Search results for: predicting factors

Authors: Sadia Munir

Abstract:

Preeclampsia is the contributor to the worldwide maternal mortality of approximately 100,000 deaths a year. It complicates about 10% of all pregnancies and is the first cause of maternal admission to intensive care units. Predicting preeclampsia is a major challenge in obstetrics. More importantly, no major progress has been achieved in the treatment of preeclampsia. As placenta is the main cause of the disease, the only way to treat the disease is to extract placental and deliver the baby. In developed countries, the cost of an average case of preeclampsia is estimated at £9000. Interestingly, preeclampsia may have an impact on the health of mother or infant, beyond the pregnancy. We performed a systematic search of PubMed including the combination of terms such as preeclampsia, biomarkers, treatment, hypoxia, inflammation, oxidative stress, vascular endothelial growth factor A, activin A, inhibin A, placental growth factor, transforming growth factor β-1, Nodal, placenta, trophoblast cells, microRNAs. In this review, we have summarized current knowledge on the identification of potential biomarkers for the diagnosis of preeclampsia. Although these studies show promising data in early diagnosis of preeclampsia, the current value of these factors as biomarkers, for the precise prediction of preeclampsia, has its limitation. Therefore, future studies need to be done to support some of the very promising and interesting data to develop affordable and widely available tests for early detection and treatment of preeclampsia.

Keywords: activin, biomarkers, growth factors, miroRNA

Procedia PDF Downloads 442

Authors: Salem Alsanusi, Loubna Bentaher

Abstract:

Response Surface Methods (RSM) provide statistically validated predictive models that can then be manipulated for finding optimal process configurations. Variation transmitted to responses from poorly controlled process factors can be accounted for by the mathematical technique of propagation of error (POE), which facilitates ‘finding the flats’ on the surfaces generated by RSM. The dual response approach to RSM captures the standard deviation of the output as well as the average. It accounts for unknown sources of variation. Dual response plus propagation of error (POE) provides a more useful model of overall response variation. In our case, we implemented this technique in predicting compressive strength of concrete of 28 days in age. Since 28 days is quite time consuming, while it is important to ensure the quality control process. This paper investigates the potential of using design of experiments (DOE-RSM) to predict the compressive strength of concrete at 28th day. Data used for this study was carried out from experiment schemes at university of Benghazi, civil engineering department. A total of 114 sets of data were implemented. ACI mix design method was utilized for the mix design. No admixtures were used, only the main concrete mix constituents such as cement, coarse-aggregate, fine aggregate and water were utilized in all mixes. Different mix proportions of the ingredients and different water cement ratio were used. The proposed mathematical models are capable of predicting the required concrete compressive strength of concrete from early ages.

Keywords: mix proportioning, response surface methodology, compressive strength, optimal design

Procedia PDF Downloads 267

Authors: Bharatendra Rai

Abstract:

Cutting tools are widely used in manufacturing processes and drilling is the most commonly used machining process. Although drill-bits used in drilling may not be expensive, their breakage can cause damage to expensive work piece being drilled and at the same time has major impact on productivity. Predicting drill-bit breakage, therefore, is important in reducing cost and improving productivity. This study uses twenty features extracted from two degradation signals viz., thrust force and torque. The methodology used involves developing and comparing decision tree, random forest, and multinomial logistic regression models for classifying and predicting drill-bit breakage using degradation signals.

Keywords: degradation signal, drill-bit breakage, random forest, multinomial logistic regression

Procedia PDF Downloads 352

Authors: Asma Qudrat, Abid Ullah, Rafi Ullah, Ali Raza, Shah Zeb, Syed Ali Shan Ul-Haq, Shahkar Ahmed Shah, Attiya Hameed Khan, Saad Zaheer, Umama Qasim, Kiran Jamal, Zahoor khan

Abstract:

Objectives: Coronary artery disease (CAD) is the major public health issue associated with high mortality and morbidity rate worldwide. Young patients with ACS have unique characteristics with different demographic profiles and risk factors. The precise diagnosis and early risk stratification is important in guiding treatment and predicting the prognosis of young patients with ACS. To evaluate the associated demographics, risk factors, and outcomes profile of ACS in young age patients. Methods: The research follow a retrospective design, the single centre study of patients diagnosis with the first event of ACS in young age (>18 and <40) were included. Data collection included demographic profiles, risk factors, and in-hospital outcomes of young ACS patients. The patient’s data was retrieved through Electronic Medical Records (EMR) of Peshawar Institute of Cardiology (PIC), and all characteristic were assessed. Results: In this study, 77% were male, and 23% were female patients. The risk factors were assessed with CAD and shown significant results (P < 0.01). The most common presentation was STEMI, with (45%) most in ACS young patients. The angiographic pattern showed single vessel disease (SVD) in 49%, double vessel disease (DVD) in 17% and triple vessel disease (TVD) was found in 10%, and Left Artery Disease (LAD) (54%) was present to be the most common involved artery. Conclusion: It is concluded that the male sex was predominant in ACS young age patients. SVD was the common coronary angiographic finding. Risk factors showed significant results towards CAD and common presentations.

