Catalogue Search | MBRL
Are you sure you want to remove the book from the shelf?
{{itemTitle}}
6,775
result(s) for
"Ajay Kumar"
Sort by:
Recommendation of Machine Learning Techniques for Software Effort Estimation using Multi-Criteria Decision Making
For the development of the software industry, Software Effort Estimation (SEE) is one of the essential tasks. Project managers can overcome budget and time overrun issues by accurately estimating a software project's development effort in the software life cycle. In prior studies, a variety of machine learning methods for SEE modeling were applied. The outcomes for various performance or accuracy measures are inconclusive. Therefore, a mechanism for assessing machine learning approaches for SEE modeling in the context of several contradictory accuracy measures is desperately needed. This study addresses selecting the most appropriate machine learning technique for SEE modeling as a Multi-Criteria Decision Making (MCDM) problem. The machine learning techniques are selected through a novel approach based on MCDM. In the proposed approach, three MCDM methods- Weighted Aggregated Sum Product Assessment (WASPAS), Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), and VIseKriterijumska Optimizacija I Kompromisno Resenje (VIKOR) were applied to determine the ranking of machine learning techniques on SEE performance based on multiple conflicting accuracy measures. For validating the proposed method, an experimental study was conducted over three SEE datasets using ten machine-learning techniques and six performance measures. Based on MCDM rankings, Random Forest, Support Vector Regression, and Kstar are recommended as the most appropriate machine learning techniques for SEE modeling. The results show how effectively the suggested MCDM-based approach can be used to recommend the appropriate machine learning technique for SEE modeling while considering various competing accuracy or performance measures altogether.
Journal Article
Effect of glycemic control and type of diabetes treatment on unsuccessful TB treatment outcomes among people with TB-Diabetes: A systematic review
Stringent glycemic control by using insulin as a replacement or in addition to oral hypoglycemic agents (OHAs) has been recommended for people with tuberculosis and diabetes mellitus (TB-DM). This systematic review (PROSPERO 2016:CRD42016039101) analyses whether this improves TB treatment outcomes.
Among people with drug-susceptible TB and DM on anti-TB treatment, to determine the effect of i) glycemic control (stringent or less stringent) compared to poor glycemic control and ii) insulin (only or with OHAs) compared to 'OHAs only' on unsuccessful TB treatment outcome(s). We looked for unfavourable TB treatment outcomes at the end of intensive phase and/or end of TB treatment (minimum six months and maximum 12 months follow up). Secondary outcomes were development of MDR-TB during the course of treatment, recurrence after 6 months and/or after 1 year post successful treatment completion and development of adverse events related to glucose lowering treatment (including hypoglycemic episodes).
All interventional studies (with comparison arm) and cohort studies on people with TB-DM on anti-TB treatment reporting glycemic control, DM treatment details and TB treatment outcomes were eligible. We searched electronic databases (EMBASE, PubMed, Google Scholar) and grey literature between 1996 and April 2017. Screening, data extraction and risk of bias assessment were done independently by two investigators and recourse to a third investigator, for resolution of differences.
After removal of duplicates from 2326 identified articles, 2054 underwent title and abstract screening. Following full text screening of 56 articles, nine cohort studies were included. Considering high methodological and clinical heterogeneity, we decided to report the results qualitatively and not perform a meta-analysis. Eight studies dealt with glycemic control, of which only two were free of the risk of bias (with confounder-adjusted measures of effect). An Indian study reported 30% fewer unsuccessful treatment outcomes (aOR (0.95 CI): 0.72 (0.64-0.81)) and 2.8 times higher odds of 'no recurrence' (aOR (0.95 CI): 2.83 (2.60-2.92)) among patients with optimal glycemic control at baseline. A Peruvian study reported faster culture conversion among those with glycemic control (aHR (0.95 CI): 2.2 (1.1,4)). Two poor quality studies reported the effect of insulin on TB treatment outcomes.
We identified few studies that were free of the risk of bias. There were limited data and inconsistent findings among available studies. We recommend robustly designed and analyzed studies including randomized controlled trials on the effect of glucose lowering treatment options on TB treatment outcomes.
