Search results for: facility data model

Authors: Oscar E. Cariceo, Claudia V. Casal

Abstract:

Machine learning offers a set of techniques to promote social work interventions and can lead to support decisions of practitioners in order to predict new behaviors based on data produced by the organizations, services agencies, users, clients or individuals. Machine learning techniques include a set of generalizable algorithms that are data-driven, which means that rules and solutions are derived by examining data, based on the patterns that are present within any data set. In other words, the goal of machine learning is teaching computers through 'examples', by training data to test specifics hypothesis and predict what would be a certain outcome, based on a current scenario and improve that experience. Machine learning can be classified into two general categories depending on the nature of the problem that this technique needs to tackle. First, supervised learning involves a dataset that is already known in terms of their output. Supervising learning problems are categorized, into regression problems, which involve a prediction from quantitative variables, using a continuous function; and classification problems, which seek predict results from discrete qualitative variables. For social work research, machine learning generates predictions as a key element to improving social interventions on complex social issues by providing better inference from data and establishing more precise estimated effects, for example in services that seek to improve their outcomes. This paper exposes the results of a classification algorithm to predict cyberbullying among adolescents. Data were retrieved from the National Polyvictimization Survey conducted by the government of Chile in 2017. A logistic regression model was created to predict if an adolescent would experience cyberbullying based on the interaction and behavior of gender, age, grade, type of school, and self-esteem sentiments. The model can predict with an accuracy of 59.8% if an adolescent will suffer cyberbullying. These results can help to promote programs to avoid cyberbullying at schools and improve evidence based practice.

Keywords: cyberbullying, evidence based practice, machine learning, social work research

Procedia PDF Downloads 166

Authors: Farid Habibi Tanha, Mojtaba Jahanbazi, Morteza Foroutan, Rasidah Mohd Rashid

Abstract:

This paper depicts the effects of asymmetric information in determining capital inflows to be captured through stock market microstructure. The model can explain several stylized facts regarding the capital immobility. The first phase of the research involves in collecting and refining 150,000,000 daily data of 11 stock markets over a period of one decade in an effort to minimize the impact of survivorship bias. Three micro techniques were used to measure information asymmetries. The final phase analyzes the model through panel data approach. As a unique contribution, this research will provide valuable information regarding negative effects of information asymmetries in stock markets on attracting foreign investments. The results of this study can be directly considered by policy makers to monitor and control changes of capital flow in order to keep market conditions in a healthy manner, by preventing and managing possible shocks to avoid sudden reversals and market failures.

Keywords: asymmetric information, capital inflow, market microstructure, investment

Procedia PDF Downloads 317

Authors: Robert Höttger, Lukas Krawczyk, Burkhard Igel

Abstract:

This paper introduces novel approaches to partitioning and mapping in terms of model-based embedded multicore system engineering and further discusses benefits, industrial relevance and features in common with existing approaches. In order to assess and evaluate results, both approaches have been applied to a real industrial application as well as to various prototypical demonstrative applications, that have been developed and implemented for different purposes. Evaluations show, that such applications improve significantly according to performance, energy efficiency, meeting timing constraints and covering maintaining issues by using the AMALTHEA platform and the implemented approaches. Further- more, the model-based design provides an open, expandable, platform independent and scalable exchange format between OEMs, suppliers and developers on different levels. Our proposed mechanisms provide meaningful multicore system utilization since load balancing by means of partitioning and mapping is effectively performed with regard to the modeled systems including hardware, software, operating system, scheduling, constraints, configuration and more data.

Keywords: partitioning, mapping, distributed systems, scheduling, embedded multicore systems, model-based, system analysis

Procedia PDF Downloads 617

Authors: Farnaz Farhangi

Abstract:

Many people in New Zealand believe that the access to water is inexhaustible, and it comes from a history of virtually unrestricted access to it. For the region like Hamilton which is one of New Zealand’s fastest growing cities, it is crucial for policy makers to know about the future water consumption and implementation of rules and regulation such as universal water metering. Hamilton residents use water freely and they do not have any idea about how much water they use. Hence, one of proposed objectives of this research is focusing on forecasting water consumption using different methods. Residential water consumption time series exhibits seasonal and trend variations. Seasonality is the pattern caused by repeating events such as weather conditions in summer and winter, public holidays, etc. The problem with this seasonal fluctuation is that, it dominates other time series components and makes difficulties in determining other variations (such as educational campaign’s effect, regulation, etc.) in time series. Apart from seasonality, a stochastic trend is also combined with seasonality and makes different effects on results of forecasting. According to the forecasting literature, preprocessing (de-trending and de-seasonalization) is essential to have more performed forecasting results, while some other researchers mention that seasonally non-adjusted data should be used. Hence, I answer the question that is pre-processing essential? A wide range of forecasting methods exists with different pros and cons. In this research, I apply double seasonal ARIMA and Artificial Neural Network (ANN), considering diverse elements such as seasonality and calendar effects (public and school holidays) and combine their results to find the best predicted values. My hypothesis is the examination the results of combined method (hybrid model) and individual methods and comparing the accuracy and robustness. In order to use ARIMA, the data should be stationary. Also, ANN has successful forecasting applications in terms of forecasting seasonal and trend time series. Using a hybrid model is a way to improve the accuracy of the methods. Due to the fact that water demand is dominated by different seasonality, in order to find their sensitivity to weather conditions or calendar effects or other seasonal patterns, I combine different methods. The advantage of this combination is reduction of errors by averaging of each individual model. It is also useful when we are not sure about the accuracy of each forecasting model and it can ease the problem of model selection. Using daily residential water consumption data from January 2000 to July 2015 in Hamilton, I indicate how prediction by different methods varies. ANN has more accurate forecasting results than other method and preprocessing is essential when we use seasonal time series. Using hybrid model reduces forecasting average errors and increases the performance.

