Search results for: vector error correction model
16677 Design of a Small and Medium Enterprise Growth Prediction Model Based on Web Mining
Authors: Yiea Funk Te, Daniel Mueller, Irena Pletikosa Cvijikj
Abstract:
Small and medium enterprises (SMEs) play an important role in the economy of many countries. When the overall world economy is considered, SMEs represent 95% of all businesses in the world, accounting for 66% of the total employment. Existing studies show that the current business environment is characterized as highly turbulent and strongly influenced by modern information and communication technologies, thus forcing SMEs to experience more severe challenges in maintaining their existence and expanding their business. To support SMEs at improving their competitiveness, researchers recently turned their focus on applying data mining techniques to build risk and growth prediction models. However, data used to assess risk and growth indicators is primarily obtained via questionnaires, which is very laborious and time-consuming, or is provided by financial institutes, thus highly sensitive to privacy issues. Recently, web mining (WM) has emerged as a new approach towards obtaining valuable insights in the business world. WM enables automatic and large scale collection and analysis of potentially valuable data from various online platforms, including companies’ websites. While WM methods have been frequently studied to anticipate growth of sales volume for e-commerce platforms, their application for assessment of SME risk and growth indicators is still scarce. Considering that a vast proportion of SMEs own a website, WM bears a great potential in revealing valuable information hidden in SME websites, which can further be used to understand SME risk and growth indicators, as well as to enhance current SME risk and growth prediction models. This study aims at developing an automated system to collect business-relevant data from the Web and predict future growth trends of SMEs by means of WM and data mining techniques. The envisioned system should serve as an 'early recognition system' for future growth opportunities. In an initial step, we examine how structured and semi-structured Web data in governmental or SME websites can be used to explain the success of SMEs. WM methods are applied to extract Web data in a form of additional input features for the growth prediction model. The data on SMEs provided by a large Swiss insurance company is used as ground truth data (i.e. growth-labeled data) to train the growth prediction model. Different machine learning classification algorithms such as the Support Vector Machine, Random Forest and Artificial Neural Network are applied and compared, with the goal to optimize the prediction performance. The results are compared to those from previous studies, in order to assess the contribution of growth indicators retrieved from the Web for increasing the predictive power of the model.Keywords: data mining, SME growth, success factors, web mining
Procedia PDF Downloads 25816676 Fraud Detection in Credit Cards with Machine Learning
Authors: Anjali Chouksey, Riya Nimje, Jahanvi Saraf
Abstract:
Online transactions have increased dramatically in this new ‘social-distancing’ era. With online transactions, Fraud in online payments has also increased significantly. Frauds are a significant problem in various industries like insurance companies, baking, etc. These frauds include leaking sensitive information related to the credit card, which can be easily misused. Due to the government also pushing online transactions, E-commerce is on a boom. But due to increasing frauds in online payments, these E-commerce industries are suffering a great loss of trust from their customers. These companies are finding credit card fraud to be a big problem. People have started using online payment options and thus are becoming easy targets of credit card fraud. In this research paper, we will be discussing machine learning algorithms. We have used a decision tree, XGBOOST, k-nearest neighbour, logistic-regression, random forest, and SVM on a dataset in which there are transactions done online mode using credit cards. We will test all these algorithms for detecting fraud cases using the confusion matrix, F1 score, and calculating the accuracy score for each model to identify which algorithm can be used in detecting frauds.Keywords: machine learning, fraud detection, artificial intelligence, decision tree, k nearest neighbour, random forest, XGBOOST, logistic regression, support vector machine
Procedia PDF Downloads 13816675 Evaluation of Three Digital Graphical Methods of Baseflow Separation Techniques in the Tekeze Water Basin in Ethiopia
Authors: Alebachew Halefom, Navsal Kumar, Arunava Poddar
Abstract:
The purpose of this work is to specify the parameter values, the base flow index (BFI), and to rank the methods that should be used for base flow separation. Three different digital graphical approaches are chosen and used in this study for the purpose of comparison. The daily time series discharge data were collected from the site for a period of 30 years (1986 up to 2015) and were used to evaluate the algorithms. In order to separate the base flow and the surface runoff, daily recorded streamflow (m³/s) data were used to calibrate procedures and get parameter values for the basin. Additionally, the performance of the model was assessed by the use of the standard error (SE), the coefficient of determination (R²), and the flow duration curve (FDC) and baseflow indexes. The findings indicate that, in general, each strategy can be used worldwide to differentiate base flow; however, the Sliding Interval Method (SIM) performs significantly better than the other two techniques in this basin. The average base flow index was calculated to be 0.72 using the local minimum method, 0.76 using the fixed interval method, and 0.78 using the sliding interval method, respectively.Keywords: baseflow index, digital graphical methods, streamflow, Emba Madre Watershed
Procedia PDF Downloads 7016674 Generating Music with More Refined Emotions
Authors: Shao-Di Feng, Von-Wun Soo
Abstract:
To generate symbolic music with specific emotions is a challenging task due to symbolic music datasets that have emotion labels are scarce and incomplete. This research aims to generate more refined emotions based on the training datasets that are only labeled with four quadrants in Russel’s 2D emotion model. We focus on the theory of Music Fadernet and map arousal and valence to the low-level attributes, and build a symbolic music generation model by combining transformer and GM-VAE. We adopt an in-attention mechanism for the model and improve it by allowing modulation by conditional information. And we show the music generation model could control the generation of music according to the emotions specified by users in terms of high-level linguistic expression and by manipulating their corresponding low-level musical attributes. Finally, we evaluate the model performance using a pre-trained emotion classifier against a pop piano midi dataset called EMOPIA, and by subjective listening evaluation, we demonstrate that the model could generate music with more refined emotions correctly.Keywords: music generation, music emotion controlling, deep learning, semi-supervised learning
