Search results for: survival data analysis
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 41948

Search results for: survival data analysis

37088 Local Boundary Analysis for Generative Theory of Tonal Music: From the Aspect of Classic Music Melody Analysis

Authors: Po-Chun Wang, Yan-Ru Lai, Sophia I. C. Lin, Alvin W. Y. Su

Abstract:

The Generative Theory of Tonal Music (GTTM) provides systematic approaches to recognizing local boundaries of music. The rules have been implemented in some automated melody segmentation algorithms. Besides, there are also deep learning methods with GTTM features applied to boundary detection tasks. However, these studies might face constraints such as a lack of or inconsistent label data. The GTTM database is currently the most widely used GTTM database, which includes manually labeled GTTM rules and local boundaries. Even so, we found some problems with these labels. They are sometimes discrepancies with GTTM rules. In addition, since it is labeled at different times by multiple musicians, they are not within the same scope in some cases. Therefore, in this paper, we examine this database with musicians from the aspect of classical music and relabel the scores. The relabeled database - GTTM Database v2.0 - will be released for academic research usage. Despite the experimental and statistical results showing that the relabeled database is more consistent, the improvement in boundary detection is not substantial. It seems that we need more clues than GTTM rules for boundary detection in the future.

Keywords: dataset, GTTM, local boundary, neural network

Procedia PDF Downloads 134
37087 Economical Analysis of Optimum Insulation Thickness for HVAC Duct

Authors: D. Kumar, S. Kumar, A. G. Memon, R. A. Memon, K. Harijan

Abstract:

A considerable amount of energy is usually lost due to compression of insulation in Heating, ventilation, and air conditioning (HVAC) duct. In this paper, the economic impact of compression of insulation is estimated. Relevant mathematical models were used to estimate the optimal thickness at the points of compression. Furthermore, the payback period is calculated for the optimal thickness at the critical parts of supply air duct (SAD) and return air duct (RAD) considering natural gas (NG) and liquefied petroleum gas (LPG) as fuels for chillier operation. The mathematical model is developed using preliminary data obtained for an HVAC system of a pharmaceutical company. The higher heat gain and cooling loss, due to compression of thermal insulation, is estimated using relevant heat transfer equations. The results reveal that maximum energy savings (ES) in SAD is 34.5 and 40%, while in RAD is 22.9% and 29% for NG and LPG, respectively. Moreover, the minimum payback period (PP) for SAD is 2 and 1.6years, while in RAD is 4.3 and 2.7years for NG and LPG, respectively. The optimum insulation thickness (OIT) corresponding to maximum ES and minimum PP is estimated to be 35 and 42mm for SAD, while 30 and 38mm for RAD in case of NG and LPG, respectively.

Keywords: optimum insulation thickness, life cycle cost analysis, payback period, HVAC system

Procedia PDF Downloads 210
37086 Population Structure Analysis of Pakistani Indigenous Cattle Population by Using High Density SNP Array

Authors: Hamid Mustafa, Huson J. Heather, Kim Eiusoo, McClure Matt, Khalid Javed, Talat Nasser Pasha, Afzal Ali1, Adeela Ajmal, Tad Sonstegard

Abstract:

Genetic differences associated with speciation, breed formation or local adaptation can help to preserve and effective utilization of animals in selection programs. Analyses of population structure and breed diversity have provided insight into the origin and evolution of cattle. In this study, we used a high-density panel of SNP markers to examine population structure and diversity among ten Pakistani indigenous cattle breeds. In total, 25 individuals from three cattle populations, including Achi (n=08), Bhagnari (n=04) and Cholistani (n=13) were genotyped for 777, 962 single nucleotide polymorphism (SNP) markers. Population structure was examined using the linkage model in the program STRUCTURE. After characterizing SNP polymorphism in the different populations, we performed a detailed analysis of genetic structure at both the individual and population levels. The whole-genome SNP panel identified several levels of population substructure in the set of examined cattle breeds. We further searched for spatial patterns of genetic diversity among these breeds under the recently developed spatial principal component analysis framework. Overall, such high throughput genotyping data confirmed a clear partitioning of the cattle genetic diversity into distinct breeds. The resulting complex historical origins associated with both natural and artificial selection have led to the differentiation of numerous different cattle breeds displaying a broad phenotypic variety over a short period of time.

Keywords: Pakistan, cattle, genetic diversity, population structure

Procedia PDF Downloads 610
37085 Fostering Student Interest in Senior Secondary Two Biology Using Prior Knowledge of Behavioural Objectives and Assertive Questioning Strategies in Benue State, Nigeria

Authors: John Odo Ogah

Abstract:

The study investigated ways of fostering students’ interest in senior secondary two Biology, using prior knowledge of behavioural objectives and assertive questioning strategies in Benue State of Nigeria. A quasi-experimental research design was adopted; the population comprised 8,571 senior Secondary two students. The sample consisted of 265 SSII biology students selected from six government schools in the study area using a multi-staged sampling technique. Data was generated using the Biology Interest Inventory (BII). The instrument was validated and subjected to reliability analysis using Cronbach’s Alpha formula, which yielded a coefficient of 0.73. Three research questions guided the study, while three hypotheses were formulated and tested. Data collected were analyzed using means, bar graphs, and standard deviations to answer the research questions, while analysis of covariance (ANCOVA) was employed in testing the hypotheses at 0.05 level of significance. The finding revealed that there is a significant difference in the mean interest ratings of students taught cellular respiration and excretory system using assertive questioning strategy, prior knowledge of behavioural objectives strategy and lecture method (p=0.000˂0.05). There is no significant difference in the mean interest ratings of male and female students taught cellular respiration and excretory systems using an assertive questioning strategy (p=0.790>0.05). There is significant difference in the mean interest ratings of male and female students taught cellular respiration and execratory system using prior knowledge of behavioural objectives strategy (p=0.028˂0.05). It was recommended, among others, that teachers should endeavor to utilize prior knowledge of behavioral objectives strategy in teaching biology in order to harness its benefits as it enhances students’ interest.

