Search results for: outbreak prediction

Authors: Ariane Plaisance, Holly O. Witteman, Patrick Michel Archambault

Abstract:

Upon admission to an intensive care unit (ICU), all patients should discuss their wishes concerning life-sustaining interventions (e.g., cardiopulmonary resuscitation (CPR)). Without such discussions, interventions that prolong life at the cost of decreasing its quality may be used without appropriate guidance from patients. We employed user-centered design to adapt an existing decision aid (DA) about CPR to create a novel wiki-based DA adapted to the context of a single ICU and tailored to individual patient’s risk factors. During Phase 1, we conducted three weeks of ethnography of the decision-making context in our ICU to identify clinician and patient needs for a decision aid. During this time, we observed five dyads of intensivists and patients discussing their wishes concerning life-sustaining interventions. We also conducted semi-structured interviews with the attending intensivists in this ICU. During Phase 2, we conducted three rounds of rapid prototyping involving 15 patients and 11 other allied health professionals. We recorded discussions between intensivists and patients and used a standardized observation grid to collect patients’ comments and sociodemographic data. We applied content analysis to field notes, verbatim transcripts and the completed observation grids. Each round of observations and rapid prototyping iteratively informed the design of the next prototype. We also used the programming architecture of a wiki platform to embed the GO-FAR prediction rule programming code that we linked to a risk graphics software to better illustrate outcome risks calculated. During Phase I, we identified the need to add a section in our DA concerning invasive mechanical ventilation in addition to CPR because both life-sustaining interventions were often discussed together by physicians. During Phase II, we produced a context-adapted decision aid about CPR and mechanical ventilation that includes a values clarification section, questions about the patient’s functional autonomy prior to admission to the ICU and the functional decline that they would judge acceptable upon hospital discharge, risks and benefits of CPR and invasive mechanical ventilation, population-level statistics about CPR, a synthesis section to help patients come to a final decision and an online calculator based on the GO-FAR prediction rule. Even though the three rounds of rapid prototyping led to simplifying the information in our DA, 60% (n= 3/5) of the patients involved in the last cycle still did not understand the purpose of the DA. We also identified gaps in the discussion and documentation of patients’ preferences concerning life-sustaining interventions (e.g.,. CPR, invasive mechanical ventilation). The final version of our DA and our online wiki-based GO-FAR risk calculator using the IconArray.com risk graphics software are available online at www.wikidecision.org and are ready to be adapted to other contexts. Our results inform producers of decision aids on the use of wikis and user-centered design to develop DAs that are better adapted to users’ needs. Further work is needed on the creation of a video version of our DA. Physicians will also need the training to use our DA and to develop shared decision-making skills about goals of care.

Keywords: ethnography, intensive care units, life-sustaining therapies, user-centered design

Procedia PDF Downloads 337

Authors: Elison Eduardo Jardim Bierhals, Claudineia Brazil, Deivid Pires, Rafael Haag, Elton Gimenez Rossini

Abstract:

This study evaluated the uncertainties involved in the solar radiation projections generated by the Brazilian Earth System Model (BESM) of the Weather and Climate Prediction Center (CPTEC) belonging to Coupled Model Intercomparison Phase 5 (CMIP5), with the aim of identifying efficiency in the projections for solar radiation of said model and in this way establish the viability of its use. Two different scenarios elaborated by Intergovernmental Panel on Climate Change (IPCC) were evaluated: RCP 4.5 (with more optimistic contour conditions) and 8.5 (with more pessimistic initial conditions). The method used to verify the accuracy of the present model was the Nash coefficient and the Statistical bias, as it better represents these atmospheric patterns. The BESM showed a tendency to overestimate the data ​​of solar radiation projections in most regions of the state of Rio Grande do Sul and through the validation methods adopted by this study, BESM did not present a satisfactory accuracy.

Keywords: climate changes, projections, solar radiation, uncertainty

Procedia PDF Downloads 231

Authors: Ashutosh Biswas, Poonam Coushic, Kalpana Baruah, Paras Singla, A. C. Dhariwal, Pawana Murthy

Abstract:

