Search results for: state machine

Authors: Muhammad Atif, Cang Yan

Abstract:

The enhancement of low-light images is a significant area of study aimed at enhancing the quality of captured images in challenging lighting environments. Recently, methods based on Convolutional Neural Networks (CNN) have gained prominence as they offer state-of-the-art performance. However, many approaches based on CNN rely on increasing the size and complexity of the neural network. In this study, we propose an alternative method for improving low-light images using an Autoencoders-based multiscale knowledge transfer model. Our method leverages the power of three autoencoders, where the encoders of the first two autoencoders are directly connected to the decoder of the third autoencoder. Additionally, the decoder of the first two autoencoders is connected to the encoder of the third autoencoder. This architecture enables effective knowledge transfer, allowing the third autoencoder to learn and benefit from the enhanced knowledge extracted by the first two autoencoders. We further integrate the proposed model into the Pix-to-Pix GAN framework. By integrating our proposed model as the generator in the GAN framework, we aim to produce enhanced images that not only exhibit improved visual quality but also possess a more authentic and realistic appearance. These experimental results, both qualitative and quantitative, show that our method is better than the state-of-the-art methodologies.

Keywords: Low light image enhancement, deep learning, convolutional neural network, image processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 34

Authors: Hamdi Melih Saraoğlu, Muhlis Yıldırım, Abdurrahman Özbeyaz, Feyzullah Temurtas

Abstract:

In this research, the diabetes conditions of people (healthy, prediabete and diabete) were tried to be identified with noninvasive palm perspiration measurements. Data clusters gathered from 200 subjects were used (1.Individual Attributes Cluster and 2. Palm Perspiration Attributes Cluster). To decrase the dimensions of these data clusters, Principal Component Analysis Method was used. Data clusters, prepared in that way, were classified with Support Vector Machines. Classifications with highest success were 82% for Glucose parameters and 84% for HbA1c parametres.

Keywords: Palm perspiration, Diabetes, Support Vector Machine, Classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1946

Authors: József Valyon, Gábor Horváth

Abstract:

Among neural models the Support Vector Machine (SVM) solutions are attracting increasing attention, mostly because they eliminate certain crucial questions involved by neural network construction. The main drawback of standard SVM is its high computational complexity, therefore recently a new technique, the Least Squares SVM (LS–SVM) has been introduced. In this paper we present an extended view of the Least Squares Support Vector Regression (LS–SVR), which enables us to develop new formulations and algorithms to this regression technique. Based on manipulating the linear equation set -which embodies all information about the regression in the learning process- some new methods are introduced to simplify the formulations, speed up the calculations and/or provide better results.

Keywords: Function estimation, Least–Squares Support VectorMachines, Regression, System Modeling

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2009

Authors: Vandana Sharma, Parvinder S. Sandhu, Satwinder Singh, Baljit Saini

Abstract:

In field of Computer Science and Mathematics, sorting algorithm is an algorithm that puts elements of a list in a certain order i.e. ascending or descending. Sorting is perhaps the most widely studied problem in computer science and is frequently used as a benchmark of a system-s performance. This paper presented the comparative performance study of four sorting algorithms on different platform. For each machine, it is found that the algorithm depends upon the number of elements to be sorted. In addition, as expected, results show that the relative performance of the algorithms differed on the various machines. So, algorithm performance is dependent on data size and there exists impact of hardware also.

Keywords: Algorithm, Analysis, Complexity, Sorting.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2412

Authors: K. Oh, J. P. Hwang, E. Kim, H. Lee

Abstract:

This paper presents an algorithm which extends the rapidly-exploring random tree (RRT) framework to deal with change of the task environments. This algorithm called the Retrieval RRT Strategy (RRS) combines a support vector machine (SVM) and RRT and plans the robot motion in the presence of the change of the surrounding environment. This algorithm consists of two levels. At the first level, the SVM is built and selects a proper path from the bank of RRTs for a given environment. At the second level, a real path is planned by the RRT planners for the given environment. The suggested method is applied to the control of KUKA™,, a commercial 6 DOF robot manipulator, and its feasibility and efficiency are demonstrated via the cosimulatation of MatLab™, and RecurDyn™,.

Keywords: Path planning, RRT, 6 DOF manipulator, SVM.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2531

Authors: S. B. Kotsiantis, D. Kanellopoulos, P. E. Pintelas

Abstract:

Many factors affect the success of Machine Learning (ML) on a given task. The representation and quality of the instance data is first and foremost. If there is much irrelevant and redundant information present or noisy and unreliable data, then knowledge discovery during the training phase is more difficult. It is well known that data preparation and filtering steps take considerable amount of processing time in ML problems. Data pre-processing includes data cleaning, normalization, transformation, feature extraction and selection, etc. The product of data pre-processing is the final training set. It would be nice if a single sequence of data pre-processing algorithms had the best performance for each data set but this is not happened. Thus, we present the most well know algorithms for each step of data pre-processing so that one achieves the best performance for their data set.

Keywords: Data mining, feature selection, data cleaning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 6091

Authors: E. D. Paul, H. Otanwa, O. F. Paul, A. J. Salifu, J. E. Toryila, C. E. Gimba

Abstract:

The concentration levels of six heavy metals (Cd, Cr, Fe, Ni, Pb and Zn) and two mineral elements (Ca and Mg) were determined in soil samples collected from the vicinity of two auto mechanic workshops in Sabon-Gari, Kaduna state, Nigeria, using Atomic Absorption Spectrometry (AAS), in order to compare the gradation of their concentrations with distance and depth of soil from the workshop sites. At site 1, concentrations of Lead, Chromium, Iron and Zinc were generally found to be above the World Health Organization limits, while those of Nickel and Cadmium fell within the limits. Iron had the highest concentration with a range of 176.274 ppm to 489.127 ppm at depths of 5 cm to 15 cm and a distance range of 5 m to 15 m, while the concentration of cadmium was least with a range of 0.001 ppm to 0.008 ppm at similar depth and distance ranges. In addition, there was more of calcium (11.521 ppm to 121.709 ppm), in all the samples, than magnesium (11.293 ppm to 21.635 ppm). Similar results were obtained for site II. The concentrations of all the metals analyzed showed a downward gradient with increase in depth and distance from both workshop sites except for iron and zinc at site 2. The immediate and remote implications of these findings on the biota are discussed.

