Search results for: TensorFlow probability

Authors: Mujtaba Roshan, John A. Schormans

Abstract:

Quality of Experience (QoE) drives churn in the broadband networks industry, and good QoE plays a large part in the retention of customers. QoE is known to be affected by the Quality of Service (QoS) factors packet loss probability (PLP), delay and delay jitter caused by the network. Earlier results have shown that the relationship between these QoS factors and QoE is non-linear, and may vary from application to application. We use the network emulator Netem as the basis for experimentation, and evaluate how QoE varies as we change the emulated QoS metrics. Focusing on Video-on-Demand, we discovered that the reported QoE may differ widely for users of different age groups, and that the most demanding age group (the youngest) can require an order of magnitude lower PLP to achieve the same QoE than is required by the most widely studied age group of users. We then used a bottleneck TCP model to evaluate the capacity cost of achieving an order of magnitude decrease in PLP, and found it be (almost always) a 3-fold increase in link capacity that was required.

Keywords: network capacity, packet loss probability, quality of experience, quality of service

Procedia PDF Downloads 243

Authors: Oh Hyeon Jeon, WooYoung Jung

Abstract:

In this study, seepage analysis was performed by the level difference between upstream and downstream of weir structure for safety evaluation of weir structure against flooding. Monte Carlo Simulation method was employed by considering the probability distribution of the adjacent ground parameter, i.e., permeability coefficient of weir structure. Moreover, by using a commercially available finite element program (ABAQUS), modeling of the weir structure is carried out. Based on this model, the characteristic of water seepage during flooding was determined at each water level with consideration of the uncertainty of their corresponding permeability coefficient. Subsequently, fragility function could be constructed based on this response from numerical analysis; this fragility function results could be used to determine the weakness of weir structure subjected to flooding disaster. They can also be used as a reference data that can comprehensively predict the probability of failur,e and the degree of damage of a weir structure.

Keywords: weir structure, seepage, flood disaster fragility, probabilistic risk assessment, Monte-Carlo simulation, permeability coefficient

Procedia PDF Downloads 320

Authors: Zhuoran Shan, Li Wan, Xianchun Zhang

Abstract:

With an increasing trend of regionalization and polycentricity in Chinese contemporary big cities, “sub-region life circle” turns to be an effective method on rational organization of urban function and spatial structure. By the method of questionnaire, network big data, route inversion on internet map, GIS spatial analysis and logistic regression, this article makes research on characteristic and formation mechanism of “sub-region life circle” based on human high-probability daily activity in Chinese big cities. Firstly, it shows that “sub-region life circle” has been a new general spatial sphere of residents' high-probability daily activity and mobility in China. Unlike the former analysis of the whole metropolitan or the micro community, “sub-region life circle” has its own characteristic on geographical sphere, functional element, spatial morphology and land distribution. Secondly, according to the analysis result with Binary Logistic Regression Model, the research also shows that seven factors including land-use mixed degree and bus station density impact the formation of “sub-region life circle” most, and then analyzes the index critical value of each factor. Finally, to establish a smarter “sub-region life circle”, this paper indicates that several strategies including jobs-housing fit, service cohesion and space reconstruction are the keys for its spatial organization optimization. This study expands the further understanding of cities' inner sub-region spatial structure based on human daily activity, and contributes to the theory of “life circle” in urban's meso-scale.

Keywords: sub-region life circle, characteristic, formation mechanism, human activity, spatial structure

Procedia PDF Downloads 268

Authors: Yousef Abu Nahleh, Alhasan Hakami, Arun Kumar, Fugen Daver

Abstract:

This study considers the problem of calculating safety stocks in disaster situations inventory systems that face demand uncertainties. Safety stocks are essential to make the supply chain, which is controlled by forecasts of customer needs, in response to demand uncertainties and to reach predefined goal service levels. To solve the problem of uncertainties due to the disaster situations affecting the industry sector, the concept of Emergency Safety Stock (ESS) was proposed. While there exists a huge body of literature on determining safety stock levels, this literature does not address the problem arising due to the disaster and dealing with the situations. In this paper, the problem of improving the Order Quantity Model to deal with uncertainty of demand due to disasters is managed by incorporating a new idea called ESS which is based on the probability of disaster occurrence and uses probability matrix calculated from the historical data.

Keywords: Emergency Safety Stocks, safety stocks, Order Quantity Model, supply chain

Procedia PDF Downloads 321

Authors: Jaime Martín-de-Nicolás, David Mata-Moya, Nerea del-Rey-Maestre, Pedro Gómez-del-Hoyo, María-Pilar Jarabo-Amores

Abstract:

Ship detection is nowadays quite an important issue in tasks related to sea traffic control, fishery management and ship search and rescue. Although it has traditionally been carried out by patrol ships or aircrafts, coverage and weather conditions and sea state can become a problem. Synthetic aperture radars can surpass these coverage limitations and work under any climatological condition. A fast CFAR ship detector based on a robust statistical modeling of sea clutter with respect to sea states in SAR images is used. In this paper, the minimum SNR required to obtain a given detection probability with a given false alarm rate for any sea state is determined. A Gaussian target model using real SAR data is considered. Results show that SNR does not depend heavily on the class considered. Provided there is some variation in the backscattering of targets in SAR imagery, the detection probability is limited and a post-processing stage based on morphology would be suitable.

