Search results for: probabilistic neural network(PNN)

Authors: P. C. Tewari, Parveen Kumar

Abstract:

The paper describes the availability analysis of milling system of a rice milling plant using probabilistic approach. The subsystems under study are special purpose machines. The availability analysis of the system is carried out to determine the effect of failure and repair rates of each subsystem on overall performance (i.e. steady state availability) of system concerned. Further, on the basis of effect of repair rates on the system availability, maintenance repair priorities have been suggested. The problem is formulated using Markov Birth-Death process taking exponential distribution for probable failures and repair rates. The first order differential equations associated with transition diagram are developed by using mnemonic rule. These equations are solved using normalizing conditions and recursive method to drive out the steady state availability expression of the system. The findings of the paper are presented and discussed with the plant personnel to adopt a suitable maintenance policy to increase the productivity of the rice milling plant.

Keywords: Markov process, milling system, availability modeling, rice milling plant.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1580

Authors: Fatemeh Behjati Ardakani, Fatemeh Khademian, Abbas Nowzari Dalini, Reza Ebrahimpour

Abstract:

Human activity is a major concern in a wide variety of applications, such as video surveillance, human computer interface and face image database management. Detecting and recognizing faces is a crucial step in these applications. Furthermore, major advancements and initiatives in security applications in the past years have propelled face recognition technology into the spotlight. The performance of existing face recognition systems declines significantly if the resolution of the face image falls below a certain level. This is especially critical in surveillance imagery where often, due to many reasons, only low-resolution video of faces is available. If these low-resolution images are passed to a face recognition system, the performance is usually unacceptable. Hence, resolution plays a key role in face recognition systems. In this paper we introduce a new low resolution face recognition system based on mixture of expert neural networks. In order to produce the low resolution input images we down-sampled the 48 × 48 ORL images to 12 × 12 ones using the nearest neighbor interpolation method and after that applying the bicubic interpolation method yields enhanced images which is given to the Principal Component Analysis feature extractor system. Comparison with some of the most related methods indicates that the proposed novel model yields excellent recognition rate in low resolution face recognition that is the recognition rate of 100% for the training set and 96.5% for the test set.

Keywords: Low resolution face recognition, Multilayered neuralnetwork, Mixture of experts neural network, Principal componentanalysis, Bicubic interpolation, Nearest neighbor interpolation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1727

Authors: Mohamed Ali KAMMOUN, Ahmed Ben HAMIDA

Abstract:

In this paper, we present a novel statistical approach to corpus-based speech synthesis. Classically, phonetic information is defined and considered as acoustic reference to be respected. In this way, many studies were elaborated for acoustical unit classification. This type of classification allows separating units according to their symbolic characteristics. Indeed, target cost and concatenation cost were classically defined for unit selection. In Corpus-Based Speech Synthesis System, when using large text corpora, cost functions were limited to a juxtaposition of symbolic criteria and the acoustic information of units is not exploited in the definition of the target cost. In this manuscript, we token in our consideration the unit phonetic information corresponding to acoustic information. This would be realized by defining a probabilistic linguistic Bi-grams model basically used for unit selection. The selected units would be extracted from the English TIMIT corpora.

Keywords: Unit selection, Corpus-based Speech Synthesis, Bigram model

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1445

Authors: Kasthurirangan Gopalakrishnan, Marshall R. Thompson, Anshu Manik

Abstract:

This paper describes the use of artificial neural networks (ANN) for predicting non-linear layer moduli of flexible airfield pavements subjected to new generation aircraft (NGA) loading, based on the deflection profiles obtained from Heavy Weight Deflectometer (HWD) test data. The HWD test is one of the most widely used tests for routinely assessing the structural integrity of airport pavements in a non-destructive manner. The elastic moduli of the individual pavement layers backcalculated from the HWD deflection profiles are effective indicators of layer condition and are used for estimating the pavement remaining life. HWD tests were periodically conducted at the Federal Aviation Administration-s (FAA-s) National Airport Pavement Test Facility (NAPTF) to monitor the effect of Boeing 777 (B777) and Beoing 747 (B747) test gear trafficking on the structural condition of flexible pavement sections. In this study, a multi-layer, feed-forward network which uses an error-backpropagation algorithm was trained to approximate the HWD backcalculation function. The synthetic database generated using an advanced non-linear pavement finite-element program was used to train the ANN to overcome the limitations associated with conventional pavement moduli backcalculation. The changes in ANN-based backcalculated pavement moduli with trafficking were used to compare the relative severity effects of the aircraft landing gears on the NAPTF test pavements.

