTM for datasets involving document categorization where context is less predictive of class membership. Concatenating numerous classic embeddings or growing their size for word embeddings doesn't greatly increase performance, while there are few instances when there are marginal gains. Contrarily, context-based embeddings like ELMo and BERT are investigated, with BERT showing better overall performance, particularly for longer document datasets. On short datasets, both context-based embeddings perform better, but on longer datasets, no significant improvement is seen.In conclusion, this study emphasizes the significance of word embeddings and their impact on downstream tasks, highlighting the advantages of BERT over ELMo, especially for lengthier documents, and CNN over BiLSTM for certain scenarios involving document classification.

Open Access
Relevant
Data Mining Applications for Enhancing Healthcare Services: A Comprehensive Review

The healthcare industry is experiencing a data-driven transformation, marked by the prolific generation of electronic health records (EHRs) and patient-related data. This paper delves into the potent realm of data mining applications within the healthcare environment, illustrating its capacity to revolutionize healthcare services. The extensive review explores data preprocessing techniques essential for enhancing data quality and reliability. It explores predictive modeling techniques, such as logistic regression, decision trees, and support vector machines, which empower healthcare professionals to predict disease risks, patient readmission rates, and medication adherence with precision. Furthermore, the paper elucidates the utility of clustering and classification techniques in devising personalized treatment regimens. Association rule mining is presented as a powerful tool for revealing concealed relationships amidst healthcare data, including symptom co-occurrence, drug interactions, and disease patterns. In practice, data mining serves as the bedrock for Clinical Decision Support Systems (CDSS), driving evidence-based healthcare decisions and recommendations. The applications extend to disease surveillance and outbreak detection, offering early warning systems that can trigger timely public health interventions. Data mining's capacity to unravel medication adherence challenges is showcased, thereby optimizing patient compliance. Additionally, healthcare fraud detection benefits from data mining's ability to uncover anomalous billing patterns. The paper concludes by addressing challenges like data privacy, source integration, and ethical considerations, while also highlighting the promising future of data mining in the realm of personalized medicine. As healthcare continues to digitize and data sources proliferate, harnessing data mining's capabilities is pivotal in advancing healthcare services, improving patient outcomes, and managing costs effectively.

Open Access
Relevant
Factors influencing Cryptocurrencies investment intention: A study on the customer perception in Sultanate of Oman

E-governance which is a recent technology plays in a significant role around the world which includes blockchain approach. The topic of cryptocurrency is discussed by numerous research scholars and analysed accordingly to identify the profitable cryptos as it comprises of lots of risk factors. Implementation of block chain in a country governs rules and administration in bureaucratic country. This study would help to understand e-governance and related literature to explore the probable value, risks components and its own restrictions in Sultanate of Oman. Early years in the country regarding the blockchain technology bear cost elements, accuracy matters and reliability aspects, transparent issues and accountable services. Centralization of delegated authority is obligatory to set new guidelines in the Sultanate to resolve the issues relating to block chain methodologies using manpower who are dynamic to frame tax laws. The objective of this article is to understand the concept of cryptocurrency around the world in general and in particular in Sultanate of Oman. The study also would analyze the regulation of cryptocurrencies in Oman and also to comprehend the perception of the general public and investors around the Muscat City. Cryptocurrencies have not been explored much in gulf region and this study would also help us to discover more of cryptocurrencies through a questionnaire which has been collected from investors and general public. The findings of the study have been interpreted with the help latest research statistics.

Open Access
Relevant