Keywords: SAR, generalized gamma distribution, detection curves, radar detection

Procedia PDF Downloads 429

Authors: Tong He, Long Chen, Irag Mantegh, Wen-Fang Xie

Abstract:

This paper proposes an image-based obstacle avoidance and tracking target identification strategy in GPS-degraded or GPS-denied environment for an Unmanned Aerial Vehicle (UAV). The traditional force algorithm for obstacle avoidance could produce local minima area, in which UAV cannot get away obstacle effectively. In order to eliminate it, an artificial potential approach based on harmonic potential is proposed to guide the UAV to avoid the obstacle by using the vision system. And image-based visual servoing scheme (IBVS) has been adopted to implement the proposed obstacle avoidance approach. In IBVS, the pixel accuracy is a key factor to realize the obstacle avoidance. In this paper, the deep reinforcement learning framework has been applied by reducing pixel errors through constant interaction between the environment and the agent. In addition, the combination of OpenTLD and Tensorflow based on neural network is used to identify the type of tracking target. Numerical simulation in Matlab and ROS GAZEBO show the satisfactory result in target identification and obstacle avoidance.

Keywords: image-based visual servoing, obstacle avoidance, tracking target identification, deep reinforcement learning, artificial potential approach, neural network

Procedia PDF Downloads 114

Authors: Agnieszka Dudzik

Abstract:

The problem of correlation between random variables in the structural reliability analysis has been extensively discussed in literature on the subject. The cases taken under consideration were usually related to correlation between random variables from one side of ultimate limit state: correlation between particular loads applied on structure or correlation between resistance of particular members of a structure as a system. It has been proved that positive correlation between these random variables reduces the reliability of structure and increases the probability of failure. In the paper, the problem of correlation between random variables from both side of the limit state equation will be taken under consideration. The simplest case where these random variables are of the normal distributions will be concerned. The case when a degree of that correlation is described by the covariance or the coefficient of correlation will be used. Special attention will be paid on questions: how much that correlation changes the reliability level and can it be ignored. In reliability analysis will be used well-known methods for assessment of the failure probability: based on the Hasofer-Lind reliability index and Monte Carlo method adapted to the problem of correlation. The main purpose of this work will be a presentation how correlation of random variables influence on reliability index of steel bar structures. Structural design parameters will be defined as deterministic values and random variables. The latter will be correlated. The criterion of structural failure will be expressed by limit functions related to the ultimate and serviceability limit state. In the description of random variables will be used only for the normal distribution. Sensitivity of reliability index to the random variables will be defined. If the reliability index sensitivity due to the random variable X will be low when compared with other variables, it can be stated that the impact of this variable on failure probability is small. Therefore, in successive computations, it can be treated as a deterministic parameter. Sensitivity analysis leads to simplify the description of the mathematical model, determine the new limit functions and values of the Hasofer-Lind reliability index. In the examples, the NUMPRESS software will be used in the reliability analysis.

Keywords: correlation of random variables, reliability index, sensitivity of reliability index, steel structure

Procedia PDF Downloads 206

Authors: Arefeh Arabaninezhad, Ali Fakher

Abstract:

Since the deterministic analysis methods fail to take system uncertainties into account, probabilistic and non-probabilistic methods are suggested. Geotechnical analyses are used to determine the stress and deformation caused by construction; accordingly, many input variables which depend on ground behavior are required for geotechnical analyses. The Random Set approach is an applicable reliability analysis method when comprehensive sources of information are not available. Using Random Set method, with relatively small number of simulations compared to fully probabilistic methods, smooth extremes on system responses are obtained. Therefore random set approach has been proposed for reliability analysis in geotechnical problems. In the present study, the application of random set method in reliability analysis of deep excavations is investigated through three deep excavation projects which were monitored during the excavating process. A finite element code is utilized for numerical modeling. Two expected ranges, from different sources of information, are established for each input variable, and a specific probability assignment is defined for each range. To determine the most influential input variables and subsequently reducing the number of required finite element calculations, sensitivity analysis is carried out. Input data for finite element model are obtained by combining the upper and lower bounds of the input variables. The relevant probability share of each finite element calculation is determined considering the probability assigned to input variables present in these combinations. Horizontal displacement of the top point of excavation is considered as the main response of the system. The result of reliability analysis for each intended deep excavation is presented by constructing the Belief and Plausibility distribution function (i.e. lower and upper bounds) of system response obtained from deterministic finite element calculations. To evaluate the quality of input variables as well as applied reliability analysis method, the range of displacements extracted from models has been compared to the in situ measurements and good agreement is observed. The comparison also showed that Random Set Finite Element Method applies to estimate the horizontal displacement of the top point of deep excavation. Finally, the probability of failure or unsatisfactory performance of the system is evaluated by comparing the threshold displacement with reliability analysis results.