Keywords: artificial neural network (ANN), double seasonal ARIMA, forecasting, hybrid model

Procedia PDF Downloads 334

Authors: Estela Mayra de Moura Vianna, Thiago José Tavares Ávila, Bruno Morais Silva, Diego Henrique Bezerra, Paulo Henrique Gomes Silva, Alan Pedro da Silva

Abstract:

The Brazilian Federal Constitution defines the access to information as a crucial right of the citizen and the Law on Access to Public Information, which regulates this right. Accordingly, the Fiscal Responsibility Act, 2000, amended in 2009 by the “Law of Transparency”, began demanding a wider disclosure of public accounts for the society, including electronic media for public access. Thus, public entities began to create "Transparency Portals," which aim to gather a diversity of data and information. However, this information, in general, is still published in formats that do not simplify understanding of the data by citizens and that could be better especially available for audit purposes. In this context, a proposal of ontology about Brazilian Transparency Portal can play a key role in how these data will be better available. This study aims to identify and implement in ontology, the data model about Transparency Portal ecosystem, with emphasis in activities that use these data for some applications, like audits, press activities, social government control, and others.

Keywords: audit, government transparency, ontology, public sector

Procedia PDF Downloads 504

Authors: Abhisek Chakrabarty, Subhraprakash Mandal

Abstract:

Flash flood is one of the catastrophic natural hazards in the mountainous region of India. The recent flood in the Mandakini River in Kedarnath (14-17th June, 2013) is a classic example of flash floods that devastated Uttarakhand by killing thousands of people.The disaster was an integrated effect of high intensityrainfall, sudden breach of Chorabari Lake and very steep topography. Every year in Himalayan Region flash flood occur due to intense rainfall over a short period of time, cloud burst, glacial lake outburst and collapse of artificial check dam that cause high flow of river water. In Sikkim-Derjeeling Himalaya one of the probable flash flood occurrence zone is Teesta Watershed. The Teesta River is a right tributary of the Brahmaputra with draining mountain area of approximately 8600 Sq. km. It originates in the Pauhunri massif (7127 m). The total length of the mountain section of the river amounts to 182 km. The Teesta is characterized by a complex hydrological regime. The river is fed not only by precipitation, but also by melting glaciers and snow as well as groundwater. The present study describes an attempt to model surface runoff in upper Teesta basin, which is directly related to catastrophic flood events, by creating a system based on GIS technology. The main object was to construct a direct unit hydrograph for an excess rainfall by estimating the stream flow response at the outlet of a watershed. Specifically, the methodology was based on the creation of a spatial database in GIS environment and on data editing. Moreover, rainfall time-series data collected from Indian Meteorological Department and they were processed in order to calculate flow time and the runoff volume. Apart from the meteorological data, background data such as topography, drainage network, land cover and geological data were also collected. Clipping the watershed from the entire area and the streamline generation for Teesta watershed were done and cross-sectional profiles plotted across the river at various locations from Aster DEM data using the ERDAS IMAGINE 9.0 and Arc GIS 10.0 software. The analysis of different hydraulic model to detect flash flood probability ware done using HEC-RAS, Flow-2D, HEC-HMS Software, which were of great importance in order to achieve the final result. With an input rainfall intensity above 400 mm per day for three days the flood runoff simulation models shows outbursts of lakes and check dam individually or in combination with run-off causing severe damage to the downstream settlements. Model output shows that 313 Sq. km area were found to be most vulnerable to flash flood includes Melli, Jourthang, Chungthang, and Lachung and 655sq. km. as moderately vulnerable includes Rangpo,Yathang, Dambung,Bardang, Singtam, Teesta Bazarand Thangu Valley. The model was validated by inserting the rain fall data of a flood event took place in August 1968, and 78% of the actual area flooded reflected in the output of the model. Lastly preventive and curative measures were suggested to reduce the losses by probable flash flood event.

Keywords: flash flood, GIS, runoff, simulation model, Teesta river basin

Procedia PDF Downloads 314

Authors: Mohammad Amjad, Muhammad Iqbal Zafar, Ashfaq Ahmed Maan, Muhammad Tayyab Kashif

Abstract:

Obesity is an abnormal physical condition where an increased and undesirable fat accumulates in the human body. Obesity is an international phenomenon. In the present study, 12 schools were randomly selected from each district considering the areas i.e. Elite Private Schools in the private sector, Government schools in urban areas and Government schools in rural areas. Interviews were conducted with male students studying in grade 5 to grade 9 in each school. The sample size was 600 students; 300 from Faisalabad district and 300 from Rawalpindi district in Pakistan. A well-structured and pre-tested questionnaire was used for data collection. The calibrated scales were used to attain the heights and weights of the respondents. Obesity of school-going children depends on family types, family size, family history, junk food consumption, mother’s education, weekly time spent in walking, and sports facility at school levels. Academic performance, physical health and psychological health of school going children are affected with obesity. Concrete steps and policies could minimize the incidence of obesity in children in Pakistan.