Procedia PDF Downloads 7916673 Life Time Improvement of Clamp Structural by Using Fatigue Analysis
Authors: Pisut Boonkaew, Jatuporn Thongsri
Abstract:
In hard disk drive manufacturing industry, the process of reducing an unnecessary part and qualifying the quality of part before assembling is important. Thus, clamp was designed and fabricated as a fixture for holding in testing process. Basically, testing by trial and error consumes a long time to improve. Consequently, the simulation was brought to improve the part and reduce the time taken. The problem is the present clamp has a low life expectancy because of the critical stress that occurred. Hence, the simulation was brought to study the behavior of stress and compressive force to improve the clamp expectancy with all probability of designs which are present up to 27 designs, which excluding the repeated designs. The probability was calculated followed by the full fractional rules of six sigma methodology which was provided correctly. The six sigma methodology is a well-structured method for improving quality level by detecting and reducing the variability of the process. Therefore, the defective will be decreased while the process capability increasing. This research focuses on the methodology of stress and fatigue reduction while compressive force still remains in the acceptable range that has been set by the company. In the simulation, ANSYS simulates the 3D CAD with the same condition during the experiment. Then the force at each distance started from 0.01 to 0.1 mm will be recorded. The setting in ANSYS was verified by mesh convergence methodology and compared the percentage error with the experimental result; the error must not exceed the acceptable range. Therefore, the improved process focuses on degree, radius, and length that will reduce stress and still remain in the acceptable force number. Therefore, the fatigue analysis will be brought as the next process in order to guarantee that the lifetime will be extended by simulating through ANSYS simulation program. Not only to simulate it, but also to confirm the setting by comparing with the actual clamp in order to observe the different of fatigue between both designs. This brings the life time improvement up to 57% compared with the actual clamp in the manufacturing. This study provides a precise and trustable setting enough to be set as a reference methodology for the future design. Because of the combination and adaptation from the six sigma method, finite element, fatigue and linear regressive analysis that lead to accurate calculation, this project will able to save up to 60 million dollars annually.Keywords: clamp, finite element analysis, structural, six sigma, linear regressive analysis, fatigue analysis, probability
Procedia PDF Downloads 23216672 Electrodynamic Principles for Generation and Wireless Transfer of Energy
Authors: Steven D. P. Moore
Abstract:
An electrical discharge in the air induces an electromagnetic (EM) wave capable of wireless transfer, reception, and conversion back into electrical discharge at a distant location. Following Norton’s ground wave principles, EM wave radiation (EMR) runs parallel to the Earth’s surface. Energy in an EMR wave can move through the air and be focused to create a spark at a distant location, focused by a receiver to generate a local electrical discharge. This local discharge can be amplified and stored but also has the propensity to initiate another EMR wave. In addition to typical EM waves, lightning is also associated with atmospheric events, trans-ionospheric pulse pairs, the most powerful natural EMR signal on the planet. With each lightning strike, regardless of global position, it generates naturally occurring pulse-pairs that are emitted towards space within a narrow cone. An EMR wave can self-propagate, travel at the speed of light, and, if polarized, contain vector properties. If this reflective pulse could be directed by design through structures that have increased probabilities for lighting strikes, it could theoretically travel near the surface of the Earth at light speed towards a selected receiver for local transformation into electrical energy. Through research, there are several influencing parameters that could be modified to model, test, and increase the potential for adopting this technology towards the goal of developing a global grid that utilizes natural sources of energy.Keywords: electricity, sparkgap, wireless, electromagnetic
Procedia PDF Downloads 18216671 Active Flutter Suppression of Sports Aircraft Tailplane by Supplementary Control Surface
Authors: Aleš Kratochvíl, Svatomír Slavík
Abstract:
The paper presents an aircraft flutter suppression by active damping of supplementary control surface at trailing edge. The mathematical model of thin oscillation airfoil with control surface driven by pilot is developed. The supplementary control surface driven by control law is added. Active damping of flutter by several control law is present. The structural model of tailplane with an aerodynamic strip theory based on the airfoil model is developed by a finite element method. The optimization process of stiffens parameters is carried out to match the structural model with results from a ground vibration test of a small sport airplane. The implementation of supplementary control surface driven by control law is present. The active damping of tailplane model is shown.Keywords: active damping, finite element method, flutter, tailplane model
Procedia PDF Downloads 28716670 Generic Model for Timetabling Problems by Integer Linear Programmimg Approach
Authors: Nur Aidya Hanum Aizam, Vikneswary Uvaraja
Abstract:
The agenda of showing the scheduled time for performing certain tasks is known as timetabling. It widely used in many departments such as transportation, education, and production. Some difficulties arise to ensure all tasks happen in the time and place allocated. Therefore, many researchers invented various programming model to solve the scheduling problems from several fields. However, the studies in developing the general integer programming model for many timetabling problems are still questionable. Meanwhile, this thesis describe about creating a general model which solve different types of timetabling problems by considering the basic constraints. Initially, the common basic constraints from five different fields are selected and analyzed. A general basic integer programming model was created and then verified by using the medium set of data obtained randomly which is much similar to realistic data. The mathematical software, AIMMS with CPLEX as a solver has been used to solve the model. The model obtained is significant in solving many timetabling problems easily since it is modifiable to all types of scheduling problems which have same basic constraints.Keywords: AIMMS mathematical software, integer linear programming, scheduling problems, timetabling