Keywords: deep excavation, random set finite element method, reliability analysis, uncertainty

Procedia PDF Downloads 243

Authors: Babak Mirbaha, Mahmoud Saffarzadeh, Atieh Asgari Toorzani

Abstract:

Pedestrians are the most vulnerable road users since they do not have a protective shell. One of the most common collisions for them is pedestrian-vehicle at intersections. In order to develop appropriate countermeasures to improve safety for them, researches have to be conducted to identify the factors that affect the risk of getting involved in such collisions. More specifically, this study investigates factors such as the influence of walking alone or having a baby while crossing the street, the observable age of pedestrian, the speed of pedestrians and the speed of approaching vehicles on risk perception of pedestrians. A nested logit model was used for modeling the behavioral structure of pedestrians. The results show that the presence of more lanes at intersections and not being alone especially having a baby while crossing, decrease the probability of taking a risk among pedestrians. Also, it seems that teenagers show more risky behaviors in crossing the street in comparison to other age groups. Also, the speed of approaching vehicles was considered significant. The probability of risk taking among pedestrians decreases by increasing the speed of approaching vehicle in both the first and the second lanes of crossings.

Keywords: pedestrians, intersection, nested logit, risk

Procedia PDF Downloads 151

Authors: Shahab Uddin, Kazi M. Uddin, Hamamah Sadiqa

Abstract:

The paper deals with the Banghabandhu Multipurpose Bridge (BMB), the 11th longest bridge in the world was constructed in 1998 aimed at contributing to promote economic development in Bangladesh. In recent years, however, the high incidence of traffic accidents and injuries at the bridge sites looms as a great safety concern. Investigation into the derailment of nine bogies out of thirteen of Dinajpur-bound intercity train ‘Drutajan Express ’were derailed and inclined on the Banghabandhu Multipurpose Bridge on 28 April 2014. The train accident in Bridge will be deep concern for both structural safety of bridge and people than other vehicles accident. In this study we analyzed the disaster probability of the Banghabandhu Multipurpose Bridge for accidents by checking the fitness of Bridge structure. We found that train accident impact is more risky than other vehicles accidents. We also found that socio-economic impact on Bangladesh will be deep concerned.

Keywords: train accident, derailment, disaster, socio-economic

Procedia PDF Downloads 276

Authors: Ashkan Zakaryazad, Ekrem Duman

Abstract:

A typical classification technique ranks the instances in a data set according to the likelihood of belonging to one (positive) class. A credit card (CC) fraud detection model ranks the transactions in terms of probability of being fraud. In fact, this approach is often criticized, because firms do not care about fraud probability but about the profitability or costliness of detecting a fraudulent transaction. The key contribution in this study is to focus on the profit maximization in the model building step. The artificial neural network proposed in this study works based on profit maximization instead of minimizing the error of prediction. Moreover, some studies have shown that the back propagation algorithm, similar to other gradient–based algorithms, usually gets trapped in local optima and swarm-based algorithms are more successful in this respect. In this study, we train our profit maximization ANN using the Migrating Birds optimization (MBO) which is introduced to literature recently.

Keywords: neural network, profit-based neural network, sum of squared errors (SSE), MBO, gradient descent

Procedia PDF Downloads 443

Authors: Yun-Pang Flötteröd, Jakob Erdmann

Abstract:

The human behaviors during evacuations are quite complex. One of the critical behaviors which affect the efficiency of evacuation is route choice. Therefore, the respective simulation modeling work needs to function properly. In this paper, Simulation of Urban Mobility’s (SUMO) current dynamic route modeling during evacuation, i.e. the rerouting functions, is examined with a real case study. The result consistency of the simulation and the reality is checked as well. Four influence factors (1) time to get information, (2) probability to cancel a trip, (3) probability to use navigation equipment, and (4) rerouting and information updating period are considered to analyze possible traffic impacts during the evacuation and to examine the rerouting functions in SUMO. Furthermore, some behavioral characters of the case study are analyzed with use of the corresponding detector data and applied in the simulation. The experiment results show that the dynamic route modeling in SUMO can deal with the proposed scenarios properly. Some issues and function needs related to route choice are discussed and further improvements are suggested.

