Search results for: prediction interval

Authors: Grienggrai Rajchakit

Abstract:

This paper is concerned with the exponential stability of switched linear systems with interval time-varying delays. The time delay is any continuous function belonging to a given interval, in which the lower bound of delay is not restricted to zero. By constructing a suitable augmented Lyapunov-Krasovskii functional combined with Leibniz-Newton's formula, a switching rule for the exponential stability of switched linear systems with interval time-varying delays and new delay-dependent sufficient conditions for the exponential stability of the systems are first established in terms of LMIs. Finally, some examples are exploited to illustrate the effectiveness of the proposed schemes.

Keywords: exponential stability, hybrid systems, time-varying delays, lyapunov-krasovskii functional, leibniz-newton's formula

Procedia PDF Downloads 522

Authors: Mohammad Ghavami, Reza S. Dilmaghani

Abstract:

This paper presents an adaptive framework for modelling financial markets using equity risk premiums, risk free rates and volatilities. The recorded economic factors are initially used to train four adaptive filters for a certain limited period of time in the past. Once the systems are trained, the adjusted coefficients are used for modelling and prediction of an important financial market index. Two different approaches based on least mean squares (LMS) and recursive least squares (RLS) algorithms are investigated. Performance analysis of each method in terms of the mean squared error (MSE) is presented and the results are discussed. Computer simulations carried out using recorded data show MSEs of 4% and 3.4% for the next month prediction using LMS and RLS adaptive algorithms, respectively. In terms of twelve months prediction, RLS method shows a better tendency estimation compared to the LMS algorithm.

Keywords: adaptive methods, LSE, MSE, prediction of financial Markets

Procedia PDF Downloads 303

Authors: Arunee Wongkhao, Suparat Niwitpong, Sa-aat Niwitpong

Abstract:

In this paper, we propose two new confidence intervals for the difference between the inverse of normal means with known coefficients of variation. One of these two confidence intervals for this problem is constructed based on the generalized confidence interval and the other confidence interval is constructed based on the closed form method of variance estimation. We examine the performance of these confidence intervals in terms of coverage probabilities and expected lengths via Monte Carlo simulation.

Keywords: coverage probability, expected length, inverse of normal mean, coefficient of variation, generalized confidence interval, closed form method of variance estimation

Procedia PDF Downloads 278

Authors: Seyoung Kim, Jeongmin Kim, Kwang Ryel Ryu

Abstract:

A database that records average traffic speeds measured at five-minute intervals for all the links in the traffic network of a metropolitan city. While learning from this data the models that can predict future traffic speed would be beneficial for the applications such as the car navigation system, building predictive models for every link becomes a nontrivial job if the number of links in a given network is huge. An advantage of adopting k-nearest neighbor (k-NN) as predictive models is that it does not require any explicit model building. Instead, k-NN takes a long time to make a prediction because it needs to search for the k-nearest neighbors in the database at prediction time. In this paper, we investigate how much we can speed up k-NN in making traffic speed predictions by reducing the amount of data to be searched for without a significant sacrifice of prediction accuracy. The rationale behind this is that we had a better look at only the recent data because the traffic patterns not only repeat daily or weekly but also change over time. In our experiments, we build several different k-NN models employing different sets of features which are the current and past traffic speeds of the target link and the neighbor links in its up/down-stream. The performances of these models are compared by measuring the average prediction accuracy and the average time taken to make a prediction using various amounts of data.

Keywords: big data, k-NN, machine learning, traffic speed prediction

Procedia PDF Downloads 331

Authors: Jiun Jeon, Byung-Ju Yi

Abstract:

This paper investigates modeling and shape prediction of elastic kinematic chains such as colonoscopy. 2D and 3D models of elastic kinematic chains are suggested and their behaviors are demonstrated through simulation. To corroborate the effectiveness of those models, experimental work is performed using a magnetic sensor system.

