Search results for: facility data model

Authors: M. Kosacka, I. Kudelska

Abstract:

Vehicle is one of the most influential and complex product worldwide, which affects people’s life, state of the environment and condition of the economy (all aspects of sustainable development concept) during each stage of lifecycle. With the increase of vehicles’ number, there is growing potential for management of End of Life Vehicle (ELV), which is hazardous waste. From one point of view, the ELV should be managed to ensure risk elimination, but from another point, it should be treated as a source of valuable materials and spare parts. In order to obtain materials and spare parts, there are established recycling networks, which are an example of sustainable policy realization at the national level. The basic object in the polish recycling network is dismantling facility. The output material streams in dismantling stations include waste, which very often generate costs and spare parts, that have the biggest potential for revenues creation. Both outputs are stored into warehouses, according to the law. In accordance to the revenue creation and sustainability potential, it has been placed a strong emphasis on storage process. We present the concept of storage method, which takes into account the specific of the dismantling facility in order to support decision-making process with regard to the principles of sustainable development. The method was developed on the basis of case study of one of the greatest dismantling facility in Poland.

Keywords: dismantling, end of life vehicles, sustainability, storage

Procedia PDF Downloads 268

Authors: Komol Phaisarn, Anuphan Suttimarn, Vitchanan Keawtong, Kittisak Thongyoun, Chaiyos Jamsawang

Abstract:

This article is intended to analyze insurance information which contains information on the customer decision when purchasing life insurance pay package. The data were analyzed in order to present new customers with Life Insurance Perfect Pay package to meet new customers’ needs as much as possible. The basic data of insurance pay package were collect to get data mining; thus, reducing the scattering of information. The data were then classified in order to get decision model or decision tree using Algorithm C4.5 (J-48). In the classification, WEKA tools are used to form the model and testing datasets are used to test the decision tree for the accurate decision. The validation of this model in classifying showed that the accurate prediction was 68.43% while 31.25% were errors. The same set of data were then tested with other models, i.e. Naive Bayes and Zero R. The results showed that J-48 method could predict more accurately. So, the researcher applied the decision tree in writing the program used to introduce the product to new customers to persuade customers’ decision making in purchasing the insurance package that meets the new customers’ needs as much as possible.

Keywords: decision tree, data mining, customers, life insurance pay package

Procedia PDF Downloads 423

Authors: Dana Al-Qattan, Faiza Goodarzi, Heba Al-Resheedan, Kawther Shehab, Shoug Al-Ansari

Abstract:

This project involves working with different types of forecasting methods and facility planning tools to help the company we have chosen to improve and reduce its inventory, increase its sales, and decrease its wastes and losses. The methods that have been used by the company have shown no improvement in decreasing the annual losses. The research made in the company has shown that no interest has been made in exploring different techniques to help the company. In this report, we introduce several methods and techniques that will help the company make more accurate forecasts and use of the available space efficiently. We expect our approach to reduce costs without affecting the quality of the product, and hence making production more viable.

Keywords: production planning, inventory management, inventory control, simulation, facility planning and design, engineering economy and costs

Procedia PDF Downloads 565

Authors: K. Khanafer

Abstract:

The aim of this investigation was to validate the fluid-structure interaction (FSI) model of type B aortic dissection with our experimental results from a bench-top-model. Another objective was to study the relationship between the size of a septectomy that increases the outflow of the false lumen and its effect on the values of the differential of pressure between true lumen and false lumen. FSI analysis based on Galerkin’s formulation was used in this investigation to study flow pattern and hemodynamics within a flexible type B aortic dissection model using boundary conditions from our experimental data. The numerical results of our model were verified against the experimental data for various tear size and location. Thus, CFD tools have a potential role in evaluating different scenarios and aortic dissection configurations.

