Search results for: velocity prediction program
Commenced in January 2007
Frequency: Monthly
Edition: International
Paper Count: 7434

Search results for: velocity prediction program

3324 Towards Long-Range Pixels Connection for Context-Aware Semantic Segmentation

Authors: Muhammad Zubair Khan, Yugyung Lee

Abstract:

Deep learning has recently achieved enormous response in semantic image segmentation. The previously developed U-Net inspired architectures operate with continuous stride and pooling operations, leading to spatial data loss. Also, the methods lack establishing long-term pixels connection to preserve context knowledge and reduce spatial loss in prediction. This article developed encoder-decoder architecture with bi-directional LSTM embedded in long skip-connections and densely connected convolution blocks. The network non-linearly combines the feature maps across encoder-decoder paths for finding dependency and correlation between image pixels. Additionally, the densely connected convolutional blocks are kept in the final encoding layer to reuse features and prevent redundant data sharing. The method applied batch-normalization for reducing internal covariate shift in data distributions. The empirical evidence shows a promising response to our method compared with other semantic segmentation techniques.

Keywords: deep learning, semantic segmentation, image analysis, pixels connection, convolution neural network

Procedia PDF Downloads 107
3323 Excitation Experiments of a Cone Loudspeaker and Vibration-Acoustic Analysis Using FEM

Authors: Y. Hu, X. Zhao, T. Yamaguchi, M. Sasajima, Y. Koike

Abstract:

To focus on the vibration mode of a cone loudspeaker, which acts as an electroacoustic transducer, excitation experiments were performed using two types of loudspeaker units: one employing an impulse hammer and the other a sweep signal. The on-axis sound pressure frequency properties of the loudspeaker were evaluated, and the characteristic properties of the loudspeakers were successfully determined in both excitation experiments. Moreover, under conditions identical to the experiment conditions, a coupled analysis of the vibration-acoustics of the cone loudspeaker was performed using an acoustic analysis software program that considers the impact of damping caused by air viscosity. The result of sound pressure frequency properties with the numerical analysis are the most closely match that measured in the excitation experiments over a wide range of frequency bands.

Keywords: anechoic room, finite element method, impulse hammer, loudspeaker, reverberation room, sweep signal

Procedia PDF Downloads 438
3322 Design of Active Power Filters for Harmonics on Power System and Reducing Harmonic Currents

Authors: Düzgün Akmaz, Hüseyin Erişti

Abstract:

In the last few years, harmonics have been occurred with the increasing use of nonlinear loads, and these harmonics have been an ever increasing problem for the line systems. This situation importantly affects the quality of power and gives large losses to the network. An efficient way to solve these problems is providing harmonic compensation through parallel active power filters. Many methods can be used in the control systems of the parallel active power filters which provide the compensation. These methods efficiently affect the performance of the active power filters. For this reason, the chosen control method is significant. In this study, Fourier analysis (FA) control method and synchronous reference frame (SRF) control method are discussed. These control methods are designed for both eliminate harmonics and perform reactive power compensation in MATLAB/Simulink pack program and are tested. The results have been compared for each two methods.

Keywords: parallel active power filters, harmonic compensation, power quality, harmonics

Procedia PDF Downloads 463
3321 Numerical Study on the Performance of Upgraded Victorian Brown Coal in an Ironmaking Blast Furnace

Authors: Junhai Liao, Yansong Shen, Aibing Yu

Abstract:

A 3D numerical model is developed to simulate the complicated in-furnace combustion phenomena in the lower part of an ironmaking blast furnace (BF) while using pulverized coal injection (PCI) technology to reduce the consumption of relatively expensive coke. The computational domain covers blowpipe-tuyere-raceway-coke bed in the BF. The model is validated against experimental data in terms of gaseous compositions and coal burnout. Parameters, such as coal properties and some key operational variables, play an important role on the performance of coal combustion. Their diverse effects on different combustion characteristics are examined in the domain, in terms of gas compositions, temperature, and burnout. The heat generated by the combustion of upgraded Victorian brown coal is able to meet the heating requirement of a BF, hence making upgraded brown coal injected into BF possible. It is evidenced that the model is suitable to investigate the mechanism of the PCI operation in a BF. Prediction results provide scientific insights to optimize and control of the PCI operation. This model cuts the cost to investigate and understand the comprehensive combustion phenomena of upgraded Victorian brown coal in a full-scale BF.