Keywords: coronary artery disease, Non-ST elevation myocardial infarction, ST elevation myocardial infarction, unstable angina, acute coronary syndrome

Procedia PDF Downloads 164

Authors: Li Yu, Chenlu Jiao, Hongrun Xin, Yan Wang, Kaiyang Wang

Abstract:

In order to study the impact of various factors on the housing price, we propose to build different prediction models based on deep learning to determine the existing data of the real estate in order to more accurately predict the housing price or its changing trend in the future. Considering that the factors which affect the housing price vary widely, the proposed prediction models include two categories. The first one is based on multiple characteristic factors of the real estate. We built Convolution Neural Network (CNN) prediction model and Long Short-Term Memory (LSTM) neural network prediction model based on deep learning, and logical regression model was implemented to make a comparison between these three models. Another prediction model is time series model. Based on deep learning, we proposed an LSTM-1 model purely regard to time series, then implementing and comparing the LSTM model and the Auto-Regressive and Moving Average (ARMA) model. In this paper, comprehensive study of the second-hand housing price in Beijing has been conducted from three aspects: crawling and analyzing, housing price predicting, and the result comparing. Ultimately the best model program was produced, which is of great significance to evaluation and prediction of the housing price in the real estate industry.

Keywords: deep learning, convolutional neural network, LSTM, housing prediction

Procedia PDF Downloads 306

Authors: Rana Alkattan

Abstract:

Aim: This study aims to identify and analyze the factors predicting the professional clinical competency among newly recruited registered nurses. In addition, it aims to explore factors significantly correlated with high and low professional clinical competency score. Method: A descriptive analytical is applied in this study, cross-sectional which conducted between June 2012 and June 2013 at King Abdulaziz University Hospital, as one of the largest governmental university tertiary Hospital in Saudi Arabia. A survey questionnaire was designed to collect data. And then, data were analyzed using the SPSS. Results: A total of the 86 nurses provided valid responses. 69 were female and 17 were male. The majority of the participants in this study were married, from the Philippines, between 20-29 years old. The majority had certified university bachelor’s degree in nursing, as well as had prior experience in nursing between 1 to 5 years. There are two categories emerged from the data, which significantly correlated with nurses' professional competence and development. The first was the newly employed registered nurses demographic characteristic (correlation coefficients 0.154 to 0.470, P < 0.05), while the second was the list of studied environmental factors except 'job rotation factor' (correlation coefficients 0.122 to 0.540, P < 0.01). However, nurses' attitude including motivation and confidence were not associated with nurse's professional competency. Conclusion: that nurses' professional competence development is a process affected by certain personal demographic and environmental factors which will enable newly graduates nurses to provide safe effective patients' care and maintain their career responsibilities.

Keywords: clinical, competence, development nurses professional, registered

Procedia PDF Downloads 355

Authors: Seyed Sobhan Alvani, Mohammad Gohari

Abstract:

By developing cities and increasing the population, traffic congestion has become a vital problem. Due to this crisis, urban designers try to present solutions to decrease this difficulty. On the other hand, predicting the model with perfect accuracy is essential for solution-providing. The current study presents a model based on artificial intelligence which can predict traffic index based on city population, growth rate, and area. The accuracy of the model was evaluated, which is acceptable and it is around 90%. Thus, urban designers and planners can employ it for predicting traffic index in the future to provide strategies.

Keywords: traffic index, population growth rate, cities wideness, artificial neural network

Procedia PDF Downloads 40

Authors: Shital Patil, Surendra Bhosale

Abstract:

Cardiac diseases are the leading causes of mortality and morbidity in the world, from recent few decades accounting for a large number of deaths have emerged as the most life-threatening disorder globally. Machine learning and Artificial intelligence have been playing key role in predicting the heart diseases. A relevant set of feature can be very helpful in predicting the disease accurately. In this study, we proposed a comparative analysis of 4 different features selection methods and evaluated their performance with both raw (Unbalanced dataset) and sampled (Balanced) dataset. The publicly available Z-Alizadeh Sani dataset have been used for this study. Four feature selection methods: Data Analysis, minimum Redundancy maximum Relevance (mRMR), Recursive Feature Elimination (RFE), Chi-squared are used in this study. These methods are tested with 8 different classification models to get the best accuracy possible. Using balanced and unbalanced dataset, the study shows promising results in terms of various performance metrics in accurately predicting heart disease. Experimental results obtained by the proposed method with the raw data obtains maximum AUC of 100%, maximum F1 score of 94%, maximum Recall of 98%, maximum Precision of 93%. While with the balanced dataset obtained results are, maximum AUC of 100%, F1-score 95%, maximum Recall of 95%, maximum Precision of 97%.

Keywords: cardio vascular diseases, machine learning, feature selection, SMOTE

Procedia PDF Downloads 118

Authors: Riktesh Srivastava

Abstract:

Online Shopping have established an astonishing evolution in the last few years. And it is now apparent that B2C architecture is becoming progressively imperative channel for even traditional brick and mortar type traders as well. In this completion knowing customers and predicting behavior are extremely important. More important, when any customer logs onto the B2C architecture, the traces of their buying patterns can be stored and used for future predictions. Such a prediction is called Customer Lifetime Value (CLV). Earlier, we used Net Present Value to do so, however, it ignores two important aspects of B2C architecture, “market risks” and “big amount of customer data”. Now, we use RFM- Recency, Frequency and Monetary Value to estimate the CLV, and as the term exemplifies, market risks, is well sheltered. Big Data Analysis is also roofed in RFM, which gives real exploration of the Big Data and lead to a better estimation for future cash flow from customers. In the present paper, 6 factors (collected from varied sources) are used to determine as to what attracts the customers to the B2C architecture. For these 6 factors, RFM is computed for 3 years (2013, 2014 and 2015) respectively. CLV and Revenue are the two parameters defined using RFM analysis, which gives the clear picture of the future predictions.