Keywords: body mass index, cardiovascular disease, fast food, morbidity, overweight

Procedia PDF Downloads 178

Authors: S.K. Bhandari, E. Veneklaas, L. McCaw, R. Mazanec, K. Whitford, M. Renton

Abstract:

Eucalyptus marginata, E. diversicolor and Corymbia calophylla form widespread forests in south-west Western Australia (SWWA). These forests have economic and ecological importance, and therefore, tree growth and sustainable management are of high priority. This paper aimed to analyse and model the growth of these species at both stand and individual levels, but this presentation will focus on predicting the growth of E. Marginata at the individual tree level. More specifically, the study wanted to investigate how well individual E. marginata tree growth could be predicted by considering the diameter and height of the tree at the start of the growth period, and whether this prediction could be improved by also accounting for the competition from neighbouring trees in different ways. The study also wanted to investigate how many neighbouring trees or what neighbourhood distance needed to be considered when accounting for competition. To achieve this aim, the Pearson correlation coefficient was examined among competition indices (CIs), between CIs and dbh growth, and selected the competition index that can best predict the diameter growth of individual trees of E. marginata forest managed under different thinning regimes at Inglehope in SWWA. Furthermore, individual tree growth models were developed using simple linear regression, multiple linear regression, and linear mixed effect modelling approaches. Individual tree growth models were developed for thinned and unthinned stand separately. The developed models were validated using two approaches. In the first approach, models were validated using a subset of data that was not used in model fitting. In the second approach, the model of the one growth period was validated with the data of another growth period. Tree size (diameter and height) was a significant predictor of growth. This prediction was improved when the competition was included in the model. The fit statistic (coefficient of determination) of the model ranged from 0.31 to 0.68. The model with spatial competition indices validated as being more accurate than with non-spatial indices. The model prediction can be optimized if 10 to 15 competitors (by number) or competitors within ~10 m (by distance) from the base of the subject tree are included in the model, which can reduce the time and cost of collecting the information about the competitors. As competition from neighbours was a significant predictor with a negative effect on growth, it is recommended including neighbourhood competition when predicting growth and considering thinning treatments to minimize the effect of competition on growth. These model approaches are likely to be useful tools for the conservations and sustainable management of forests of E. marginata in SWWA. As a next step in optimizing the number and distance of competitors, further studies in larger size plots and with a larger number of plots than those used in the present study are recommended.

Keywords: competition, growth, model, thinning

Procedia PDF Downloads 121

Authors: Prashant Shrivastava

Abstract:

The purpose of this study is to explore re3dat.org registry to identify research data repositories registration workflow process. Further objective is to depict a graph for present development of research data repositories in India. Preliminarily with an approach to understand re3data.org registry framework and schema design then further proceed to explore the status of research data repositories of India in re3data.org registry. Research data repositories are getting wider relevance due to e-research concepts. Now available registry re3data.org is a good tool for users and researchers to identify appropriate research data repositories as per their research requirements. In Indian environment, a compatible National Research Data Policy is the need of the time to boost the management of research data. Registry for Research Data Repositories is a crucial tool to discover specific information in specific domain. Also, Research Data Repositories in India have not been studied. Re3data.org registry and status of Indian research data repositories both discussed in this study.

Keywords: research data, research data repositories, research data registry, re3data.org

Procedia PDF Downloads 320

Authors: Ronal Muresano, Andrea Pagano

Abstract:

Nowadays, the mathematical/statistical applications are developed with more complexity and accuracy. However, these precisions and complexities have brought as result that applications need more computational power in order to be executed faster. In this sense, the multicore environments are playing an important role to improve and to optimize the execution time of these applications. These environments allow us the inclusion of more parallelism inside the node. However, to take advantage of this parallelism is not an easy task, because we have to deal with some problems such as: cores communications, data locality, memory sizes (cache and RAM), synchronizations, data dependencies on the model, etc. These issues are becoming more important when we wish to improve the application’s performance and scalability. Hence, this paper describes an optimization method developed for Systemic Model of Banking Originated Losses (SYMBOL) tool developed by the European Commission, which is based on analyzing the application's weakness in order to exploit the advantages of the multicore. All these improvements are done in an automatic and transparent manner with the aim of improving the performance metrics of our tool. Finally, experimental evaluations show the effectiveness of our new optimized version, in which we have achieved a considerable improvement on the execution time. The time has been reduced around 96% for the best case tested, between the original serial version and the automatic parallel version.

