Browse publications by year: 2024

  1. Rajendiran S, Li Ping W, Veloo Y, Syed Abu Thahir S
    Hum Vaccin Immunother, 2024 Dec 31;20(1):2318133.
    PMID: 38433096 DOI: 10.1080/21645515.2024.2318133
    Concern about the zoonotic Hepatitis E virus (HEV) is rising. Since, food handlers are at greater risk in contracting HEV, the present study aims to determine awareness, knowledge, prevention practices against HEV, and immunization attitudes. A cross sectional study was conducted among 400 food handlers in Klang Valley, Malaysia from December 2021 to March 2022. A structured questionnaire was employed for data collection and analysis with Statistical Package for Social Science (SPSS) version 29. Approximately 4.5% of the respondents (18) reported having heard of HEV, while the median scores for the knowledge and practice domains were 0/10 and 1/5, respectively. A total of 316 (79%) respondents expressed willingness to obtain vaccination if made available. This study also found that those respondents who completed their tertiary education were significantly possessed better knowledge of the disease [odd ratio (OR) = 8.95, and 95% confidence interval (CI) 4.98-16.10]. Respondents with HEV awareness reported considerably better practices (OR = 8.24, 95% CI 1.72-39.63). Food handlers with one to five years of experience in the industry expressed notable willingness to take vaccination (OR = 7.71, 95% CI 1.79-33.18). Addressing poor HEV awareness and knowledge and poor practices against the disease is crucial in enlightening the policy makers about awareness among food handlers and general population. Nonetheless, a good immunization attitude, significant acceptance toward vaccination even with the vaccine being unavailable in Malaysia, and limited awareness of HEV highlight a promising development.
    MeSH terms: Cross-Sectional Studies; Humans; Immunization; Malaysia; Vaccination; Hepatitis E virus*
  2. Hiew VV, Teoh PL
    Mol Biol Rep, 2024 Mar 03;51(1):383.
    PMID: 38433142 DOI: 10.1007/s11033-024-09324-9
    BACKGROUND: Graphene oxide (GO) is widespread in scaffold engineering owing to its extraordinary properties such as multiple oxygen functional groups, high hydrophilicity ability and biocompatibility. It is known to promote differentiation in mesenchymal stem cells, but concomitant comparison of its modulation on the expression profiles of Wharton's jelly (WJ)-MSC surface markers, lineage differentiation, and epigenetic regulatory genes in basal and induced condition are still lacking. Unraveling the fundamental mechanisms is essential for the effective utilization of WJ-MSCs incorporated with GO in therapy. This study aims to explore the unique gene expression profiles and epigenetic characteristics of WJ-MSCs influenced by GO.

    METHODS AND RESULTS: The characterized GO-coated coverslip served as a substrate for culturing WJ-MSCs. In addition to investigating the impact of GO on cell proliferation and differentiation, we conducted a gene expression study using PCR array, while epigenetic control was assessed through bisulfite sequencing and Western blot analysis. Our findings indicate that the presence of GO maintained the proliferation and survival of WJ-MSCs. In the absence of induction, GO led to minor lipid and glycosaminoglycan deposition in WJ-MSCs. This was evidenced by the sustained expression of pluripotency and lineage-specific genes, demethylation at the OCT4 promoter, and a decrease in H3K9 methylation. In osteo-induced condition, the occurrence of osteogenesis appeared to be guided by BMP/TGF and ERK pathway activation, accompanied by the upregulation of osteogenic-related genes and downregulation of DNMT3b.

    CONCLUSIONS: GO in osteo-induced condition create a favorable microenvironment that promotes the osteogenesis of WJ-MSCs by influencing genetic and epigenetic controls. This helps in advancing our knowledge on the use of GO as priming platform and WJ-MSCs an alternate source for bone repair and regeneration.

