MyMedR

Displaying all 10 publications

Abstract:

Sort:

Pollutant transport and residence time of a shallow and narrow coastal lagoon estimated using a numerical model

Zainol Z, Akhir MF, Zainol Z

Mar Pollut Bull, 2021 Mar;164:112011.
PMID: 33485016 DOI: 10.1016/j.marpolbul.2021.112011

Setiu Wetland is rapidly developing into an aquaculture and agriculture hub, causing concern about its water quality condition. To address this issue, it is imperative to acquire knowledge of the spatial and temporal distributions of pollutants. Consequently, this study applied combinations of hydrodynamic and particle tracking models to identify the transport behaviour of pollutants and calculate the residence time in Setiu Lagoon. The particle tracking results indicated that the residence time in Setiu Lagoon was highly influenced by the release location, where particles released closer to the river mouth exhibited shorter residence times than those released further upstream. Despite this fact, the pulse of river discharges successfully reduced the residence time in the order of two to twelve times shorter. Under different tidal phases, the residence time during the neap tide was longer regardless of heavy rainfalls, implying the domination of tidal flow in the water renewal within the lagoon.
Fulltext Feature Selection for High-Dimensional and Imbalanced Biomedical Data Based on Robust Correlation Based Redundancy and Binary Grasshopper Optimization Algorithm

Abdulrauf Sharifai G, Zainol Z

Genes (Basel), 2020 06 27;11(7).
PMID: 32605144 DOI: 10.3390/genes11070717

The training machine learning algorithm from an imbalanced data set is an inherently challenging task. It becomes more demanding with limited samples but with a massive number of features (high dimensionality). The high dimensional and imbalanced data set has posed severe challenges in many real-world applications, such as biomedical data sets. Numerous researchers investigated either imbalanced class or high dimensional data sets and came up with various methods. Nonetheless, few approaches reported in the literature have addressed the intersection of the high dimensional and imbalanced class problem due to their complicated interactions. Lately, feature selection has become a well-known technique that has been used to overcome this problem by selecting discriminative features that represent minority and majority class. This paper proposes a new method called Robust Correlation Based Redundancy and Binary Grasshopper Optimization Algorithm (rCBR-BGOA); rCBR-BGOA has employed an ensemble of multi-filters coupled with the Correlation-Based Redundancy method to select optimal feature subsets. A binary Grasshopper optimisation algorithm (BGOA) is used to construct the feature selection process as an optimisation problem to select the best (near-optimal) combination of features from the majority and minority class. The obtained results, supported by the proper statistical analysis, indicate that rCBR-BGOA can improve the classification performance for high dimensional and imbalanced datasets in terms of G-mean and the Area Under the Curve (AUC) performance metrics.
Fulltext Personality prediction based on social media using decision tree algorithm

Tan Lee CY, Ngatirin NR, Zainol Z

Pertanika Journal of Science & Technology, 2017;25(104):237-248.
MyJurnal

Personality represents the mixture of features and qualities that built an individual’s distinctive characters including thinking, feeling and behaving. Traditionally, self-assessment method via questionnaire is the most common means to identify personality. Since recommender systems and advertisement
campaigns have evolved rapidly, personality computing has become a popular research field to provide personalisation to users. Currently, researchers have utilised social media data for automatically predicting personality. However, it is complex to mine the social media data as they are noisy, free-format, and
of varying length and multimedia. This paper proposes a decision tree C4.5 algorithm to automatically predict personality based on Big Five model. The Big Five Inventory and ZeroR algorithm were included to be served as the baseline for performance evaluation. Experimental evaluation demonstrated that C4.5
performs better than ZeroR in terms of accuracy.
Keywords: Big Five, decision tree, personality, social media
Fulltext Water quality data in a shallow and narrow Setiu Lagoon

Zainol Z, Akhir MF, Johari A, Ali A

Data Brief, 2021 Apr;35:106866.
PMID: 33816725 DOI: 10.1016/j.dib.2021.106866

This article contains water quality data collected in a shallow and narrow Setiu Lagoon during the southwest monsoon, wet period of northeast monsoon and dry period of northeast monsoon. The surface water quality parameters, which include the temperature, salinity, chlorophyll-a and nutrients (ammonia, nitrate, phosphate, and silicate) were sampled twice per day (high and low tides) at a total of eight stations. Hourly current speed and direction was obtained from mooring of two units of current meters. Compared to the Malaysia Marine Water Quality Criteria and Standard (MWQCS), nutrients in Setiu Lagoon were in Class 2. Although limited, this dataset can provide insights on the changes of water quality condition in Setiu Lagoon under the presence of anthropogenic pressures.
Fulltext A comparative study of machine learning techniques for suicide attempts predictive model

