MyMedR

Displaying all 5 publications

Abstract:

Sort:

Heavy metals prediction in coastal marine sediments using hybridized machine learning models with metaheuristic optimization algorithm

Yaseen ZM, Melini Wan Mohtar WH, Homod RZ, Alawi OA, Abba SI, Oudah AY, et al.

Chemosphere, 2024 Jan 29;352:141329.
PMID: 38296204 DOI: 10.1016/j.chemosphere.2024.141329

This study proposes different standalone models viz: Elman neural network (ENN), Boosted Tree algorithm (BTA), and f relevance vector machine (RVM) for modeling arsenic (As (mg/kg)) and zinc (Zn (mg/kg)) in marine sediments owing to anthropogenic activities. A heuristic algorithm based on the potential of RVM and a flower pollination algorithm (RVM-FPA) was developed to improve the prediction performance. Several evaluation indicators and graphical methods coupled with visualized cumulative probability function (CDF) were used to evaluate the accuracy of the models. Akaike (AIC) and Schwarz (SCI) information criteria based on Dickey-Fuller (ADF) and Philip Perron (PP) tests were introduced to check the reliability and stationarity of the data. The prediction performance in the verification phase indicated that RVM-M2 (PBAIS = -o.0465, MAE = 0.0335) and ENN-M2 (PBAIS = 0.0043, MAE = 0.0322) emerged as the best model for As (mg/kg) and Zn (mg/kg), respectively. In contrast with the standalone approaches, the simulated hybrid RVM-FPA proved merit and the most reliable, with a 5 % and 18 % predictive increase for As (mg/kg) and Zn (mg/kg), respectively. The study's findings validated the potential for estimating complex HMs through intelligent data-driven models and heuristic optimization. The study also generated valuable insights that can inform the decision-makers and stockholders for environmental management strategies.
Surface water quality index forecasting using multivariate complementing approach reinforced with locally weighted linear regression model

Hai T, Ahmadianfar I, Halder B, Heddam S, Al-Areeq AM, Demir V, et al.

Environ Sci Pollut Res Int, 2024 Apr 23.
PMID: 38653893 DOI: 10.1007/s11356-024-33027-0

River water quality management and monitoring are essential responsibilities for communities near rivers. Government decision-makers should monitor important quality factors like temperature, dissolved oxygen (DO), pH, and biochemical oxygen demand (BOD). Among water quality parameters, the BOD throughout 5 days is an important index that must be detected by devoting a significant amount of time and effort, which is a source of significant concern in both academic and commercial settings. The traditional experimental and statistical methods cannot give enough accuracy or solve the problem for a long time to detect something. This study used a unique hybrid model called MVMD-LWLR, which introduced an innovative method for forecasting BOD in the Klang River, Malaysia. The hybrid model combines a locally weighted linear regression (LWLR) model with a wavelet-based kernel function, along with multivariate variational mode decomposition (MVMD) for the decomposition of input variables. In addition, categorical boosting (Catboost) feature selection was used to discover and extract significant input variables. This combination of MVMD-LWLR and Catboost is the first use of such a complete model for predicting BOD levels in the given river environment. In addition, an optimization process was used to improve the performance of the model. This process utilized the gradient-based optimization (GBO) approach to fine-tune the parameters and better the overall accuracy of predicting BOD levels. To assess the robustness of the proposed method, we compared it to other popular models such as kernel ridge (KRidge) regression, LASSO, elastic net, and gaussian process regression (GPR). Several metrics, comprising root-mean-square error (RMSE), R (correlation coefficient), U95% (uncertainty coefficient at 95% level), and NSE (Nash-Sutcliffe efficiency), as well as visual interpretation, were used to evaluate the predictive efficacy of hybrid models. Extensive testing revealed that, in forecasting the BOD parameter, the MVMD-LWLR model outperformed its competitors. Consequently, for BOD forecasting, the suggested MVMD-LWLR optimized with the GBO algorithm yields encouraging and reliable results, with increased forecasting accuracy and minimal error.
Fulltext Inoculation and colonization of the entomopathogenic fungi, Isaria javanica and Purpureocillium lilacinum, in tomato plants, and their effect on seedling growth, mortality and adult emergence of Bemisia tabaci (Gennadius)

Sani I, Jamian S, Saad N, Abdullah S, Mohd Hata E, Jalinas J, et al.

