Search results for: predicting judgements

Authors: Carol Anne Hargreaves

Abstract:

A key issue in stock investment is how to select representative features for stock selection. The objective of this paper is to firstly determine whether an automated stock investment system, using machine learning techniques, may be used to identify a portfolio of growth stocks that are highly likely to provide returns better than the stock market index. The second objective is to identify the technical features that best characterize whether a stock’s price is likely to go up and to identify the most important factors and their contribution to predicting the likelihood of the stock price going up. Unsupervised machine learning techniques, such as cluster analysis, were applied to the stock data to identify a cluster of stocks that was likely to go up in price – portfolio 1. Next, the principal component analysis technique was used to select stocks that were rated high on component one and component two – portfolio 2. Thirdly, a supervised machine learning technique, the logistic regression method, was used to select stocks with a high probability of their price going up – portfolio 3. The predictive models were validated with metrics such as, sensitivity (recall), specificity and overall accuracy for all models. All accuracy measures were above 70%. All portfolios outperformed the market by more than eight times. The top three stocks were selected for each of the three stock portfolios and traded in the market for one month. After one month the return for each stock portfolio was computed and compared with the stock market index returns. The returns for all three stock portfolios was 23.87% for the principal component analysis stock portfolio, 11.65% for the logistic regression portfolio and 8.88% for the K-means cluster portfolio while the stock market performance was 0.38%. This study confirms that an automated stock investment system using machine learning techniques can identify top performing stock portfolios that outperform the stock market.

Keywords: machine learning, stock market trading, logistic regression, cluster analysis, factor analysis, decision trees, neural networks, automated stock investment system

Procedia PDF Downloads 135

Authors: Shyaka Eugene

Abstract:

The efficient and safe demolition of structures is a critical challenge in civil engineering and construction. This study focuses on the development of optimal demolition strategies by investigating the crack propagation behavior in beams induced by soundless cracking agents. It is commonly used in controlled demolition and has gained prominence due to its non-explosive and environmentally friendly nature. This research employs a comprehensive experimental and computational approach to analyze the crack initiation, propagation, and eventual failure in beams subjected to soundless cracking agents. Experimental testing involves the application of various cracking agents under controlled conditions to understand their effects on the structural integrity of beams. High-resolution imaging and strain measurements are used to capture the crack propagation process. In parallel, numerical simulations are conducted using advanced finite element analysis (FEA) techniques to model crack propagation in beams, considering various parameters such as cracking agent composition, loading conditions, and beam properties. The FEA models are validated against experimental results, ensuring their accuracy in predicting crack propagation patterns. The findings of this study provide valuable insights into optimizing demolition strategies, allowing engineers and demolition experts to make informed decisions regarding the selection of cracking agents, their application techniques, and structural reinforcement methods. Ultimately, this research contributes to enhancing the safety, efficiency, and sustainability of demolition practices in the construction industry, reducing environmental impact and ensuring the protection of adjacent structures and the surrounding environment.

Keywords: expansion pressure, energy release rate, soundless chemical demolition agent, crack propagation

Procedia PDF Downloads 42

Authors: N. Alias, W. Z. W. Muhammad, M. N. M. Ibrahim, M. Mohamed, H. F. S. Saipol, U. N. Z. Ariffin, N. A. Zakaria, M. S. Z. Suardi

Abstract:

This paper presents the performance comparison of some computation software for solving the boundary element method (BEM). BEM formulation is the numerical technique and high potential for solving the advance mathematical modeling to predict the production of oil well in arbitrarily shaped based on multiple leases reservoir. The limitation of data validation for ensuring that a program meets the accuracy of the mathematical modeling is considered as the research motivation of this paper. Thus, based on this limitation, there are three steps involved to validate the accuracy of the oil production simulation process. In the first step, identify the mathematical modeling based on partial differential equation (PDE) with Poisson-elliptic type to perform the BEM discretization. In the second step, implement the simulation of the 2D BEM discretization using COMSOL Multiphysic and MATLAB programming languages. In the last step, analyze the numerical performance indicators for both programming languages by using the validation of Fortran programming. The performance comparisons of numerical analysis are investigated in terms of percentage error, comparison graph and 2D visualization of pressure on oil production of multiple leases reservoir. According to the performance comparison, the structured programming in Fortran programming is the alternative software for implementing the accurate numerical simulation of BEM. As a conclusion, high-level language for numerical computation and numerical performance evaluation are satisfied to prove that Fortran is well suited for capturing the visualization of the production of oil well in arbitrarily shaped.

Keywords: performance comparison, 2D visualization, COMSOL multiphysic, MATLAB, Fortran, modelling and simulation, boundary element method, reservoir pressure

Procedia PDF Downloads 472

Authors: Mohamed Elghorab, Vendra C. Madhav Rao, Jennifer X. Wen

Abstract:

Turbulence modelling is still evolving, and efforts are on to improve and develop numerical methods to simulate the real turbulence structures by using the empirical and experimental information. The monotonically integrated large eddy simulation (MILES) is an attractive approach for modelling turbulence in high Re flows, which is based on the solving of the unfiltered flow equations with no explicit sub-grid scale (SGS) model. In the current work, this approach has been used, and the action of the SGS model has been included implicitly by intrinsic nonlinear high-frequency filters built into the convection discretization schemes. The MILES solver is developed using the opensource CFD OpenFOAM libraries. The role of flux limiters schemes namely, Gamma, superBee, van-Albada and van-Leer, is studied in predicting turbulent statistical quantities for a fully developed channel flow with a friction Reynolds number, Re_T = 180, and compared the numerical predictions with the well-established Direct Numerical Simulation (DNS) results for studying the wall generated turbulence. It is inferred from the numerical predictions that Gamma, van-Leer and van-Albada limiters produced more diffusion and overpredicted the velocity profiles, while superBee scheme reproduced velocity profiles and turbulence statistical quantities in good agreement with the reference DNS data in the streamwise direction although it deviated slightly in the spanwise and normal to the wall directions. The simulation results are further discussed in terms of the turbulence intensities and Reynolds stresses averaged in time and space to draw conclusion on the flux limiter schemes performance in OpenFOAM context.