Keywords: algorithm optimization, bank failures, OpenMP, parallel techniques, statistical tool

Procedia PDF Downloads 365

Authors: Angela U. Makolo

Abstract:

Protein-coding and Non-coding regions determine the biology of a sequenced transcriptome. Research advances have shown that Non-coding regions are important in disease progression and clinical diagnosis. Existing bioinformatics tools have been targeted towards Protein-coding regions alone. Therefore, there are challenges associated with gaining biological insights from transcriptome sequence data. These tools are also limited to computationally intensive sequence alignment, which is inadequate and less accurate to identify both Protein-coding and Non-coding regions. Alignment-free techniques can overcome the limitation of identifying both regions. Therefore, this study was designed to develop an efficient sequence alignment-free model for identifying both Protein-coding and Non-coding regions in sequenced transcriptomes. Feature grouping and randomization procedures were applied to the input transcriptomes (37,503 data points). Successive iterations were carried out to compute the gradient vector that converged the developed Protein-coding and Non-coding Region Identifier (PNRI) model to the approximate coefficient vector. The logistic regression algorithm was used with a sigmoid activation function. A parameter vector was estimated for every sample in 37,503 data points in a bid to reduce the generalization error and cost. Maximum Likelihood Estimation (MLE) was used for parameter estimation by taking the log-likelihood of six features and combining them into a summation function. Dynamic thresholding was used to classify the Protein-coding and Non-coding regions, and the Receiver Operating Characteristic (ROC) curve was determined. The generalization performance of PNRI was determined in terms of F1 score, accuracy, sensitivity, and specificity. The average generalization performance of PNRI was determined using a benchmark of multi-species organisms. The generalization error for identifying Protein-coding and Non-coding regions decreased from 0.514 to 0.508 and to 0.378, respectively, after three iterations. The cost (difference between the predicted and the actual outcome) also decreased from 1.446 to 0.842 and to 0.718, respectively, for the first, second and third iterations. The iterations terminated at the 390th epoch, having an error of 0.036 and a cost of 0.316. The computed elements of the parameter vector that maximized the objective function were 0.043, 0.519, 0.715, 0.878, 1.157, and 2.575. The PNRI gave an ROC of 0.97, indicating an improved predictive ability. The PNRI identified both Protein-coding and Non-coding regions with an F1 score of 0.970, accuracy (0.969), sensitivity (0.966), and specificity of 0.973. Using 13 non-human multi-species model organisms, the average generalization performance of the traditional method was 74.4%, while that of the developed model was 85.2%, thereby making the developed model better in the identification of Protein-coding and Non-coding regions in transcriptomes. The developed Protein-coding and Non-coding region identifier model efficiently identified the Protein-coding and Non-coding transcriptomic regions. It could be used in genome annotation and in the analysis of transcriptomes.

Keywords: sequence alignment-free model, dynamic thresholding classification, input randomization, genome annotation

Procedia PDF Downloads 64

Authors: Wanwadee Neamsakul

Abstract:

VARK learning style is an effective method of learning that could enhance all skills of the students like visual (V), auditory (A), read/write (R), and kinesthetic (K). This learning style benefits the students in terms of professional competencies, critical thinking and lifelong learning which are the desirable characteristics of the nursing students. This study aimed to develop a model of teaching and learning clinical practicum at postpartum ward for nursing students by using VARK learning styles, and evaluate the nursing students’ opinions about the developmental model. A methodology used for this study was research and development (R&D). The model was developed by focus group discussion with five obstetric nursing instructors who have experiences teaching Maternal Newborn and Midwifery I subject. The activities related to practices in the postpartum (PP) ward including all skills of VARK were assigned into the matrix table. The researcher asked the experts to supervise the model and adjusted the model following the supervision. Subsequently, it was brought to be tried out with the nursing students who practiced on the PP ward. Thirty third year nursing students from one of the northern Nursing Colleges, Academic year 2015 were purposive sampling. The opinions about the satisfaction of the model were collected using a questionnaire which was tested for its validity and reliability. Data were analyzed using descriptive statistics. The developed model composed of 27 activities. Seven activities were developed as enhancement of visual skills for the nursing students (25.93%), five activities as auditory skills (18.52%), six activities as read and write skills (22.22%), and nine activities as kinesthetic skills (33.33%). Overall opinions about the model were reported at the highest level of average satisfaction (mean=4.63, S.D=0.45). In the aspects of visual skill (mean=4.80, S.D=0.45) was reported at the highest level of average satisfaction followed by auditory skill (mean=4.62, S.D=0.43), read and write skill (mean=4.57, S.D=0.46), and kinesthetic skill (mean=4.53, S.D=0.45) which were reported at the highest level of average satisfaction, respectively. The nursing students reported that the model could help them employ all of their skills during practicing and taking care of the postpartum women and newborn babies. They could establish self-confidence while providing care and felt proud of themselves by the benefits of the model. It can be said that using VARK learning style to develop the model could enhance both nursing students’ competencies and positive attitude towards the nursing profession. Consequently, they could provide quality care for postpartum women and newborn babies effectively in the long run.

Keywords: model, nursing students, postpartum ward, teaching and learning clinical practicum

Procedia PDF Downloads 146

Authors: Jamal Al-Zain, O. El Hajjaji, T. El Bardouni

Abstract:

A (Th-U) O2 fuel pin benchmark made up of 25 w/o U and 75 w/o Th was used. In order to analyze the depletion and inventory of the fuel for the pressurized water reactor pin-cell model. The new version VIII.0 of the ENDF/B nuclear data library was used to create a data set in ACE format at various temperatures and process the data using the MAKXSF6.2 and NJOY2016 programs to process the data at the various temperatures in order to conduct this study and analyze cross-section data. The infinite multiplication factor, the concentrations and activities of the main fission products, the actinide radionuclides accumulated in the pin cell, and the total radioactivity were all estimated and compared in this study using the Monte Carlo N-Particle 6 (MCNP6.2) and DRAGON5 programs. Additionally, the behavior of the Pressurized Water Reactor (PWR) thorium pin cell that is dependent on burn-up (BU) was validated and compared with the reference data obtained using the Massachusetts Institute of Technology (MIT-MOCUP), Idaho National Engineering and Environmental Laboratory (INEEL-MOCUP), and CASMO-4 codes. The results of this study indicate that all of the codes examined have good agreements.