Keywords: aortic dissection, fluid-structure interaction, in vitro model, numerical

Procedia PDF Downloads 267

Authors: Dolgormaa Munkhbaatar, Munkhsaikhan Adiya, Tseedulam Khuut

Abstract:

We performed an inversion method to determine the 1D-velocity model with station corrections of the Gobi-Altai area in the southern part of Mongolia using earthquake data collected in the National Data Center during the last 10 years. In this study, the concept of the new 1D model has been employed to minimize the average RMS of a set of well-located earthquakes, recorded at permanent (between 2006 and 2016) and temporary seismic stations (between 2014 and 2016), compute solutions for the coupled hypocenter and 1D velocity model. We selected 4800 events with RMS less than 0.5 seconds and with a maximum GAP of 170 degrees and determined velocity structures. Also, we relocated all possible events located in the Gobi-Altai area using the new 1D velocity model and achieved constrained hypocentral determinations for events within this area. We concluded that the estimated new 1D velocity model is a relatively low range compared to the previous velocity model in a significant improvement intend to, and the quality of the information basis for future research center locations to determine the earthquake epicenter area with this new transmission model.

Keywords: 1D velocity model, earthquake, relocation, Velest

Procedia PDF Downloads 162

Authors: Deike Janssen

Abstract:

In the scenery of the Tyrolean mountains, at an altitude of 1300 meters, stands a building. Residents and activists call it a prison. However, it is not a prison -according to authorities, it is a 'Return Counseling Facility' where migrants and refugees should be "motivated" to return "voluntary" to their countries of origin. This paper argues that the geographical location of the camp functions as a site of exclusion, isolation, and coercion where no one can decide “voluntary” to return, but where people are brought to despair to leave Austria. Through a qualitative case study, this paper documents the heavy impact of offshore detention on the mental, physical and social state of the residents and a variety of human rights problems in the centre. Different developments at the Return Counselling Facility and the law that back up the centre uncover a worrying dynamic that deliberately accepts human rights problems in order to enforce borders, a policy that disregards humanitarian, legal, and ethical stands in order to deport people at all hazards. It, therefore, can be seen as a creative and ultimate exercise of state power, which uses isolated locations to control migration. While the analysis revises the micro and macro implications of the facility and, therefore, the legal and political facets, it also sheds light on the role of the civil society, which tries to increase through constant and collective efforts the human rights efforts of the government.

Keywords: deportation, human rights, migration, refugee detention, voluntary return

Procedia PDF Downloads 133

Authors: Sajid Hussain

Abstract:

The complex domain approach for image segmentation based on active contour has been designed, which deforms step by step to partition an image into numerous expedient regions. A novel region-based trigonometric complex pressure force function is proposed, which propagates around the region of interest using image forces. The signed trigonometric force function controls the propagation of the active contour and the active contour stops on the exact edges of the object accurately. The proposed model makes the level set function binary and uses Gaussian smoothing kernel to adjust and escape the re-initialization procedure. The working principle of the proposed model is as follows: The real image data is transformed into complex data by iota (i) times of image data and the average iota (i) times of horizontal and vertical components of the gradient of image data is inserted in the proposed model to catch complex gradient of the image data. A simple finite difference mathematical technique has been used to implement the proposed model. The efficiency and robustness of the proposed model have been verified and compared with other state-of-the-art models.

Keywords: image segmentation, active contour, level set, Mumford and Shah model

Procedia PDF Downloads 104

Authors: Ya-Chuan Hsu, Wen-Chen Ouyang, Wei-Siang Huang

Abstract:

Problem/Background: With constantly increasing aged populations, quality of life (QOL) in persons with dementia has become a significant research concern. The Alzheimer’s Related Quality of Life (ADRQL) is a high-validated, theory-derived, and multidimensional instrument. It has widely utilized in many countries, except in Taiwan. However, diverse results of quality of life from different countries by using the same measurement can provide the potential to help understand the impact of cultural contributor on QOL. Objective: To investigate the extent to which quality of life on older adults with dementia in Taiwan. Methods: Cross-sectional, descriptive study conducted in an assisting living facility affiliated with a daycare center in southern Taiwan. A purposeful sample of 34 participants was recruited. Inclusion criteria included those who were at least 65 years old, able to communicate, and diagnosed with mild to moderate dementia. The QOL was measured by Chinese version ADRQL. This observational instrument consists of 30 items that is divided into five subscales with the full range of each subscale scores from 0 to 100.0. Higher scores indicate better QOL. Results: The means for subscale of the Social Interaction, Awareness of Self, Feelings and Mood, Enjoyment of Activities, and Response to Surroundings were 87.9, 74.7, 91.3, 64.5, and 90.3, respectively. The overall mean for the ADQOL was 0.83. Conclusion: Findings suggest that the level of Enjoyment of Activities is the lowest and may convey information about a need of evaluation on arrangement of facility’s activities.