Burden of Dengue in Northern India Ashutosh Biswas, Poonam Coushic, Kalpana Baruah, Paras Singla, AC Dhariwal, Pawana Murthy. All India Institute of Medical Sciences, NVBDCP,WHO New Delhi, India Aim: This study was conducted to estimate the burden of dengue in capital region of India. Methodology:Seropositivity of Dengue for IgM Ab, NS1 Ag and IgG Ab were performed among the blood donors’ samples from blood bank, those who were coming to donate blood for the requirement of blood for the admitted patients in hospital. Blood samplles were collected through out the year to estimate seroprevalance of dengue with or without outbreak season. All the subjects were asymptomatic at the time of blood donation. Results: A total of 1558 donors were screened for the study. On the basis of inclusion/ exclusion criteria, we enrolled 1531subjects for the study.Twenty seven donors were excluded from the study, out of which 6 were detected HIV +ve, 11 were positive for HBsAg and 10 were found positive for HCV.Mean age was 30.51 ± 7.75 years.Of 1531subjects, 18 (1.18%) had a past history of typhoid fever, 28 (1.83%) had chikungunya fever, 9 (0.59%) had malaria and 43 subjects (2.81%) had a past history of symptomatic dengue infection.About 2.22% (34) of subjects were found to have sero-positive for NS1 Ag with a peak point prevalence of 7.14% in the month of October and sero-positive of IgM Ab was observed about 5.49% (84)with a peak point prevalence of 14.29% in the month of October. Sero-prevalnce of IgGwas detected in about 64.21% (983) of subjects. Conclusion: Acute asymptomatic dengue (NS1 Ag+ve) was observed in 7.14%, as the subjects were having no symptoms at the time of sampling. This group of subjects poses a potential public health threat for transmitting dengue infection through blood transfusion (TTI) in the community as evident by presence of active viral infection due to NS1Ag +VE. Therefore a policy may be implemented in the blood bank for testing NS1 Ag to look for active dengue infection for preventing dengue transmission through blood transfusion (TTI). Acute or Subacute dengue infection ( IgM Ab+ve) was observed from 5.49% to 14.29% which is a peak point prevalence in the month of October. About 64.21% of the population were immunized by natural dengue infection ( IgG Ab+ve) in theNorthern province of India. This might be helpful for implementing the dengue vaccine in a region. Blood samples in blood banks should be tested for dengue before transfusion to any other person to prevent transfusion transmitted dengue infection as we estimated upto 7.14% positivity of NS1 Ag in our study which indicates presence of dengue virus in blood donors’ samples.

Keywords: Dengue Burden, Seroprevalance, Asymptomatic dengue, Dengue transmission through blood transfusion

Procedia PDF Downloads 129

Authors: Ali Kezmane, Said Boukais, Mohand Hamizi

Abstract:

This paper presents an analytical study on the behavior of reinforced concrete walls with rectangular cross section. Several experiments on such walls have been selected to be studied. Database from various experiments were collected and nominal shear wall strengths have been calculated using formulas, such as those of the ACI (American), NZS (New Zealand), Mexican (NTCC), and Wood and Barda equations. Subsequently, nominal shear wall strengths from the formulas were compared with the ultimate shear wall strengths from the database. These formulas vary substantially in functional form and do not account for all variables that affect the response of walls. There is substantial scatter in the predicted values of ultimate shear strength. Two new semi empirical equations are developed using data from tests of 57 walls for transitions walls and 27 for slender walls with the objective of improving the prediction of peak strength of walls with the most possible accurate.

Keywords: shear strength, reinforced concrete walls, rectangular walls, shear walls, models

Procedia PDF Downloads 325

Authors: Mladen Dragičević, Mirjana Pejić Bach, Vanja Šimičević

Abstract:

The purpose of this paper is to develop models that would enable predicting student success. These models could improve allocation of students among colleges and optimize the newly introduced model of government subsidies for higher education. For the purpose of collecting data, an anonymous survey was carried out in the last year of undergraduate degree student population using random sampling method. Decision trees were created of which two have been chosen that were most successful in predicting student success based on two criteria: Grade Point Average (GPA) and time that a student needs to finish the undergraduate program (time-to-degree). Decision trees have been shown as a good method of classification student success and they could be even more improved by increasing survey sample and developing specialized decision trees for each type of college. These types of methods have a big potential for use in decision support systems.

Keywords: data mining, knowledge discovery in databases, prediction models, student success

Procedia PDF Downloads 395

Authors: Adel Almasarwah

Abstract:

This study investigates the nature of association between profit warnings and stock price informativeness in the context of Jordan as an emerging country. The analysis is based on the response of stock price synchronicity to profit warnings percentages that have been published in Jordanian firms throughout the period spanning 2005–2016 in the Amman Stock Exchange. The standard of profit warnings indicators have related negatively to stock price synchronicity in Jordanian firms, meaning that firms with a high portion of profit warnings integrate with more firm-specific information into stock price. Robust regression was used rather than OLS as a parametric test to overcome the variances inflation factor (VIF) and heteroscedasticity issues recognised as having occurred during running the OLS regression; this enabled us to obtained stronger results that fall in line with our prediction that higher profit warning encourages firm investors to collect and process more firm-specific information than common market information.

