Search results for: RLS identification algorithm
4402 Walmart Sales Forecasting using Machine Learning in Python
Authors: Niyati Sharma, Om Anand, Sanjeev Kumar Prasad
Abstract:
Assuming future sale value for any of the organizations is one of the major essential characteristics of tactical development. Walmart Sales Forecasting is the finest illustration to work with as a beginner; subsequently, it has the major retail data set. Walmart uses this sales estimate problem for hiring purposes also. We would like to analyzing how the internal and external effects of one of the largest companies in the US can walk out their Weekly Sales in the future. Demand forecasting is the planned prerequisite of products or services in the imminent on the basis of present and previous data and different stages of the market. Since all associations is facing the anonymous future and we do not distinguish in the future good demand. Hence, through exploring former statistics and recent market statistics, we envisage the forthcoming claim and building of individual goods, which are extra challenging in the near future. As a result of this, we are producing the required products in pursuance of the petition of the souk in advance. We will be using several machine learning models to test the exactness and then lastly, train the whole data by Using linear regression and fitting the training data into it. Accuracy is 8.88%. The extra trees regression model gives the best accuracy of 97.15%.Keywords: random forest algorithm, linear regression algorithm, extra trees classifier, mean absolute error
Procedia PDF Downloads 1474401 Supervised/Unsupervised Mahalanobis Algorithm for Improving Performance for Cyberattack Detection over Communications Networks
Authors: Radhika Ranjan Roy
Abstract:
Deployment of machine learning (ML)/deep learning (DL) algorithms for cyberattack detection in operational communications networks (wireless and/or wire-line) is being delayed because of low-performance parameters (e.g., recall, precision, and f₁-score). If datasets become imbalanced, which is the usual case for communications networks, the performance tends to become worse. Complexities in handling reducing dimensions of the feature sets for increasing performance are also a huge problem. Mahalanobis algorithms have been widely applied in scientific research because Mahalanobis distance metric learning is a successful framework. In this paper, we have investigated the Mahalanobis binary classifier algorithm for increasing cyberattack detection performance over communications networks as a proof of concept. We have also found that high-dimensional information in intermediate features that are not utilized as much for classification tasks in ML/DL algorithms are the main contributor to the state-of-the-art of improved performance of the Mahalanobis method, even for imbalanced and sparse datasets. With no feature reduction, MD offers uniform results for precision, recall, and f₁-score for unbalanced and sparse NSL-KDD datasets.Keywords: Mahalanobis distance, machine learning, deep learning, NS-KDD, local intrinsic dimensionality, chi-square, positive semi-definite, area under the curve
Procedia PDF Downloads 754400 A Priority Based Imbalanced Time Minimization Assignment Problem: An Iterative Approach
Authors: Ekta Jain, Kalpana Dahiya, Vanita Verma
Abstract:
This paper discusses a priority based imbalanced time minimization assignment problem dealing with the allocation of n jobs to m < n persons in which the project is carried out in two stages, viz. Stage-I and Stage-II. Stage-I consists of n1 ( < m) primary jobs and Stage-II consists of remaining (n-n1) secondary jobs which are commenced only after primary jobs are finished. Each job is to be allocated to exactly one person, and each person has to do at least one job. It is assumed that nature of the Stage-I jobs is such that one person can do exactly one primary job whereas a person can do more than one secondary job in Stage-II. In a particular stage, all persons start doing the jobs simultaneously, but if a person is doing more than one job, he does them one after the other in any order. The aim of the proposed study is to find the feasible assignment which minimizes the total time for the two stage execution of the project. For this, an iterative algorithm is proposed, which at each iteration, solves a constrained imbalanced time minimization assignment problem to generate a pair of Stage-I and Stage-II times. For solving this constrained problem, an algorithm is developed in the current paper. Later, alternate combinations based method to solve the priority based imbalanced problem is also discussed and a comparative study is carried out. Numerical illustrations are provided in support of the theory.Keywords: assignment, imbalanced, priority, time minimization
Procedia PDF Downloads 2284399 Machine Learning Approach for Mutation Testing
Authors: Michael Stewart
Abstract:
Mutation testing is a type of software testing proposed in the 1970s where program statements are deliberately changed to introduce simple errors so that test cases can be validated to determine if they can detect the errors. Test cases are executed against the mutant code to determine if one fails, detects the error and ensures the program is correct. One major issue with this type of testing was it became intensive computationally to generate and test all possible mutations for complex programs. This paper used reinforcement learning and parallel processing within the context of mutation testing for the selection of mutation operators and test cases that reduced the computational cost of testing and improved test suite effectiveness. Experiments were conducted using sample programs to determine how well the reinforcement learning-based algorithm performed with one live mutation, multiple live mutations and no live mutations. The experiments, measured by mutation score, were used to update the algorithm and improved accuracy for predictions. The performance was then evaluated on multiple processor computers. With reinforcement learning, the mutation operators utilized were reduced by 50 – 100%.Keywords: automated-testing, machine learning, mutation testing, parallel processing, reinforcement learning, software engineering, software testing
Procedia PDF Downloads 1954398 Comparing the Detection of Autism Spectrum Disorder within Males and Females Using Machine Learning Techniques
Authors: Joseph Wolff, Jeffrey Eilbott
Abstract:
Autism Spectrum Disorders (ASD) are a spectrum of social disorders characterized by deficits in social communication, verbal ability, and interaction that can vary in severity. In recent years, researchers have used magnetic resonance imaging (MRI) to help detect how neural patterns in individuals with ASD differ from those of neurotypical (NT) controls for classification purposes. This study analyzed the classification of ASD within males and females using functional MRI data. Functional connectivity (FC) correlations among brain regions were used as feature inputs for machine learning algorithms. Analysis was performed on 558 cases from the Autism Brain Imaging Data Exchange (ABIDE) I dataset. When trained specifically on females, the algorithm underperformed in classifying the ASD subset of our testing population. Although the subject size was relatively smaller in the female group, the manual matching of both male and female training groups helps explain the algorithm’s bias, indicating the altered sex abnormalities in functional brain networks compared to typically developing peers. These results highlight the importance of taking sex into account when considering how generalizations of findings on males with ASD apply to females.Keywords: autism spectrum disorder, machine learning, neuroimaging, sex differences
Procedia PDF Downloads 2054397 A Methodology for the Identification of Technological Gaps and the Measurement of the Level of Technological Acceptance in the Rural Sector in Colombia
Authors: Anyi Katherine Garzon Robles, Luis Carlos Gomez Florez
Abstract:
Since the advent of the Internet, the use of Information Technologies (IT) has increased exponentially. The field of informatics and telecommunications has put on the table countless possibilities for the development of different socio-economic activities, promoting a change of social paradigm and the emergence of the so-called information and knowledge society. For more than a decade, the Colombian government has been working on the incorporation of IT into the public sector through an e-government strategy. However, to date, many technological gaps has not yet been identified in the country to our knowledge, especially in rural areas and far from large cities, where factors such as low investment and the expansion of the armed conflict have led to economic and technological stagnation. This paper presents the research results obtained from the execution of a research project, which was approach from a qualitative approach and a methodological design of a participatory action research type. This design consists of nine fundamental stages divided into four work cycles. For which different strategies for data collection and analysis were established. From which, a methodology was obtained for the identification of technological gaps and the measurement of the level of technological acceptance in the rural sector, based on the TAM (Technology Acceptance Model) model, as a previous activity to the development of IT solutions framed in the e-government strategy in Colombia. The result of this research work represents a contribution from academia for the improvement of the country's technological development and a guide for the proper planning of IT solutions aimed at promoting a close relationship between government and citizens.Keywords: E-government, knowledge society, level of technological acceptance, technological gaps, technology acceptance model
Procedia PDF Downloads 2354396 Flow Analysis of Viscous Nanofluid Due to Rotating Rigid Disk with Navier’s Slip: A Numerical Study
Authors: Khalil Ur Rehman, M. Y. Malik, Usman Ali
Abstract:
In this paper, the problem proposed by Von Karman is treated in the attendance of additional flow field effects when the liquid is spaced above the rotating rigid disk. To be more specific, a purely viscous fluid flow yield by rotating rigid disk with Navier’s condition is considered in both magnetohydrodynamic and hydrodynamic frames. The rotating flow regime is manifested with heat source/sink and chemically reactive species. Moreover, the features of thermophoresis and Brownian motion are reported by considering nanofluid model. The flow field formulation is obtained mathematically in terms of high order differential equations. The reduced system of equations is solved numerically through self-coded computational algorithm. The pertinent outcomes are discussed systematically and provided through graphical and tabular practices. A simultaneous way of study makes this attempt attractive in this sense that the article contains dual framework and validation of results with existing work confirms the execution of self-coded algorithm for fluid flow regime over a rotating rigid disk.Keywords: Navier’s condition, Newtonian fluid model, chemical reaction, heat source/sink
Procedia PDF Downloads 1674395 Performance Enrichment of Deep Feed Forward Neural Network and Deep Belief Neural Networks for Fault Detection of Automobile Gearbox Using Vibration Signal
Authors: T. Praveenkumar, Kulpreet Singh, Divy Bhanpuriya, M. Saimurugan
Abstract:
This study analysed the classification accuracy for gearbox faults using Machine Learning Techniques. Gearboxes are widely used for mechanical power transmission in rotating machines. Its rotating components such as bearings, gears, and shafts tend to wear due to prolonged usage, causing fluctuating vibrations. Increasing the dependability of mechanical components like a gearbox is hampered by their sealed design, which makes visual inspection difficult. One way of detecting impending failure is to detect a change in the vibration signature. The current study proposes various machine learning algorithms, with aid of these vibration signals for obtaining the fault classification accuracy of an automotive 4-Speed synchromesh gearbox. Experimental data in the form of vibration signals were acquired from a 4-Speed synchromesh gearbox using Data Acquisition System (DAQs). Statistical features were extracted from the acquired vibration signal under various operating conditions. Then the extracted features were given as input to the algorithms for fault classification. Supervised Machine Learning algorithms such as Support Vector Machines (SVM) and unsupervised algorithms such as Deep Feed Forward Neural Network (DFFNN), Deep Belief Networks (DBN) algorithms are used for fault classification. The fusion of DBN & DFFNN classifiers were architected to further enhance the classification accuracy and to reduce the computational complexity. The fault classification accuracy for each algorithm was thoroughly studied, tabulated, and graphically analysed for fused and individual algorithms. In conclusion, the fusion of DBN and DFFNN algorithm yielded the better classification accuracy and was selected for fault detection due to its faster computational processing and greater efficiency.Keywords: deep belief networks, DBN, deep feed forward neural network, DFFNN, fault diagnosis, fusion of algorithm, vibration signal
Procedia PDF Downloads 1084394 Feasibility Study of MongoDB and Radio Frequency Identification Technology in Asset Tracking System
