MyMedR

Displaying all 7 publications

Abstract:

Sort:

Fulltext Master-Leader-Slave Cuckoo Search with Parameter Control for ANN Optimization and Its Real-World Application to Water Quality Prediction

Jaddi NS, Abdullah S, Abdul Malek M

PLoS One, 2017;12(1):e0170372.
PMID: 28125609 DOI: 10.1371/journal.pone.0170372

Artificial neural networks (ANNs) have been employed to solve a broad variety of tasks. The selection of an ANN model with appropriate weights is important in achieving accurate results. This paper presents an optimization strategy for ANN model selection based on the cuckoo search (CS) algorithm, which is rooted in the obligate brood parasitic actions of some cuckoo species. In order to enhance the convergence ability of basic CS, some modifications are proposed. The fraction Pa of the n nests replaced by new nests is a fixed parameter in basic CS. As the selection of Pa is a challenging issue and has a direct effect on exploration and therefore on convergence ability, in this work the Pa is set to a maximum value at initialization to achieve more exploration in early iterations and it is decreased during the search to achieve more exploitation in later iterations until it reaches the minimum value in the final iteration. In addition, a novel master-leader-slave multi-population strategy is used where the slaves employ the best fitness function among all slaves, which is selected by the leader under a certain condition. This fitness function is used for subsequent Lévy flights. In each iteration a copy of the best solution of each slave is migrated to the master and then the best solution is found by the master. The method is tested on benchmark classification and time series prediction problems and the statistical analysis proves the ability of the method. This method is also applied to a real-world water quality prediction problem with promising results.
Fulltext Genetic variability and selection criteria in rice mutant lines as revealed by quantitative traits

Oladosu Y, Rafii MY, Abdullah N, Abdul Malek M, Rahim HA, Hussin G, et al.

ScientificWorldJournal, 2014;2014:190531.
PMID: 25431777 DOI: 10.1155/2014/190531

Genetic based knowledge of different vegetative and yield traits play a major role in varietal improvement of rice. Genetic variation gives room for recombinants which are essential for the development of a new variety in any crop. Based on this background, this work was carried out to evaluate genetic diversity of derived mutant lines and establish relationships between their yield and yield components using multivariate analysis. To achieve this objective, two field trials were carried out on 45 mutant rice genotypes to evaluate their growth and yield traits. Data were taken on vegetative traits and yield and its components, while genotypic and phenotypic coefficients, variance components, expected genetic advance, and heritability were calculated. All the genotypes showed variations for vegetative traits and yield and its components. Also, there was positive relationship between the quantitative traits and the final yield with the exception of number of tillers. Finally, the evaluated genotypes were grouped into five major clusters based on the assessed traits with the aid of UPGMA dendrogram. So hybridization of group I with group V or group VI could be used to attain higher heterosis or vigour among the genotypes. Also, this evaluation could be useful in developing reliable selection indices for important agronomic traits in rice.
Fulltext PM2.5 forecasting for an urban area based on deep learning and decomposition method

Zaini N, Ean LW, Ahmed AN, Abdul Malek M, Chow MF

Sci Rep, 2022 Oct 20;12(1):17565.
PMID: 36266317 DOI: 10.1038/s41598-022-21769-1

Rapid growth in industrialization and urbanization have resulted in high concentration of air pollutants in the environment and thus causing severe air pollution. Excessive emission of particulate matter to ambient air has negatively impacted the health and well-being of human society. Therefore, accurate forecasting of air pollutant concentration is crucial to mitigate the associated health risk. This study aims to predict the hourly PM2.5 concentration for an urban area in Malaysia using a hybrid deep learning model. Ensemble empirical mode decomposition (EEMD) was employed to decompose the original sequence data of particulate matter into several subseries. Long short-term memory (LSTM) was used to individually forecast the decomposed subseries considering the influence of air pollutant parameters for 1-h ahead forecasting. Then, the outputs of each forecast were aggregated to obtain the final forecasting of PM2.5 concentration. This study utilized two air quality datasets from two monitoring stations to validate the performance of proposed hybrid EEMD-LSTM model based on various data distributions. The spatial and temporal correlation for the proposed dataset were analysed to determine the significant input parameters for the forecasting model. The LSTM architecture consists of two LSTM layers and the data decomposition method is added in the data pre-processing stage to improve the forecasting accuracy. Finally, a comparison analysis was conducted to compare the performance of the proposed model with other deep learning models. The results illustrated that EEMD-LSTM yielded the highest accuracy results among other deep learning models, and the hybrid forecasting model was proved to have superior performance as compared to individual models.
Sustainable management of water demand using fuzzy inference system: a case study of Kenyir Lake, Malaysia

Mohd Azlan NNI, Abdul Malek M, Zolkepli M, Mohd Salim J, Ahmed AN

Environ Sci Pollut Res Int, 2021 Apr;28(16):20261-20272.
PMID: 33405154 DOI: 10.1007/s11356-020-11908-4

Sustainable water demand management has become a necessity to the world since the immensely growing population and development have caused water deficit and groundwater depletion. This study aims to overcome water deficit by analyzing water demand at Kenyir Lake, Terengganu, using a fuzzy inference system (FIS). The analysis is widened by comparing FIS with the multiple linear regression (MLR) method. FIS applied as an analysis tool provides good generalization capability for optimum solutions and utilizes human behavior influenced by expert knowledge in water resources management for fuzzy rules specified in the system, whereas MLR can simultaneously adjust and compare several variables as per the needs of the study. The water demand dataset of Kenyir Lake was analyzed using FIS and MLR, resulting in total forecasted water consumptions at Kenyir Lake of 2314.38 m3 and 1358.22 m3, respectively. It is confirmed that both techniques converge close to the actual water consumption of 1249.98 m3. MLR showed the accuracy of the water demand values with smaller forecasted errors to be higher than FIS did. To attain sustainable water demand management, the techniques used can be examined extensively by researchers, educators, and learners by adding more variables, which will provide more anticipated outcomes.
Exploring machine learning algorithms for accurate water level forecasting in Muda river, Malaysia

Adli Zakaria MN, Ahmed AN, Abdul Malek M, Birima AH, Hayet Khan MM, Sherif M, et al.