Keywords: CLV, RFM, revenue, recency, frequency, monetary value

Procedia PDF Downloads 220

Authors: Bakr Gomaa

Abstract:

Cross ventilation is an important and practical mean to achieve thermal comfort and conserve energy. This is especially true in the breezy waterfront settings. However, due to a number of factors, cross ventilation in buildings is usually studied by using oversimplified scenarios. It is then reasonable to study the impact of complex set of factors on the accuracy of predicting air flow rate because of wind driven cross ventilation. The objective of this paper is to provide architects with the tools necessary to achieve natural ventilation for cooling purposes in a waterfront urban canyon context. Also, urban canyons have not received much attention in terms of their impact on cross ventilation, and while we know how the wind flows between buildings in different urban canyon settings, the effect of the parallel-to-the-wind urban canyon on cross ventilation in buildings remains unclear. For this, we use detailed weather data, boundary layer correction factor, and CFD simulations to study the pressure patterns that form on the canyons surfaces in the case study of Alexandria. We found that the simplified numerical methods of calculating the cross ventilation in buildings can lead to inaccurate design decisions.

Keywords: cross ventilation, Alexandria, CFD, urban canyon

Procedia PDF Downloads 254

Authors: D. Supaporn, B. Julaluk

Abstract:

The purposes of this study were to study symptom cluster, functional status and quality of life of patients with chronic obstructive pulmonary disease (COPD), and to examine factors related to and predicting symptom cluster, functional status and quality of life of COPD patients. The sample was 180 COPD patients multi-stage random sampling from 4 hospitals in the eastern region, Thailand. The research instruments were 8 questionnaires and recorded forms measuring personal and illness data, co-morbidity, physical and psychological symptom, health status perception, social support, and regimen adherence, functional status and quality of life. Spearman rank and Pearson correlation coefficient, exploratory factors analysis and standard multiple regression were used to analyzed data. The findings revealed that two symptom clusters were generated: physical symptom cluster including dyspnea, fatigue and insomnia; and, psychological symptom cluster including anxiety and depression. Scores of physical symptom cluster was at moderate level while that of psychological symptom cluster was at low level. Scores on functional status, social support and overall regimen adherence were at good level whereas scores on quality of life and health status perception were at moderate level. Disease severity was positively related to physical symptom cluster, psychological symptom cluster and quality of life, and was negatively related to functional status at a moderate level (rs = .512, .509, .588 and -.611, respectively). Co-morbidity was positively related to physical symptom cluster and psychological symptom cluster at a low level (r = .179 and .176, respectively). Regimen adherence was negatively related to quality of life and psychological symptom cluster at a low level (r=-.277 and -.309, respectively), and was positively related to functional status at a moderate level (r=.331). Health status perception was negatively related to physical symptom cluster, psychological symptom cluster and quality of life at a moderate to high level (r = -.567, -.640 and -.721, respectively) and was positively related to functional status at a high level (r = .732). Social support was positively related to functional status (r=.235) and was negatively related to quality of life at a low level (r=-.178). Physical symptom cluster was negatively related to functional status (r= -.490) and was positively related to quality of life at a moderate level (r=.566). Psychological symptom cluster was negatively related to functional status and was positively related to quality of life at a moderate level (r= -.566 and .559, respectively). Disease severity, co-morbidity and health status perception could predict 40.2% of the variance of physical symptom cluster. Disease severity, co-morbidity, regimen adherence and health status perception could predict 49.8% of the variance of psychological symptom cluster. Co-morbidity, regimen adherence and health status perception could predict 65.0% of the variance of functional status. Disease severity, health status perception and physical symptom cluster could predict 60.0% of the variance of quality of life in COPD patients. The results of this study can be used for enhancing quality of life of COPD patients.

Keywords: chronic obstructive pulmonary disease, functional status, quality of life, symptom cluster

Procedia PDF Downloads 558

Authors: Omar Nouri, Wafa Mnejja, Fatma Dhouib, Syrine Zouari, Wicem Siala, Ilhem Charfeddine, Afef Khanfir, Leila Farhat, Nejla Fourati, Jamel Daoud

Abstract:

Purpose and Objective: Intensity modulated radiation (IMRT) technique, associated with induction chemotherapy (IC) and/or concomitant chemotherapy (CC), is actually the recommended treatment modality for nasopharyngeal carcinomas (NPC). The aim of this study was to evaluate the therapeutic results and the patterns of relapse with this treatment protocol. Material and methods: A retrospective monocentric study of 145 patients with NPC treated between June 2016 and July 2021. All patients received IMRT with integrated simultaneous boost (SIB) of 33 daily fractions at a dose of 69.96 Gy for high-risk volume, 60 Gy for intermediate risk volume and 54 Gy for low-risk volume. The high-risk volume dose was 66.5 Gy in children. Survival analysis was performed according to the Kaplan-Meier method, and the Log-rank test was used to compare factors that may influence survival. Results: Median age was 48 years (11-80) with a sex ratio of 2.9. One hundred-twenty tumors (82.7%) were classified as stages III-IV according to the 2017 UICC TNM classification. Ten patients (6.9%) were metastatic at diagnosis. One hundred-thirty-five patient (93.1%) received IC, 104 of which (77%) were TPF-based (taxanes, cisplatin and 5 fluoro-uracil). One hundred-thirty-eight patient (95.2%) received CC, mostly cisplatin in 134 cases (97%). After a median follow-up of 50 months [22-82], 46 patients (31.7%) had a relapse: 12 (8.2%) experienced local and/or regional relapse after a median of 18 months [6-43], 29 (20%) experienced distant relapse after a median of 9 months [2-24] and 5 patients (3.4%) had both. Thirty-five patients (24.1%) died, including 5 (3.4%) from a cause other than their cancer. Three-year overall survival (OS), cancer specific survival, disease free survival, metastasis free survival and loco-regional free survival were respectively 78.1%, 81.3%, 67.8%, 74.5% and 88.1%. Anatomo-clinic factors predicting OS were age > 50 years (88.7 vs. 70.5%; p=0.004), diabetes history (81.2 vs. 66.7%; p=0.027), UICC N classification (100 vs. 95 vs. 77.5 vs. 68.8% respectively for N0, N1, N2 and N3; p=0.008), the practice of a lymph node biopsy (84.2 vs. 57%; p=0.05), and UICC TNM stages III-IV (93.8 vs. 73.6% respectively for stage I-II vs. III-IV; p=0.044). Therapeutic factors predicting OS were a number of CC courses (less than 4 courses: 65.8 vs. 86%; p=0.03, less than 5 courses: 71.5 vs. 89%; p=0.041), a weight loss > 10% during treatment (84.1 vs. 60.9%; p=0.021) and a total cumulative cisplatin dose, including IC and CC, < 380 mg/m² (64.4 vs. 87.6%; p=0.003). Radiotherapy delay and total duration did not significantly affect OS. No grade 3-4 late side effects were noted in the evaluable 127 patients (87.6%). The most common toxicity was dry mouth which was grade 2 in 47 cases (37%) and grade 1 in 55 cases (43.3%).Conclusion: IMRT for nasopharyngeal carcinoma granted a high loco-regional control rate for patients during the last five years. However, distant relapses remain frequent and conditionate the prognosis. We identified many anatomo-clinic and therapeutic prognosis factors. Therefore, high-risk patients require a more aggressive therapeutic approach, such as radiotherapy dose escalation or adding adjuvant chemotherapy.