Authors: Mohd Noah A. Rahman, Afzaal H. Seyal, Sharul T. Tajuddin, Hartiny Md Azmi
Abstract:
Taking into consideration the real time situation specifically the higher academic institutions, small, medium to large companies, public to private sectors and the remaining sectors, do experience the inventory or asset shrinkages due to theft, loss or even inventory tracking errors. This happening is due to a zero or poor security systems and measures being taken and implemented in their organizations. Henceforth, implementing the Radio Frequency Identification (RFID) technology into any manual or existing web-based system or web application can simply deter and will eventually solve certain major issues to serve better data retrieval and data access. Having said, this manual or existing system can be enhanced into a mobile-based system or application. In addition to that, the availability of internet connections can aid better services of the system. Such involvement of various technologies resulting various privileges to individuals or organizations in terms of accessibility, availability, mobility, efficiency, effectiveness, real-time information and also security. This paper will look deeper into the integration of mobile devices with RFID technologies with the purpose of asset tracking and control. Next, it is to be followed by the development and utilization of MongoDB as the main database to store data and its association with RFID technology. Finally, the development of a web based system which can be viewed in a mobile based formation with the aid of Hypertext Preprocessor (PHP), MongoDB, Hyper-Text Markup Language 5 (HTML5), Android, JavaScript and AJAX programming language.Keywords: RFID, asset tracking system, MongoDB, NoSQL
Procedia PDF Downloads 3034393 Scalable Systolic Multiplier over Binary Extension Fields Based on Two-Level Karatsuba Decomposition
Authors: Chiou-Yng Lee, Wen-Yo Lee, Chieh-Tsai Wu, Cheng-Chen Yang
Abstract:
Shifted polynomial basis (SPB) is a variation of polynomial basis representation. SPB has potential for efficient bit-level and digit-level implementations of multiplication over binary extension fields with subquadratic space complexity. For efficient implementation of pairing computation with large finite fields, this paper presents a new SPB multiplication algorithm based on Karatsuba schemes, and used that to derive a novel scalable multiplier architecture. Analytical results show that the proposed multiplier provides a trade-off between space and time complexities. Our proposed multiplier is modular, regular, and suitable for very-large-scale integration (VLSI) implementations. It involves less area complexity compared to the multipliers based on traditional decomposition methods. It is therefore, more suitable for efficient hardware implementation of pairing based cryptography and elliptic curve cryptography (ECC) in constraint driven applications.Keywords: digit-serial systolic multiplier, elliptic curve cryptography (ECC), Karatsuba algorithm (KA), shifted polynomial basis (SPB), pairing computation
Procedia PDF Downloads 3594392 Detecting Anomalous Matches: An Empirical Study from National Basketball Association
Authors: Jacky Liu, Dulani Jayasuriya, Ryan Elmore
Abstract:
Match fixing and anomalous sports events have increasingly threatened the integrity of professional sports, prompting concerns about existing detection methods. This study addresses prior research limitations in match fixing detection, improving the identification of potential fraudulent matches by incorporating advanced anomaly detection techniques. We develop a novel method to identify anomalous matches and player performances by examining series of matches, such as playoffs. Additionally, we investigate bettors' potential profits when avoiding anomaly matches and explore factors behind unusual player performances. Our literature review covers match fixing detection, match outcome forecasting models, and anomaly detection methods, underscoring current limitations and proposing a new sports anomaly detection method. Our findings reveal anomalous series in the 2022 NBA playoffs, with the Phoenix Suns vs Dallas Mavericks series having the lowest natural occurrence probability. We identify abnormal player performances and bettors' profits significantly decrease when post-season matches are included. This study contributes by developing a new approach to detect anomalous matches and player performances, and assisting investigators in identifying responsible parties. While we cannot conclusively establish reasons behind unusual player performances, our findings suggest factors such as team financial difficulties, executive mismanagement, and individual player contract issues.Keywords: anomaly match detection, match fixing, match outcome forecasting, problematic players identification
Procedia PDF Downloads 774391 Groundwater Potential Zone Identification in Unconsolidated Aquifer Using Geophysical Techniques around Tarbela Ghazi, District Haripur, Pakistan
Authors: Syed Muzyan Shahzad, Liu Jianxin, Asim Shahzad, Muhammad Sharjeel Raza, Sun Ya, Fanidi Meryem
Abstract:
Electrical resistivity investigation was conducted in vicinity of Tarbela Ghazi, in order to study the subsurface layer with a view of determining the depth to the aquifer and thickness of groundwater potential zones. Vertical Electrical Sounding (VES) using Schlumberger array was carried out at 16 VES stations. Well logging data at four tube wells have been used to mark the super saturated zones with great discharge rate. The present paper shows a geoelectrical identification of the lithology and an estimate of the relationship between the resistivity and Dar Zarrouk parameters (transverse unit resistance and longitudinal unit conductance). The VES results revealed both homogeneous and heterogeneous nature of the subsurface strata. Aquifer is unconfined to confine in nature, and at few locations though perched aquifer has been identified, groundwater potential zones are developed in unconsolidated deposits layers and more than seven geo-electric layers are observed at some VES locations. Saturated zones thickness ranges from 5 m to 150 m, whereas at few area aquifer is beyond 150 m thick. The average anisotropy, transvers resistance and longitudinal conductance values are 0.86 %, 35750.9821 Ω.m2, 0.729 Siemens, respectively. The transverse unit resistance values fluctuate all over the aquifer system, whereas below at particular depth high values are observed, that significantly associated with the high transmissivity zones. The groundwater quality in all analyzed samples is below permissible limit according to World Health Standard (WHO).Keywords: aquifer, Dar Zarrouk parameters, geoelectric layers, Tarbela Ghazi