Keywords: Airfield pavements, ANN, backcalculation, newgeneration aircraft

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2188

Authors: J. Menčík

Abstract:

Actual load, material characteristics and other quantities often differ from the design values. This can cause worse function, shorter life or failure of a civil engineering structure, a machine, vehicle or another appliance. The paper shows main causes of the uncertainties and deviations and presents a systematic approach and efficient tools for their elimination or mitigation of consequences. Emphasis is put on the design stage, which is most important for reliability ensuring. Principles of robust design and important tools are explained, including FMEA, sensitivity analysis and probabilistic simulation methods. The lifetime prediction of long-life objects can be improved by long-term monitoring of the load response and damage accumulation in operation. The condition evaluation of engineering structures, such as bridges, is often based on visual inspection and verbal description. Here, methods based on fuzzy logic can reduce the subjective influences.

Keywords: Design, fuzzy methods, Monte Carlo, reliability, robust design, sensitivity analysis, simulation, uncertainties.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1818

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 APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1170

Authors: Saudagar Abdul Khader Jilani, Syed Abdul Sattar

Abstract:

Image compression plays a vital role in today-s communication. The limitation in allocated bandwidth leads to slower communication. To exchange the rate of transmission in the limited bandwidth the Image data must be compressed before transmission. Basically there are two types of compressions, 1) LOSSY compression and 2) LOSSLESS compression. Lossy compression though gives more compression compared to lossless compression; the accuracy in retrievation is less in case of lossy compression as compared to lossless compression. JPEG, JPEG2000 image compression system follows huffman coding for image compression. JPEG 2000 coding system use wavelet transform, which decompose the image into different levels, where the coefficient in each sub band are uncorrelated from coefficient of other sub bands. Embedded Zero tree wavelet (EZW) coding exploits the multi-resolution properties of the wavelet transform to give a computationally simple algorithm with better performance compared to existing wavelet transforms. For further improvement of compression applications other coding methods were recently been suggested. An ANN base approach is one such method. Artificial Neural Network has been applied to many problems in image processing and has demonstrated their superiority over classical methods when dealing with noisy or incomplete data for image compression applications. The performance analysis of different images is proposed with an analysis of EZW coding system with Error Backpropagation algorithm. The implementation and analysis shows approximately 30% more accuracy in retrieved image compare to the existing EZW coding system.

Keywords: Accuracy, Compression, EZW, JPEG2000, Performance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1936

Authors: Kuen-Long Leu, Yung-Yuan Chen, Chin-Long Wey, Jwu-E Chen, Chung-Hsien Hsu

Abstract:

The increasing importance of FlexRay systems in automotive domain inspires unceasingly relative researches. One primary issue among researches is to verify the reliability of FlexRay systems either from protocol aspect or from system design aspect. However, research rarely discusses the effect of network topology on the system reliability. In this paper, we will illustrate how to model the reliability of FlexRay systems with various network topologies by a well-known probabilistic reasoning technology, Bayesian Network. In this illustration, we especially investigate the effectiveness of error containment built in star topology and fault-tolerant midpoint synchronization algorithm adopted in FlexRay communication protocol. Through a FlexRay steer-by-wire case study, the influence of different topologies on the failure probability of the FlexRay steerby- wire system is demonstrated. The notable value of this research is to show that the Bayesian Network inference is a powerful and feasible method for the reliability assessment of FlexRay systems.