Journal Article
Advances in hydrology and climate change : historical trends and new approaches in water resources management
\"Advances in Hydrology and Climate Change: Historical Trends and New Approaches in Water Resources Management highlights recent trends in the water sector that employ a variety of different innovative management and conservation approaches. The volume provides an informative overview of the issues and challenges in water resources affected by climate change conditions, such as drought, flooding, glacier changes, and overbuilt-up urban areas. Focusing on surface and groundwater related issues and sustainable solutions, the chapters present a variety of methods, including morphometric assessment, parameter estimation, long-term trend analysis, sustainability indexes, storm water management models (SWMM), entropy-based measurement of long-term precipitation, etc. The volume focuses on providing a better understanding of climatic uncertainty through hydrometeorological data sets and their application in hydrological modeling. These analyses help to serve as the basis for the design of flood-control and water-usage management policies. The chapters discuss climatic variability that depends on several factors, i.e., its erratic distribution, topography, seasonal variation, land-use change, anthropogenic activities, etc., demonstrating the overall interconnection between different parameters of hydrological cycles to design modeling approaches that include using soft-computing applications, remote sensing and GIS-based techniques, artificial neural networks, and more. This book will be a standard reference work for disciplines in water resources, soil and water engineering, engineering hydrology, groundwater hydrology, climate change, agrometeorology, agriculture, lohani, anil ecology and environmental science, leading to a way forward for strategy formulation for combating hydrology and climate change\"-- Provided by publisher.
Book
A Neuro-Fuzzy Hybridized Approach for Software Reliability Prediction
Context: Reliability prediction is critical for software engineers in the current challenging scenario of increased demand for high-quality software. Even though various software reliability prediction models have been established so far, there is always a need for a more accurate model in today's competitive environment for producing high-quality software. Objective: This paper proposes a neuro-fuzzy hybridized method by integrating self-organized- map (SOM) and fuzzy time series (FTS) forecasting for the reliability prediction of a software system. Methodology: In the proposed approach, a well-known supervised clustering algorithm SOM is incorporated with FTS forecasting for developing a hybrid model for software reliability prediction. To validate the proposed approach, an experimental study is done by applying proposed neuro-fuzzy method on a software failure dataset. In addition, a comparative study was conducted for evaluating the performance of the proposed method by comparing it with some of the existing FTS models. Results: Experimental outcomes show that the proposed approach performs better than the existing FTS models. Conclusion: The results show that the proposed approach can be used efficiently in the software industry for software reliability prediction.
Journal Article
Effect of glycemic control and type of diabetes treatment on TB treatment outcomes among people with TB-diabetes: A systematic review (updated August 2024)
Stringent glycemic control and/or using insulin either as a replacement for or in addition to oral hypoglycemic agents (OHAs) has been recommended for people with tuberculosis and diabetes mellitus (TB-DM). This systematic review (PROSPERO 2016:CRD42016039101) analyses whether this improves TB treatment outcomes. This is an updated review (up to August 2024) of a previously published systematic review (1996 - April 2017).
Among people with drug-susceptible TB-DM on anti-TB treatment, to determine the effect of i) glycemic control (stringent or less stringent) compared to poor glycemic control and ii) insulin (only or with OHAs) compared to 'OHAs only' on unfavorable TB treatment outcome(s) at the end of intensive phase and/ or end of TB treatment (minimum six months and maximum 12 months follow up).
We conducted comprehensive searches across multiple databases (EMBASE, PubMed, Google Scholar, Cochrane Database of Systematic Reviews) and sources. Eligible studies included interventional and cohort studies examining people with TB-DM. Screening, data extraction and risk of bias assessment were done independently by two investigators and recourse to a third investigator, for resolution of differences.
From a total of 7107 articles, we included 14 studies, with five added in this update (all observational cohort studies). Of 14, only one high-quality study reported that stringent glycemic control (HbA1c < 7% at baseline) was associated with lower risk of unfavorable treatment outcomes, including recurrence, compared to non-stringent and/or poor glycemic control. Other studies showed mixed results and had significant biases or were limited by sample size. The five newly included studies had a high risk of bias and did not provide clear evidence. Due to clinical and methodological heterogeneity, we did not perform a meta-analysis.
The updated review re-emphasizes the need for high-quality research on the effects of glycemic control and addition of insulin among people with TB-DM on TB treatment outcomes. We need well-designed randomized controlled trials, specifically for the effect of adding insulin on TB treatment outcomes. We discuss ten measures to guide well-designed cohort studies on this topic. Harmonization of the methods is needed and would facilitate comparisons.
Journal Article
Feasibility, enablers and challenges of using timeliness metrics for household contact tracing and TB preventive therapy in Pakistan
Screening household contacts of TB patients and providing TB preventive therapy (TPT) is a key intervention to end the TB epidemic. Global and timely implementation of TPT in household contacts, however, is dismal. We adapted the 7-1-7 timeliness metric designed to evaluate and respond to infectious disease outbreaks or pandemics, and assessed the feasibility, enablers and challenges of implementing this metric for screening and management of household contacts of index patients with bacteriologically-confirmed pulmonary TB in Karachi city, Pakistan.
We conducted an explanatory mixed methods study with a quantitative component (cohort design) followed by a qualitative component (descriptive design with focus group discussions).