Keywords: elastic kinematic chain, shape prediction, colonoscopy, modeling

Procedia PDF Downloads 566

Authors: Noor F. Ilias, Mazlifah Omar, Hashbullah Ismail

Abstract:

Exercise training has been shown to improve functional capacity and is recommended as a therapy for management of blood pressure. Our purpose was to establish whether different exercise capacity produces different effect size for Cardiorespiratory Fitness (CRF), systolic (SBP) and diastolic (DBP) blood pressure in patients with hypertension. Exercise characteristic is required in order to have optimal benefit from the training, but optimal exercise capacity is still unwarranted. A MEDLINE search (1985 to 2015) was conducted for exercise based rehabilitation trials in hypertensive patients. Thirty-seven studies met the selection criteria. Of these, 31 (83.7%) were aerobic exercise and 6 (16.3%) aerobic with additional resistance exercise, providing a total of 1318 exercise subjects and 819 control, the total of subjects was 2137. We calculated exercise volume and energy expenditure through the description of exercise characteristics. 4 studies (18.2%) were 451kcal - 900 kcal, 12 (54.5%) were 900 kcal – 1350 kcal and 6 (27.3%) >1351kcal per week. Peak oxygen consumption (peak VO2) increased by mean difference of 1.44 ml/kg/min (95% confidence interval [CI]: 1.08 to 1.79 ml/kg/min; p = 0.00001) with weighted mean 21.2% for aerobic exercise compare to aerobic with additional resistance exercise 4.50 ml/kg/min (95% confidence interval [CI]: 3.57 to 5.42 ml/kg/min; p = 0.00001) with weighted mean 14.5%. SBP was clinically reduce for both aerobic and aerobic with resistance training by mean difference of -4.66 mmHg (95% confidence interval [CI]: -5.68 to -3.63 mmHg; p = 0.00001) weighted mean 6% reduction and -5.06 mmHg (95% confidence interval [CI]: -7.32 to -2.8 mmHg; p = 0.0001) weighted mean 5% reduction respectively. Result for DBP was clinically reduce for aerobic by mean difference of -1.62 mmHg (95% confidence interval [CI]: -2.09 to -1.15 mmHg; p = 0.00001) weighted mean 4% reduction and aerobic with resistance training reduce by mean difference of -3.26 mmHg (95% confidence interval [CI]: -4.87 to -1.65 mmHg; p = 0.0001) weighted mean 6% reduction. Optimum exercise capacity for 451 kcal – 900 kcal showed greater improvement in peak VO2 and SBP by 2.76 ml/kg/min (95% confidence interval [CI]: 1.47 to 4.05 ml/kg/min; p = 0.0001) with weighted mean 40.6% and -16.66 mmHg (95% confidence interval [CI]: -21.72 to -11.60 mmHg; p = 0.00001) weighted mean 9.8% respectively. Our data demonstrated that aerobic exercise with total volume of 451 kcal – 900 kcal/ week energy expenditure may elicit greater changes in cardiorespiratory fitness and blood pressure in hypertensive patients. Higher exercise capacity weekly does not seem better result in management hypertensive patients.

Keywords: blood Pressure, exercise, hypertension, peak VO2

Procedia PDF Downloads 257

Authors: Aya Gamal Khattab

Abstract:

Chronic infection with the hepatitis C virus (HCV) is now the leading cause of liver-related morbidity and mortality; Currently, alanine aminotransferase ALT measurement is not only widely used in detecting the incidence, development, and prognosis of liver disease with obvious clinical symptoms, but also provides reference on screening the overall health status during health check-ups. Exercise is a low-cost, reliable and sustainable therapy for many chronic diseases. Low-volume high intensity interval training HIT is time efficient while also having wider application to different populations including people at risk for chronic inflammatory diseases. Purpose of this study was to investigate the effect of low volume high intensity interval training on ALT, AST in HCV patients. All practical work was done in outpatient physiotherapy clinic of Suez Canal Authority Hospitals. Forty patients both gender (27 male, 13 female), age ranged (40-60) years old submitted to low volume high intensity interval training on treadmill for two months three sessions per week. Each session consisting of five min warming up, two bouts for 10 min each bout consisting of 30 sec - 1 min of high intensity (75%-85%) HRmax then two to four min active recovery at intensity (40%-60%) HRmax, so the sum of high intensity intervals was one to two min for each session and four to eight min active recovery, and ends with five min cooling down. ALT and AST were measured before starting exercise session and 2 months later after finishing the total exercise sessions through blood samples. Results showed significant decrease in ALT, AST with improvement percentage (18.85%), (23.87%) in the study, so the study concluded that low volume high intensity interval training had a significant effect in lowering the level of circulating liver enzymes (ALT, AST) which means protection of hepatic cells and restoration of its function.