Keywords: Profit Warnings, Jordanian Firms, Stock Price Informativeness, Synchronicity

Procedia PDF Downloads 129

Authors: Francesco Morgan Bono, Simone Cinquemani

Abstract:

This research aims to enhance bridge monitoring by employing innovative techniques that incorporate exogenous factors into the modeling of sensor signals, thereby improving long-term predictability beyond traditional static methods. Using real datasets from two different bridges equipped with Linear Variable Displacement Transducer (LVDT) sensors, the study investigates the fundamental principles governing sensor behavior for more precise long-term forecasts. Additionally, the research evaluates performance on noisy and synthetically damaged data, proposing a residual-based alarm system to detect anomalies in the bridge. In summary, this novel approach combines advanced modeling, exogenous factors, and anomaly detection to extend prediction horizons and improve preemptive damage recognition, significantly advancing structural health monitoring practices.

Keywords: structural health monitoring, dynamic models, sindy, railway bridges

Procedia PDF Downloads 17

Authors: Henry Memczak, Marc Hovestaedt, Bernhard Ay, Sandra Saenger, Thorsten Wolff, Frank F. Bier

Abstract:

The influenza viruses cause flu epidemics every year and serious pandemics in larger time intervals. The only cost-effective protection against influenza is vaccination. Due to rapid mutation continuously new subtypes appear, what requires annual reimmunization. For a correct vaccination recommendation, the circulating influenza strains had to be detected promptly and exactly and characterized due to their antigenic properties. During the flu season 2016/17, a wrong vaccination recommendation has been given because of the great time interval between identification of the relevant influenza vaccine strains and outbreak of the flu epidemic during the following winter. Due to such recurring incidents of vaccine mismatches, there is a great need to speed up the process chain from identifying the right vaccine strains to their administration. The monitoring of subtypes as part of this process chain is carried out by national reference laboratories within the WHO Global Influenza Surveillance and Response System (GISRS). To this end, thousands of viruses from patient samples (e.g., throat smears) are isolated and analyzed each year. Currently, this analysis involves complex and time-intensive (several weeks) animal experiments to produce specific hyperimmune sera in ferrets, which are necessary for the determination of the antigen profiles of circulating virus strains. These tests also bear difficulties in standardization and reproducibility, which restricts the significance of the results. To replace this test a peptide-based assay for influenza virus subtyping from corresponding virus samples was developed. The differentiation of the viruses takes place by a set of specifically designed peptidic recognition molecules which interact differently with the different influenza virus subtypes. The differentiation of influenza subtypes is performed by pattern recognition guided by machine learning algorithms, without any animal experiments. Synthetic peptides are immobilized in multiplex format on various platforms (e.g., 96-well microtiter plate, microarray). Afterwards, the viruses are incubated and analyzed comparing different signaling mechanisms and a variety of assay conditions. Differentiation of a range of influenza subtypes, including H1N1, H3N2, H5N1, as well as fine differentiation of single strains within these subtypes is possible using the peptide-based subtyping platform. Thereby, the platform could be capable of replacing the current antigenic characterization of influenza strains using ferret hyperimmune sera.

Keywords: antigenic characterization, influenza-binding peptides, influenza subtyping, influenza surveillance

Procedia PDF Downloads 135

Authors: Mitrajit Biswas

Abstract:

This paper is trying to understand the issues related to maintaining a fan base over a period of time. The paper would be trying to look into how the fan base can be actually engaged. That is what are the attributes of keeping a fan base interested and not feeling fatigued or tired. It would also try to understand that what are the key elements required for a franchise to be active and keep the fans engaged. The paper would look to understand the primary elements of a franchise like Marvel to keep the fans engaged for such a long period of time. This will help to improve the scope of literature on consumer engagement and consumption behaviour in modern times of unpredictability. It will also help to understand how the consumers take in a longer period of engagement. This would help to understand that despite huge success and investment in fan engagement and what could be the possible reasons for disengagement? This would include in-depth interviews with a global sample of around 50 people, which would be connected through purposive, convenient, and snowball sampling. It will help to understand whether the customer lifetime value as a theory can be sustained based on customer relationship management. If yes, how can products from certain companies predict and keep up the strategy for the prediction of the consumer engagement process?

Keywords: consumption, fatigue, brand loyalty, sustainable consumption

Procedia PDF Downloads 60

Authors: Bin Wang, Yong Xu, Honggang Qu, Rongmei Liu, Zhenji Gao

Abstract:

Today's mining industry is advancing gradually toward digital and visual direction. The three dimensional visualization geological modeling of mine is the digital characterization of mineral deposit, and is one of the key technology of digital mine. The three-dimensional geological modeling is a technology that combines the geological spatial information management, geological interpretation, geological spatial analysis and prediction, geostatistical analysis, entity content analysis and graphic visualization in three-dimensional environment with computer technology, and is used in geological analysis. In this paper, the three-dimensional geological modeling of an iron mine through the use of Surpac is constructed, and the weight difference of the estimation methods between distance power inverse ratio method and ordinary kriging is studied, and the ore body volume and reserves are simulated and calculated by using these two methods. Compared with the actual mine reserves, its result is relatively accurate, so it provided scientific bases for mine resource assessment, reserve calculation, mining design and so on.