Keywords: dementia, quality of life, elders, Alzheimer’s related quality of life

Procedia PDF Downloads 298

Authors: Kanyarat Bussaban, Kunyanuth Kularbphettong

Abstract:

This research aims to create a model for analysis of student behavior using Library resources based on data mining technique in case of Suan Sunandha Rajabhat University. The model was created under association rules, apriori algorithm. The results were found 14 rules and the rules were tested with testing data set and it showed that the ability of classify data was 79.24 percent and the MSE was 22.91. The results showed that the user’s behavior model by using association rule technique can use to manage the library resources.

Keywords: behavior, data mining technique, a priori algorithm, knowledge discovery

Procedia PDF Downloads 400

Authors: Paul Dallyn, Ashraf El-Hamalawi, Alessandro Palmeri, Bob Knight

Abstract:

In order to better understand the long term implications of the grout wear failure mode in large-diameter plain-sided grouted connections, a numerical model has been developed and calibrated that can take advantage of existing operational plant data to predict the wear accumulation for the actual load conditions experienced over a given period, thus limiting the need for expensive monitoring systems. This model has been derived and calibrated based on site structural condition monitoring (SCM) data and supervisory control and data acquisition systems (SCADA) data for two operational wind turbine generator substructures afflicted with this challenge, along with experimentally derived wear rates.

Keywords: grouted connection, numerical model, offshore structure, wear, wind energy

Procedia PDF Downloads 448

Authors: Abdela Zeinu Yasin

Abstract:

The current research aimed to assess the status of IMC in providing treatment for malnourished children and programs in water, sanitation, and hygiene (WASH), food and livelihood security, and comprehensive healthcare through Mobile health and nutrition programs during the last 5 years period. We have conducted 60 in-depth interviews with women during the period from conception to a child’s birthday, health facility staff, and female community health volunteers (FCHVs), as well as 12 focus group discussions with health facility staff and other household decision-makers. We employed thematic analysis using framework matrices and analytical memorandums. The study revealed that 78% of the respondents, of whom 97% were women, have benefited from the selected vulnerable areas. The use of the clear water and sanitization program has reached the 81% of selected households. The use of a modern baby delivery system among the respondent has been 68% of the women and health facilities among the decision-makers/focal person. More than 8 in 10 participants (84%) could read and understand the health facility instructions, and the majority (82%) of women, health facility staff, and male decision-makers can also read and write bulletins and instructions. We found that decision-maker women preferred participative education, whereas health facilities and the IMC desired educational and motivational bulletins. A Mobile Health and Nutrition program intervention by the IMC is acceptable in the conditions of the Ethiopian community and has the potential to improve community health and nutrition service utilization, particularly by providing clean water and sanitization; women’s birth control, and health improvement in the vulnerable regions of the country. The current research findings shall contribute to text IMC Mobile Health and Nutritional intervention design in under-resourced settings.

Keywords: clean water, health and nutrition services, hygiene, IMC, mobile health, sanitation

Procedia PDF Downloads 90

Authors: Mahadev Bhise, Nabanita Majumder

Abstract:

Recent studies have found association between air pollutants and mortality, particularly how concentration of air pollutant explains under-five mortality across the countries. Thus, the present study evaluates the relationship between Carbon dioxide (CO2) emission and under-five mortality, while controlling other well-being determinant of Under-five mortality in 100 countries using panel unbalanced cross sectional data. We have used PCSE and GMM model for the period 1990-2011 to meet our objectives. Our findings suggest that, the positive relationship between lagged periods of carbon dioxide and under-five mortality; the percentage of rural population with access of improved water is negatively associated with under-five mortality, while in case of urban population with access of improved water, is positively related to under-five mortality. Access of sanitation facility, food production index, GDP per capita, and concentration of urban population have significant negative impact on under-five mortality. Further, total fertility rate is significantly associated (positive) with under-five mortality which indicates relative change in fertility is related to relative change in under-five mortality.