Keywords: alanine aminotransferase (ALT), aspartate aminotransferase (AST), hepatitis C (HCV), low volume high intensity interval training

Procedia PDF Downloads 275

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

Abstract:

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

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

Procedia PDF Downloads 278

Authors: Mohamed M. A. Rahoma

Abstract:

This paper presents the results of my sedimentological and petrographical study of the Nubian Formation in the north Gialo area in the Sirte basin in Libya that was used for identifying and recognizing the facies type and their changes through the studied interval. It also helped me to interpret the depositional processes and the depositional environments and describe the textural characteristics, detrital mineralogy, Authigenic mineralogy and porosity characteristics of the rocks within the cored interval. Thus, we can identify the principal controls on porosity and permeability within the reservoir sections for the studied interval. To achieve this study, I described the cores studied well and marked all features represented in color, grain size, lithology, and sedimentary structures and used them to identify the facies. Then, I chose a number of samples according to a noticeable change in the facies through the interval for microscopic investigation. The results of the microscopic investigation showed that the authigenic clays and the authigenic types of cement have an important influence on the reservoir quality by converting intergranular macropores to microporosity and reducing permeability. It is recommended to give these authigenic minerals more investigation in future studies since they have an essential influence on the potential of sandstones reservoirs.

Keywords: diagenesis processes, authigenic minerals, Nubian Sandstone, reservoir quality

Procedia PDF Downloads 104

Authors: A. K. M. Kamrul Islam, Abdelhamid Bouchachia, Suang Cang, Hongnian Yu

Abstract:

Forecasting model has a great impact in terms of prediction and continues to do so into the future. Although many forecasting models have been studied in recent years, most researchers focus on different forecasting methods based on fuzzy time series to solve forecasting problems. The forecasted models accuracy fully depends on the two terms that are the length of the interval in the universe of discourse and the content of the forecast rules. Moreover, a hybrid forecasting method can be an effective and efficient way to improve forecasts rather than an individual forecasting model. There are different hybrids forecasting models which combined fuzzy time series with evolutionary algorithms, but the performances are not quite satisfactory. In this paper, we proposed a hybrid forecasting model which deals with the first order as well as high order fuzzy time series and particle swarm optimization to improve the forecasted accuracy. The proposed method used the historical enrollments of the University of Alabama as dataset in the forecasting process. Firstly, we considered an automatic clustering algorithm to calculate the appropriate interval for the historical enrollments. Then particle swarm optimization and fuzzy time series are combined that shows better forecasting accuracy than other existing forecasting models.

Keywords: fuzzy time series (fts), particle swarm optimization, clustering algorithm, hybrid forecasting model

Procedia PDF Downloads 220

Authors: Sujay Bisht

Abstract:

The purpose of the study was to evaluate and find out the effect of Hill interval training on VO₂ MAX among field Hockey players. Thirty male field hockey players were selected from LNIPE, Guwahati who were studied in B.P.Ed course. The selected subjects were aged between 18 to 23 years. The VO₂ MAX was calculated and they were divided into two group. One group (N=15) considered as control group that did not participated in any special training apart from regular scheduled/curriculum and another group (N=15) considered as an experimental group which underwent four week Hill Training program. The selected criterion variable such VO₂ Max was measured by the cooper 12min/run/walk test and scores was recorded in ml/kg/min. The subjects were tested on selected criterion variable such as VO₂ Max prior and immediately after the training program. The pretest and posttest data were evaluate by the Analysis of Covariance (ANCOVA) to find out the significance difference if any between the experimental and control group on selected criterion variable. The level of significance was set at 0.05 level of confidence. After applied ANCOVA it was revealed that there was a significant different among the experimental and control group on VO₂ Max. Finally it was concluded that 4 week of Hill interval training effect the VO₂ max performance of field hockey players.