Keywords: PWR thorium pin cell, ENDF/B-VIII.0, MAKXSF6.2, NJOY2016, MCNP6.2, DRAGON5, fuel burn-up.

Procedia PDF Downloads 96

Authors: Ilgin Gökaşar, Saman Ghaffarian

Abstract:

The need for fast processed big data of transportation ridership (eg., smartcard data) and traffic operation (e.g., traffic detectors data) which requires a lot of computational power is incontrovertible in Intelligent Transportation Systems. Nowadays cloud computing is one of the important subjects and popular information technology solution for data processing. It enables users to process enormous measure of data without having their own particular computing power. Thus, it can also be a good selection for transportation big data processing as well. This paper intends to examine how the cloud computing can enhance transportation big data process with contrasting its advantages and disadvantages, and discussing cloud computing features.

Keywords: big data, cloud computing, Intelligent Transportation Systems, ITS, traffic data processing

Procedia PDF Downloads 461

Authors: Ha Phuong Tran, Feng Wang, Jo Dewulf, Hai Trung Huynh, Thomas Schaubroeck

Abstract:

The fast increase and complex components have made waste of electrical and electronic equipment (or e-waste) one of the most problematic waste streams worldwide. Precise information on its size on national, regional and global level has therefore been highlighted as prerequisite to obtain a proper management system. However, this is a very challenging task, especially in developing countries where both formal e-waste management system and necessary statistical data for e-waste estimation, i.e. data on the production, sale and trade of electrical and electronic equipment (EEE), are often lacking. Moreover, there is an inflow of non-registered electronic and electric equipment, which ‘invisibly’ enters the EEE domestic market and then is used for domestic consumption. The non-registration/invisibility and (in most of the case) illicit nature of this flow make it difficult or even impossible to be captured in any statistical system. The e-waste generated from it is thus often uncounted in current e-waste estimation based on statistical market data. Therefore, this study focuses on enhancing e-waste estimation in developing countries and proposing a calculation pathway to quantify the magnitude of the non-registered EEE inflow. An advanced Input-Out Analysis model (i.e. the Sale–Stock–Lifespan model) has been integrated in the calculation procedure. In general, Sale-Stock-Lifespan model assists to improve the quality of input data for modeling (i.e. perform data consolidation to create more accurate lifespan profile, model dynamic lifespan to take into account its changes over time), via which the quality of e-waste estimation can be improved. To demonstrate the above objectives, a case study on televisions (TVs) in Vietnam has been employed. The results show that the amount of waste TVs in Vietnam has increased four times since 2000 till now. This upward trend is expected to continue in the future. In 2035, a total of 9.51 million TVs are predicted to be discarded. Moreover, estimation of non-registered TV inflow shows that it might on average contribute about 15% to the total TVs sold on the Vietnamese market during the whole period of 2002 to 2013. To tackle potential uncertainties associated with estimation models and input data, sensitivity analysis has been applied. The results show that both estimations of waste and non-registered inflow depend on two parameters i.e. number of TVs used in household and the lifespan. Particularly, with a 1% increase in the TV in-use rate, the average market share of non-register inflow in the period 2002-2013 increases 0.95%. However, it decreases from 27% to 15% when the constant unadjusted lifespan is replaced by the dynamic adjusted lifespan. The effect of these two parameters on the amount of waste TV generation for each year is more complex and non-linear over time. To conclude, despite of remaining uncertainty, this study is the first attempt to apply the Sale-Stock-Lifespan model to improve the e-waste estimation in developing countries and to quantify the non-registered EEE inflow to domestic consumption. It therefore can be further improved in future with more knowledge and data.

Keywords: e-waste, non-registered electrical and electronic equipment, TVs, Vietnam

Procedia PDF Downloads 244

Authors: Akshay Paranjape, Nils Plettenberg, Robert Schmitt

Abstract:

Producing faulty products can be costly for manufacturing companies and wastes resources. To reduce scrap rates in manufacturing, process parameters can be optimized using machine learning. Thus far, research mainly focused on optimizing specific processes using traditional algorithms. To develop a framework that enables real-time optimization based on a predictive model for an arbitrary production process, this study explores the application of reinforcement learning (RL) in this field. Based on a thorough review of literature about RL and process parameter optimization, a model based on maximum a posteriori policy optimization that can handle both numerical and categorical parameters is proposed. A case study compares the model to state–of–the–art traditional algorithms and shows that RL can find optima of similar quality while requiring significantly less time. These results are confirmed in a large-scale validation study on data sets from both production and other fields. Finally, multiple ways to improve the model are discussed.