Keywords: arbon dioxide (CO2), under-five mortality (0q5), gross domestic product (GDP), urban population, food production, panel corrected standard errors (PCSE), generalized method of moments (GMM)

Procedia PDF Downloads 306

Authors: Zhi Zhu, Boquan Zhang, Tian Jing, Jingjing Li, Tao Wang

Abstract:

Data assimilation is a model and data hybrid-driven method that dynamically fuses new observation data with a numerical model to iteratively approach the real system state. It is widely used in state prediction and parameter inference of continuous systems. Because of the discrete event system’s non-linearity and non-Gaussianity, traditional Kalman Filter based on linear and Gaussian assumptions cannot perform data assimilation for such systems, so particle filter has gradually become a technical approach for discrete event simulation data assimilation. Hence, we proposed a particle filter-based discrete event simulation data assimilation method and took the unmanned aerial vehicle (UAV) maintenance service system as a proof of concept to conduct simulation experiments. The experimental results showed that the filtered state data is closer to the real state of the system, which verifies the effectiveness of the proposed method. This research can provide a reference framework for the data assimilation process of other complex nonlinear systems, such as discrete-time and agent simulation.

Keywords: discrete event simulation, data assimilation, particle filter, model and data-driven

Procedia PDF Downloads 4

Authors: Wang Yichen, Haruka Yamashita

Abstract:

In recent years, in the field of sports, decision making such as member in the game and strategy of the game based on then analysis of the accumulated sports data are widely attempted. In fact, in the NBA basketball league where the world's highest level players gather, to win the games, teams analyze the data using various statistical techniques. However, it is difficult to analyze the game data for each play such as the ball tracking or motion of the players in the game, because the situation of the game changes rapidly, and the structure of the data should be complicated. Therefore, it is considered that the analysis method for real time game play data is proposed. In this research, we propose an analytical model for "determining the optimal lineup composition" using the real time play data, which is considered to be difficult for all coaches. In this study, because replacing the entire lineup is too complicated, and the actual question for the replacement of players is "whether or not the lineup should be changed", and “whether or not Small Ball lineup is adopted”. Therefore, we propose an analytical model for the optimal player selection problem based on Small Ball lineups. In basketball, we can accumulate scoring data for each play, which indicates a player's contribution to the game, and the scoring data can be considered as a time series data. In order to compare the importance of players in different situations and lineups, we combine RNN (Recurrent Neural Network) model, which can analyze time series data, and NN (Neural Network) model, which can analyze the situation on the field, to build the prediction model of score. This model is capable to identify the current optimal lineup for different situations. In this research, we collected all the data of accumulated data of NBA from 2019-2020. Then we apply the method to the actual basketball play data to verify the reliability of the proposed model.

Keywords: recurrent neural network, players lineup, basketball data, decision making model

Procedia PDF Downloads 129

Authors: Qing Zhang, Jiachen Nie, Yujia Wen, Guanyuan Kou, Peng Yu, Kun Xia, Qin Yang, Li Ding

Abstract:

BACKGROUND: A facility layout problem (FLP) is an NP-complete (non-deterministic polynomial) problem, which is hard to obtain an exact optimal solution. FLP has been widely studied in various limited spaces and workflows. For example, cafeterias with many types of equipment for troops cause chaotic processes when dining. OBJECTIVE: This article tried to optimize the layout of troops’ cafeteria and to improve the overall efficiency of the dining process. METHODS: First, the original cafeteria layout design scheme was analyzed from an ergonomic perspective and two new design schemes were generated. Next, three facility layout models were designed, and further simulation was applied to compare the total time and density of troops between each scheme. Last, an experiment of the dining process with video observation and analysis verified the simulation results. RESULTS: In a simulation, the dining time under the second new layout is shortened by 2.25% and 1.89% (p<0.0001, p=0.0001) compared with the other two layouts, while troops-flow density and interference both greatly reduced in the two new layouts. In the experiment, process completing time and the number of interference reduced as well, which verified corresponding simulation results. CONCLUSIONS: Our two new layout schemes are tested to be optimal by a series of simulation and space experiments. In future research, similar approaches could be applied when taking layout-design algorithm calculation into consideration.