Keywords: therapeutic results, prognostic factors, intensity-modulated radiotherapy, nasopharyngeal carcinoma

Procedia PDF Downloads 64

Authors: Osayande Pascal Omondiagbe, Sherlock a Licorish

Abstract:

Stack Overflow is a popular community question and answer portal which is used by practitioners to solve technology-related challenges during software development. Previous studies have shown that this forum is becoming a substitute for official software programming languages documentation. While tools have looked to aid developers by presenting interfaces to explore Stack Overflow, developers often face challenges searching through many possible answers to their questions, and this extends the development time. To this end, researchers have provided ways of predicting acceptable Stack Overflow answers by using various modeling techniques. However, less interest is dedicated to examining the performance and quality of typically used modeling methods, and especially in relation to models’ and features’ complexity. Such insights could be of practical significance to the many practitioners that use Stack Overflow. This study examines the performance and quality of various modeling methods that are used for predicting acceptable answers on Stack Overflow, drawn from 2014, 2015 and 2016. Our findings reveal significant differences in models’ performance and quality given the type of features and complexity of models used. Researchers examining classifiers’ performance and quality and features’ complexity may leverage these findings in selecting suitable techniques when developing prediction models.

Keywords: feature selection, modeling and prediction, neural network, random forest, stack overflow

Procedia PDF Downloads 132

Authors: Sireethorn Nimitvilai, Ussanee Poolvivatchaikarn, Nuchanart Tomeun

Abstract:

Objective: To determine the simple laboratory parameters to predict disease severity among COVID-19 patients in resource-limited settings. Material and methods: A retrospective cohort study was conducted at Nakhonpathom Hospital, a 722-bed tertiary care hospital, with an average of 50,000 admissions per year, during April 15 and May 15, 2021. Eligible patients were adults aged ≥ 15 years who were hospitalized with COVID-19. Baseline characteristics, comorbid conditions ad laboratory findings at admission were collected. Predictive factors for severe COVID-19 infection were analyzed. Result: There were 207 patients (79 male and 128 female) and the mean age was 46.7 (16.8) years. Of these, 39 cases (18.8%) were severe and 168 (81.2%) cases were non-severe. Factors associated with severe COVID-19 were neutrophil to lymphocyte ratio ≥ 4 (OR 8.1, 95%CI 2.3-20.3, P < 0.001) and C-reactive protein to albumin ratio ≥ 10 (OR 3.49, 95%CI 1.3-9.1, p 0.01). Conclusions: Complete blood counts, C-reactive protein and albumin are simple, inexpensive, widely available tests and can be used to predict severe COVID-19 in resource-limited settings.

Keywords: COVID-19, predictor of severity, resource-limiting settings, simple laboratory parameters

Procedia PDF Downloads 180

Authors: M. K. Yusuf, W. O. Hamman, U. E. Umana, S. B. Oladele

Abstract:

Background: Dilatation of the inferior vena cava (IVC) is used as the ultrasonic diagnostic feature in patients suspected of congestive heart failure. The IVC diameter has been reported to vary among the various body mass indexes (BMI) and body shape indexes (ABSI). Knowledge of these variations is useful in precision diagnoses of CHF by imaging scientists. Aim: The study aimed to establish an equation for predicting the ultrasonic mean diameter of the IVC among the various BMI/ABSI of inhabitants of Azare, Bauchi State-Nigeria. Methodology: Two hundred physically healthy adult subjects of both sexes were classified into under, normal, over, and obese weights using their BMIs after selection using a structured questionnaire following their informed consent for an abdominal ultrasound scan. The probe was placed on the midline of the body, halfway between the xiphoid process and the umbilicus, with the marker on the probe directed towards the patient's head to obtain a longitudinal view of the IVC. The maximum IVC diameter was measured from the subcostal view using the electronic caliper of the scan machine. The mean value of each group was obtained, and the results were analysed. Results: A novel equation {(IVC Diameter = 1.04 +0.01(X) where X= BMI} has been generated for determining the IVC diameter among the populace. Conclusion: An equation for predicting the IVC diameter from individual BMI values in apparently healthy subjects has been established.