Keywords: VO₂ max, hill interval training, ANCOVA, experimental group

Procedia PDF Downloads 189

Authors: Muhammad Yusuf, Abdul Latief Toleng, Djoni Prawira Rahardja, Ambo Ako, Sahiruddin Sahiruddin, Abdi Eriansyah

Abstract:

The objective of this study was to know the reproductive performance of dairy cows at different parities. A total of 60 dairy Holstein-Friesian cows with parity one to three from five small farms raised by the farmers were used in the study. All cows were confined in tie stall barn with rubber on the concrete floor. The herds were visited twice for survey with the help of a questionnaire. Reproductive parameters used in the study were days open, calving interval, and service per conception (S/C). The results of this study showed that the mean (±SD) days open of the cows in parity 2 was slightly longer than those in parity 3 (228.2±121.5 vs. 205.5±144.5; P=0.061). None cows conceived within 85 days postpartum in parity 3 in comparison to 13.8% cows conceived in parity 2. However, total cows conceived within 150 days post partum in parity 2 and parity 3 were 30.1% and 36.4%, respectively. Likewise, after reaching 210 days after calving, number of cows conceived in parity 3 had higher than number of cows in parity 2 (72.8% vs. 44.8%; P<0.05). The mean (±SD) calving interval of the cows in parity 2 and parity 3 were 508.2±121.5 and 495.5±144.1, respectively. Number of cows with calving interval of 400 and 450 days in parity 3 was higher than those cows in parity 2 (23.1% vs. 17.2% and 53.9% vs. 31.0%). Cows in parity 1 had significantly (P<0.01) lower number of S/C in comparison to the cows with parity 2 and parity 3 (1.6±1.2 vs. 3.5±3.4 and 3.3±2.1). It can be concluded that reproductive performance of the cows is affected by different parities.

Keywords: dairy cows, parity, days open, calving interval, service per conception

Procedia PDF Downloads 228

Authors: Michael B. C. Khoo, J. L. Khoo, W. C. Yeong, W. L. Teoh

Abstract:

The Shewhart Xbar control chart is a useful process monitoring tool in manufacturing industries to detect the presence of assignable causes. However, it is insensitive in detecting small process shifts. To circumvent this problem, adaptive control charts are suggested. An adaptive chart enables at least one of the chart’s parameters to be adjusted to increase the chart’s sensitivity. Two common adaptive charts that exist in the literature are the double sampling (DS) Xbar and variable sampling interval (VSI) Xbar charts. This paper compares the performances of the DS and VSI Xbar charts, based on the average time to signal (ATS) criterion. The ATS profiles of the DS Xbar and VSI Xbar charts are obtained using the Mathematica and Statistical Analysis System (SAS) programs, respectively. The results show that the VSI Xbar chart is generally superior to the DS Xbar chart.

Keywords: adaptive charts, average time to signal, double sampling, charts, variable sampling interval

Procedia PDF Downloads 259

Authors: Dimitrios Triantakonstantis, Demetris Stathakis

Abstract:

Urban areas have been expanded throughout the globe. Monitoring and modeling urban growth have become a necessity for a sustainable urban planning and decision making. Urban prediction models are important tools for analyzing the causes and consequences of urban land use dynamics. The objective of this research paper is to analyze and model the urban change, which has been occurred from 1990 to 2000 using CORINE land cover maps. The model was developed using drivers of urban changes (such as road distance, slope, etc.) under an Artificial Neural Network modeling approach. Validation was achieved using a prediction map for 2006 which was compared with a real map of Urban Atlas of 2006. The accuracy produced a Kappa index of agreement of 0,639 and a value of Cramer's V of 0,648. These encouraging results indicate the importance of the developed urban growth prediction model which using a set of available common biophysical drivers could serve as a management tool for the assessment of urban change.

Keywords: artificial neural networks, CORINE, urban atlas, urban growth prediction

Procedia PDF Downloads 499

Authors: P. S. Jagadeesh Kumar, S. Meenakshi Sundaram, Wenli Hu, Yang Yung

Abstract:

In 3D video games, the dominance of production is unceasingly growing with a protruding level of affordability in terms of budget. Afterward, the automation of speech-lip synchronization technique is customarily onerous and has advanced a critical research subject in virtual reality based 3D video games. This paper presents one of these automatic tools, precisely riveted on the synchronization of the speech and the lip movement of the game characters. A robust and precise speech recognition segment that systematized with Algebraic Code Excited Linear Prediction method is developed which unconventionally delivers lip sync results. The Algebraic Code Excited Linear Prediction algorithm is constructed on that used in code-excited linear prediction, but Algebraic Code Excited Linear Prediction codebooks have an explicit algebraic structure levied upon them. This affords a quicker substitute to the software enactments of lip sync algorithms and thus advances the superiority of service factors abridged production cost.