Nordin N, Zainol Z, Mohd Noor MH, Lai Fong C

Health Informatics J, 2021 3 23;27(1):1460458221989395.
PMID: 33745355 DOI: 10.1177/1460458221989395

Current suicide risk assessments for predicting suicide attempts are time consuming, of low predictive value and have inadequate reliability. This paper aims to develop a predictive model for suicide attempts among patients with depression using machine learning algorithms as well as presents a comparative study on single predictive models with ensemble predictive models for differentiating depressed patients with suicide attempts from non-suicide attempters. We applied and trained eight different machine learning algorithms using a dataset that consists of 75 patients diagnosed with a depressive disorder. A recursive feature elimination was used to reduce the features via three-fold cross validation. An ensemble predictive models outperformed the single predictive models. Voting and bagging revealed the highest accuracy of 92% compared to other machine learning algorithms. Our findings indicate that history of suicide attempt, religion, race, suicide ideation and severity of clinical depression are useful factors for prediction of suicide attempts.
Suicidal behaviour prediction models using machine learning techniques: A systematic review

Nordin N, Zainol Z, Mohd Noor MH, Chan LF

Artif Intell Med, 2022 10;132:102395.
PMID: 36207078 DOI: 10.1016/j.artmed.2022.102395

BACKGROUND: Early detection and prediction of suicidal behaviour are key factors in suicide control. In conjunction with recent advances in the field of artificial intelligence, there is increasing research into how machine learning can assist in the detection, prediction and treatment of suicidal behaviour. Therefore, this study aims to provide a comprehensive review of the literature exploring machine learning techniques in the study of suicidal behaviour prediction.
METHODS: A search of four databases was conducted: Web of Science, PubMed, Dimensions, and Scopus for research papers dated between January 2016 and September 2021. The search keywords are 'data mining', 'machine learning' in combination with 'suicidal behaviour', 'suicide', 'suicide attempt', 'suicidal ideation', 'suicide plan' and 'self-harm'. The studies that used machine learning techniques were synthesized according to the countries of the articles, sample description, sample size, classification tasks, number of features used to develop the models, types of machine learning techniques, and evaluation of performance metrics.
RESULTS: Thirty-five empirical articles met the criteria to be included in the current review. We provide a general overview of machine learning techniques, examine the feature categories, describe methodological challenges, and suggest areas for improvement and research directions. Ensemble prediction models have been shown to be more accurate and useful than single prediction models.
CONCLUSIONS: Machine learning has great potential for improving estimates of future suicidal behaviour and monitoring changes in risk over time. Further research can address important challenges and potential opportunities that may contribute to significant advances in suicide prediction.
An explainable predictive model for suicide attempt risk using an ensemble learning and Shapley Additive Explanations (SHAP) approach

Nordin N, Zainol Z, Mohd Noor MH, Chan LF

Asian J Psychiatr, 2023 Jan;79:103316.
PMID: 36395702 DOI: 10.1016/j.ajp.2022.103316

Machine learning approaches have been used to develop suicide attempt predictive models recently and have been shown to have a good performance. However, those proposed models have difficulty interpreting and understanding why an individual has suicidal attempts. To overcome this issue, the identification of features such as risk factors in predicting suicide attempts is important for clinicians to make decisions. Therefore, the aim of this study is to propose an explainable predictive model to predict and analyse the importance of features for suicide attempts. This model can also provide explanations to improve the clinical understanding of suicide attempts. Two complex ensemble learning models, namely Random Forest and Gradient Boosting with an explanatory model (SHapley Additive exPlanations (SHAP)) have been constructed. The models are used for predictive interpretation and understanding of the importance of the features. The experiment shows that both models with SHAP are able to interpret and understand the nature of an individual's predictions with suicide attempts. However, compared with Random Forest, the results show that Gradient Boosting with SHAP achieves higher accuracy and the analyses found that history of suicide attempts, suicidal ideation, and ethnicity as the main predictors for suicide attempts.
Fulltext Enhanced Intrusion Detection with Data Stream Classification and Concept Drift Guided by the Incremental Learning Genetic Programming Combiner