Keywords: flux limiters, implicit SGS, MILES, OpenFOAM, turbulence statistics

Procedia PDF Downloads 165

Authors: Dong Wu, Michael Grenn

Abstract:

Managing software projects effectively is crucial for meeting deadlines, ensuring quality, and managing resources well. Traditional methods often struggle with predicting project timelines accurately due to uncertain schedules and complex data. This study addresses these challenges by combining time prediction algorithms with Large Language Models (LLMs). It makes use of real-world software project data to construct and validate a model. The model takes detailed project progress data such as task completion dynamic, team Interaction and development metrics as its input and outputs predictions of project timelines. To evaluate the effectiveness of this model, a comprehensive methodology is employed, involving simulations and practical applications in a variety of real-world software project scenarios. This multifaceted evaluation strategy is designed to validate the model's significant role in enhancing forecast accuracy and elevating overall management efficiency, particularly in complex software project environments. The results indicate that the integration of time prediction algorithms with LLMs has the potential to optimize software project progress management. These quantitative results suggest the effectiveness of the method in practical applications. In conclusion, this study demonstrates that integrating time prediction algorithms with LLMs can significantly improve the predictive accuracy and efficiency of software project management. This offers an advanced project management tool for the industry, with the potential to improve operational efficiency, optimize resource allocation, and ensure timely project completion.

Keywords: software project management, time prediction algorithms, large language models (LLMS), forecast accuracy, project progress prediction

Procedia PDF Downloads 56

Authors: Emmanuelle Maria, Pierre Crançon, Gaëtane Lespes

Abstract:

The knowledge of uranium migration processes within underground environments is a major issue in the environmental risk assessment associated with nuclear activities. This process is identified as strongly controlled by adsorption mechanisms, thus leading to strongly delayed migration paths. Colloidal ligands are likely to significantly increase the mobility of uranium in natural environments. The ability of colloids to mobilize and transport uranium depends on their origin, their nature, their structure, their stability and their reactivity with uranium. Thus, the colloidal mobilization and transport properties are often described as site-specific. In this work, the colloidal phases of two leachates obtained from two different horizons of the same podzolic soil were characterized with a speciation approach. For this purpose, a multi-technique strategy was used, based on Field-Flow Fractionation coupled to Ultraviolet, Multi-Angle Light Scattering and Inductively Coupled Plasma Mass Spectrometry (AF4-UV-MALS-ICPMS), Transmission Electron Microscopy (TEM), Electrospray Ionization Orbitrap Mass Spectrometry (ESI-Orbitrap), and Time-Resolved Laser Fluorescence Spectroscopy (TRLFS-EEM). Thus, elemental composition, size distribution, microscopic structure, colloidal stability and possible organic and/or inorganic content of colloids were determined, as well as their association with uranium. The leachates exhibit differences in their physical and chemical characteristics, mainly in the nature of organic matter constituents. The multi-technique investigation strategy used provides original data about colloidal phase structure and composition, offering a new vision of the way the uranium can be mobilized and transported in the considered soil. This information is a real significant contribution opening the way to our understanding and predicting of the colloidal transport.

Keywords: colloids, migration, multi-technique, speciation, transport, uranium

Procedia PDF Downloads 128

Authors: Rewadee Watakakosol, Arunya Tuicomepee, Panrapee Suttiwan, Sakkaphat T. Ngamake

Abstract:

Health problems caused by alcohol consumption not only have short-term effects at the time of drinking but also leave long-lasting health conditions. Teenagers who start drinking in their middle-high or high school years or before entering college have higher likelihood to increase their alcohol use and abuse, and they were found to be less healthy compared with their non-drinking peers when entering adulthood. This study aimed to examine factors that predict intention and readiness to reduce and quit alcohol consumption among Thai teenagers. Participants were 826 high-school and vocational school students, most of whom were females (64.4%) with the average age of 16.4 (SD = 0.9) and the average age of first drinking at 13.7 (SD = 2.2). Instruments included the scales that developed based on the Theory of Planned Behaviour theoretical framework. They were the Attitude toward Alcohol Reduction and Cessation Scale, Normative Group and Influence Scale, Perceived Behavioral Control toward Alcohol Reduction and Cessation Scale, Behavioral Intent toward Alcohol Reduction and Cessation Scale, and Readiness to Reduce and Quit Alcohol Consumption Scale. Findings revealed that readiness to reduce / quit alcohol was the most powerful predictive factor (β=. 53, p < .01), followed by attitude of easiness in alcohol reduction and cessation (β=.46, p < .01), perceived behavioral control toward alcohol reduction and cessation (β =.41, p < .01), normative group and influence (β=.15, p < .01), and attitude of being accepted from alcohol reduction and cessation (β = -.12, p < .01), respectively. Attitude of improved health after alcohol reduction and cessation did not show statistically significantly predictive power. All factors significantly predict teenagers’ alcohol reduction and cessation behavior and accounted for 59 percent of total variance of alcohol consumption reduction and cessation.

Keywords: alcohol consumption reduction and cessation, intention, readiness to change, Thai teenagers

Procedia PDF Downloads 312

Authors: Xianping Du, Runlu Miao, Guanjun Zhang, Libo Cao, Feng Zhu

Abstract:

Current vehicle safety standards and human body injury criteria were established based on the biomechanical response of Euro-American human body, without considering the difference in the body anthropometry and injury characteristics among different races, particularly the East Asian people with smaller body size. Absence of such race specific design considerations will negatively influence the protective performance of safety products for these populations, and weaken the accuracy of injury thresholds derived. To resolve these issues, in this study, we aim to develop a race specific finite element model to simulate the impact response of the lower extremity of a 50th percentile East Asian (Chinese) male. The model was built based on medical images for the leg of an average size Chinese male and slightly adjusted based on the statistical data. The model includes detailed anatomic features and is able to simulate the muscle active force. Thirteen biomechanical tests available in the literature were used to validate its biofidelity. Using the validated model, a pedestrian-car impact accident taking place in China was re-constructed computationally. The results show that the newly developed lower leg model has a good performance in predicting dynamic response and tibia fracture pattern. An additional comparison on the fracture tolerance of the East Asian and Euro-American lower limb suggests that the current injury criterion underestimates the degree of injury of East Asian human body.