Keywords: evacuation, microscopic traffic simulation, rerouting, SUMO

Procedia PDF Downloads 161

Authors: Justin Zhengjie Tan, Yang Zhao

Abstract:

Adiabatic Rapid Passage, a popular method of achieving population inversion, is studied in a Rabi dimer model in the presence of noise which acts as a dissipative environment. The integration of the multi-Davydov D2 Ansatz into the time-dependent variational framework enables us to model the intricate quantum system accurately. By influencing the system with a driving field strength resonant with the energy spacing, the probability of adiabatic rapid passage, which is modelled after the Landau Zener model, can be derived along with several other observables, such as the photon population. The effects of a dissipative environment can be reproduced by coupling the system to a common phonon mode. By manipulating the strength and frequency of the driving field, along with the coupling strength of the phonon mode to the qubits, we are able to control the qubits and photon dynamics and subsequently increase the probability of Adiabatic Rapid Passage happening.

Keywords: quantum electrodynamics, adiabatic rapid passage, Landau-Zener transitions, dissipative environment

Procedia PDF Downloads 54

Authors: K. S. Zaytsev, Y. R. Nartsissov

Abstract:

Glycine is one of the key inhibitory neurotransmitters in Central nervous system (CNS) meanwhile glycinergic transmission is highly dependable on its appropriate reuptake from synaptic cleft. Glycine transporters (GlyT) of types 1 and 2 are the enzymes providing glycine transport back to neuronal and glial cells along with Na⁺ and Cl⁻ co-transport. The distribution and stoichiometry of GlyT1 and GlyT2 differ in details, and GlyT2 is more interesting for the research as it reuptakes glycine to neuron cells, whereas GlyT1 is located in glial cells. In the process of GlyT2 activity, the translocation of the amino acid is accompanied with binding of both one chloride and three sodium ions consequently (two sodium ions for GlyT1). In the present study, we developed a computer simulator of GlyT2 and GlyT1 activity based on known experimental data for quantitative estimation of membrane glycine transport. The trait of a single protein functioning was described using the probability approach where each enzyme state was considered separately. Created scheme of transporter functioning realized as a consequence of elemental steps allowed to take into account each event of substrate association and dissociation. Computer experiments using up-to-date kinetic parameters allowed receiving the number of translocated glycine molecules, Na⁺ and Cl⁻ ions per time period. Flexibility of developed software makes it possible to evaluate glycine reuptake pattern in time under different internal characteristics of enzyme conformational transitions. We investigated the behavior of the system in a wide range of equilibrium constant (from 0.2 to 100), which is not determined experimentally. The significant influence of equilibrium constant in the range from 0.2 to 10 on the glycine transfer process is shown. The environmental conditions such as ion and glycine concentrations are decisive if the values of the constant are outside the specified range.

Keywords: glycine, inhibitory neurotransmitters, probability approach, single protein functioning

Procedia PDF Downloads 86

Authors: Surya R. Niraula, Devendra B Chhetry, Girish K. Singh, S. Nagesh, Frederick A. Connell

Abstract:

Background: Although random sampling is generally considered to be the gold standard for population-based research, the majority of drug abuse research is based on non-random sampling despite the well-known limitations of this kind of sampling. Method: We compared the statistical properties of two surveys of drug abuse in the same community: one using snowball sampling of drug users who then identified “friend controls” and the other using a random sample of non-drug users (controls) who then identified “friend cases.” Models to predict drug abuse based on risk factors were developed for each data set using conditional logistic regression. We compared the precision of each model using bootstrapping method and the predictive properties of each model using receiver operating characteristics (ROC) curves. Results: Analysis of 100 random bootstrap samples drawn from the snowball-sample data set showed a wide variation in the standard errors of the beta coefficients of the predictive model, none of which achieved statistical significance. One the other hand, bootstrap analysis of the random-sample data set showed less variation, and did not change the significance of the predictors at the 5% level when compared to the non-bootstrap analysis. Comparison of the area under the ROC curves using the model derived from the random-sample data set was similar when fitted to either data set (0.93, for random-sample data vs. 0.91 for snowball-sample data, p=0.35); however, when the model derived from the snowball-sample data set was fitted to each of the data sets, the areas under the curve were significantly different (0.98 vs. 0.83, p < .001). Conclusion: The proposed method of random sampling of controls appears to be superior from a statistical perspective to snowball sampling and may represent a viable alternative to snowball sampling.

Keywords: drug abuse, matched case-control study, non-probability sampling, probability sampling

Procedia PDF Downloads 467

Authors: Bernardo C. P. Albuquerque, Darym J. F. Campos

Abstract:

Increasing our ability to solve complex engineering problems is directly related to the processing capacity of computers. By means of such equipments, one is able to fast and accurately run numerical algorithms. Besides the increasing interest in numerical simulations, probabilistic approaches are also of great importance. This way, statistical tools have shown their relevance to the modelling of practical engineering problems. In general, statistical approaches to such problems consider that the random variables involved follow a normal distribution. This assumption tends to provide incorrect results when skew data is present since normal distributions are symmetric about their means. Thus, in order to visualize and quantify this aspect, 9 statistical distributions (symmetric and skew) have been considered to model a hypothetical slope stability problem. The data modeled is the friction angle of a superficial soil in Brasilia, Brazil. Despite the apparent universality, the normal distribution did not qualify as the best fit. In the present effort, data obtained in consolidated-drained triaxial tests and saturated direct shear tests have been modeled and used to analytically derive the probability density function (PDF) of the safety factor of a hypothetical slope based on Mohr-Coulomb rupture criterion. Therefore, based on this analysis, it is possible to explicitly derive the failure probability considering the friction angle as a random variable. Furthermore, it is possible to compare the stability analysis when the friction angle is modelled as a Dagum distribution (distribution that presented the best fit to the histogram) and as a Normal distribution. This comparison leads to relevant differences when analyzed in light of the risk management.

Keywords: statistical slope stability analysis, skew distributions, probability of failure, functions of random variables

Procedia PDF Downloads 307

Authors: Babak Kamrani, Nozar Kishi

Abstract:

Stochastic catalog represents the events module of the earthquake loss estimation models. It includes series of events with different magnitudes and corresponding frequencies/probabilities. For the development of the stochastic catalog, random or uniform sampling methods are used to sample the events from the seismicity model. For covering all the Magnitude Frequency Distribution (MFD), a huge number of events should be generated for the above-mentioned methods. Characteristic Event (CE) method chooses the events based on the interest of the insurance industry. We divide the MFD of each source into bins. We have chosen the bins based on the probability of the interest by the insurance industry. First, we have collected the information for the available seismic sources. Sources are divided into Fault sources, subduction, and events without specific fault source. We have developed the MFD for each of the individual and areal source based on the seismicity of the sources. Afterward, we have calculated the CE magnitudes based on the desired probability. To develop the stochastic catalog, we have introduced uncertainty to the location of the events too.

Keywords: stochastic catalogue, earthquake loss, uncertainty, characteristic event

Procedia PDF Downloads 269

Authors: Komal Babbar

Abstract:

Multiuser Detection is the intelligent estimation/demodulation of transmitted bits in the presence of Multiple Access Interference. The authors have presented the Bit-error rate (BER) achieved by linear multi-user detectors: Matched filter (which treats the MAI as AWGN), Decorrelating and MMSE. In this work, authors investigate the bit error probability analysis for Matched filter, decorrelating, and MMSE. This problem arises in several practical CDMA applications where the receiver may not have full knowledge of the number of active users and their signature sequences. In particular, the behavior of MAI at the output of the Multi-user detectors (MUD) is examined under various asymptotic conditions including large signal to noise ratio; large near-far ratios; and a large number of users. In the last section Authors also shows Matlab Simulation results for Multiuser detection techniques i.e., Matched filter, Decorrelating, MMSE for 2 users and 10 users.

Keywords: code division multiple access, decorrelating, matched filter, minimum mean square detection (MMSE) detection, multiple access interference (MAI), multiuser detection (MUD)

Procedia PDF Downloads 495

Authors: Wern Lin Yeo, Choo Kim Tan, Sook Ling Lew

Abstract:

Mathematics anxiety refers to the feeling of anxious when one having difficulties in solving mathematical problem. Mathematics anxiety is the most common type of anxiety among other types of anxiety which occurs among the students. However, level of anxiety among males and females are different. There were few past study were conducted to determine the relationship of anxiety and gender but there were still did not have an exact results. Hence, the purpose of this study is to determine the relationship of anxiety level between male and female undergraduates at a private university in Malaysia. Convenient sampling method used in this study in which the students were selected based on the grouping assigned by the faculty. There were 214 undergraduates who registered the probability courses had participated in this study. Mathematics Anxiety Rating Scale (MARS) was the instrument used in study which used to determine students’ anxiety level towards probability. Reliability and validity of instrument was done before the major study was conducted. In the major study, students were given briefing about the study conducted. Participation of this study were voluntary. Students were given consent form to determine whether they agree to participate in the study. Duration of two weeks were given for students to complete the given online questionnaire. The data collected will be analyzed using Statistical Package for the Social Sciences (SPSS) to determine the level of anxiety. There were three anxiety level, i.e., low, average and high. Students’ anxiety level were determined based on their scores obtained compared with the mean and standard deviation. If the scores obtained were below mean and standard deviation, the anxiety level was low. If the scores were at below and above the mean and between one standard deviation, the anxiety level was average. If the scores were above the mean and greater than one standard deviation, the anxiety level was high. Results showed that both of the gender were having average anxiety level. Males having high frequency of three anxiety level which were low, average and high anxiety level as compared to females. Hence, the mean values obtained for males (M = 3.62) was higher than females (M = 3.42). In order to be significant of anxiety level among the gender, the p-value should be less than .05. The p-value obtained in this study was .117. However, this value was greater than .05. Thus, there was no significant difference of anxiety level among the gender. In other words, there was no relationship of anxiety level with the gender.