Heliyon, 2023 Jul;9(7):e17689.
PMID: 37456046 DOI: 10.1016/j.heliyon.2023.e17689

Accurate water level prediction for both lake and river is essential for flood warning and freshwater resource management. In this study, three machine learning algorithms: multi-layer perceptron neural network (MLP-NN), long short-term memory neural network (LSTM) and extreme gradient boosting XGBoost were applied to develop water level forecasting models in Muda River, Malaysia. The models were developed using limited amount of daily water level and meteorological data from 2016 to 2018. Different input scenarios were tested to investigate the performance of the models. The results of the evaluation showed that the MLP model outperformed both the LSTM and the XGBoost models in predicting water levels, with an overall accuracy score of 0.871 compared to 0.865 for LSTM and 0.831 for XGBoost. No noticeable improvement has been achieved after incorporating meteorological data into the models. Even though the lowest reported performance was reported by the XGBoost, it is the faster of the three algorithms due to its advanced parallel processing capabilities and distributed computing architecture. In terms of different time horizons, the LSTM model was found to be more accurate than the MLP and XGBoost model when predicting 7 days ahead, demonstrating its superiority in capturing long-term dependencies. Therefore, it can be concluded that each ML model has its own merits and weaknesses, and the performance of different ML models differs on each case because these models depends largely on the quantity and quality of data available for the model training.
Fulltext Microwave radiation-induced grafting of 2-methacryloyloxyethyl trimethyl ammonium chloride onto lentil extract (LE-g-DMC) as an emerging high-performance plant-based grafted coagulant

Chua SC, Chong FK, Ul Mustafa MR, Mohamed Kutty SR, Sujarwo W, Abdul Malek M, et al.

Sci Rep, 2020 03 03;10(1):3959.
PMID: 32127558 DOI: 10.1038/s41598-020-60119-x

The importance of graft copolymerization in the field of polymer science is analogous to the importance of alloying in the field of metals. This is attribute to the ability of the grafting method to regulate the properties of polymer 'tailor-made' according to specific needs. This paper described a novel plant-based coagulant, LE-g-DMC that synthesized through grafting of 2-methacryloyloxyethyl trimethyl ammonium chloride (DMC) onto the backbone of the lentil extract. The grafting process was optimized through the response surface methodology (RSM) using three-level Box-Behnken Design (BBD). Under optimum conditions, a promising grafting percentage of 120% was achieved. Besides, characterization study including SEM, zeta potential, TGA, FTIR and EDX were used to confirm the grafting of the DMC monomer chain onto the backbone of lentil extract. The grafted coagulant, LE-g-DMC outperformed lentil extract and alum in turbidity reduction and effective across a wide range of pH from pH 4 to pH 10. Besides, the use of LE-g-DMC as coagulant produced flocs with excellent settling ability (5.09 mL/g) and produced the least amount of sludge. Therefore, from an application and economic point of views, LE-g-DMC was superior to native lentil extract coagulant and commercial chemical coagulant, alum.
Fulltext What information and the extent of information research participants need in informed consent forms: a multi-country survey

Karbwang J, Koonrungsesomboon N, Torres CE, Jimenez EB, Kaur G, Mathur R, et al.

BMC Med Ethics, 2018 09 15;19(1):79.
PMID: 30219106 DOI: 10.1186/s12910-018-0318-x

BACKGROUND: The use of lengthy, detailed, and complex informed consent forms (ICFs) is of paramount concern in biomedical research as it may not truly promote the rights and interests of research participants. The extent of information in ICFs has been the subject of debates for decades; however, no clear guidance is given. Thus, the objective of this study was to determine the perspectives of research participants about the type and extent of information they need when they are invited to participate in biomedical research.
METHODS: This multi-center, cross-sectional, descriptive survey was conducted at 54 study sites in seven Asia-Pacific countries. A modified Likert-scale questionnaire was used to determine the importance of each element in the ICF among research participants of a biomedical study, with an anchored rating scale from 1 (not important) to 5 (very important).
RESULTS: Of the 2484 questionnaires distributed, 2113 (85.1%) were returned. The majority of respondents considered most elements required in the ICF to be 'moderately important' to 'very important' for their decision making (mean score, ranging from 3.58 to 4.47). Major foreseeable risk, direct benefit, and common adverse effects of the intervention were considered to be of most concerned elements in the ICF (mean score = 4.47, 4.47, and 4.45, respectively).
CONCLUSIONS: Research participants would like to be informed of the ICF elements required by ethical guidelines and regulations; however, the importance of each element varied, e.g., risk and benefit associated with research participants were considered to be more important than the general nature or technical details of research. Using a participant-oriented approach by providing more details of the participant-interested elements while avoiding unnecessarily lengthy details of other less important elements would enhance the quality of the ICF.