Keywords: Bayesian Network, FlexRay, fault tolerance, network topology, reliability.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2033

Authors: M. F. Yilmaz, B. Ö. Çağlayan

Abstract:

Fragility curve is an effective common used tool to determine the earthquake performance of structural and nonstructural components. Also, it is used to determine the nonlinear behavior of bridges. There are many historical bridges in the Turkish railway network; the earthquake performances of these bridges are needed to be investigated. To derive fragility curve Intensity measures (IMs) and Engineering demand parameters (EDP) are needed to be determined. And the relation between IMs and EDP are needed to be derived. In this study, a typical simply supported steel girder riveted railway bridge is studied. Fragility curves of this bridge are derived by two parameters lognormal distribution. Time history analyses are done for selected 60 real earthquake data to determine the relation between IMs and EDP. Moreover, efficiency, practicality, and sufficiency of three different IMs are discussed. PGA, Sa(0.2s) and Sa(1s), the most common used IMs parameters for fragility curve in the literature, are taken into consideration in terms of efficiency, practicality and sufficiency.

Keywords: Railway bridges, earthquake performance, fragility analyses, selection of intensity measures.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 908

Authors: Siti Khadijah Che Osmi, Syed Mohd Ahmad

Abstract:

This paper presents a methodology to develop fragility curves for shallow tunnels so as to describe a relationship between seismic hazard and tunnel vulnerability. Emphasis is given to the influence of surrounding soil material properties because the dynamic behaviour of the tunnel mostly depends on it. Four ground properties of soils ranging from stiff to soft soils are selected. A 3D nonlinear time history analysis is used to evaluate the seismic response of the tunnel when subjected to five real earthquake ground intensities. The derived curves show the future probabilistic performance of the tunnels based on the predicted level of damage states corresponding to the peak ground acceleration. A comparison of the obtained results with the previous literature is provided to validate the reliability of the proposed fragility curves. Results show the significant role of soil properties and input motions in evaluating the seismic performance and response of shallow tunnels.

Keywords: Fragility analysis, seismic performance, tunnel lining, vulnerability.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1392

Authors: Wanhyun Cho, Soonja Kang, Sangkyoon Kim, Soonyoung Park

Abstract:

We present probabilistic multinomial Dirichlet classification model for multidimensional data and Gaussian process priors. Here, we have considered efficient computational method that can be used to obtain the approximate posteriors for latent variables and parameters needed to define the multiclass Gaussian process classification model. We first investigated the process of inducing a posterior distribution for various parameters and latent function by using the variational Bayesian approximations and important sampling method, and next we derived a predictive distribution of latent function needed to classify new samples. The proposed model is applied to classify the synthetic multivariate dataset in order to verify the performance of our model. Experiment result shows that our model is more accurate than the other approximation methods.

Keywords: Multinomial dirichlet classification model, Gaussian process priors, variational Bayesian approximation, Importance sampling, approximate posterior distribution, Marginal likelihood evidence.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1618

Authors: Anju Shri, Parvinder S. Sandhu, Vikas Gupta, Sanyam Anand

Abstract:

In literature, there are metrics for identifying the quality of reusable components but the framework that makes use of these metrics to precisely predict reusability of software components is still need to be worked out. These reusability metrics if identified in the design phase or even in the coding phase can help us to reduce the rework by improving quality of reuse of the software component and hence improve the productivity due to probabilistic increase in the reuse level. As CK metric suit is most widely used metrics for extraction of structural features of an object oriented (OO) software; So, in this study, tuned CK metric suit i.e. WMC, DIT, NOC, CBO and LCOM, is used to obtain the structural analysis of OO-based software components. An algorithm has been proposed in which the inputs can be given to K-Means Clustering system in form of tuned values of the OO software component and decision tree is formed for the 10-fold cross validation of data to evaluate the in terms of linguistic reusability value of the component. The developed reusability model has produced high precision results as desired.