Keywords: three-dimensional geological modeling, geological database, geostatistics, block model

Procedia PDF Downloads 56

Authors: Tanmay Bisen, Aastha Shayla, Susham Biswas

Abstract:

Oil spills from tankers can cause significant harm to the environment and local communities, as well as have economic consequences. Early predictions of oil spills can help to minimize these impacts. Our proposed system uses machine learning and neural networks to predict potential oil spills by monitoring data from ship Automatic Identification Systems (AIS). The model analyzes ship movements, speeds, and changes in direction to identify patterns that deviate from the norm and could indicate a potential spill. Our approach not only identifies anomalies but also predicts spills before they occur, providing early detection and mitigation measures. This can prevent or minimize damage to the reputation of the company responsible and the country where the spill takes place. The model's performance on the MV Wakashio oil spill provides insight into its ability to detect and respond to real-world oil spills, highlighting areas for improvement and further research.

Keywords: Anomaly Detection, Oil Spill Prediction, Machine Learning, Image Processing, Graph Neural Network (GNN)

Procedia PDF Downloads 54

Authors: M. S. Meon, M. N. Rao, K-U. Schröder

Abstract:

Mechanical fasteners especially bolting is commonly used in joining carbon-fiber reinforced polymer (CFRP) composite structures due to their good joinability and easy for maintenance characteristics. Since this approach involves with notching, a proper progressive damage model (PDM) need to be implemented and verified to capture existence of damages in the structure. A three dimensional (3D) failure criteria of Puck is established to predict the ultimate bearing failure of such joint. The failure criteria incorporated with degradation scheme are coded based on user subroutine executed in Abaqus. Single lap joint (SLJ) of composite bolted joint is used as target configuration. The results revealed that the PDM adopted here could sufficiently predict the behaviour of composite bolted joint up to ultimate bearing failure. In addition, mesh refinement near holes increased the accuracy of predicted strength as well as computational effort.

Keywords: bearing strength, bolted joint, degradation scheme, progressive damage model

Procedia PDF Downloads 484

Authors: Guoliang Fan, Aiping Li, Xuemei Liu, Liyun Xu

Abstract:

The performance of the tightening equipment will decline with the working process in manufacturing system. The main manifestations are the randomness and discretization degree increasing of the tightening performance. To evaluate the degradation tendency of the tightening performance accurately, a complexity measurement approach based on Kolmogorov entropy is presented. At first, the states of performance index are divided for calibrating the discrete degree. Then the complexity measurement model based on Kolmogorov entropy is built. The model describes the performance degradation tendency of tightening equipment quantitatively. At last, a study case is applied for verifying the efficiency and validity of the approach. The research achievement shows that the presented complexity measurement can effectively evaluate the degradation tendency of the tightening equipment. It can provide theoretical basis for preventive maintenance and life prediction of equipment.

Keywords: complexity measurement, Kolmogorov entropy, manufacturing system, performance evaluation, tightening equipment

Procedia PDF Downloads 249

Authors: José Eugenio Ortiz, Pierre Plaza, Josefa Herrero, Iván Cabria, José Luis Blanco, Javier Gavilanes, José Ignacio Escavy, Ignacio López-Cilla, Virginia Yagüe, César Pérez, Silvia Rodríguez, Jorge Rico, Cecilia Serrano, Jesús Bernat

Abstract:

The development of Artificial Intelligence services in mining processes, specifically in aggregate quarries, is facilitating automation and improving numerous aspects of operations. Ultimately, AI is transforming the mining industry by improving efficiency, safety and sustainability. With the ability to analyze large amounts of data and make autonomous decisions, AI offers great opportunities to optimize mining operations and maximize the economic and social benefits of this vital industry. Within the framework of the European DIGIECOQUARRY project, various services were developed for the identification of material quality, production estimation, detection of anomalies and prediction of consumption and production automatically with good results.