Keywords: layout optimization, dining efficiency, troops’ cafeteria, anylogic simulation, field experiment

Procedia PDF Downloads 140

Authors: Wookyong Kwon, Sangmoon Lee

Abstract:

In this paper, a sampled-data model predictive tracking control method is presented for mobile robots which is modeled as constrained continuous-time linear parameter varying (LPV) systems. The presented sampled-data predictive controller is designed by linear matrix inequality approach. Based on the input delay approach, a controller design condition is derived by constructing a new Lyapunov function. Finally, a numerical example is given to demonstrate the effectiveness of the presented method.

Keywords: model predictive control, sampled-data control, linear parameter varying systems, LPV

Procedia PDF Downloads 306

Authors: Budi Nurani Ruchjana, Atje Setiawan Abdullah, I. Gede Nyoman Mindra Jaya, Eddy Hermawan

Abstract:

In this paper, we propose the application package to estimate parameters of spatiotemporal model based on the multivariate time series analysis using the R open-source software. We build packages mainly to estimate the parameters of the Generalized Space Time Autoregressive (GSTAR) model. GSTAR is a combination of time series and spatial models that have parameters vary per location. We use the method of Ordinary Least Squares (OLS) and use the Mean Average Percentage Error (MAPE) to fit the model to spatiotemporal real phenomenon. For case study, we use oil production data from volcanic layer at Jatibarang Indonesia or climate data such as rainfall in Indonesia. Software R is very user-friendly and it is making calculation easier, processing the data is accurate and faster. Limitations R script for the estimation of model parameters spatiotemporal GSTAR built is still limited to a stationary time series model. Therefore, the R program under windows can be developed either for theoretical studies and application.

Keywords: GSTAR Model, MAPE, OLS method, oil production, R software

Procedia PDF Downloads 237

Authors: Ilker Ali Ozkan

Abstract:

In this study, an artificial neural network model has been developed to estimate chronic kidney failure which is a common disease. The patients’ age, their blood and biochemical values, and 24 input data which consists of various chronic diseases are used for the estimation process. The input data have been subjected to preprocessing because they contain both missing values and nominal values. 147 patient data which was obtained from the preprocessing have been divided into as 70% training and 30% testing data. As a result of the study, artificial neural network model with 25 neurons in the hidden layer has been found as the model with the lowest error value. Chronic kidney failure disease has been able to be estimated accurately at the rate of 99.3% using this artificial neural network model. The developed artificial neural network has been found successful for the estimation of chronic kidney failure disease using clinical data.

Keywords: estimation, artificial neural network, chronic kidney failure disease, disease diagnosis

Procedia PDF Downloads 438

Authors: Martin Böhmer, Agatha Dabrowski, Boris Otto

Abstract:

The trend of digitization significantly changes the role of data for enterprises. Data turn from an enabler to an intangible organizational asset that requires management and qualifies as a tradeable good. The idea of a networked economy has gained momentum in the data domain as collaborative approaches for data management emerge. Traditional organizational knowledge consequently needs to be extended by comprehensive knowledge about data. The knowledge about data is vital for organizations to ensure that data quality requirements are met and data can be effectively utilized and sovereignly governed. As this specific knowledge has been paid little attention to so far by academics, the aim of the research presented in this paper is to conceptualize it by proposing a “data knowledge model”. Relevant model entities have been identified based on a design science research (DSR) approach that iteratively integrates insights of various industry case studies and literature research.

Keywords: data management, digitization, industry 4.0, knowledge engineering, metamodel

Procedia PDF Downloads 351

Authors: Hyun-Woo Cho

Abstract:

Detection of incipient abnormal events in production processes is important to improve safety and reliability of manufacturing operations and reduce losses caused by failures. The construction of calibration models for predicting faulty conditions is quite essential in making decisions on when to perform preventive maintenance. This paper presents a multivariate calibration monitoring approach based on the statistical analysis of process measurement data. The calibration model is used to predict faulty conditions from historical reference data. This approach utilizes variable selection techniques, and the predictive performance of several prediction methods are evaluated using real data. The results shows that the calibration model based on supervised probabilistic model yielded best performance in this work. By adopting a proper variable selection scheme in calibration models, the prediction performance can be improved by excluding non-informative variables from their model building steps.