Keywords: CK-Metric, Desicion Tree, Kmeans, Reusability.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1917

Authors: Fares Innal, Yves Dutuit, Mourad Chebila

Abstract:

The object of this work is the probabilistic performance evaluation of safety instrumented systems (SIS), i.e. the average probability of dangerous failure on demand (PFD_avg) and the average frequency of failure (PFH), taking into account the uncertainties related to the different parameters that come into play: failure rate (λ), common cause failure proportion (β), diagnostic coverage (DC)... This leads to an accurate and safe assessment of the safety integrity level (SIL) inherent to the safety function performed by such systems. This aim is in keeping with the requirement of the IEC 61508 standard with respect to handling uncertainty. To do this, we propose an approach that combines (1) Monte Carlo simulation and (2) fuzzy sets. Indeed, the first method is appropriate where representative statistical data are available (using pdf of the relating parameters), while the latter applies in the case characterized by vague and subjective information (using membership function). The proposed approach is fully supported with a suitable computer code.

Keywords: Fuzzy sets, Monte Carlo simulation, Safety instrumented system, Safety integrity level.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2782

Authors: Amar Aliche, Hocine Hammoum, Karima Bouzelha, Arezki Ben Abderrahmane

Abstract:

Traditionally, the dimensioning of storage tanks is conducted with a deterministic approach based on partial coefficients of safety. These coefficients are applied to take into account the uncertainties related to hazards on properties of materials used and applied loads. However, the use of these safety factors in the design process does not assure an optimal and reliable solution and can sometimes lead to a lack of robustness of the structure. The reliability theory based on a probabilistic formulation of constructions safety can respond in an adapted manner. It allows constructing a modelling in which uncertain data are represented by random variables, and therefore allows a better appreciation of safety margins with confidence indicators. The work presented in this paper consists of a mecano-reliability analysis of a concrete storage tank placed on ground. The classical method of Monte Carlo simulation is used to evaluate the failure probability of concrete tank by considering the seismic acceleration as random variable.

Keywords: Reliability approach, storage tanks, Monte Carlo simulation, seismic acceleration.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1491

Authors: Raja Singh Khela, R. K. Bansal, K. S. Sandhu, A. K. Goel

Abstract:

Self-Excited Induction Generator (SEIG) builds up voltage while it enters in its magnetic saturation region. Due to non-linear magnetic characteristics, the performance analysis of SEIG involves cumbersome mathematical computations. The dependence of air-gap voltage on saturated magnetizing reactance can only be established at rated frequency by conducting a laboratory test commonly known as synchronous run test. But, there is no laboratory method to determine saturated magnetizing reactance and air-gap voltage of SEIG at varying speed, terminal capacitance and other loading conditions. For overall analysis of SEIG, prior information of magnetizing reactance, generated frequency and air-gap voltage is essentially required. Thus, analytical methods are the only alternative to determine these variables. Non-existence of direct mathematical relationship of these variables for different terminal conditions has forced the researchers to evolve new computational techniques. Artificial Neural Networks (ANNs) are very useful for solution of such complex problems, as they do not require any a priori information about the system. In this paper, an attempt is made to use cascaded neural networks to first determine the generated frequency and magnetizing reactance with varying terminal conditions and then air-gap voltage of SEIG. The results obtained from the ANN model are used to evaluate the overall performance of SEIG and are found to be in good agreement with experimental results. Hence, it is concluded that analysis of SEIG can be carried out effectively using ANNs.

Keywords: Self-Excited Induction Generator, Artificial NeuralNetworks, Exciting Capacitance and Saturated magnetizingreactance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1695

Authors: Insung Jung, Gi-Nam Wang

Abstract:

In this paper, we present user pattern learning algorithm based MDSS (Medical Decision support system) under ubiquitous. Most of researches are focus on hardware system, hospital management and whole concept of ubiquitous environment even though it is hard to implement. Our objective of this paper is to design a MDSS framework. It helps to patient for medical treatment and prevention of the high risk patient (COPD, heart disease, Diabetes). This framework consist database, CAD (Computer Aided diagnosis support system) and CAP (computer aided user vital sign prediction system). It can be applied to develop user pattern learning algorithm based MDSS for homecare and silver town service. Especially this CAD has wise decision making competency. It compares current vital sign with user-s normal condition pattern data. In addition, the CAP computes user vital sign prediction using past data of the patient. The novel approach is using neural network method, wireless vital sign acquisition devices and personal computer DB system. An intelligent agent based MDSS will help elder people and high risk patients to prevent sudden death and disease, the physician to get the online access to patients- data, the plan of medication service priority (e.g. emergency case).