Keywords: interest, assertive, questioning, prior, knowledge

Procedia PDF Downloads 40
37084 Computational Fluid Dynamics Simulation of a Boiler Outlet Header Constructed of Inconel Alloy 740H

Authors: Sherman Ho, Ahmed Cherif Megri

Abstract:

Headers play a critical role in conveying steam to regulate heating system temperatures. While various materials like steel grades 91 and 92 have been traditionally used for pipes, this research proposes the use of a robust and innovative material, INCONEL Alloy 740H. Boilers in power plant configurations are exposed to cycling conditions due to factors such as daily, seasonal, and yearly variations in weather. These cycling conditions can lead to the deterioration of headers, which are vital components with intricate geometries. Header failures result in substantial financial losses from repair costs and power plant shutdowns, along with significant public inconveniences such as the loss of heating and hot water. To address this issue and seek solutions, a mechanical analysis, as well as a structural analysis, are recommended. Transient analysis to predict heat transfer conditions is of paramount importance, as the direction of heat transfer within the header walls and the passing steam can vary based on the location of interest, load, and operating conditions. The geometry and material of the header are also crucial design factors, and the choice of pipe material depends on its usage. In this context, the heat transfer coefficient plays a vital role in header design and analysis. This research employs ANSYS Fluent, a numerical simulation program, to understand header behavior, predict heat transfer, and analyze mechanical phenomena within the header. Transient simulations are conducted to investigate parameters like heat transfer coefficient, pressure loss coefficients, and heat flux, with the results used to optimize header design.

Keywords: CFD, header, power plant, heat transfer coefficient, simulation using experimental data

Procedia PDF Downloads 57
37083 Serum Neurotrophins in Different Metabolic Types of Obesity

Authors: Irina M. Kolesnikova, Andrey M. Gaponov, Sergey A. Roumiantsev, Tatiana V. Grigoryeva, Alexander V. Laikov, Alexander V. Shestopalov

Abstract:

Background. Neuropathy is a common complication of obesity. In this regard, the content of neurotrophins in such patients is of particular interest. Neurotrophins are the proteins that regulate neuron survival and neuroplasticity and include brain-derived neurotrophic factor (BDNF) and nerve growth factor (NGF). However, the risk of complications depends on the metabolic type of obesity. Metabolically unhealthy obesity (MUHO) is associated with a high risk of complications, while this is not the case with metabolically healthy obesity (MHO). Therefore, the aim of our work was to study the effect of the obesity metabolic type on serum neurotrophins levels. Patients, materials, methods. The study included 134 healthy donors and 104 obese patients. Depending on the metabolic type of obesity, the obese patients were divided into subgroups with MHO (n=40) and MUHO (n=55). In the blood serum, the concentration of BDNF and NGF was determined. In addition, the content of adipokines (leptin, asprosin, resistin, adiponectin), myokines (irisin, myostatin, osteocrin), indicators of carbohydrate, and lipid metabolism were measured. Correlation analysis revealed the relationship between the studied parameters. Results. We found that serum BDNF concentration was not different between obese patients and healthy donors, regardless of obesity metabolic type. At the same time, in obese patients, there was a decrease in serum NGF level versus control. A similar trend was characteristic of both MHO and MUHO. However, MUHO patients had a higher NGF level than MHO patients. The literature indicates that obesity is associated with an increase in the plasma concentration of NGF. It can be assumed that in obesity, there is a violation of NGF storage in platelets, which accelerates neurotrophin degradation. We found that BDNF concentration correlated with irisin levels in MUHO patients. Healthy donors had a weak association between NGF and VEGF levels. No such association was found in obese patients, but there was an association between NGF and leptin concentrations. In MHO, the concentration of NHF correlated with the content of leptin, irisin, osteocrin, insulin, and the HOMA-IR index. But in MUHO patients, we found only the relationship between NGF and adipokines (leptin, asprosin). It can be assumed that in patients with MHO, the replenishment of serum NGF occurs under the influence of muscle and adipose tissue. In the MUHO patients only the effect of adipose tissue on NGF was observed. Conclusion. Obesity, regardless of metabolic type, is associated with a decrease in serum NGF concentration. We showed that muscle and adipose tissues make a significant contribution to the serum NGF pool in the MHO patients. In MUHO there is no effect of muscle on the NGF level, but the effect of adipose tissue remains.

Keywords: neurotrophins, nerve growth factor, NGF, brain-derived neurotrophic factor, BDNF, obesity, metabolically healthy obesity, metabolically unhealthy obesity

Procedia PDF Downloads 99
37082 Neural Network Approach to Classifying Truck Traffic

Authors: Ren Moses

Abstract:

The process of classifying vehicles on a highway is hereby viewed as a pattern recognition problem in which connectionist techniques such as artificial neural networks (ANN) can be used to assign vehicles to their correct classes and hence to establish optimum axle spacing thresholds. In the United States, vehicles are typically classified into 13 classes using a methodology commonly referred to as “Scheme F”. In this research, the ANN model was developed, trained, and applied to field data of vehicles. The data comprised of three vehicular features—axle spacing, number of axles per vehicle, and overall vehicle weight. The ANN reduced the classification error rate from 9.5 percent to 6.2 percent when compared to an existing classification algorithm that is not ANN-based and which uses two vehicular features for classification, that is, axle spacing and number of axles. The inclusion of overall vehicle weight as a third classification variable further reduced the error rate from 6.2 percent to only 3.0 percent. The promising results from the neural networks were used to set up new thresholds that reduce classification error rate.

Keywords: artificial neural networks, vehicle classification, traffic flow, traffic analysis, and highway opera-tions

Procedia PDF Downloads 302
37081 Machine Learning-Driven Prediction of Cardiovascular Diseases: A Supervised Approach

Authors: Thota Sai Prakash, B. Yaswanth, Jhade Bhuvaneswar, Marreddy Divakar Reddy, Shyam Ji Gupta

Abstract:

Across the globe, there are a lot of chronic diseases, and heart disease stands out as one of the most perilous. Sadly, many lives are lost to this condition, even though early intervention could prevent such tragedies. However, identifying heart disease in its initial stages is not easy. To address this challenge, we propose an automated system aimed at predicting the presence of heart disease using advanced techniques. By doing so, we hope to empower individuals with the knowledge needed to take proactive measures against this potentially fatal illness. Our approach towards this problem involves meticulous data preprocessing and the development of predictive models utilizing classification algorithms such as Support Vector Machines (SVM), Decision Tree, and Random Forest. We assess the efficiency of every model based on metrics like accuracy, ensuring that we select the most reliable option. Additionally, we conduct thorough data analysis to reveal the importance of different attributes. Among the models considered, Random Forest emerges as the standout performer with an accuracy rate of 96.04% in our study.

