Search results for: radial basis function networks

Authors: Kamel Al-Khaled

Abstract:

A comparative study of the Sinc-Galerkin and Sinc-Collocation methods for solving the Kuramoto-Sivashinsky equation is given. Both approaches depend on using Sinc basis functions. Firstly, a numerical scheme using Sinc-Galerkin method is developed to approximate the solution of Kuramoto-Sivashinsky equation. Sinc approximations to both derivatives and indefinite integrals reduces the solution to an explicit system of algebraic equations. The error in the solution is shown to converge to the exact solution at an exponential. The convergence proof of the solution for the discrete system is given using fixed-point iteration. Secondly, a combination of a Crank-Nicolson formula in the time direction, with the Sinc-collocation in the space direction is presented, where the derivatives in the space variable are replaced by the necessary matrices to produce a system of algebraic equations. The methods are tested on two examples. The demonstrated results show that both of the presented methods more or less have the same accuracy.

Keywords: Sinc-Collocation, nonlinear PDEs, numerical methods, fixed-point

Procedia PDF Downloads 471

Authors: Rezaei Hachesu Peyman, Oliyaee Azadeh, Salahzadeh Zahra, Alizadeh Somayyeh, Safaei Naser

Abstract:

Coronary Artery Disease (CAD) is one major cause of disability in adults and one main cause of death in developed. In this study, data mining techniques including Decision Trees, Artificial neural networks (ANNs), and Support Vector Machine (SVM) analyze CAD data. Data of 4948 patients who had suffered from heart diseases were included in the analysis. CAD is the target variable, and 24 inputs or predictor variables are used for the classification. The performance of these techniques is compared in terms of sensitivity, specificity, and accuracy. The most significant factor influencing CAD is chest pain. Elderly males (age > 53) have a high probability to be diagnosed with CAD. SVM algorithm is the most useful way for evaluation and prediction of CAD patients as compared to non-CAD ones. Application of data mining techniques in analyzing coronary artery diseases is a good method for investigating the existing relationships between variables.

Keywords: classification, coronary artery disease, data-mining, knowledge discovery, extract

Procedia PDF Downloads 657

Authors: Hee-Choul Kwon, Hyungjin Cho, Heeyong Kwon

Abstract:

Image rotation is one of main pre-processing step in image processing or image pattern recognition. It is implemented with rotation matrix multiplication. However it requires lots of floating point arithmetic operations and trigonometric function calculations, so it takes long execution time. We propose a new high speed image rotation algorithm without two major time-consuming operations. We compare the proposed algorithm with the conventional rotation one with various size images. Experimental results show that the proposed algorithm is superior to the conventional rotation ones.

Keywords: high speed rotation operation, image processing, image rotation, pattern recognition, transformation matrix

Procedia PDF Downloads 506

Authors: Abbas Hadj Abbas, Hacini Massaoud, Aiad Lahcen

Abstract:

In Hassi-Messoud’s oil industry, the systems which are water based (WBM) are generally used for drilling in the first phase. For the rest of the well, the oil mud systems are employed (OBM). In the field of oil exploration, panoply of chemical products is employed in the drilling fluids formulation. These components of different natures and whose toxicity and biodegradability are of ill-defined parameters are; however, thrown into nature. In addition to the hydrocarbon (HC, such as diesel) which is a major constituent of oil based mud, we also can notice spills as well as a variety of other products and additives on the drilling sites. These wastes are usually stored in places called (crud wastes). These may cause major problems to the ecosystem. To treat these wastes, we have considered two methods which are: solidification/ stabilization (chemical) and thermal. So that we can evaluate the techniques of treatment, a series of analyses are performed on dozens of specimens of wastes before treatment. After that, and on the basis of our analyses of wastes, we opted for diagnostic treatments of pollution before and after solidification and stabilization. Finally, we have done some analyses before and after the thermal treatment to check the efficiency of the methods followed in the study.

Keywords: wastes treatment, the oil pollution, the norms, wastes drilling

Procedia PDF Downloads 294

Authors: Guesh Simretab Gebremedhin, Saumya Rajan Jena

Abstract:

In this work, a septic B-spline scheme has been used to simplify the process of solving an approximate solution of the generalized Rosenau-regularized long-wave equation (GR-RLWE) with initial boundary conditions. The resulting system of first-order ODEs has dealt with Butcher’s fifth order Runge-Kutta (BFRK) approach without using finite difference techniques for discretizing the time-dependent variables at each time level. Here, no transformation or any kind of linearization technique is employed to tackle the nonlinearity of the equation. Two test problems have been selected for numerical justifications and comparisons with other researchers on the basis of efficiency, accuracy, and results of the two invariants Mᵢ (mass) and Eᵢ (energy) of some motion that has been used to test the conservative properties of the proposed scheme.