Keywords: lower limb, East Asian body characteristics, traffic accident reconstruction, finite element analysis, injury tolerance

Procedia PDF Downloads 267

Authors: Neslihan Sahin Celik, Ali Eraslan

Abstract:

Mathematical model and modeling are one of the topics that have been intensively discussed in recent years. In line with the results of the PISA studies, researchers in many countries have begun to question how much students in school-education system are prepared to solve the real-world problems they encounter in their future professional lives. As a result, many mathematics educators have begun to emphasize the importance of new skills and understanding such as constructing, Hypothesizing, Describing, manipulating, predicting, working together for complex and multifaceted problems for success in beyond the school. When students increasingly face this kind of situations in their daily life, it is important to make sure that students have enough experience to work together and interpret mathematical situations that enable them to think in different ways and share their ideas with their peers. Thus, model eliciting activities are one of main tools that help students to gain experiences and the new skills required. This research study was carried on the town center of a big city located in the Black Sea region in Turkey. The participants were eighth-grade students in a middle school. After a six-week preliminary study, three students in an eighth-grade classroom were selected using criterion sampling technique and placed in a focus group. The focus group of three students was videotaped as they worked on a model eliciting activity, the Summer Job Problem. The conversation of the group was transcribed, examined with students’ written work and then qualitatively analyzed through the lens of Blum’s (1996) modeling processing cycle. The study results showed that eighth grade students can successfully work with the model eliciting, develop a model based on the two parameters and review the whole process. On the other hand, they had difficulties to relate parameters to each other and take all parameters into account to establish the model.

Keywords: middle school, modeling, mathematical modeling, summer job problem

Procedia PDF Downloads 319

Authors: Shiran Bord, Assaf Oshri, Matthew W. Carlson, Sihong Liu

Abstract:

Background: Alcohol-impaired driving (AID) and binge drinking are major health concerns among college students. Although the link between binge drinking and AID is well established, knowledge regarding binge drinking patterns, the factors influencing binge drinking, and the associations between consumption patterns and alcohol-related risk behaviors is lacking. Aims: To examine heterogeneous trajectories of binge drinking during college and tests factors that might predict class membership as well as class membership outcomes. Methods: Data were obtained from a sample of 1,265 college students (Mage = 18.5, SD = .66) as part of the Longitudinal Study of Violence Against Women (N = 1,265; 59.3% female; 69.2% white). Analyses were completed in three stages. First, a growth curve analysis was conducted to identify trajectories of binge drinking over time. Second, growth curve mixture modeling analyses were pursued to assess unobserved growth trajectories of binge drinking without predictors. Lastly, parental drinking variables were added to the model as predictors of class membership, and AID and being a passenger of a drunk driver were added to the model as outcomes. Results: Three binge drinking trajectories were identified: high-convex, medium concave and low-increasing. Parental drinking was associated with being in high-convex and medium-concave classes. Compared to the low-increasing class, the high convex and medium concave classes reported more AID and being a passenger of a drunk driver more frequently. Conclusions: Parental drinking may affect children’s later engagement in AID. Efforts should focus on parents' education regarding the consequences of parental modeling of alcohol consumption.

Keywords: alcohol impaired driving, alcohol consumption, binge drinking, college students, parental modeling

Procedia PDF Downloads 261

Authors: Aihong Zhao, Priya Sastry, Mark L Field, Mohamad Bashir, Arvind Singh, David Richens

Abstract:

Objectives: Intramural haematoma (IMH) is one of the pathologies, along with acute aortic dissection, that present as Acute Aortic Syndrome (AAS). Evidence suggests that unlike aortic dissection, some intramural haematomas may regress with medical management. However, intramural haematomas have been traditionally managed like acute aortic dissections. Given that some of these pathologies may regress with conservative management, it would be useful to be able to identify which of these may not need high risk emergency intervention. A computational aortic model was used in this study to try and identify intramural haematomas with risk of progression to aortic dissection. Methods: We created a computational model of the aorta with luminal blood flow. Reports in the literature have identified 11 mm as the radial clot thickness that is associated with heightened risk of progression of intramural haematoma. Accordingly, haematomas of varying sizes were implanted in the modeled aortic wall to test this hypothesis. The model was exposed to physiological blood flows and the stresses and strains in each layer of the aortic wall were recorded. Results: Size and shape of clot were seen to affect the magnitude of aortic stresses. The greatest stresses and strains were recorded in the intima of the model. When the haematoma exceeded 10 mm in all dimensions, the stress on the intima reached breaking point. Conclusion: Intramural clot size appears to be a contributory factor affecting aortic wall stress. Our computer simulation corroborates clinical evidence in the literature proposing that IMH diameter greater than 11 mm may be predictive of progression. This preliminary report suggests finite element modelling of the aortic wall may be a useful process by which to examine putative variables important in predicting progression or regression of intramural haematoma.

Keywords: intramural haematoma, acute aortic syndrome, finite element analysis,

Procedia PDF Downloads 414

Authors: Yang Shen, Yongpan Cheng, Jinliang Xu

Abstract:

The effective blade cooling is of great significance for improving the performance of turbine. The mist cooling emerges as the promising way compared with the transitional single-phase cooling. In the mist cooling, the injected droplet will evaporate rapidly, and cool down the blade surface due to the absorbed latent heat, hence the lifetime for evaporating droplet becomes critical for design of cooling passages for the blade. So far there have been extensive studies on the droplet evaporation, but usually the isothermal model is applied for most of the studies. Actually the surface cooling effect can affect the droplet evaporation greatly, it can prolong the droplet evaporation lifetime significantly. In our study, a new theoretical model for sessile droplet evaporation with surface cooling effect is built up in toroidal coordinate. Three evaporation modes are analyzed during the evaporation lifetime, include “Constant Contact Radius”(CCR) mode、“Constant Contact Angle”(CCA) mode and “stick-slip”(SS) mode. The dimensionless number E0 is introduced to indicate the strength of the evaporative cooling, it is defined based on the thermal properties of the liquid and the atmosphere. Our model can predict accurately the lifetime of evaporation by validating with available experimental data. Then the temporal variation of droplet volume, contact angle and contact radius are presented under CCR, CCA and SS mode, the following conclusions are obtained. 1) The larger the dimensionless number E0, the longer the lifetime of three evaporation cases is; 2) The droplet volume over time still follows “2/3 power law” in the CCA mode, as in the isothermal model without the cooling effect; 3) In the “SS” mode, the large transition contact angle can reduce the evaporation time in CCR mode, and increase the time in CCA mode, the overall lifetime will be increased; 4) The correction factor for predicting instantaneous volume of the droplet is derived to predict the droplet life time accurately. These findings may be of great significance to explore the dynamics and heat transfer of sessile droplet evaporation.