Keywords: support vector machines, decision tree, random forest

Procedia PDF Downloads 31
37080 Propeller Performance Modeling through a Computational Fluid Dynamics Analysis Method

Authors: Maxime Alex Junior Kuitche, Ruxandra Mihaela Botez, Jean-Chirstophe Maunand

Abstract:

The evolution of aircraft is closely linked to the study and improvement of propulsion systems. Determining the propulsion performance is a real challenge in aircraft modeling and design. In addition to theoretical methodologies, experimental procedures are used to obtain a good estimation of the propulsion performances. For piston-propeller propulsion, the propeller needs several experimental tests which could be extremely demanding in terms of time and money. This paper presents a new procedure to estimate the performance of a propeller from a numerical approach using computational fluid dynamic analysis. The propeller was initially scanned, and then, its 3D model was represented using CATIA. A structured meshing and Shear Stress Transition k-ω turbulence model were applied to describe accurately the flow pattern around the propeller. Thus, the Partial Differential Equations were solved using ANSYS FLUENT software. The method was applied on the UAS-S45’s propeller designed and manufactured by Hydra Technologies in Mexico. An extensive investigation was performed for several flight conditions in terms of altitudes and airspeeds with the aim to determine thrust coefficients, power coefficients and efficiency of the propeller. The Computational Fluid Dynamics results were compared with experimental data acquired from wind tunnel tests performed at the LARCASE Price-Paidoussis wind tunnel. The results of this comparison have demonstrated that our approach was highly accurate.

Keywords: CFD analysis, propeller performance, unmanned aerial system propeller, UAS-S45

Procedia PDF Downloads 348
37079 Re-Engineering Management Process in IRAN’s Smart Schools

Authors: M. R. Babaei, S. M. Hosseini, S. Rahmani, L. Moradi

Abstract:

Today, the quality of education and training systems and the effectiveness of the education systems of most concern to stakeholders and decision-makers of our country's development in each country. In Iran this is a double issue of concern to numerous reasons; So that governments, over the past decade have hardly even paid the running costs of education. ICT is claiming it has the power to change the structure of a program for training, reduce costs and increase quality, and do education systems and products consistent with the needs of the community and take steps to practice education. Own of the areas that the introduction of information technology has fundamentally changed is the field of education. The aim of this research is process reengineering management in schools simultaneously has been using field studies to collect data in the form of interviews and a questionnaire survey. The statistical community of this research has been the country of Iran and smart schools under the education. Sampling was targeted. The data collection tool was a questionnaire composed of two parts. The questionnaire consists of 36 questions that each question designates one of effective factors on the management of smart schools. Also each question consists of two parts. The first part designates the operating position in the management process, which represents the domain's belonging to the management agent (planning, organizing, leading, controlling). According to the classification of Dabryn and in second part the factors affect the process of managing the smart schools were examined, that Likert scale is used to classify. Questions the validity of the group of experts and prominent university professors in the fields of information technology, management and reengineering of approved and Cronbach's alpha reliability and also with the use of the formula is evaluated and approved. To analyse the data, descriptive and inferential statistics were used to analyse the factors contributing to the rating of (Linkert scale) descriptive statistics (frequency table data, mean, median, mode) was used. To analyse the data using analysis of variance and nonparametric tests and Friedman test, the assumption was evaluated. The research conclusions show that the factors influencing the management process re-engineering smart schools in school performance is affected.

Keywords: re-engineering, management process, smart school, Iran's school

Procedia PDF Downloads 239
37078 Drama, a Microcosm of Life Experiences: An Analysis of Symbolic Order and Social Relationships in Olu Obafemi’s Play

Authors: Victor Ademulegun Arijeniwa

Abstract:

This is a sociolinguistic study of Olu Obafemi’s Naira Has No Gender as a microcosm of life experiences. The paper assesses how Olu Obafemi’s use of language in the dramatic world serves as both social relationships and symbolic order of communicative roadmap that are capable of yielding well expressed and richly articulated sociolinguistic implications. Being the interface between language and social institutions, sociolinguistics and its application is highly utilitarian in linguistics analysis, especially where the language of a text appears to be deeply tensed, such as found in dramatic texts. The aim of this paper has been (i) to assess the symbolic orderly presentation of form in Olu Obafemi’Naira Has No Gender; (ii) to find out the linguistic elements and textual organization that represent social relationships in Olu Obafemi’s Naira Has No Gender. Using qualitative research design in data generation with insights from John Gumperz Interactional Sociolinguistics Theory with particular reference to contextualization cues and miscommunication, the paper identifies the implication of the dramatic discourse on society.

Keywords: sociolinguistics, Microcosm, contextualisation, miscommunication variable, identity, symbolic order

Procedia PDF Downloads 188
37077 Women’s Language and Gender Positioning in the Discourse of Indonesian Instagram Videos

Authors: Haira Rizka, Imas Istiani

Abstract:

The way women and men use language is an interesting topic to discuss. Nowadays, Instagram shows many videos which illustrate the difference of women’s and men’s language. Furthermore, the videos show how different genders behave in daily communication. This research aims to (1) investigate conversational characteristics of women represented in Indonesian Instagram videos, and (2) investigate how different genders behave in daily communication. To analyze the two research problems, this research employs Tannen’s theory of language and gender (1996). This is a descriptive qualitative research which describes phenomena of language and gender shown in Indonesian Instagram videos. The data were collected through observation. The collected data were then analyzed by employing ethnography and textual analysis. The research results show that in Indonesian Instagram videos, women dominate the conversation than men. Women’s are portrayed as a figure who are talkative, never wrong, and sensitive. Women’s dominating men proves that women always want to be understood, produce more words than men, and are more creative in producing verbal communication. Meanwhile, men are portrayed as calm, gentle, and patient creature who listen to women’s talk. Furthermore, men are portrayed to prefer being silent for avoiding conflict.