Keywords: septic B-spline scheme, Butcher's fifth order Runge-Kutta approach, error norms, generalized Rosenau-RLW equation

Procedia PDF Downloads 66

Authors: Zbigniew Czyz, Krzysztof Skiba, Miroslaw Wendeker

Abstract:

This paper discusses the results of aerodynamic investigation of the Tajfun gyroplane body designed by a Polish company, Aviation Artur Trendak. This gyroplane has been studied as a 1:8 scale model. Scaling objects for aerodynamic investigation is an inherent procedure in any kind of designing. If scaling, the criteria of similarity need to be satisfied. The basic criteria of similarity are geometric, kinematic and dynamic. Despite the results of aerodynamic research are often reduced to aerodynamic coefficients, one should pay attention to how values of coefficients behave if certain criteria are to be satisfied. To satisfy the dynamic criterion, for example, the Reynolds number should be focused on. This is the correlation of inertial to viscous forces. With the multiplied flow speed by the specific dimension as a numerator (with a constant kinematic viscosity coefficient), flow speed in a wind tunnel research should be increased as many times as an object is decreased. The aerodynamic coefficients specified in this research depend on the real forces that act on an object, its specific dimension, medium speed and variations in its density. Rapid prototyping with a 3D printer was applied to create the research object. The research was performed with a T-1 low-speed wind tunnel (its diameter of the measurement volume is 1.5 m) and a six-element aerodynamic internal scales, WDP1, at the Institute of Aviation in Warsaw. This T-1 wind tunnel is low-speed continuous operation with open space measurement. The research covered a number of the selected speeds of undisturbed flow, i.e. V = 20, 30 and 40 m/s, corresponding to the Reynolds numbers (as referred to 1 m) Re = 1.31∙106, 1.96∙106, 2.62∙106 for the angles of attack ranging -15° ≤ α ≤ 20°. Our research resulted in basic aerodynamic characteristics and observing the impact of undisturbed flow speed on the correlation of aerodynamic coefficients as a function of the angle of attack of the gyroplane body. If the speed of undisturbed flow in the wind tunnel changes, the aerodynamic coefficients are significantly impacted. At speed from 20 m/s to 30 m/s, drag coefficient, Cx, changes by 2.4% up to 9.9%, whereas lift coefficient, Cz, changes by -25.5% up to 15.7% if the angle of attack of 0° excluded or by -25.5% up to 236.9% if the angle of attack of 0° included. Within the same speed range, the coefficient of a pitching moment, Cmy, changes by -21.1% up to 7.3% if the angles of attack -15° and -10° excluded or by -142.8% up to 618.4% if the angle of attack -15° and -10° included. These discrepancies in the coefficients of aerodynamic forces definitely need to consider while designing the aircraft. For example, if load of certain aircraft surfaces is calculated, additional correction factors definitely need to be applied. This study allows us to estimate the discrepancies in the aerodynamic forces while scaling the aircraft. This work has been financed by the Polish Ministry of Science and Higher Education.

Keywords: aerodynamics, criteria of similarity, gyroplane, research tunnel

Procedia PDF Downloads 393

Authors: Junwu Tian

Abstract:

Chinese poetics originated in the pre-Qin period, while Western poetics came into being in the Hellenistic period. Although there was no mutual communication and influence between the two kinds of poetics due to both geographical distance and chronological displacement, the Sino-Western thinkers shared much in common, particularly in the social function of literature and art, the pursuit of unified and harmonious aesthetics, the advocacy of poets’ subjective initiative in the creative process of literature and art. In the sphere of rhetoric, the poetics of the pre-Qin scholars and their Greek counterparts also had heterogeneous similarities. By comparing the aesthetic ideas of Confucius, Mencius, Xun Zi, and Deng Xi with those of Plato, Aristotle, and Protagoras, this paper intends to reveal the common concerns of Chinese and Western poetics in the context of heterogeneous cultures and in their respective origin periods.

Keywords: Pre-Qin poetics, ancient Greek poetics, heterogeneous similarity, origin period

Procedia PDF Downloads 80

Authors: Mihai Rebenciuc, Simona Mihaela Bibic

Abstract:

Branch of modern mathematics, graphs represent instruments for optimization and solving practical applications in various fields such as economic networks, engineering, network optimization, the geometry of social action, generally, complex systems including contemporary urban problems (path or transport efficiencies, biourbanism, & c.). In this paper is studied the interconnection of some urban network, which can lead to a simulation problem of a digraph through another digraph. The simulation is made univoc or more general multivoc. The concepts of fragment and atom are very useful in the study of connectivity in the digraph that is simulation - including an alternative evaluation of k- connectivity. Rough set approach in (bi)digraph which is proposed in premier in this paper contribute to improved significantly the evaluation of k-connectivity. This rough set approach is based on generalized rough sets - basic facts are presented in this paper.

