Search

Customer churn prediction is vital for organizations to mitigate costs and foster growth. Ensemble learning models are commonly used for churn prediction. Diversity and prediction performance are two essential principles for constructing ensemble classifiers. Therefore, developing accurate ensemble learning models consisting of diverse base classifiers is a considerable challenge in this area. In this study, we propose two multi-objective evolutionary ensemble learning models based on clustering (MOEECs), which are include a novel diversity measure. Also, to overcome the data imbalance problem, another objective function is presented in the second model to evaluate ensemble performance. The proposed models in this paper are evaluated with a dataset collected from a mobile operator database. Our first model, MOEEC-1, achieves an accuracy of 97.30% and an AUC of 93.76%, outperforming classical classifiers and other ensemble models. Similarly, MOEEC-2 attains an accuracy of 96.35% and an AUC of 94.89%, showcasing its effectiveness in churn prediction. Furthermore, comparison with previous churn models reveals that MOEEC-1 and MOEEC-2 exhibit superior performance in accuracy, precision, and F-score. Overall, our proposed MOEECs demonstrate significant advancements in churn prediction accuracy and outperform existing models in terms of key performance metrics. These findings underscore the efficacy of our approach in addressing the challenges of customer churn prediction and its potential for practical application in organizational decision-making., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2024 Faraji Googerdchi et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Objectives: Hospital-acquired infections (HAIs) are significant problems as public health issues which need attention. Such infections are significant problems for society and healthcare organizations. This study aimed to carry out a systematic review and a meta-analysis to analyze the prevalence of HAIs globally., Methods: We conducted a comprehensive search of electronic databases including EMBASE, Scopus, PubMed and Web of Science between 2000 and June 2021. We found 7031 articles. After removing the duplicates, 5430 studies were screened based on the titles/ abstracts. Then, we systematically evaluated the full texts of the 1909 remaining studies and selected 400 records with 29,159,630 participants for meta-analysis. Random-effects model was used for the analysis, and heterogeneity analysis and publication bias test were conducted., Results: The rate of universal HAIs was 0.14 percent. The rate of HAIs is increasing by 0.06 percent annually. The highest rate of HAIs was in the AFR, while the lowest prevalence were in AMR and WPR. Besides, AFR prevalence in central Africa is higher than in other parts of the world by 0.27 (95% CI, 0.22-0.34). Besides, E. coli infected patients more than other micro-organisms such as Coagulase-negative staphylococci, Staphylococcus spp. and Pseudomonas aeruginosa. In hospital wards, Transplant, and Neonatal wards and ICU had the highest rates. The prevalence of HAIs was higher in men than in women., Conclusion: We identified several essential details about the rate of HAIs in various parts of the world. The HAIs rate and the most common micro-organism were different in various contexts. However, several essential gaps were also identified. The study findings can help hospital managers and health policy makers identify the reason for HAIs and apply effective control programs to implement different plans to reduce the HAIs rate and the financial costs of such infections and save resources., Competing Interests: The authors have declared that no competing interests exist., (Copyright: © 2023 Raoofi et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.)

Concerns about the negative effects of declining agricultural biodiversity due to modern agricultural practices and climatic constraints in various parts of the world, including Iran, on the sustainability of agricultural ecosystems are increasingly growing. However, the historical knowledge of temporal and spatial biodiversity is lacking. To determine the value and trend of crop diversity in Iran, we used biodiversity indices based on the area under rainfed and irrigated crops and total cropland area from 1991 to 2018. There were large fluctuations in the amount of cultivated area in the past 30 years, peaking around 2005 to 2007 with about 13.1 million cultivated hectares. However, no general trend in increase or decrease of total cultivated land was shown. The crop species diversity of irrigated cropland was higher than the rainfed and total cropland. The Shannon diversity index showed a constant trend with a negligible slope, but species richness was increased, which was related to the rise in the area of some crop species in recent years. The area of wheat and barley had a significant impact on crop diversity, so Shannon diversity index reduced with their dominance. Overall, this study revealed that the Iranian agricultural system relies on wheat and barley. We warn that by increasing the area of these crops and the prevalence of monoculture, the probability of damage from external factors such as sudden weather changes or the spread of diseases will increase, leading to instability and production risks in the future., Competing Interests: The authors have declared that no competing interests exist.

Previously, we demonstrated a strong correlation between the amplitude of human speech and the emission rate of micron-scale expiratory aerosol particles, which are believed to play a role in respiratory disease transmission. To further those findings, here we systematically investigate the effect of different 'phones' (the basic sound units of speech) on the emission of particles from the human respiratory tract during speech. We measured the respiratory particle emission rates of 56 healthy human volunteers voicing specific phones, both in isolation and in the context of a standard spoken text. We found that certain phones are associated with significantly higher particle production; for example, the vowel /i/ ("need," "sea") produces more particles than /ɑ/ ("saw," "hot") or /u/ ("blue," "mood"), while disyllabic words including voiced plosive consonants (e.g., /d/, /b/, /g/) yield more particles than words with voiceless fricatives (e.g., /s/, /h/, /f/). These trends for discrete phones and words were corroborated by the time-resolved particle emission rates as volunteers read aloud from a standard text passage that incorporates a broad range of the phones present in spoken English. Our measurements showed that particle emission rates were positively correlated with the vowel content of a phrase; conversely, particle emission decreased during phrases with a high fraction of voiceless fricatives. Our particle emission data is broadly consistent with prior measurements of the egressive airflow rate associated with the vocalization of various phones that differ in voicing and articulation. These results suggest that airborne transmission of respiratory pathogens via speech aerosol particles could be modulated by specific phonetic characteristics of the language spoken by a given human population, along with other, more frequently considered epidemiological variables., Competing Interests: The authors have declared that no competing interests exist.