Keywords: gender, Instagram videos, language variety, women's language

Procedia PDF Downloads 418
37076 Social Network Roles in Organizations: Influencers, Bridges, and Soloists

Authors: Sofia Dokuka, Liz Lockhart, Alex Furman

Abstract:

Organizational hierarchy, traditionally composed of individual contributors, middle management, and executives, is enhanced by the understanding of informal social roles. These roles, identified with organizational network analysis (ONA), might have an important effect on organizational functioning. In this paper, we identify three social roles – influencers, bridges, and soloists, and provide empirical analysis based on real-world organizational networks. Influencers are employees with broad networks and whose contacts also have rich networks. Influence is calculated using PageRank, initially proposed for measuring website importance, but now applied in various network settings, including social networks. Influencers, having high PageRank, become key players in shaping opinions and behaviors within an organization. Bridges serve as links between loosely connected groups within the organization. Bridges are identified using betweenness and Burt’s constraint. Betweenness quantifies a node's control over information flows by evaluating its role in the control over the shortest paths within the network. Burt's constraint measures the extent of interconnection among an individual's contacts. A high constraint value suggests fewer structural holes and lesser control over information flows, whereas a low value suggests the contrary. Soloists are individuals with fewer than 5 stable social contacts, potentially facing challenges due to reduced social interaction and hypothetical lack of feedback and communication. We considered social roles in the analysis of real-world organizations (N=1,060). Based on data from digital traces (Slack, corporate email and calendar) we reconstructed an organizational communication network and identified influencers, bridges and soloists. We also collected employee engagement data through an online survey. Among the top-5% of influencers, 10% are members of the Executive Team. 56% of the Executive Team members are part of the top influencers group. The same proportion of top influencers (10%) is individual contributors, accounting for just 0.6% of all individual contributors in the company. The majority of influencers (80%) are at the middle management level. Out of all middle managers, 19% hold the role of influencers. However, individual contributors represent a small proportion of influencers, and having information about these individuals who hold influential roles can be crucial for management in identifying high-potential talents. Among the bridges, 4% are members of the Executive Team, 16% are individual contributors, and 80% are middle management. Predominantly middle management acts as a bridge. Bridge positions of some members of the executive team might indicate potential micromanagement on the leader's part. Recognizing the individuals serving as bridges in an organization uncovers potential communication problems. The majority of soloists are individual contributors (96%), and 4% of soloists are from middle management. These managers might face communication difficulties. We found an association between being an influencer and attitude toward a company's direction. There is a statistically significant 20% higher perception that the company is headed in the right direction among influencers compared to non-influencers (p < 0.05, Mann-Whitney test). Taken together, we demonstrate that considering social roles in the company might indicate both positive and negative aspects of organizational functioning that should be considered in data-driven decision-making.

Keywords: organizational network analysis, social roles, influencer, bridge, soloist

Procedia PDF Downloads 95
37075 A Web Service Based Sensor Data Management System

Authors: Rose A. Yemson, Ping Jiang, Oyedeji L. Inumoh

Abstract:

The deployment of wireless sensor network has rapidly increased, however with the increased capacity and diversity of sensors, and applications ranging from biological, environmental, military etc. generates tremendous volume of data’s where more attention is placed on the distributed sensing and little on how to manage, analyze, retrieve and understand the data generated. This makes it more quite difficult to process live sensor data, run concurrent control and update because sensor data are either heavyweight, complex, and slow. This work will focus on developing a web service platform for automatic detection of sensors, acquisition of sensor data, storage of sensor data into a database, processing of sensor data using reconfigurable software components. This work will also create a web service based sensor data management system to monitor physical movement of an individual wearing wireless network sensor technology (SunSPOT). The sensor will detect movement of that individual by sensing the acceleration in the direction of X, Y and Z axes accordingly and then send the sensed reading to a database that will be interfaced with an internet platform. The collected sensed data will determine the posture of the person such as standing, sitting and lying down. The system is designed using the Unified Modeling Language (UML) and implemented using Java, JavaScript, html and MySQL. This system allows real time monitoring an individual closely and obtain their physical activity details without been physically presence for in-situ measurement which enables you to work remotely instead of the time consuming check of an individual. These details can help in evaluating an individual’s physical activity and generate feedback on medication. It can also help in keeping track of any mandatory physical activities required to be done by the individuals. These evaluations and feedback can help in maintaining a better health status of the individual and providing improved health care.

Keywords: HTML, java, javascript, MySQL, sunspot, UML, web-based, wireless network sensor

Procedia PDF Downloads 207
37074 Determination of the Needs for Development of Infertility Psycho-Educational Program and the Design of a Website about Infertility for University Students

Authors: Bahar Baran, Şirin Nur Kaptan, D.Yelda Kağnıcı, Erol Esen, Barışcan Öztürk, Ender Siyez, Diğdem M Siyez

Abstract:

It is known that some factors associated with infertility have preventable characteristics and that young people's knowledge levels in this regard are inadequate, but very few studies focus on effective prevention studies on infertility. Psycho-educational programs have an important place for infertility prevention efforts. Nowadays, considering the households' utilization rates from technology and the Internet, it seems that young people have applied to websites as a primary source of information related to a health problem they have encountered. However, one of the prerequisites for the effectiveness of websites or face-to-face psycho-education programs is to consider the needs of participants. In particular, it is expected that these programs will be appropriate to the cultural infrastructure and the diversity of beliefs and values in society. The aim of this research is to determine what university students want to learn about infertility and fertility and examine their views on the structure of the website. The sample of the research consisted of 9693 university students who study in 21 public higher education programs in Turkey. 51.6 % (n = 5002) were female and 48.4% (n = 4691) were male. The Needs Analysis Questionnaire developed by the researchers was used as data collection tool in the research. In the analysis of the data, descriptive analysis was conducted in SPSS software. According to the findings, among the topics that university students wanted to study about infertility and fertility, the first topics were 'misconceptions about infertility' (94.9 %), 'misconceptions about sexual behaviors' (94.6 %), 'factors affecting infertility' (92.8 %), 'sexual health and reproductive health' (92.5 %), 'sexually transmitted diseases' (92.7 %), 'sexuality and society' (90.9 %), 'healthy life (help centers)' (90.4 %). In addition, the questions about how the content of the website should be designed for university students were analyzed descriptively. According to the results, 91.5 % (n = 8871) of the university students proposed to use frequently asked questions and their answers, 89.2 % (n = 8648) stated that expert video should be included, 82.6 % (n = 8008) requested animations and simulations, 76.1 % (n = 7380) proposed different content according to sex and 66 % (n = 6460) proposed different designs according to sex. The results of the research indicated that the findings are similar to the contents of the program carried out in other countries in terms of the topics to be studied. It is suggested to take into account the opinions of the participants during the design of website.