Keywords: (bi)digraphs, rough set theory, systems of interacting agents, complex systems

Procedia PDF Downloads 243

Authors: Yuchao Hua, Lingai Luo

Abstract:

Thermal energy storage is of critical importance for the highly-efficient utilization of renewable energy sources. Over the past decades, single-tank thermocline technology has attracted much attention owing to its high cost-effectiveness. In the present work, we investigate the influence of the filler porosity’s non-uniform distribution on the thermal performance of the packed-bed sensible heat thermocline storage tanks on the basis of the analytical model obtained by the Laplace transform. It is found that when the total amount of filler materials (i.e., the integration of porosity) is fixed, the different porosity distributions can result in the significantly-different behaviors of outlet temperature and thus the varied charging and discharging efficiencies. Our results indicate that a non-uniform distribution of the fillers with the proper design can improve the heat storage performance without changing the total amount of the filling materials.

Keywords: energy storage, heat thermocline storage tank, packed bed, transient thermal analysis

Procedia PDF Downloads 94

Authors: Deniz Peksen

Abstract:

This thesis aims to predict trend movement of closing price of stock and to maximize portfolio by utilizing the predictions. In this context, the study aims to define a stock portfolio strategy from models created by using Logistic Regression, Gradient Boosting and Random Forest. Recently, predicting the trend of stock price has gained a significance role in making buy and sell decisions and generating returns with investment strategies formed by machine learning basis decisions. There are plenty of studies in the literature on the prediction of stock prices in capital markets using machine learning methods but most of them focus on closing prices instead of the direction of price trend. Our study differs from literature in terms of target definition. Ours is a classification problem which is focusing on the market trend in next 20 trading days. To predict trend direction, fourteen years of data were used for training. Following three years were used for validation. Finally, last three years were used for testing. Training data are between 2002-06-18 and 2016-12-30 Validation data are between 2017-01-02 and 2019-12-31 Testing data are between 2020-01-02 and 2022-03-17 We determine Hold Stock Portfolio, Best Stock Portfolio and USD-TRY Exchange rate as benchmarks which we should outperform. We compared our machine learning basis portfolio return on test data with return of Hold Stock Portfolio, Best Stock Portfolio and USD-TRY Exchange rate. We assessed our model performance with the help of roc-auc score and lift charts. We use logistic regression, Gradient Boosting and Random Forest with grid search approach to fine-tune hyper-parameters. As a result of the empirical study, the existence of uptrend and downtrend of five stocks could not be predicted by the models. When we use these predictions to define buy and sell decisions in order to generate model-based-portfolio, model-based-portfolio fails in test dataset. It was found that Model-based buy and sell decisions generated a stock portfolio strategy whose returns can not outperform non-model portfolio strategies on test dataset. We found that any effort for predicting the trend which is formulated on stock price is a challenge. We found same results as Random Walk Theory claims which says that stock price or price changes are unpredictable. Our model iterations failed on test dataset. Although, we built up several good models on validation dataset, we failed on test dataset. We implemented Random Forest, Gradient Boosting and Logistic Regression. We discovered that complex models did not provide advantage or additional performance while comparing them with Logistic Regression. More complexity did not lead us to reach better performance. Using a complex model is not an answer to figure out the stock-related prediction problem. Our approach was to predict the trend instead of the price. This approach converted our problem into classification. However, this label approach does not lead us to solve the stock prediction problem and deny or refute the accuracy of the Random Walk Theory for the stock price.

Keywords: stock prediction, portfolio optimization, data science, machine learning

Procedia PDF Downloads 80

Authors: David Loh, Wan Chee Wai, Pei Nan, Chen Zhe

Abstract:

To increase the conveyance capacity to Western Singapore and to meet Singapore’s long-term water needs in a more cost-effective manner, four new transmission pipelines consisting of two 2200 mm diameter water pipes and two 1200mm diameter water pipes will be needed by 2024 to convey water from a Water Reclamation Plant to existing networks in the west region of Singapore. Out of the several possible routes studied, the most cost-effective and technically feasible route was selected to lay the proposed 1.6km-long pipelines that cross a channel via a 6m diameter subsea tunnel. This paper outlines the challenges the team faced throughout the project thus far. It also examined the difficulties such as (1) construction of a 56m-deep launching shaft near a highly sensitive 700mm diameter Gas Transmission Pipeline (GTP) and at a location with high groundwater; (2) manpower and supply disruptions caused by the COVID-19 pandemic situation.

Keywords: underwater tunnel, subsea engineering, subsea tunnel construction, waterpipe construction

Procedia PDF Downloads 28

Authors: S. Nagheli, N. Samani, D. A. Barry

Abstract:

In this paper, the velocity potential and stream function of capture zone for a well field in an aquifer bounded by two parallel streams with or without a uniform regional flow of any directions are presented. The well field includes any number of extraction or injection wells or a combination of both types with any pumping rates. To delineate the capture envelope, the potential and streamlines equations are derived by conformal mapping method. This method can help us to release constrains of other methods. The equations can be applied as useful tools to design in-situ groundwater remediation systems, to evaluate the surface–subsurface water interaction and to manage the water resources.