Shyaa MA, Zainol Z, Abdullah R, Anbar M, Alzubaidi L, Santamaría J

Sensors (Basel), 2023 Apr 04;23(7).
PMID: 37050795 DOI: 10.3390/s23073736

Concept drift (CD) in data streaming scenarios such as networking intrusion detection systems (IDS) refers to the change in the statistical distribution of the data over time. There are five principal variants related to CD: incremental, gradual, recurrent, sudden, and blip. Genetic programming combiner (GPC) classification is an effective core candidate for data stream classification for IDS. However, its basic structure relies on the usage of traditional static machine learning models that receive onetime training, limiting its ability to handle CD. To address this issue, we propose an extended variant of the GPC using three main components. First, we replace existing classifiers with alternatives: online sequential extreme learning machine (OSELM), feature adaptive OSELM (FA-OSELM), and knowledge preservation OSELM (KP-OSELM). Second, we add two new components to the GPC, specifically, a data balancing and a classifier update. Third, the coordination between the sub-models produces three novel variants of the GPC: GPC-KOS for KA-OSELM; GPC-FOS for FA-OSELM; and GPC-OS for OSELM. This article presents the first data stream-based classification framework that provides novel strategies for handling CD variants. The experimental results demonstrate that both GPC-KOS and GPC-FOS outperform the traditional GPC and other state-of-the-art methods, and the transfer learning and memory features contribute to the effective handling of most types of CD. Moreover, the application of our incremental variants on real-world datasets (KDD Cup '99, CICIDS-2017, CSE-CIC-IDS-2018, and ISCX '12) demonstrate improved performance (GPC-FOS in connection with CSE-CIC-IDS-2018 and CICIDS-2017; GPC-KOS in connection with ISCX2012 and KDD Cup '99), with maximum accuracy rates of 100% and 98% by GPC-KOS and GPC-FOS, respectively. Additionally, our GPC variants do not show superior performance in handling blip drift.
Performance evaluation of two multiplex qualitative RT-PCR assays for detection of respiratory infection in paediatric population

Ali U, Zainal M, Zainol Z, Tai CW, Tang SF, Lee PC, et al.

Malays J Pathol, 2023 Aug;45(2):215-227.
PMID: 37658531

INTRODUCTION: Acute respiratory infection (ARI) contributes to significant mortality and morbidity worldwide and is usually caused by a wide range of respiratory pathogens. This study aims to describe the performance of QIAstat-Dx® Respiratory Panel V2 (RP) and RespiFinder® 2SMART assays for respiratory pathogens detection.
MATERIALS AND METHODS: A total of 110 nasopharyngeal swabs (NPS) were collected from children aged one month to 12 years old who were admitted with ARI in UKMMC during a one-year period. The two qPCR assays were conducted in parallel.
RESULTS: Ninety-seven samples (88.2%) were positive by QIAstat-Dx RP and 86 (78.2%) by RespiFinder assay. The overall agreement on both assays was substantial (kappa value: 0.769) with excellent concordance rate of 96.95%. Using both assays, hRV/EV, INF A/H1N1 and RSV were the most common pathogens detected. Influenza A/H1N1 infection was significantly seen higher in older children (age group > 60 months old) (53.3%, p-value < 0.05). Meanwhile, RSV and hRV/EV infection were seen among below one-year-old children. Co-infections by two to four pathogens were detected in 17 (17.5%) samples by QIAstat-Dx RP and 12 (14%) samples by RespiFinder, mainly involving hRV/EV. Bacterial detection was observed only in 5 (4.5%) and 6 (5.4%) samples by QIAstat-Dx RP and RespiFinder, respectively, with Mycoplasma pneumoniae the most common detected.
CONCLUSION: The overall performance of the two qPCR assays was comparable and showed excellent agreement. Both detected various clinically important respiratory pathogens in a single test with simultaneous multiple infection detection. The use of qPCR as a routine diagnostic test can improve diagnosis and management.
Fulltext Factors associated with placenta praevia in primigravidas and its pregnancy outcome

Nur Azurah AG, Wan Zainol Z, Lim PS, Shafiee MN, Kampan N, Mohsin WS, et al.

ScientificWorldJournal, 2014;2014:270120.
PMID: 25478587 DOI: 10.1155/2014/270120

To examine the factors associated with placenta praevia in primigravidas and also compare the pregnancy outcomes between primigravidas and nonprimigravidas.