Best investment in the road infrastructure or the network design is perceived as a fundamental and benchmark problem in transportation. Given a set of candidate road projects with associated costs, finding the best subset with respect to a limited budget is known as a bilevel Discrete Network Design Problem (DNDP) of NP-hard computationally complexity. We engage with the complexity with a hybrid exact-heuristic methodology based on a two-stage relaxation as follows: (i) the bilevel feature is relaxed to a single-level problem by taking the network performance function of the upper level into the user equilibrium traffic assignment problem (UE-TAP) in the lower level as a constraint. It results in a mixed-integer nonlinear programming (MINLP) problem which is then solved using the Outer Approximation (OA) algorithm (ii) we further relax the multi-commodity UE-TAP to a single-commodity MILP problem, that is, the multiple OD pairs are aggregated to a single OD pair. This methodology has two main advantages: (i) the method is proven to be highly efficient to solve the DNDP for a large-sized network of Winnipeg, Canada. The results suggest that within a limited number of iterations (as termination criterion), global optimum solutions are quickly reached in most of the cases; otherwise, good solutions (close to global optimum solutions) are found in early iterations. Comparative analysis of the networks of Gao and Sioux-Falls shows that for such a non-exact method the global optimum solutions are found in fewer iterations than those found in some analytically exact algorithms in the literature. (ii) Integration of the objective function among the constraints provides a commensurate capability to tackle the multi-objective (or multi-criteria) DNDP as well.

Mast cells are hematopoietically-derived tissue immune cells that participate in acquired and innate immunity, as well as in inflammation through release of many chemokines and cytokines, especially in response to the pro-inflammatory peptide substance P (SP). Inflammation is critical in the pathogenesis of many diseases, but the trigger(s) is often unknown. We investigated if mast cell stimulation leads to secretion of mitochondrial components and whether these could elicit autocrine and/or paracrine inflammatory effects. Here we show that human LAD2 mast cells stimulated by IgE/anti-IgE or by the SP led to secretion of mitochondrial particles, mitochondrial (mt) mtDNA and ATP without cell death. Mitochondria purified from LAD2 cells and, when mitochondria added to mast cells trigger degranulation and release of histamine, PGD(2), IL-8, TNF, and IL-1β. This stimulatory effect is partially inhibited by an ATP receptor antagonist and by DNAse. These results suggest that the mitochondrial protein fraction may also contribute. Purified mitochondria also stimulate IL-8 and vascular endothelial growth factor (VEGF) release from cultured human keratinocytes, and VEGF release from primary human microvascular endothelial cells. In order to investigate if mitochondrial components could be secreted in vivo, we injected rats intraperiotoneally (ip) with compound 48/80, which mimicks the action of SP. Peritoneal mast cells degranulated and mitochondrial particles were documented by transimission electron microscopy outside the cells. We also wished to investigate if mitochondrial components secreted locally could reach the systemic circulation. Administration ip of mtDNA isolated from LAD2 cells in rats was detected in their serum within 4 hr, indicating that extravascular mtDNA could enter the systemic circulation. Secretion of mitochondrial components from stimulated live mast cells may act as "autopathogens" contributing to the pathogenesis of inflammatory diseases and may be used as targets for novel treatments.

Mast cells are immune cells critical in the pathogenesis of allergic, but also inflammatory and autoimmune diseases through release of many pro-inflammatory cytokines such as IL-8 and TNF. Contact dermatitis and photosensitivity are skin conditions that involve non-immune triggers such as substance P (SP), and do not respond to conventional treatment. Inhibition of mast cell cytokine release could be effective therapy for such diseases. Unfortunately, disodium cromoglycate (cromolyn), the only compound marketed as a mast cell "stabilizer", is not particularly effective in blocking human mast cells. Instead, flavonoids are potent anti-oxidant and anti-inflammatory compounds with mast cell inhibitory actions. Here, we first compared the flavonoid quercetin (Que) and cromolyn on cultured human mast cells. Que and cromolyn (100 µM) can effectively inhibit secretion of histamine and PGD(2). Que and cromolyn also inhibit histamine, leukotrienes and PGD(2) from primary human cord blood-derived cultured mast cells (hCBMCs) stimulated by IgE/Anti-IgE. However, Que is more effective than cromolyn in inhibiting IL-8 and TNF release from LAD2 mast cells stimulated by SP. Moreover, Que reduces IL-6 release from hCBMCs in a dose-dependent manner. Que inhibits cytosolic calcium level increase and NF-kappa B activation. Interestingly, Que is effective prophylactically, while cromolyn must be added together with the trigger or it rapidly loses its effect. In two pilot, open-label, clinical trials, Que significantly decreased contact dermatitis and photosensitivity, skin conditions that do not respond to conventional treatment. In summary, Que is a promising candidate as an effective mast cell inhibitor for allergic and inflammatory diseases, especially in formulations that permit more sufficient oral absorption.

Stress affects immunity, but the mechanism is not known. Neurotensin (NT) and corticotropin-releasing hormone (CRH) are secreted under stress in various tissues, and have immunomodulatory actions. We had previously shown that NT augments the ability of CRH to increase mast cell-dependent skin vascular permeability in rodents. Here we show that NT triggered human mast cell degranulation and significantly augmented CRH-induced vascular endothelial growth factor (VEGF) release. Investigation of various signaling molecules indicated that only NF-κB activation was involved. These effects were blocked by pretreatment with the NTR antagonist SR48692. NT induced expression of CRH receptor-1 (CRHR-1), as shown by Western blot and FACS analysis. Interestingly, CRH also induced NTR gene and protein expression. These results indicate unique interactions among NT, CRH, and mast cells that may contribute to auto-immune and inflammatory diseases that worsen with stress.