Keywords: complex potential, conformal mapping, image well theory, Laplace’s equation, superposition principle

Procedia PDF Downloads 432

Authors: Taweechai Nuntawisuttiwong, Natasha Dejdumrong

Abstract:

Geometric modeling plays an important role in the constructions and manufacturing of curve, surface and solid modeling. Their algorithms are critically important not only in the automobile, ship and aircraft manufacturing business, but are also absolutely necessary in a wide variety of modern applications, e.g., robotics, optimization, computer vision, data analytics and visualization. The calculation and display of geometric objects can be accomplished by these six techniques: Polynomial basis, Recursive, Iterative, Coefficient matrix, Polar form approach and Pyramidal algorithms. In this research, the coefficient matrix (simply called monomial form approach) will be used to model polynomial rectangular patches, i.e., Said-Ball, Wang-Ball, DP, Dejdumrong and NB1 surfaces. Some examples of the monomial forms for these surface modeling are illustrated in many aspects, e.g., construction, derivatives, model transformation, degree elevation and degress reduction.

Keywords: monomial forms, rectangular surfaces, CAGD curves, monomial matrix applications

Procedia PDF Downloads 146

Authors: Tamara Slišković, Tomislav Sekur

Abstract:

This manuscript examines factors that affect demand and supply of the housing market in Croatia. The period from the beginning of this century, until 2008, was characterized by a strong expansion of construction, housing and real estate market in general. Demand for residential units was expanding, and this was supported by favorable lending conditions of banks. Indicators on the supply side, such as the number of newly built houses and the construction volume index were also increasing. Rapid growth of demand, along with the somewhat slower supply growth, led to the situation in which new apartments were sold before the completion of residential buildings. This resulted in a rise of housing price which was indication of a clear link between the housing prices with the supply and demand in the housing market. However, after 2008 general economic conditions in Croatia worsened and demand for housing has fallen dramatically, while supply descended at much slower pace. Given that there is a gap between supply and demand, it can be concluded that the housing market in Croatia is in imbalance. Such trend is accompanied by a relatively small decrease in housing price. The final result of such movements is the large number of unsold housing units at relatively high price levels. For this reason, it can be argued that housing prices are sticky and that, consequently, the price level in the aftermath of a crisis does not correspond to the discrepancy between supply and demand on the Croatian housing market. The degree of rigidity of the housing price can be determined by inclusion of the housing price as the explanatory variable in the housing demand function. Other independent variables are demographic variable (e.g. the number of households), the interest rate on housing loans, households' disposable income and rent. The equilibrium price is reached when the demand for housing equals its supply, and the speed of adjustment of actual prices to equilibrium prices reveals the extent to which the prices are rigid. The latter requires inclusion of the housing prices with time lag as an independent variable in estimating demand function. We also observe the supply side of the housing market, in order to explain to what extent housing prices explain the movement of new construction activity, and other variables that describe the supply. In this context, we test whether new construction on the Croatian market is dependent on current prices or prices with a time lag. Number of dwellings is used to approximate new construction (flow variable), while the housing prices (current or lagged), quantity of dwellings in the previous period (stock variable) and a series of costs related to new construction are independent variables. We conclude that the key reason for the imbalance in the Croatian housing market should be sought in the relative relationship of price elasticities of supply and demand.

Keywords: Croatian housing market, economic crisis, housing prices, supply imbalance, demand imbalance

Procedia PDF Downloads 273

Authors: Muhammad Ahnaf Zahin, Yaw Adu-Gyamfi

Abstract:

Bus transit is a crucial component of transportation networks, especially in urban areas. Any intelligent transportation system must have accurate real-time information on bus travel times since it minimizes waiting times for passengers at different stations along a route, improves service reliability, and significantly optimizes travel patterns. Bus agencies must enhance the quality of their information service to serve their passengers better and draw in more travelers since people waiting at bus stops are frequently anxious about when the bus will arrive at their starting point and when it will reach their destination. For solving this issue, different models have been developed for predicting bus travel times recently, but most of them are focused on smaller road networks due to their relatively subpar performance in high-density urban areas on a vast network. This paper develops a deep learning-based architecture using a single-step multi-station forecasting approach to predict average bus travel times for numerous routes, stops, and trips on a large-scale network using heterogeneous bus transit data collected from the GTFS database. Over one week, data was gathered from multiple bus routes in Saint Louis, Missouri. In this study, Gated Recurrent Unit (GRU) neural network was followed to predict the mean vehicle travel times for different hours of the day for multiple stations along multiple routes. Historical time steps and prediction horizon were set up to 5 and 1, respectively, which means that five hours of historical average travel time data were used to predict average travel time for the following hour. The spatial and temporal information and the historical average travel times were captured from the dataset for model input parameters. As adjacency matrices for the spatial input parameters, the station distances and sequence numbers were used, and the time of day (hour) was considered for the temporal inputs. Other inputs, including volatility information such as standard deviation and variance of journey durations, were also included in the model to make it more robust. The model's performance was evaluated based on a metric called mean absolute percentage error (MAPE). The observed prediction errors for various routes, trips, and stations remained consistent throughout the day. The results showed that the developed model could predict travel times more accurately during peak traffic hours, having a MAPE of around 14%, and performed less accurately during the latter part of the day. In the context of a complicated transportation network in high-density urban areas, the model showed its applicability for real-time travel time prediction of public transportation and ensured the high quality of the predictions generated by the model.