Keywords: anxiety level, gender, mathematics anxiety, probability and statistics

Procedia PDF Downloads 267

Authors: Shanxiong Chen, Xu Han, Xiaolong Wang, Hui Ma

Abstract:

Yi is an ethnic group mainly living in mainland China, with its own spoken and written language systems, after development of thousands of years. Ancient Yi is one of the six ancient languages in the world, which keeps a record of the history of the Yi people and offers documents valuable for research into human civilization. Recognition of the characters in ancient Yi helps to transform the documents into an electronic form, making their storage and spreading convenient. Due to historical and regional limitations, research on recognition of ancient characters is still inadequate. Thus, deep learning technology was applied to the recognition of such characters. Five models were developed on the basis of the four-layer convolutional neural network (CNN). Alpha-Beta divergence was taken as a penalty term to re-encode output neurons of the five models. Two fully connected layers fulfilled the compression of the features. Finally, at the softmax layer, the orthographic features of ancient Yi characters were re-evaluated, their probability distributions were obtained, and characters with features of the highest probability were recognized. Tests conducted show that the method has achieved higher precision compared with the traditional CNN model for handwriting recognition of the ancient Yi.

Keywords: recognition, CNN, Yi character, divergence

Procedia PDF Downloads 136

Authors: Redouane Tlemsani, Redouane, Belkacem Kouninef, Abdelkader Benyettou

Abstract:

In this paper, our system is a Markovien system which we can see it like a Dynamic Bayesian Networks. One of the major interests of these systems resides in the complete training of the models (topology and parameters) starting from training data. The Bayesian Networks are representing models of dubious knowledge on complex phenomena. They are a union between the theory of probability and the graph theory in order to give effective tools to represent a joined probability distribution on a set of random variables. The representation of knowledge bases on description, by graphs, relations of causality existing between the variables defining the field of study. The theory of Dynamic Bayesian Networks is a generalization of the Bayesians networks to the dynamic processes. Our objective amounts finding the better structure which represents the relationships (dependencies) between the variables of a dynamic bayesian network. In applications in pattern recognition, one will carry out the fixing of the structure which obliges us to admit some strong assumptions (for example independence between some variables).

Keywords: Arabic on line character recognition, dynamic Bayesian network, pattern recognition, networks

Procedia PDF Downloads 583

Authors: M. Reni Sagayaraj, S. Anand Gnana Selvam, R. Reynald Susainathan

Abstract:

This study analyzed a queueing system with blocking and no waiting line. The customers arrive according to a Poisson process and the service times follow exponential distribution. There are two non-identical servers in the system. The queue discipline is FCFS, and the customers select the servers on fastest server first (FSF) basis. The service times are exponentially distributed with parameters μ1 and μ2 at servers I and II, respectively. Besides, the catastrophes occur in a Poisson manner with rate γ in the system. When server I is busy or blocked, the customer who arrives in the system leaves the system without being served. Such customers are called lost customers. The probability of losing a customer was computed for the system. The explicit time dependent probabilities of system size are obtained and a numerical example is presented in order to show the managerial insights of the model. Finally, the probability that arriving customer finds system busy and average number of server busy in steady state are obtained numerically.

Keywords: queueing system, blocking, poisson process, heterogeneous servers, queue discipline FCFS, busy period

Procedia PDF Downloads 477

Authors: Yong Wee Foo, Lai Meng Tang

Abstract:

Artificial Intelligence (AI), particularly the usage of deep neural networks for hierarchical representations from data, has found numerous complex applications across various domains, including computer vision, robotics, autonomous vehicles, and other scientific fields. However, their inherent “black box” nature can sometimes make it challenging for early researchers or school students of various levels to comprehend and trust the results they produce. Consequently, there has been a growing demand for reliable visualization tools in engineering and science education to help learners understand, trust, and explain a deep learning network. This has led to a notable emphasis on the visualization of AI in the research community in recent years. AI visualization tools are increasingly being adopted to significantly improve the comprehension of complex topics in deep learning. This paper proposes a novel approach to empower students to actively explore the inner workings of deep neural networks by combining the student-centered learning approach of flipped classroom models with the investigative power of AI visualization tools, namely, the TensorFlow Playground, the Local Interpretable Model-agnostic Explanations (LIME), and the SHapley Additive exPlanations (SHAP), for delivering an AI education curriculum. Combining the two factors is vital in fostering ownership, responsibility, and critical thinking skills in the age of AI.