Keywords: blade cooling, droplet evaporation, lifetime, theoretical analysis

Procedia PDF Downloads 128

Authors: Matthew Cruickshank, Chaaruchandra Korde, Roger P. West, John Reddy

Abstract:

Precast concrete element exports are growing in importance in Ireland’s concrete industry and with the increased global focus on reducing carbon emissions, the industry is exploring more sustainable alternatives such as using ground granulated blast-furnace slag (GGBS) as a partial replacement of Portland cement. It is well established that GGBS, with low early age strength development, has limited use in precast manufacturing due to the need for early de-moulding, cutting of pre-stressed strands and lifting. In this dichotomy, the effects of temperature, admixture, are explored to try to achieve the required very early age strength. Testing of the strength of mortars is mandated in the European cement standard, so here with 50% GGBS and Super Fine GGBS, with three admixture conditions (none, conventional accelerator, novel accelerator) and two early age curing temperature conditions (20°C and 35°C), standard mortar strengths are measured at six ages (16 hours, 1, 2, 3, 7, 28 days). The present paper will describe the effort towards developing maturity curves to aid in understanding the effect of these accelerating admixtures and GGBS fineness on slag cement mortars, allowing prediction of their strength with time and temperature. This study is of particular importance to the precast industry where concrete temperature can be controlled. For the climatic conditions in Ireland, heating of precast beds for long hours will amount to an additional cost and also contribute to the carbon footprint of the products. When transitioned from mortar to concrete, these maturity curves are expected to play a vital role in predicting the strength of the GGBS concrete at a very early age prior to demoulding.

Keywords: accelerating admixture, early age strength, ground granulated blast-furnace slag, GGBS, maturity, precast concrete

Procedia PDF Downloads 140

Authors: Shalu Jain, Anju Bansal, Anup Kumar, Sunita Saxena

Abstract:

Objectives: The novel TMPRSS2:ERG gene fusion is a common somatic event in prostate cancer that in some studies is linked with a more aggressive disease phenotype. Thus, this study aims to determine whether clinical variables are associated with the presence of TMPRSS2:ERG-fusion gene transcript in Indian patients of prostate cancer. Methods: We evaluated the clinical variables with presence and absence of TMPRSS2:ERG gene fusion in prostate cancer and BPH association of clinical patients. Patients referred for prostate biopsy because of abnormal DRE or/and elevated sPSA were enrolled for this prospective clinical study. TMPRSS2:ERG mRNA copies in samples were quantified using a Taqman chemistry by real time PCR assay in prostate biopsy samples (N=42). The T2:ERG assay detects the gene fusion mRNA isoform TMPRSS2 exon1 to ERG exon4. Results: Histopathology report has confirmed 25 cases as prostate cancer adenocarcinoma (PCa) and 17 patients as benign prostate hyperplasia (BPH). Out of 25 PCa cases, 16 (64%) were T2: ERG fusion positive. All 17 BPH controls were fusion negative. The T2:ERG fusion transcript was exclusively specific for prostate cancer as no case of BPH was detected having T2:ERG fusion, showing 100% specificity. The positive predictive value of fusion marker for prostate cancer is thus 100% and the negative predictive value is 65.3%. The T2:ERG fusion marker is significantly associated with clinical variables like no. of positive cores in prostate biopsy, Gleason score, serum PSA, perineural invasion, perivascular invasion and periprostatic fat involvement. Conclusions: Prostate cancer is a heterogeneous disease that may be defined by molecular subtypes such as the TMPRSS2:ERG fusion. In the present prospective study, the T2:ERG quantitative assay demonstrated high specificity for predicting biopsy outcome; sensitivity was similar to the prevalence of T2:ERG gene fusions in prostate tumors. These data suggest that further improvement in diagnostic accuracy could be achieved using a nomogram that combines T2:ERG with other markers and risk factors for prostate cancer.

Keywords: prostate cancer, genetic rearrangement, TMPRSS2:ERG fusion, clinical variables

Procedia PDF Downloads 425

Authors: Michael Luc Andre, Célia Maintenant

Abstract:

Theory of mind is a milestone in child development which allows children to understand that others could have different mental states than theirs. Understanding the developmental stages of theory of mind in children leaded researchers on two Connected research problems. In one hand, the link between executive function and theory of mind, and on the other hand, the relationship of theory of mind and syntax processing. These two lines of research involved a great literature, full of important results, despite certain level of disagreement between researchers. For a long time, these two research perspectives continue to grow up separately despite research conclusion suggesting that the three variables should implicate same developmental period. Indeed, our goal was to study the relation between theory of mind, executive function, and language via a unique research question. It supposed that between executive function and language, one of the two variables could play a critical role in the relationship between theory of mind and the other variable. Thus, 112 children aged between three and six years old were recruited for completing a receptive and an expressive vocabulary task, a syntax understanding task, a theory of mind task, and three executive function tasks (inhibition, cognitive flexibility and working memory). The results showed significant correlations between performance on theory of mind task and performance on executive function domain tasks, except for cognitive flexibility task. We also found significant correlations between success on theory of mind task and performance in all language tasks. Multiple regression analysis justified only syntax and general abilities of language as possible predictors of theory of mind performance in our preschool age children sample. The results were discussed in the perspective of a great role of language abilities in theory of mind development. We also discussed possible reasons that could explain the non-significance of executive domains in predicting theory of mind performance, and the meaning of our results for the literature.

Keywords: child development, executive function, general language, syntax, theory of mind

Procedia PDF Downloads 44

Authors: Ashwin Belle, Bryce Benson, Mark Salamango, Fadi Islim, Rodney Daniels, Kevin Ward

Abstract:

A reliable, real-time, and non-invasive system that can identify patients at risk for hemodynamic instability is needed to aid clinicians in their efforts to anticipate patient deterioration and initiate early interventions. The purpose of this pilot study was to explore the clinical capabilities of a real-time analytic from a single lead of an electrocardiograph to correctly distinguish between rapid response team (RRT) activations due to hemodynamic (H-RRT) and non-hemodynamic (NH-RRT) causes, as well as predict H-RRT cases with actionable lead times. The study consisted of a single center, retrospective cohort of 21 patients with RRT activations from step-down and telemetry units. Through electronic health record review and blinded to the analytic’s output, each patient was categorized by clinicians into H-RRT and NH-RRT cases. The analytic output and the categorization were compared. The prediction lead time prior to the RRT call was calculated. The analytic correctly distinguished between H-RRT and NH-RRT cases with 100% accuracy, demonstrating 100% positive and negative predictive values, and 100% sensitivity and specificity. In H-RRT cases, the analytic detected hemodynamic deterioration with a median lead time of 9.5 hours prior to the RRT call (range 14 minutes to 52 hours). The study demonstrates that an electrocardiogram (ECG) based analytic has the potential for providing clinical decision and monitoring support for caregivers to identify at risk patients within a clinically relevant timeframe allowing for increased vigilance and early interventional support to reduce the chances of continued patient deterioration.