Keywords: infertility, prevention, psycho-education, web based education

Procedia PDF Downloads 208
37073 Analysis of Steel Beam-Column Joints Under Seismic Loads

Authors: Mizam Doğan

Abstract:

Adapazarı railway car factory, the only railway car factory of Turkey, was constructed in 1950. It was a steel design and it had filled beam sections and truss beam systems. Columns were steel profiles and box sections. The factory was damaged heavily on Izmit Earthquake and closed. In this earthquake 90% of damaged structures are reinforced concrete, the others are %7 prefabricated and 3% steel construction. As can be seen in statistical data, damaged industrial buildings in this earthquake were generally reinforced concrete and prefabricated structures. Adapazari railway car factory is the greatest steel structure damaged in the earthquake. This factory has 95% of the total damaged steel structure area. In this paper; earthquake damages on beams and columns of the factory are studied by considering TS648 'Turkish Standard Building Code for Steel Structures' and also damaged connection elements as welds, rivets and bolts are examined. A model similar to the damaged system is made and high-stress zones are searched. These examinations, conclusions, suggestions are explained by damage photos and details.

Keywords: column-beam connection, seismic analysis, seismic load, steel structure

Procedia PDF Downloads 272
37072 Promoting the Contructor's Reputation in the Nigerian Construction Industry

Authors: Abdulkadir Adamu Shehu

Abstract:

Company’s reputation is an elusive asset. The reputation gained by companies must be preserved for sustainability of the company. However, the construction project is still suffering from declination of character due to the factors that affect their reputation. The problem led to the loss of projects, abandoning of the projects and many more. This contributed to negative impact on the contractors in the construction industry. As for today, previous studies have not investigated in this regards yet. For that reason, this paper examines the factors which could promote contractor’s reputation in the construction industry in Nigeria. To achieve this aim, 140 questionnaires were distributed to the Nigerian contractors. Based on the 67% response rate, descriptive analysis and analysis of variance (ANOVA) were the tools applied for the data obtained to be analysed. The result shows that, good communication system and improve quality of output of products are the most significant variables that can promote contractor’s reputation. The homogenous analyses indicate that there are significant different perceptions of respondents in term of the significant effects. The research concluded that contractor’s reputation in construction industry must be maintained and further research was suggested to focus on the qualitative method to have in-depth knowledge on contractor’s reputation in the construction industry.

Keywords: construction industry, contractor’s reputation, effects of delay, Nigeria

Procedia PDF Downloads 424
37071 Comparison of the Anthropometric Obesity Indices in Prediction of Cardiovascular Disease Risk: Systematic Review and Meta-analysis

Authors: Saeed Pourhassan, Nastaran Maghbouli

Abstract:

Statement of the problem: The relationship between obesity and cardiovascular diseases has been studied widely(1). The distribution of fat tissue gained attention in relation to cardiovascular risk factors during lang-time research (2). American College of Cardiology/American Heart Association (ACC/AHA) is widely and the most reliable tool to be used as a cardiovascular risk (CVR) assessment tool(3). This study aimed to determine which anthropometric index is better in discrimination of high CVR patients from low risks using ACC/AHA score in addition to finding the best index as a CVR predictor among both genders in different races and countries. Methodology & theoretical orientation: The literature in PubMed, Scopus, Embase, Web of Science, and Google Scholar were searched by two independent investigators using the keywords "anthropometric indices," "cardiovascular risk," and "obesity." The search strategy was limited to studies published prior to Jan 2022 as full-texts in the English language. Studies using ACC/AHA risk assessment tool as CVR and those consisted at least 2 anthropometric indices (ancient ones and novel ones) are included. Study characteristics and data were extracted. The relative risks were pooled with the use of the random-effect model. Analysis was repeated in subgroups. Findings: Pooled relative risk for 7 studies with 16,348 participants were 1.56 (1.35-1.72) for BMI, 1.67(1.36-1.83) for WC [waist circumference], 1.72 (1.54-1.89) for WHR [waist-to-hip ratio], 1.60 (1.44-1.78) for WHtR [waist-to-height ratio], 1.61 (1.37-1.82) for ABSI [A body shape index] and 1.63 (1.32-1.89) for CI [Conicity index]. Considering gender, WC among females and WHR among men gained the highest RR. The heterogeneity of studies was moderate (α²: 56%), which was not decreased by subgroup analysis. Some indices such as VAI and LAP were evaluated just in one study. Conclusion & significance: This meta-analysis showed WHR could predict CVR better in comparison to BMI or WHtR. Some new indices like CI and ABSI are less accurate than WHR and WC. Among women, WC seems to be a better choice to predict cardiovascular disease risk.

Keywords: obesity, cardiovascular disease, risk assessment, anthropometric indices

Procedia PDF Downloads 95
37070 Analysis of the Interest of High School Students in Tirana for Physical Activity, Sports and Foreign Languages

Authors: Zylfi Shehu, Shpetim Madani, Bashkim Delia

Abstract:

Context: The study focuses on the interest and engagement of high school students in Tirana, Albania, in physical activity, sports, and foreign languages. It acknowledges the numerous physiological benefits of physical activity, such as cardiovascular health and improved mood. It also recognizes the importance of physical activity in childhood and adolescence for proper skeletal development and long-term health. Research Aim: The main purpose of the study is to investigate and analyze the preferences and interests of male and female high school students in Tirana regarding their functional development, physical activity, sports participation, and choice of foreign languages. The aim is to provide insights for the students and teachers to guide future objectives and improve the quality of physical education. Methodology: The study employed a survey-based approach, targeting both male and female students in public high schools in Tirana. A total of 410 students aged 15 to 19 years old, participated in the study. The data collected from the survey were processed using Excel and presented through tables and graphs. Findings: The results revealed that team sports were more favored by the students, with football being the preferred choice among males, while basketball and volleyball were more popular among females. Additionally, English was found to be the most preferred foreign language, selected by a higher percentage of females (38.57%) compared to males (16.90%). German followed as the second preferred language. Theoretical Importance: This study contributes to the understanding of students' interests in physical activity, sports, and foreign languages in Tirana's high schools. The findings highlight the need to focus on specific sports and languages to cater to students' preferences and guide future educational objectives. It also emphasizes the importance of physical education in promoting students' overall well-being and highlights potential areas for policy and program improvement. Data Collection and Analysis Procedures: The study collected data through surveys administered to high school students in Tirana. The survey responses were processed and analyzed using Excel, and the findings were presented through tables and graphs. The data analysis allowed for the identification of preferences and trends among male and female students, providing valuable insights for future decision-making. Question Addressed: The study aimed to address the question of high school students' interest in physical activity, sports, and foreign languages. It sought to understand the preferences and choices made by students in Tirana and investigate factors such as gender, family income, and accessibility to extracurricular sports activities. Conclusion: The study revealed that high school students in Tirana show a preference for team sports, with football being the most favored among males and basketball and volleyball among females. English was found to be the most preferred foreign language. The findings provide important insights for educators and policymakers to enhance physical education programs and consider students' preferences and interests to foster a more effective learning environment. The study also emphasizes the importance of physical activity and sports in promoting students' physical and mental well-being.