Keywords: gated recurrent unit, mean absolute percentage error, single-step forecasting, travel time prediction.

Procedia PDF Downloads 72

Authors: P. Vindin, R. Cordier, N. J. Wilson, H. Lee

Abstract:

Engagement in community-based activities such as education, employment, and social relationships can improve the quality of life for individuals with Autism Spectrum Disorder (ASD). Community mobility is vital to attaining independence for individuals with ASD. Learning to drive and gaining a driver’s license is a critical link to community mobility; however, for individuals with ASD acquiring safe driving skills can be a challenging process. Issues related to anxiety, executive function, and social communication may affect driving behaviours. Driving training and education aimed at addressing barriers faced by learner drivers with ASD can help them improve their driving performance. A multi-site randomized controlled trial (RCT) was conducted to evaluate the effectiveness of an autism-specific driving training intervention for improving the on-road driving performance of learner drivers with ASD. The intervention was delivered via a training manual and interactive website consisting of five modules covering varying driving environments starting with a focus on off-road preparations and progressing through basic to complex driving skill mastery. Seventy-two learner drivers with ASD aged 16 to 35 were randomized using a blinded group allocation procedure into either the intervention or control group. The intervention group received 10 driving lessons with the instructors trained in the use of an autism-specific driving training protocol, whereas the control group received 10 driving lessons as usual. Learner drivers completed a pre- and post-observation drive using a standardized driving route to measure driving performance using the Driving Performance Checklist (DPC). They also completed anxiety, executive function, and social responsiveness measures. The findings showed that there were significant improvements in driving performance for both the intervention (d = 1.02) and the control group (d = 1.15). However, the differences were not significant between groups (p = 0.614) or study sites (p = 0.842). None of the potential moderator variables (anxiety, cognition, social responsiveness, and driving instructor experience) influenced driving performance. This study is an important step toward improving community mobility for individuals with ASD showing that an autism-specific driving training intervention can improve the driving performance of leaner drivers with ASD. It also highlighted the complexity of conducting a multi-site design even when sites were matched according to geography and traffic conditions. Driving instructors also need more and clearer information on how to communicate with learner drivers with restricted verbal expression.

Keywords: autism spectrum disorder, community mobility, driving training, transportation

Procedia PDF Downloads 132

Authors: Aries Nawel, Bentarzi Mohamed

Abstract:

This paper deals with the study of some probabilistic and statistical properties of a Periodic Integer-Valued Moving Average Model (PINMA_{S}(q)). The closed forms of the mean, the second moment and the periodic autocovariance function are obtained. Furthermore, the time reversibility of the model is discussed in details. Moreover, the estimation of the underlying parameters are obtained by the Yule-Walker method, the Conditional Least Square method (CLS) and the Weighted Conditional Least Square method (WCLS). A simulation study is carried out to evaluate the performance of the estimation method. Moreover, an application on real data set is provided.

Keywords: periodic integer-valued moving average, periodically correlated process, time reversibility, count data

Procedia PDF Downloads 202

Authors: Anatoly D. Pluzhnikov, Elena N. Pribludova, Alexander G. Ryndyk

Abstract:

In conjunction with the problem of the target selection on a clutter background, the analysis of the scanning rate influence on the spatial-temporal signal structure, the generalized multivariate correlation function and the quality of the resolution with the increase pulse repetition frequency is made. The possibility of the object space-distance resolution, which is conditioned by the range-to-angle conversion with an increased scanning rate, is substantiated. The calculations for the real cylindrical array at high scanning rate are presented. The high scanning rate let to get the signal to noise improvement of the order of 10 dB for the space-time signal processing.

Keywords: antenna pattern, array, signal processing, spatial resolution

Procedia PDF Downloads 180

Authors: Yogita Weikey, Shobha Lata Sinha, Satish Kumar Dewangan

Abstract:

In the present investigation, rheology of the three different natural gums has been evaluated experimentally using MCR 102 rheometer. Various samples based on the variation of the concentration of the solid gum powder have been prepared. Their non-Newtonian behavior has been observed by the consistency plots and viscosity variation plots with respect to different solid concentration. The viscosity-shear rate curves of gums are similar and the behavior is shear thinning. Gums are showing pseudoplastic behavior. The value of k and n are calculated by using various models. Results show that the Herschel–Bulkley rheological model is reliable to describe the relationship of shear stress as a function of shear rate. R² values are also calculated to support the choice of gum selection.

