Improving Software Reliability Prediction with a Hybrid ANN-SARIMA Model Enhanced by Jaya Optimization DOI
Suneel Kumar Rath, Madhusmita Sahu, Shom Prasad Das

и другие.

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Сен. 6, 2024

Abstract Software reliability stands as a crucial attribute for intricate computing systems, its absence can lead to cascade of issues such increased costs, project delays, and tarnished reputations software providers. Therefore, ensuring prior customer delivery is paramount any company. Timely error detection, with reasonable level accuracy, preventing potential consequences. Despite the existence various growth models, many them rely on unrealistic assumptions about development testing environments, often using black box methodologies. In response this challenge, hybrid forecasting model proposed in paper. The combines artificial neural network (ANN) seasonal auto-regressive integrated moving average (SARIMA) approaches, which are optimised by Jaya optimisation. Improving overall fault predicting main objectives. Because it detects possible faults early on, essential both programme maintenance. With optimisation, complementing advantages ANN SARIMA produce more accurate forecasts improved flexibility intricacies dynamic systems. Empirical assessment real-world data shows that approach outperforms conventional techniques. durable resilient systems greatly aided research, given quickly changing nature technology today.

Язык: Английский

AI-driven forecasting of river discharge: the case study of the Himalayan mountainous river DOI
Shakeel Ahmad Rather, Mahesh Patel, Kanish Kapoor

и другие.

Earth Science Informatics, Год журнала: 2025, Номер 18(2)

Опубликована: Фев. 1, 2025

Язык: Английский

Процитировано

0

Improving Software Reliability Prediction with a Hybrid ANN-SARIMA Model Enhanced by Jaya Optimization DOI
Suneel Kumar Rath, Madhusmita Sahu, Shom Prasad Das

и другие.

Research Square (Research Square), Год журнала: 2024, Номер unknown

Опубликована: Сен. 6, 2024

Abstract Software reliability stands as a crucial attribute for intricate computing systems, its absence can lead to cascade of issues such increased costs, project delays, and tarnished reputations software providers. Therefore, ensuring prior customer delivery is paramount any company. Timely error detection, with reasonable level accuracy, preventing potential consequences. Despite the existence various growth models, many them rely on unrealistic assumptions about development testing environments, often using black box methodologies. In response this challenge, hybrid forecasting model proposed in paper. The combines artificial neural network (ANN) seasonal auto-regressive integrated moving average (SARIMA) approaches, which are optimised by Jaya optimisation. Improving overall fault predicting main objectives. Because it detects possible faults early on, essential both programme maintenance. With optimisation, complementing advantages ANN SARIMA produce more accurate forecasts improved flexibility intricacies dynamic systems. Empirical assessment real-world data shows that approach outperforms conventional techniques. durable resilient systems greatly aided research, given quickly changing nature technology today.

Язык: Английский

Процитировано

0