Search

In the dynamic field of Customer Retention Prediction (CRP), strategic marketing and promotion efforts targeting specific customers are crucial. Understanding customer behavior and identifying churn indicators are vital for devising effective retention strategies. However, identifying customers likely to terminate services presents a challenge, leading to data imbalance issues. Existing CRP studies using Machine Learning (ML) techniques and data imbalance methods face problems such as overfitting and computational complexity. Similarly, recent CRP studies employing Deep Learning (DL) approaches rely on data sampling techniques, which can result in overfitting and a lack of cost sensitivity. Additionally, DL approaches struggle with slow convergence and get stuck in local minima. This paper introduces an effective hybrid of Deep Learning (DL) classifiers focusing on cost-metric integration to address data imbalance issues and period-shift Cosine Annealing Learning Rate (ps-CALR) to accelerate model training, ultimately enhancing performance. Three Telecom datasets, namely IBM, Iranian, and Orange, were used to assess the model performance. Empirical findings show that the hybrid DL classifiers significantly improved CRP over conventional ML. This paper contributes methodological advancements and practical insights for effective customer retention in the telecom industry.

Abstract Background Point-of-care testing (POCT) is commonly used in epidemiological surveys due to its various advantages, such as portability and immediate test results. The CardioChek® PA analyser 3-in-1 lipid panel measures total cholesterol (TC), triglyceride (TG), high-density lipoprotein (HDL) cholesterol and low-density lipoprotein (LDL) cholesterol. This study tested the reliability and diagnostic accuracy of the CardioChek® PA analyser using a 3-in-1 lipid panel. Methods A cross-sectional study design with quota sampling was used. A total of 203 respondents aged 18 years and above from a research centre in the Ministry of Health, Malaysia, were recruited. Venous blood was sent to the laboratory and tested with Siemens Atellica CH, while a POCT analyser was used for capillary blood measurements. Intraclass coefficient correlation (ICC) analysis was employed to determine the agreement between capillary and venous blood parameters. The diagnostic performance of the evaluated tests was evaluated using STATA version 12. Results The agreement between capillary and laboratory venous blood was moderate (0.64–0.67) for TC and HDL, good (0.75) for LDL and excellent (0.91) for TG). The sensitivity, specificity, positive predictive value (PPV) and negative predictive value (NPV) were as follows: TC, 57.1%, 94.3%, 92.3% and 64.8%; TG, 76.0%, 100%, 100%, and 96.6%; HDL, 96.2%, 83.2%, 47.2% and 99.3%; and LDL, 81.0%, 100%, 100% and 68.3%, respectively. Conclusions The CardioChek® PA analyser showed acceptable diagnostic accuracy for screening high-risk individuals more often in places where laboratories are inaccessible. It could also be used in clinical settings where patients would benefit from swift treatment decisions.

Abstract Peritoneal metastasis (PM), the regional progression of intra-abdominal malignancies, is a common sequelae of colorectal cancer (CRC). Immunotherapy is slated to be effective in generating long-lasting anti-tumour response as it utilizes the specificity and memory of the immune system. In the tumour microenvironment, tumour associated macrophages (TAMs) are posited to create an anti-inflammatory pro-tumorigenic environment. In this paper, we aimed to identify immunomodulatory factors associated with colorectal PM (CPM). A publicly available colorectal single cell database (GSE183916) was analysed to identify possible immunological markers that are associated with the activation of macrophages in cancers. Immunohistochemical analysis for V-set and immunoglobin containing domain 4 (VSIG4) expression was performed on tumour microarrays (TMAs) of tumours of colorectal origin (n = 211). Expression of VSIG4 in cell-free ascites obtained from CPM patients (n = 39) was determined using enzyme-linked immunosorbent assay (ELISA). CD163-positive TAMs cluster expression was extracted from a publicly available single cell database and evaluated for the top 100 genes. From these macrophage-expressed genes, VSIG4, a membrane protein produced by the M2 macrophages, mediates the up-regulation of anti-inflammatory and down-regulation of pro-inflammatory macrophages, contributing to an overall anti-inflammatory state. CRC TMA IHC staining showed that low expression of VSIG4 in stromal tissues of primary CRC are associated with poor prognosis (p = 0.0226). CPM ascites also contained varying concentrations of VSIG4, which points to a possible role of VSIG4 in the ascites. The contribution of VSIG4 to CPM development can be further evaluated for its potential as an immunotherapeutic agent.

This paper presents an analysis of various split-ring resonator (SRR) configurations coupled with coplanar waveguides (CPW). Three distinct resonant structures are presented, namely, the S-shaped split-ring resonator (S-SRR), the conventional split-ring resonator (SRR), and a pair of SRR. Among the examined resonant structures, it is observed that the S-SRR exhibits the smallest electrical size with the corresponding resonant frequency of 1.37 GHz, while the conventional SRR has the largest electrical size with the corresponding resonant frequency of 3.34 GHz. On the other hand, the resonant frequency of a dual SRR is 2.37 GHz. However, the transmission coefficient of a dual SRR is -11.43 dB, which is higher than S-SRR (-10.02 dB) and SRR (-8.18 dB). Furthermore, this study extends the analysis between a square dual SRR and a circular dual SRR with retained area. The square SRR demonstrates a lower resonance frequency (2.23 GHz) relative to its circular counterpart (2.37 GHz). The comparison also shows that the transmission coefficient of the square configuration is -13.88 dB, which is higher than its circular counterpart (-11.43 dB). The realization of a barcode application is achieved by loading multiple S-shaped split ring resonators (S-SRRs) with varying geometric parameters adjacently onto the transmission line. By individually rotating each of these S-SRRs, it becomes possible to alter the notch magnitude, thereby positioning it within a specific designated range corresponding to a particular code. In the case of a configuration involving rotations of (0°, 45°, 90°, 0°, 45°, 90°), this approach results in the creation of a barcode denoted as "100 010 000 100 011 000". This methodology enables the encoding of information in the form of distinctive resonant responses, providing a versatile and compact means of realizing barcode applications.

Abstract Erectile dysfunction (ED) is a pervasive problem among men, often shrouded in silence and stigma. This manuscript analysed the National Health and Morbidity Survey 2019 data to identify the prevalence of moderate to severe ED among men aged 18 and above in Malaysia and describe its associated factors. Self-administered questionnaire on ED utilised a locally validated International Index of Erectile Function. Variables on sociodemographics, risky lifestyles and comorbidities were obtained via an interviewer-administered questionnaire. The prevalence was determined using complex sampling analysis, and logistic regression was used to determine the associated factors of ED. A sample of 2403 men aged ≥ 18 participated, with a moderate to severe ED prevalence was 31.6% (95% CI 28.8, 34.6). The mean (± SD) of the total score of IIEF-5 for overall respondents was 18.16 (± 4.13). Multiple logistic regression analysis revealed a significant association between moderate to severe ED among men aged 60 years and above, single or divorcee, men without formal, primary, and secondary education, non-government employees, unemployed, and retiree, as well as physically inactive men. Focused public health interventions are necessary to improve education in sexual health, increase health promotion programs, and promote healthy ageing across the population.