Keywords: calibration model, monitoring, quality improvement, feature selection

Procedia PDF Downloads 352

Authors: Michael Gidey Gebru

Abstract:

Most DEA models operate in a static environment with input and output parameters that are chosen by deterministic data. However, due to ambiguity brought on shifting market conditions, input and output data are not always precisely gathered in real-world scenarios. Fuzzy numbers can be used to address this kind of ambiguity in input and output data. Therefore, this work aims to expand crisp DEA into DEA with fuzzy environment. In this study, the input and output data are regarded as fuzzy triangular numbers. Then, the DEA model with fuzzy environment is solved using a multi-objective method to gauge the Decision Making Units’ efficiency. Finally, the developed DEA model is illustrated with an application on real data 50 educational institutions.

Keywords: efficiency, DEA, fuzzy, decision making units, higher education institutions

Procedia PDF Downloads 48

Authors: Ling Qi, Matloob Khushi, Josiah Poon

Abstract:

This paper introduces a pre-trained Masked Candlestick Model (MCM) for trading time-series data. The pre-trained model is based on three core designs. First, we convert trading price data at each data point as a set of normalized elements and produce embeddings of each element. Second, we generate a masked sequence of such embedded elements as inputs for self-supervised learning. Third, we use the encoder mechanism from the transformer to train the inputs. The masked model learns the contextual relations among the sequence of embedded elements, which can aid downstream classification tasks. To evaluate the performance of the pre-trained model, we fine-tune MCM for three different downstream classification tasks to predict future price trends. The fine-tuned models achieved better accuracy rates for all three tasks than the baseline models. To better analyze the effectiveness of MCM, we test the same architecture for three currency pairs, namely EUR/GBP, AUD/USD, and EUR/JPY. The experimentation results demonstrate MCM’s effectiveness on all three currency pairs and indicate the MCM’s capability for signal extraction from trading data.

Keywords: masked language model, transformer, time series prediction, trading prediction, embedding, transfer learning, self-supervised learning

Procedia PDF Downloads 120

Authors: Nafe Moradkhani, Frederick Benaben, Benoit Montreuil, Ali Vatankhah Barenji, Dima Nazzal

Abstract:

In the context of the global pandemic, the practical management of the 2020 presidential election in the USA was a strong concern. To anticipate and prepare for this election accurately, one of the main challenges was to confront (i) forecasts of voter turnout, (ii) capacities of the facilities and, (iii) potential configuration options of resources. The approach chosen to conduct this anticipative study consists of collecting data about forecasts and using simulation models to work simultaneously on resource allocation and facility configuration of polling places in Fulton County, Georgia’s largest county. A polling place is a dedicated facility where voters cast their ballots in elections using different devices. This article presents the results of the simulations of such places facing pre-identified potential risks. These results are oriented towards the efficiency of these places according to different criteria (health, trust, comfort). Then a dynamic framework is introduced to describe risks as physical forces perturbing the efficiency of the observed system. Finally, the main benefits and contributions resulting from this simulation campaign are presented.

Keywords: performance, decision support, simulation, artificial intelligence, risk management, election, pandemics, information system

Procedia PDF Downloads 149

Authors: Shahram Payandeh

Abstract:

This paper presents an overview of a model which can be used as a part of a decision support system when fusing information from multiple sensing environment. Data fusion has been widely studied in the past few decades and numerous frameworks have been proposed to facilitate decision making process under uncertainties. Multi-sensor data fusion technology plays an increasingly significant role during people tracking and activity recognition. This paper presents an overview of a quantum model as a part of a decision-making process in the context of multi-sensor data fusion. The paper presents basic definitions and relationships associating the decision-making process and quantum model formulation in the presence of uncertainties.