Keywords: equation, ultrasonic, IVC diameter, body adiposities

Procedia PDF Downloads 72

Authors: RuiJin Zhang, HengJiang Cai, JinSong Gui

Abstract:

It takes Patinopecten yessoensis larvae more than 20 days from spawning to settlement. Due to the natural environmental factors such as current, Patinopecten yessoensis larvae are transported to a distance more than hundreds of kilometers, leading to a high instability of their spatial and temporal distribution and great difficulties in the natural spat collection. Therefore predicting the distribution is of great significance to improve the operating efficiency of the collecting. Hydrodynamic model of Northern China Yellow Sea was established and the motions equations of physical oceanography and verified by the tidal harmonic constants and the measured data velocities of Dalian Bay. According to the passivity drift characteristics of the larvae, combined with the hydrodynamic model and the particle tracking model, the spatial and temporal distribution prediction model was established and the spatial and temporal distribution of the larvae under the influence of flow and wind were simulated. It can be concluded from the model results: ocean currents have greatest impacts on the passive drift path and diffusion of Patinopecten yessoensis larvae; the impact of wind is also important, which changed the direction and speed of the drift. Patinopecten yessoensis larvae were generated in the sea along Zhangzi Island and Guanglu-Dachangshan Island, but after two months, with the impact of wind and currents, the larvae appeared in the west of Dalian and the southern of Lvshun, and even in Bohai Bay. The model results are consistent with the relevant literature on qualitative analysis, and this conclusion explains where the larvae come from in the perspective of numerical simulation.

Keywords: numerical simulation, Patinopecten yessoensis larvae, predicting model, spatial and temporal distribution

Procedia PDF Downloads 304

Authors: Paula A. Cruise, Carvell McLeary

Abstract:

Employee turnover leads to lowered productivity, decreased morale and work quality, and psychological effects associated with employee separation and replacement. Yet, it remains unknown why talented employees willingly withdraw from organizations. This uncertainty is worsened as studies; a) priorities organizational over individual predictors resulting in restriction in range in turnover measurement; b) focus on actual rather than intended turnover thereby limiting conceptual understanding of the turnover construct and its relationship with other variables and; c) produce inconsistent findings across cultures, contexts and industries despite a clear need for a unified perspective. The current study addressed these gaps by adopting the theory of planned behavior (TPB) framework to examine socio-cognitive factors in organizational trust and individual turnover intentions among bankers and energy employees in Jamaica. In a comparative study of n=369 [n_bank= 264; male=57 (22.73%); n_energy =105; male =45 (42.86)], it was hypothesized that organizational trust was a predictor of employee turnover intention, and the effect of individual, group, cognitive and socio-affective variables varied across industry. Findings from structural equation modelling confirmed the hypothesis, with a model of both cognitive and socio-affective variables being a better fit [CMIN (χ²) = 800.067, df = 364, p ≤ .000; CFI = 0.950; RMSEA = 0.057 with 90% C.I. (0.052 - 0.062); PCLOSE = 0.016; PNFI = 0.818 in predicting turnover intention. The findings are discussed in relation to socio-cognitive components of trust models and predicting negative employee behaviors across cultures and industries.

Keywords: context-specific organizational trust, cross-cultural psychology, theory of planned behavior, employee turnover intention

Procedia PDF Downloads 248

Authors: Zelalem Markos Borko

Abstract:

Work-related stress is a reaction that occurs when the work weight progress toward becoming excessive. Therefore, unless properly managed, stress leads to high employee turnover, decreased performance, illness and absenteeism. Yet, little has been addressed regarding work-related stress and its predictors in the study area. Therefore, the objective of this study was to assess stress prevalence and its predictors in the study area. To that effect, a cross-sectional study design was conducted on 281 employees from the Ethiopian Federal Bureau of Investigation by using stratified random sampling techniques. Survey questionnaire scales were employed to collect data. Data were analyzed by percentage, Pearson correlation coefficients, simple linear regression, multiple linear regressions, independent t-test and one-way ANOVA statistical techniques. In the present study13.9% of participants faced high stress, whereas 13.5% of participants faced low stress and the rest 72.6% of officers experienced moderate stress. There is no significant group difference among workers due to age, gender, marital status, educational level, years of service and police rank. This study concludes that factors such as role conflict, performance over-utilization, role ambiguity, and qualitative and quantitative role overload together predict 39.6% of work-related stress. This indicates that 60.4% of the variation in stress is explained by other factors, so other additional research should be done to identify additional factors predicting stress. To prevent occupational stress among police, the Ethiopian Federal Bureau of Investigation should develop strategies based on factors that will help to develop stress reduction management.

Keywords: work-related stress, Ethiopian federal bureau of investigation, predictors, Addis Ababa

Procedia PDF Downloads 70

Authors: Roham Rafiee, Behzad Mazhari

Abstract:

Composite structures, having incredible properties, have gained considerable popularity in the last few decades. Among all types, polymer matrix composites are being used extensively due to their unique characteristics including low weight, convenient fabrication process and low cost. Having polymer as matrix, these type of composites show different creep behavior when compared to metals and even other types of composites since most polymers undergo creep even in room temperature. One of the most challenging topics in creep is to introduce new techniques for predicting long term creep behavior of materials. Depending on the material which is being studied the appropriate method would be different. Methods already proposed for predicting long term creep behavior of polymer matrix composites can be divided into five categories: (1) Analytical Modeling, (2) Empirical Modeling, (3) Superposition Based Modeling (Semi-empirical), (4) Rheological Modeling, (5) Finite Element Modeling. Each of these methods has individual characteristics. Studies have shown that none of the mentioned methods can predict long term creep behavior of all PMC composites in all circumstances (loading, temperature, etc.) but each of them has its own priority in different situations. The reason to this issue can be found in theoretical basis of these methods. In this study after a brief review over the background theory of each method, they are compared in terms of their applicability in predicting long-term behavior of composite structures. Finally, the explained materials are observed through some experimental studies executed by other researchers.