Keywords: reinforcement learning, production process optimization, evolutionary algorithms, policy optimization, actor critic approach

Procedia PDF Downloads 92

Authors: Wenqi Liu, Reginald Bailey

Abstract:

This study explores an advanced approach to enhancing B2B sales forecasting by integrating machine learning models with a rule-based decision framework. The methodology begins with the development of a machine learning classification model to predict conversion likelihood, aiming to improve accuracy over traditional methods like logistic regression. The classification model's effectiveness is measured using metrics such as accuracy, precision, recall, and F1 score, alongside a feature importance analysis to identify key predictors. Following this, a machine learning regression model is used to forecast sales value, with the objective of reducing mean absolute error (MAE) compared to linear regression techniques. The regression model's performance is assessed using MAE, root mean square error (RMSE), and R-squared metrics, emphasizing feature contribution to the prediction. To bridge the gap between predictive analytics and decision-making, a rule-based decision model is introduced that prioritizes customers based on predefined thresholds for conversion probability and predicted sales value. This approach significantly enhances customer prioritization and improves overall sales performance by increasing conversion rates and optimizing revenue generation. The findings suggest that this combined framework offers a practical, data-driven solution for sales teams, facilitating more strategic decision-making in B2B environments.

Keywords: sales forecasting, machine learning, rule-based decision model, customer prioritization, predictive analytics

Procedia PDF Downloads 5

Authors: Sean Paulsen, Michael Casey

Abstract:

In this work we present a self-supervised pretraining framework for transformers on functional Magnetic Resonance Imaging (fMRI) data. First, we pretrain our architecture on two self-supervised tasks simultaneously to teach the model a general understanding of the temporal and spatial dynamics of human auditory cortex during music listening. Our pretraining results are the first to suggest a synergistic effect of multitask training on fMRI data. Second, we finetune the pretrained models and train additional fresh models on a supervised fMRI classification task. We observe significantly improved accuracy on held-out runs with the finetuned models, which demonstrates the ability of our pretraining tasks to facilitate transfer learning. This work contributes to the growing body of literature on transformer architectures for pretraining and transfer learning with fMRI data, and serves as a proof of concept for our pretraining tasks and multitask pretraining on fMRI data.

Keywords: transfer learning, fMRI, self-supervised, brain decoding, transformer, multitask training

Procedia PDF Downloads 87

Authors: Ksheeraj Sai Vepuri, Nada Attar

Abstract:

We as humans use words with accompanying visual and facial cues to communicate effectively. Classifying facial emotion using computer vision methodologies has been an active research area in the computer vision field. In this paper, we propose a simple method for facial expression recognition that enhances accuracy. We tested our method on the FER-2013 dataset that contains static images. Instead of using Histogram equalization to preprocess the dataset, we used Unsharp Mask to emphasize texture and details and sharpened the edges. We also used ImageDataGenerator from Keras library for data augmentation. Then we used Convolutional Neural Networks (CNN) model to classify the images into 7 different facial expressions, yielding an accuracy of 69.46% on the test set. Our results show that using image preprocessing such as the sharpening technique for a CNN model can improve the performance, even when the CNN model is relatively simple.

Keywords: facial expression recognittion, image preprocessing, deep learning, CNN

Procedia PDF Downloads 139

Authors: Asaiel Alohaly

Abstract:

A theoretical framework for corporate governance is needed to bridge the gap between the corporate governance of private companies and State-owned Enterprises (SOEs). The two dominant models, being shareholder and stakeholder, do not always address the specific requirements and challenges posed by ‘hybrid’ companies; namely, previously national bodies that have been privatised bffu t where the government retains significant control or holds a majority of shareholders. Thus, an exploratory theoretical study is needed to identify how ‘hybrid’ companies should be defined and why the state model should be acknowledged since it is the less conspicuous model in comparison with the shareholder and stakeholder models. This research focuses on ‘the state model of corporate governance to understand the complex ownership, control pattern, goals, and corporate governance of these hybrid companies. The significance of this research lies in the fact that there is a limited available publication on the state model. The outcomes of this research are as follows. It became evident that the state model exists in the ecosystem. However, corporate governance theories have not extensively covered this model. Though, there is a lot being said about it by OECD and the World Bank. In response to this gap between theories and industry practice, this research argues for the state model, which proceeds from an understanding of the institutionally embedded character of hybrid companies where the government is either a majority of the total shares or a controlling shareholder.

Keywords: corporate governance, control, shareholders, state model

Procedia PDF Downloads 138

Authors: Ch. Sridevi, S. P. Shailender Kumar, B. Gurudayal, A. Chalapathi Rao, K. Koteswara Rao, P. Srinivasulu

Abstract:

System reliability and system availability evaluation plays a crucial role in ensuring the seamless operation of complex satellite data reception system with consistent performance for longer periods. This paper presents a novel approach for the same using a case study on one of the antenna systems at satellite data reception ground station in India. The methodology involves analyzing system's components, their failure rates, system's architecture, generation of logical reliability block diagram model and estimating the reliability of the system using the component level mean time between failures considering exponential distribution to derive a baseline estimate of the system's reliability. The model is then validated with collected system level field failure data from the operational satellite data reception systems that includes failure occurred, failure time, criticality of the failure and repair times by using statistical techniques like median rank, regression and Weibull analysis to extract meaningful insights regarding failure patterns and practical reliability of the system and to assess the accuracy of the developed reliability model. The study mainly focused on identification of critical units within the system, which are prone to failures and have a significant impact on overall performance and brought out a reliability model of the identified critical unit. This model takes into account the interdependencies among system components and their impact on overall system reliability and provides valuable insights into the performance of the system to understand the Improvement or degradation of the system over a period of time and will be the vital input to arrive at the optimized design for future development. It also provides a plug and play framework to understand the effect on performance of the system in case of any up gradations or new designs of the unit. It helps in effective planning and formulating contingency plans to address potential system failures, ensuring the continuity of operations. Furthermore, to instill confidence in system users, the duration for which the system can operate continuously with the desired level of 3 sigma reliability was estimated that turned out to be a vital input to maintenance plan. System availability and station availability was also assessed by considering scenarios of clash and non-clash to determine the overall system performance and potential bottlenecks. Overall, this paper establishes a comprehensive methodology for reliability and availability analysis of complex satellite data reception systems. The results derived from this approach facilitate effective planning contingency measures, and provide users with confidence in system performance and enables decision-makers to make informed choices about system maintenance, upgrades and replacements. It also aids in identifying critical units and assessing system availability in various scenarios and helps in minimizing downtime and optimizing resource allocation.

