Search results for: PREDICT score

Authors: Baladitya Swaika, Rahul Khatry

Abstract:

Computer Adaptive Tests (CATs) is one of the most efficient ways for testing the cognitive abilities of students. CATs are based on Item Response Theory (IRT) which is based on item selection and ability estimation using statistical methods of maximum information selection/selection from posterior and maximum-likelihood (ML)/maximum a posteriori (MAP) estimators respectively. This study aims at combining both classical and Bayesian approaches to IRT to create a dataset which is then fed to a neural network which automates the process of ability estimation and then comparing it to traditional CAT models designed using IRT. This study uses python as the base coding language, pymc for statistical modelling of the IRT and scikit-learn for neural network implementations. On creation of the model and on comparison, it is found that the Neural Network based model performs 7-10% worse than the IRT model for score estimations. Although performing poorly, compared to the IRT model, the neural network model can be beneficially used in back-ends for reducing time complexity as the IRT model would have to re-calculate the ability every-time it gets a request whereas the prediction from a neural network could be done in a single step for an existing trained Regressor. This study also proposes a new kind of framework whereby the neural network model could be used to incorporate feature sets, other than the normal IRT feature set and use a neural network’s capacity of learning unknown functions to give rise to better CAT models. Categorical features like test type, etc. could be learnt and incorporated in IRT functions with the help of techniques like logistic regression and can be used to learn functions and expressed as models which may not be trivial to be expressed via equations. This kind of a framework, when implemented would be highly advantageous in psychometrics and cognitive assessments. This study gives a brief overview as to how neural networks can be used in adaptive testing, not only by reducing time-complexity but also by being able to incorporate newer and better datasets which would eventually lead to higher quality testing.

Keywords: computer adaptive tests, item response theory, machine learning, neural networks

Procedia PDF Downloads 172

Authors: Roongtiwa Chobchuen, Angkana Srikhan, Pattra Wattanapan

Abstract:

Background: Neurogenic bowel is common condition after spinal cord injury. Most of spinal cord injured patients have motor weakness, mobility impairment which leads to constipation. Moreover, the neural pathway involving bowel function is interrupted. Therefore, the bowel management program should be implemented in nursing care in the earliest time after the onset of the disease to prevent the morbidity and mortality. Objective: To study the outcome of bowel management program of the patients with spinal cord injury who admitted for rehabilitation program. Study design: Descriptive study. Setting: Rehabilitation ward in Srinagarind Hospital. Populations: patients with subacute to chronic spinal cord injury who admitted at rehabilitation ward, Srinagarind hospital, aged over 18 years old. Instrument: The neurogenic bowel dysfunction score (NBDS) was used to determine the severity of neurogenic bowel. Procedure and statistical analysis: All participants were asked to complete the demographic data; age gender, duration of disease, diagnosis. The individual bowel function was assessed using NBDS at admission. The patients and caregivers were trained by nurses about the bowel management program which consisted of diet modification, abdominal massage, digital stimulation, stool evacuation including medication and physical activity. The outcome of the bowel management program was assessed by NBDS at discharge. The chi-square test was used to detect the difference in severity of neurogenic bowel at admission and discharge. Results: Sixteen spinal cord injured patients were enrolled in the study (age 45 ± 17 years old, 69% were male). Most of them (50%) were tetraplegia. On the admission, 12.5%, 12.5%, 43.75% and 31.25% were categorized as very minor (NBDS 0-6), minor (NBDS 7-9), moderate (NBDS 10-13) and severe (NBDS 14+) respectively. The severity of neurogenic bowel was decreased significantly at discharge (56.25%, 18.755%, 18.75% and 6.25% for very minor, minor, moderate and severe group respectively; p < 0.001) compared with NBDS at admission. Conclusions: Implementation of the effective bowel program decrease the severity of the neurogenic bowel in patient with spinal cord injury.

Keywords: neurogenic bowel, NBDS, spinal cord injury, bowel program

Procedia PDF Downloads 240

Authors: Vipul M. Patel, Hemantkumar B. Mehta

Abstract:

Technological innovations in electronic world demand novel, compact, simple in design, less costly and effective heat transfer devices. Closed Loop Pulsating Heat Pipe (CLPHP) is a passive phase change heat transfer device and has potential to transfer heat quickly and efficiently from source to sink. Thermal performance of a CLPHP is governed by various parameters such as number of U-turns, orientations, input heat, working fluids and filling ratio. The present paper is an attempt to predict the thermal performance of a CLPHP using Artificial Neural Network (ANN). Filling ratio and heat input are considered as input parameters while thermal resistance is set as target parameter. Types of neural networks considered in the present paper are radial basis, generalized regression, linear layer, cascade forward back propagation, feed forward back propagation; feed forward distributed time delay, layer recurrent and Elman back propagation. Linear, logistic sigmoid, tangent sigmoid and Radial Basis Gaussian Function are used as transfer functions. Prediction accuracy is measured based on the experimental data reported by the researchers in open literature as a function of Mean Absolute Relative Deviation (MARD). The prediction of a generalized regression ANN model with spread constant of 4.8 is found in agreement with the experimental data for MARD in the range of ±1.81%.

Keywords: ANN models, CLPHP, filling ratio, generalized regression, spread constant

Procedia PDF Downloads 287

Authors: Latif Duran, Erdem Aydin, Ahmet Baydin, Ali Kemal Erenler, Iskender Aksoy

Abstract:

Aim: In this retrospective study, we aim to contribute to the literature by presenting the proposals for taking measures to reduce the mortality by examining the demographic characteristics of the pediatric age group patients presenting with trauma and the factors that may cause mortality Material and Method: This study has been performed by retrospectively investigating the data obtained from the patient files and the hospital automation registration system of the pediatric trauma patients who applied to the Adult Emergency Department of the Ondokuz Mayıs University Medical Faculty between January 1, 2016, and December 31, 2016. Results: 289 of 415 patients involved in our study, were males. The median age was 11.3 years. The most common trauma mechanism was falling from the high. A significant statistical difference was found on the association between trauma mechanisms and gender. An increase in the number of trauma cases was found especially in the summer months. The study showed that thoracic and abdominal trauma was relevant to the increased mortality. Computerized tomography was the most common diagnostic imaging modality. The presence of subarachnoid hemorrhage has increased the risk of mortality by 62.3 fold. Eight of the patients (1.9%) died. Scoring systems were statistically significant to predict mortality. Conclusion: Children are vulnerable to trauma because of their unique anatomical and physiological differences compared to adult patient groups. It will be more successful in the mortality rate and in the post-traumatic healing process by administering the patient triage fast and most appropriate trauma centers in the prehospital period, management of the critical patients with the scoring systems and management with standard treatment protocols