Procedia PDF Downloads 42816669 Integrating Knowledge Distillation of Multiple Strategies
Authors: Min Jindong, Wang Mingxia
Abstract:
With the widespread use of artificial intelligence in life, computer vision, especially deep convolutional neural network models, has developed rapidly. With the increase of the complexity of the real visual target detection task and the improvement of the recognition accuracy, the target detection network model is also very large. The huge deep neural network model is not conducive to deployment on edge devices with limited resources, and the timeliness of network model inference is poor. In this paper, knowledge distillation is used to compress the huge and complex deep neural network model, and the knowledge contained in the complex network model is comprehensively transferred to another lightweight network model. Different from traditional knowledge distillation methods, we propose a novel knowledge distillation that incorporates multi-faceted features, called M-KD. In this paper, when training and optimizing the deep neural network model for target detection, the knowledge of the soft target output of the teacher network in knowledge distillation, the relationship between the layers of the teacher network and the feature attention map of the hidden layer of the teacher network are transferred to the student network as all knowledge. in the model. At the same time, we also introduce an intermediate transition layer, that is, an intermediate guidance layer, between the teacher network and the student network to make up for the huge difference between the teacher network and the student network. Finally, this paper adds an exploration module to the traditional knowledge distillation teacher-student network model. The student network model not only inherits the knowledge of the teacher network but also explores some new knowledge and characteristics. Comprehensive experiments in this paper using different distillation parameter configurations across multiple datasets and convolutional neural network models demonstrate that our proposed new network model achieves substantial improvements in speed and accuracy performance.Keywords: object detection, knowledge distillation, convolutional network, model compression
Procedia PDF Downloads 27016668 Effects of Research-Based Blended Learning Model Using Adaptive Scaffolding to Enhance Graduate Students' Research Competency and Analytical Thinking Skills
Authors: Panita Wannapiroon, Prachyanun Nilsook
Abstract:
This paper is a report on the findings of a Research and Development (R&D) aiming to develop the model of Research-Based Blended Learning Model Using Adaptive Scaffolding (RBBL-AS) to enhance graduate students’ research competency and analytical thinking skills, to study the result of using such model. The sample consisted of 10 experts in the fields during the model developing stage, while there were 23 graduate students of KMUTNB for the RBBL-AS model try out stage. The research procedures included 4 phases: 1) literature review, 2) model development, 3) model experiment, and 4) model revision and confirmation. The research results were divided into 3 parts according to the procedures as described in the following session. First, the data gathering from the literature review were reported as a draft model; followed by the research finding from the experts’ interviews indicated that the model should be included 8 components to enhance graduate students’ research competency and analytical thinking skills. The 8 components were 1) cloud learning environment, 2) Ubiquitous Cloud Learning Management System (UCLMS), 3) learning courseware, 4) learning resources, 5) adaptive Scaffolding, 6) communication and collaboration tolls, 7) learning assessment, and 8) research-based blended learning activity. Second, the research finding from the experimental stage found that there were statistically significant difference of the research competency and analytical thinking skills posttest scores over the pretest scores at the .05 level. The Graduate students agreed that learning with the RBBL-AS model was at a high level of satisfaction. Third, according to the finding from the experimental stage and the comments from the experts, the developed model was revised and proposed in the report for further implication and references.Keywords: research based learning, blended learning, adaptive scaffolding, research competency, analytical thinking skills
Procedia PDF Downloads 41316667 Rapid Building Detection in Population-Dense Regions with Overfitted Machine Learning Models
Authors: V. Mantey, N. Findlay, I. Maddox
Abstract:
The quality and quantity of global satellite data have been increasing exponentially in recent years as spaceborne systems become more affordable and the sensors themselves become more sophisticated. This is a valuable resource for many applications, including disaster management and relief. However, while more information can be valuable, the volume of data available is impossible to manually examine. Therefore, the question becomes how to extract as much information as possible from the data with limited manpower. Buildings are a key feature of interest in satellite imagery with applications including telecommunications, population models, and disaster relief. Machine learning tools are fast becoming one of the key resources to solve this problem, and models have been developed to detect buildings in optical satellite imagery. However, by and large, most models focus on affluent regions where buildings are generally larger and constructed further apart. This work is focused on the more difficult problem of detection in populated regions. The primary challenge with detecting small buildings in densely populated regions is both the spatial and spectral resolution of the optical sensor. Densely packed buildings with similar construction materials will be difficult to separate due to a similarity in color and because the physical separation between structures is either non-existent or smaller than the spatial resolution. This study finds that training models until they are overfitting the input sample can perform better in these areas than a more robust, generalized model. An overfitted model takes less time to fine-tune from a generalized pre-trained model and requires fewer input data. The model developed for this study has also been fine-tuned using existing, open-source, building vector