Keywords: aggregates, artificial intelligence, automatization, mining operations

Procedia PDF Downloads 76

Authors: S. O. Oyamakin, A. U. Chukwu

Abstract:

Richard's growth equation being a generalized logistic growth equation was improved upon by introducing an allometric parameter using the hyperbolic sine function. The integral solution to this was called hyperbolic Richard's growth model having transformed the solution from deterministic to a stochastic growth model. Its ability in model prediction was compared with the classical Richard's growth model an approach which mimicked the natural variability of heights/diameter increment with respect to age and therefore provides a more realistic height/diameter predictions using the coefficient of determination (R2), Mean Absolute Error (MAE) and Mean Square Error (MSE) results. The Kolmogorov-Smirnov test and Shapiro-Wilk test was also used to test the behavior of the error term for possible violations. The mean function of top height/Dbh over age using the two models under study predicted closely the observed values of top height/Dbh in the hyperbolic Richard's nonlinear growth models better than the classical Richard's growth model.

Keywords: height, Dbh, forest, Pinus caribaea, hyperbolic, Richard's, stochastic

Procedia PDF Downloads 460

Authors: T. S. Yang, J. H. Liang

Abstract:

This study applies the finite element method (FEM) to predict maximum forging load, effective stress distribution, effective strain distribution, workpiece temperature temperature in spiral bevel gear forging of AISI 1015. Maximum forging load, effective stress, effective strain, workpiece temperature are determined for different process parameters, such as modules, number of teeth, helical angle and workpiece temperature of the spiral bevel gear hot forging, using the FEM. Finally, the prediction of the power requirement for the spiral bevel gear hot forging of AISI 1015 is determined.

Keywords: spiral bevel gear, hot forging, finite element method

Procedia PDF Downloads 469

Authors: Jesus Ruano, Asensi Oliva

Abstract:

The hydrodynamic field generated by a jet expansion is computed via three dimensional compressible Large Eddy Simulation (LES). Finite Volume Method (FVM) will be the discretization used during this simulation as well as hybrid schemes based on Kinetic Energy Preserving (KEP) schemes and up-winding Godunov based schemes with instabilities detectors. Velocity and pressure fields will be stored at different surfaces near the jet, but far enough to enclose all the fluctuations, in order to use them as input for the acoustic solver. The acoustic field is obtained in the far-field region at several locations by means of a hybrid method based on Ffowcs-Williams and Hawkings (FWH) equation. This equation will be formulated in the spectral domain, via Fourier Transform of the acoustic sources, which are modeled from the results of the initial simulation. The obtained results will allow the study of the broadband noise generated as well as sound directivities.

Keywords: far-field noise, Ffowcs-Williams and Hawkings, finite volume method, large eddy simulation, jet noise

Procedia PDF Downloads 285

Authors: Reneiloe Seodigeng, Malwandla Hanabe, Haleden Chiririwa, Hilary Rutto, Tumisang Seodigeng

Abstract:

Neutralisation of acid-mine drainage (AMD) using limestone is cost effective, and good results can be obtained. However, this process has its limitations; it cannot be used for highly acidic water which consists of Fe(III). When Fe(III) reacts with CaCO₃, it results in armoring. Armoring slows the reaction, and additional alkalinity can no longer be generated. Limestone is easily accessible, so this problem can be easily dealt with. Experiments were carried out to evaluate the effect of PVC pipe length on ferric and ferrous ions. It was found that the shorter the pipe length the more these dissolved metals precipitate. The effect of the pipe length on the hydrogen ions was also studied, and it was found that these two have an inverse relationship. Experimental data were further compared with the model prediction data to see if they behave in a similar fashion. The model was able to predict the behaviour of 1.5m and 2 m pipes in ferric and ferrous ion precipitation.

Keywords: acid mine drainage, neutralisation, limestone, mathematical modelling

Procedia PDF Downloads 350

Authors: Rajaian Hoonejani Mohammad, Eshraghi Pegah, Zomorodian Zahra Sadat, Tahsildoost Mohammad

Abstract:

Over the past decade, energy consumption in educational buildings has steadily increased. The purpose of this research is to provide a method to quickly predict the energy consumption of buildings using separate evaluation of zones and decomposing the building to eliminate the complexity of geometry at the early design stage. To produce this framework, machine learning algorithms such as Support vector regression (SVR) and Artificial neural network (ANN) are used to predict energy consumption and thermal comfort metrics in a school as a case. The database consists of more than 55000 samples in three climates of Iran. Cross-validation evaluation and unseen data have been used for validation. In a specific label, cooling energy, it can be said the accuracy of prediction is at least 84% and 89% in SVR and ANN, respectively. The results show that the SVR performed much better than the ANN.