Keywords: emergency service, pediatric patients, scoring systems, trauma, age groups

Procedia PDF Downloads 195

Authors: Makduma Zahan Badhan, M. Abdul Matin

Abstract:

A study has been undertaken to develop a fluvial stage-discharge rating curve for Jamuna River. Past Cross-sectional survey of Jamuna River reach within Sirajgonj and Tangail has been analyzed. The analysis includes the estimation of discharge carrying capacity, possible maximum scour depth and sediment transport capacity of the selected reaches. To predict the discharge and sediment carrying capacity, stream flow data which include cross-sectional area, top width, water surface slope and median diameter of the bed material of selected stations have been collected and some are calculated from reduced level data. A well-known resistance equation has been adopted and modified to a simple form in order to be used in the present analysis. The modified resistance equation has been used to calculate the mean velocity through the channel sections. In addition, a sediment transport equation has been applied for the prediction of transport capacity of the various sections. Results show that the existing drainage sections of Jamuna channel reach under study have adequate carrying capacity under existing bank-full conditions, but these reaches are subject to bed erosion even in low flow situations. Regarding sediment transport rate, it can be estimated that the channel flow has a relatively high range of bed material concentration. Finally, stage­ discharge curves for various sections have been developed. Based on stage-discharge rating data of various sections, water surface profile and sediment-rating curve of Jamuna River have been developed and also the flooding conditions have been analyzed from predicted water surface profile.

Keywords: discharge rating, flow profile, fluvial, sediment rating

Procedia PDF Downloads 181

Authors: Şeyma Özçirak Ergün, Ergün Şakalar, Emrah Yalazi̇, Nebahat Şahi̇n

Abstract:

Food irradiation is a usage of exposing food to ionising radiation (IR) such as gamma rays. IR has been used to decrease the number of harmful microorganisms in the food such as spices. Excessive usage of IR can cause damage to both food and people who consuming food. And also it causes to damages on food DNA. Generally, IR detection techniques were utilized in literature for spices are Electron Spin Resonance (ESR), Thermos Luminescence (TL). Storage creates negative effect on IR detection method then analyses of samples have been performed without storage in general. In the experimental part, red pepper (Capsicum annuum) and mint (Mentha piperita) as spices were exposed to 0, 0.272, 0.497, 1.06, 3.64, 8.82, and 17.42 kGy ionize radiation. ESR was applied to samples irradiated. DNA isolation from irradiated samples was performed using GIDAGEN Multi Fast DNA isolation kit. The DNA concentration was measured using a microplate reader spectrophotometer (Infinite® 200 PRO-Life Science–Tecan). The concentration of each DNA was adjusted to 50 ng/µL. Genomic DNA was imaged by UV transilluminator (Gel Doc XR System, Bio-Rad) for the estimation of genomic DNA bp-fragment size after IR. Thus, agarose gel profiles of irradiated spices were obtained to determine the change of band profiles. Besides, samples were examined at three different time periods (0, 3, 6 months storage) to show the feasibility of developed method. Results of gel electrophoresis showed especially degradation of DNA of irradiated samples. In conclusion, this study with gel electrophoresis can be used as a basis for the identification of the dose of irradiation by looking at degradation profiles at specific amounts of irradiation. Agarose gel results of irradiated samples were confirmed with ESR analysis. This method can be applied widely to not only food products but also all biological materials containing DNA to predict radiation-induced damage of DNA.

Keywords: DNA, electrophoresis, gel electrophoresis, ionizeradiation

Procedia PDF Downloads 255

Authors: Sumera, Sanila Amber, Fatima Javed Mirza, Amjad Ali, Saadia Zahid

Abstract:

Glioblastoma multiforme (GBM) is a widely spread and fatal primary brain tumor with an increased risk of relapse in spite of aggressive treatment. The current procedures for GBM diagnosis include invasive procedures i.e. resection or biopsy, to acquire tumor mass. Implementation of negligibly invasive tests as a potential diagnostic technique and biofluid-based monitoring of GBM stresses on discovering biomarkers in CSF and blood. Therefore, we performed a comprehensive in silico analysis to identify potential circulating biomarkers for GBM. Initially, six gene and protein databases were utilized to mine brain-specific proteins. The resulting proteins were filtered using a channel of five tools to predict the secretory proteins. Subsequently, the expression profile of the secreted proteins was verified in the brain and blood using two databases. Additional verification of the resulting proteins was done using Plasma Proteome Database (PPD) to confirm their presence in blood. The final set of proteins was searched in literature for their relationship with GBM, keeping a special emphasis on secretome proteome. 2145 proteins were firstly mined as brain-specific, out of which 69 proteins were identified as secretory in nature. Verification of expression profile in brain and blood eliminated 58 proteins from the 69 proteins, providing a final list of 11 proteins. Further verification of these 11 proteins further eliminated 2 proteins, giving a final set of nine secretory proteins i.e. OPCML, NPTX1, LGI1, CNTN2, LY6H, SLIT1, CREG2, GDF1 and SERPINI1. Out of these 9 proteins, 7 were found to be linked to GBM, whereas 2 proteins are not investigated in GBM so far. We propose that these secretory proteins can serve as potential circulating biomarker signatures of GBM and will facilitate the development of minimally invasive diagnostic methods and novel therapeutic interventions for GBM.

Keywords: glioblastoma multiforme, secretory proteins, brain secretome, biomarkers

Procedia PDF Downloads 150

Authors: Akriti Srivastava, Soumi Awasthy

Abstract:

One of the disciplines that provoked increased interest in the importance of intelligence is the management and organization development literature. Organization intelligence is a key enabling force underlying many vital activities and processes dominating organizational life. Hence, the factors which lead to organizational intelligence and the result which comes out of the whole procedure is important to be understood with the understanding of OI. The focus of this research was to uncover potential antecedents and consequences of organizational intelligence, thus a non-experimental explanatory survey research design was used. A non-experimental research design is in which the manipulation of variables and randomization of samples are not present. The data was collected with the help of the questionnaire from 321 scientists from different laboratories of an R & D organization. Out of which 304 data were found suitable for the analysis. There were 194 males (age, M= 35.03, SD=7.63) and 110 females (age, M= 34.34, SD=8.44). This study tested a conceptual model linking antecedent variables (leadership and organizational culture) to organizational intelligence, followed by organizational innovational capability and organizational performance. Structural equation modeling techniques were used to analyze the hypothesized model. But, before that, confirmatory factor analysis of organizational intelligence scale was done which resulted in an insignificant model. Then, exploratory factor analysis was done which gave six factors for organizational intelligence scale. This structure was used throughout the study. Following this, the final analysis revealed relatively good fit of data to the hypothesized model with certain modifications. Leadership and organizational culture emerged out as the significant antecedents of organizational intelligence. Organizational innovational capability and organizational performance came out to be the consequent factors of organizational intelligence. But organizational intelligence did not predict organizational performance via organizational innovational capability. With this, additional significant pathway emerged out between leadership and organizational performance. The model offers a fresh and comprehensive view of the organizational intelligence. In this study, prior studies in related literature were reviewed to offer a basic framework of organizational intelligence. The study proved to be beneficial for organizational intelligence scholarship, seeing its importance in the competitive environment.