    MeSH terms: Graphite*; Blotting, Western; Gene Expression; Mesenchymal Stromal Cells*; Wharton Jelly*
  3. Rao K, Abdullah M, Ahmed U, Wehelie HI, Shah MR, Siddiqui R, et al.
    Arch Microbiol, 2024 Mar 04;206(4):134.
    PMID: 38433145 DOI: 10.1007/s00203-024-03854-3
    Acanthamoeba castellanii are opportunistic pathogens known to cause infection of the central nervous system termed: granulomatous amoebic encephalitis, that mostly effects immunocompromised individuals, and a sight threatening keratitis, known as Acanthamoeba keratitis, which mostly affects contact lens wearers. The current treatment available is problematic, and is toxic. Herein, an amphiphilic star polymer with AB2 miktoarms [A = hydrophobic poly(ℇ-Caprolacton) and B = hydrophilic poly (ethylene glycol)] was synthesized by ring opening polymerization and CuI catalyzed azide-alkyne cycloaddition. Characterization by 1H and 13C NMR spectroscopy, size-exclusion chromatography and fluorescence spectroscopy was accomplished. The hydrophobic drug itraconazole (ITZ) was incorporated in self-assembled micellar structure of AB2 miktoarms through co-solvent evaporation. The properties of ITZ loaded (ITZ-PCL-PEG2) and blank micelles (PCL-PEG2) were investigated through zeta sizer, scanning electron microscopy and Fourier-transform infrared spectroscopy. Itraconazole alone (ITZ), polymer (DPB-PCL), empty polymeric micelles (PCL-PEG2) alone, and itraconazole loaded in polymeric micelles (ITZ-PCL-PEG2) were tested for anti-amoebic potential against Acanthamoeba, and the cytotoxicity on human cells were determined. The polymer was able to self-assemble in aqueous conditions and exhibited low value for critical micelle concentration (CMC) 0.05-0.06 µg/mL. The maximum entrapment efficiency of ITZ was 68%. Of note, ITZ, DPB, PCL-PEG2 and ITZ-PCL-PEG2 inhibited amoebae trophozoites by 37.34%, 36.30%, 35.77%, and 68.24%, respectively, as compared to controls. Moreover, ITZ-PCL-PEG2 revealed limited cytotoxicity against human keratinocyte cells. These results are indicative that ITZ-PCL-PEG2 micelle show significantly better anti-amoebic effects as compared to ITZ alone and thus should be investigated further in vivo to determine its clinical potential.
    MeSH terms: Alkynes; Humans; Micelles*; Polymers; Itraconazole/pharmacology; Acanthamoeba castellanii*
  4. Ong LT, Fan SWD
    Cardiol Young, 2024 Mar 04.
    PMID: 38433549 DOI: 10.1017/S1047951124000337
    OBJECTIVES: Hypertrophic cardiomyopathy is the leading cause of sudden cardiac death among the paediatric population. The aim of this study is to investigate the prevalence and clinical significance of late gadolinium enhancement, as assessed by cardiac MRI, in paediatric hypertrophic cardiomyopathy.

    METHODS: A systematic literature search was conducted in PubMed, SCOPUS, and Ovid SP to identify relevant studies. Pooled estimates with a 95% confidence interval were calculated using the random-effects generic inverse variance model. Statistical analysis was performed using Review Manager v5.4 and R programming.

    RESULTS: Seventeen studies were included in this meta-analysis, encompassing a total of 778 patients. Late gadolinium enhancement was highly prevalent in paediatric hypertrophic cardiomyopathy, with a pooled prevalence of 51% (95% confidence interval, 40-62%). The estimated extent of focal fibrosis expressed as a percentage of left ventricular mass was 4.70% (95% confidence interval, 2.11-7.30%). The presence of late gadolinium enhancement was associated with an increased risk of adverse cardiac events (pooled odds ratio 3.49, 95% confidence interval 1.10-11.09). The left ventricular mass index of late gadolinium enhancement-positive group was higher than the negative group, with a standardised mean difference of 0.91 (95% confidence interval, 0.42-1.41).

    CONCLUSION: This meta-analysis demonstrates that prevalence of late gadolinium enhancement in paediatric hypertrophic cardiomyopathy is similar to that in the adult population. The presence and extent of late gadolinium enhancement are independent predictors of adverse cardiac events, underscoring their prognostic significance among the paediatric population.

