Current Organizations / Institutes

The organizations/institutes from the scholar's latest article

Previous Organizations / Institutes

The organizations / institutes from the scholar's other articles in the past ten years


Suhaila Zainudin has a total of 30 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    A Transfer Learning-Based Text-Centric Model for Multimodal Sentiment Analysis

    by Shaowei Yi, Suhaila Zainudin

    Multimodal sentiment analysis (MMSA) is a research method that extracts effective information from heterogeneous modal information. Then, MMSA processes the multimodal data and performs sentiment analysis. Along with big data and machine learning development, multimodal sentiment analysis has become a hot research direction in multimodal learning and natural language processing. Although various feature extraction methods and information fusion methods have been continuously proposed, challenges exist in MMSA research. First, in terms of feature extraction, pre-trained models trained with many data sets can obtain higher quality features, but research on how to use these feature extraction methods to extract the best features is still needed. Currently, the more popular feature fusion methods do not focus on the interaction between multiple modal information and the retention of basic information. To overcome these problems a multimodal sentiment analysis model utilizes text features as core modal features, using video and audio modal features as auxiliary modal features, multimodal feature modality attention mechanism to extract the intrinsic connection between different modalities. The attention mechanism uses the features of video modality and audio modality as the focus and then enhances the text modality with the fusion of video modality and modality. To improve the quality of extracted features, this method chooses the transfer learning training method and uses the pre-trained model for processing. This research uses the CMU-MOSI dataset to test the proposed method. Experimental results show that the performance of the proposed model in emotion score prediction and emotion classification tasks exceeds traditional methods and baseline methods.

  • Open Access

    Enhancing Automated Test Case Generation Through KNN algorithm in Software Testing

    by Abdulrahman Ahmed Khudhur, Ibrahim Mohamed, Suhaila Zainudin

    In the ever-evolving world of software development, assuring the stability and resilience of software systems remains a vital task. This study aims to tackle this problem by suggesting a novel method for generating automated test cases. It involves incorporating the robust KNN algorithm into the domain of data mining methods. The research intends to exploit previous testing data to detect patterns and trends, increasing the production of effective and targeted test scenarios. The literature study highlights the increasing overlap between data mining and software testing, underscoring the need for sophisticated methods to address the requirements of contemporary, ever-changing applications. In this regard, our study presents the KNN algorithm as a new addition to the collection of data mining tools for software testing. The process entails gathering extensive historical testing data, including information on test cases, errors, and the attributes of tested software applications. By using rigorous preprocessing and feature selection techniques, the KNN method is used to examine the correlations between various variables and the probability of flaws. The KNN model is trained and optimized using the dataset, and the resultant predictions are then used in an automated system for generating test cases. The experimental results confirm the efficacy of the suggested method in finding crucial test scenarios and prioritizing test cases according to past fault trends. The practical usefulness and advantages of incorporating the KNN algorithm into the automated test case-generating process are further confirmed by real-world case studies. In conclusion, this study expands the discourse on data mining in software testing by proposing the KNN algorithm as a vital component in automated test case development. By using KNN, testing teams can adjust to the ever-changing characteristics of contemporary applications, leading to enhanced efficiency and effectiveness in testing procedures. The results of this research enhance the continuous development of software quality assurance methods and provide opportunities for additional investigation at the convergence of machine learning and software testing


  • Open Access

    Semi-Supervised Model for Aspect Sentiment Detection

    by Zohreh Madhoushi, Abdul Razak Hamdan, Suhaila Zainudin

    Advancements in text representation have produced many deep language models (LMs), such as Word2Vec and recurrent-based LMs. However, there are scarce works that focus on detecting implicit sentiments with a small amount of labelled data because there are many different review areas. Deep learning techniques are suitable to automate the representation learning process. Hence, we proposed a semi-supervised aspect-based sentiment analysis (ABSA) model for online review to predict explicit and implicit sentiment in three domains (laptop, restaurant, and hotel). The datasets of this study, S1 and S2, were obtained from a standard SemEval online competition and Amazon review datasets. The proposed models outperform the previous baseline models regarding the F1-score of aspect category detection and accuracy of sentiment detection. This study finds more relevant aspects and accurate sentiment for ABSA by developing more stable and robust models. The accuracy of sentiment detection is 84.87% in the restaurant domain on the first dataset. For the second dataset, the proposed method achieved 84.43% in the laptop domain, 85.21% in the restaurant domain, and 85.57% in the hotel domain. The novelty is the proposed new semi-supervised model for aspect sentiment detection with embedded aspect inspired by the encoder–decoder architecture in the neural machine translation (NMT) model.