Keywords: creep, comparative study, modeling, composite materials

Procedia PDF Downloads 441

Authors: Zane Turner, Kevin Labille, Susan Gauch

Abstract:

Sentiment analysis is a broad and expanding field that aims to extract and classify opinions from textual data. Lexicon-based approaches are based on the use of a sentiment lexicon, i.e., a list of words each mapped to a sentiment score, to rate the sentiment of a text chunk. Our work focuses on predicting stock price change using a sentiment lexicon built from financial conference call logs. We present a method to generate a sentiment lexicon based upon an existing probabilistic approach. By using a domain-specific lexicon, we outperform traditional techniques and demonstrate that domain-specific sentiment lexicons provide higher accuracy than generic sentiment lexicons when predicting stock price change.

Keywords: computational finance, sentiment analysis, sentiment lexicon, stock movement prediction

Procedia PDF Downloads 127

Authors: Zane Turner, Kevin Labille, Susan Gauch

Abstract:

Sentiment analysis is a broad and expanding field that aims to extract and classify opinions from textual data. Lexicon-based approaches are based on the use of a sentiment lexicon, i.e., a list of words each mapped to a sentiment score, to rate the sentiment of a text chunk. Our work focuses on predicting stock price change using a sentiment lexicon built from financial conference call logs. We introduce a method to generate a sentiment lexicon based upon an existing probabilistic approach. By using a domain-specific lexicon, we outperform traditional techniques and demonstrate that domain-specific sentiment lexicons provide higher accuracy than generic sentiment lexicons when predicting stock price change.

Keywords: computational finance, sentiment analysis, sentiment lexicon, stock movement prediction

Procedia PDF Downloads 170

Authors: Abubakar Mukhtar Yakasai, Muhammad Tahir Jan

Abstract:

Purpose: This paper is aimed at exploring factors influencing online shopping intention among the young consumers in Nigeria. Design/Methodology/approach: The paper adopted and extended Technology Acceptance Model (TAM) as the basis for literature review. Additionally, the paper proposed a framework with the inclusion of culture as a moderating factor of consumer online shopping intention among consumers in Nigeria. Findings: Despite high rate of internet penetration in Nigerian, as well as the rapid advancement of online shopping in the world, little attention was paid to this important revolution specifically among Nigeria’s consumers. Based on the review of extant literature, the TAM extended to include perceived risk and enjoyment (PR and PE) was discovered to be a better alternative framework for predicting Nigeria’s young consumers’ online shopping intention. The moderating effect of culture in the proposed model is shown to help immensely in ascertaining differences, if any, between various cultural groups among online shoppers in Nigeria. Originality/ value: The critical analysis of different factors will assist practitioners (like online retailers, e-marketing managers, website developers, etc.) by signifying which combinations of factors can best predict consumer online shopping behaviour in particular instances, thereby resulting in effective value delivery. Online shopping is a newly adopted technology in Nigeria, hence the paper will give a clear focus for effective e-marketing strategy. In addition, the proposed framework in this paper will guide future researchers by providing a tool for systematic evaluation and testing of real empirical situation of online shopping in Nigeria.

Keywords: online shopping, perceived ease of use, perceived usefulness, perceived enjoyment, technology acceptance model, Nigeria

Procedia PDF Downloads 279

Authors: Brindha Senthil Kumar, Payel Chakraborty, Senthil Kumar Nachimuthu, Arindam Maitra, Prem Nath

Abstract:

Gastric cancer is predominantly caused by demographic and diet factors as compared to other cancer types. The aim of the study is to predict Early Gastric Cancer (ECG) from diet and lifestyle factors using supervised machine learning algorithms. For this study, 160 healthy individual and 80 cases were selected who had been followed for 3 years (2016-2019), at Civil Hospital, Aizawl, Mizoram. A dataset containing 11 features that are core risk factors for the gastric cancer were extracted. Supervised machine algorithms: Logistic Regression, Naive Bayes, Support Vector Machine (SVM), Multilayer perceptron, and Random Forest were used to analyze the dataset using Python Jupyter Notebook Version 3. The obtained classified results had been evaluated using metrics parameters: minimum_false_positives, brier_score, accuracy, precision, recall, F1_score, and Receiver Operating Characteristics (ROC) curve. Data analysis results showed Naive Bayes - 88, 0.11; Random Forest - 83, 0.16; SVM - 77, 0.22; Logistic Regression - 75, 0.25 and Multilayer perceptron - 72, 0.27 with respect to accuracy and brier_score in percent. Naive Bayes algorithm out performs with very low false positive rates as well as brier_score and good accuracy. Naive Bayes algorithm classification results in predicting ECG showed very satisfactory results using only diet cum lifestyle factors which will be very helpful for the physicians to educate the patients and public, thereby mortality of gastric cancer can be reduced/avoided with this knowledge mining work.

