MyMedR

Displaying all 4 publications

Abstract:

Sort:

Improved GART neural network model for pattern classification and rule extraction with application to power systems

Yap KS, Lim CP, Au MT

IEEE Trans Neural Netw, 2011 Dec;22(12):2310-23.
PMID: 22067292 DOI: 10.1109/TNN.2011.2173502

Generalized adaptive resonance theory (GART) is a neural network model that is capable of online learning and is effective in tackling pattern classification tasks. In this paper, we propose an improved GART model (IGART), and demonstrate its applicability to power systems. IGART enhances the dynamics of GART in several aspects, which include the use of the Laplacian likelihood function, a new vigilance function, a new match-tracking mechanism, an ordering algorithm for determining the sequence of training data, and a rule extraction capability to elicit if-then rules from the network. To assess the effectiveness of IGART and to compare its performances with those from other methods, three datasets that are related to power systems are employed. The experimental results demonstrate the usefulness of IGART with the rule extraction capability in undertaking classification problems in power systems engineering.
A hybrid ART-GRNN online learning neural network with a epsilon -insensitive loss function

Yap KS, Lim CP, Abidin IZ

IEEE Trans Neural Netw, 2008 Sep;19(9):1641-6.
PMID: 18779094 DOI: 10.1109/TNN.2008.2000992

In this brief, a new neural network model called generalized adaptive resonance theory (GART) is introduced. GART is a hybrid model that comprises a modified Gaussian adaptive resonance theory (MGA) and the generalized regression neural network (GRNN). It is an enhanced version of the GRNN, which preserves the online learning properties of adaptive resonance theory (ART). A series of empirical studies to assess the effectiveness of GART in classification, regression, and time series prediction tasks is conducted. The results demonstrate that GART is able to produce good performances as compared with those of other methods, including the online sequential extreme learning machine (OSELM) and sequential learning radial basis function (RBF) neural network models.
A feasibility study on preoperative carbohydrate loading in older patients undergoing hip fracture surgery

Yap KS, Loh PS, Foong YX, Mok CZ, Ong T, Khor HM

BMC Geriatr, 2024 May 06;24(1):401.
PMID: 38711010 DOI: 10.1186/s12877-024-04958-7

BACKGROUND: Preoperative carbohydrate loading in Enhanced Recovery After Surgery is an independent predictor of postoperative outcomes. By reducing the impact of surgical stress response, fasting-induced insulin resistance is modulated. As a clear fluid, consuming carbohydrate drink is safe up to 2 h preoperatively. Widely practiced in abdominal surgeries, its implementation in hip fracture surgeries is yet to be recognized. This study aimed to identify the feasibility of preoperative carbohydrate loading in hip fracture surgery and assess its clinical effects.
METHODS: This was a randomized controlled, open labelled trial. Patients ≥ 65 years old without diabetes mellitus, has hip fracture were recruited in a tertiary hospital between November 2020 and May 2021. The intervention was carbohydrate loading versus standard preoperative fasting.
RESULTS: Thirty-four ASA I-III patients (carbohydrate loading and control, n = 17 each), mean age 78 years (SEM ± 1.5), mean body mass index 23.7 (SEM ± 0.6 kg/m2) were recruited. Analysis for feasibility of carbohydrate loading (n = 17) demonstrated attrition rate of 29% (n = 5). Otherwise, all recruited patients were compliant (100% compliance) with no adverse events reported. There was no significant difference among groups in the postoperative nausea and vomiting, pain score, fatigue level, muscle strength, postoperative infection and length of hospital stay assessed at 24-48 h postoperatively.
CONCLUSION: The implementation of preoperative carbohydrate loading was found to be feasible preoperatively in hip fracture surgeries but requires careful coordination among multidisciplinary teams. An adequately powered randomized controlled study is needed to examine the full benefits of preoperative carbohydrate loading in this group of patients.
TRIAL REGISTRATION: This study was registered in ClinicalTrial.gov (ClinicalTrials.gov identifier: NCT04614181, date of registration: 03/11/2020).
Fulltext Mechanisms Underlying the Anti-Inflammatory Effects of Clinacanthus nutans Lindau Extracts: Inhibition of Cytokine Production and Toll-Like Receptor-4 Activation

Mai CW, Yap KS, Kho MT, Ismail NH, Yusoff K, Shaari K, et al.

Front Pharmacol, 2016;7:7.
PMID: 26869924 DOI: 10.3389/fphar.2016.00007

Clinacanthus nutans has had a long history of use in folk medicine in Malaysia and Southeast Asia; mostly in the relief of inflammatory conditions. In this study, we investigated the effects of different extracts of C. nutans upon lipopolysaccharide (LPS) induced inflammation in order to identify its mechanism of action. Extracts of leaves and stem bark of C. nutans were prepared using polar and non-polar solvents to produce four extracts, namely polar leaf extract (LP), non-polar leaf extract (LN), polar stem extract (SP), and non-polar stem extracts (SN). The extracts were standardized by determining its total phenolic and total flavonoid contents. Its anti-inflammatory effects were assessed on LPS induced nitrite release in RAW264.7 macrophages and Toll-like receptor (TLR-4) activation in TLR-4 transfected human embryonic kidney cells (HEK-Blue(TM)-hTLR4 cells). The levels of inflammatory cytokines (TNF-α, IFN-γ, IL-1β, IL-6, IL-12p40, and IL-17) in treated RAW264.7 macrophages were quantified to verify its anti-inflammatory effects. Western blotting was used to investigate the effect of the most potent extract (LP) on TLR-4 related inflammatory proteins (p65, p38, ERK, JNK, IRF3) in RAW264.7 macrophages. All four extracts produced a significant, concentration-dependent reduction in LPS-stimulated nitric oxide, LPS-induced TLR-4 activation in HEK-Blue(TM)-hTLR4 cells and LPS-stimulated cytokines production in RAW264.7 macrophages. The most potent extract, LP, also inhibited all LPS-induced TLR-4 inflammatory proteins. These results provide a basis for understanding the mechanisms underlying the previously demonstrated anti-inflammatory activity of C. nutans extracts.