Keywords: blast furnace, numerical study, pulverized coal injection, Victorian brown coal

Procedia PDF Downloads 246
3320 Saline Water Transgression into Fresh Coastal Groundwater in the Confined Aquifer of Lagos, Nigeria

Authors: Babatunde Adebo, Adedeji Adetoyinbo

Abstract:

Groundwater is an important constituent of the hydrological cycle and plays a vital role in augmenting water supply to meet the ever-increasing needs of people for domestic, agricultural and industrial purposes. Unfortunately, this important resource has in most cases been contaminated due to the advancement of seawater into the fresh groundwater. This is due to the high volume of water being abstracted in these areas as a result of a high population of coastal dwellers. The knowledge of salinity level and intrusion of saltwater into the freshwater aquifer is, therefore, necessary for groundwater monitoring and prediction in the coastal areas. In this work, an advection-dispersion saltwater intrusion model is used to study and simulate saltwater intrusion in a typical coastal aquifer. The aquifer portion was divided into a grid with elements and nodes. Map of the study area indicating well locations were overlain on the grid system such that these locations coincide with the nodes. Chlorides at these well were considered as initial nodal salinities. Results showed a highest and lowest increase in simulated chloride of 37.89 mg/L and 0.8 mg/L respectively. It also revealed that the chloride concentration of most of the considered well might climb unacceptable level in the next few years, if the current abstraction rate continues unabated.

Keywords: saltwater intrusion, coastal aquifer, nodal salinity, chloride concentration

Procedia PDF Downloads 244
3319 A Model for Diagnosis and Prediction of Coronavirus Using Neural Network

Authors: Sajjad Baghernezhad

Abstract:

Meta-heuristic and hybrid algorithms have high adeer in modeling medical problems. In this study, a neural network was used to predict covid-19 among high-risk and low-risk patients. This study was conducted to collect the applied method and its target population consisting of 550 high-risk and low-risk patients from the Kerman University of medical sciences medical center to predict the coronavirus. In this study, the memetic algorithm, which is a combination of a genetic algorithm and a local search algorithm, has been used to update the weights of the neural network and develop the accuracy of the neural network. The initial study showed that the accuracy of the neural network was 88%. After updating the weights, the memetic algorithm increased by 93%. For the proposed model, sensitivity, specificity, positive predictivity value, value/accuracy to 97.4, 92.3, 95.8, 96.2, and 0.918, respectively; for the genetic algorithm model, 87.05, 9.20 7, 89.45, 97.30 and 0.967 and for logistic regression model were 87.40, 95.20, 93.79, 0.87 and 0.916. Based on the findings of this study, neural network models have a lower error rate in the diagnosis of patients based on individual variables and vital signs compared to the regression model. The findings of this study can help planners and health care providers in signing programs and early diagnosis of COVID-19 or Corona.

Keywords: COVID-19, decision support technique, neural network, genetic algorithm, memetic algorithm

Procedia PDF Downloads 71
3318 Thermal Comfort Study of School Buildings in South Minahasa Regency Case Study: SMA Negeri 1 Amurang, Indonesia

Authors: Virgino Stephano Moniaga

Abstract:

Thermal comfort inside a building can affect students in their learning process. The learning process of students can be improved if the condition of the classrooms is comfortable. This study will be conducted in SMA Negeri 1 Amurang which is a senior high school building located in South Minahasa Regency. Based on preliminary survey, generally, students were not satisfied with the existing level of comfort, which subsequently affected the teaching and learning process in the classroom. The purpose of this study is to analyze the comfort level of classrooms occupants and recommend building design solutions that can improve the thermal comfort of classrooms. In this study, three classrooms will be selected for thermal comfort measurements. The thermal comfort measurements will be taken in naturally ventilated classrooms. The measured data comprise of personal data (clothing and students activity), air humidity, air temperature, mean radiant temperature and air flow velocity. Simultaneously, the students will be asked to fill out a questionnaire that asked about the level of comfort that was felt at the time. The results of field measurements and questionnaires will be analyzed based on the PMV and PPD indices. The results of the analysis will decide whether the classrooms are comfortable or not. This study can be continued to obtain a more optimal design solution to improve the thermal comfort of the classrooms. The expected results from this study can improve the quality of teaching and learning process between teachers and students which can further assist the government efforts to improve the quality of national education.

Keywords: classrooms, PMV, PPD, thermal comfort

Procedia PDF Downloads 322
3317 Contestation of Local and Non-Local Knowledge in Developing Bali Cattle at Barru Regency, Province of South Sulawesi, Indonesia

Authors: A. Amidah Amrawaty, M. Saleh S. Ali, Darmawan Salman

Abstract:

The aim of this study was to identify local and non local knowledge in Bali cattle development, to analyze the contestation between local and non-local knowledge. The paradigm used was constructivism paradigm with a qualitative approach. descriptive type of research using case study method. The study was conducted in four villages subjected to Agropolitan Program, i.e. Palakka, Tompo, Galung and Anabanua in Barru District, province of South Sulawesi. The results indicated that the local knowledge of the farmers were: a) knowledge of animal housing, b) knowledge of the prevention and control disease, c) knowledge of the feed, d) knowledge of breed selection, e) knowledge of sharing arrangement, f) knowledge of marketing, Generally, there are three patterns of knowledge contestation namely coexistence, ‘zero sum game’ and hybridization but in this research only coexistence and zero sum game patterns took place, while the pattern of hybridization did not occur.