Keywords: Neural network, U-healthcare, MDSS, CAP, DSS.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1843

Authors: Deokho Kim, Wonwoo Lee, Jaewoong Lee, Teresa Ng, Gun-Ill Lee, Jiwon Jeong

Abstract:

This paper presents a method for improving object search accuracy using a deep learning model. A major limitation to provide accurate similarity with deep learning is the requirement of huge amount of data for training pairwise similarity scores (metrics), which is impractical to collect. Thus, similarity scores are usually trained with a relatively small dataset, which comes from a different domain, causing limited accuracy on measuring similarity. For this reason, this paper proposes a deep learning model that can be trained with a significantly small amount of data, a clustered data which of each cluster contains a set of visually similar images. In order to measure similarity distance with the proposed method, visual features of two images are extracted from intermediate layers of a convolutional neural network with various pooling methods, and the network is trained with pairwise similarity scores which is defined zero for images in identical cluster. The proposed method outperforms the state-of-the-art object similarity scoring techniques on evaluation for finding exact items. The proposed method achieves 86.5% of accuracy compared to the accuracy of the state-of-the-art technique, which is 59.9%. That is, an exact item can be found among four retrieved images with an accuracy of 86.5%, and the rest can possibly be similar products more than the accuracy. Therefore, the proposed method can greatly reduce the amount of training data with an order of magnitude as well as providing a reliable similarity metric.

Keywords: Visual search, deep learning, convolutional neural network, machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 832

Authors: Sotirios Raptis

Abstract:

Bayesian reasoning (BR) or Linear (Auto) Regression (AR/LR) can predict different sources of data using priors or other data, and can link social service demands in cohorts, while their consideration in isolation (self-prediction) may lead to service misuse ignoring the context. The paper advocates that BR with Binomial (BD), or Normal (ND) models or raw data (.D) as probabilistic updates can be compared to AR/LR to link services in Scotland and reduce cost by sharing healthcare (HC) resources. Clustering, cross-correlation, along with BR, LR, AR can better predict demand. Insurance companies and policymakers can link such services, and examples include those offered to the elderly, and low-income people, smoking-related services linked to mental health services, or epidemiological weight in children. 22 service packs are used that are published by Public Health Services (PHS) Scotland and Scottish Government (SG) from 1981 to 2019, broken into 110 year series (factors), joined using LR, AR, BR. The Primary component analysis found 11 significant factors, while C-Means (CM) clustering gave five major clusters.

Keywords: Bayesian probability, cohorts, data frames, regression, services, prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 232

Authors: Nurnadiah Z., Lazim A.

Abstract:

The design of weight is one of the important parts in fuzzy decision making, as it would have a deep effect on the evaluation results. Entropy is one of the weight measure based on objective evaluation. Non--probabilistic-type entropy measures for fuzzy set and interval type-2 fuzzy sets (IT2FS) have been developed and applied to weight measure. Since the entropy for (IT2FS) for decision making yet to be explored, this paper proposes a new objective weight method by using entropy weight method for multiple attribute decision making (MADM). This paper utilizes the nature of IT2FS concept in the evaluation process to assess the attribute weight based on the credibility of data. An example was presented to demonstrate the feasibility of the new method in decision making. The entropy measure of interval type-2 fuzzy sets yield flexible judgment and could be applied in decision making environment.

Keywords: Objective weight, entropy weight, multiple attributedecision making, type-2 fuzzy sets, interval type-2 fuzzy sets

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1665

Authors: P. C. Tewari, Rajiv Kumar, Dinesh Khanduja

Abstract:

This paper discusses the performance modeling and availability analysis of Yarn Dyeing System of a Textile Industry. The Textile Industry is a complex and repairable engineering system. Yarn Dyeing System of Textile Industry consists of five subsystems arranged in series configuration. For performance modeling and analysis of availability, a performance evaluating model has been developed with the help of mathematical formulation based on Markov-Birth-Death Process. The differential equations have been developed on the basis of Probabilistic Approach using a Transition Diagram. These equations have further been solved using normalizing condition in order to develop the steady state availability, a performance measure of the system concerned. The system performance has been further analyzed with the help of decision matrices. These matrices provide various availability levels for different combinations of failure and repair rates for various subsystems. The findings of this paper are therefore, considered to be useful for the analysis of availability and determination of the best possible maintenance strategies which can be implemented in future to enhance the system performance.