Keywords: early stage of design, energy, thermal comfort, validation, machine learning

Procedia PDF Downloads 47

Authors: Fadwa Jewilli

Abstract:

A sudden leak of a 6-inch gas line pipe after being in service for one year was observed. The pipe had been designed to transport dry gas. The failure had taken place in 6 o’clock position at the stage discharge of the flow process. Laboratory investigations were conducted to find out the cause of the pipe rupture. Visual and metallographic observations confirmed that the pipe split was due to a crack initiated in circumferential and then turned into longitudinal direction. Sever wall thickness reduction was noticed on the internal pipe surface. Scanning electron microscopy observations at the fracture surface revealed features of ductile fracture mode. Corrosion product analysis showed the traces of iron carbonate and iron sulphate. The laboratory analysis resulted in the conclusion that the pipe failed due to the effect of wet fluid (condensate) caused severe wall thickness dissolution resulted in pipe could not stand the continuation at in-service working condition.

Keywords: gas line pipe, corrosion prediction ductile fracture, ductile fracture, failure analysis

Procedia PDF Downloads 69

Authors: Rose Shayeghi, Pejman Hosseinioun

Abstract:

The Multiple Intelligences theory characterizes human intelligence as a multifaceted entity that exists in all human beings with varying degrees. The most important contribution of this theory to the field of English Language Teaching (ELT) is its role in identifying individual differences and designing more learner-centered programs. The present study aims at investigating the relationship between different elements of multiple intelligence and grammar scores. To this end, 63 female Iranian EFL learner selected from among intermediate students participated in the study. The instruments employed were a Nelson English language test, Michigan Grammar Test, and Teele Inventory for Multiple Intelligences (TIMI). The results of Pearson Product-Moment Correlation revealed a significant positive correlation between grammatical accuracy and linguistic as well as interpersonal intelligence. The results of Stepwise Multiple Regression indicated that linguistic intelligence contributed to the prediction of grammatical accuracy.

Keywords: multiple intelligence, grammar, ELT, EFL, TIMI

Procedia PDF Downloads 473

Authors: Nishtha Madaan, Prateek Chaudhury, Nishant Kumar, Srikanta Bedathur

Abstract:

In modern NLP applications, word embeddings are a crucial backbone that can be readily shared across a number of tasks. However, as the text distributions change and word semantics evolve over time, the downstream applications using the embeddings can suffer if the word representations do not conform to the data drift. Thus, maintaining word embeddings to be consistent with the underlying data distribution is a key problem. In this work, we tackle this problem and propose TransDrift, a transformer-based prediction model for word embeddings. Leveraging the flexibility of the transformer, our model accurately learns the dynamics of the embedding drift and predicts future embedding. In experiments, we compare with existing methods and show that our model makes significantly more accurate predictions of the word embedding than the baselines. Crucially, by applying the predicted embeddings as a backbone for downstream classification tasks, we show that our embeddings lead to superior performance compared to the previous methods.

Keywords: NLP applications, transformers, Word2vec, drift, word embeddings

Procedia PDF Downloads 71

Authors: Nikolaos Georgoulopoulos, Alkis Hatzopoulos, Konstantinos Karamitsios, Konstantinos Kotrotsios, Alexandros I. Metsai

Abstract:

In modern server systems, business critical applications run in different types of infrastructure, such as cloud systems, physical machines and virtualization. Often, due to high load and over time, various hardware faults occur in servers that translate to errors, resulting to malfunction or even server breakdown. CPU, RAM and hard drive (HDD) are the hardware parts that concern server administrators the most regarding errors. In this work, selected RAM, HDD and CPU errors, that have been observed or can be simulated in kernel ring buffer log files from two groups of Linux servers, are investigated. Moreover, a severity characterization is given for each error type. Better understanding of such errors can lead to more efficient analysis of kernel logs that are usually exploited for fault diagnosis and prediction. In addition, this work summarizes ways of simulating hardware errors in RAM and HDD, in order to test the error detection and correction mechanisms of a Linux server.

Keywords: hardware errors, Kernel logs, Linux servers, RAM, hard disk, CPU

Procedia PDF Downloads 141

Authors: Abhigyan Hedau, Priya Shelke, Riddhi Mirajkar, Shreyash Chaple, Mrunali Gadekar, Himanshu Akula

Abstract:

The heart is the coordinating centre of the major endocrine glandular structure of the body, which produces hormones that profoundly affect the operations of the body, and diagnosing cardiovascular disease is a difficult but critical task. By extracting knowledge and information about the disease from patient data, data mining is a more practical technique to help doctors detect disorders. We use a variety of machine learning methods here, including logistic regression and support vector classifiers (SVC), K-nearest neighbours Classifiers (KNN), Decision Tree Classifiers, Random Forest classifiers and Gradient Boosting classifiers. These algorithms are applied to patient data containing 13 different factors to build a system that predicts heart disease in less time with more accuracy.