Keywords: Early Gastric cancer, Machine Learning, Diet, Lifestyle Characteristics

Procedia PDF Downloads 161

Authors: Chun-Qing Li, Hassan Baji, Wei Yang

Abstract:

Corrosion of steel in reinforced concrete structures is a major problem worldwide. The volume expansion of corrosion products causes concrete cover cracking, which could lead to delamination of concrete cover. The time to cover cracking plays a key role to the assessment of serviceability of reinforced concrete structures subjected to corrosion. Many analytical, numerical, and empirical models have been developed to predict the time to cracking initiation due to corrosion. In this study, a numerical model based on finite element modeling of corrosion-induced cracking process is used. In order to predict the service life based on time to cover initiation, the numerical approach is coupled with a probabilistic procedure. In this procedure, all the influential factors affecting time to cover cracking are modeled as random variables. The results show that the time to cover cracking is highly variables. It is also shown that rust product expansion ratio and the size of more porous concrete zone around the rebar are the most influential factors in predicting service life of corrosion-affected structures.

Keywords: corrosion, crack width, probabilistic, service life

Procedia PDF Downloads 207

Authors: Saahith M. S., Sivakami R.

Abstract:

In the realm of football analytics, particularly focusing on predicting football player performance, the ability to forecast player success accurately is of paramount importance for teams, managers, and fans. This study introduces an elaborate examination of predicting football player performance through the integration of data visualization methods and machine learning algorithms. The research entails the compilation of an extensive dataset comprising player attributes, conducting data preprocessing, feature selection, model selection, and model training to construct predictive models. The analysis within this study will involve delving into feature significance using methodologies like Select Best and Recursive Feature Elimination (RFE) to pinpoint pertinent attributes for predicting player performance. Various machine learning algorithms, including Random Forest, Decision Tree, Linear Regression, Support Vector Regression (SVR), and Artificial Neural Networks (ANN), will be explored to develop predictive models. The evaluation of each model's performance utilizing metrics such as Mean Squared Error (MSE) and R-squared will be executed to gauge their efficacy in predicting player performance. Furthermore, this investigation will encompass a top player analysis to recognize the top-performing players based on the anticipated overall performance scores. Nationality analysis will entail scrutinizing the player distribution based on nationality and investigating potential correlations between nationality and player performance. Positional analysis will concentrate on examining the player distribution across various positions and assessing the average performance of players in each position. Age analysis will evaluate the influence of age on player performance and identify any discernible trends or patterns associated with player age groups. The primary objective is to predict a football player's overall performance accurately based on their individual attributes, leveraging data-driven insights to enrich the comprehension of player success on the field. By amalgamating data visualization and machine learning methodologies, the aim is to furnish valuable tools for teams, managers, and fans to effectively analyze and forecast player performance. This research contributes to the progression of sports analytics by showcasing the potential of machine learning in predicting football player performance and offering actionable insights for diverse stakeholders in the football industry.

Keywords: football analytics, player performance prediction, data visualization, machine learning algorithms, random forest, decision tree, linear regression, support vector regression, artificial neural networks, model evaluation, top player analysis, nationality analysis, positional analysis

Procedia PDF Downloads 38

Authors: Shamsulhaq Amin

Abstract:

Unbound granular materials (UGMs) are pivotal in ensuring long-term quality, especially in the layers under the surface of flexible pavements and other constructions. This study seeks to better understand the behavior of the UGMs by looking at popular models for predicting lasting deformation under various levels of stresses and load cycles. These models focus on variables such as the number of load cycles, stress levels, and features specific to materials and were evaluated on the basis of their ability to accurately predict outcomes. The study showed that these factors play a crucial role in how well the models work. Therefore, the research highlights the need to look at a wide range of stress situations to more accurately predict how much the UGMs bend or shift. The research looked at important factors, like how permanent deformation relates to the number of times a load is applied, how quickly this phenomenon happens, and the shakedown effect, in two different types of UGMs: granite and limestone. A detailed study was done over 100,000 load cycles, which provided deep insights into how these materials behave. In this study, a number of factors, such as the level of stress applied, the number of load cycles, the density of the material, and the moisture present were seen as the main factors affecting permanent deformation. It is vital to fully understand these elements for better designing pavements that last long and handle wear and tear. A series of laboratory tests were performed to evaluate the mechanical properties of materials and acquire model parameters. The testing included gradation tests, CBR tests, and Repeated load triaxial tests. The repeated load triaxial tests were crucial for studying the significant components that affect deformation. This test involved applying various stress levels to estimate model parameters. In addition, certain model parameters were established by regression analysis, and optimization was conducted to improve outcomes. Afterward, the material parameters that were acquired were used to construct graphs for each model. The graphs were subsequently compared to the outcomes obtained from the repeated load triaxial testing. Additionally, the models were evaluated to determine if they demonstrated the two inherent deformation behaviors of materials when subjected to repetitive load: the initial phase, post-compaction, and the second phase volumetric changes. In this study, using log-log graphs was key to making the complex data easier to understand. This method made the analysis clearer and helped make the findings easier to interpret, adding both precision and depth to the research. This research provides important insight into picking the right models for predicting how these materials will act under expected stress and load conditions. Moreover, it offers crucial information regarding the effect of load cycle and permanent deformation as well as the shakedown effect on granite and limestone UGMs.

Keywords: permanent deformation, unbound granular materials, load cycles, stress level

Procedia PDF Downloads 39

Authors: Sai Sankalp Vemavarapu

Abstract:

This paper discusses the application of machine learning in the field of transportation engineering for predicting engineering properties of pavement more accurately and efficiently. Predicting the elastic properties aid us in assessing the current road conditions and taking appropriate measures to avoid any inconvenience to commuters. This improves the longevity and sustainability of the pavement layer while reducing its overall life-cycle cost. As an example, we have implemented differential evolution (DE) in the back-calculation of the elastic modulus of multi-layered pavement. The proposed DE global optimization back-calculation approach is integrated with a forward response model. This approach treats back-calculation as a global optimization problem where the cost function to be minimized is defined as the root mean square error in measured and computed deflections. The optimal solution which is elastic modulus, in this case, is searched for in the solution space by the DE algorithm. The best DE parameter combinations and the most optimum value is predicted so that the results are reproducible whenever the need arises. The algorithm’s performance in varied scenarios was analyzed by changing the input parameters. The prediction was well within the permissible error, establishing the supremacy of DE.