Keywords: algebraic code excited linear prediction, speech-lip synchronization, video games, virtual reality

Procedia PDF Downloads 442

Authors: Pradeep Singh, Shrish Verma

Abstract:

Software fault prediction models are created by using the source code, processed metrics from the same or previous version of code and related fault data. Some company do not store and keep track of all artifacts which are required for software fault prediction. To construct fault prediction model for such company, the training data from the other projects can be one potential solution. The earlier we predict the fault the less cost it requires to correct. The training data consists of metrics data and related fault data at function/module level. This paper investigates fault predictions at early stage using the cross-project data focusing on the design metrics. In this study, empirical analysis is carried out to validate design metrics for cross project fault prediction. The machine learning techniques used for evaluation is Naïve Bayes. The design phase metrics of other projects can be used as initial guideline for the projects where no previous fault data is available. We analyze seven data sets from NASA Metrics Data Program which offer design as well as code metrics. Overall, the results of cross project is comparable to the within company data learning.

Keywords: software metrics, fault prediction, cross project, within project.

Procedia PDF Downloads 311

Authors: Chih-Jer Lin, Chun-Ying Lee, Ying Liu, Chiang-Ho Cheng

Abstract:

The main objective of this article is to present the semi-active vibration control using an electro-rheological fluid embedded sandwich structure for a cantilever beam. ER fluid is a smart material, which cause the suspended particles polarize and connect each other to form chain. The stiffness and damping coefficients of the ER fluid can be changed in 10 micro seconds; therefore, ERF is suitable to become the material embedded in the tunable vibration absorber to become a smart absorber. For the ERF smart material embedded structure, the fuzzy control law depends on the experimental expert database and the proposed self-tuning strategy. The electric field is controlled by a CRIO embedded system to implement the real application. This study investigates the different performances using the Type-1 fuzzy and interval Type-2 fuzzy controllers. The Interval type-2 fuzzy control is used to improve the modeling uncertainties for this ERF embedded shock absorber. The self-tuning vibration controllers using Type-1 and Interval Type-2 fuzzy law are implemented to the shock absorber system. Based on the resulting performance, Internal Type-2 fuzzy is better than the traditional Type-1 fuzzy control for this vibration control system.

Keywords: electro-rheological fluid, semi-active vibration control, shock absorber, type 2 fuzzy control

Procedia PDF Downloads 413

Authors: Haozhe Xiang

Abstract:

With the rise of the Internet of Things era, intelligent products are gradually integrating into people's lives. Pedestrian trajectory prediction has become a key issue, which is crucial for the motion path planning of intelligent agents such as autonomous vehicles, robots, and drones. In the current technological context, deep learning technology is becoming increasingly sophisticated and gradually replacing traditional models. The pedestrian trajectory prediction algorithm combining neural networks and attention mechanisms has significantly improved prediction accuracy. Based on in-depth research on deep learning and pedestrian trajectory prediction algorithms, this article focuses on physical environment modeling and learning of historical trajectory time dependence. At the same time, social interaction between pedestrians and scene interaction between pedestrians and the environment were handled. An improved pedestrian trajectory prediction algorithm is proposed by analyzing the existing model architecture. With the help of these improvements, acceptable predicted trajectories were successfully obtained. Experiments on public datasets have demonstrated the algorithm's effectiveness and achieved acceptable results.

Keywords: deep learning, graph convolutional network, attention mechanism, LSTM

Procedia PDF Downloads 30

Authors: Dalin Si, Azizan Aziz, Bertrand Lasternas

Abstract:

To encourage building owners to purchase electricity at the wholesale market and reduce building peak demand, this study aims to develop models that predict day-ahead hourly electricity consumption and demand using artificial neural network (ANN) and support vector machine (SVM). All prediction models are built in Python, with tool Scikit-learn and Pybrain. The input data for both consumption and demand prediction are time stamp, outdoor dry bulb temperature, relative humidity, air handling unit (AHU), supply air temperature and solar radiation. Solar radiation, which is unavailable a day-ahead, is predicted at first, and then this estimation is used as an input to predict consumption and demand. Models to predict consumption and demand are trained in both SVM and ANN, and depend on cooling or heating, weekdays or weekends. The results show that ANN is the better option for both consumption and demand prediction. It can achieve 15.50% to 20.03% coefficient of variance of root mean square error (CVRMSE) for consumption prediction and 22.89% to 32.42% CVRMSE for demand prediction, respectively. To conclude, the presented models have potential to help building owners to purchase electricity at the wholesale market, but they are not robust when used in demand response control.