Keywords: contestation, local knowledge, non-local knowledge, developing of Bali cattle

Procedia PDF Downloads 409
3316 Anti-Inflammatory Effect of Myristic Acid through Inhibiting NF-κB and MAPK Signaling Pathways in Lipopolysaccharide-Stimulated RAW 264.7 Macrophage Cells

Authors: Hyun Ji Hyun, Hyo Sun Suh, Min Kook Kim, Yong Chan Kwon, Byung-Mu Lee

Abstract:

Scope: This study is focused on the effect of myristic acid on LPS-induced inflammation in RAW 264.7 macrophage cells. Methods and results: For the experiment, RAW 264.7 mouse macrophage cell line was used. Results showed that treatment with myristic acid can attenuate LPS-induced inflammation. Moreover, myristic acid significantly suppressed expression of inflammatory mediators and down-regulating UVB-induced intracellular ROS generation. Furthermore, myristic acid reduced the expression of NF-κB by inhibiting degradation of IκB-α and ERK, JNK, and p38 pathways by inhibiting phosphorylation in RAW 264.7 macrophage cells. Conclusion: Overall, these data suggest that the myristic acid could reduce LPS-induced inflammation. Acknowledgment: This research was supported by the Ministry of Trade, Industry & Energy(MOTIE), Korea Institute for Advancement of Technology(KIAT) through the Encouragement Program for The Industries of Economic Cooperation Region

Keywords: anti-inflammation, myristic acid, ROS, ultraviolet light

Procedia PDF Downloads 206
3315 Interaction between University Art Gallery and the Community through Public Art Exhibitions

Authors: Qiao Mao

Abstract:

Starting from the theoretical viewpoints of relational aesthetics, this study explores the relationship between the university art gallery and the communities, taking Art Scattering Program in the Name of Trees of the Art Gallery of National Taiwan Normal University (NTNU) as a case. The researcher uses observational and interview methods to obtain research materials to explore how university art galleries interact with communities through public art exhibitions and strengthen the relatively weak relationships with community residents. The researcher also observes how community residents can change their opinions about the university gallery by participating in public art exhibitions. The results show that the university art gallery can effectively establish the interaction with the community residents and repair the relationship with them through such programs as "collection-sharing," "teacher-student co-creation," "artist stationing," and "education promotion activities," playing an active role in promoting interpersonal communication, sustaining the natural environment development and improving community public space.

Keywords: university art gallery, public art, relational aesthetics, communities, interaction

Procedia PDF Downloads 92
3314 Rain Dropsize Distribution from Individual Storms and Variability in Nigeria Topical Region

Authors: Akinyemi Tomiwa

Abstract:

The microstructure of rainfall is important for predicting and modeling various environmental processes, such as rainfall interception by vegetation, soil erosion, and radar signals in rainfall. This rain microstructure was studied with a vertically pointing Micro Rain Radar (MRR) located at a tropical location in Akure South West Nigeria (7o 15’ N, 5o 15’ E). This research utilizes two years of data (2018 and 2019), and the data obtained comprises rainfall parameters such as Rain rates, radar reflectivity, liquid water content, fall velocity and Drop Size Distribution (DSD) based on vertical profiles. The measurement and variations of rain microstructure of these parameters with heights for different rain types were presented from ground level up to the height of 4800 m at 160 m range gates. It has been found that the convective, stratiform and mixed, which are the three major rain types, have different rain microstructures at different heights and were evaluated in this research. The correlation coefficient and the regression line equation were computed for each rain event. The highest rain rate and liquid water content were observed within the height range of 160-4800. It was found that a good correlation exists between the measured parameters. Hence it shows that specific liquid water content increases with increasing rain rate for both stratiform and convective rain types in this part of the world. The results can be very useful for a better understanding of rain structure over tropical regions.

Keywords: rain microstructure, drop size distribution, rain rates, stratiform, convective.

Procedia PDF Downloads 43
3313 Recurring as a Means of Partial Strength Recovery of Concrete Subjected to Elevated Temperatures

Authors: Shree Laxmi Prashant, Subhash C. Yaragal, K. S. Babu Narayan

Abstract:

Concrete is found to undergo degradation when subjected to elevated temperatures and loose substantial amount of its strength. The loss of strength in concrete is mainly attributed to decomposition of C-S-H and release of physically and chemically bound water, which begins when the exposure temperature exceeds 100°C. When such a concrete comes in contact with moisture, the cement paste is found rehydrate and considerable amount of strength lost is found to recover. This paper presents results of an experimental program carried out to investigate the effect of recuring on strength gain of OPC concrete specimens subjected to elevated temperatures from 200°C to 800°C, which were subjected to retention time of two hours and four hours at the designated temperature. Strength recoveries for concrete subjected to 7 designated elevated temperatures are compared. It is found that the efficacy of recuring as a measure of strength recovery reduces with increase in exposure temperature.