Keywords: exponential distribution, reliability modeling, reliability block diagram, satellite data reception system, system availability, weibull analysis

Procedia PDF Downloads 82

Authors: Charles Lee

Abstract:

The Principal Orthogonal Decomposition (POD) technique has been used as a model reduction tool for many applications in engineering and science. In principle, one begins with an ensemble of data, called snapshots, collected from an experiment or laboratory results. The beauty of the POD technique is that when applied, the entire data set can be represented by the smallest number of orthogonal basis elements. It is the such capability that allows us to reduce the complexity and dimensions of many physical applications. Mathematical formulations and numerical schemes for the POD method will be discussed along with applications in NASA’s Deep Space Large Antenna Arrays, Satellite Image Reconstruction, Cancer Detection with DNA Microarray Data, Maximizing Stock Return, and Medical Imaging.

Keywords: reduced-order methods, principal component analysis, cancer detection, image reconstruction, stock portfolios

Procedia PDF Downloads 79

Authors: Kehinde Peter Oyeduntan, Kayode Oshinubi

Abstract:

Nigeria is referred as the ‘Giant of Africa’ due to high population, land mass and large economy. However, it still trails far behind many smaller economies in the continent in terms of maritime operations. As we have seen that the maritime industry is the spark plug for national growth, because it houses the most crucial infrastructure that generates wealth for a nation, it is worrisome that a nation with six seaports lag in maritime activities. In this research, we have studied how the Gross Domestic Product (GDP) of the maritime transport influences the Nigerian economy. To do this, we applied Simple Linear Regression (SLR), Support Vector Machine (SVM), Polynomial Regression Model (PRM), Generalized Additive Model (GAM) and Generalized Linear Mixed Model (GLMM) to model the relationship between the nation’s Total GDP (TGDP) and the Maritime Transport GDP (MGDP) using a time series data of 20 years. The result showed that the MGDP is statistically significant to the Nigerian economy. Amongst the statistical tool applied, the PRM of order 4 describes the relationship better when compared to other methods. The recommendations presented in this study will guide policy makers and help improve the economy of Nigeria in terms of its GDP.

Keywords: maritime transport, economy, GDP, regression, port

Procedia PDF Downloads 150

Authors: Ali Asheibi

Abstract:

The rapid increase in the size of databases required to store power quality monitoring data has demanded new techniques for analysing and understanding the data. One suggested technique to assist in analysis is data mining. Preparing raw data to be ready for data mining exploration take up most of the effort and time spent in the whole data mining process. Clustering is an important technique in data mining and machine learning in which underlying and meaningful groups of data are discovered. Large amounts of harmonic data have been collected from an actual harmonic monitoring system in a distribution system in Australia for three years. This amount of acquired data makes it difficult to identify operational events that significantly impact the harmonics generated on the system. In this paper, harmonic data preparation processes to better understanding of the data have been presented. Underlying classes in this data has then been identified using clustering technique based on the Minimum Message Length (MML) method. The underlying operational information contained within the clusters can be rapidly visualised by the engineers. The C5.0 algorithm was used for classification and interpretation of the generated clusters.

Keywords: data mining, harmonic data, clustering, classification

Procedia PDF Downloads 242

Authors: Kunyanuth Kularbphettong, Cholticha Tongsiri

Abstract:

This paper aims to create the model for student in choosing an emphasized track of student majoring in computer science at Suan Sunandha Rajabhat University. The objective of this research is to develop the suggested system using data mining technique to analyze knowledge and conduct decision rules. Such relationships can be used to demonstrate the reasonableness of student choosing a track as well as to support his/her decision and the system is verified by experts in the field. The sampling is from student of computer science based on the system and the questionnaire to see the satisfaction. The system result is found to be satisfactory by both experts and student as well.

Keywords: data mining technique, the decision support system, knowledge and decision rules, education

Procedia PDF Downloads 420

Authors: E. Y. Igde, S. Aydogan, F. E. Boran, D. Akay

Abstract:

Patent data have an increasingly important role in economic growth, innovation, technical advantages and business strategies and even in countries competitions. Analyzing of patent data is crucial since patents cover large part of all technological information of the world. In this paper, we have used the linguistic summarization technique to prove the validity of the hypotheses related to patent data stated in the literature.