Keywords: critical care, early warning systems, emergency medicine, heart rate variability, hemodynamic instability, rapid response team

Procedia PDF Downloads 130

Authors: Yongjiang Zhang, Kallol Barai, Umesh R. Hodeghatta, Trang Tran, Vikas Dhiman

Abstract:

Detecting water stress on crops early and accurately is crucial to minimize its impact. This study aims to measure water stress in wild blueberry crops non-destructively by analyzing proximal hyperspectral data. The data collection took place in the summer growing season of 2022. A drought experiment was conducted on wild blueberries in the randomized block design in the greenhouse, incorporating various genotypes and irrigation treatments. Hyperspectral data ( spectral range: 400-1000 nm) using a handheld spectroradiometer and leaf water potential data using a pressure chamber were collected from wild blueberry plants. Machine learning techniques, including multiple regression analysis and random forest models, were employed to predict leaf water potential (MPa). We explored the optimal wavelength bands for simple differences (RY1-R Y2), simple ratios (RY1/RY2), and normalized differences (|RY1-R Y2|/ (RY1-R Y2)). NDWI ((R857 - R1241)/(R857 + R1241)), SD (R2188 – R2245), and SR (R1752 / R1756) emerged as top predictors for predicting leaf water potential, significantly contributing to the highest model performance. The base learner models achieved an R-squared value of approximately 0.81, indicating their capacity to explain 81% of the variance. Research is underway to develop a neural vegetation index (NVI) that automates the process of index development by searching for specific wavelengths in the space ratio of linear functions of reflectance. The NVI framework could work across species and predict different physiological parameters.

Keywords: hyperspectral reflectance, water potential, spectral indices, machine learning, wild blueberries, optimal bands

Procedia PDF Downloads 52

Authors: Stefaan Carpentier, Aya Al Masri, Fabrice Leroy, Thibault Julien, Safoin Aktaou, Malorie Martin, Fouad Maaloul

Abstract:

Introduction: During an 'Interventional Radiology (IR)' procedure, the patient's skin-dose may become very high for a burn, necrosis, and ulceration to appear. In order to prevent these deterministic effects, a prediction of the peak skin-dose for the patient is important in order to improve the post-operative care to be given to the patient. The objective of this study is to estimate, before the intervention, the patient dose for ‘Chronic Total Occlusion (CTO)’ procedures by selecting relevant clinical indicators. Materials and methods: 103 procedures were performed in the ‘Interventional Cardiology (IC)’ department using a Siemens Artis Zee image intensifier that provides the Air Kerma of each IC exam. Peak Skin Dose (PSD) was measured for each procedure using radiochromic films. Patient parameters such as sex, age, weight, and height were recorded. The complexity index J-CTO score, specific to each intervention, was determined by the cardiologist. A correlation method applied to these indicators allowed to specify their influence on the dose. A predictive model of the dose was created using multiple linear regressions. Results: Out of 103 patients involved in the study, 5 were excluded for clinical reasons and 2 for placement of radiochromic films outside the exposure field. 96 2D-dose maps were finally used. The influencing factors having the highest correlation with the PSD are the patient's diameter and the J-CTO score. The predictive model is based on these parameters. The comparison between estimated and measured skin doses shows an average difference of 0.85 ± 0.55 Gy for doses of less than 6 Gy. The mean difference between air-Kerma and PSD is 1.66 Gy ± 1.16 Gy. Conclusion: Using our developed method, a first estimate of the dose to the skin of the patient is available before the start of the procedure, which helps the cardiologist in carrying out its intervention. This estimation is more accurate than that provided by the Air-Kerma.

Keywords: chronic total occlusion procedures, clinical experimentation, interventional radiology, patient's peak skin dose

Procedia PDF Downloads 119

Authors: Caren Hilger, Silke Burkert, Friederike Kendel

Abstract:

Men with localized prostate cancer (PCa) have to choose among different treatment options, such as active surveillance (AS) and radical prostatectomy (RP). All available treatment options may be accompanied by specific psychological or physiological side effects. Depending on the nature and extent of these side effects, patients are more or less likely to be satisfied or to struggle with their treatment decision in the long term. Therefore, the aim of this study was to assess and explain decisional regret in men with localized PCa. The role of erectile functioning as one of the main physiological side effects of invasive PCa treatment, depressive symptoms as a common psychological side effect, and the association of erectile functioning and depressive symptoms with decisional regret were investigated. Men with localized PCa initially managed with AS or RP (N=292) were matched according to length of therapy (mean 47.9±15.4 months). Subjects completed mailed questionnaires assessing decisional regret, changes in erectile functioning, depressive symptoms, and sociodemographic variables. Clinical data were obtained from case report forms. Differences among the two treatment groups (AS and RP) were calculated using t-tests and χ²-tests, relationships of decisional regret with erectile functioning and depressive symptoms were computed using multiple regression. Men were on average 70±7.2 years old. The two treatment groups differed markedly regarding decisional regret (p<.001, d=.50), changes in erectile functioning (p<.001, d=1.2), and depressive symptoms (p=.01, d=.30), with men after RP reporting higher values, respectively. Regression analyses showed that after adjustment for age, tumor risk category, and changes in erectile functioning, depressive symptoms were still significantly associated with decisional regret (B=0.52, p<.001). Additionally, when predicting decisional regret, the interaction of changes in erectile functioning and depressive symptoms reached significance for men after RP (B=0.52, p<.001), but not for men under AS (B=-0.16, p=.14). With increased changes in erectile functioning, the association of depressive symptoms with decisional regret became stronger in men after RP. Decisional regret is a phenomenon more prominent in men after RP than in men under AS. Erectile functioning and depressive symptoms interact in their prediction of decisional regret. Screening and treating depressive symptoms might constitute a starting point for interventions aiming to reduce decisional regret in this target group.