  5. Exélis MP, Ramli R, Abdul Latif SA, Idris AH, Clemente-Orta G, Kermorvant C
    Heliyon, 2024 Feb 29;10(4):e26105.
    PMID: 38434038 DOI: 10.1016/j.heliyon.2024.e26105
    Oecophylla smaragdina F., the Asian weaver ant, is one of the oil palm plantation's (Elaeis guineensis) potential predators, for the invasive bagworm species Metisa plana Walker, but this ant is a nuisance species that irritates plantation workers with their sharp bites. Here we assess the foraging activities (FA) of O. smaragdina's major workers, identify its inactive times and the existence of supervision, a novelty for social insects. Between 2018 and 2022, the pattern of trunk foraging activity was used as a mitigation measure. The relationship between trunk FA and air temperature (AT), relative humidity (RH), air pressure (AP), and rainfall interception (RI) was also investigated. Our results showed that, O. smaragdina is a strictly diurnal ant species, has little to no crepuscular activity, and stopped foraging during darkness. Moreover, veteran bigger workers systematically acted as supervisors by monitoring trails, intercepting, and bringing back to nests smaller individuals during heat peaks. In relation to population size relative abundance, all colonies displayed greater intensity during the warmest daily periods with higher mean forager density among the bigger colony, regardless of the dry-rainy intervals corresponded to minimal activity from late scotophase to early photophase and showed a bimodal pattern. Thus, forager activity peaked between 1100-1530 h and 1745-1845 h, and an average two-fold daily sudden decrease in intensity between 1620 and 1650 h as a partial cut-off period (first report). Furthermore, foraging activity, AT, AP showed a significant positive correlation while RH was negative. Finally, we found that from the base palm trunks, defensive territorial layers extended to 5 m on average with different spatial configurations indicating greater foraging density within the first 2 m. Our study shows O. smaragdina daily low activity periods, before 1000 h, being the most suitable to avoid forager attacks to facilitate pruning and harvesting tasks.
  6. Kamarudin R, Ang YZ, Topare NS, Ismail MN, Mustafa KF, Gunnasegaran P, et al.
    Heliyon, 2024 Mar 15;10(5):e26597.
    PMID: 38434285 DOI: 10.1016/j.heliyon.2024.e26597
    The generation of power and fuel sustainability that contributes to a cleaner output of exhaust gases is one of the most important objectives the world seeks. In this paper, oxyhydrogen gas is used to retrofit into a two-stroke engine. The water was electrolysed and generated a mixture of oxygen (O2) and hydrogen (H2) or known as oxyhydrogen (HHO) gas via an electrolytic dry cell generator. The HHO was retrofitted experimentally to investigate the engine emissions and exhaust gas temperature from a 1.5 kW gasoline engine. The engine was tested with different power ratings (84-720 W) to investigate the performance and emissions of the engine using gasoline followed by the addition of HHO. The emissions of CO and NOx were measured with different amounts of HHO added. The exhaust temperature was calculated as one of the variables to be considered in relation to pollution. The air-fuel ratios are varied from 12 to 20% in the experiment. The most appropriate air-fuel ratio needed to start the generator with the most environmentally friendly gas emission was analysed. The results showed that the addition of HHO to the engine is successful in reducing fuel consumption up to 8.9%. A higher percentage of HHO added also has improved the emissions and reduced exhaust gas temperature. In this study, the highest quantity of HHO added at 0.15% of the volume fraction reduced CO gas emission by up to 9.41%, NOx gas up to 4.31%, and exhaust gas temperature by up to 2.02%. Generally, adding oxyhydrogen gas has significantly reduced the emissions, and exhaust temperature and provided an eco-friendly environment.
  7. Butt S, Ramzan M, Wong WK, Chohan MA, Bazhair AH
    Heliyon, 2024 Mar 15;10(5):e26512.
    PMID: 38434319 DOI: 10.1016/j.heliyon.2024.e26512
    This paper proposes a nonlinear threshold cointegration framework to study how energy prices affect Malaysia's nominal exchange rate, considering the money supply, income, and interest rate. The study employs a threshold cointegration approach utilizing threshold autoregressive and momentum threshold autoregressive models. The momentum threshold vector error correction model determines the short-run adjustment of exchange rate deviation from the long-run equilibrium level. The findings reveal that the nonlinear adjustment process to capture the short-run deviation in the long-run equilibrium path is primarily influenced by energy prices, money supply, and interest rates. These results highlight the importance of considering the impact of energy prices on exchange rate policies when formulating and implementing economic policies in Malaysia. The findings can also be valuable for decision-makers to comprehend the future dynamics of exchange rates and make well-informed decisions.
  8. Zhu J, Zhou Y, Wei Y, Luo Q, Huang H
    Heliyon, 2024 Mar 15;10(5):e26427.
    PMID: 38434358 DOI: 10.1016/j.heliyon.2024.e26427
    For the classical multi-objective optimal power flow (MOOPF) problem, only traditional thermal power generators are used in power systems. However, there is an increasing interest in renewable energy sources and the MOOPF problem using wind and solar energy has been raised to replace part of the thermal generators in the system with wind turbines and solar photovoltaics (PV) generators. The optimization objectives of MOOPF with renewable energy sources vary with the study case. They are mainly a combination of 2-4 objectives from fuel cost, emissions, power loss and voltage deviation (VD). In addition, reasonable prediction of renewable power is a major difficulty due to the discontinuous, disordered and unstable nature of renewable energy. In this paper, the Weibull probability distribution function (PDF) and lognormal PDF are applied to evaluate the available wind and available solar power, respectively. In this paper, an enhanced multi-objective mayfly algorithm (NSMA-SF) based on non-dominated sorting and the superiority of feasible solutions is implemented to tackle the MOOPF problem with wind and solar energy. The algorithm NSMA-SF is applied to the modified IEEE-30 and standard IEEE-57 bus test systems. The simulation results are analyzed and compared with the recently reported MOOPF results.
  9. Abas MZ, Li K, Hairi NN, Choo WY, Wan KS
    J Public Health Res, 2024 Jan;13(1):22799036241231786.
    PMID: 38434578 DOI: 10.1177/22799036241231786
    BACKGROUND: The prevalence of diabetes in Malaysia is increasing, and identifying patients with higher risk of complications is crucial for effective management. The use of machine learning (ML) to develop prediction models has been shown to outperform non-ML models. This study aims to develop predictive models for Type 2 Diabetes (T2D) complications in Malaysia using ML techniques.