Keywords: quantum model, sensor space, sensor network, decision support

Procedia PDF Downloads 222

Authors: Mesbaholdin Salami, Farzad Movahedi Sobhani, Mohammad Sadegh Ghazizadeh

Abstract:

Evaluation of organizational performance is among the most important measures that help organizations and entities continuously improve their efficiency. Organizations can use the existing data and results from the comparison of units under investigation to obtain an estimation of their performance. The Malmquist Productivity Index (MPI) is an important index in the evaluation of overall productivity, which considers technological developments and technical efficiency at the same time. This article proposed a model based on the multistage MPI, considering limited data (Grey’s theory). This model can evaluate the performance of units using limited and uncertain data in a multistage process. It was applied by the electricity market manager to Iran’s electric power supply chain (EPSC), which contains uncertain data, to evaluate the performance of its actors. Results from solving the model showed an improvement in the accuracy of future performance of the units under investigation, using the Grey’s system theory. This model can be used in all case studies, in which MPI is used and there are limited or uncertain data.

Keywords: Malmquist Index, Grey's Theory, CCR Model, network data envelopment analysis, Iran electricity power chain

Procedia PDF Downloads 161

Authors: Samiah Alammari, Nassim Ammour

Abstract:

When providing a massive number of tasks successively to a deep learning process, a good performance of the model requires preserving the previous tasks data to retrain the model for each upcoming classification. Otherwise, the model performs poorly due to the catastrophic forgetting phenomenon. To overcome this shortcoming, we developed a successful continual learning deep model for remote sensing hyperspectral image regions classification. The proposed neural network architecture encapsulates two trainable subnetworks. The first module adapts its weights by minimizing the discrimination error between the land-cover classes during the new task learning, and the second module tries to learn how to replicate the data of the previous tasks by discovering the latent data structure of the new task dataset. We conduct experiments on HSI dataset Indian Pines. The results confirm the capability of the proposed method.

Keywords: continual learning, data reconstruction, remote sensing, hyperspectral image segmentation

Procedia PDF Downloads 257

Authors: Monika Chuchro

Abstract:

This paper presents a preliminary attempt to apply classification of time series using meta-clusters in order to improve the quality of regression models. In this case, clustering was performed as a method to obtain a subgroups of time series data with normal distribution from inflow into waste water treatment plant data which Composed of several groups differing by mean value. Two simple algorithms: K-mean and EM were chosen as a clustering method. The rand index was used to measure the similarity. After simple meta-clustering, regression model was performed for each subgroups. The final model was a sum of subgroups models. The quality of obtained model was compared with the regression model made using the same explanatory variables but with no clustering of data. Results were compared by determination coefficient (R2), measure of prediction accuracy mean absolute percentage error (MAPE) and comparison on linear chart. Preliminary results allows to foresee the potential of the presented technique.

Keywords: clustering, data analysis, data mining, predictive models

Procedia PDF Downloads 462

Authors: Aswathi Thrivikraman, S. Advaith

Abstract:

The study is aimed at designing encoders for deciphering intricacies in time series data by redescribing the dynamics operating on a lower-dimensional manifold. A semi-supervised LSTM autoencoder is devised and investigated to see if the latent representation of the time series data can better forecast the data. End-to-end training of the LSTM autoencoder, together with another LSTM network that is connected to the latent space, forces the hidden states of the encoder to represent the most meaningful latent variables relevant for forecasting. Furthermore, the study compares the predictions with those of a traditional seq2seq model.

Keywords: LSTM, autoencoder, forecasting, seq2seq model

Procedia PDF Downloads 149

Authors: Faezeh Mosallat, Eric L. Bibeau, Tarek El Mekkawy

Abstract:

Availability of a wide variety of renewable resources, such as large reserves of hydro, biomass, solar and wind in Canada provides significant potential to improve the sustainability of energy uses. As buildings represent a considerable portion of energy use in Canada, application of distributed solar energy systems for heating and cooling may increase the amount of renewable energy use. Parabolic solar trough systems have seen limited deployments in cold northern climates as they are more suitable for electricity production in southern latitudes. Heat production by concentrating solar rays using parabolic troughs can overcome the poor efficiencies of flat panels and evacuated tubes in cold climates. A numerical dynamic model is developed to simulate an installed parabolic solar trough facility in Winnipeg. The results of the numerical model are validated using the experimental data obtained from this system. The model is developed in Simulink and will be utilized to simulate a tri-generation system for heating, cooling and electricity generation in remote northern communities. The main objective of this simulation is to obtain operational data of solar troughs in cold climates as this is lacking in the literature. In this paper, the validated Simulink model is applied to simulate a solar assisted absorption cooling system along with electricity generation using organic Rankine cycle (ORC) and thermal storage. A control strategy is employed to distribute the heated oil from solar collectors among the above three systems considering the temperature requirements. This modeling provides dynamic performance results using real time minutely meteorological data which are collected at the same location the solar system is installed. This is a big step ahead of the current models by accurately calculating the available solar energy at each time step considering the solar radiation fluctuations due to passing clouds. The solar absorption cooling is modeled to use the generated heat from the solar trough system and provide cooling in summer for a greenhouse which is located next to the solar field. A natural gas water heater provides the required excess heat for the absorption cooling at low or no solar radiation periods. The results of the simulation are presented for a summer month in Winnipeg which includes the amount of generated electric power from ORC and contribution of solar energy in the cooling load provision

Keywords: absorption cooling, parabolic solar trough, remote community, validated model

Procedia PDF Downloads 211

Authors: D. Bianco, A. Sollazzo, M. Barbarino, G. Elia, A. Smoraldi, N. Favaloro

Abstract:

The activities, described in the present paper, have been conducted in the framework of the HYPROB-New Program, carried out by the Italian Aerospace Research Centre (CIRA) promoted and funded by the Italian Ministry of University and Research (MIUR) in order to improve the National background on rocket engine systems for space applications. The Program has the strategic objective to improve National system and technology capabilities in the field of liquid rocket engines (LRE) for future Space Propulsion Systems applications, with specific regard to LOX/LCH4 technology. The main purpose of the HYPROB program is to design and build a Propulsion Test Facility (HIMP) allowing test activities on Liquid Thrusters. The development of skills in liquid rocket propulsion can only pass through extensive test campaign. Following its mission, CIRA has planned the development of new testing facilities and infrastructures for space propulsion characterized by adequate sizes and instrumentation. The IMP test cell is devoted to testing articles representative of small combustion chambers, fed with oxygen and methane, both in liquid and gaseous phase. This article describes the activities that have been carried out for the evaluation of the acoustic impact, and its consequent mitigation. The impact of the simulated acoustic disturbance has been evaluated, first, using an approximated method based on experimental data by Baumann and Coney, included in “Noise and Vibration Control Engineering” edited by Vér and Beranek. This methodology, used to evaluate the free-field radiation of jet in ideal acoustical medium, analyzes in details the jet noise and assumes sources acting at the same time. It considers as principal radiation sources the jet mixing noise, caused by the turbulent mixing of jet gas and the ambient medium. Empirical models, allowing a direct calculation of the Sound Pressure Level, are commonly used for rocket noise simulation. The model named after K. Eldred is probably one of the most exploited in this area. In this paper, an improvement of the Eldred Standard model has been used for a detailed investigation of the acoustical impact of the Hyprob facility. This new formulation contains an explicit expression for the acoustic pressure of each equivalent noise source, in terms of amplitude and phase, allowing the investigation of the sources correlation effects and their propagation through wave equations. In order to enhance the evaluation of the facility acoustic impact, including an assessment of the mitigation strategies to be set in place, a more advanced simulation campaign has been conducted using both an in-house code for noise propagation and scattering, and a commercial code for industrial noise environmental impact, CadnaA. The noise prediction obtained with the revised Eldred-based model has then been used for formulating an empirical/BEM (Boundary Element Method) hybrid approach allowing the evaluation of the barrier mitigation effect, at the design. This approach has been compared with the analogous empirical/ray-acoustics approach, implemented within CadnaA using a customized definition of sources and directivity factor. The resulting impact evaluation study is reported here, along with the design-level barrier optimization for noise mitigation.

Keywords: acoustic impact, industrial noise, mitigation, rocket noise

Procedia PDF Downloads 140