Procedia PDF Downloads 1904390 Hybrid Precoder Design Based on Iterative Hard Thresholding Algorithm for Millimeter Wave Multiple-Input-Multiple-Output Systems
Authors: Ameni Mejri, Moufida Hajjaj, Salem Hasnaoui, Ridha Bouallegue
Abstract:
The technology advances have most lately made the millimeter wave (mmWave) communication possible. Due to the huge amount of spectrum that is available in MmWave frequency bands, this promising candidate is considered as a key technology for the deployment of 5G cellular networks. In order to enhance system capacity and achieve spectral efficiency, very large antenna arrays are employed at mmWave systems by exploiting array gain. However, it has been shown that conventional beamforming strategies are not suitable for mmWave hardware implementation. Therefore, new features are required for mmWave cellular applications. Unlike traditional multiple-input-multiple-output (MIMO) systems for which only digital precoders are essential to accomplish precoding, MIMO technology seems to be different at mmWave because of digital precoding limitations. Moreover, precoding implements a greater number of radio frequency (RF) chains supporting more signal mixers and analog-to-digital converters. As RF chain cost and power consumption is increasing, we need to resort to another alternative. Although the hybrid precoding architecture has been regarded as the best solution based on a combination between a baseband precoder and an RF precoder, we still do not get the optimal design of hybrid precoders. According to the mapping strategies from RF chains to the different antenna elements, there are two main categories of hybrid precoding architecture. Given as a hybrid precoding sub-array architecture, the partially-connected structure reduces hardware complexity by using a less number of phase shifters, whereas it sacrifices some beamforming gain. In this paper, we treat the hybrid precoder design in mmWave MIMO systems as a problem of matrix factorization. Thus, we adopt the alternating minimization principle in order to solve the design problem. Further, we present our proposed algorithm for the partially-connected structure, which is based on the iterative hard thresholding method. Through simulation results, we show that our hybrid precoding algorithm provides significant performance gains over existing algorithms. We also show that the proposed approach reduces significantly the computational complexity. Furthermore, valuable design insights are provided when we use the proposed algorithm to make simulation comparisons between the hybrid precoding partially-connected structure and the fully-connected structure.Keywords: alternating minimization, hybrid precoding, iterative hard thresholding, low-complexity, millimeter wave communication, partially-connected structure
Procedia PDF Downloads 3184389 A New DIDS Design Based on a Combination Feature Selection Approach
Authors: Adel Sabry Eesa, Adnan Mohsin Abdulazeez Brifcani, Zeynep Orman
Abstract:
Feature selection has been used in many fields such as classification, data mining and object recognition and proven to be effective for removing irrelevant and redundant features from the original data set. In this paper, a new design of distributed intrusion detection system using a combination feature selection model based on bees and decision tree. Bees algorithm is used as the search strategy to find the optimal subset of features, whereas decision tree is used as a judgment for the selected features. Both the produced features and the generated rules are used by Decision Making Mobile Agent to decide whether there is an attack or not in the networks. Decision Making Mobile Agent will migrate through the networks, moving from node to another, if it found that there is an attack on one of the nodes, it then alerts the user through User Interface Agent or takes some action through Action Mobile Agent. The KDD Cup 99 data set is used to test the effectiveness of the proposed system. The results show that even if only four features are used, the proposed system gives a better performance when it is compared with the obtained results using all 41 features.Keywords: distributed intrusion detection system, mobile agent, feature selection, bees algorithm, decision tree
Procedia PDF Downloads 4034388 Pavement Failures and Its Maintenance
Authors: Maulik L. Sisodia, Tirth K. Raval, Aarsh S. Mistry
Abstract:
This paper summarizes the ongoing researches about the defects in both flexible and rigid pavement and the maintenance in both flexible and rigid pavements. Various defects in pavements have been identified since the existence of both flexible and rigid pavement. Flexible Pavement failure is defined in terms of decreasing serviceability caused by the development of cracks, ruts, potholes etc. Flexible Pavement structure can be destroyed in a single season due to water penetration. Defects in flexible pavements is a problem of multiple dimensions, phenomenal growth of vehicular traffic (in terms of no. of axle loading of commercial vehicles), the rapid expansion in the road network, non-availability of suitable technology, material, equipment, skilled labor and poor funds allocation have all added complexities to the problem of flexible pavements. In rigid pavements due to different type of destress the failure like joint spalling, faulting, shrinkage cracking, punch out, corner break etc. Application of correction in the existing surface will enhance the life of maintenance works as well as that of strengthening layer. Maintenance of a road network involves a variety of operations, i.e., identification of deficiencies and planning, programming and scheduling for actual implementation in the field and monitoring. The essential objective should be to keep the road surface and appurtenances in good condition and to extend the life of the road assets to its design life. The paper describes lessons learnt from pavement failures and problems experienced during the last few years on a number of projects in India. Broadly, the activities include identification of defects and the possible cause there off, determination of appropriate remedial measures; implement these in the field and monitoring of the results.Keywords: Flexible Pavements, Rigid Pavements, Defects, Maintenance
Procedia PDF Downloads 1604387 Algorithms Minimizing Total Tardiness
Authors: Harun Aydilek, Asiye Aydilek, Ali Allahverdi
Abstract:
The total tardiness is a widely used performance measure in the scheduling literature. This performance measure is particularly important in situations where there is a cost to complete a job beyond its due date. The cost of scheduling increases as the gap between a job's due date and its completion time increases. Such costs may also be penalty costs in contracts, loss of goodwill. This performance measure is important as the fulfillment of due dates of customers has to be taken into account while making scheduling decisions. The problem is addressed in the literature, however, it has been assumed zero setup times. Even though this assumption may be valid for some environments, it is not valid for some other scheduling environments. When setup times are treated as separate from processing times, it is possible to increase machine utilization and to reduce total tardiness. Therefore, non-zero setup times need to be considered as separate. A dominance relation is developed and several algorithms are proposed. The developed dominance relation is utilized in the proposed algorithms. Extensive computational experiments are conducted for the evaluation of the algorithms. The experiments indicated that the developed algorithms perform much better than the existing algorithms in the literature. More specifically, one of the newly proposed algorithms reduces the error of the best existing algorithm in the literature by 40 percent.Keywords: algorithm, assembly flowshop, dominance relation, total tardiness
Procedia PDF Downloads 3494386 New Machine Learning Optimization Approach Based on Input Variables Disposition Applied for Time Series Prediction
Authors: Hervice Roméo Fogno Fotsoa, Germaine Djuidje Kenmoe, Claude Vidal Aloyem Kazé
Abstract:
One of the main applications of machine learning is the prediction of time series. But a more accurate prediction requires a more optimal model of machine learning. Several optimization techniques have been developed, but without considering the input variables disposition of the system. Thus, this work aims to present a new machine learning architecture optimization technique based on their optimal input variables disposition. The validations are done on the prediction of wind time series, using data collected in Cameroon. The number of possible dispositions with four input variables is determined, i.e., twenty-four. Each of the dispositions is used to perform the prediction, with the main criteria being the training and prediction performances. The results obtained from a static architecture and a dynamic architecture of neural networks have shown that these performances are a function of the input variable's disposition, and this is in a different way from the architectures. This analysis revealed that it is necessary to take into account the input variable's disposition for the development of a more optimal neural network model. Thus, a new neural network training algorithm is proposed by introducing the search for the optimal input variables disposition in the traditional back-propagation algorithm. The results of the application of this new optimization approach on the two single neural network architectures are compared with the previously obtained results step by step. Moreover, this proposed approach is validated in a collaborative optimization method with a single objective optimization technique, i.e., genetic algorithm back-propagation neural networks. From these comparisons, it is concluded that each proposed model outperforms its traditional model in terms of training and prediction performance of time series. Thus the proposed optimization approach can be useful in improving the accuracy of time series forecasts. This proves that the proposed optimization approach can be useful in improving the accuracy of time series prediction based on machine learning.Keywords: input variable disposition, machine learning, optimization, performance, time series prediction
Procedia PDF Downloads 1044385 Discovery of Exoplanets in Kepler Data Using a Graphics Processing Unit Fast Folding Method and a Deep Learning Model
Authors: Kevin Wang, Jian Ge, Yinan Zhao, Kevin Willis
Abstract:
Kepler has discovered over 4000 exoplanets and candidates. However, current transit planet detection techniques based on the wavelet analysis and the Box Least Squares (BLS) algorithm have limited sensitivity in detecting minor planets with a low signal-to-noise ratio (SNR) and long periods with only 3-4 repeated signals over the mission lifetime of 4 years. This paper presents a novel precise-period transit signal detection methodology based on a new Graphics Processing Unit (GPU) Fast Folding algorithm in conjunction with a Convolutional Neural Network (CNN) to detect low SNR and/or long-period transit planet signals. A comparison with BLS is conducted on both simulated light curves and real data, demonstrating that the new method has higher speed, sensitivity, and reliability. For instance, the new system can detect transits with SNR as low as three while the performance of BLS drops off quickly around SNR of 7. Meanwhile, the GPU Fast Folding method folds light curves 25 times faster than BLS, a significant gain that allows exoplanet detection to occur at unprecedented period precision. This new method has been tested with all known transit signals with 100% confirmation. In addition, this new method has been successfully applied to the Kepler of Interest (KOI) data and identified a few new Earth-sized Ultra-short period (USP) exoplanet candidates and habitable planet candidates. The results highlight the promise for GPU Fast Folding as a replacement to the traditional BLS algorithm for finding small and/or long-period habitable and Earth-sized planet candidates in-transit data taken with Kepler and other space transit missions such as TESS(Transiting Exoplanet Survey Satellite) and PLATO(PLAnetary Transits and Oscillations of stars).Keywords: algorithms, astronomy data analysis, deep learning, exoplanet detection methods, small planets, habitable planets, transit photometry
Procedia PDF Downloads 2164384 GPU Accelerated Fractal Image Compression for Medical Imaging in Parallel Computing Platform
Authors: Md. Enamul Haque, Abdullah Al Kaisan, Mahmudur R. Saniat, Aminur Rahman
Abstract:
In this paper, we have implemented both sequential and parallel version of fractal image compression algorithms using CUDA (Compute Unified Device Architecture) programming model for parallelizing the program in Graphics Processing Unit for medical images, as they are highly similar within the image itself. There is several improvements in the implementation of the algorithm as well. Fractal image compression is based on the self similarity of an image, meaning an image having similarity in majority of the regions. We take this opportunity to implement the compression algorithm and monitor the effect of it using both parallel and sequential implementation. Fractal compression has the property of high compression rate and the dimensionless scheme. Compression scheme for fractal image is of two kinds, one is encoding and another is decoding. Encoding is very much computational expensive. On the other hand decoding is less computational. The application of fractal compression to medical images would allow obtaining much higher compression ratios. While the fractal magnification an inseparable feature of the fractal compression would be very useful in presenting the reconstructed image in a highly readable form. However, like all irreversible methods, the fractal compression is connected with the problem of information loss, which is especially troublesome in the medical imaging. A very time consuming encoding process, which can last even several hours, is another bothersome drawback of the fractal compression.Keywords: accelerated GPU, CUDA, parallel computing, fractal image compression