    DESIGN AND METHODS: This 10-year retrospective cohort study uses clinical audit datasets from Malaysian National Diabetes Registry from 2011 to 2021. T2D patients who received treatment in public health clinics in the southern region of Malaysia with at least two data points in 10 years are included. Patients with diabetes complications at baseline are excluded to ensure temporality between predictors and the target variable. Appropriate methods are used to address issues related to data cleaning, missing data imputation, data splitting, feature selection, and class imbalance. The study uses 7 ML algorithms, including logistic regression, support vector machine, k-nearest neighbours, decision tree, random forest, extreme gradient boosting, and light gradient boosting machine, to develop predictive models for four target variables: nephropathy, retinopathy, ischaemic heart disease, and stroke. Hyperparameter tuning is performed for each algorithm. The model training is performed using a stratified k-fold cross-validation technique. The best model for each algorithm is evaluated on a hold-out dataset using multiple metrics.

    EXPECTED IMPACT OF THE STUDY ON PUBLIC HEALTH: The prediction model may be a valuable tool for diabetes management and secondary prevention by enabling earlier interventions and optimal resource allocation, leading to better health outcomes.

  10. Sharan J, Shivakumar I, Shivakumar A, Kamal VK, Chaudhari PK, Challasany S, et al.
    J Oral Biol Craniofac Res, 2024;14(2):192-200.
    PMID: 38434677 DOI: 10.1016/j.jobcr.2024.02.005
    INTRODUCTION: This review synthesizes the available evidence pertinent to the effect of platelet-rich fibrin on the rate of orthodontic tooth movement during comprehensive orthodontic treatment.

    METHOD: This review followed the Preferred Reporting Items for Systematic Review and Meta-Analysis guidelines. Nine electronic databases were searched until January 2024 without restrictions, followed by a hand search of the reference lists. Controlled randomized split-mouth human studies assessing the effect of platelet-rich fibrin on the rate of orthodontic tooth movement were included. All relevant data from the included studies were extracted and pooled for qualitative and quantitative analysis. Risk-of-Bias was assessed using the Cochrane Risk of Bias tool. The certainty of the evidence was graded using the Grading of Recommendations, Assessment, Development, and Evaluation tool.