Keywords: bentonite, Indian gum, non-Newtonian model, rheology

Procedia PDF Downloads 310

Authors: Hassan Eshkiki, Benjamin Mora

Abstract:

The Neighbor Migrating Generator is a simple and efficient approach to finding the closest potential neighbor(s) with a different label for a given instance and so without the need to calibrate any kernel settings at all. This allows determining and explaining the most important features that will influence an AI model. It can be used to either migrate a specific sample to the class decision boundary of the original model within a close neighborhood of that sample or identify global features that can help localising neighbor classes. The proposed technique works by minimizing a loss function that is divided into two components which are independently weighted according to three parameters α, β, and ω, α being self-adjusting. Results show that this approach is superior to past techniques when detecting the smallest changes in the feature space and may also point out issues in models like over-fitting.

Keywords: explainable AI, EX AI, feature importance, counterfactual explanations

Procedia PDF Downloads 193

Authors: Adetunji A. Adeyanju., Mathew O. Omeike, Johnson O. Adeniran, Biodun S. Badmus

Abstract:

In this paper, we discuss certain conditions for uniform asymptotic stability and uniform ultimate boundedness of solutions to some systems of Aizermann-type of differential equations by means of second method of Lyapunov. In achieving our goal, some Lyapunov functions are constructed to serve as basic tools. The stability results in this paper, extend some stability results for some Aizermann-type of differential equations found in literature. Also, we prove some results on uniform boundedness and uniform ultimate boundedness of solutions of systems of equations study.

Keywords: Aizermann, boundedness, first order, Lyapunov function, stability

Procedia PDF Downloads 84

Authors: Egemen Sert, Leila Hedayatifar, Rachel A. Rigg, Amir Akhavan, Olha Buchel, Dominic Elias Saadi, Aabir Abubaker Kar, Alfredo J. Morales, Yaneer Bar-Yam

Abstract:

The complexity of providing timely and cost-effective distribution of finished goods from industrial facilities to customers makes effective operational coordination difficult, yet effectiveness is crucial for maintaining customer service levels and sustaining a business. Logistics planning becomes increasingly complex with growing numbers of customers, varied geographical locations, the uncertainty of future orders, and sometimes extreme competitive pressure to reduce inventory costs. Linear optimization methods become cumbersome or intractable due to a large number of variables and nonlinear dependencies involved. Here we develop a complex systems approach to optimizing logistics networks based upon dimensional reduction methods and apply our approach to a case study of a manufacturing company. In order to characterize the complexity in customer behavior, we define a “customer space” in which individual customer behavior is described by only the two most relevant dimensions: the distance to production facilities over current transportation routes and the customer's demand frequency. These dimensions provide essential insight into the domain of effective strategies for customers; direct and indirect strategies. In the direct strategy, goods are sent to the customer directly from a production facility using box or bulk trucks. In the indirect strategy, in advance of an order by the customer, goods are shipped to an external warehouse near a customer using trains and then "last-mile" shipped by trucks when orders are placed. Each strategy applies to an area of the customer space with an indeterminate boundary between them. Specific company policies determine the location of the boundary generally. We then identify the optimal delivery strategy for each customer by constructing a detailed model of costs of transportation and temporary storage in a set of specified external warehouses. Customer spaces help give an aggregate view of customer behaviors and characteristics. They allow policymakers to compare customers and develop strategies based on the aggregate behavior of the system as a whole. In addition to optimization over existing facilities, using customer logistics and the k-means algorithm, we propose additional warehouse locations. We apply these methods to a medium-sized American manufacturing company with a particular logistics network, consisting of multiple production facilities, external warehouses, and customers along with three types of shipment methods (box truck, bulk truck and train). For the case study, our method forecasts 10.5% savings on yearly transportation costs and an additional 4.6% savings with three new warehouses.

Keywords: logistics network optimization, direct and indirect strategies, K-means algorithm, dimensional reduction

Procedia PDF Downloads 139

Authors: Doaa Wael, Naswa Abdelbaky

Abstract:

Malware is malicious software that is built to cause destructive actions and damage information systems and networks. Malware infections increase rapidly, and types of malware have become more sophisticated, which makes the malware detection process more difficult. On the other side, the Internet of Things IoT technology is vulnerable to malware attacks. These IoT devices are always connected to the internet and lack security. This makes them easy for hackers to access. These malware attacks are becoming the go-to attack for hackers. Thus, in order to deal with this challenge, new malware detection techniques are needed. Currently, building a blockchain solution that allows IoT devices to download any file from the internet and to verify/approve whether it is malicious or not is the need of the hour. In recent years, blockchain technology has stood as a solution to everything due to its features like decentralization, persistence, and anonymity. Moreover, using blockchain technology overcomes some difficulties in malware detection and improves the malware detection ratio over-than the techniques that do not utilize blockchain technology. In this paper, we study malware detection models which are based on blockchain technology. Furthermore, we elaborate on the effect of blockchain technology in malware detection, especially in the android environment.