Keywords: building energy prediction, data mining, demand response, electricity market

Procedia PDF Downloads 290

Authors: Yong-Il Lee, Do-Yeon Hwang, Won-Seog Jeong, Duckshin Park

Abstract:

Recently, because of the high-speed trains forced ventilation, it is important to control the ventilation. The ventilation is for controlling various contaminants, temperature, and humidity. The high-speed train route is straight to a destination having a high speed. And there are many mountainous areas in Korea. So, tunnel rate is higher then other country. KTX HVAC block off the outdoor air, when entering tunnel. So the high tunnel rate is an effect of ventilation in the KTX cabin. It is important to reduction rate in CO2 concentration prediction. To meet the air quality of the public transport vehicles recommend standards, the KTX cabin of CO2 concentration should be managed. In this study, the concentration change was predicted by CO2 prediction simulation in route to be opened.

Keywords: CO2 prediction, KTX, ventilation, infrastructure and transportation engineering

Procedia PDF Downloads 511

Authors: Katawut Kaewbanjong

Abstract:

We analyzed a volume of data and found significant user satisfaction in software project factors. A statistical significance analysis (logistic regression) and collinearity analysis determined the significance factors from a group of 71 pre-defined factors from 191 software projects in ISBSG Release 12. The eight prediction models used for testing the prediction potential of these factors were Neural network, k-NN, Naïve Bayes, Random forest, Decision tree, Gradient boosted tree, linear regression and logistic regression prediction model. Fifteen pre-defined factors were truly significant in predicting user satisfaction, and they provided 82.71% prediction accuracy when used with a neural network prediction model. These factors were client-server, personnel changes, total defects delivered, project inactive time, industry sector, application type, development type, how methodology was acquired, development techniques, decision making process, intended market, size estimate approach, size estimate method, cost recording method, and effort estimate method. These findings may benefit software development managers considerably.

Keywords: prediction model, statistical analysis, software project, user satisfaction factor

Procedia PDF Downloads 90

Authors: K. Petcharaporn, S. Kumchoo

Abstract:

The acidity (citric acid) is one of the chemical contents that can refer to the internal quality and the maturity index of tomato. The titratable acidity (%TA) can be predicted by a non-destructive method prediction by using the transmittance short wavelength (SW-NIR). Spectroscopy in the wavelength range between 665-955 nm. The set of 167 tomato samples divided into groups of 117 tomatoes sample for training set and 50 tomatoes sample for test set were used to establish the calibration model to predict and measure %TA by partial least squares regression (PLSR) technique. The spectra were pretreated with MSC pretreatment and it gave the optimal result for calibration model as (R = 0.92, RMSEC = 0.03%) and this model obtained high accuracy result to use for %TA prediction in test set as (R = 0.81, RMSEP = 0.05%). From the result of prediction in test set shown that the transmittance SW-NIR spectroscopy technique can be used for a non-destructive method for %TA prediction of tomatoes.

Keywords: tomato, quality, prediction, transmittance, titratable acidity, citric acid

Procedia PDF Downloads 241

Authors: Venkat S. Somayajula

Abstract:

Ground surface temperature history prediction model plays a vital role in determining standards for international nuclear waste management. International standards for borehole based nuclear waste disposal require paleoclimate cycle predictions on scale of a million forward years for the place of waste disposal. This research focuses on developing a paleoclimate cycle prediction model using Bayesian long-short term memory (LSTM) neural architecture operated on accumulated borehole temperature history data. Bayesian models have been previously used for paleoclimate cycle prediction based on Monte-Carlo weight method, but due to limitations pertaining model coupling with certain other prediction networks, Bayesian models in past couldn’t accommodate prediction cycle’s over 1000 years. LSTM has provided frontier to couple developed models with other prediction networks with ease. Paleoclimate cycle developed using this process will be trained on existing borehole data and then will be coupled to surface temperature history prediction networks which give endpoints for backpropagation of LSTM network and optimize the cycle of prediction for larger prediction time scales. Trained LSTM will be tested on past data for validation and then propagated for forward prediction of temperatures at borehole locations. This research will be beneficial for study pertaining to nuclear waste management, anthropological cycle predictions and geophysical features