Keywords: leadership, organizational culture, organizational intelligence, organizational innovational capability

Procedia PDF Downloads 336

Authors: Afshin Zahedi, Keivan Jamshidi

Abstract:

This study was conducted to determine the neurotoxic effects of different doses of ACR on the thoracic axons of the spinal cord of rat. To evaluate this hypothesis in the thoracic axons, amino-cupric silver staining technique of the de Olmos was conducted to define the histopathologic characteristic (argyrophilia) of axonal damage following ACR exposure. For this purpose 60 adult male rats (Wistar, approximately 250 g) were selected. Rats were hosed in polycarbonate boxes as two per each. Randomly assigned groups of rats (10 rats per exposure group, total 5 exposure groups as A, B, C, D and E) were exposed to 0.5, 5, 50, 100 and 500 mg/kg per day×11days intraperitoneal injection (IP injection) respectively. The remaining 10 rats were housed in group (F) as control group. Control rats received daily injections of 0.9% saline (3ml/kg). As indices of developing neurotoxicity, weight gain, gait scores and landing hindlimb foot splay (LHF) were determined. Weight gains were measured daily prior to injection. Gait scoring involved observation of spontaneous open field locomotion, included evaluations of ataxia, hopping, rearing and hind foot placement, and hindlimb foot splay were determined 3-4 times per week. Gait score was assigned from 1-4. After 11 days, two rats for silver stain, were randomly selected, dissected and proper samples were collected from thoracic portion of the spinal cord of rat. Results did show no neurological behavior in groups A, B and F, whereas severe neurotoxicity was observed in groups C and D. Rats in groups E died within 1-2 hours due to severe toxemia. In histopathological studies based on the de Olmos technique no argyrophilic neurons or processes were observed in stained sections obtained from the thoracic portion of the spinal cord of rats belong to groups A, B and F, while moderate to severe argyrophilic changes were observed in different stained sections obtained from the thoracic portion of the spinal cord of rats belong to groups C and D.

Keywords: acrylamide, rat, axonopathy, argyrophily, de Olmos

Procedia PDF Downloads 339

Authors: Mohd Asharf Ganie, Aafia Rashid, Mohd Afzal Zargar, Showkat Ali Zargar, Syed Mudasar, Tabasum Parvaiz, Zafar Amin Shah

Abstract:

Accumulating evidence suggests that Vitamin D deficiency (VDD) might at least contribute to the metabolic co-morbidities in PCOS. Hence, we aimed to study the effect of vitamin D supplementation in co-prescription with insulin sensitizers like metformin and pioglitazone on clinical, hormonal and metabolic parameters in women with PCOS. In this open label randomized, controlled trial a total of 120 women with PCOS diagnosis (AE-PCOS 2009 Criteria) were assigned to four treatment groups (n= 30 in each): group I (metformin 1 gm/day in combination with cholecalciferol 4000 IU/day), group II (pioglitazone 30 mg/day in combination with cholecalciferol 4000 IU/day), group III (metformin 1 gm /day) and group IV (pioglitazone 30 mg/day). Vitamin D supplementation was given as 60,000 units every two weeks for 24 weeks. All the subjects were routinely evaluated for clinical, biochemical, hormonal and insulin sensitivity parameters in addition to various safety parameters especially serum calcium levels at baseline and after 24 weeks of the treatment. Our results indicate that 95.5% of PCOS women were vitamin D deficient at baseline. Serum 25 (OH) D levels increased significantly (p < 0.001) in groups I and II without any adverse effects after 24 weeks of oral administration of 4000 IU cholecalciferol daily. However, serum 25 (OH) D levels remained unchanged in group III and IV. By six months, number of menstrual cycles per year increased whereas Ferriman-Gallwey score, serum total testosterone and HOMA-IR decreased significantly (P < 0.001) in the treatment groups supplemented with cholecalciferol as compared to those treated either drug alone. No significant beneficial changes were observed on weight, BMI, blood pressure, glucose tolerance and serum lipids in any of the groups supplemented with cholecalciferol. We conclude that daily dose of 4000 IU cholecalciferol might be a useful adjunct in complex treatment of PCOS with fewer adverse events. Furthermore, pioglitazone and cholecalciferol combination seems to be marginally better although there was no statistical significance.

Keywords: PCOS, vitamin D supplementation, insulin resistance, spironolactone, metformin, pioglitazone

Procedia PDF Downloads 376

Authors: Luis Alvarado, Victor Poblete, Isaac Gonzalez, Yetzabeth Gonzalez

Abstract:

In MIREX 2016 (http://www.music-ir.org/mirex), the deep neural network (DNN)-Deep Chroma Extractor, proposed by Korzeniowski and Wiedmer, reached the highest score in an audio chord recognition task. In the present paper, this tool is assessed under acoustic reverberant environments and distinct source-microphone distances. The evaluation dataset comprises The Beatles and Queen datasets. These datasets are sequentially re-recorded with a single microphone in a real reverberant chamber at four reverberation times (0 -anechoic-, 1, 2, and 3 s, approximately), as well as four source-microphone distances (32, 64, 128, and 256 cm). It is expected that the performance of the trained DNN will dramatically decrease under these acoustic conditions with signals degraded by room reverberation and distance to the source. Recently, the effect of the bio-inspired Locally-Normalized Cepstral Coefficients (LNCC), has been assessed in a text independent speaker verification task using speech signals degraded by additive noise at different signal-to-noise ratios with variations of recording distance, and it has also been assessed under reverberant conditions with variations of recording distance. LNCC showed a performance so high as the state-of-the-art Mel Frequency Cepstral Coefficient filters. Based on these results, this paper proposes a variation of locally-normalized triangular filters called Locally-Normalized Quarter Tone (LNQT) filters. By using the LNQT spectrogram, robustness improvements of the trained Deep Chroma Extractor are expected, compared with classical triangular filters, and thus compensating the music signal degradation improving the accuracy of the chord recognition system.