Procedia PDF Downloads 3304383 Permeability Prediction Based on Hydraulic Flow Unit Identification and Artificial Neural Networks
Authors: Emad A. Mohammed
Abstract:
The concept of hydraulic flow units (HFU) has been used for decades in the petroleum industry to improve the prediction of permeability. This concept is strongly related to the flow zone indicator (FZI) which is a function of the reservoir rock quality index (RQI). Both indices are based on reservoir porosity and permeability of core samples. It is assumed that core samples with similar FZI values belong to the same HFU. Thus, after dividing the porosity-permeability data based on the HFU, transformations can be done in order to estimate the permeability from the porosity. The conventional practice is to use the power law transformation using conventional HFU where percentage of error is considerably high. In this paper, neural network technique is employed as a soft computing transformation method to predict permeability instead of power law method to avoid higher percentage of error. This technique is based on HFU identification where Amaefule et al. (1993) method is utilized. In this regard, Kozeny and Carman (K–C) model, and modified K–C model by Hasan and Hossain (2011) are employed. A comparison is made between the two transformation techniques for the two porosity-permeability models. Results show that the modified K-C model helps in getting better results with lower percentage of error in predicting permeability. The results also show that the use of artificial intelligence techniques give more accurate prediction than power law method. This study was conducted on a heterogeneous complex carbonate reservoir in Oman. Data were collected from seven wells to obtain the permeability correlations for the whole field. The findings of this study will help in getting better estimation of permeability of a complex reservoir.Keywords: permeability, hydraulic flow units, artificial intelligence, correlation
Procedia PDF Downloads 1334382 Human-Computer Interaction: Strategies for Ensuring the Design of User-Centered Web Interfaces for Smartphones
Authors: Byron Joseph A. Hallar, Annjeannette Alain D. Galang, Maria Visitacion N. Gumabay
Abstract:
The widespread adoption and increasing proliferation of smartphones that started during the first decade of the twenty-first century have enabled their users to communicate and access information in ways that were merely thought of as possibilities in the few years before the smartphone revolution. A product of the convergence of the cellular phone and portable computer, the smartphone provides an additional important function that used to be the exclusive domain of desktop-bound computers and portable computers: Web Browsing. For increasing numbers of users, the smartphone and allied devices such as tablet computers have become their first and often their only means of accessing the World Wide Web. This has led to the development of websites that cater to the needs of the new breed of smartphone-carrying web users. The smaller size of smartphones as compared with conventional computers has provided unique challenges to web interface designers. The smaller screen size and touchscreen interface have made it much more difficult to read and navigate through web pages that were in most part designed for traditional desktop and portable computers. Although increasing numbers of websites now provide an alternate website formatted for smartphones, problems with ease of use, reliability and usability still remain. This study focuses on the identification of the problems associated with smartphone web interfaces, the compliance with accepted standards of user-oriented web interface design, the strategies that could be utilized to ensure the design of user-centric web interfaces for smartphones, and the identification of the current trends and developments related to user-centric web interface design intended for the consumption of smartphone users.Keywords: human-computer interaction, user-centered design, web interface, mobile, smartphone
Procedia PDF Downloads 3494381 Determination of Identification and Antibiotic Resistance Rates of Pseudomonas aeruginosa Strains from Various Clinical Specimens in a University Hospital for Two Years, 2013-2015
Authors: Recep Kesli, Gulsah Asik, Cengiz Demir, Onur Turkyilmaz
Abstract:
Objective: Pseudomonas aeruginosa (P. aeruginosa) is an important nosocomial pathogen which causes serious hospital infections and is resistant to many commonly used antibiotics. P. aeruginosa can develop resistance during therapy and also it is very resistant to disinfectant chemicals. It may be found in respiratory support devices in hospitals. In this study, the antibiotic resistance of P. aeruginosa strains isolated from bronchial aspiration samples was evaluated retrospectively. Methods: Between October 2013 and September 2015, a total of 318 P. aeruginosa were isolated from clinical samples obtained from various intensive care units and inpatient patients hospitalized at Afyon Kocatepe University, ANS Practice and Research Hospital. Isolated bacteria identified by using both the conventional methods and automated identification system-VITEK 2 (bioMerieux, Marcy l’etoile France). Antibacterial resistance tests were performed by using Kirby-Bauer disc (Oxoid, Hampshire, England) diffusion method following the recommendations of CLSI. Results: Antibiotic resistance rates of identified 318 P. aeruginosa strains were found as follows for tested antibiotics; 32 % amikacin, 42% gentamicin, 43% imipenem, 43% meropenem, 50% ciprofloxacin, 57% levofloxacin, 38% cefepime, 63% ceftazidime, and 85% piperacillin/tazobactam. Conclusion: Resistance profiles change according to years and provinces for P. aeruginosa, so these findings should be considered empirical treatment choices. In this study, the highest and lowest resistance rates found against piperacillin/tazobactam % 85, and amikacin %32.Keywords: Pseudomonas aeruginosa, antibiotic resistance rates, intensive care unit, Pseudomonas spp.