Keywords: elevated temperature, recuring, strength recovery, compressive strength

Procedia PDF Downloads 601
3312 Autonomous Landing of UAV on Moving Platform: A Mathematical Approach

Authors: Mortez Alijani, Anas Osman

Abstract:

Recently, the popularity of Unmanned aerial vehicles (UAVs) has skyrocketed amidst the unprecedented events and the global pandemic, as they play a key role in both the security and health sectors, through surveillance, taking test samples, transportation of crucial goods and spreading awareness among civilians. However, the process of designing and producing such aerial robots is suppressed by the internal and external constraints that pose serious challenges. Landing is one of the key operations during flight, especially, the autonomous landing of UAVs on a moving platform is a scientifically complex engineering problem. Typically having a successful automatic landing of UAV on a moving platform requires accurate localization of landing, fast trajectory planning, and robust control planning. To achieve these goals, the information about the autonomous landing process such as the intersection point, the position of platform/UAV and inclination angle are more necessary. In this study, the mathematical approach to this problem in the X-Y axis based on the inclination angle and position of UAV in the landing process have been presented. The experimental results depict the accurate position of the UAV, intersection between UAV and moving platform and inclination angle in the landing process, allowing prediction of the intersection point.

Keywords: autonomous landing, inclination angle, unmanned aerial vehicles, moving platform, X-Y axis, intersection point

Procedia PDF Downloads 168
3311 Drawing, Design and Building Information Modelling (BIM): Embedding Advanced Digital Tools in the Academy Programs for Building Engineers and Architects

Authors: Vittorio Caffi, Maria Pignataro, Antonio Cosimo Devito, Marco Pesenti

Abstract:

This paper deals with the integration of advanced digital design and modelling tools and methodologies, known as Building Information Modelling, into the traditional Academy educational programs for building engineers and architects. Nowadays, the challenge the Academy has to face is to present the new tools and their features to the pupils, making sure they acquire the proper skills in order to leverage the potential they offer also for the other courses embedded in the educational curriculum. The syllabus here presented refers to the “Drawing for building engineering”, “2D and 3D laboratory” and “3D modelling” curricula of the MSc in Building Engineering of the Politecnico di Milano. Such topics, included since the first year in the MSc program, are fundamental to give the students the instruments to master the complexity of an architectural or building engineering project with digital tools, so as to represent it in its various forms.

Keywords: BIM, BIM curricula, computational design, digital modelling

Procedia PDF Downloads 671
3310 Genetic Algorithm Methods for Determination Over Flow Coefficient of Medium Throat Length Morning Glory Spillway Equipped Crest Vortex Breakers

Authors: Roozbeh Aghamajidi

Abstract:

Shaft spillways are circling spillways used generally for emptying unexpected floods on earth and concrete dams. There are different types of shaft spillways: Stepped and Smooth spillways. Stepped spillways pass more flow discharges through themselves in comparison to smooth spillways. Therefore, awareness of flow behavior of these spillways helps using them better and more efficiently. Moreover, using vortex breaker has great effect on passing flow through shaft spillway. In order to use more efficiently, the risk of flow pressure decreases to less than fluid vapor pressure, called cavitations, should be prevented as far as possible. At this research, it has been tried to study different behavior of spillway with different vortex shapes on spillway crest on flow. From the viewpoint of the effects of flow regime changes on spillway, changes of step dimensions, and the change of type of discharge will be studied effectively. Therefore, two spillway models with three different vortex breakers and three arrangements have been used to assess the hydraulic characteristics of flow. With regard to the inlet discharge to spillway, the parameters of pressure and flow velocity on spillway surface have been measured at several points and after each run. Using these kinds of information leads us to create better design criteria of spillway profile. To achieve these purposes, optimization has important role and genetic algorithm are utilized to study the emptying discharge. As a result, it turned out that the best type of spillway with maximum discharge coefficient is smooth spillway with ogee shapes as vortex breaker and 3 number as arrangement. Besides it has been concluded that the genetic algorithm can be used to optimize the results.

Keywords: shaft spillway, vortex breaker, flow, genetic algorithm

Procedia PDF Downloads 375
3309 Design Considerations for the Construction of an Open Decontamination Facility for Managing Civil Emergencies

Authors: Sarmin, S., Ologuin, R.S.