datasets. This is particularly valuable in the context of disaster relief, where information is required in a very short time span. Leveraging existing datasets means that little to no manpower or time is required to collect data in the region of interest. The training period itself is also shorter for smaller datasets. Requiring less data means that only a few quality areas are necessary, and so any weaknesses or underpopulated regions in the data can be skipped over in favor of areas with higher quality vectors. In this study, a landcover classification model was developed in conjunction with the building detection tool to provide a secondary source to quality check the detected buildings. This has greatly reduced the false positive rate. The proposed methodologies have been implemented and integrated into a configurable production environment and have been employed for a number of large-scale commercial projects, including continent-wide DEM production, where the extracted building footprints are being used to enhance digital elevation models. Overfitted machine learning models are often considered too specific to have any predictive capacity. However, this study demonstrates that, in cases where input data is scarce, overfitted models can be judiciously applied to solve time-sensitive problems.Keywords: building detection, disaster relief, mask-RCNN, satellite mapping
Procedia PDF Downloads 16616666 Investigation on Machine Tools Energy Consumptions
Authors: Shiva Abdoli, Daniel T.Semere
Abstract:
Several researches have been conducted to study consumption of energy in cutting process. Most of these researches are focusing to measure the consumption and propose consumption reduction methods. In this work, the relation between the cutting parameters and the consumption is investigated in order to establish a generalized energy consumption model that can be used for process and production planning in real production lines. Using the generalized model, the process planning will be carried out by taking into account the energy as a function of the selected process parameters. Similarly, the generalized model can be used in production planning to select the right operational parameters like batch sizes, routing, buffer size, etc. in a production line. The description and derivation of the model as well as a case study are given in this paper to illustrate the applicability and validity of the model.Keywords: process parameters, cutting process, energy efficiency, Material Removal Rate (MRR)
Procedia PDF Downloads 49316665 Development of EREC IF Model to Increase Critical Thinking and Creativity Skills of Undergraduate Nursing Students
Authors: Kamolrat Turner, Boontuan Wattanakul
Abstract:
Critical thinking and creativity are prerequisite skills for working professionals in the 21st century. A survey conducted in 2014 at the Boromarajonani College of Nursing, Chon Buri, Thailand, revealed that these skills within students across all academic years was at a low to moderate level. An action research study was conducted to develop the EREC IF Model, a framework which includes the concepts of experience, reflection, engagement, culture and language, ICT, and flexibility and fun, to guide pedagogic activities for 75 sophomores of the undergraduate nursing science program at the college. The model was applied to all professional nursing courses. Prior to implementation, workshops were held to prepare lecturers and students. Both lecturers and students initially expressed their discomfort and pointed to the difficulties with the model. However, later they felt more comfortable, and by the end of the project they expressed their understanding and appreciation of the model. A survey conducted four and eight months after implementation found that the critical thinking and creativity skills of the sophomores were significantly higher than those recorded in the pretest. It could be concluded that the EREC IF model is efficient for fostering critical thinking and creativity skills in the undergraduate nursing science program. This model should be used for other levels of students.Keywords: critical thinking, creativity, undergraduate nursing students, EREC IF model
Procedia PDF Downloads 31816664 Artificial Intelligence in the Design of a Retaining Structure
Authors: Kelvin Lo
Abstract:
Nowadays, numerical modelling in geotechnical engineering is very common but sophisticated. Many advanced input settings and considerable computational efforts are required to optimize the design to reduce the construction cost. To optimize a design, it usually requires huge numerical models. If the optimization is conducted manually, there is a potentially dangerous consequence from human errors, and the time spent on the input and data extraction from output is significant. This paper presents an automation process introduced to numerical modelling (Plaxis 2D) of a trench excavation supported by a secant-pile retaining structure for a top-down tunnel project. Python code is adopted to control the process, and numerical modelling is conducted automatically in every 20m chainage along the 200m tunnel, with maximum retained height occurring in the middle chainage. Python code continuously changes the geological stratum and excavation depth under groundwater flow conditions in each 20m section. It automatically conducts trial and error to determine the required pile length and the use of props to achieve the required factor of safety and target displacement. Once the bending moment of the pile exceeds its capacity, it will increase in size. When the pile embedment reaches the default maximum length, it will turn on the prop system. Results showed that it saves time, increases efficiency, lowers design costs, and replaces human labor to minimize error.Keywords: automation, numerical modelling, Python, retaining structures
Procedia PDF Downloads 4516663 Using Artificial Intelligence Method to Explore the Important Factors in the Reuse of Telecare by the Elderly
Authors: Jui-Chen Huang
Abstract:
This research used artificial intelligence method to explore elderly’s opinions on the reuse of telecare, its effect on their service quality, satisfaction and the relationship between customer perceived value and intention to reuse. This study conducted a questionnaire survey on the elderly. A total of 124 valid copies of a questionnaire were obtained. It adopted Backpropagation Network (BPN) to propose an effective and feasible analysis method, which is different from the traditional method. Two third of the total samples (82 samples) were taken as the training data, and the one third of the samples (42 samples) were taken as the testing data. The training and testing data RMSE (root mean square error) are 0.022 and 0.009 in the BPN, respectively. As shown, the errors are acceptable. On the other hand, the training and testing data RMSE are 0.100 and 0.099 in the regression model, respectively. In addition, the results showed the service quality has the greatest effects on the intention to reuse, followed by the satisfaction, and perceived value. This result of the Backpropagation Network method is better than the regression analysis. This result can be used as a reference for future research.Keywords: artificial intelligence, backpropagation network (BPN), elderly, reuse, telecare