    RESULTS: From 515 studies, eleven randomized clinical trials were included for qualitative analysis and nine for quantitative analysis. The certainty of the evidence for these studies was low to moderate. The overall risk of bias for most studies was of some concern. The pooled estimate of the data from ten studies has a mean revealed difference of 1.31 (0.13-2.48) at a 95 % confidence interval with significant heterogeneity.

    CONCLUSIONS: This systematic review suggest that platelet-rich fibrin enhances the orthodontic tooth movement rate, but the evidence quality was moderate. Further, based on the currently available evidence, the effectiveness of platelet-rich fibrin on the acceleration of orthodontic tooth movement could not be fully established.

    TRIAL REGISTRATION: PROSPERO: (CRD42021261836).

  11. Vitamia C, Iftinan GN, Latarissa IR, Wilar G, Cahyanto A, Mohammed AFA, et al.
    Front Pharmacol, 2024;15:1353503.
    PMID: 38434698 DOI: 10.3389/fphar.2024.1353503
    Background: Recurrent Aphthous Stomatitis (RAS) is a common ulcerative disease of the oral mucosa which is characterized by pain, and recurrent lesions in the oral cavity. This condition is quite painful, causing difficulty in eating, speaking and swallowing. Topical medications have been used for this condition, but the obstacle in using topical medications is the difficulty of achieving drug effects due to saliva wash out. This problem can be overcome by film hydrogel formulation which can protect the ulcer and reduce the pain to some extent. α-mangostin is a xanthone isolated from the rind of the mangosteen fruit. One of the activities of α-mangostin is anti-inflammatory effects, which operate through the characteristic mechanism of inhibiting the inflammatory response. This protocol study aims to investigate the efficacy of an α-mangostin hydrogel film with a chitosan alginate base for recurrent aphthous stomatitis (RAS) in comparison with a placebo over a period of 7 days. Study design: This is a two-arm, double blinding, randomized controlled trial enrolling patients with RAS. The efficacy test of α-mangostin Hydrogel Film will be tested against the placebo. Patients with RAS will be allocated randomly into the two arms and the hydrogel film will be administered for 7 days. The diameter of ulcer and visual analog scale (VAS) score will be used as the primary efficacy endpoint. The outcome measure will be compared between the two arms at the baseline, day 3, day 5, and at the end of 7 days. Discussion: The purpose of this clinical research is to provide scientific evidence on the efficacy of α-mangostin hydrogel film with a chitosan alginate basis in treating recurrent aphthous stomatitis. The trial is expected to improve our capacity to scientifically confirm the anti-inflammatory effectiveness of α-mangostin compounds in a final formulation that is ready to use. Trial registration: NCT06039774 (14 September 2023).
  12. Romli R, Mohd Hashim S, Abd Rahman R, Chew KT, Mohamad EMW, Mohammed Nawi A
    Gynecol Oncol Rep, 2024 Apr;52:101349.
    PMID: 38435346 DOI: 10.1016/j.gore.2024.101349
    PURPOSE: Cervical cancer (CC) screening remains challenging, where the motivational focus towards utilizing CC screening services is rarely highlighted. This study aimed to understand the motivation to undergo CC screening from women and healthcare practitioners' perspectives based on Protection Motivation Theory (PMT).

    METHOD: This qualitative study used the nominal group technique (NGT) and in-depth interview (IDI), where the NGT participants were healthcare practitioners from various disciplines (n = 12). Nominal group discussions were conducted via Zoom and involved one moderator, facilitator and observer. The IDI was conducted via Google Meet among seven women who had been included based on purposive sampling. All nominal group discussions and interviews were transcribed, verbatim and underwent deductive thematic analysis.

    RESULTS: Healthcare practitioners emphasized input on CC knowledge of epidemiology, risk, etiology, nature, and outcome to encourage motivation. Women underlined their important role in the family, and reducing the negative perception as a motivational focus. Having living example of witnessing the CC patient dying and fear of stigma of cancer could be the driven force to undergo screening. Emphasis on the important of sufficient knowledge and correct the misconceptions towards screening could impart the motivation among women.