Abstract:

Background: Rapid population growth and land constraints in Singapore results in a possible situation in which we face a higher number of casualties and lack of operational space in healthcare facilities during disasters and HAZMAT events, collectively known as Civil Emergencies. This creates a need for available working space within hospital grounds to be amphibious or multi-functional, to ensure the institution’s capability to respond efficiently to Civil Emergencies. The Emergency Department (ED) mitigates this issue by converting the Ambulance Assembly Area used during peacetime into an Open Decontamination Facility (ODF) during Civil Emergency Response, for decontamination of casualties before they proceed to treatment areas into Ambulance Assembly Area used during peacetime. Aims: To effectively operationalize the Open Decontamination Facility (ODF) through the reduction of manual handling. Methods: From past experiences on Civil Emergency exercises, it was labor-intensive for staff to set up the Open Decontamination Facility (ODF). Manual handling to set up the Decontamination lanes by bringing down the curtains and supply of water was required to be turned on. Conclusion: The effectiveness of the design construction of an Open Decontamination Facility (ODF) is based on the use of automation of bringing down the curtains on the various lanes. The use of control panels for water supply to decontaminate patients. Safety within the ODF was considered with the installation of panic buttons, intercom for staff communication, and perimeter curtains were installed with stability arm to manage the condition with high wind velocity.

Keywords: civil emergencies, disaster, emergency department, Hazmat

Procedia PDF Downloads 103
3308 An Integrative Computational Pipeline for Detection of Tumor Epitopes in Cancer Patients

Authors: Tanushree Jaitly, Shailendra Gupta, Leila Taher, Gerold Schuler, Julio Vera

Abstract:

Genomics-based personalized medicine is a promising approach to fight aggressive tumors based on patient's specific tumor mutation and expression profiles. A remarkable case is, dendritic cell-based immunotherapy, in which tumor epitopes targeting patient's specific mutations are used to design a vaccine that helps in stimulating cytotoxic T cell mediated anticancer immunity. Here we present a computational pipeline for epitope-based personalized cancer vaccines using patient-specific haplotype and cancer mutation profiles. In the workflow proposed, we analyze Whole Exome Sequencing and RNA Sequencing patient data to detect patient-specific mutations and their expression level. Epitopes including the tumor mutations are computationally predicted using patient's haplotype and filtered based on their expression level, binding affinity, and immunogenicity. We calculate binding energy for each filtered major histocompatibility complex (MHC)-peptide complex using docking studies, and use this feature to select good epitope candidates further.

Keywords: cancer immunotherapy, epitope prediction, NGS data, personalized medicine

Procedia PDF Downloads 259
3307 Medical Image Augmentation Using Spatial Transformations for Convolutional Neural Network

Authors: Trupti Chavan, Ramachandra Guda, Kameshwar Rao

Abstract:

The lack of data is a pain problem in medical image analysis using a convolutional neural network (CNN). This work uses various spatial transformation techniques to address the medical image augmentation issue for knee detection and localization using an enhanced single shot detector (SSD) network. The spatial transforms like a negative, histogram equalization, power law, sharpening, averaging, gaussian blurring, etc. help to generate more samples, serve as pre-processing methods, and highlight the features of interest. The experimentation is done on the OpenKnee dataset which is a collection of knee images from the openly available online sources. The CNN called enhanced single shot detector (SSD) is utilized for the detection and localization of the knee joint from a given X-ray image. It is an enhanced version of the famous SSD network and is modified in such a way that it will reduce the number of prediction boxes at the output side. It consists of a classification network (VGGNET) and an auxiliary detection network. The performance is measured in mean average precision (mAP), and 99.96% mAP is achieved using the proposed enhanced SSD with spatial transformations. It is also seen that the localization boundary is comparatively more refined and closer to the ground truth in spatial augmentation and gives better detection and localization of knee joints.

Keywords: data augmentation, enhanced SSD, knee detection and localization, medical image analysis, openKnee, Spatial transformations

Procedia PDF Downloads 161
3306 Computational Analysis of Cavity Effect over Aircraft Wing

Authors: P. Booma Devi, Dilip A. Shah

Abstract:

This paper seeks the potentials of studying aerodynamic characteristics of inward cavities called dimples, as an alternative to the classical vortex generators. Increasing stalling angle is a greater challenge in wing design. But our examination is primarily focused on increasing lift. In this paper, enhancement of lift is mainly done by introduction of dimple or cavity in a wing. In general, aircraft performance can be enhanced by increasing aerodynamic efficiency that is lift to drag ratio of an aircraft wing. Efficiency improvement can be achieved by improving the maximum lift co-efficient or by reducing the drag co-efficient. At the time of landing aircraft, high angle of attack may lead to stalling of aircraft. To avoid this kind of situation, increase in the stalling angle is warranted. Hence, improved stalling characteristic is the best way to ease landing complexity. Computational analysis is done for the wing segment made of NACA 0012. Simulation is carried out for 30 m/s free stream velocity over plain airfoil and different types of cavities. The wing is modeled in CATIA V5R20 and analyses are carried out using ANSYS CFX. Triangle and square shapes are used as cavities for analysis. Simulations revealed that cavity placed on wing segment shows an increase of maximum lift co-efficient when compared to normal wing configuration. Flow separation is delayed at downstream of the wing by the presence of cavities up to a particular angle of attack.