Keywords: Availability Analysis, Markov Process, Performance Modeling, Steady State Availability.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2305

Authors: Dim En Nyaung, Thin Lai Lai Thein

Abstract:

Due to the rapid increase of Internet, web opinion sources dynamically emerge which is useful for both potential customers and product manufacturers for prediction and decision purposes. These are the user generated contents written in natural languages and are unstructured-free-texts scheme. Therefore, opinion mining techniques become popular to automatically process customer reviews for extracting product features and user opinions expressed over them. Since customer reviews may contain both opinionated and factual sentences, a supervised machine learning technique applies for subjectivity classification to improve the mining performance. In this paper, we dedicate our work is the task of opinion summarization. Therefore, product feature and opinion extraction is critical to opinion summarization, because its effectiveness significantly affects the identification of semantic relationships. The polarity and numeric score of all the features are determined by Senti-WordNet Lexicon. The problem of opinion summarization refers how to relate the opinion words with respect to a certain feature. Probabilistic based model of supervised learning will improve the result that is more flexible and effective.

Keywords: Opinion Mining, Opinion Summarization, Sentiment Analysis, Text Mining.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2935

Authors: Rajvir Kaur, Jeewani Anupama Ginige

Abstract:

With recent trends in Big Data and advancements in Information and Communication Technologies, the healthcare industry is at the stage of its transition from clinician oriented to technology oriented. Many people around the world die of cancer because the diagnosis of disease was not done at an early stage. Nowadays, the computational methods in the form of Machine Learning (ML) are used to develop automated decision support systems that can diagnose cancer with high confidence in a timely manner. This paper aims to carry out the comparative evaluation of a selected set of ML classifiers on two existing datasets: breast cancer and cervical cancer. The ML classifiers compared in this study are Decision Tree (DT), Support Vector Machine (SVM), k-Nearest Neighbor (k-NN), Logistic Regression, Ensemble (Bagged Tree) and Artificial Neural Networks (ANN). The evaluation is carried out based on standard evaluation metrics Precision (P), Recall (R), F1-score and Accuracy. The experimental results based on the evaluation metrics show that ANN showed the highest-level accuracy (99.4%) when tested with breast cancer dataset. On the other hand, when these ML classifiers are tested with the cervical cancer dataset, Ensemble (Bagged Tree) technique gave better accuracy (93.1%) in comparison to other classifiers.

Keywords: Artificial neural networks, breast cancer, cancer dataset, classifiers, cervical cancer, F-score, logistic regression, machine learning, precision, recall, support vector machine.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1558

Authors: Peyman Shadman Heidari, Roohollah Ahmady Jazany, Mahmood Reza Mehran, Pouya Shadman Heidari, Mohammad khorasani

Abstract:

Modeling of Panel Zone (PZ) seismic behavior, because of its role in overall ductility and lateral stiffness of steel moment frames, has been considered a challenge for years. There are some studies regarding the effects of different doubler plates thicknesses and geometric properties of PZ on its seismic behavior. However, there is not much investigation on the effects of number of provided continuity plates in case of presence of one triangular haunch, two triangular haunches and rectangular haunch (T shape haunches) for exterior columns. In this research first detailed finite element models of 12tested connection of SAC joint venture were created and analyzed then obtained cyclic behavior backbone curves of these models besides other FE models for similar tests were used for neural network training. Then seismic behavior of these data is categorized according to continuity plate-s arrangements and differences in type of haunches. PZ with one-sided haunches have little plastic rotation. As the number of continuity plates increases due to presence of two triangular haunches (four continuity plate), there will be no plastic rotation, in other words PZ behaves in its elastic range. In the case of rectangular haunch, PZ show more plastic rotation in comparison with one-sided triangular haunch and especially double-sided triangular haunches. Moreover, the models that will be presented in case of triangular one-sided and double- sided haunches and rectangular haunches as a result of this study seem to have a proper estimation of PZ seismic behavior.