Keywords: female, male, foreign languages, sports, physical education, high school students

Procedia PDF Downloads 86
37069 Exploring Psychosocial Stressors in Crack Cocaine Use

Authors: Yaa Asuaba Duopah, Lisa Moran, Khalifa Elmusharaf, Dervla Kelly

Abstract:

Background: Research has identified a strong link between stress and drug use behaviours. Also, it has been established that the prolonged use of crack cocaine stimulates emotional, cognitive, neurological, and social changes. This paper examines the psychosocial stressors associated with crack cocaine use. Methodology: The study is qualitative and adopts a critical realist approach. Data was collected through 26 face-to-face, in-depth, semi-structured interviews with people who use crack cocaine. Study participants were recruited through two addiction services using purposive. Participants consisted of 15 males and 11 females between the ages of 24-57 years. Data were analysed using thematic analysis. Results: Cravings, financial hardship, family breakdown, and emotional stimulation were revealed as psychosocial stressors associated with crack cocaine use. Conclusion: Addressing the psychosocial stressors identified in this paper through targeted interventions and supportive policies is crucial for improving the well-being of persons who use crack cocaine. Collaboration between addiction, mental health, and support services is recommended to develop and deliver these interventions.

Keywords: psychological stress, substance misuse disorder, mental health, coping

Procedia PDF Downloads 47
37068 Expert Supporting System for Diagnosing Lymphoid Neoplasms Using Probabilistic Decision Tree Algorithm and Immunohistochemistry Profile Database

Authors: Yosep Chong, Yejin Kim, Jingyun Choi, Hwanjo Yu, Eun Jung Lee, Chang Suk Kang

Abstract:

For the past decades, immunohistochemistry (IHC) has been playing an important role in the diagnosis of human neoplasms, by helping pathologists to make a clearer decision on differential diagnosis, subtyping, personalized treatment plan, and finally prognosis prediction. However, the IHC performed in various tumors of daily practice often shows conflicting and very challenging results to interpret. Even comprehensive diagnosis synthesizing clinical, histologic and immunohistochemical findings can be helpless in some twisted cases. Another important issue is that the IHC data is increasing exponentially and more and more information have to be taken into account. For this reason, we reached an idea to develop an expert supporting system to help pathologists to make a better decision in diagnosing human neoplasms with IHC results. We gave probabilistic decision tree algorithm and tested the algorithm with real case data of lymphoid neoplasms, in which the IHC profile is more important to make a proper diagnosis than other human neoplasms. We designed probabilistic decision tree based on Bayesian theorem, program computational process using MATLAB (The MathWorks, Inc., USA) and prepared IHC profile database (about 104 disease category and 88 IHC antibodies) based on WHO classification by reviewing the literature. The initial probability of each neoplasm was set with the epidemiologic data of lymphoid neoplasm in Korea. With the IHC results of 131 patients sequentially selected, top three presumptive diagnoses for each case were made and compared with the original diagnoses. After the review of the data, 124 out of 131 were used for final analysis. As a result, the presumptive diagnoses were concordant with the original diagnoses in 118 cases (93.7%). The major reason of discordant cases was that the similarity of the IHC profile between two or three different neoplasms. The expert supporting system algorithm presented in this study is in its elementary stage and need more optimization using more advanced technology such as deep-learning with data of real cases, especially in differentiating T-cell lymphomas. Although it needs more refinement, it may be used to aid pathological decision making in future. A further application to determine IHC antibodies for a certain subset of differential diagnoses might be possible in near future.

Keywords: database, expert supporting system, immunohistochemistry, probabilistic decision tree

Procedia PDF Downloads 217
37067 Mental Health Impacts of COVID-19 on Diverse Youth and Families in Canada

Authors: Lucksini Raveendran

Abstract:

Introduction: This mixed-methods study focuses on the experiences of ethnocultural youth and families in Canada, identifying key barriers and opportunities to inform service programming and policies that can better meet their mental health needs during the COVID-19 pandemic and beyond. Methods: Mental Health Commission of Canada's Headstrong initiative administered the youth survey (April – June 2020) and family survey (June – August 2020) with a total sample size of 137 and 481 respondents, respectively. Thematic analysis was conducted to identify key challenges faced, coping strategies used, and help-seeking behaviours. A similar approach was also applied to the family survey data, but instead, a representative sample was collated to analyze geographically variable and ethnically diverse subgroups. Results and analysis: Multiple challenges have impacted families, including increased feelings of loneliness and distress from border travel restrictions, especially among those navigating pregnancy alone or managing children with developmental needs, which is often understudied. Also, marginalized groups were disproportionately affected by inequitable access to communication technologies, further deepening the digital divide. Some reported living in congregated homes with regular conflicts, thus leading to increased anxiety and exposure to violence. For many families, urbanicity and ethnicity played a key role in how families reported coping with feelings of uncertainty while managing work commitments, navigating community resources, fulfilling care responsibilities, and homeschooling children of all ages. Despite these challenges, there was evidence of post-traumatic growth and building community resiliency. Conclusions and implications for policy, practice, or additional research: There is a need to foster opportunities to promote and sustain mental health, wellness, and resilience for families through social connections. Also, intersectionality must be embedded in the collection, analysis, and application of data to improve equitable access to evidence-based and recovery-oriented mental health supports among diverse families in Canada. Lastly, address future research on the long-term COVID-19 impacts of travel border restrictions on family wellness.