Keywords: malware analysis, blockchain, malware attacks, malware detection approaches

Procedia PDF Downloads 87

Authors: Shady Gamal Aziz Shehata

Abstract:

Difficulty in defining construction quality arises due to perception based on the nature and requirements of the market, the different partners themselves and the results they want. Quantitative research was used in this constructivist research. A case-based study was conducted to assess the structures of positive attitudes and expectations in the context of quality improvement. A survey based on expert opinions was analyzed among construction organizations/companies operating in the construction industry in Pakistan. The financial strength, management structure and construction experience of the construction companies formed the basis of their selection. A good concept is visible at the project level and is seen as the most valuable part of the construction project. Each quality improvement technique was expected to increase the user's profits by improving the efficiency of the construction project. The Survey is useful for construction professionals to evaluate current construction concepts and expectations for the application of quality improvement techniques in construction projects.

Keywords: correlation analysis, lean construction tools, lean construction, logistic regression analysis, risk management, safety construction quality, expectation, improvement, perception

Procedia PDF Downloads 59

Authors: Donya Ashtiani Haghighi, Amirali Baniasadi

Abstract:

Coronavirus (COVID-19) disease has spread abruptly all over the world since the end of 2019. Computed tomography (CT) scans and X-ray images are used to detect this disease. Different Deep Neural Network (DNN)-based diagnosis solutions have been developed, mainly based on Convolutional Neural Networks (CNNs), to accelerate the identification of COVID-19 cases. However, CNNs lose important information in intermediate layers and require large datasets. In this paper, Capsule Network (CapsNet) is used. Capsule Network performs better than CNNs for small datasets. Accuracy of 0.9885, f1-score of 0.9883, precision of 0.9859, recall of 0.9908, and Area Under the Curve (AUC) of 0.9948 are achieved on the Capsule-based framework with hyperparameter tuning. Moreover, different dropout rates are investigated to decrease overfitting. Accordingly, a dropout rate of 0.1 shows the best results. Finally, we remove one convolution layer and decrease the number of trainable parameters to 146,752, which is a promising result.

Keywords: capsule network, dropout, hyperparameter tuning, classification

Procedia PDF Downloads 78

Authors: Aidan Ryan, Nahima Miah, Sahaj Kaur, Imogen Sutherland, Mohamed Saleh

Abstract:

Pulmonary symptoms are a common presentation to the emergency department. Due to a lack of understanding of the underlying pathophysiology, chronic liver disease is not often considered a cause of dyspnea. We present three patients who were admitted with significant respiratory distress secondary to hepatopulmonary syndrome, portopulmonary hypertension, and hepatic hydrothorax. The first is a 27-year-old male with a 6-month history of progressive dyspnea. The patient developed a severe type 1 respiratory failure with a PaO₂ of 6.3kPa and was escalated to critical care, where he was managed with non-invasive ventilation to maintain oxygen saturation. He had an agitated saline contrast echocardiogram, which showed the presence of a possible shunt. A CT angiogram revealed significant liver cirrhosis, portal hypertension, and large para esophageal varices. Ultrasound of the abdomen showed coarse liver echo patter and enlarged spleen. Along with these imaging findings, his biochemistry demonstrated impaired synthetic liver function with an elevated international normalized ratio (INR) of 1.4 and hypoalbuminaemia of 28g/L. The patient was then transferred to a tertiary center for further management. Further investigations confirmed a shunt of 56%, and liver biopsy confirmed cirrhosis suggestive of alpha-1-antitripsyin deficiency. The findings were consistent with a diagnosis of hepatopulmonary syndrome, and the patient is awaiting a liver transplant. The second patient is a 56-year-old male with a 12-month history of worsening dyspnoea, jaundice, confusion. His medical history included liver cirrhosis, portal hypertension, and grade 1 oesophageal varices secondary to significant alcohol excess. On admission, he developed a type 1 respiratory failure with PaO₂ of 6.8kPa requiring 10L of oxygen. CT pulmonary angiogram was negative for pulmonary embolism but showed evidence of chronic pulmonary hypertension, liver cirrhosis, and portal hypertension. An echocardiogram revealed a grossly dilated right heart with reduced function, pulmonary and tricuspid regurgitation, and pulmonary artery pressures estimated at 78mmHg. His biochemical markers showed impaired synthetic liver function with an INR of 3.2, albumin of 29g/L, along with raised bilirubin of 148mg/dL. During his long admission, he was managed with diuretics with little improvement. After three weeks, he was diagnosed with portopulmonary hypertension and was commenced on terlipressin. This resulted in successfully weaning off oxygen, and he was discharged home. The third patient is a 61-year-old male who presented to the local ambulatory care unit for therapeutic paracentesis on a background of decompensated liver cirrhosis. On presenting, he complained of a 2-day history of worsening dyspnoea and a productive cough. Chest x-ray showed a large pleural effusion, increasing in size over the previous eight months, and his abdomen was visibly distended with ascitic fluid. Unfortunately, the patient deteriorated, developing a larger effusion along with an increase in oxygen demand, and passed away. Without underlying cardiorespiratory disease, in the presence of a persistent pleural effusion with underlying decompensated cirrhosis, he was diagnosed with hepatic hydrothorax. While each presented with dyspnoea, the cause and underlying pathophysiology differ significantly from case to case. By describing these complications, we hope to improve awareness and aid prompt and accurate diagnosis, vital for improving outcomes.