Keywords: lift, drag reduce, square dimple, triangle dimple, enhancement of stall angle

Procedia PDF Downloads 353
3305 Influence and Dissemination of Solecism among Moroccan High School and University Students

Authors: Rachid Ed-Dali, Khalid Elasri

Abstract:

Mass media seem to provide a rich content for language acquisition. Exposure to television, the Internet, the mobile phone and other technological gadgets and devices helps enrich the student’s lexicon positively as well as negatively. The difficulties encountered by students while learning and acquiring second languages in addition to their eagerness to comprehend the content of a particular program prompt them to diversify their methods so as to achieve their targets. The present study highlights the significance of certain media channels and their involvement in language acquisition with the employment of the Natural Approach to further grasp whether students, especially secondary and high school students, learn and acquire errors through watching subtitled television programs. The chief objective is investigating the deductive and inductive relevance of certain programs beside the involvement of peripheral learning while acquiring mistakes.

Keywords: errors, mistakes, Natural Approach, peripheral learning, solecism

Procedia PDF Downloads 124
3304 Data-Driven Approach to Predict Inpatient's Estimated Discharge Date

Authors: Ayliana Dharmawan, Heng Yong Sheng, Zhang Xiaojin, Tan Thai Lian

Abstract:

To facilitate discharge planning, doctors are presently required to assign an Estimated Discharge Date (EDD) for each patient admitted to the hospital. This assignment of the EDD is largely based on the doctor’s judgment. This can be difficult for cases which are complex or relatively new to the doctor. It is hypothesized that a data-driven approach would be able to facilitate the doctors to make accurate estimations of the discharge date. Making use of routinely collected data on inpatient discharges between January 2013 and May 2016, a predictive model was developed using machine learning techniques to predict the Length of Stay (and hence the EDD) of inpatients, at the point of admission. The predictive performance of the model was compared to that of the clinicians using accuracy measures. Overall, the best performing model was found to be able to predict EDD with an accuracy improvement in Average Squared Error (ASE) by -38% as compared to the first EDD determined by the present method. It was found that important predictors of the EDD include the provisional diagnosis code, patient’s age, attending doctor at admission, medical specialty at admission, accommodation type, and the mean length of stay of the patient in the past year. The predictive model can be used as a tool to accurately predict the EDD.

Keywords: inpatient, estimated discharge date, EDD, prediction, data-driven

Procedia PDF Downloads 176
3303 Data Science-Based Key Factor Analysis and Risk Prediction of Diabetic

Authors: Fei Gao, Rodolfo C. Raga Jr.

Abstract:

This research proposal will ascertain the major risk factors for diabetes and to design a predictive model for risk assessment. The project aims to improve diabetes early detection and management by utilizing data science techniques, which may improve patient outcomes and healthcare efficiency. The phase relation values of each attribute were used to analyze and choose the attributes that might influence the examiner's survival probability using Diabetes Health Indicators Dataset from Kaggle’s data as the research data. We compare and evaluate eight machine learning algorithms. Our investigation begins with comprehensive data preprocessing, including feature engineering and dimensionality reduction, aimed at enhancing data quality. The dataset, comprising health indicators and medical data, serves as a foundation for training and testing these algorithms. A rigorous cross-validation process is applied, and we assess their performance using five key metrics like accuracy, precision, recall, F1-score, and area under the receiver operating characteristic curve (AUC-ROC). After analyzing the data characteristics, investigate their impact on the likelihood of diabetes and develop corresponding risk indicators.

Keywords: diabetes, risk factors, predictive model, risk assessment, data science techniques, early detection, data analysis, Kaggle

Procedia PDF Downloads 81
3302 Developing a Web-Based Workflow Management System in Cloud Computing Platforms

Authors: Wang Shuen-Tai, Lin Yu-Ching, Chang Hsi-Ya

Abstract:

Cloud computing is the innovative and leading information technology model for enabling convenient, on-demand network access to a shared pool of configurable computing resources that can be rapidly provisioned and released with minimal management effort. In this paper, we aim at the development of workflow management system for cloud computing platforms based on our previous research on the dynamic allocation of the cloud computing resources and its workflow process. We took advantage of the HTML 5 technology and developed web-based workflow interface. In order to enable the combination of many tasks running on the cloud platform in sequence, we designed a mechanism and developed an execution engine for workflow management on clouds. We also established a prediction model which was integrated with job queuing system to estimate the waiting time and cost of the individual tasks on different computing nodes, therefore helping users achieve maximum performance at lowest payment. This proposed effort has the potential to positively provide an efficient, resilience and elastic environment for cloud computing platform. This development also helps boost user productivity by promoting a flexible workflow interface that lets users design and control their tasks' flow from anywhere.