Procedia PDF Downloads 2874380 Heuristic Classification of Hydrophone Recordings
Authors: Daniel M. Wolff, Patricia Gray, Rafael de la Parra Venegas
Abstract:
An unsupervised machine listening system is constructed and applied to a dataset of 17,195 30-second marine hydrophone recordings. The system is then heuristically supplemented with anecdotal listening, contextual recording information, and supervised learning techniques to reduce the number of false positives. Features for classification are assembled by extracting the following data from each of the audio files: the spectral centroid, root-mean-squared values for each frequency band of a 10-octave filter bank, and mel-frequency cepstral coefficients in 5-second frames. In this way both time- and frequency-domain information are contained in the features to be passed to a clustering algorithm. Classification is performed using the k-means algorithm and then a k-nearest neighbors search. Different values of k are experimented with, in addition to different combinations of the available feature sets. Hypothesized class labels are 'primarily anthrophony' and 'primarily biophony', where the best class result conforming to the former label has 104 members after heuristic pruning. This demonstrates how a large audio dataset has been made more tractable with machine learning techniques, forming the foundation of a framework designed to acoustically monitor and gauge biological and anthropogenic activity in a marine environment.Keywords: anthrophony, hydrophone, k-means, machine learning
Procedia PDF Downloads 1664379 Design of Low Latency Multiport Network Router on Chip
Authors: P. G. Kaviya, B. Muthupandian, R. Ganesan
Abstract:
On-chip routers typically have buffers are used input or output ports for temporarily storing packets. The buffers are consuming some router area and power. The multiple queues in parallel as in VC router. While running a traffic trace, not all input ports have incoming packets needed to be transferred. Therefore large numbers of queues are empty and others are busy in the network. So the time consumption should be high for the high traffic. Therefore using a RoShaQ, minimize the buffer area and time The RoShaQ architecture was send the input packets are travel through the shared queues at low traffic. At high load traffic the input packets are bypasses the shared queues. So the power and area consumption was reduced. A parallel cross bar architecture is proposed in this project in order to reduce the power consumption. Also a new adaptive weighted routing algorithm for 8-port router architecture is proposed in order to decrease the delay of the network on chip router. The proposed system is simulated using Modelsim and synthesized using Xilinx Project Navigator.Keywords: buffer, RoShaQ architecture, shared queue, VC router, weighted routing algorithm
Procedia PDF Downloads 5394378 Locomotion Effects of Redundant Degrees of Freedom in Multi-Legged Quadruped Robots
Authors: Hossein Keshavarz, Alejandro Ramirez-Serrano
Abstract:
Energy efficiency and locomotion speed are two key parameters for legged robots; thus, finding ways to improve them are important. This paper proposes a locomotion framework to analyze the energy usage and speed of quadruped robots via a Genetic Algorithm (GA) optimization process. For this, a quadruped robot platform with joint redundancy in its hind legs that we believe will help multi-legged robots improve their speed and energy consumption is used. ContinuO, the quadruped robot of interest, has 14 active degrees of freedom (DoFs), including three DoFs for each front leg, and unlike previously developed quadruped robots, four DoFs for each hind leg. ContinuO aims to realize a cost-effective quadruped robot for real-world scenarios with high speeds and the ability to overcome large obstructions. The proposed framework is used to locomote the robot and analyze its energy consumed at diverse stride lengths and locomotion speeds. The analysis is performed by comparing the obtained results in two modes, with and without the joint redundancy on the robot’s hind legs.Keywords: genetic algorithm optimization, locomotion path planning, quadruped robots, redundant legs
Procedia PDF Downloads 924377 On the Influence of the Metric Space in the Critical Behavior of Magnetic Temperature
Authors: J. C. Riaño-Rojas, J. D. Alzate-Cardona, E. Restrepo-Parra
Abstract:
In this work, a study of generic magnetic nanoparticles varying the metric space is presented. As the metric space is changed, the nanoparticle form and the inner product are also varied, since the energetic scale is not conserved. This study is carried out using Monte Carlo simulations combined with the Wolff embedding and Metropolis algorithms. The Metropolis algorithm is used at high temperature regions to reach the equilibrium quickly. The Wolff embedding algorithm is used at low and critical temperature regions in order to reduce the critical slowing down phenomenon. The ions number is kept constant for the different forms and the critical temperatures using finite size scaling are found. We observed that critical temperatures don't exhibit significant changes when the metric space was varied. Additionally, the effective dimension according the metric space was determined. A study of static behavior for reaching the static critical exponents was developed. The objective of this work is to observe the behavior of the thermodynamic quantities as energy, magnetization, specific heat, susceptibility and Binder's cumulants at the critical region, in order to demonstrate if the magnetic nanoparticles describe their magnetic interactions in the Euclidean space or if there is any correspondence in other metric spaces.Keywords: nanoparticles, metric, Monte Carlo, critical behaviour
Procedia PDF Downloads 5124376 Energy Efficient Clustering with Adaptive Particle Swarm Optimization
Authors: KumarShashvat, ArshpreetKaur, RajeshKumar, Raman Chadha
Abstract:
Wireless sensor networks have principal characteristic of having restricted energy and with limitation that energy of the nodes cannot be replenished. To increase the lifetime in this scenario WSN route for data transmission is opted such that utilization of energy along the selected route is negligible. For this energy efficient network, dandy infrastructure is needed because it impinges the network lifespan. Clustering is a technique in which nodes are grouped into disjoints and non–overlapping sets. In this technique data is collected at the cluster head. In this paper, Adaptive-PSO algorithm is proposed which forms energy aware clusters by minimizing the cost of locating the cluster head. The main concern is of the suitability of the swarms by adjusting the learning parameters of PSO. Particle Swarm Optimization converges quickly at the beginning stage of the search but during the course of time, it becomes stable and may be trapped in local optima. In suggested network model swarms are given the intelligence of the spiders which makes them capable enough to avoid earlier convergence and also help them to escape from the local optima. Comparison analysis with traditional PSO shows that new algorithm considerably enhances the performance where multi-dimensional functions are taken into consideration.Keywords: Particle Swarm Optimization, adaptive – PSO, comparison between PSO and A-PSO, energy efficient clustering
Procedia PDF Downloads 2434375 Systematic Identification of Noncoding Cancer Driver Somatic Mutations
Authors: Zohar Manber, Ran Elkon
Abstract:
Accumulation of somatic mutations (SMs) in the genome is a major driving force of cancer development. Most SMs in the tumor's genome are functionally neutral; however, some cause damage to critical processes and provide the tumor with a selective growth advantage (termed cancer driver mutations). Current research on functional significance of SMs is mainly focused on finding alterations in protein coding sequences. However, the exome comprises only 3% of the human genome, and thus, SMs in the noncoding genome significantly outnumber those that map to protein-coding regions. Although our understanding of noncoding driver SMs is very rudimentary, it is likely that disruption of regulatory elements in the genome is an important, yet largely underexplored mechanism by which somatic mutations contribute to cancer development. The expression of most human genes is controlled by multiple enhancers, and therefore, it is conceivable that regulatory SMs are distributed across different enhancers of the same target gene. Yet, to date, most statistical searches for regulatory SMs have considered each regulatory element individually, which may reduce statistical power. The first challenge in considering the cumulative activity of all the enhancers of a gene as a single unit is to map enhancers to their target promoters. Such mapping defines for each gene its set of regulating enhancers (termed "set of regulatory elements" (SRE)). Considering multiple enhancers of each gene as one unit holds great promise for enhancing the identification of driver regulatory SMs. However, the success of this approach is greatly dependent on the availability of comprehensive and accurate enhancer-promoter (E-P) maps. To date, the discovery of driver regulatory SMs has been hindered by insufficient sample sizes and statistical analyses that often considered each regulatory element separately. In this study, we analyzed more than 2,500 whole-genome sequence (WGS) samples provided by The Cancer Genome Atlas (TCGA) and The International Cancer Genome Consortium (ICGC) in order to identify such driver regulatory SMs. Our analyses took into account the combinatorial aspect of gene regulation by considering all the enhancers that control the same target gene as one unit, based on E-P maps from three genomics resources. The identification of candidate driver noncoding SMs is based on their recurrence. We searched for SREs of genes that are "hotspots" for SMs (that is, they accumulate SMs at a significantly elevated rate). To test the statistical significance of recurrence of SMs within a gene's SRE, we used both global and local background mutation rates. Using this approach, we detected - in seven different cancer types - numerous "hotspots" for SMs. To support the functional significance of these recurrent noncoding SMs, we further examined their association with the expression level of their target gene (using gene expression data provided by the ICGC and TCGA for samples that were also analyzed by WGS).Keywords: cancer genomics, enhancers, noncoding genome, regulatory elements
Procedia PDF Downloads 1004374 Multi Objective Optimization for Two-Sided Assembly Line Balancing
Authors: Srushti Bhatt, M. B. Kiran
Abstract:
Two-sided assembly line balancing problem is yet to be addressed simply to compete for the global market for manufacturers. The task assigned in an ordered sequence to get optimum performance of the system is known as assembly line balancing problem mainly classified as single and two sided. It is very challenging in manufacturing industries to balance two-sided assembly line, wherein the set of sequential workstations the task operations are performed in two sides of the line. The conflicting major objective in two-sided assembly line balancing problem is either to maximize /minimize the performance parameters. The present study emphases on combining different evolutionary algorithm; ant colony, Tabu search and petri net method; and compares their results of an algorithm for solving two-sided assembly line balancing problem. The concept of multi objective optimization of performance parameters is now a day adopted to make a decision involving more than one objective function to be simultaneously optimized. The optimum result can be expected among the selected methods using multi-objective optimization. The performance parameters considered in the present study are a number of workstation, slickness and smoothness index. The simulation of the assembly line balancing problem provides optimal results of classical and practical problems.Keywords: Ant colony, petri net, tabu search, two sided ALBP
Procedia PDF Downloads 2734373 Modeling Search-And-Rescue Operations by Autonomous Mobile Robots at Sea
Authors: B. Kriheli, E. Levner, T. C. E. Cheng, C. T. Ng
Abstract:
During the last decades, research interest in planning, scheduling, and control of emergency response operations, especially people rescue and evacuation from the dangerous zone of marine accidents, has increased dramatically. Until the survivors (called ‘targets’) are found and saved, it may cause loss or damage whose extent depends on the location of the targets and the search duration. The problem is to efficiently search for and detect/rescue the targets as soon as possible with the help of intelligent mobile robots so as to maximize the number of saved people and/or minimize the search cost under restrictions on the amount of saved people within the allowable response time. We consider a special situation when the autonomous mobile robots (AMR), e.g., unmanned aerial vehicles and remote-controlled robo-ships have no operator on board as they are guided and completely controlled by on-board sensors and computer programs. We construct a mathematical model for the search process in an uncertain environment and provide a new fast algorithm for scheduling the activities of the autonomous robots during the search-and rescue missions after an accident at sea. We presume that in the unknown environments, the AMR’s search-and-rescue activity is subject to two types of error: (i) a 'false-negative' detection error where a target object is not discovered (‘overlooked') by the AMR’s sensors in spite that the AMR is in a close neighborhood of the latter and (ii) a 'false-positive' detection error, also known as ‘a false alarm’, in which a clean place or area is wrongly classified by the AMR’s sensors as a correct target. As the general resource-constrained discrete search problem is NP-hard, we restrict our study to finding local-optimal strategies. A specificity of the considered operational research problem in comparison with the traditional Kadane-De Groot-Stone search models is that in our model the probability of the successful search outcome depends not only on cost/time/probability parameters assigned to each individual location but, as well, on parameters characterizing the entire history of (unsuccessful) search before selecting any next location. We provide a fast approximation algorithm for finding the AMR route adopting a greedy search strategy in which, in each step, the on-board computer computes a current search effectiveness value for each location in the zone and sequentially searches for a location with the highest search effectiveness value. Extensive experiments with random and real-life data provide strong evidence in favor of the suggested operations research model and corresponding algorithm.Keywords: disaster management, intelligent robots, scheduling algorithm, search-and-rescue at sea
Procedia PDF Downloads 168