Keywords: chord recognition, deep neural networks, feature extraction, music information retrieval

Procedia PDF Downloads 229

Authors: A. Hayrapetyan, A. Simon, P. Marques, G. Renart

Abstract:

Business survival is a question of greatest interest for any economy. Firm characteristics that can explain or predict performance and, ultimately, business survival become of the greatest significance, as the sustainable longevity of any business can mean health for the future of the country. Family Firms (FFs) are one of the most ubiquitous forms of business worldwide, as more than half of European firms (60%) are considered as family firms. Therefore, the inherent characteristics of FFs are one of the possible explanatory variables for firm survival because FFs have strategic goals that differentiate them from other types of businesses. Although there is literature on the performance of FFs across generations, there are fewer studies on the factors that impact the survival of family and non-family FFs, as there is a lack of data on failed firms. To address this gap, this paper explores the differential survival of family firms versus non-family firms with a representative sample of companies of the region of Catalonia (Northeast of Spain) that were adhoc classified as family or nonfamily firms, as well as classified as failed or surviving, since no census data for family firms or for failed firms is available in Spain. By using the COX regression model on a representative sample of 629 family and non-family firms, this study investigates to what extent financial ratios, such as Liquidity, Solvency Rate can impact business survival, taking into consideration the socioemotional side of family firms, as well as revealing the differences between family and non-family firms. The findings show that the liquidity rate is significant for non-family firm survival, whereas not for family firms. On the other hand, FFs can benefit while having a higher solvency rate. Ultimately, this paper discovers that FFs increase their chances of survival when they are small, as the growth in size starts negatively impacting the socioemotional objectives of the firm. This study proves the existence of significant differences between family and non-family firms’ survival during economic crises, suggesting that the prioritization of emotional wealth creates distinct conditions for both types of firms.

Keywords: COX regression, economy crises, family firm, non-family firm, survival

Procedia PDF Downloads 66

Authors: Mohammed Islam, Jungyong Wang, Dong Cheol Seo

Abstract:

The Smoothed Particle Hydrodynamics (SPH) method is a novel, meshless, and Lagrangian technique based numerical method that has shown promises to accurately predict the hydrodynamics of water and structure interactions in violent flow conditions. The main goal of this study is to build confidence on the versatility of the Smoothed Particle Hydrodynamics (SPH) based tool, to use it as a complementary tool to the physical model testing capabilities and support research need for the performance evaluation of ships and offshore platforms exposed to an extreme and harsh environment. In the current endeavor, an open-sourced SPH-based tool was used and validated for modeling and predictions of the hydrodynamic interactions of a 6-DOF ship and bergy bits. The study involved the modeling of a modern generic drillship and simplified bergy bits in floating and towing scenarios and in regular and irregular wave conditions. The predictions were validated using the model-scale measurements on a moored ship towed at multiple oblique angles approaching a floating bergy bit in waves. Overall, this study results in a thorough comparison between the model scale measurements and the prediction outcomes from the SPH tool for performance and accuracy. The SPH predicted ship motions and forces were primarily within ±5% of the measurements. The velocity and pressure distribution and wave characteristics over the free surface depicts realistic interactions of the wave, ship, and the bergy bit. This work identifies and presents several challenges in preparing the input file, particularly while defining the mass properties of complex geometry, the computational requirements, and the post-processing of the outcomes.

Keywords: SPH, ship and bergy bit, hydrodynamic interactions, model validation, physical model testing

Procedia PDF Downloads 129

Authors: Helen K. Buteme, Rebecca Axelsson-Robertson, Moses L. Joloba, Henry W. Boom, Gunilla Kallenius, Markus Maeurer

Abstract:

Background: The Ugandan population is heavily affected by infectious diseases and Human leukocyte antigen (HLA) diversity plays a crucial role in the host-pathogen interaction and affects the rates of disease acquisition and outcome. The identification of HLA class 1 alleles and determining which alleles are associated with tuberculosis (TB) outcomes would help in screening individuals in TB endemic areas for susceptibility to TB and to predict resistance or progression to TB which would inevitably lead to better clinical management of TB. Aims: To be able to determine the HLA class 1 phenotype distribution in a Ugandan TB cohort and to establish the relationship between these phenotypes and active and latent TB. Methods: Blood samples were drawn from 32 HIV negative individuals with active TB and 45 HIV negative individuals with latent MTB infection. DNA was extracted from the blood samples and the DNA samples HLA typed by the polymerase chain reaction-sequence specific primer method. The allelic frequencies were determined by direct count. Results: HLA-A*02, A*01, A*74, A*30, B*15, B*58, C*07, C*03 and C*04 were the dominant phenotypes in this Ugandan cohort. There were differences in the distribution of HLA types between the individuals with active TB and the individuals with LTBI with only HLA-A*03 allele showing a statistically significant difference (p=0.0136). However, after FDR computation the corresponding q-value is above the expected proportion of false discoveries (q-value 0.2176). Key findings: We identified a number of HLA class I alleles in a population from Central Uganda which will enable us to carry out a functional characterization of CD8+ T-cell mediated immune responses to MTB. Our results also suggest that there may be a positive association between the HLA-A*03 allele and TB implying that individuals with the HLA-A*03 allele are at a higher risk of developing active TB.

Keywords: HLA, phenotype, tuberculosis, Uganda

Procedia PDF Downloads 398

Authors: Bibire Abdulkareem Hussein

Abstract:

Job satisfaction and motivation are considered as major tools in sustaining institutional development, they are also the machinery used to achieve an institutional goals and objectives. However, it has been observed that some institutions failed in motivating and stimulating their workers; in contrast, workers may be motivated but not satisfied with the job and failed to perform efficiently and effectively. It is hoped that the study of this nature would be of significance value to all stakeholders in education specifically, lecturers in higher institutions in Nigeria. Also it significances will enhance lecturers’ effectiveness and performance in discharging their duties. It is against this backdrop that, this study investigated whether job satisfaction and motivation predict lecturers’ effectiveness in Nigeria Police Academy, Wudil, KanoState. The correlational research method was adopted for the study while purposive sampling technique was used to choose the institution and the sampled lectures (70). Simple random sampling technique was used to select one hundred cadets across the academy. Two instruments were used to elicit information from both lecturers and cadets. These were job satisfaction and motivation; and lecturers’ effectiveness Questionnaires. The instruments were subjected to pilot testing and found to have reliability coefficient of 0.69 and 0.71 respectively. The results of the study revealed that there was a significance relationship among job satisfaction, motivation and lecturers effectiveness in Nigeria Police Academy, Job satisfaction had a Beta weight (β) of .125, t = 3.253, p<0.05, Job motivation had a Beta weight (β) of .185, t = 3.849, p<0.05. There was a significance relationship between job satisfaction and lecturers’ effectiveness in Nigeria Police Academy the cal r is 0.21 while the crt r is 0.19. at p<0.05 and; there was a significance relationship between job motivation and lecturers effectiveness in Nigeria Police Academy the cal r is 0.20 while the crt r is 0.19 at p<0.05This study therefore concluded that there was a significance relationship among job satisfaction, motivation and lecturers effectiveness in Nigeria Police Academy s,In view of the findings of this study, the paper recommends that lecturers should be more pro-active and more effective in their primary assignment (teaching) in order to make meaningful impacts and inputs in the life of cadets and boost the standard of the academy. In the same vein, it is recommended that management should intensify efforts to improve lecturers’ welfares by providing more motivational techniques to enhance more productivity.

Keywords: academy, lecturers effectiveness, motivation, satisfaction

Procedia PDF Downloads 469

Authors: Sumaia Jawad, Shalaweh Salem, Walid Kamal, Nicolette Roman

Abstract:

Background: HIV patients have many social problems like depression, which adversely affects their quality of life. HIV infection is linked to psychological distress such as anxiety. In terms of coping styles, avoidant emotion-focused strategies such as fatalism, wishful thinking and self-blame are associated with higher levels of psychological distress in persons with HIV. In Cairo, Egypt current services are not adapted to provide advice and psychological support to people living with HIV to help them develop problem-solving skills to cope with the stress of living with HIV. Yet, no studies have examined the relationship between quality of life, psychological distress and coping strategies of persons living with HIV/AIDS in Egypt. Therefore, the purpose of this study was to examine the relationship between quality of life, psychological distress and coping strategies of persons living with HIV/AIDS in Cairo, Egypt. Methods: This study used a quantitative methodology with a cross-sectional correlational design. The data was collected using: Quality of Life Enjoyment and Satisfaction Questionnaire (Q-LES-Q), Depression, Anxiety and Stress Scale (DASS) and Cope Inventory. The sample consisted of 202 participants who accessed the National AIDS Program (NAP). The data was analysed using the Statistical Program for Social Science V23 (SPSS). Results: The results show that psychological distress and certain coping styles such as substance abuse and behavioural disengagement negatively predict the quality of life of patients with HIV/AIDS. Positive predictors included coping styles such as active coping, self-distraction, venting, positive reframing, humor, acceptance, and religion. Conclusions: It would probably be best to reduce psychological distress and increase coping styles in order to improve the quality of life of patients with HIV/AIDS.

Keywords: HIV/AIDS, quality of life, psychological distress, coping strategies

Procedia PDF Downloads 405

Authors: Milan Joshi, Harsh Agrawal, Pallaw Mishra, Sanand Sule

Abstract:

Predicting electricity usage is a crucial aspect of organizing and controlling sustainable energy systems. The task of forecasting electricity load is intricate and requires a lot of effort due to the combined impact of social, economic, technical, environmental, and cultural factors on power consumption in communities. As a result, it is important to create strong models that can handle the significant non-linear and complex nature of the task. The objective of this study is to create and compare three machine learning techniques for predicting electricity load for both the day ahead and intraday, taking into account various factors such as meteorological data and social events including holidays and festivals. The proposed methods include a LightGBM, FBProphet, combination of FBProphet and LightGBM for day ahead and Motifs( Stumpy) based on Mueens algorithm for similarity search for intraday. We utilize these techniques to predict electricity usage during normal days and social events in the Himachal Region. We then assess their performance by measuring the MSE, RMSE, and MAPE values. The outcomes demonstrate that the combination of FBProphet and LightGBM method is the most accurate for day ahead and Motifs for intraday forecasting of electricity usage, surpassing other models in terms of MAPE, RMSE, and MSE. Moreover, the FBProphet - LightGBM approach proves to be highly effective in forecasting electricity load during social events, exhibiting precise day ahead predictions. In summary, our proposed electricity forecasting techniques display excellent performance in predicting electricity usage during normal days and special events in the Himachal Region.

Keywords: feature engineering, FBProphet, LightGBM, MASS, Motifs, MAPE

Procedia PDF Downloads 66

Authors: Yixin Yan, Miao Yan, Irini Angelidaki, Ioannis Fotidis

Abstract:

Ammonia, which derives from the degradation of urea and protein-substrates, is the major toxicant of the commercial anaerobic digestion reactors causing loses of up to 1/3 of their practical biogas production, which reflects directly on the overall revenue of the plants. The current experimental work is aiming to alleviate the ammonia inhibition in anaerobic digestion (AD) process by developing an innovative bioaugmentation method of ammonia tolerant methanogenic consortia. The ammonia tolerant consortia were cultured in batch reactors and immobilized together with biochar in agar (customized inocula). Three continuous stirred-tank reactors (CSTR), fed with the organic fraction of municipal solid waste at a hydraulic retention time of 15 days and operated at thermophilic (55°C) conditions were assessed. After an ammonia shock of 4 g NH4+-N L-1, the customized inocula were bioaugmented into the CSTR reactors to alleviate ammonia toxicity effect on AD process. Recovery rate of methane production and methanogenic activity will be assessed to evaluate the bioaugmentation performance, while 16s rRNA gene sequence will be used to reveal the difference of microbial community changes through bioaugmentation. At the microbial level, the microbial community structures of the four reactors will be analysed to find the mechanism of bioaugmentation. Changes in hydrogen formation potential will be used to predict direct interspecies electron transfer (DIET) between ammonia tolerant methanogens and syntrophic bacteria. This experimental work is expected to create bioaugmentation inocula that will be easy to obtain, transport, handled and bioaugment in AD reactors to efficiently alleviate the ammonia toxicity, without alternating any of the other operational parameters including the ammonia-rich feedstocks.