Keywords: deep learning, explainable AI, AI visualization, representation learning

Procedia PDF Downloads 35

Authors: Theodoros Tziolas, Konstantinos Papageorgiou, Theodosios Theodosiou, Sebastian Pantoja, Nikos Dimitriou Dimosthenis, Elpiniki Papageorgiou

Abstract:

Assembly processes involve disparate materials that possess dissimilar resiliencies and, therefore, are prone to generating defective products. Manually performed quality inspection of such products is a time-consuming and susceptible to error process. The emerging computer vision techniques in smart manufacturing can alleviate the need for thorough, manually performed quality control. Object detection techniques provide crucial localization abilities, thus helping the operators further validate the identified defect with ease. In this work, several state-of-the-art object detection models are assessed in a real industrial imagery dataset and with the use of transfer learning. EfficientDet D2 is proposed for the identification and localization of antenna defects that are generated during the assembly process. To further enhance the dataset, heavy on-the-fly data augmentation was employed, along with synthetic samples generated with the use of image processing software. The proposed approach utilizing EfficientDet D2 can increase the Average Precision from 0.90 (at IoU 0.5) to 0.97 (at IoU 0.3). The overall performance is further evaluated by applying the F1-Score at each confidence score. For conducting the experiments, the TensorFlow object detection API is employed.

Keywords: defect detection, EfficientDet, deep learning, smart manufacturing, classification

Procedia PDF Downloads 22

Authors: Alexander E. Hramov, Vadim V. Grubov, Alexey A. Koronovskii, Maria K. Kurovskaуa, Anastasija E. Runnova

Abstract:

The perception of visual signals in the brain was among the first issues discussed in terms of multistability which has been introduced to provide mechanisms for information processing in biological neural systems. In this work the influence of the cognitive noise on the visual perception of multistable pictures has been investigated. The study includes an experiment with the bistable Necker cube illusion and the theoretical background explaining the obtained experimental results. In our experiments Necker cubes with different wireframe contrast were demonstrated repeatedly to different people and the probability of the choice of one of the cubes projection was calculated for each picture. The Necker cube was placed at the middle of a computer screen as black lines on a white background. The contrast of the three middle lines centered in the left middle corner was used as one of the control parameter. Between two successive demonstrations of Necker cubes another picture was shown to distract attention and to make a perception of next Necker cube more independent from the previous one. Eleven subjects, male and female, of the ages 20 through 45 were studied. The choice of the Necker cube projection was detected with the Electroencephalograph-recorder Encephalan-EEGR-19/26, Medicom MTD. To treat the experimental results we carried out theoretical consideration using the simplest double-well potential model with the presence of noise that led to the Fokker-Planck equation for the probability density of the stochastic process. At the first time an analytical solution for the probability of the selection of one of the Necker cube projection for different values of wireframe contrast have been obtained. Furthermore, having used the results of the experimental measurements with the help of the method of least squares we have calculated the value of the parameter corresponding to the cognitive noise of the person being studied. The range of cognitive noise parameter values for studied subjects turned to be [0.08; 0.55]. It should be noted, that experimental results have a good reproducibility, the same person being studied repeatedly another day produces very similar data with very close levels of cognitive noise. We found an excellent agreement between analytically deduced probability and the results obtained in the experiment. A good qualitative agreement between theoretical and experimental results indicates that even such a simple model allows simulating brain cognitive dynamics and estimating important cognitive characteristic of the brain, such as brain noise.

Keywords: bistability, brain, noise, perception, stochastic processes

Procedia PDF Downloads 421

Authors: Lian Kösters, Wendy Smits, Raymond Montizaan

Abstract:

The number of solo self-employed in the Netherlands has been increasing for years. The relative increase is among the largest in the EU. To explain this increase, most studies have focused on the supply side, workers who offer themselves as solo self-employed. The number of studies that focus on the demand side, the employer who hires the solo self-employed, is still scarce. Studies into employer behaviour conducted until now show that employers mainly choose self-employed workers when they have a temporary need for specialist knowledge, but also during projects or production peaks. These studies do not provide insight into the employers’ considerations for different contract types. In this study, interviews with employers were conducted, and available literature was consulted to provide an overview of the several factors employers use to compare different contract types. That input was used to set up a vignette study. This was carried out at the end of 2021 among almost 1000 business owners, HR managers, and business leaders of Dutch companies. Each respondent was given two sets of five fictitious candidates for two possible positions in their organization. They were asked to rank these candidates. The positions varied with regard to the type of tasks (core tasks or support tasks) and the time it took to train new people for the position. The respondents were asked additional questions about the positions, such as the required level of education, the duration, and the degree of predictability of tasks. The fictitious candidates varied, among other things, in the type of contract on which they would come to work for the organization. The results were analyzed using a rank-ordered logit analysis. This vignette setup makes it possible to see which factors are most important for employers when choosing to hire a solo self-employed person compared to other contracts. The results show that there are no indications that employers would want to hire solo self-employed workers en masse. They prefer regular employee contracts. The probability of being chosen with a solo self-employed contract over someone who comes to work as a temporary employee is 32 percent. This probability is even lower than for on-call and temporary agency workers. For a permanent contract, this probability is 46 percent. The results provide indications that employers consider knowledge and skills more important than the solo self-employed contract and that this can compensate. A solo self-employed candidate with 10 years of work experience has a 63 percent probability of being found attractive by an employer compared to a temporary employee without work experience. This suggests that employers are willing to give someone a less attractive contract for the employer if the worker so wishes. The results also show that the probability that a solo self-employed person is preferred over a candidate with a temporary employee contract is somewhat higher in business economics, administrative and technical professions. No significant results were found for factors where it was expected that solo self-employed workers are preferred more often, such as for unpredictable or temporary work.