Keywords: logistic regression, support vector classifier, k-nearest neighbour, decision tree, random forest and gradient boosting

Procedia PDF Downloads 32

Authors: Sachin Jain, Daniel Perez-Astudillo, Dunia A. Bachour, Antonio P. Sanfilippo

Abstract:

The future of solar energy in Qatar is evolving steadily. Hence, high-quality spatial solar radiation data is of the uttermost requirement for any planning and commissioning of solar technology. Generally, two types of solar radiation data are available: satellite data and ground observations. Satellite solar radiation data is developed by the physical and statistical model. Ground data is collected by solar radiation measurement stations. The ground data is of high quality. However, they are limited to distributed point locations with the high cost of installation and maintenance for the ground stations. On the other hand, satellite solar radiation data is continuous and available throughout geographical locations, but they are relatively less accurate than ground data. To utilize the advantage of both data, a product has been developed here which provides spatial continuity and higher accuracy than any of the data alone. The popular satellite databases: National Solar radiation Data Base, NSRDB (PSM V3 model, spatial resolution: 4 km) is chosen here for merging with ground-measured solar radiation measurement in Qatar. The spatial distribution of ground solar radiation measurement stations is comprehensive in Qatar, with a network of 13 ground stations. The monthly average of the daily total Global Horizontal Irradiation (GHI) component from ground and satellite data is used for error analysis. The normalized root means square error (NRMSE) values of 3.31%, 6.53%, and 6.63% for October, November, and December 2019 were observed respectively when comparing in-situ and NSRDB data. The method is based on the Empirical Bayesian Kriging Regression Prediction model available in ArcGIS, ESRI. The workflow of the algorithm is based on the combination of regression and kriging methods. A regression model (OLS, ordinary least square) is fitted between the ground and NSBRD data points. A semi-variogram is fitted into the experimental semi-variogram obtained from the residuals. The kriging residuals obtained after fitting the semi-variogram model were added to NSRBD data predicted values obtained from the regression model to obtain the final predicted values. The NRMSE values obtained after merging are respectively 1.84%, 1.28%, and 1.81% for October, November, and December 2019. One more explanatory variable, that is the ground elevation, has been incorporated in the regression and kriging methods to reduce the error and to provide higher spatial resolution (30 m). The final GHI maps have been created after merging, and NRMSE values of 1.24%, 1.28%, and 1.28% have been observed for October, November, and December 2019, respectively. The proposed merging method has proven as a highly accurate method. An additional method is also proposed here to generate calibrated maps by using regression and kriging model and further to use the calibrated model to generate solar radiation maps from the explanatory variable only when not enough historical ground data is available for long-term analysis. The NRMSE values obtained after the comparison of the calibrated maps with ground data are 5.60% and 5.31% for November and December 2019 month respectively.

Keywords: global horizontal irradiation, GIS, empirical bayesian kriging regression prediction, NSRDB

Procedia PDF Downloads 76

Authors: Chia-Feng Lu, Yuh-Jen Wang, Yu-Te Wu, Sui-Hing Yan

Abstract:

This study aimed at investigating whether the functional brain networks constructed using the initial EEG (obtained when patients first visited hospital) can be correlated with the progression of cognitive decline calculated as the changes of mini-mental state examination (MMSE) scores between the latest and initial examinations. We integrated the time–frequency cross mutual information (TFCMI) method to estimate the EEG functional connectivity between cortical regions, and the network analysis based on graph theory to investigate the organization of functional networks in aMCI. Our finding suggested that higher integrated functional network with sufficient connection strengths, dense connection between local regions, and high network efficiency in processing information at the initial stage may result in a better prognosis of the subsequent cognitive functions for aMCI. In conclusion, the functional connectivity can be a useful biomarker to assist in prediction of cognitive declines in aMCI.

Keywords: cognitive decline, functional connectivity, MCI, MMSE

Procedia PDF Downloads 367

Authors: Abdulrahman Alenezi, B. Stefan

Abstract:

Abstract— The investigation of fluids containing particles or filaments includes a category of complex fluids and is vital in both theory and application. The forecast of particle behaviors plays a significant role in the existing technology as well as future technology. This paper focuses on the prediction of the particle behavior through the investigation of the particle disentrainment from a pipe on a horizontal air stream. This allows for examining the influence of the particle physical properties on its behavior when falling on horizontal air stream. This investigation was conducted on a device located at the University of Greenwich's Medway Campus. Two materials were selected to carry out this study: Salt and Glass Beads particles. The shape of the Slat particles is cubic where the shape of the Glass Beads is almost spherical. The outcome from the experimental work were presented in terms of distance travelled by the particles according to their diameters as After that, the particles sizes were measured using Laser Diffraction device and used to determine the drag coefficient and the settling velocity.