Keywords: artisanal fishing waste, acidogenesis, volatile fatty acids, pH, inoculum/substrate ratio

Procedia PDF Downloads 119

Authors: Joohyun Park, Jin Baek

Abstract:

The purpose of this study is to Analyze the role and effect arise from Diagonal Plane Control by Street Width (DPCSW) in Architecture in Seoul, and to predict the aspect of transition about the relationship among buildings and Urban morphology After the abolition. To find the tendency of building shape regulation, This study review Building Acts concerned with form making (the building to land Ratio, building designated line, wall designated line, building height limit (DPCSW) and etc.) and simulate the shape of urban blocks made by Acts in drawings. The review results show DPCSW is not only limitation about height, but also making the building setback from road and make the Road broader. And it makes the typical shape of the urban block that buildings are moving away from surrounding road After the Abolition of DPCSW; it is expected by the legislature that domestic real estate’s market would be promoted by increased total floor areas in each building. Some substitution from the legislature is announced, but it just deals with Building Maximum unit by Block unit except the regulation about arrangement in urban Figure and Ground. In conclusion, refrain from the uncontrolled development of city, It is important to make regulation about not only height factors but limitation line in land. Furthermore, through revising District Unit Plan, It is positively necessary to reset the relationship between buildings for the making the city space better.

Keywords: diagonal plane control by street width, building maximum height, district unit plan, building acts, urban block type, morphology, building shape

Procedia PDF Downloads 306

Authors: Amira Benabdelkader

Abstract:

Communication presents the channel by which humankind create and maintain their relationship with others, express themselves, exchange information, learn and teach etc. The context of communication plays a distinctive role in deciding about the language to be used. The term context is mainly used to refer to the interlocutors, their cultures, languages, relationship, physical surrounding that is the communication setting, type of the information to be transmitted, the topic etc. Cultures, on one hand, impose on humans certain behaviours, attitudes, gestures and beliefs. On the other hand, the focus on language is inevitable as it is with its verbal and non-verbal components, a key tool in and for communication. Moreover, each language has its particularity in how people voice, address and express their thoughts, feelings and beliefs. Being in the same setting with people from different cultures and languages and having conversations with them would call upon the intercultural communicative competence. This latter would promote the success of their conversations. Additionally, this competence could manifest in several ways during their interactions, to the extent that no one can predict when and how the interlocutors would use it. The only thing probably that could be confirmed is that the setting and culture would in a way or another intervene and often shape the flow of their communication, if not the whole communication. Therefore, this paper will look at the intercultural communicative competence of language learners when introducing their cultures to each other in an online language tandem (henceforth OLT) using their second and/or foreign language with the L1 language speakers. The participants of this study are Algerian (use L2: French, FL: English), British (L1: English, L2/FL: French). In other words, this current paper will provide a qualitative analysis of the OLT experiment by emphasising how language learners can overcome the cultural differences in an intercultural setting while communicating online using Skype (video conversations) with people from different countries, cultures and L1. The non-verbal cues will have the lion share in the analysis by focusing on how they have been used to maintain this intercultural communication or hinder it through the misinterpretation of gestures, head movements, grimaces etc.

Keywords: intercultural communicative competence, non-verbal cues, online language tandem, Skype

Procedia PDF Downloads 277

Authors: Hasan Izhar Khan, Naiqiang Zhang, Hong Xu, Zhongliang Zhu, Dongfang Jiang

Abstract:

Inconel 625 is a nickel-based alloy having outstanding corrosion resistance and developed for use at service temperatures ranging from cryogenic to 980°C. It got a wide range of applications in nuclear, petrochemical, chemical, marine, aeronautical, and aerospace industries. Currently, it is one of the candidate materials to be used as a structural material in ultra-supercritical (USC) power plants. In the high-temperature corrosive medium environment, metallic materials are susceptible to corrosion fatigue (CF). CF is an interaction between cyclic stress and corrosive medium environment that acts on a susceptible material and results in initiation and propagation of cracks. For the application of Inconel 625 as a structural material in USC power plants, CF behavior must be evaluated in steam and supercritical water (SCW) environment. Fatigue crack growth rate (FCGR) curves obtained from CF experiments are required to predict residual life of metallic materials used in power plants. In this study, FCGR tests of Inconel 625 were obtained by using compact tension specimen at 550-650 °C in steam (8 MPa) and SCW (25 MPa). The dissolved oxygen level was kept constant at 8000 ppb for the test conducted in steam and SCW. The tests were performed under sine wave loading waveform, 1 Hz loading frequency, stress ratio of 0.6 and maximum stress intensity factor of 32 MPa√m. Crack growth rate (CGR) was detected by using direct current potential drop technique. Results showed that CGR increased with an increase in temperature in the tested environmental conditions. The mechanism concerning the influence of temperature on FCGR are further discussed.

Keywords: corrosion fatigue, crack growth rate, nickel-based alloy, temperature

Procedia PDF Downloads 128

Authors: Abdul Fatah, Naveenchandra Acharya, Vamshi Krishna, T. Shivaprasad, Ramesh Ramayya

Abstract:

Background: Significant number of patients with bladder outlet obstruction due to BPH are on anti-platelets and anticoagulants. Prostate surgery in this group of patients either in the form of TURP or Open prostatectomy is associated with increased risk of bleeding complications requiring transfusions, packing of the prostatic fossa or ligation or embolization of internal iliac arteries. Withholding of antiplatelets and anticoagulants may be associated with cardiac and other complications. Efficacy of Thulium Laser in the above group of patients was evaluated in terms of peri-operative, postoperative and delayed bleeding complications as well as cardiac events in peri-operative and immediate postoperative period. Methods: 217 patients with a mean age of 68.8 years were enrolled between March 2009 and March 2013 (36 months), and treated for BPH with ThuLEP. Every patient was evaluated at base line according to: Digital Rectal Examination (DRE), prostate volume, Post-Voided volume (PVR), International Prostate Symptoms Score (I-PSS), PSA values, urine analysis and urine culture, uroflowmetry. The post operative complications in the form of drop in hemoglobin level, transfusion rates, post –operative cardiac events within a period of 30 days, delayed hematuria and events like deep vein thrombosis and pulmonary embolism were noted. Results: Our data showed a better post-operative outcome in terms of, postoperative bleeding requiring intervention 7 (3.2%), transfusion rate 4 (1.8%) and cardiac events within a period of 30 days 4(1.8%), delayed hematuria within 6 months 2(0.9 %) compared other series of prostatectomies. Conclusion: The thulium LASER prostatectomy is a safe and effective option for patients with cardiac comorbidties and those patients who are on antiplatelet agents and anticoagulants. The complication rate is less as compared to larger series reported with open and transurethral prostatectomies.