Keywords: Continuity plate, FE models, Neural network, Panel zone, Plastic rotation, Rectangular haunch, Seismic behavior

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2012

Authors: S. Dorbani, M. Badaoui, D. Benouar

Abstract:

The aim of this paper is to investigate the effect of the building fundamental period of reinforced concrete buildings of (6, 9, and 12-storey), with different floor plans: Symmetric, mono-symmetric, and unsymmetric. These structures are erected at different epicentral distances. Using the Boumerdes, Algeria (2003) earthquake data, we focused primarily on the establishment of the deterministic formulation linking the base shear force to two parameters: The first one is the fundamental period that represents the numerical fingerprint of the structure, and the second one is the epicentral distance used to represent the impact of the earthquake on this force. In a second step, with a view to highlight the effect of uncertainty in these parameters on the analyzed response, these parameters are modeled as random variables with a log-normal distribution. The variability of the coefficients of variation of the chosen uncertain parameters, on the statistics on the seismic base shear force, showed that the effect of uncertainty on fundamental period on this force statistics is low compared to the epicentral distance uncertainty influence.

Keywords: Base shear force, fundamental period, epicentral distance, uncertainty, lognormal variable, statistics.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1306

Authors: Yitao Lei, Xingxiang Zhai, Burra Venkata Durga Kumar

Abstract:

As the quantity and complexity of computing in large-scale software systems increase, distributed system computing becomes increasingly important. The distributed system realizes high-performance computing by collaboration between different computing resources. If there are no efficient resource scheduling resources, the abuse of distributed computing may cause resource waste and high costs. However, resource scheduling is usually an NP-hard problem, so we cannot find a general solution. However, some optimization algorithms exist like genetic algorithm, ant colony optimization, etc. The large scale of distributed systems makes this traditional optimization algorithm challenging to work with. Heuristic and machine learning algorithms are usually applied in this situation to ease the computing load. As a result, we do a review of traditional resource scheduling optimization algorithms and try to introduce a deep reinforcement learning method that utilizes the perceptual ability of neural networks and the decision-making ability of reinforcement learning. Using the machine learning method, we try to find important factors that influence the performance of distributed system computing and help the distributed system do an efficient computing resource scheduling. This paper surveys the application of deep reinforcement learning on distributed system computing resource scheduling. The research proposes a deep reinforcement learning method that uses a recurrent neural network to optimize the resource scheduling. The paper concludes the challenges and improvement directions for Deep Reinforcement Learning-based resource scheduling algorithms.

Keywords: Resource scheduling, deep reinforcement learning, distributed system, artificial intelligence.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 499

Authors: Rao Fu, Jie Chen, Shutian Zeng, Yiping Zhuang, Agus Sudjianto

Abstract:

Generative Adversarial Net (GAN) has proved to be a powerful machine learning tool in image data analysis and generation. In this paper, we propose to use Conditional Generative Adversarial Net (CGAN) to learn and simulate time series data. The conditions include both categorical and continuous variables with different auxiliary information. Our simulation studies show that CGAN has the capability to learn different types of normal and heavy-tailed distributions, as well as dependent structures of different time series. It also has the capability to generate conditional predictive distributions consistent with training data distributions. We also provide an in-depth discussion on the rationale behind GAN and the neural networks as hierarchical splines to establish a clear connection with existing statistical methods of distribution generation. In practice, CGAN has a wide range of applications in market risk and counterparty risk analysis: it can be applied to learn historical data and generate scenarios for the calculation of Value-at-Risk (VaR) and Expected Shortfall (ES), and it can also predict the movement of the market risk factors. We present a real data analysis including a backtesting to demonstrate that CGAN can outperform Historical Simulation (HS), a popular method in market risk analysis to calculate VaR. CGAN can also be applied in economic time series modeling and forecasting. In this regard, we have included an example of hypothetical shock analysis for economic models and the generation of potential CCAR scenarios by CGAN at the end of the paper.