Keywords: dyspnea, hepatic hydrothorax, hepatopulmonary syndrome, portopulmonary syndrome

Procedia PDF Downloads 121

Authors: Ashutosh Mishra, Nikhil Goyal

Abstract:

A 3D facial emotion recognition model based on deep learning is proposed in this paper. Two convolution layers and a pooling layer are employed in the deep learning architecture. After the convolution process, the pooling is finished. The probabilities for various classes of human faces are calculated using the sigmoid activation function. To verify the efficiency of deep learning-based systems, a set of faces. The Kaggle dataset is used to verify the accuracy of a deep learning-based face recognition model. The model's accuracy is about 65 percent, which is lower than that of other facial expression recognition techniques. Despite significant gains in representation precision due to the nonlinearity of profound image representations.

Keywords: facial recognition, computational intelligence, convolutional neural network, depth map

Procedia PDF Downloads 231

Authors: V. Sacca, A. Sarica, F. Novellino, S. Barone, T. Tallarico, E. Filippelli, A. Granata, P. Valentino, A. Quattrone

Abstract:

In the last few years, resting-state functional MRI (rs-fMRI) was widely used to investigate the architecture of brain networks by investigating the Blood Oxygenation Level Dependent response. This technique represented an interesting, robust and reliable approach to compare pathologic and healthy subjects in order to investigate neurodegenerative diseases evolution. On the other hand, the elaboration of rs-fMRI data resulted to be very prone to noise due to confounding factors especially the head motion. Head motion has long been known to be a source of artefacts in task-based functional MRI studies, but it has become a particularly challenging problem in recent studies using rs-fMRI. The aim of this work was to evaluate in MS patients a well-known motion correction algorithm from the FMRIB's Software Library - MCFLIRT - that could be applied to minimize the head motion distortions, allowing to correctly interpret rs-fMRI results.

Keywords: head motion correction, MCFLIRT algorithm, multiple sclerosis, resting state fMRI

Procedia PDF Downloads 212

Authors: M. G. Dirodi, G. Gugliotta, C. Leonardi

Abstract:

The member states shall establish zones and agglomerations throughout their territory to assess and manage air quality in order to comply with European directives. In Italy decree 155/2010, transposing Directive 2008/50/EC on ambient air quality and cleaner air for Europe, merged into a single act the previous provisions on ambient air quality assessment and management, including those resulting from the implementation of Directive 2004/107/EC relating to arsenic, cadmium, nickel, mercury, and polycyclic aromatic hydrocarbons in ambient air. Decree 155/2010 introduced stricter rules for identifying zones on the basis of the characteristics of the territory in spite of considering pollution levels, as it was in the past. The implementation of such new criteria has reduced the great variability of the previous zoning, leading to a significant reduction of the total number of zones and to a complete and uniform ambient air quality assessment and management throughout the Country. The present document is related to the new zones definition in Italy according to Decree 155/2010. In particular, the paper contains the description and the analysis of the outcome of zoning and classification.

Keywords: zones, agglomerations, air quality assessment, classification

Procedia PDF Downloads 330

Authors: JingWei Yu, Hong Yang Yu

Abstract:

At present, the increasingly serious air pollution in various cities of China has made people pay more attention to the air quality index(hereinafter referred to as AQI) of their living areas. To face this situation, it is of great significance to predict air pollution in heavily polluted areas. In this paper, based on the time series model of LSTM, a spatiotemporal prediction model of PM2.5 concentration in Mianyang, Sichuan Province, is established. The model fully considers the temporal variability and spatial distribution characteristics of PM2.5 concentration. The spatial correlation of air quality at different locations is based on the Air quality status of other nearby monitoring stations, including AQI and meteorological data to predict the air quality of a monitoring station. The experimental results show that the method has good prediction accuracy that the fitting degree with the actual measured data reaches more than 0.7, which can be applied to the modeling and prediction of the spatial and temporal distribution of regional PM2.5 concentration.

Keywords: LSTM, PM2.5, neural networks, spatio-temporal prediction

Procedia PDF Downloads 134