PLoS One, 2023;18(5):e0285666.
PMID: 37216342 DOI: 10.1371/journal.pone.0285666

Entomopathogenic fungi (EPF) are natural enemies which affect insect population and have long been recognized as biological control agents against many insect pests. Some isolates have also been established as endophytes, benefiting their host plants without causing any symptoms or negative effects. Here we demonstrated two entomopathogenic fungal species, Isariajavanica (Frieder. & Bally) Samson & Hywel-jone 2005 and Purpureocillium lilacinum (Thom) Luangsa-ard, Hou-braken, Hywel-Jones & Samson (2011) as endophytes in tomato plants by using the seed inoculation method and examined their effect on plant growth, B. tabaci mortality, and adult emergence. Our study indicated that tomato seeds treated with a fungal suspension of I. javanica and P. lilacinum enabled their recovery from plant tissues (root, stem and leaf) up to 60 days after inoculation (DAI). Both endophytic isolates also caused significant mortality of adult B. tabaci on seedlings inoculated with, I. javanica (51.92±4.78%), and P. lilacinum (45.32±0.20%) compared to the control treatment (19.29±2.35). Adult emergence rates were significantly high in the control treatments (57.50±2.66%) compared to I. javanica (15.00±1.47%) and P. lilacinum (28.75±4.78%) treatments. This study provides evidence that endophytic isolates of I. javanica and P. lilacinum have a biocontrol potentials for used against whiteflies and could also explored as plant growth promoters.
Presence of SARS-CoV-2-like coronaviruses in bats from east coast Malaysia

Gilbert M, Mohamed M, Choong SS, Baqi A, Kumaran JV, Sani I, et al.

Trop Biomed, 2023 Sep 01;40(3):273-280.
PMID: 37897158 DOI: 10.47665/tb.40.3.001

Most of the public health importance coronaviruses, such as Severe acute respiratory syndrome coronavirus (SARS-CoV), Middle East respiratory syndrome coronavirus (MERS-CoV) and SARS-CoV-2 are likely originated from bats and spread to humans through intermediate hosts; civet cats, dromedary camel and Malayan pangolin, respectively. SARS-CoV-2-like coronaviruses were detected in Thailand, which is neighbouring with Kelantan in East Coast Malaysia. To date, there is no report on the presence of public health concerns (SARS-CoV, SARS-CoV-2 and MERS-CoV) coronaviruses in bats from Malaysia. This study was aimed to elucidate the presence of these coronaviruses in bat samples from East Coast, Malaysia. A total of hundred seventy oropharyngeal swab samples were collected from three states of East Coast Malaysia. Reverse Transcription-Polymerase Chain Reaction (RT-PCR) was conducted based on partial 3' Untranslated region (3'UTR) or ORF10 gene and the products were sequenced. The sequences were compared with all coronavirus sequences from the National Center for Biotechnology Information-GenBank (NCBI-GenBank) using NCBI-Basic Local Alignment Search Tool (NCBI-BLAST) software. A phylogenetic tree was constructed to determine the genetic relationship among the detected coronaviruses with the reference coronaviruses from the NCBI-GenBank. Our results showed that SARSCoV-2-like viruses were present in 3% (5/170) of the bats from East Coast Malaysia that have 98-99% sequence identities and are genetically related to SARS-CoV-2 from humans. This finding indicates the presence of SARS-CoV-2-like viruses in bats from East Coast Malaysia that may become a public health concern in the future.
Fulltext Snakehead Consumption Enhances Wound Healing? From Tradition to Modern Clinical Practice: A Prospective Randomized Controlled Trial

Sahid NA, Hayati F, Rao CV, Ramely R, Sani I, Dzulkarnaen A, et al.

Evid Based Complement Alternat Med, 2018;2018:3032790.
PMID: 30538757 DOI: 10.1155/2018/3032790

BACKGROUND: Snakehead fish (Channa striatus) is a fresh water fish indigenous to many Asia countries and believed to have medical value. Studies showed that it contains all the essential amino acids and fatty acids able to accelerate wound healing and it has antinociceptive effect. However, little human study has been done to assess the effectiveness of Channa striatus in wound healing. A prospective RCT has been conducted on the effect of Channa striatus spray versus placebo on clean wound to assess its pain control effect and cosmetic outcome.
METHODOLOGY: One hundred and two patients (102) underwent clean elective surgery; postoperatively they were randomized into two group. One group received Channa striatus extract spray (n=51) another group received placebo (n=51) on daily basis for 2 weeks. They were followed up on 2nd, 4th, and 6th weeks. Pain control effect was assessed based on Visual Analog Pain Score (VAPS) and cosmetic outcome based on Visual Analog Cosmetic Scale (VACS), Wound Evaluation Scale (WES), and Vancouver Scar Scale (VSS).
RESULT: The patient treated with Channa striatus spray displayed a better outcome in terms of pain control compared to placebo. During analysis using repeated measure ANOVA, there was significant difference of patient's pain score based on VAPS between Channa striatus spray and placebo (F-stat (df) = 4.80 (2), p-value = 0.010). For cosmetic outcome it showed a better result in Channa striatus spray group for all the 3-scoring system, VACS, (F-stat (df) = 2.68 (2) , p-value <0.001), WES (F-stat (df) = 3.09 (2), p-value = 0.048), and VSS (F-stat (df) = 1.72 (2) , p-value = 0.011).
CONCLUSION: Our study suggest that application of Channa striatus extract spray on clean wound has shown a significant better pain score result and cosmetic outcome on week 2, week 4, and week 6 comparatively with placebo.