Keywords: Conditional Generative Adversarial Net, market and credit risk management, neural network, time series.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1210

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.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1117

Authors: F. Rahnamay Roodposhti, M. Falah Shams, H. Kordlouie

Abstract:

The aim of the article is extending and developing econometrics and network structure based methods which are able to distinguish price manipulation in Tehran stock exchange. The principal goal of the present study is to offer model for approximating price manipulation in Tehran stock exchange. In order to do so by applying separation method a sample consisting of 397 companies accepted at Tehran stock exchange were selected and information related to their price and volume of trades during years 2001 until 2009 were collected and then through performing runs test, skewness test and duration correlative test the selected companies were divided into 2 sets of manipulated and non manipulated companies. In the next stage by investigating cumulative return process and volume of trades in manipulated companies, the date of starting price manipulation was specified and in this way the logit model, artificial neural network, multiple discriminant analysis and by using information related to size of company, clarity of information, ratio of P/E and liquidity of stock one year prior price manipulation; a model for forecasting price manipulation of stocks of companies present in Tehran stock exchange were designed. At the end the power of forecasting models were studied by using data of test set. Whereas the power of forecasting logit model for test set was 92.1%, for artificial neural network was 94.1% and multi audit analysis model was 90.2%; therefore all of the 3 aforesaid models has high power to forecast price manipulation and there is no considerable difference among forecasting power of these 3 models.

Keywords: Price Manipulation, Liquidity, Size of Company, Floating Stock, Information Clarity

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2857

Authors: Arash Taheri, Meysam Mohammadi-Amin, Seyed Hossein Moosavy

Abstract:

Medical applications are among the most impactful areas of microrobotics. The ultimate goal of medical microrobots is to reach currently inaccessible areas of the human body and carry out a host of complex operations such as minimally invasive surgery (MIS), highly localized drug delivery, and screening for diseases at their very early stages. Miniature, safe and efficient propulsion systems hold the key to maturing this technology but they pose significant challenges. A new type of propulsion developed recently, uses multi-flagella architecture inspired by the motility mechanism of prokaryotic microorganisms. There is a lack of efficient methods for designing this type of propulsion system. The goal of this paper is to overcome the lack and this way, a numerical strategy is proposed to design multi-flagella propulsion systems. The strategy is based on the implementation of the regularized stokeslet and rotlet theory, RFT theory and new approach of “local corrected velocity". The effects of shape parameters and angular velocities of each flagellum on overall flow field and on the robot net forces and moments are considered. Then a multi-layer perceptron artificial neural network is designed and employed to adjust the angular velocities of the motors for propulsion control. The proposed method applied successfully on a sample configuration and useful demonstrative results is obtained.

Keywords: Artificial Neural Network, Biomimetic Microrobots, Flagellar Propulsion, Swimming Robots.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1914

Authors: Anuja Vyas, Aikel Indurkhya, Hari Krishna Garg

Abstract:

Nearly 25 years have passed since the landmark publication of the Human Genome Project, yet scientists have only begun to scratch the surface of its potential benefits. To bridge this gap, a personalized genomic application has been envisioned as a transformative tool accessible to people worldwide. This innovative solution proposes an integrated framework combining blockchain technology, genome-specific applications, and data compression techniques, ensuring operations to be swift, secure, transparent, and space-efficient. The software harnesses advanced Artificial Intelligence and Machine Learning methodologies, such as neural networks, evaluation matrices, fuzzy logic, and expert systems, to analyze individual genomic data. It generates personalized reports by comparing a user's genome with a reference genome, highlighting significant differences. Blockchain technology, with its inherent security, encryption, and immutability features, is leveraged for robust data transport and storage. In addition, a 'Data Abbreviation' technique ensures that genetic data and reports occupy minimal space. This integrated approach promises to be a significant leap forward, potentially transforming human health and well-being on a global scale.

Keywords: Artificial intelligence in genomics, blockchain technology, data abbreviation, data compression, data security in genomics, data storage, expert systems, fuzzy logic, genome applications, genomic data analysis, human genome project, neural networks, personalized genomics.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 58