Keywords: flow experiment, drag coefficient, Particle Settling, Flow Chamber

Procedia PDF Downloads 120

Authors: David X. Dong, Qingming Zhang, Meng Lu

Abstract:

Nitrites enter waterways as runoff from croplands and are discharged from many industrial sites. Excessive nitrite inputs to water bodies lead to eutrophication. On-site rapid detection of nitrite is of increasing interest for managing fertilizer application and monitoring water source quality. Existing methods for detecting nitrites use spectrophotometry, ion chromatography, electrochemical sensors, ion-selective electrodes, chemiluminescence, and colorimetric methods. However, these methods either suffer from high cost or provide low measurement accuracy due to their poor selectivity to nitrites. Therefore, it is desired to develop an accurate and economical method to monitor nitrites in environments. We report a low-cost optical sensor, in conjunction with a machine learning (ML) approach to enable high-accuracy detection of nitrites in water sources. The sensor works under the principle of measuring molecular absorptions of nitrites at three narrowband wavelengths (295 nm, 310 nm, and 357 nm) in the ultraviolet (UV) region. These wavelengths are chosen because they have relatively high sensitivity to nitrites; low-cost light-emitting devices (LEDs) and photodetectors are also available at these wavelengths. A regression model is built, trained, and utilized to minimize cross-sensitivities of these wavelengths to the same analyte, thus achieving precise and reliable measurements with various interference ions. The measured absorbance data is input to the trained model that can provide nitrite concentration prediction for the sample. The sensor is built with i) a miniature quartz cuvette as the test cell that contains a liquid sample under test, ii) three low-cost UV LEDs placed on one side of the cell as light sources, with each LED providing a narrowband light, and iii) a photodetector with a built-in amplifier and an analog-to-digital converter placed on the other side of the test cell to measure the power of transmitted light. This simple optical design allows measuring the absorbance data of the sample at the three wavelengths. To train the regression model, absorbances of nitrite ions and their combination with various interference ions are first obtained at the three UV wavelengths using a conventional spectrophotometer. Then, the spectrophotometric data are inputs to different regression algorithm models for training and evaluating high-accuracy nitrite concentration prediction. Our experimental results show that the proposed approach enables instantaneous nitrite detection within several seconds. The sensor hardware costs about one hundred dollars, which is much cheaper than a commercial spectrophotometer. The ML algorithm helps to reduce the average relative errors to below 3.5% over a concentration range from 0.1 ppm to 100 ppm of nitrites. The sensor has been validated to measure nitrites at three sites in Ames, Iowa, USA. This work demonstrates an economical and effective approach to the rapid, reagent-free determination of nitrites with high accuracy. The integration of the low-cost optical sensor and ML data processing can find a wide range of applications in environmental monitoring and management.

Keywords: optical sensor, regression model, nitrites, water quality

Procedia PDF Downloads 60

Authors: Aritras Roy, Rinku Mukherjee

Abstract:

The current study couples a quasi-steady Vortex Lattice Method and a camber correcting technique, ‘Decambering’ for unsteady post-stall flow prediction. The wake is force-free and discrete such that the wake lattices move with the free-stream once shed from the wing. It is observed that the time-averaged unsteady coefficient of lift sees a relative drop at post-stall angles of attack in comparison to its steady counterpart for some angles of attack. Multiple solutions occur at post-stall and three different algorithms to choose solutions in these regimes show both unsteadiness and non-convergence of the iterations. The distribution of coefficient of lift on the wing span also shows sawtooth. Distribution of vorticity changes both along span and in the direction of the free-stream as the wake develops over time with distinct roll-up, which increases with time.

Keywords: post-stall, unsteady, wing, aerodynamics

Procedia PDF Downloads 354

Authors: Ashish Kumar, Kaptan Singh, Amit Saxena

Abstract:

Today, it is believed that crimes have the greatest impact on a person's ability to progress financially and personally. Identifying places where individuals shouldn't go is crucial for preventing crimes and is one of the key considerations. As society and technologies have advanced significantly, so have crimes and the harm they wreak. When there is a concentration of people in one place and changes happen quickly, it is even harder to prevent. Because of this, many crime prevention strategies have been embraced as a component of the development of smart cities in numerous cities. However, crimes can occur anywhere; all that is required is to identify the pattern of their occurrences, which will help to lower the crime rate. In this paper, an analysis related to crime has been done; information related to crimes is collected from all over India that can be accessed from anywhere. The purpose of this paper is to investigate the relationship between several factors and India's crime rate. The review has covered information related to every state of India and their associated regions of the period going in between 2001- 2014. However various classes of violations have a marginally unique scope over the years.

Keywords: K-nearest neighbor, random forest, decision tree, pre-processing

Procedia PDF Downloads 72