From January-June 2023, 92% of 450 index patients had their household contacts line-listed within seven days of initiating anti-TB treatment (\"first 7\"). In 84% of 1342 household contacts, screening outcomes were ascertained within one day of line-listing (\"next 1\"). In 35% of 256 household contacts eligible for further evaluation by a medical officer (aged ≤5 years or with chest symptoms), anti-tuberculosis treatment, TPT or a decision for no drugs was made within seven days of symptom screening (\"second 7\"). The principal reason for not starting anti-tuberculosis treatment or TPT was failure to consult a medical officer: only 129(50%) of 256 contacts consulted a medical officer. Reasons for poor performance in the \"second 7\" component included travel costs to see a medical officer, loss of daily earnings and fear of a TB diagnosis. Field staff reported that timeliness metrics motivated them to take prompt action in household contact screening and TPT provision and they suggested these be included in national guidelines.
Field staff found \"7-1-7\" timeliness metrics to be feasible and useful. Integration of these metrics into national guidelines could improve timeliness of diagnosis, treatment and prevention of TB within households of index patients.
Journal Article
HIV testing uptake and HIV positivity among presumptive tuberculosis patients in Mandalay, Myanmar, 2014-2017
The World Health Organization's framework for TB/HIV collaborative activities recommends provider-initiated HIV testing and counselling (PITC) of patients with presumptive TB. In Myanmar, PITC among presumptive TB patients was started at the TB outpatient department (TB OPD) in Mandalay in 2014. In this study, we assessed the uptake of PITC among presumptive TB patients and the number needed to screen to find one additional HIV positive case, stratified by demographic and clinical characteristics. This was a cross-sectional study using routinely collected data of presumptive TB patients who registered for PITC services at the TB OPD between August 2014 and December 2017 in Mandalay. Among 21,989 presumptive TB patients registered, 9,796 (44.5%) had known HIV status at registration and 2,763 (28.2%) were people already living with HIV (PLHIV). Of the remainder, 85.3% (10,401/12,193) were newly tested for HIV. Patients <55 years old, those registered in 2014, 2015 and 2017, those employed and those having a history of TB contact had higher uptakes of HIV testing. Among 10,401 patients tested for HIV, 213 (2.1%) patients were newly diagnosed with HIV and this included 147 (69.0%) who were not diagnosed as having TB. The overall prevalence of HIV (previously known and newly diagnosed) among presumptive TB patients was 14.8% (2,976/20,119). The number needed to screen to find one additional HIV case was 48: this number was lower (i.e., a higher yield) among patients aged 35-44 years and among those who were divorced or separated. Uptake of HIV testing among eligible presumptive TB patients was high with four out of five presumptive TB patients being tested for HIV. This strategy detected many additional HIV-positive persons, and this included those who were not diagnosed with TB. We strongly recommend that this strategy be implemented nationwide in Myanmar.
Journal Article
Modeling the spectrum and determinants of multimorbidity risk among older adults in India
India is passing through a parallel phase of demographic and epidemiological transition coupled with the shifting burden of multimorbidity. Unhealthy ageing and escalating morbidity burden have been identified as key drivers of this shifting multimorbidity risk among older adults in India. This study aims to assess the distribution of morbidities and multimorbidity, provide new estimates of multimorbidity risk by socio-economic and demographic factors and further evaluate the multimorbidity count risk conditioned on leading factors.
This study used the nationally representative Longitudinal Ageing Study in India (LASI), Wave - 1, 2017-18, data of individuals aged 45 years and above. First, we assessed the relative proportional share of morbidities and compositions of multimorbidity counts over age. Second, we applied the Random Forest (RF) model to estimate the age-specific risk of multimorbidity susceptibility associated with socio-economic and demographic factors over age. Finally, conditional plots were constructed to assess the distributional composition of the leading factors affecting multimorbidity counts.
The prevalence of multimorbidity was 43.20%. Eye disorders, followed by cardiovascular disease (CVDs), had the highest proportional share over age. Endocrine diseases, Gastrointestinal Conditions, and Infectious diseases showed a concordant decreasing proportional share in later age. The relative share of five or more multimorbidity counts increased significantly with age. The median expected risk of multimorbidity was significantly higher in females (66 years) than in males (71 years). The study also provides empirical evidence that individuals with higher levels of education, obesity, currently working, and poor childhood health were more prone to higher risk of multimorbidity at an early age. Furthermore, obesity was significantly associated with early multimorbidity onset and led to a pronounced escalation of complex multimorbidity progression, particularly in females.
Collective public health interventions are crucial to address early multimorbidity onset and burden disparities, to promote healthier ageing, and to address etiological factors.
Journal Article