Keywords: Bayesian long-short term memory neural network, borehole temperature, ground surface temperature history, paleoclimate cycle

Procedia PDF Downloads 101

Authors: Soha A. Bahanshal, Byung G. Kim

Abstract:

Identification of patients at high risk for hospital readmission is of crucial importance for quality health care and cost reduction. Predicting hospital readmissions among diabetic patients has been of great interest to many researchers and health decision makers. We build a prediction model to predict hospital readmission for diabetic patients within 30 days of discharge. The core of the prediction model is a modified k Nearest Neighbor called Hybrid Fuzzy Weighted k Nearest Neighbor algorithm. The prediction is performed on a patient dataset which consists of more than 70,000 patients with 50 attributes. We applied data preprocessing using different techniques in order to handle data imbalance and to fuzzify the data to suit the prediction algorithm. The model so far achieved classification accuracy of 80% compared to other models that only use k Nearest Neighbor.

Keywords: machine learning, prediction, classification, hybrid fuzzy weighted k-nearest neighbor, diabetic hospital readmission

Procedia PDF Downloads 156

Authors: Stepan Kuchar, Martin Golasowski, Radim Vavrik, Michal Podhoranyi, Boris Sir, Jan Martinovic

Abstract:

The main goal of this article is to describe the online flood monitoring and prediction system Floreon+ primarily developed for the Moravian-Silesian region in the Czech Republic and the basic process it uses for running automatic rainfall-runoff and hydrodynamic simulations along with their calibration and uncertainty modeling. It takes a long time to execute such process sequentially, which is not acceptable in the online scenario, so the use of high-performance computing environment is proposed for all parts of the process to shorten their duration. Finally, a case study on the Ostravice river catchment is presented that shows actual durations and their gain from the parallel implementation.

Keywords: flood prediction process, high performance computing, online flood prediction system, parallelization

Procedia PDF Downloads 464

Authors: Suriya

Abstract:

Rapid socio-economic development and urbanization have led to an increasingly serious air pollution problem in Ulaanbaatar (UB), the capital of Mongolia. PM₂.₅ pollution has become the most pressing aspect of UB air pollution. Therefore, monitoring and predicting PM₂.₅ concentration in UB is of great significance for the health of the local people and environmental management. As of yet, very few studies have used models to predict PM₂.₅ concentrations in UB. Using data from 0:00 on June 1, 2018, to 23:00 on April 30, 2020, we proposed two deep learning models based on Bayesian-optimized LSTM (Bayes-LSTM) and CNN-LSTM. We utilized hourly observed data, including Himawari8 (H8) aerosol optical depth (AOD), meteorology, and PM₂.₅ concentration, as input for the prediction of PM₂.₅ concentrations. The correlation strengths between meteorology, AOD, and PM₂.₅ were analyzed using the gray correlation analysis method; the comparison of the performance improvement of the model by using the AOD input value was tested, and the performance of these models was evaluated using mean absolute error (MAE) and root mean square error (RMSE). The prediction accuracies of Bayes-LSTM and CNN-LSTM deep learning models were both improved when AOD was included as an input parameter. Improvement of the prediction accuracy of the CNN-LSTM model was particularly enhanced in the non-heating season; in the heating season, the prediction accuracy of the Bayes-LSTM model slightly improved, while the prediction accuracy of the CNN-LSTM model slightly decreased. We propose two novel deep learning models for PM₂.₅ concentration prediction in UB, Bayes-LSTM, and CNN-LSTM deep learning models. Pioneering the use of AOD data from H8 and demonstrating the inclusion of AOD input data improves the performance of our two proposed deep learning models.

Keywords: deep learning, AOD, PM2.5, prediction, Ulaanbaatar

Procedia PDF Downloads 18

Authors: A. Majidian

Abstract:

The life prediction of thermal power plant components is necessary to prevent the unexpected outages, optimize maintenance tasks in periodic overhauls and plan inspection tasks with their schedules. One of the main critical components in a power plant is condenser because its failure can affect many other components which are positioned in downstream of condenser. This paper deals with factors affecting life of condenser. Failure rates dependency vs. these factors has been investigated using Artificial Neural Network (ANN) and fuzzy logic algorithms. These algorithms have shown their capabilities as dynamic tools to evaluate life prediction of power plant equipments.