Keywords: web-based, workflow, HTML5, Cloud Computing, Queuing System

Procedia PDF Downloads 311
3301 Estimation of Elastic Modulus of Soil Surrounding Buried Pipeline Using Multi-Response Surface Methodology

Authors: Won Mog Choi, Seong Kyeong Hong, Seok Young Jeong

Abstract:

The stress on the buried pipeline under pavement is significantly affected by vehicle loads and elastic modulus of the soil surrounding the pipeline. The correct elastic modulus of soil has to be applied to the finite element model to investigate the effect of the vehicle loads on the buried pipeline using finite element analysis. The purpose of this study is to establish the approach to calculating the correct elastic modulus of soil using the optimization process. The optimal elastic modulus of soil, which minimizes the difference between the strain measured from vehicle driving test at the velocity of 35km/h and the strain calculated from finite element analyses, was calculated through the optimization process using multi-response surface methodology. Three elastic moduli of soil (road layer, original soil, dense sand) surrounding the pipeline were defined as the variables for the optimization. Further analyses with the optimal elastic modulus at the velocities of 4.27km/h, 15.47km/h, 24.18km/h were performed and compared to the test results to verify the applicability of multi-response surface methodology. The results indicated that the strain of the buried pipeline was mostly affected by the elastic modulus of original soil, followed by the dense sand and the load layer, as well as the results of further analyses with optimal elastic modulus of soil show good agreement with the test.

Keywords: pipeline, optimization, elastic modulus of soil, response surface methodology

Procedia PDF Downloads 390
3300 Teaching Legal English in Russia: Traditions and Problems

Authors: Irina A. Martynenko, Viktoriia V. Pikalova

Abstract:

At the moment, there are more than a thousand law schools in Russia. The program of preparation in each of them without exception includes English language course. It is believed that lawyers in Russia are best trained at the MGIMO University, the All-Russian State University of Justice, Kutafin Moscow State Law University, Peoples’ Friendship University of Russia, Lomonosov Moscow State University, St. Petersburg State University, Diplomatic Academy of Russian Foreign Ministry and some others. Currently, the overwhelming majority of universities operate using the two-level system of education: bachelor's plus master's degree. Foreign languages are taught at both levels. The main example of consideration used throughout this paper is Kutafin Moscow State Law University being one of the best law schools in the country. The article examines traditions of teaching legal English in Russia and highlights problem arising in this process. The authors suggest ways of solving them in the scope of modern views and practice of teaching English for specific purposes.

Keywords: Kutafin Moscow State Law University, legal English, Russia, teaching

Procedia PDF Downloads 234
3299 The Development of Web Based Instruction on Puppet Show

Authors: Piyanut Sujit

Abstract:

The purposes of this study were to: 1) create knowledge and develop web based instruction on the puppet show, 2) evaluate the effectiveness of the web based instruction on the puppet show by using the criteria of 80/80, and 3) compare and analyze the achievement of the students before and after learning with web based instruction on the puppet show. The population of this study included 53 students in the Program of Library and Information Sciences who registered in the subject of Reading and Reading Promotion in semester 1/2011, Suansunandha Rajabhat University. The research instruments consisted of web based instruction on the puppet show, specialist evaluation form, achievement test, and tests during the lesson. The research statistics included arithmetic mean, variable means, standard deviation, and t-test in SPSS for Windows. The results revealed that the effectiveness of the developed web based instruction was 84.67/80.47 which was higher than the set criteria at 80/80. The student achievement before and after learning showed statistically significant difference at 0.05 as in the hypothesis.

Keywords: puppet, puppet show, web based instruction, library and information sciences

Procedia PDF Downloads 370
3298 Constructing a Physics Guided Machine Learning Neural Network to Predict Tonal Noise Emitted by a Propeller

Authors: Arthur D. Wiedemann, Christopher Fuller, Kyle A. Pascioni

Abstract:

With the introduction of electric motors, small unmanned aerial vehicle designers have to consider trade-offs between acoustic noise and thrust generated. Currently, there are few low-computational tools available for predicting acoustic noise emitted by a propeller into the far-field. Artificial neural networks offer a highly non-linear and adaptive model for predicting isolated and interactive tonal noise. But neural networks require large data sets, exceeding practical considerations in modeling experimental results. A methodology known as physics guided machine learning has been applied in this study to reduce the required data set to train the network. After building and evaluating several neural networks, the best model is investigated to determine how the network successfully predicts the acoustic waveform. Lastly, a post-network transfer function is developed to remove discontinuity from the predicted waveform. Overall, methodologies from physics guided machine learning show a notable improvement in prediction performance, but additional loss functions are necessary for constructing predictive networks on small datasets.