  • Open Access

    Optimizing the Production of Valuable Metabolites using a Hybrid of Constraint-based Model and Machine Learning Algorithms: A Review

    by Kauthar Mohd Daud, Ridho Ananda, Suhaila Zainudin, Chan Weng Howe

    The advances in genome sequencing and metabolic engineering have allowed the reengineering of the cellular function of an organism. Furthermore, given the abundance of omics data, data collection has increased considerably, thus shifting the perspective of molecular biology. Therefore, researchers have recently used artificial intelligence and machine learning tools to simulate and improve the reconstruction and analysis by identifying meaningful features from the large multiomics dataset. This review paper summarizes research on the hybrid of constraint-based models and machine learning algorithms in optimizing valuable metabolites. The research articles published between 2020 and 2023 on machine learning and constraint-based modeling have been collected, synthesized, and analyzed. The articles are obtained from the Web of Science and Scopus databases using the keywords: “Machine learning”, “flux balance analysis”, and “metabolic engineering”. At the end of the search, this review contained 13 records. This review paper aims to provide current trends and approaches in in silico metabolic engineering while providing research directions by highlighting the research gaps. In addition, we have discussed the methodology for integrating machine learning and constraint-based modeling approaches.


  • Open Access

    Optimization of Discrete Wavelet Transform Feature Representation and Hierarchical Classification of G-Protein Coupled Receptor Using Firefly Algorithm and Particle Swarm Optimization

    by Nor Ashikin Mohamad Kamal, Azuraliza Abu Bakar, Suhaila Zainudin

    Ineffective protein feature representation poses problems in protein classification in hierarchical structures. Discrete wavelet transform (DWT) is a feature representation method which generates global and local features based on different wavelet families and decomposition levels. To represent protein sequences, the proper wavelet family and decomposition level must be selected. This paper proposed a hybrid optimization method using particle swarm optimization and the firefly algorithm (FAPSO) to choose the suitable wavelet family and decomposition level of wavelet transformation for protein feature representation. The suggested approach improved on the work of earlier researchers who, in most cases, manually selected the wavelet family and level of decomposition based solely on experience and not on data. The paper also applied the virtual class methods to overcome the error propagation problems in hierarchical classification. The effectiveness of the proposed method was tested on a G-Protein Coupled Receptor (GPCR) protein data set consisting of 5 classes at the family level, 38 classes at the subfamily level, and 87 classes at the sub-subfamily level. Based on the result obtained, the most selected wavelet family and decomposition level chosen to represent GPCR classes by FAPSO are Biorthogonal wavelets and decomposition level 1, respectively. The experimental results show that the representation of GPCR protein using the FAPSO algorithm with virtual classes can yield 97.9%, 86.9%, and 81.3% classification accuracy at the family, subfamily, and sub-subfamily levels, respectively. In conclusion, the result shows that the selection of optimized wavelet family and decomposition level by the FAPSO algorithm, and the virtual class method can be potentially used as the feature representation method and a hierarchical classification method for GPCR protein.


  • Open Access

    GPCR Protein Feature Representation using Discrete Wavelet Transform and Particle Swarm Optimisation Algorithm

    by Nor Ashikin Mohamad Kamal, Azuraliza Abu Bakar, Suhaila Zainudin

    Features play an important role in representing classes in the hierarchy structure, and using unsuitable features will affect classification performance. The discrete wavelet transform (DWT) approach provides the ability to create the appropriate features to represent data. DWT can produce global and local features using different wavelet families and decomposition levels. These two parameters are essential to obtain a suitable representation for classes in the hierarchy structure. This study proposes using a particle swarm optimisation (PSO) algorithm to select the suitable wavelet family and decomposition level for G-protein coupled receptor (GPCR) hierarchical class representation. The results indicate that the PSO algorithm mostly selects Biorthogonal wavelets and decomposition level 2 to represent GPCR protein. Concerning the performance, the proposed method achieved an accuracy of 97.9%, 85.9%, and 77.5% at the family, subfamily, and sub-subfamily levels, respectively.


  • Open Access

    Identifying Students' Learning Patterns in Online Learning Environments: A Literature Review

    by Maryam Abdulsalam Ali, Noraidah Sahari Ashaari, Siti Fadzilah Mat Noor, Suhaila Zainudin

    Digital learning environments have offered new opportunities to stream educational materials such as courses, educational videos, forums and provide outcomes of the students, grades, engagement details, and learning patterns. These valuable educational data has emerged with the latest technologies and software tools to provide researchers and decision-makers with a better understanding of students' behaviours. These virtual learning environments can professionally aid struggling students by observing, learning, and identifying different learning patterns. Many researchers have discussed that even if there are instructions and helping tools within these environments, some students remain at risk of negative learning behaviours such as boredom, disengagement, and failure. Particularly when approaching complex or new educational content. Previous researchers have observed that the students exhibit high persistence levels when spending too much time on a particular task when they are learning remotely or too many tries to solve a specific task without reaching the success level. Students' persistence is identified as a prominent learning skill contributing to confirmed success while learning new education materials. Many works of literature recognised the value of persistence. They reached a fundamental fact that not all persistence is considered productive, especially when spending more time and effort without moving toward a state of mastery in learning new skills and topics. This scenario may eventually lead to frustration and disengagement; in the worst-case scenarios, the students will finally drop the course or just quit learning. By examining the most relevant literature, this paper discusses the main factors affecting students' digital learning persistence. Different models performed at each learning opportunity are observed to categorise when involvements may be arranged to best aid the learners facing learning struggles.