Keywords: employer behaviour, rank-ordered logit analysis, solo self-employment, temporary contract, vignette study

Procedia PDF Downloads 45

Authors: K. Thiagarajan, K. Saranya, A. Veeraiah, B. Sudha

Abstract:

This paper presents a novel algorithm for secure, reliable and flexible transmission of big data in two hop wireless networks using cooperative jamming scheme. Two hop wireless networks consist of source, relay and destination nodes. Big data has to transmit from source to relay and from relay to destination by deploying security in physical layer. Cooperative jamming scheme determines transmission of big data in more secure manner by protecting it from eavesdroppers and malicious nodes of unknown location. The novel algorithm that ensures secure and energy balance transmission of big data, includes selection of data transmitting region, segmenting the selected region, determining probability ratio for each node (capture node, non-capture and eavesdropper node) in every segment, evaluating the probability using binary based evaluation. If it is secure transmission resume with the two- hop transmission of big data, otherwise prevent the attackers by cooperative jamming scheme and transmit the data in two-hop transmission.

Keywords: big data, two-hop transmission, physical layer wireless security, cooperative jamming, energy balance

Procedia PDF Downloads 456

Authors: P. Zarfam, M. Mansouri Baghbaderani

Abstract:

In seismic design, the proper reaction to the earthquake and the correct and accurate prediction of its subsequent effects on the structure are critical. Choose a proper probability distribution, which gives a more realistic probability of the structure's damage rate, is essential in damage discussions. With the development of design based on performance, analytical method of modal push over as an inexpensive, efficacious, and quick one in the estimation of the structures' seismic response is broadly used in engineering contexts. In this research three concrete frames of 3, 6, and 13 stories are analyzed in non-linear modal push over by 30 different earthquake records by OpenSEES software, then the detriment indexes of roof's displacement and relative displacement ratio of the stories are calculated by two parameters: peak ground acceleration and spectra acceleration. These indexes are used to establish the value of damage relations with log-normal distribution and logistics distribution. Finally the value of these relations is compared and the effect of height on the mentioned damage relations is studied, too.

Keywords: modal pushover analysis, concrete structure, seismic damage, log-normal distribution, logistic distribution

Procedia PDF Downloads 221

Authors: Nurul Bin Ibrahim

Abstract:

Advancements in neural networks have offered valuable insights into Fluid Dynamics, notably in addressing turbulence-related challenges. In this research, we introduce multiple applications of models of neural networks, namely Feed-Forward and Recurrent Neural Networks, to explore the relationship between jet formations and stratified turbulence within stochastically excited Boussinesq systems. Using machine learning tools like TensorFlow and PyTorch, the study has created models that effectively mimic and show the underlying features of the complex patterns of jet formation and stratified turbulence. These models do more than just help us understand these patterns; they also offer a faster way to solve problems in stochastic systems, improving upon traditional numerical techniques to solve stochastic differential equations such as the Euler-Maruyama method. In addition, the research includes a thorough comparison with the Statistical State Dynamics (SSD) approach, which is a well-established method for studying chaotic systems. This comparison helps evaluate how well neural networks can help us understand the complex relationship between jet formations and stratified turbulence. The results of this study underscore the potential of neural networks in computational physics and fluid dynamics, opening up new possibilities for more efficient and accurate simulations in these fields.

Keywords: neural networks, machine learning, computational fluid dynamics, stochastic systems, simulation, stratified turbulence

Procedia PDF Downloads 40

Authors: A. Preetha Priyadharshini, S. B. M. Priya

Abstract:

In this paper, we consider the MU-MISO downlink scenario, under imperfect channel state information (CSI). The main issue in imperfect CSI is to keep the probability of each user achievable outage rate below the given threshold level. Such a rate outage constraints present significant and analytical challenges. There are many probabilistic methods are used to minimize the transmit optimization problem under imperfect CSI. Here, decomposition based large deviation inequality and Bernstein type inequality convex restriction methods are used to perform the optimization problem under imperfect CSI. These methods are used for achieving improved output quality and lower complexity. They provide a safe tractable approximation of the original rate outage constraints. Based on these method implementations, performance has been evaluated in the terms of feasible rate and average transmission power. The simulation results are shown that all the two methods offer significantly improved outage quality and lower computational complexity.

Keywords: imperfect channel state information, outage probability, multiuser- multi input single output, channel state information

Procedia PDF Downloads 775