    CONCLUSIONS: The motivational focus was enriched by the differing perspectives of the healthcare practitioners and women. The findings can guide intervention program development towards enhancing CC screening in the future.

  13. Ahmad K, Anchah L, Ting CY, Lim SE
    Contemp Clin Trials Commun, 2024 Apr;38:101280.
    PMID: 38435429 DOI: 10.1016/j.conctc.2024.101280
    AIMS: This study presents a protocol for the Pharmacy Integrated Community Care (PICC) program, meticulously designed to enhance Hemoglobin A1c (HbA1c) levels and augment knowledge about diabetes mellitus (DM) among individuals diagnosed with Type 2 Diabetes Mellitus (T2DM) in the Sarawak State of Malaysia.

    METHODS: From 1 May to December 31, 2023, a prospective, multicenter, parallel-design randomised controlled trial will be conducted with two groups, each consisting of 47 participants. The intervention group will receive a structured, four-session group-based program guided by experienced pharmacists, focusing on medication adherence and diabetes management. The control group will follow the standard Diabetes Mellitus Adherence Clinic program. The primary outcomes of this study encompass enhancements in knowledge regarding diabetes medication management and adherence, followed by subsequent changes in HbA1c levels.

    CONCLUSIONS: The successful implementation of the PICC program holds promise for enhancing health outcomes in the T2DM population, potentially leading to more effective diabetes management initiatives and better health practices in the community.

    TRIAL REGISTRATION CLINICALTRIALSGOV IDENTIFIER: NCT05106231.