Keywords: data mining, fuzzy sets, linguistic summarization, patent data

Procedia PDF Downloads 267

Authors: Bin Wang, Hengyu Ji, Zhifeng Ye

Abstract:

Fuel Metering Unit (FMU) in fuel system of an aeroengine sometimes has direct influence on the engine performance, which is neglected for the sake of easy access to mathematical model of the engine in most cases. In order to verify the influence of FMU on an engine model, this paper presents a co-simulation of a stepping motor driven FMU (digital FMU) in a turboshaft aeroengine, using AMESim and MATLAB to obtain the steady and dynamic characteristics of the FMU. For this method, mechanical and hydraulic section of the unit is modeled through AMESim, while the stepping motor is mathematically modeled through MATLAB/Simulink. Combining these two sub-models yields an AMESim/MATLAB co-model of the FMU. A simplified component level model for the turboshaft engine is established and connected with the FMU model. Simulation results on the full model show that the engine model considering FMU characteristics describes the engine more precisely especially in its transition state. An FMU dynamics will cut down the rotation speed of the high pressure shaft and the inlet pressure of the combustor during the step response. The work in this paper reveals the impact of FMU on engine operation characteristics and provides a reference to an engine model for ground tests.

Keywords: fuel metering unit, stepping motor, AMESim/Matlab, full digital simulation

Procedia PDF Downloads 242

Authors: Hsiang-Yu Yuan, Marc Baguelin, Kin O. Kwok, Nimalan Arinaminpathy, Edwin Leeuwen, Steven Riley

Abstract:

Traditional syndromic surveillance for influenza has substantial public health value in characterizing epidemics. Because the relationship between syndromic incidence and the true infection events can vary from one population to another and from one year to another, recent studies rely on combining serological test results with syndromic data from traditional surveillance into epidemic models to make inference on epidemiological processes of influenza. However, despite the widespread availability of serological data, epidemic models have thus far not explicitly represented antibody titre levels and their correspondence with immunity. Most studies use dichotomized data with a threshold (Typically, a titre of 1:40 was used) to define individuals as likely recently infected and likely immune and further estimate the cumulative incidence. Underestimation of Influenza attack rate could be resulted from the dichotomized data. In order to improve the use of serosurveillance data, here, a refinement of the concept of the stratified immunity within an epidemic model for influenza transmission was proposed, such that all individual antibody titre levels were enumerated explicitly and mapped onto a variable scale of susceptibility in different age groups. Haemagglutination inhibition titres from 523 individuals and 465 individuals during pre- and post-pandemic phase of the 2009 pandemic in Hong Kong were collected. The model was fitted to serological data in age-structured population using Bayesian framework and was able to reproduce key features of the epidemics. The effects of age-specific antibody boosting and protection were explored in greater detail. RB was defined to be the effective reproductive number in the presence of stratified immunity and its temporal dynamics was compared to the traditional epidemic model using use dichotomized seropositivity data. Deviance Information Criterion (DIC) was used to measure the fitness of the model to serological data with different mechanisms of the serological response. The results demonstrated that the differential antibody response with age was present (ΔDIC = -7.0). The age-specific mixing patterns with children specific transmissibility, rather than pre-existing immunity, was most likely to explain the high serological attack rates in children and low serological attack rates in elderly (ΔDIC = -38.5). Our results suggested that the disease dynamics and herd immunity of a population could be described more accurately for influenza when the distribution of immunity was explicitly represented, rather than relying only on the dichotomous states 'susceptible' and 'immune' defined by the threshold titre (1:40) (ΔDIC = -11.5). During the outbreak, RB declined slowly from 1.22[1.16-1.28] in the first four months after 1st May. RB dropped rapidly below to 1 during September and October, which was consistent to the observed epidemic peak time in the late September. One of the most important challenges for infectious disease control is to monitor disease transmissibility in real time with statistics such as the effective reproduction number. Once early estimates of antibody boosting and protection are obtained, disease dynamics can be reconstructed, which are valuable for infectious disease prevention and control.

Keywords: effective reproductive number, epidemic model, influenza epidemic dynamics, stratified immunity

Procedia PDF Downloads 259

Authors: M. Kebisek, L. Spendla, M. Kopcek, T. Skulavik

Abstract:

In our paper we describe the security capabilities of data collection. Data are collected with probes located in the near and distant surroundings of the company. Considering the numerous obstacles e.g. forests, hills, urban areas, the data collection is realized in several ways. The collection of data uses connection via wireless communication, LAN network, GSM network and in certain areas data are collected by using vehicles. In order to ensure the connection to the server most of the probes have ability to communicate in several ways. Collected data are archived and subsequently used in supervisory applications. To ensure the collection of the required data, it is necessary to propose algorithms that will allow the probes to select suitable communication channel.

Keywords: communication, computer network, data collection, probe

Procedia PDF Downloads 358

Authors: Lunliang Zhong, Bin Duan

Abstract:

The undergraduate graduation project is a vital part of the higher education curriculum, crucial for engineering accreditation. Current evaluations often summarize data without identifying underlying issues. This study applies the Peter-Clark algorithm to analyze causal relationships within the graduation project data of an Electronics and Information Engineering program, creating a causal model. Structural equation modeling confirmed the model's validity. The analysis reveals key teaching stages affecting project success, uncovering problems in the process. Introducing causal discovery and inference into project evaluation helps identify issues and propose targeted improvement measures. The effectiveness of these measures is validated by comparing the learning outcomes of two student cohorts, stratified by confounding factors, leading to improved teaching quality.

Keywords: causal discovery, causal inference, continuous improvement, Peter-Clark algorithm, structural equation modeling

Procedia PDF Downloads 12