Noor Hafhizah Abd Rahim
Universiti Malaysia Terengganu

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Novelty circular neighboring technique using reactive fault tolerance method Ahmad Shukri Mohd Noor; Nur Farhah Mat Zian; Noor Hafhizah Abd Rahim; Rabiei Mamat; Wan Nur Amira Wan Azman
International Journal of Electrical and Computer Engineering (IJECE) Vol 9, No 6: December 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (449.946 KB) | DOI: 10.11591/ijece.v9i6.pp5211-5217

Abstract

The availability of the data in a distributed system can be increase by implementing fault tolerance mechanism in the system. Reactive method in fault tolerance mechanism deals with restarting the failed services, placing redundant copies of data in multiple nodes across network, in other words data replication and migrating the data for recovery. Even if the idea of data replication is solid, the challenge is to choose the right replication technique that able to provide better data availability as well as consistency that involves read and write operations on the redundant copies. Circular Neighboring Replication (CNR) technique exploits neighboring policy in replicating the data items in the system performs well with regards to lower copies needed to maintain the system availability at the highest. In a performance analysis with existing techniques, results show that CNR improves system availability by average 37% by offering only two replicas needed to maintain data availability and consistency. The study demonstrates the possibility of the proposed technique and the potential of deploying in larger and complex environment.
An improved hybrid semi-stacked autoencoder for item-features of recommendation system (iHSARS) Ahed Mleih Al-Sbou; Noor Hafhizah Abd Rahim
Indonesian Journal of Electrical Engineering and Computer Science Vol 30, No 1: April 2023
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v30.i1.pp481-490

Abstract

In recent years, information overload has become a phenomenon where it makes people difficult to filter relevant information. To address issues such as high-dimensional data, cold start, and data sparsity, semi-autoencoder is one of the unsupervised deep learning methods used in the recommendation systems. It is particularly useful for reducing data dimensions, capturing latent representations, and flexibly reconstructing various parts of input data. In this article, we propose an improved hybrid semi-stacked autoencoder for item-features of recommendation system (iHSARS) framework. This method aims to show better performance of the hybrid collaborative recommendation via semi-autoencoder (HRSA) technique. Two novel elements for iHSARS’s architecture have been introduced. The first element is an increase sources of side information of the input layer, while the second element is the number of hidden layers has been expanded. To verify the improvement of the model, MovieLens-100K and MovieLens-1M datasets have been applied to the model. The comparison between the proposed model and different state-of-the-art methods has been carried using mean absolute error (MAE) and root mean square error (RMSE) metrics. The experiments demonstrate that our framework improved the efficiency of the recommendation system better than others.