Keywords: life prediction, condenser tube, neural network, fuzzy logic

Procedia PDF Downloads 323

Authors: Daniel Botero, Oscar Rubiano, Pedro P. Barragan, Jaime Baron, Leonardo Rodriguez Perdomo, Jaime Rodriguez

Abstract:

In the last decade interval training (IT) has gained importance when is compare with strength training (ST). However, there are few studies analyzing the impact of these training over the autonomic nervous system (ANS). This work has aimed to compare the activity of the autonomic nervous system, when is expose to an IT or ST indoor cycling mode. After approval by the ethics committee, a cross-over clinical trial with 22 healthy participants (age 21 ± 3 years) was implemented. The selection of participants for the groups with sequence force-interval (F-I) and interval-force (I-F) was made randomly with assignation of 11 participants for each group. The temporal series of heart rate was obtained before and after each training using the POLAR TEAM® heart monitor. The evaluation of the ANS was performed with spectral analysis of the heart rate variability (HRV) using the fast Fourier transform (Kubios software). A training of 8 weeks in each sequence (4 weeks with each training) with an intermediate period of two weeks of washout was implemented for each group. The power parameter of the HRV in the low frequency band (LF = 0.04-0.15Hz related to the sympathetic nervous system), high frequency (HF = 0.15-0.4Hz, related to the parasympathetic) and LF/HF (with reference to a modulation of parasympathetic over the sympathetic), were calculated. Afterward, the difference between the parameters before and after was realized. Then, to evaluate statistical differences between each training was implemented the method of Wellek (Wellek and Blettner, 2012, Medicine, 109 (15), 276-81). To determine the difference of effect over parasympathetic when FT and IT are used, the T test is implemented obtaining a T value of 0.73 with p-value ≤ 0.1. For the sympathetic was obtained a T of 0.33 with p ≤ 0.1 and for LF/HF the T was 1.44 with a p ≥ 0.1. Then, the carry over effect was evaluated and was not present. Significant changes over autonomic activity with strength or interval training were not observed. However, a modulation of the parasympathetic over the sympathetic can be observed. Probably, these findings should be explained because the sample is little and/or the time of training was insufficient to generate changes.

Keywords: autonomic nervous, force training, indoor cycling, interval training

Procedia PDF Downloads 192

Authors: Tarek Aboueldahab, Amin Mohamed Nassar

Abstract:

Wind energy is a fluctuating energy source unlike conventional power plants, thus, it is necessary to accurately predict short term wind speed to integrate wind energy in the electricity supply structure. To do so, we present a hybrid artificial intelligence model of short term wind speed prediction based on passive aggregation of the particle swarm optimization and neural networks. As a result, improvement of the prediction accuracy is obviously obtained compared to the standard artificial intelligence method.

Keywords: artificial intelligence, neural networks, particle swarm optimization, passive aggregation, wind speed prediction

Procedia PDF Downloads 418

Authors: Thinh Ngo, Paul Rad, Brian Kelley

Abstract:

Noise estimation is essential in today wireless systems for power control, adaptive modulation, interference suppression and quality of service. Deep learning (DL) has already been applied in the physical layer for modulation and signal classifications. Unacceptably low accuracy of less than 50% is found to undermine traditional application of DL classification for SNR prediction. In this paper, we use divide-and-conquer algorithm and classifier fusion method to simplify SNR classification and therefore enhances DL learning and prediction. Specifically, multiple CNNs are used for classification rather than a single CNN. Each CNN performs a binary classification of a single SNR with two labels: less than, greater than or equal. Together, multiple CNNs are combined to effectively classify over a range of SNR values from −20 ≤ SNR ≤ 32 dB.We use pre-trained CNNs to predict SNR over a wide range of joint channel parameters including multiple Doppler shifts (0, 60, 120 Hz), power-delay profiles, and signal-modulation types (QPSK,16QAM,64-QAM). The approach achieves individual SNR prediction accuracy of 92%, composite accuracy of 70% and prediction convergence one order of magnitude faster than that of traditional estimation.

Keywords: classification, CNN, deep learning, prediction, SNR

Procedia PDF Downloads 102