Keywords: active surveillance, decisional regret, depressive symptoms, erectile functioning, prostate cancer, radical prostatectomy

Procedia PDF Downloads 202

Authors: Mehdi Khaki, Ehsan Forootan, Joseph Awange, Michael Kuhn

Abstract:

Terrestrial water storage, as a source of freshwater, plays an important role in human lives. Hydrological models offer important tools for simulating and predicting water storages at global and regional scales. However, their comparisons with 'reality' are imperfect mainly due to a high level of uncertainty in input data and limitations in accounting for all complex water cycle processes, uncertainties of (unknown) empirical model parameters, as well as the absence of high resolution (both spatially and temporally) data. Data assimilation can mitigate this drawback by incorporating new sets of observations into models. In this effort, we use multi-mission satellite-derived remotely sensed observations to improve the performance of World-Wide Water Resources Assessment system (W3RA) hydrological model for estimating terrestrial water storages. For this purpose, we assimilate total water storage (TWS) data from the Gravity Recovery And Climate Experiment (GRACE) and surface soil moisture data from the Advanced Microwave Scanning Radiometer for the Earth Observing System (AMSR-E) into W3RA. This is done to (i) improve model estimations of water stored in ground and soil moisture, and (ii) assess the impacts of each satellite of data (from GRACE and AMSR-E) and their combination on the final terrestrial water storage estimations. These data are assimilated into W3RA using the Ensemble Square-Root Filter (EnSRF) filtering technique over Mississippi Basin (the United States) and Murray-Darling Basin (Australia) between 2002 and 2013. In order to evaluate the results, independent ground-based groundwater and soil moisture measurements within each basin are used.

Keywords: data assimilation, GRACE, AMSR-E, hydrological model, EnSRF

Procedia PDF Downloads 265

Authors: Aschalew Cherie Workneh, K. S. Hari Prasad, Chandra Shekhar Prasad Ojha

Abstract:

Due to the increase in water scarcity, the crop water stress index (CWSI) is receiving significant attention these days, especially in arid and semiarid regions, for quantifying water stress and effective irrigation scheduling. Nowadays, machine learning techniques such as neural networks are being widely used to determine CWSI. In the present study, the performance of two artificial neural networks, namely, Self-Organizing Maps (SOM) and Feed Forward-Back Propagation Artificial Neural Networks (FF-BP-ANN), are compared while determining the CWSI of rice crop. Irrigation field experiments with varying degrees of irrigation were conducted at the irrigation field laboratory of the Indian Institute of Technology, Roorkee, during the growing season of the rice crop. The CWSI of rice was computed empirically by measuring key meteorological variables (relative humidity, air temperature, wind speed, and canopy temperature) and crop parameters (crop height and root depth). The empirically computed CWSI was compared with SOM and FF-BP-ANN predicted CWSI. The upper and lower CWSI baselines are computed using multiple regression analysis. The regression analysis showed that the lower CWSI baseline for rice is a function of crop height (h), air vapor pressure deficit (AVPD), and wind speed (u), whereas the upper CWSI baseline is a function of crop height (h) and wind speed (u). The performance of SOM and FF-BP-ANN were compared by computing Nash-Sutcliffe efficiency (NSE), index of agreement (d), root mean squared error (RMSE), and coefficient of correlation (R²). It is found that FF-BP-ANN performs better than SOM while predicting the CWSI of rice crops.

Keywords: artificial neural networks; crop water stress index; canopy temperature, prediction capability

Procedia PDF Downloads 88

Authors: Jean-michel Sahut, Lubica Hikkerova, Wissal Ben Arfi

Abstract:

The Internet of Things (IoT) emerged over the last few decades in many fields. Healthcare can significantly benefit from IoT. This study aims to examine factors influencing the adoption of IoT in eHealth. To do so, an innovative framework has been developed which applies both the Technology Acceptance Model (TAM) and the United Theory of Acceptance and Use of Technology (UTAUT) model and builds on them by analyzing trust and perceived-risk dimensions to predict intention to use IoT in eHealth. In terms of methodology, a Partial Least Approach Structural Equation Modelling was carried out on a sample of 267 French users. The findings of this research support the significant positive effect of constructs set out in the TAM (perceived ease of use) on predicting behavioral intention by adding the effects identified for UTAUT variables. This research also demonstrates how perceived risk and trust are significant factors for models examining behavioral intentions to use IoT. Perceived risk enhanced by the trust has a significant effect on patients’ behavioral intentions. Moreover, the results highlight the key role of prescription as a moderator of IoT adoption in eHealth. Depending on whether an individual has a prescription to use connected devices or not, ease of use has a stronger impact on adoption, while trust has a negative impact on adoption for users without a prescription. In accordance with the empirical results, several practical implications can be proposed. All connected devices applied in a medical context should be divided into groups according to their functionality: whether they are essential for the patient’s health and whether they require a prescription or not. Devices used with a prescription are easily accepted because the intention to use them is moderated by the medical trust (discussed above). For users without a prescription, ease of use is a more significant factor than for users who have a prescription. This suggests that currently, connected e-Health devices and online healthcare systems have to take this factor into account to better meet the needs and expectations of end-users.

Keywords: internet of things, Healthcare, trust, consumer acceptance

Procedia PDF Downloads 125

Authors: Reem Alsager, James Milton

Abstract:

Coxhead’s (2000) Academic Word List (AWL) believed to be essential for students pursuing higher education and helps differentiate English for Academic Purposes (EAP) from General English as a course of study, and it is thought to be important for comprehending English academic texts. It has been described that AWL is an infrequent, discrete set of vocabulary items unreachable from general language. On the other hand, it has been known for a period of time that general vocabulary knowledge is a good predictor of academic achievement. This study, however, is an attempt to measure and compare the contribution of academic knowledge and general vocabulary knowledge to learners’ GPA and examine what knowledge is a better predictor of academic achievement and investigate whether AWL as a specialised list of infrequent words relates to the frequency effect. The participants were comprised of 44 international postgraduate students in Swansea University, all from the School of Management, following the taught MSc (Master of Science). The study employed the Academic Vocabulary Size Test (AVST) and the XK_Lex vocabulary size test. The findings indicate that AWL is a list based on word frequency rather than a discrete and unique word list and that the AWL performs the same function as general vocabulary, with tests of each found to measure largely the same quality of knowledge. The findings also suggest that the contribution that AWL knowledge provides for academic success is not sufficient and that general vocabulary knowledge is better in predicting academic achievement. Furthermore, the contribution that academic knowledge added above the contribution of general vocabulary knowledge when combined is really small and noteworthy. This study’s results are in line with the argument and suggest that it is the development of general vocabulary size is an essential quality for academic success and acquiring the words of the AWL will form part of this process. The AWL by itself does not provide sufficient coverage, and is probably not specialised enough, for knowledge of this list to influence this general process. It can be concluded that AWL as an academic word list epitomizes only a fraction of words that are actually needed for academic success in English and that knowledge of academic vocabulary combined with general vocabulary knowledge above the most frequent 3000 words is what matters most to ultimate academic success.