Keywords: mental health, youth mental health, family wellness, health equity

Procedia PDF Downloads 89
37066 DEMs: A Multivariate Comparison Approach

Authors: Juan Francisco Reinoso Gordo, Francisco Javier Ariza-López, José Rodríguez Avi, Domingo Barrera Rosillo

Abstract:

The evaluation of the quality of a data product is based on the comparison of the product with a reference of greater accuracy. In the case of MDE data products, quality assessment usually focuses on positional accuracy and few studies consider other terrain characteristics, such as slope and orientation. The proposal that is made consists of evaluating the similarity of two DEMs (a product and a reference), through the joint analysis of the distribution functions of the variables of interest, for example, elevations, slopes and orientations. This is a multivariable approach that focuses on distribution functions, not on single parameters such as mean values or dispersions (e.g. root mean squared error or variance). This is considered to be a more holistic approach. The use of the Kolmogorov-Smirnov test is proposed due to its non-parametric nature, since the distributions of the variables of interest cannot always be adequately modeled by parametric models (e.g. the Normal distribution model). In addition, its application to the multivariate case is carried out jointly by means of a single test on the convolution of the distribution functions of the variables considered, which avoids the use of corrections such as Bonferroni when several statistics hypothesis tests are carried out together. In this work, two DEM products have been considered, DEM02 with a resolution of 2x2 meters and DEM05 with a resolution of 5x5 meters, both generated by the National Geographic Institute of Spain. DEM02 is considered as the reference and DEM05 as the product to be evaluated. In addition, the slope and aspect derived models have been calculated by GIS operations on the two DEM datasets. Through sample simulation processes, the adequate behavior of the Kolmogorov-Smirnov statistical test has been verified when the null hypothesis is true, which allows calibrating the value of the statistic for the desired significance value (e.g. 5%). Once the process has been calibrated, the same process can be applied to compare the similarity of different DEM data sets (e.g. the DEM05 versus the DEM02). In summary, an innovative alternative for the comparison of DEM data sets based on a multinomial non-parametric perspective has been proposed by means of a single Kolmogorov-Smirnov test. This new approach could be extended to other DEM features of interest (e.g. curvature, etc.) and to more than three variables

Keywords: data quality, DEM, kolmogorov-smirnov test, multivariate DEM comparison

Procedia PDF Downloads 109
37065 Long-Term Otitis Media with Effusion and Related Hearing Loss and Its Impact on Developmental Outcomes

Authors: Aleema Rahman

Abstract:

Introduction: This study aims to estimate the prevalence of long-term otitis media with effusion (OME) and hearing loss in a prospective longitudinal cohort studyand to study the relationship between the condition and educational and psychosocial outcomes. Methods: Analysis of data from the Avon Longitudinal Study of Parents and Children (ALSPAC) will be undertaken. ALSPAC is a longitudinal birth cohort study carried out in the UK, which has collected detailed measures of hearing on ~7000 children from the age of seven. A descriptive analysis of the data will be undertaken to estimate the prevalence of OME and hearing loss (defined as having average hearing levels > 20dB and type B tympanogram) at 7, 9, 11, and 15 years as well as that of long-term OME and hearing loss. Logistic and linear regression analyses will be conducted to examine associations between long-term OME and hearing loss and educational outcomes (grades obtained from standardised national attainment tests) and psychosocial outcomes such as anxiety, social fears, and depression at ages 10-11 and 15-16 years. Results: Results will be presented in terms of the prevalence of OME and hearing loss in the population at each age. The prevalence of long-term OME and hearing loss, defined as having OME and hearing loss at two or more time points, will also be reported. Furthermore, any associations between long-term OME and hearing loss and the educational and psychosocial outcomes will be presented. Analyses will take into account demographic factors such as sex and social deprivation and relevant confounders, including socioeconomic status, ethnicity, and IQ. Discussion: Findings from this study will provide new epidemiological information on the prevalence of long-term OME and hearing loss. The research will provide new knowledge on the impact of OME for the small group of children who do not grow out of condition by age 7 but continue to have hearing loss and need clinical care through later childhood. The study could have clinical implications and may influence service delivery for this group of children.

Keywords: educational attainment, hearing loss, otitis media with effusion, psychosocial development

Procedia PDF Downloads 130
37064 A Computational Study of the Effect of Intake Design on Volumetric Efficiency for Best Performance in Motorsport

Authors: Dominic Wentworth-Linton, Shian Gao

Abstract:

This project was aimed at investigating the effect of velocity stacks on the intakes of internal combustion engines for motorsport applications. The intake systems in motorsport are predominantly fuel injection with a plate mounted for the stacks. Using Computational Fluid Dynamics software, the relationship between the stack length and power and torque delivery across the engine’s rev range was investigated and the results were used to choose the best option for its intended motorsport discipline. The test results are expected to vary with engine geometry and its natural manufacturer characteristics. The test was also relevant in bridging between computational data and real simulation as the results show flow, pressure and velocity readings but the behaviour of the engine is inferred from the nature of each test. The results of the data analysis were tested in a real-life simulation on a dynamometer to prove the theory of stack length on power and torque delivery, which helps determine the most suitable stack for the Vauxhall engine for rallying in the Caribbean.

Keywords: CFD simulation, Internal combustion engine, Intake system, Dynamometer test

Procedia PDF Downloads 278
37063 Theoretical Framework for Value Creation in Project Oriented Companies

Authors: Mariusz Hofman

Abstract:

The paper ‘Theoretical framework for value creation in Project-Oriented Companies’ is designed to determine, how organisations create value and whether this allows them to achieve market success. An assumption has been made that there are two routes to achieving this value. The first one is to create intangible assets (i.e. the resources of human, structural and relational capital), while the other one is to create added value (understood as the surplus of revenue over costs). It has also been assumed that the combination of the achieved added value and unique intangible assets translates to the success of a project-oriented company. The purpose of the paper is to present hypothetical and deductive model which describing the modus operandi of such companies and approach to model operationalisation. All the latent variables included in the model are theoretical constructs with observational indicators (measures). The existence of a latent variable (construct) and also submodels will be confirmed based on a covariance matrix which in turn is based on empirical data, being a set of observational indicators (measures). This will be achieved with a confirmatory factor analysis (CFA). Due to this statistical procedure, it will be verified whether the matrix arising from the adopted theoretical model differs statistically from the empirical matrix of covariance arising from the system of equations. The fit of the model with the empirical data will be evaluated using χ2, RMSEA and CFI (Comparative Fit Index). How well the theoretical model fits the empirical data is assessed through a number of indicators. If the theoretical conjectures are confirmed, an interesting development path can be defined for project-oriented companies. This will let such organisations perform efficiently in the face of the growing competition and pressure on innovation.