Keywords: aeroacoustics, machine learning, propeller, rotor, neural network, physics guided machine learning

Procedia PDF Downloads 234
3297 Evaluation in Vitro and in Silico of Pleurotus ostreatus Capacity to Decrease the Amount of Low-Density Polyethylene Microplastics Present in Water Sample from the Middle Basin of the Magdalena River, Colombia

Authors: Loren S. Bernal., Catalina Castillo, Carel E. Carvajal, José F. Ibla

Abstract:

Plastic pollution, specifically microplastics, has become a significant issue in aquatic ecosystems worldwide. The large amount of plastic waste carried by water tributaries has resulted in the accumulation of microplastics in water bodies. The polymer aging process caused by environmental influences such as photodegradation and chemical degradation of additives leads to polymer embrittlement and properties change that require degradation or reduction procedures in rivers. However, there is a lack of such procedures for freshwater entities that develop over extended periods. The aim of this study is evaluate the potential of Pleurotus ostreatus a fungus, in reducing lowdensity polyethylene microplastics present in freshwater samples collected from the middle basin of the Magdalena River in Colombia. The study aims to evaluate this process both in vitro and in silico by identifying the growth capacity of Pleurotus ostreatus in the presence of microplastics and identifying the most likely interactions of Pleurotus ostreatus enzymes and their affinity energies. The study follows an engineering development methodology applied on an experimental basis. The in vitro evaluation protocol applied in this study focused on the growth capacity of Pleurotus ostreatus on microplastics using enzymatic inducers. In terms of in silico evaluation, molecular simulations were conducted using the Autodock 1.5.7 program to calculate interaction energies. The molecular dynamics were evaluated by using the myPresto Portal and GROMACS program to calculate radius of gyration and Energies.The results of the study showed that Pleurotus ostreatus has the potential to degrade low-density polyethylene microplastics. The in vitro evaluation revealed the adherence of Pleurotus ostreatus to LDPE using scanning electron microscopy. The best results were obtained with enzymatic inducers as a MnSO4 generating the activation of laccase or manganese peroxidase enzymes in the degradation process. The in silico modelling demonstrated that Pleurotus ostreatus was able to interact with the microplastics present in LDPE, showing affinity energies in molecular docking and molecular dynamics shown a minimum energy and the representative radius of gyration between each enzyme and its substract. The study contributes to the development of bioremediation processes for the removal of microplastics from freshwater sources using the fungus Pleurotus ostreatus. The in silico study provides insights into the affinity energies of Pleurotus ostreatus microplastic degrading enzymes and their interaction with low-density polyethylene. The study demonstrated that Pleurotus ostreatus can interact with LDPE microplastics, making it a good agent for the development of bioremediation processes that aid in the recovery of freshwater sources. The results of the study suggested that bioremediation could be a promising approach to reduce microplastics in freshwater systems.

Keywords: bioremediation, in silico modelling, microplastics, Pleurotus ostreatus

Procedia PDF Downloads 116
3296 Flexural Behavior of Light-Gauge Steel Box Sections Filled with Normal and Recycled Aggregates Concrete

Authors: Rola El-Nimri, Mu’Tasime Abdel-Jaber, Yasser Hunaiti

Abstract:

The flexural behavior of light-gauge steel box sections filled with recycled concrete was assessed through an experimental program involving 15 composite beams. Recycled concrete was obtained by replacing natural aggregates (NA) with recycled concrete aggregate (RCA) and recycled asphalt pavement (RAP) with replacement levels of 20%, 40%, 60%, 80%, and 100% by the total weight of NA. In addition, RCA and RAP were incorporated in the same mixes with replacement levels of (1) 20% RCA and 80% RAP; (2) 40% RCA and 60% RAP; (3) 60% RCA and 40% RAP; and (4) 80% RCA and 20% RAP. A comparison between the experimental capacities and the theoretically predicted values according to Eurocode 4 (EC4) was made as well. Results proved that the ultimate capacity of composite beams decreased with the increase of recycled aggregate (RA) percentage and EC4 was conservative in predicting the ultimate capacity of composite beams.

Keywords: flexure, light gauge, recycled asphalt pavement, recycled concrete aggregate, steel tube

Procedia PDF Downloads 203
3295 Preoperative Weight Management Education and Its Influence on Bariatric Surgery Patient Weights

Authors: Meghana Pandit, Abhishek Chakraborty

Abstract:

There are a multitude of factors that influence the clinical success of bariatric surgery. This study seeks to determine the efficacy of preoperative weight management education. The Food and Fitness Program at Mount Sinai serves to educate patients on topics such as stress management, sleep habits, body image, nutrition, and exercise 5-6 months before their surgeries to slowly decrease their weight. Each month, patients are weighed, and a different topic is presented. To evaluate the longitudinal effects of these lectures, patient’s weights are evaluated at the first appointment, before an informative lecture is presented. Weights are then reevaluated at the last appointment before the surgery. The weights were statistically analyzed using a paired t-test and the results demonstrated a statistically significant difference (p < .0001, n=55). Thus, it is reasonable to conclude that the education paradigm employed successfully empowered patients to maintain and reduce their gross BMI before clinical intervention.

Keywords: bariatric, surgery, weight, education

Procedia PDF Downloads 138