Procedia PDF Downloads 20516662 Towards Accurate Velocity Profile Models in Turbulent Open-Channel Flows: Improved Eddy Viscosity Formulation
Authors: W. Meron Mebrahtu, R. Absi
Abstract:
Velocity distribution in turbulent open-channel flows is organized in a complex manner. This is due to the large spatial and temporal variability of fluid motion resulting from the free-surface turbulent flow condition. This phenomenon is complicated further due to the complex geometry of channels and the presence of solids transported. Thus, several efforts were made to understand the phenomenon and obtain accurate mathematical models that are suitable for engineering applications. However, predictions are inaccurate because oversimplified assumptions are involved in modeling this complex phenomenon. Therefore, the aim of this work is to study velocity distribution profiles and obtain simple, more accurate, and predictive mathematical models. Particular focus will be made on the acceptable simplification of the general transport equations and an accurate representation of eddy viscosity. Wide rectangular open-channel seems suitable to begin the study; other assumptions are smooth-wall, and sediment-free flow under steady and uniform flow conditions. These assumptions will allow examining the effect of the bottom wall and the free surface only, which is a necessary step before dealing with more complex flow scenarios. For this flow condition, two ordinary differential equations are obtained for velocity profiles; from the Reynolds-averaged Navier-Stokes (RANS) equation and equilibrium consideration between turbulent kinetic energy (TKE) production and dissipation. Then different analytic models for eddy viscosity, TKE, and mixing length were assessed. Computation results for velocity profiles were compared to experimental data for different flow conditions and the well-known linear, log, and log-wake laws. Results show that the model based on the RANS equation provides more accurate velocity profiles. In the viscous sublayer and buffer layer, the method based on Prandtl’s eddy viscosity model and Van Driest mixing length give a more precise result. For the log layer and outer region, a mixing length equation derived from Von Karman’s similarity hypothesis provides the best agreement with measured data except near the free surface where an additional correction based on a damping function for eddy viscosity is used. This method allows more accurate velocity profiles with the same value of the damping coefficient that is valid under different flow conditions. This work continues with investigating narrow channels, complex geometries, and the effect of solids transported in sewers.Keywords: accuracy, eddy viscosity, sewers, velocity profile
Procedia PDF Downloads 10716661 Assessing the Spatial Distribution of Urban Parks Using Remote Sensing and Geographic Information Systems Techniques
Authors: Hira Jabbar, Tanzeel-Ur Rehman
Abstract:
Urban parks and open spaces play a significant role in improving physical and mental health of the citizens, strengthen the societies and make the cities more attractive places to live and work. As the world’s cities continue to grow, continuing to value green space in cities is vital but is also a challenge, particularly in developing countries where there is pressure for space, resources, and development. Offering equal opportunity of accessibility to parks is one of the important issues of park distribution. The distribution of parks should allow all inhabitants to have close proximity to their residence. Remote sensing and Geographic information systems (GIS) can provide decision makers with enormous opportunities to improve the planning and management of Park facilities. This study exhibits the capability of GIS and RS techniques to provide baseline knowledge about the distribution of parks, level of accessibility and to help in identification of potential areas for such facilities. For this purpose Landsat OLI imagery for year 2016 was acquired from USGS Earth Explorer. Preprocessing models were applied using Erdas Imagine 2014v for the atmospheric correction and NDVI model was developed and applied to quantify the land use/land cover classes including built up, barren land, water, and vegetation. The parks amongst total public green spaces were selected based on their signature in remote sensing image and distribution. Percentages of total green and parks green were calculated for each town of Lahore City and results were then synchronized with the recommended standards. ANGSt model was applied to calculate the accessibility from parks. Service area analysis was performed using Network Analyst tool. Serviceability of these parks has been evaluated by employing statistical indices like service area, service population and park area per capita. Findings of the study may contribute in helping the town planners for understanding the distribution of parks, demands for new parks and potential areas which are deprived of parks. The purpose of present study is to provide necessary information to planners, policy makers and scientific researchers in the process of decision making for the management and improvement of urban parks.Keywords: accessible natural green space standards (ANGSt), geographic information systems (GIS), remote sensing (RS), United States geological survey (USGS)
Procedia PDF Downloads 33016660 Proactive Pure Handoff Model with SAW-TOPSIS Selection and Time Series Predict
Authors: Harold Vásquez, Cesar Hernández, Ingrid Páez
Abstract:
This paper approach cognitive radio technic and applied pure proactive handoff Model to decrease interference between PU and SU and comparing it with reactive handoff model. Through the study and analysis of multivariate models SAW and TOPSIS join to 3 dynamic prediction techniques AR, MA ,and ARMA. To evaluate the best model is taken four metrics: number failed handoff, number handoff, number predictions, and number interference. The result presented the advantages using this type of pure proactive models to predict changes in the PU according to the selected channel and reduce interference. The model showed better performance was TOPSIS-MA, although TOPSIS-AR had a higher predictive ability this was not reflected in the interference reduction.Keywords: cognitive radio, spectrum handoff, decision making, time series, wireless networks
Procedia PDF Downloads 48016659 Software Assessment Using Ant Colony Optimization Algorithm
Authors: Saad M. Darwish