Keywords: value creation, project-oriented company, structural equation modelling

Procedia PDF Downloads 286
37062 A Method for Reconfigurable Manufacturing Systems Customization Measurement

Authors: Jesus Kombaya, Nadia Hamani, Lyes Kermad

Abstract:

The preservation of a company’s place on the market in such aggressive competition is becoming a survival challenge for manufacturers. In this context, survivors are only those who succeed to satisfy their customers’ needs as quickly as possible. The production system should be endowed with a certain level of flexibility to eliminate or reduce the rigidity of the production systems in order to facilitate the conversion and/or the change of system’s features to produce different products. Therefore, it is essential to guarantee the quality, the speed and the flexibility to survive in this competition. According to literature, this adaptability is referred to as the notion of "change". Indeed, companies are trying to establish a more flexible and agile manufacturing system through several reconfiguration actions. Reconfiguration contributes to the extension of the manufacturing system life cycle by modifying its physical, organizational and computer characteristics according to the changing market conditions. Reconfigurability is characterized by six key elements that are: modularity, integrability, diagnosability, convertibility, scalability and customization. In order to control the production systems, it is essential for manufacturers to make good use of this capability in order to be sure that the system has an optimal and adapted level of reconfigurability that allows it to produce in accordance with the set requirements. This document develops a measure of customization of reconfigurable production systems. These measures do not only impact the production system but also impact the product design and the process design, which can therefore serve as a guide for the customization of manufactured product. A case study is presented to show the use of the proposed approach.

Keywords: reconfigurable manufacturing systems, customization, measure, flexibility

Procedia PDF Downloads 118
37061 The Use of Geographic Information System Technologies for Geotechnical Monitoring of Pipeline Systems

Authors: A. G. Akhundov

Abstract:

Issues of obtaining unbiased data on the status of pipeline systems of oil- and oil product transportation become especially important when laying and operating pipelines under severe nature and climatic conditions. The essential attention is paid here to researching exogenous processes and their impact on linear facilities of the pipeline system. Reliable operation of pipelines under severe nature and climatic conditions, timely planning and implementation of compensating measures are only possible if operation conditions of pipeline systems are regularly monitored, and changes of permafrost soil and hydrological operation conditions are accounted for. One of the main reasons for emergency situations to appear is the geodynamic factor. Emergency situations are proved by the experience to occur within areas characterized by certain conditions of the environment and to develop according to similar scenarios depending on active processes. The analysis of natural and technical systems of main pipelines at different stages of monitoring gives a possibility of making a forecast of the change dynamics. The integration of GIS technologies, traditional means of geotechnical monitoring (in-line inspection, geodetic methods, field observations), and remote methods (aero-visual inspection, aero photo shooting, air and ground laser scanning) provides the most efficient solution of the problem. The united environment of geo information system (GIS) is a comfortable way to implement the monitoring system on the main pipelines since it provides means to describe a complex natural and technical system and every element thereof with any set of parameters. Such GIS enables a comfortable simulation of main pipelines (both in 2D and 3D), the analysis of situations and selection of recommendations to prevent negative natural or man-made processes and to mitigate their consequences. The specifics of such systems include: a multi-dimensions simulation of facilities in the pipeline system, math modelling of the processes to be observed, and the use of efficient numeric algorithms and software packets for forecasting and analyzing. We see one of the most interesting possibilities of using the monitoring results as generating of up-to-date 3D models of a facility and the surrounding area on the basis of aero laser scanning, data of aerophotoshooting, and data of in-line inspection and instrument measurements. The resulting 3D model shall be the basis of the information system providing means to store and process data of geotechnical observations with references to the facilities of the main pipeline; to plan compensating measures, and to control their implementation. The use of GISs for geotechnical monitoring of pipeline systems is aimed at improving the reliability of their operation, reducing the probability of negative events (accidents and disasters), and at mitigation of consequences thereof if they still are to occur.

Keywords: databases, 3D GIS, geotechnical monitoring, pipelines, laser scaning

Procedia PDF Downloads 186
37060 Mediatization of Politics and Democracy in Pakistan: An Interpretative Phenomenological Analysis

Authors: Shahid Imran

Abstract:

'Mediatization' has influenced the politics by shaping and transforming the attitudes and practices of political actors. It is a serious challenge to democracy in today’s era. This study aims to analyze the dynamics of media politics interplay in Pakistan and the contextual factors which govern this interplay. It will also address the perceived influence of media on the practices of politicians from the perspectives of the actors. The objectives have been achieved qualitatively through Interpretive Phenomenological Analysis (IPA). The phenomenological data have been collected using semi-structured interviews of journalists and politicians of Pakistan. The findings depict that politics in Pakistan is more driven by media logic than political or democratic logic. Media and politics have a ‘Tom and Jerry’ relationship. Political ecology is highly media-induced: politicians strategically adopt and adapt the media logic to be in the ‘media spotlight’; journalists, on the other hands, do not practice ‘fair journalism rather a more politically parallelized. The mediatized political communication behaviours of the actors are the undermining the public service logic and affecting the spirit of democracy in Pakistan. The study offers some valued implications for media, politicians and policy makers.

Keywords: medialization, media logic, politics, political logic

Procedia PDF Downloads 215
37059 Predictive Analysis of the Stock Price Market Trends with Deep Learning

Authors: Suraj Mehrotra

Abstract:

The stock market is a volatile, bustling marketplace that is a cornerstone of economics. It defines whether companies are successful or in spiral. A thorough understanding of it is important - many companies have whole divisions dedicated to analysis of both their stock and of rivaling companies. Linking the world of finance and artificial intelligence (AI), especially the stock market, has been a relatively recent development. Predicting how stocks will do considering all external factors and previous data has always been a human task. With the help of AI, however, machine learning models can help us make more complete predictions in financial trends. Taking a look at the stock market specifically, predicting the open, closing, high, and low prices for the next day is very hard to do. Machine learning makes this task a lot easier. A model that builds upon itself that takes in external factors as weights can predict trends far into the future. When used effectively, new doors can be opened up in the business and finance world, and companies can make better and more complete decisions. This paper explores the various techniques used in the prediction of stock prices, from traditional statistical methods to deep learning and neural networks based approaches, among other methods. It provides a detailed analysis of the techniques and also explores the challenges in predictive analysis. For the accuracy of the testing set, taking a look at four different models - linear regression, neural network, decision tree, and naïve Bayes - on the different stocks, Apple, Google, Tesla, Amazon, United Healthcare, Exxon Mobil, J.P. Morgan & Chase, and Johnson & Johnson, the naïve Bayes model and linear regression models worked best. For the testing set, the naïve Bayes model had the highest accuracy along with the linear regression model, followed by the neural network model and then the decision tree model. The training set had similar results except for the fact that the decision tree model was perfect with complete accuracy in its predictions, which makes sense. This means that the decision tree model likely overfitted the training set when used for the testing set.

Keywords: machine learning, testing set, artificial intelligence, stock analysis

Procedia PDF Downloads 89