Keywords: academic achievement, academic vocabulary, general vocabulary, vocabulary size

Procedia PDF Downloads 201

Authors: Adel Khorramrouz, Monireh Ahmadi Bani, Ehsan Norouzi, Morvarid Lalenoor

Abstract:

Background: Plantar pressure distribution measurement has been used for a long time to assess foot disorders. Plantar pressure is an important component affecting the foot and ankle function and Changes in plantar pressure distribution could indicate various foot and ankle disorders. Morphologic and mechanical properties of the foot may be important factors affecting the plantar pressure distribution. Accurate and early measurement may help to reduce the prevalence of pes planus. With recent developments in technology, new techniques such as machine learning have been used to assist clinicians in predicting patients with foot disorders. Significance of the study: This study proposes a neural network learning-based flat foot classification methodology using static foot pressure distribution. Methodologies: Data were collected from 895 patients who were referred to a foot clinic due to foot disorders. Patients with pes planus were labeled by an experienced physician based on clinical examination. Then all subjects (with and without pes planus) were evaluated for static plantar pressures distribution. Patients who were diagnosed with the flat foot in both feet were included in the study. In the next step, the leg length was normalized and the network was trained for plantar pressure mapping images. Findings: From a total of 895 image data, 581 were labeled as pes planus. A computational neural network (CNN) ran to evaluate the performance of the proposed model. The prediction accuracy of the basic CNN-based model was performed and the prediction model was derived through the proposed methodology. In the basic CNN model, the training accuracy was 79.14%, and the test accuracy was 72.09%. Conclusion: This model can be easily and simply used by patients with pes planus and doctors to predict the classification of pes planus and prescreen for possible musculoskeletal disorders related to this condition. However, more models need to be considered and compared for higher accuracy.

Keywords: foot disorder, machine learning, neural network, pes planus

Procedia PDF Downloads 336

Authors: Yen-Hui Chen, Terry Walker

Abstract:

As the world experiences an energy crisis, investing in sustainable energy resources is a pressing mission for many countries. Microalgae-derived biodiesel has attracted intensive attention as an important biofuel, and microalgae Chlorella protothecoides lipid is recognized as a renewable source for microalgae-derived biodiesel production. Supercritical carbon dioxide (SC-CO₂) is a promising green solvent that may potentially substitute the use of organic solvents for lipid extraction; however, the efficiency of SC-CO₂ extraction may be affected by many variables, including temperature, pressure and extraction time individually or in combination. In this study, response surface methodology (RSM) was used to optimize the process parameters, including temperature, pressure and extraction time, on C. protothecoides lipid yield by SC-CO₂ extraction. A second order polynomial model provided a good fit (R-square value of 0.94) for the C. protothecoides lipid yield. The linear and quadratic terms of temperature, pressure and extraction time—as well as the interaction between temperature and pressure—showed significant effects on lipid yield during extraction. The optimal lipid yield from the model was predicted as the temperature of 59 °C, the pressure of 350.7 bar and the extraction time 2.8 hours. Under these conditions, the experimental lipid yield (25%) was close to the predicted value. The principal fatty acid methyl esters (FAME) of C. protothecoides lipid-derived biodiesel were oleic acid methyl ester (60.1%), linoleic acid methyl ester (18.6%) and palmitic acid methyl ester (11.4%), which made up more than 90% of the total FAMEs. In summary, this study indicated that RSM was useful to characterize the optimization the SC-CO₂ extraction process of C. protothecoides lipid yield, and the second-order polynomial model could be used for predicting and describing the lipid yield very well. In addition, C. protothecoides lipid, extracted by SC-CO₂, was suggested as a potential candidate for microalgae-derived biodiesel production.

Keywords: Chlorella protothecoides, microalgal lipids, response surface methodology, supercritical carbon dioxide extraction

Procedia PDF Downloads 424

Authors: Hyuk-Hoon Kim, Young Gi Min

Abstract:

Background: In carbon monoxide (CO) intoxication, the pathophysiology of delayed neurological sequelae (DNS) is very complex and remains poorly understood. And predicting whether patients who exhibit resolved acute symptoms have escaped or will experience DNS represents a very important clinical issue. Brain magnetic resonance (MR) imaging has been conducted to assess the severity of brain damage as an objective method to predict prognosis. And co-ingestion of a second poison in patients with intentional CO poisoning occurs in almost one-half of patients. Among patients with co-ingestions, 66% ingested ethanol. We assessed the effects of ethanol on neurologic sequelae prevalence in acute CO intoxication by means of abnormal lesion in brain MR. Method: This study was conducted retrospectively by collecting data for patients who visited an emergency medical center during a period of 5 years. The enrollment criteria were diagnosis of acute CO poisoning and the measurement of the serum ethanol level and history of taking a brain MR during admission period. Official readout data by radiologist are used to decide whether abnormal lesion is existed or not. The enrolled patients were divided into two groups: patients with abnormal lesion and without abnormal lesion in Brain MR. A standardized extraction using medical record was performed; Mann Whitney U test and logistic regression analysis were performed. Result: A total of 112 patients were enrolled, and 68 patients presented abnormal brain lesion on MR. The abnormal brain lesion group had lower serum ethanol level (mean, 20.14 vs 46.71 mg/dL) (p-value<0.001). In addition, univariate logistic regression analysis showed the serum ethanol level (OR, 0.99; 95% CI, 0.98 -1.00) was independently associated with the development of abnormal lesion in brain MR. Conclusion: Ethanol could have neuroprotective effect in acute CO intoxication by sedative effect in stressful situation and mitigative effect in neuro-inflammatory reaction.

