Sep 2026· HighTech and Innovation Journal· Vol 7, pp. 1201-1216· 0 citations
TL;DR
Results indicate that LSTM-GRU consistently delivers stable performance across datasets, while LSTM-Transformer achieves superior accuracy on complex datasets due to its self-attention mechanism.
Abstract
Software development effort estimation is a critical aspect of effective project planning, as inaccurate predictions can lead to cost overruns, schedule delays, and incomplete system implementation. This study evaluates five LSTM-based deep learning architectures—Standard LSTM, CNN-BiLSTM, Residual LSTM, LSTM-GRU, and LSTM-Transformer—to determine the most robust model across diverse project conditions. The architectures (Standard LSTM, CNN-BiLSTM, Residual LSTM, LSTM-GRU, and LSTM-Transformer) are tested on three public datasets (NASA, UCP, and NASA93). Performance is measured using Mean Absolute Error (MAE), Mean Squared Error (MSE), and Root Mean Squared Error (RMSE), while the Wilcoxon Signed-Rank Test assesses statistical significance. Results indicate that LSTM-GRU consistently delivers stable performance across datasets, while LSTM-Transformer achieves superior accuracy on complex datasets due to its self-attention mechanism. This work offers a comprehensive, statistically rigorous comparison of five LSTM-based hybrid architectures, highlighting their relative strengths and weaknesses, and provides practical guidance for selecting deep learning models for reliable, data-driven software effort estimation.
A stacked deep learning framework combining Bidirectional Long Short-Term Memory units with Gated Recurrent Units with Gated Recurrent Units is proposed to strengthen the modelling of temporal dependencies within software metrics.
The increasing complexity of Synchronous Digital Hierarchy (SDH) networks necessitates reliable forecasting of network performance indicators to support proactive performance monitoring. This study evaluates deep learning approaches for forecasting key performance indicators (KPIs) in SDH networks using real-world Netw...
F. U. Didigwu· International journal of res...· 0 citations
Software defect prediction (SDP) is a critical endeavor for enshancing software reliability and optimizing quality assurance efforts by enabling the early identification of fault-prone components within the development lifecycle. This study presents a comprehensive empirical evaluation comparing the efficacy of classic...
The results indicate that HHO–NN–SDP provides an integrated approach to feature selection, neural-network optimization, and stacking, with a favorable balance between predictive performance and feature compactness across the evaluated benchmark families.
Aqsa, Yu-Lin Wang, Abdul Majid et al.· International Conference on...· 0 citations
A novel hybrid model based on a fine-tuned fully connected fully connected deep neural network, a random forest, and a convolutional neural network that achieves competitive fault prediction performance while requiring lower computational complexity and training time than recent deep-learning approaches.
Mehrasa Jouybari, Alireza Tajary, M. Fateh et al.· Jordanian Journal of Compute...· 0 citations
The Indonesian capital market, particularly the LQ45 Index and its leading sectoral stocks, exhibits high volatility and complex non-linear price patterns. This complexity renders conventional statistical methods insufficient for accurate forecasting and risk mitigation. This study aims to develop and compare three Dee...