DESIGNING AN AUTOMATED DENSE BI-LSTM-AIDED FRAMEWORK FOR ENHANCING THE PERFORMANCE MANAGEMENT IN BUSINESS ORGANIZATION USING CROSS ATTENTION-BASED FEATURE FUSION

Read full text Summarise with VIRAT
Authors: R. Sabitha, D. Sundar
Cited by: 0
References: 14

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

The role of management is to evaluate and validate the objectives of an organization. The management’s role in state-owned business enterprises is more critical due to the influence of the existing human resource performance management system. The organization’s intelligence helps to gather important data from the large unstructured data and modifies it into useful data to improve the efficiency and productivity of the organization. In the era of the Internet, conventional performance management struggled to meet the modern development of an enterprise. Hence, organizations must continuously innovate and improve their performance management strategies. Deep learning has shown potential in enhancing business intelligence with the automated validation of large and complex data sources. Nevertheless, it has not achieved much attention as they are not efficient in decision making process within the organization. Therefore, in this article, an advanced deep learning-based network is designed for effective decision-making to enhance the growth of a business organization. Initially, the necessary data for the analysis is taken from the available resources. Subsequently, the significant features from the data are extracted using the T-distributed Stochastic Neighbor Embedding (T-SNE), Principal Component Analysis (PCA) and statistical features. The extracted features are combined using the Cross Attention-based Feature Fusion (CAFF). In the end, the resultant fused features are given to Dense Bidirectional Long Short-Term Memory (D-BiLSTM) for performing efficient decision-making. Finally, comparative analysis is conducted to validate the functionality of the model. The result demonstrates that the designed framework is more efficient in decision-making to enhance the productivity of business organizations.

Fields of Study & Subjects

AI and HR Technologies Data Mining and Machine Learning Applications Impact of AI and Big Data on Business and Society

Publication details

Journal / source
JOURNAL OF MECHANICS OF CONTINUA AND MATHEMATICAL SCIENCES
Volume
21
Issue
3
Publication date
14 March 2026
Language
EN