Keywords: carbon monoxide, delayed neuropsychological sequelae, ethanol, intoxication, magnetic resonance

Procedia PDF Downloads 240

Authors: Sharon Cayzer-Haller, Shir Ginosar-Yaari, Ariel Knafo-Noam

Abstract:

The 21st century emerged as the digital century, and it is marked by a wide range of technological developments and changes, followed by potential changes in human communication skills. This technological revolution has changed human means of communication in many different ways: children and adolescents are spending much of their time in front of screens, participating in all sorts of online activities (even more so since the outbreak of COVID-19). The current study focuses on the role of values in adolescents' online bystanders' behavior. Values are cognitive, abstract representations of desirable goals that motivate behavior, and we hypothesized finding significant associations between specific values and differential online bystanders' feelings and behavior. Data was collected through online questionnaires that measured the participants' values, using Schwartz's short version of the Portrait Values Questionnaire (Schwartz, 2012). Participants’ online behavior was assessed in a questionnaire addressing reactions to situations of cyber shaming and cyberbullying, and specifically positive feelings and pro-social behavior (e.g., more supportive reactions) toward the victims, as opposed to different offensive behavioral reactions (such as laughing at the victim or ignoring the situation). Participants were recruited with a commercial research panel company, and 308 Israeli adolescents' values and online behavior were examined (mean age 15.2). As hypothesized, results show significant associations between self-transcendence values (universalism and benevolence) and conservation values (conformity, tradition, and security). These two groups of values were positively correlated with pro-social bystanders' feelings and behavior. On the opposite side of the values scale, the value of power was negatively associated with the participants' pro-social behavior, and positively associated with offensive behavioral reactions. Further research is needed, but we conclude that values serve as crucial guiding factors in directing adolescents' online feelings and behavior.

Keywords: adolescents, values, cyberbullying, online behavior, power

Procedia PDF Downloads 46

Authors: Shan-Hong Ying, Ying-Fang Wang

Abstract:

A surrogate approach was deployed for assessing exposures of multiple chemicals at the selected working area of coating processes and applied to assess the exposure concentration of similar exposed groups using the same chemicals but different formula ratios. For the selected area, 6 to 12 portable photoionization detector (PID) were placed uniformly in its workplace to measure its total VOCs concentrations (CT-VOCs) for 6 randomly selected workshifts. Simultaneously, one sampling strain was placed beside one of these portable PIDs, and the collected air sample was analyzed for individual concentration (CVOCi) of 5 VOCs (xylene, butanone, toluene, butyl acetate, and dimethylformamide). Predictive models were established by relating the CT-VOCs to CVOCi of each individual compound via simple regression analysis. The established predictive models were employed to predict each CVOCi based on the measured CT-VOC for each the similar working area using the same portable PID. Results show that predictive models obtained from simple linear regression analyses were found with an R2 = 0.83~0.99 indicating that CT-VOCs were adequate for predicting CVOCi. In order to verify the validity of the exposure prediction model, the sampling analysis of the above chemical substances was further carried out and the correlation between the measured value (Cm) and the predicted value (Cp) was analyzed. It was found that there is a good correction between the predicted value and measured value of each measured chemical substance (R2=0.83~0.98). Therefore, the surrogate approach could be assessed the exposure concentration of similar exposed groups using the same chemicals but different formula ratios. However, it is recommended to establish the prediction model between the chemical substances belonging to each coater and the direct-reading PID, which is more representative of reality exposure situation and more accurately to estimate the long-term exposure concentration of operators.

Keywords: exposure assessment, exposure prediction model, surrogate approach, TVOC

Procedia PDF Downloads 127

Authors: Fanous Mohammadi, Majid H. Tangestani, Mohammad H. Tayebi

Abstract:

This research aims to evaluate and compare Geographical Information Systems (GIS)-based fuzzy models for producing orogenic gold prospectivity maps in the Saqqez area, NW of Iran. Gold occurrences are hosted in sericite schist and mafic to felsic meta-volcanic rocks in this area and are associated with hydrothermal alterations that extend over ductile to brittle shear zones. The predictor maps, which represent the Pre-(Source/Trigger/Pathway), syn-(deposition/physical/chemical traps) and post-mineralization (preservation/distribution of indicator minerals) subsystems for gold mineralization, were generated using empirical understandings of the specifications of known orogenic gold deposits and gold mineral systems and were then pre-processed and integrated to produce mineral prospectivity maps. Five fuzzy logic operators, including AND, OR, Fuzzy Algebraic Product (FAP), Fuzzy Algebraic Sum (FAS), and GAMMA, were applied to the predictor maps in order to find the most efficient prediction model. Prediction-Area (P-A) plots and field observations were used to assess and evaluate the accuracy of prediction models. Mineral prospectivity maps generated by AND, OR, FAP, and FAS operators were inaccurate and, therefore, unable to pinpoint the exact location of discovered gold occurrences. The GAMMA operator, on the other hand, produced acceptable results and identified potentially economic target sites. The P-A plot revealed that 68 percent of known orogenic gold deposits are found in high and very high potential regions. The GAMMA operator was shown to be useful in predicting and defining cost-effective target sites for orogenic gold deposits, as well as optimizing mineral deposit exploitation.

Keywords: mineral prospectivity mapping, fuzzy logic, GIS, orogenic gold deposit, Saqqez, Iran

Procedia PDF Downloads 103

Authors: Pankaj Dhiman, Simranjeet Kaur

Abstract:

This research paper presents a comprehensive sentiment analysis of social media responses to videos on Facebook, YouTube, Twitter, and Instagram during the 2024 Indian general elections. The study focuses on the sentiment patterns of voters towards the National Democratic Alliance (NDA) and The Indian National Developmental Inclusive Alliance (INDIA) on these platforms. The analysis aims to understand the impact of social media on voter sentiment and its correlation with the election outcome. The study employed a mixed-methods approach, combining both quantitative and qualitative methods. With a total of 200 posts analysed during general election-2024 final phase, the sentiment analysis was conducted using natural language processing (NLP) techniques, including sentiment dictionaries and machine learning algorithms. The results show that NDA received significantly more positive sentiment responses across all platforms, with a positive sentiment score of 47% compared to INDIA's score of 38.98 %. The analysis also revealed that Twitter and YouTube were the most influential platforms in shaping voter sentiment, with 60% of the total sentiment score coming from these two platforms. The study's findings suggest that social media sentiment analysis can be a valuable tool for understanding voter sentiment and predicting election outcomes. The results also highlight the importance of social media in shaping public opinion and the need for political parties to engage effectively with voters on these platforms. The study's implications are significant, as they indicate that social media can be a key factor in determining the outcome of elections. The findings also underscore the need for political parties to develop effective social media strategies to engage with voters and shape public opinion.

Keywords: Indian Elections-2024, NDA, INDIA, sentiment analysis, social media, democracy

Procedia PDF Downloads 15