Keywords: thulium laser, prostatectomy, antiplatelet agents, bleeding

Procedia PDF Downloads 391

Authors: Elham Fathi, Seyed Mohammad Kalantarkousheh, Abolfazl Hatami Varzane

Abstract:

The present study aimed to determine predict capacity of the relationship among attachment styles, humor styles and communication patterns in female married students. Statistical population consisted of female married students from Allameh Tabataba’i University. The research sample consisted of 104 married students selected through convenience sampling. They responded to study instruments that consisted of attachment styles, humor styles and Communication patterns questionnaires. Data was analyzed by means of correlation method. The results indicated significant positive relationship between secure attachment styles with adaptive humor styles, and anxious attachment styles with maladaptive humor styles. Also a negative relationship between avoidant attachment with affiliative humor, and anxious attachment with self-enhancing humor was found. Furthermore, a negative relationship between self- enhancing humor styles with demand – withdraw communication pattern, and between affiliative humor with mutual avoidant communication pattern and a positive relationship between affiliative humor with mutual constructive communication pattern was observed. The relationship between secure attachment with mutual constructive communication pattern was positive, while relationship between avoidant attachment to mutual constructive communication pattern was negative and significant and its relation with mutual avoidant communication pattern was significantly positive. The result of regression analysis indicated that affliative humor style and secure attachment style, positively predicted mutual constructive communication pattern. Avoidant attachment style positively and affliative humor style negatively predicted the mutual avoidant communication pattern. And self-enhancing humor style negatively predicted the demand – withdraw communication pattern style.

Keywords: attachment styles, communication patterns, humor styles, female married students

Procedia PDF Downloads 370

Authors: Faruk Aras, Melih Inal, Tansel Cinar

Abstract:

The coordination of airport staff especially in the operations and maintenance departments is important for the airport operation. As a result, this coordination will increase the efficiency in all operation. Therefore, a Collaborative Decision-Making (CDM) system targets on improving the overall productivity of all operations by optimizing the use of resources and improving the predictability of actions. Enlarged productivity can be of major benefit for all airport operations. It also increases cost-efficiency. This study explains how predictive maintenance using IoT (Internet of Things), predictive operations and the statistical data such as Mean Time To Failure (MTTF) improves airport terminal operations and utilize airport terminal equipment in collaboration with collaborative decision making system/Airport Operation Control Center (AOCC). Data generated by the predictive maintenance methods is retrieved and analyzed by maintenance managers to predict when a problem is about to occur. With that information, maintenance can be scheduled when needed. As an example, AOCC operator would have chance to assign a new gate that towards to this gate all the equipment such as travellator, elevator, escalator etc. are operational if the maintenance team is in collaboration with AOCC since maintenance team is aware of the health of the equipment because of predictive maintenance methods. Applying predictive maintenance methods based on analyzing the health of airport terminal equipment dramatically reduces the risk of downtime by on time repairs. We can classify the categories as high priority calls for urgent repair action, as medium priority requires repair at the earliest opportunity, and low priority allows maintenance to be scheduled when convenient. In all cases, identifying potential problems early resulted in better allocation airport terminal resources by AOCC.

Keywords: airport, predictive maintenance, collaborative decision-making system, Airport Operation Control Center (AOCC)

Procedia PDF Downloads 360

Authors: Gerald Gwamba, Bo Zhou, Yajun Song, Dong Changyin

Abstract:

The challenges that sand production presents to the oil and gas industry, particularly while working in poorly consolidated reservoirs, cannot be overstated. From restricting production to blocking production tubing, sand production increases the costs associated with production as it elevates the cost of servicing production equipment over time. Production in reservoirs that present with high viscosities, flow rate, cementation, clay content as well as fine sand contents is even more complex and challenging. As opposed to the one-factor at a-time testing, investigating the interactive effects arising from a combination of several factors offers increased reliability of results as well as representation of actual field conditions. It is thus paramount to investigate the conditions leading to the onset of sanding during production to ensure the future sustainability of hydrocarbon production operations under viscous conditions. We adopt the Design of Experiments (DOE) to analyse, using Taguchi factorial designs, the most significant interactive effects of sanding. We propose an optimized regression model to predict the drawdown time at sand production. The results obtained underscore that reservoirs characterized by varying (high and low) levels of viscosity, flow rate, cementation, clay, and fine sand content have a resulting impact on sand production. The only significant interactive effect recorded arises from the interaction between BD (fine sand content and flow rate), while the main effects included fluid viscosity and cementation, with percentage significances recorded as 31.3%, 37.76%, and 30.94%, respectively. The drawdown time model presented could be useful for predicting the time to reach the maximum drawdown pressure under viscous conditions during the onset of sand production.

Keywords: factorial designs, DOE optimization, sand production prediction, drawdown time, regression model

Procedia PDF Downloads 147

Authors: Rachel Shukrun, Szilvia Baron, Victoria Fidel, Anna Shusterman, Osnat Sher, Netanya Kollender, Dror Levin, Yair Peled, Yair Gortzak, Yoav Ben-Shahar, Revital Caspi, Sagi Gordon, Michal Manisterski, Ronit Elhasid

Abstract:

Ewing sarcoma (EWS) is a highly aggressive cancer with a survival rate of 70–80% for patients with localized disease and under 30% for those with metastatic disease. Tumor-infiltrating neutrophils (TIN) can generate extracellular net-like DNA structures known as neutrophil extracellular traps (NETs). However, little is known about the presence and prognostic significance of tumor-infiltrating NETs in EWS. Herein, we investigated 46 patients diagnosed with EWS and treated in the Tel Aviv Medical Center between 2010 and 2021. TINs and NETs were identified in diagnostic biopsies of EWS by immunofluorescent. In addition, NETs were investigated in neutrophils isolated from peripheral blood samples of EWS patients at diagnosis and following neoadjuvant chemotherapy. The relationships between the presence of TINs and NETs, pathological and clinical features, and outcomes were analyzed. Our results demonstrate that TIN and NETs at diagnosis were higher in EWS patients with metastatic disease compared to those with local disease. High NETs formation at diagnosis predicted poor response to neo-adjuvant chemotherapy, relapse, and death from disease (P < .05). NETs formation in peripheral blood samples at diagnosis was significantly elevated among patients with EWS compared to pediatric controls and decreased significantly following neoadjuvant chemotherapy. In conclusion, NETs formation seems to have a role in the EWS immune microenvironment. Their presence can refine risk stratification, predict chemotherapy resistance and survival, and serve as a therapeutic target in patients with EWS.