  14. Santhiran R, Varathan KD, Chiam YK
    PeerJ Comput Sci, 2024;10:e1821.
    PMID: 38435547 DOI: 10.7717/peerj-cs.1821
    Opinion mining is gaining significant research interest, as it directly and indirectly provides a better avenue for understanding customers, their sentiments toward a service or product, and their purchasing decisions. However, extracting every opinion feature from unstructured customer review documents is challenging, especially since these reviews are often written in native languages and contain grammatical and spelling errors. Moreover, existing pattern rules frequently exclude features and opinion words that are not strictly nouns or adjectives. Thus, selecting suitable features when analyzing customer reviews is the key to uncovering their actual expectations. This study aims to enhance the performance of explicit feature extraction from product review documents. To achieve this, an approach that employs sequential pattern rules is proposed to identify and extract features with associated opinions. The improved pattern rules total 41, including 16 new rules introduced in this study and 25 existing pattern rules from previous research. An average calculated from the testing results of five datasets showed that the incorporation of this study's 16 new rules significantly improved feature extraction precision by 6%, recall by 6% and F-measure value by 5% compared to the contemporary approach. The new set of rules has proven to be effective in extracting features that were previously overlooked, thus achieving its objective of addressing gaps in existing rules. Therefore, this study has successfully enhanced feature extraction results, yielding an average precision of 0.91, an average recall value of 0.88, and an average F-measure of 0.89.
  15. Hidayat T, Ahmad A, Ngo HC
    PeerJ Comput Sci, 2024;10:e1806.
    PMID: 38435549 DOI: 10.7717/peerj-cs.1806
    An implicational base is knowledge extracted from a formal context. The implicational base of a formal context consists of attribute implications which are sound, complete, and non-redundant regarding to the formal context. Non-redundant means that each attribute implication in the implication base cannot be inferred from the others. However, sometimes some attribute implications in the implication base can be inferred from the others together with a prior knowledge. Regarding knowledge discovery, such attribute implications should be not considered as new knowledge and ignored from the implicational base. In other words, such attribute implications are redundant based on prior knowledge. One sort of prior knowledge is a set of constraints that restricts some attributes in data. In formal context, constraints restrict some attributes of objects in the formal context. This article proposes a method to generate non-redundant implication base of a formal context with some constraints which restricting the formal context. In this case, non-redundant implicational base means that the implicational base does not contain all attribute implications which can be inferred from the others together with information of the constraints. This article also proposes a formulation to check the redundant attribute implications and encoding the problem into satisfiability (SAT) problem such that the problem can be solved by SAT Solver, a software which can solve a SAT problem. After implementation, an experiment shows that the proposed method is able to check the redundant attribute implication and generates a non-redundant implicational base of formal context with constraints.
  16. Shen L, Jiang L
    PeerJ Comput Sci, 2024;10:e1858.
    PMID: 38435553 DOI: 10.7717/peerj-cs.1858
    Managing user bias in large-scale user review data is a significant challenge in optimizing children's book recommendation systems. To tackle this issue, this study introduces a novel hybrid model that combines graph convolutional networks (GCN) based on bipartite graphs and neural matrix factorization (NMF). This model aims to enhance the precision and efficiency of children's book recommendations by accurately capturing user biases. In this model, the complex interactions between users and books are modeled as a bipartite graph, with the users' book ratings serving as the weights of the edges. Through GCN and NMF, we can delve into the structure of the graph and the behavioral patterns of users, more accurately identify and address user biases, and predict their future behaviors. Compared to traditional recommendation systems, our hybrid model excels in handling large-scale user review data. Experimental results confirm that our model has significantly improved in terms of recommendation accuracy and scalability, positively contributing to the advancement of children's book recommendation systems.
  17. Cherukuru P, Mustafa MB
    PeerJ Comput Sci, 2024;10:e1901.
    PMID: 38435554 DOI: 10.7717/peerj-cs.1901
    Speech enhancement algorithms are applied in multiple levels of enhancement to improve the quality of speech signals under noisy environments known as multi-channel speech enhancement (MCSE) systems. Numerous existing algorithms are used to filter noise in speech enhancement systems, which are typically employed as a pre-processor to reduce noise and improve speech quality. They may, however, be limited in performing well under low signal-to-noise ratio (SNR) situations. The speech devices are exposed to all kinds of environmental noises which may go up to a high-level frequency of noises. The objective of this research is to conduct a noise reduction experiment for a multi-channel speech enhancement (MCSE) system in stationary and non-stationary environmental noisy situations with varying speech signal SNR levels. The experiments examined the performance of the existing and the proposed MCSE systems for environmental noises in filtering low to high SNRs environmental noises (-10 dB to 20 dB). The experiments were conducted using the AURORA and LibriSpeech datasets, which consist of different types of environmental noises. The existing MCSE (BAV-MCSE) makes use of beamforming, adaptive noise reduction and voice activity detection algorithms (BAV) to filter the noises from speech signals. The proposed MCSE (DWT-CNN-MCSE) system was developed based on discrete wavelet transform (DWT) preprocessing and convolution neural network (CNN) for denoising the input noisy speech signals to improve the performance accuracy. The performance of the existing BAV-MCSE and the proposed DWT-CNN-MCSE were measured using spectrogram analysis and word recognition rate (WRR). It was identified that the existing BAV-MCSE reported the highest WRR at 93.77% for a high SNR (at 20 dB) and 5.64% on average for a low SNR (at -10 dB) for different noises. The proposed DWT-CNN-MCSE system has proven to perform well at a low SNR with WRR of 70.55% and the highest improvement (64.91% WRR) at -10 dB SNR.
  18. Li F, Majid NA, Ding S
    PeerJ Comput Sci, 2024;10:e1875.
    PMID: 38435555 DOI: 10.7717/peerj-cs.1875
    This article aims to address the challenge of predicting the salaries of college graduates, a subject of significant practical value in the fields of human resources and career planning. Traditional prediction models often overlook diverse influencing factors and complex data distributions, limiting the accuracy and reliability of their predictions. Against this backdrop, we propose a novel prediction model that integrates maximum likelihood estimation (MLE), Jeffreys priors, Kullback-Leibler risk function, and Gaussian mixture models to optimize LSTM models in deep learning. Compared to existing research, our approach has multiple innovations: First, we successfully improve the model's predictive accuracy through the use of MLE. Second, we reduce the model's complexity and enhance its interpretability by applying Jeffreys priors. Lastly, we employ the Kullback-Leibler risk function for model selection and optimization, while the Gaussian mixture models further refine the capture of complex characteristics of salary distribution. To validate the effectiveness and robustness of our model, we conducted experiments on two different datasets. The results show significant improvements in prediction accuracy, model complexity, and risk performance. This study not only provides an efficient and reliable tool for predicting the salaries of college graduates but also offers robust theoretical and empirical foundations for future research in this field.
External Links