Abstract:
Recently, software quality issues have come to be seen as important subject as we see an enormous growth of agencies involved in software industries. However,these agencies cannot guarantee the quality of their products, thus leaving users in uncertainties. Software certification is the extension of quality by means that quality needs to be measured prior to certification granting process. This research participates in solving the problem of software assessment by proposing a model for assessment and certification of software product that uses a fuzzy inference engine to integrate both of process–driven and application-driven quality assurance strategies. The key idea of the on hand model is to improve the compactness and the interpretability of the model’s fuzzy rules via employing an ant colony optimization algorithm (ACO), which tries to find good rules description by dint of compound rules initially expressed with traditional single rules. The model has been tested by case study and the results have demonstrated feasibility and practicability of the model in a real environment.Keywords: optimization technique, quality assurance, software certification model, software assessment
Procedia PDF Downloads 48016658 Simulation Study on Vehicle Drag Reduction by Surface Dimples
Authors: S. F. Wong, S. S. Dol
Abstract:
Automotive designers have been trying to use dimples to reduce drag in vehicles. In this work, a car model has been applied with dimple surface with a parameter called dimple ratio DR, the ratio between the depths of the half dimple over the print diameter of the dimple, has been introduced and numerically simulated via k-ε turbulence model to study the aerodynamics performance with the increasing depth of the dimples The Ahmed body car model with 25 degree slant angle is simulated with the DR of 0.05, 0.2, 0.3 0.4 and 0.5 at Reynolds number of 176387 based on the frontal area of the car model. The geometry of dimple changes the kinematics and dynamics of flow. Complex interaction between the turbulent fluctuating flow and the mean flow escalates the turbulence quantities. The maximum level of turbulent kinetic energy occurs at DR = 0.4. It can be concluded that the dimples have generated extra turbulence energy at the surface and as a result, the application of dimples manages to reduce the drag coefficient of the car model compared to the model with smooth surface.Keywords: aerodynamics, boundary layer, dimple, drag, kinetic energy, turbulence
Procedia PDF Downloads 31116657 Mathematical Model for Output Yield Obtained by Single Slope Solar Still
Authors: V. Nagaraju, G. Murali, Nagarjunavarma Ganna, Atluri Pavan Kalyan, N. Sree Sai Ganesh, V. S. V. S. Badrinath
Abstract:
The present work focuses on the development of a mathematical model for the yield obtained by single slope solar still incorporated with cylindrical pipes filled with sand. The mathematical results obtained were validated with the experimental results for the 3 cm of water level at the basin. The mathematical model and results obtained with the experimental investigation are within 11% of deviation. The theoretical model to predict the yield obtained due to the capillary effect was proposed first. And then, to predict the total yield obtained, the thermal effect model was integrated with the capillary effect model. With the obtained results, it is understood that the yield obtained is more in the case of solar stills with sand-filled cylindrical pipes when compared to solar stills without sand-filled cylindrical pipes. And later model was used for predicting yield for 1 cm and 2 cm of water levels at the basin. And it is observed that the maximum yield was obtained for a 1 cm water level at the basin. It means solar still produces better yield with the lower depth of water level at the basin; this may be because of the availability of more space in the sand for evaporation.Keywords: solar still, cylindrical pipes, still efficiency, mathematical modeling, capillary effect model, yield, solar desalination
Procedia PDF Downloads 11616656 Iterative Panel RC Extraction for Capacitive Touchscreen
Authors: Chae Hoon Park, Jong Kang Park, Jong Tae Kim
Abstract:
Electrical characteristics of capacitive touchscreen need to be accurately analyzed to result in better performance for multi-channel capacitance sensing. In this paper, we extracted the panel resistances and capacitances of the touchscreen by comparing measurement data and model data. By employing a lumped RC model for driver-to-receiver paths in touchscreen, we estimated resistance and capacitance values according to the physical lengths of channel paths which are proportional to the RC model. As a result, we obtained the model having 95.54% accuracy of the measurement data.Keywords: electrical characteristics of capacitive touchscreen, iterative extraction, lumped RC model, physical lengths of channel paths
Procedia PDF Downloads 33116655 Identification of Wiener Model Using Iterative Schemes
Authors: Vikram Saini, Lillie Dewan
Abstract:
This paper presents the iterative schemes based on Least square, Hierarchical Least Square and Stochastic Approximation Gradient method for the Identification of Wiener model with parametric structure. A gradient method is presented for the parameter estimation of wiener model with noise conditions based on the stochastic approximation. Simulation results are presented for the Wiener model structure with different static non-linear elements in the presence of colored noise to show the comparative analysis of the iterative methods. The stochastic gradient method shows improvement in the estimation performance and provides fast convergence of the parameters estimates.Keywords: hard non-linearity, least square, parameter estimation, stochastic approximation gradient, Wiener model
Procedia PDF Downloads 39416654 Prediction of Thermodynamic Properties of N-Heptane in the Critical Region
Authors: Sabrina Ladjama, Aicha Rizi, Azzedine Abbaci
Abstract:
In this work, we use the crossover model to formulate a comprehensive fundamental equation of state for the thermodynamic properties for several n-alkanes in the critical region that extends to the classical region. This equation of state is constructed on the basis of comparison of selected measurements of pressure-density-temperature data, isochoric and isobaric heat capacity. The model can be applied in a wide range of temperatures and densities around the critical point for n-heptane. It is found that the developed model represents most of the reliable experimental data accurately.Keywords: crossover model, critical region, fundamental equation, n-heptane
Procedia PDF Downloads 46916653 Semi-Supervised Learning for Spanish Speech Recognition Using Deep Neural Networks
Authors: B. R. Campomanes-Alvarez, P. Quiros, B. Fernandez
Abstract:
Automatic Speech Recognition (ASR) is a machine-based process of decoding and transcribing oral speech. A typical ASR system receives acoustic input from a speaker or an audio file, analyzes it using algorithms, and produces an output in the form of a text. Some speech recognition systems use Hidden Markov Models (HMMs) to deal with the temporal variability of speech and Gaussian Mixture Models (GMMs) to determine how well each state of each HMM fits a short window of frames of coefficients that represents the acoustic input. Another way to evaluate the fit is to use a feed-forward neural network that takes several frames of coefficients as input and produces posterior probabilities over HMM states as output. Deep neural networks (DNNs) that have many hidden layers and are trained using new methods have been shown to outperform GMMs on a variety of speech recognition systems. Acoustic models for state-of-the-art ASR systems are usually training on massive amounts of data. However, audio files with their corresponding transcriptions can be difficult to obtain, especially in the Spanish language. Hence, in the case of these low-resource scenarios, building an ASR model is considered as a complex task due to the lack of labeled data, resulting in an under-trained system. Semi-supervised learning approaches arise as necessary tasks given the high cost of transcribing audio data. The main goal of this proposal is to develop a procedure based on acoustic semi-supervised learning for Spanish ASR systems by using DNNs. This semi-supervised learning approach consists of: (a) Training a seed ASR model with a DNN using a set of audios and their respective transcriptions. A DNN with a one-hidden-layer network was initialized; increasing the number of hidden layers in training, to a five. A refinement, which consisted of the weight matrix plus bias term and a Stochastic Gradient Descent (SGD) training were also performed. The objective function was the cross-entropy criterion. (b) Decoding/testing a set of unlabeled data with the obtained seed model. (c) Selecting a suitable subset of the validated data to retrain the seed model, thereby improving its performance on the target test set. To choose the most precise transcriptions, three confidence scores or metrics, regarding the lattice concept (based on the graph cost, the acoustic cost and a combination of both), was performed as selection technique. The performance of the ASR system will be calculated by means of the Word Error Rate (WER). The test dataset was renewed in order to extract the new transcriptions added to the training dataset. Some experiments were carried out in order to select the best ASR results. A comparison between a GMM-based model without retraining and the DNN proposed system was also made under the same conditions. Results showed that the semi-supervised ASR-model based on DNNs outperformed the GMM-model, in terms of WER, in all tested cases. The best result obtained an improvement of 6% relative WER. Hence, these promising results suggest that the proposed technique could be suitable for building ASR models in low-resource environments.Keywords: automatic speech recognition, deep neural networks, machine learning, semi-supervised learning
Procedia PDF Downloads 33516652 An Integrated Real-Time Hydrodynamic and Coastal Risk Assessment Model
Authors: M. Reza Hashemi, Chris Small, Scott Hayward
Abstract:
The Northeast Coast of the US faces damaging effects of coastal flooding and winds due to Atlantic tropical and extratropical storms each year. Historically, several large storm events have produced substantial levels of damage to the region; most notably of which were the Great Atlantic Hurricane of 1938, Hurricane Carol, Hurricane Bob, and recently Hurricane Sandy (2012). The objective of this study was to develop an integrated modeling system that could be used as a forecasting/hindcasting tool to evaluate and communicate the risk coastal communities face from these coastal storms. This modeling system utilizes the ADvanced CIRCulation (ADCIRC) model for storm surge predictions and the Simulating Waves Nearshore (SWAN) model for the wave environment. These models were coupled, passing information to each other and computing over the same unstructured domain, allowing for the most accurate representation of the physical storm processes. The coupled SWAN-ADCIRC model was validated and has been set up to perform real-time forecast simulations (as well as hindcast). Modeled storm parameters were then passed to a coastal risk assessment tool. This tool, which is generic and universally applicable, generates spatial structural damage estimate maps on an individual structure basis for an area of interest. The required inputs for the coastal risk model included a detailed information about the individual structures, inundation levels, and wave heights for the selected region. Additionally, calculation of wind damage to structures was incorporated. The integrated coastal risk assessment system was then tested and applied to Charlestown, a small vulnerable coastal town along the southern shore of Rhode Island. The modeling system was applied to Hurricane Sandy and a synthetic storm. In both storm cases, effect of natural dunes on coastal risk was investigated. The resulting damage maps for the area (Charlestown) clearly showed that the dune eroded scenarios affected more structures, and increased the estimated damage. The system was also tested in forecast mode for a large Nor’Easters: Stella (March 2017). The results showed a good performance of the coupled model in forecast mode when compared to observations. Finally, a nearshore model XBeach was then nested within this regional grid (ADCIRC-SWAN) to simulate nearshore sediment transport processes and coastal erosion. Hurricane Irene (2011) was used to validate XBeach, on the basis of a unique beach profile dataset at the region. XBeach showed a relatively good performance, being able to estimate eroded volumes along the beach transects with a mean error of 16%. The validated model was then used to analyze the effectiveness of several erosion mitigation methods that were recommended in a recent study of coastal erosion in New England: beach nourishment, coastal bank (engineered core), and submerged breakwater as well as artificial surfing reef. It was shown that beach nourishment and coastal banks perform better to mitigate shoreline retreat and coastal erosion.Keywords: ADCIRC, coastal flooding, storm surge, coastal risk assessment, living shorelines
Procedia PDF Downloads 10816651 Markov Characteristics of the Power Line Communication Channels in China
Authors: Ming-Yue Zhai
Abstract:
Due to the multipath and pulse noise nature, power line communications(PLC) channel can be modelled as a memory one with the finite states Markov model(FSMC). As the most important parameter modelling a Markov channel,the memory order in an FSMC is not solved in PLC systems yet. In the paper, the mutual information is used as a measure of the dependence between the different symbols, treated as the received SNA or amplitude of the current channel symbol or that of previous symbols. The joint distribution probabilities of the envelopes in PLC systems are computed based on the multi-path channel model, which is commonly used in PLC. we confirm that given the information of the symbol immediately preceding the current one, any other previous symbol is independent of the current one in PLC systems, which means the PLC channels is a Markov chain with the first-order. The field test is also performed to model the received OFDM signals with the help of AR model. The results show that the first-order AR model is enough to model the fading channel in PLC systems, which means the amount of uncertainty remaining in the current symbol should be negligible, given the information corresponding to the immediately preceding one.Keywords: power line communication, channel model, markovian, information theory, first-order
Procedia PDF Downloads 40516650 Estimation of the Effect of Initial Damping Model and Hysteretic Model on Dynamic Characteristics of Structure
Authors: Shinji Ukita, Naohiro Nakamura, Yuji Miyazu
Abstract:
In considering the dynamic characteristics of structure, natural frequency and damping ratio are useful indicator. When performing dynamic design, it's necessary to select an appropriate initial damping model and hysteretic model. In the linear region, the setting of initial damping model influences the response, and in the nonlinear region, the combination of initial damping model and hysteretic model influences the response. However, the dynamic characteristics of structure in the nonlinear region remain unclear. In this paper, we studied the effect of setting of initial damping model and hysteretic model on the dynamic characteristics of structure. On initial damping model setting, Initial stiffness proportional, Tangent stiffness proportional, and Rayleigh-type were used. On hysteretic model setting, TAKEDA model and Normal-trilinear model were used. As a study method, dynamic analysis was performed using a lumped mass model of base-fixed. During analysis, the maximum acceleration of input earthquake motion was gradually increased from 1 to 600 gal. The dynamic characteristics were calculated using the ARX model. Then, the characteristics of 1st and 2nd natural frequency and 1st damping ratio were evaluated. Input earthquake motion was simulated wave that the Building Center of Japan has published. On the building model, an RC building with 30×30m planes on each floor was assumed. The story height was 3m and the maximum height was 18m. Unit weight for each floor was 1.0t/m2. The building natural period was set to 0.36sec, and the initial stiffness of each floor was calculated by assuming the 1st mode to be an inverted triangle. First, we investigated the difference of the dynamic characteristics depending on the difference of initial damping model setting. With the increase in the maximum acceleration of the input earthquake motions, the 1st and 2nd natural frequency decreased, and the 1st damping ratio increased. Then, in the natural frequency, the difference due to initial damping model setting was small, but in the damping ratio, a significant difference was observed (Initial stiffness proportional≒Rayleigh type>Tangent stiffness proportional). The acceleration and the displacement of the earthquake response were largest in the tangent stiffness proportional. In the range where the acceleration response increased, the damping ratio was constant. In the range where the acceleration response was constant, the damping ratio increased. Next, we investigated the difference of the dynamic characteristics depending on the difference of hysteretic model setting. With the increase in the maximum acceleration of the input earthquake motions, the natural frequency decreased in TAKEDA model, but in Normal-trilinear model, the natural frequency didn’t change. The damping ratio in TAKEDA model was higher than that in Normal-trilinear model, although, both in TAKEDA model and Normal-trilinear model, the damping ratio increased. In conclusion, in initial damping model setting, the tangent stiffness proportional was evaluated the most. In the hysteretic model setting, TAKEDA model was more appreciated than the Normal-trilinear model in the nonlinear region. Our results would provide useful indicator on dynamic design.Keywords: initial damping model, damping ratio, dynamic analysis, hysteretic model, natural frequency
Procedia PDF Downloads 17316649 Spatial Time Series Models for Rice and Cassava Yields Based on Bayesian Linear Mixed Models
Authors: Panudet Saengseedam, Nanthachai Kantanantha
Abstract:
This paper proposes a linear mixed model (LMM) with spatial effects to forecast rice and cassava yields in Thailand at the same time. A multivariate conditional autoregressive (MCAR) model is assumed to present the spatial effects. A Bayesian method is used for parameter estimation via Gibbs sampling Markov Chain Monte Carlo (MCMC). The model is applied to the rice and cassava yields monthly data which have been extracted from the Office of Agricultural Economics, Ministry of Agriculture and Cooperatives of Thailand. The results show that the proposed model has better performance in most provinces in both fitting part and validation part compared to the simple exponential smoothing and conditional auto regressive models (CAR) from our previous study.Keywords: Bayesian method, linear mixed model, multivariate conditional autoregressive model, spatial time series
Procedia PDF Downloads 38816648 Comparison of Accumulated Stress Based Pore Pressure Model and Plasticity Model in 1D Site Response Analysis
Authors: Saeedullah J. Mandokhail, Shamsher Sadiq, Meer H. Khan
Abstract:
This paper presents the comparison of excess pore water pressure ratio (ru) predicted by using accumulated stress based pore pressure model and plasticity model. One dimensional effective stress site response analyses were performed on a 30 m deep sand column (consists of a liquefiable layer in between non-liquefiable layers) using accumulated stress based pore pressure model in Deepsoil and PDMY2 (PressureDependentMultiYield02) model in Opensees. Three Input motions with different peak ground acceleration (PGA) levels of 0.357 g, 0.124 g, and 0.11 g were used in this study. The developed excess pore pressure ratio predicted by the above two models were compared and analyzed along the depth. The time history of the ru at mid of the liquefiable layer and non-liquefiable layer were also compared. The comparisons show that the two models predict mostly similar ru values. The predicted ru is also consistent with the PGA level of the input motions.Keywords: effective stress, excess pore pressure ratio, pore pressure model, site response analysis
Procedia PDF Downloads 221