Keywords: cost function, differential evolution, falling weight deflectometer, genetic algorithm, global optimization, metaheuristic algorithm, multilayered pavement, pavement condition assessment, pavement layer moduli back calculation

Procedia PDF Downloads 164

Authors: Habtamu Ayenew Asegie

Abstract:

Wealth, as opposed to income or consumption, implies a more stable and permanent status. Due to natural and human-made difficulties, households' economies will be diminished, and their well-being will fall into trouble. Hence, governments and humanitarian agencies offer considerable resources for poverty and malnutrition reduction efforts. One key factor in the effectiveness of such efforts is the accuracy with which low-income or poor populations can be identified. As a result, this study aims to predict a household’s wealth status using ensemble Machine learning (ML) algorithms. In this study, design science research methodology (DSRM) is employed, and four ML algorithms, Random Forest (RF), Adaptive Boosting (AdaBoost), Light Gradient Boosted Machine (LightGBM), and Extreme Gradient Boosting (XGBoost), have been used to train models. The Ethiopian Demographic and Health Survey (EDHS) dataset is accessed for this purpose from the Central Statistical Agency (CSA)'s database. Various data pre-processing techniques were employed, and the model training has been conducted using the scikit learn Python library functions. Model evaluation is executed using various metrics like Accuracy, Precision, Recall, F1-score, area under curve-the receiver operating characteristics (AUC-ROC), and subjective evaluations of domain experts. An optimal subset of hyper-parameters for the algorithms was selected through the grid search function for the best prediction. The RF model has performed better than the rest of the algorithms by achieving an accuracy of 96.06% and is better suited as a solution model for our purpose. Following RF, LightGBM, XGBoost, and AdaBoost algorithms have an accuracy of 91.53%, 88.44%, and 58.55%, respectively. The findings suggest that some of the features like ‘Age of household head’, ‘Total children ever born’ in a family, ‘Main roof material’ of their house, ‘Region’ they lived in, whether a household uses ‘Electricity’ or not, and ‘Type of toilet facility’ of a household are determinant factors to be a focal point for economic policymakers. The determinant risk factors, extracted rules, and designed artifact achieved 82.28% of the domain expert’s evaluation. Overall, the study shows ML techniques are effective in predicting the wealth status of households.

Keywords: ensemble machine learning, households wealth status, predictive model, wealth status prediction

Procedia PDF Downloads 38

Authors: Behzad Niknam, Kourosh Shahriar, Hassan Madani

Abstract:

This paper demonstrates the applicability of Hybrid Neural Networks that combine with back propagation networks (BPN) and Genetic Algorithms (GAs) for predicting the flame length of tunnel fire A hybrid neural network model has been developed to predict the flame length of tunnel fire based parameters such as Fire Heat Release rate, air velocity, tunnel width, height and cross section area. The network has been trained with experimental data obtained from experimental work. The hybrid neural network model learned the relationship for predicting the flame length in just 3000 training epochs. After successful learning, the model predicted the flame length.

Keywords: tunnel fire, flame length, ANN, genetic algorithm

Procedia PDF Downloads 643

Authors: Abdreheman Seid Abdella

Abstract:

This study examined instructors willingness, self-efficacy beliefs, attitudes and knowledge about provisions of instructional accommodations for students with disabilities in universities. Major concepts used in this study operationally defined and some models of disability were reviewed. Questionnaires were distributed to a total of 181 instructors from four universities and quantitative data was generated. Then to analyze the data, appropriate methods of data analysis were employed. The result indicated that on average instructors had positive willingness, strong self-efficacy beliefs and positive attitudes towards providing instructional accommodations. In addition, the result showed that the majority of participants had moderate level of knowledge about provision of instructional accommodations. Concerning the relationship between instructors background variables and dependent variables, the result revealed that location of university and awareness raising training about Inclusive Education showed statistically significant relationship with all dependent variables (willingness, self-efficacy beliefs, attitudes and knowledge). On the other hand, gender and college/faculty did not show a statistically significant relationship. In addition, it was found that among the inter-correlation of dependent variables, the correlation between attitudes and willingness to provide accommodations was the strongest. Furthermore, using multiple linear regression analysis, this study also indicated that predictor variables like self-efficacy beliefs, attitudes, knowledge and teaching methodology training made statistically significant contribution to predicting the criterion willingness. Predictor variables like willingness and attitudes made statistically significant contribution to predicting self-efficacy beliefs. Predictor variables like willingness, Special Needs Education course and self-efficacy beliefs made statistically significant contribution to predict attitudes. Predictor variables like Special Needs Education courses, the location of university and willingness made statistically significant contribution to predicting knowledge. Finally, using exploratory factor analysis, this study showed that there were four components or factors each that represent the underlying constructs of willingness and self-efficacy beliefs to provide instructional accommodations items, five components for attitudes towards providing accommodations items and three components represent the underlying constructs for knowledge about provisions of instructional accommodations items. Based on the findings, recommendations were made for improving the situation of instructional accommodations in Ethiopian universities.

Keywords: willingness, self-efficacy belief, attitude, knowledge

Procedia PDF Downloads 270