Keywords: Ewing sarcoma, tumor microenvironment, neutrophil, neutrophil extracellular traps (NETs), prognosis

Procedia PDF Downloads 61

Authors: Iveta Ludviga, Agita Kalvina

Abstract:

This paper aims to link together the concepts of job satisfaction, work engagement, trust, job meaningfulness and loyalty to the organisation focusing on specific type of employment–academic jobs. The research investigates the relationships between job satisfaction, work engagement and loyalty as well as the impact of trust and job meaningfulness on the work engagement and loyalty. The survey was conducted in one of the largest Latvian higher education institutions and the sample was drawn from academic staff (n=326). Structured questionnaire with 44 reflective type questions was developed to measure toe constructs. Data was analysed using SPSS and Smart-PLS software. Variance based structural equation modelling (PLS-SEM) technique was used to test the model and to predict the most important factors relevant to employee engagement and loyalty. The first order model included two endogenous constructs (loyalty and intention to stay and recommend, and employee engagement), as well as six exogenous constructs (feeling of fair treatment and trust in management; career growth opportunities; compensation, pay and benefits; management; colleagues; teamwork; and finally job meaningfulness). Job satisfaction was developed as second order construct and both: first and second order models were designed for data analysis. It was found that academics are more engaged than satisfied with their work and main reason for that was found to be job meaningfulness, which is significant predictor for work engagement, but not for job satisfaction. Compensation is not significantly related to work engagement, but only to job satisfaction. Trust was not significantly related neither to engagement, nor to satisfaction, however, it appeared to be significant predictor of loyalty and intentions to stay with the University. This paper revealed academic jobs as specific kind of employment where employees can be more engaged than satisfied and highlighted the specific role of job meaningfulness in the University settings.

Keywords: job satisfaction, job meaningfulness, higher education, work engagement

Procedia PDF Downloads 247

Authors: Siti Anis Nadia Abu Bakar, Vani Tanggamani

Abstract:

Over recent years, the quality and environmental management practices are the necessary tasks in hospitality industry in order to provide high quality services, a comfortable and safe environment for occupants as well as innovative nature and shareholders' satisfaction, its environmental and social added value sustainable. Numerous studies have observed and measured quality management program (QMProg) and environmental management practices (EMPrac) independently. This paper analyzed the level of QMProg, and EMPrac in hospitality industry, particularly on hotel performance, specifically in the context of Malaysia as hotel industry in Malaysia has contributed tremendously to the development in the Malaysia tourism industry.The research objectives are; (1) to analyze how the level of QMProg influences on firm performance; (2) to investigate the level of EMPrac and its influence on firm performance. This paper contributes to the literature by providing added-value to the service industry strategic decision-making processes by helping to predict the varying impacts of positive and negative corporate social responsibility (CSR) activities on financial performance in their respective industries. Further, this paper also contributes to develop more applicable CSR strategies. As a matter of fact, the findings of this paper has contributed towards an integrated management system that will assist a firm in implementation of their environmental strategy by creating a higher level of accountability for environmental performance. The best results in environmental systems have instigated managers to explore more options when dealing with problems, especially problems involving the reputation of their hotel. In conclusion, the results of the study infer that the best CSR strategies of the quality and environmental management practices influences hotel performance.

Keywords: corporate social responsibility (CSR), environmental management practices (EMPrac), performance (PERF), quality management program (QMProg)

Procedia PDF Downloads 371

Authors: Anna Yagodnitsyna, Alexander Kovalev, Artur Bilsky

Abstract:

The efficiency of certain technological processes in two-phase microfluidics such as emulsion production, nanomaterial synthesis, nitration, extraction processes etc. depends on two-phase flow regimes in microchannels. For practical application in chemistry and biochemistry it is very important to predict the expected flow pattern for a large variety of fluids and channel geometries. In the case of immiscible liquids, the plug flow is a typical and optimal regime for chemical reactions and needs to be predicted by empirical data or correlations. In this work flow patterns of immiscible liquid-liquid flow in a rectangular microchannel with T-junction are investigated. Three liquid-liquid flow systems are considered, viz. kerosene – water, paraffin oil – water and castor oil – paraffin oil. Different flow patterns such as parallel flow, slug flow, plug flow, dispersed (droplet) flow, and rivulet flow are observed for different velocity ratios. New flow pattern of the parallel flow with steady wavy interface (serpentine flow) has been found. It is shown that flow pattern maps based on Weber numbers for different liquid-liquid systems do not match well. Weber number multiplied by Ohnesorge number is proposed as a parameter to generalize flow maps. Flow maps based on this parameter are superposed well for all liquid-liquid systems of this work and other experiments. Plug length and velocity are measured for the plug flow regime. When dispersed liquid wets channel walls plug length cannot be predicted by known empirical correlations. By means of particle tracking velocimetry technique instantaneous velocity fields in a plug flow regime were measured. Flow circulation inside plug was calculated using velocity data that can be useful for mass flux prediction in chemical reactions.

Keywords: flow patterns, hydrodynamics, liquid-liquid flow, microchannel

Procedia PDF Downloads 390

Authors: M. S. Wickramarachchi, L. S. Nawarathna, C. M. B. Dematawewa

Abstract:

Hatchery performance is critical for the profitability of poultry breeder operations. Some extrinsic parameters of eggs and breeders cause to increase or decrease the hatchability. This study aims to identify the affecting extrinsic parameters on the commercial hatchability of local chicken's eggs and determine the most efficient classification model with a hatchability rate greater than 90%. In this study, seven extrinsic parameters were considered: egg weight, moisture loss, breeders age, number of fertilised eggs, shell width, shell length, and shell thickness. Multiple linear regression was performed to determine the most influencing variable on hatchability. First, the correlation between each parameter and hatchability were checked. Then a multiple regression model was developed, and the accuracy of the fitted model was evaluated. Linear Discriminant Analysis (LDA), Classification and Regression Trees (CART), k-Nearest Neighbors (kNN), Support Vector Machines (SVM) with a linear kernel, and Random Forest (RF) algorithms were applied to classify the hatchability. This grouping process was conducted using binary classification techniques. Hatchability was negatively correlated with egg weight, breeders' age, shell width, shell length, and positive correlations were identified with moisture loss, number of fertilised eggs, and shell thickness. Multiple linear regression models were more accurate than single linear models regarding the highest coefficient of determination (R²) with 94% and minimum AIC and BIC values. According to the classification results, RF, CART, and kNN had performed the highest accuracy values 0.99, 0.975, and 0.972, respectively, for the commercial hatchery process. Therefore, the RF is the most appropriate machine learning algorithm for classifying the breeder outcomes, which are economically profitable or not, in a commercial hatchery.

Keywords: classification models, egg weight, fertilised eggs, multiple linear regression

Procedia PDF Downloads 84