Keywords: AAS, Heavy Metals, Mechanic Workshops, Soils.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2131

Authors: Lee Yih Rou, Hishammuddin Asmuni

Abstract:

Flexible Job Shop Problem (FJSP) is an extension of classical Job Shop Problem (JSP). The FJSP extends the routing flexibility of the JSP, i.e assigning machine to an operation. Thus it makes it more difficult than the JSP. In this study, Cooperative Coevolutionary Genetic Algorithm (CCGA) is presented to solve the FJSP. Makespan (time needed to complete all jobs) is used as the performance evaluation for CCGA. In order to test performance and efficiency of our CCGA the benchmark problems are solved. Computational result shows that the proposed CCGA is comparable with other approaches.

Keywords: Co-evolution, Genetic Algorithm (GA), Flexible JobShop Problem(FJSP)

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1788

Authors: Khwaja Naweed Seddiqi, Zabihullah Mahdi, Shigeo Honma

Abstract:

Recently increasing oil production from petroleum reservoirs is one of the most important issues in the global energy sector. So, in this paper, the recovery of oil by the waterflooding technique from petroleum reservoir are considered. To investigate the aforementioned phenomena, the relative permeability of two immiscible fluids in sand is measured in the laboratory based on the steady-state method. Two sorts of oils, kerosene and heavy oil, and water are pumped simultaneously into a vertical sand column with different pumping ratio. From the change in fractional discharge measured at the outlet, a method for determining the relative permeability is developed focusing on the displacement mechanism in sand. Then, displacement mechanism of two immiscible fluids in the sand is investigated under the Buckley-Leveret frontal displacement theory and laboratory experiment. Two sorts of experiments, one is the displacement of pore water by oil, the other is the displacement of pore oil by water, are carried out. It is revealed that the relative permeability curves display tolerably different shape owing to the properties of oils, and produce different amount of residual oils and irreducible water saturation.

Keywords: Petroleum reservoir engineering, relative permeability, two-phase flow, immiscible displacement in porous media, steady-state method, waterflooding.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1151

Authors: Mutuku Muvengei, John Kihiu

Abstract:

In this paper, a bond graph dynamic model for a valvecontrolled hydraulic cylinder has been developed. A simplified bond graph model of the inter-actuator interactions in a multi-cylinder hydraulic system has also been presented. The overall bond graph model of a valve-controlled hydraulic cylinder was developed by combining the bond graph sub-models of the pump, spool valve and the actuator using junction structures. Causality was then assigned in order to obtain a computational model which could be simulated. The causal bond graph model of the hydraulic cylinder was verified by comparing the open loop state responses to those of an ODE model which had been developed in literature based on the same assumptions. The results were found to correlate very well both in the shape of the curves, magnitude and the response times, thus indicating that the developed model represents the hydraulic dynamics of a valve-controlled cylinder. A simplified model for interactuator interaction was presented by connecting an effort source with constant pump pressure to the zero-junction from which the cylinders in a multi-cylinder system are supplied with a constant pressure from the pump. On simulating the state responses of the developed model under different situations of cylinder operations, indicated that such a simple model can be used to predict the inter-actuator interactions.

Keywords: Bond graphs, Inter-actuator interactions, Valvecontrolledhydraulic cylinder.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3036

Authors: G. V. Novikov, V. S. Sivozhelezov, S. S. Kolesnikov, K. V. Shaitan

Abstract:

The study reports about the influence of binding of orthosteric ligands as well as point mutations on the conformational dynamics of β-2-adrenoreceptor. Using molecular dynamics simulation we found that there was a little fraction of active states of the receptor in its apo (ligand free) ensemble corresponded to its constitutive activity. Analysis of MD trajectories indicated that such spontaneous activation of the receptor is accompanied by the motion in intracellular part of its alpha-helices. Thus receptor’s constitutive activity directly results from its conformational dynamics. On the other hand the binding of a full agonist resulted in a significant shift of the initial equilibrium towards its active state. Finally, the binding of the inverse agonist stabilized the receptor in its inactive state. It is likely that the binding of inverse agonists might be a universal way of constitutive activity inhibition in vivo. Our results indicate that ligand binding redistribute pre-existing conformational degrees of freedom (in accordance to the Monod-Wyman-Changeux-Model) of the receptor rather than cause induced fit in it. Therefore, the ensemble of biologically relevant receptor conformations is encoded in its spatial structure, and individual conformations from that ensemble might be used by the cell in conformity with the physiological behavior.

Keywords: Seven-transmembrane receptors, constitutive activity, activation, x-ray crystallography, principal component analysis, molecular dynamics simulation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3957

Authors: András Szekrényes

Abstract:

Delamination is one of the major failure modes in laminated composite structures. Delamination tips are mostly captured by spatial numerical models in order to predict crack growth. This paper presents some mechanical models of delaminated composite shells based on shallow shell theories. The mechanical fields are based on a third-order displacement field in terms of the through-thickness coordinate of the laminated shell. The undelaminated and delaminated parts are captured by separate models and the continuity and boundary conditions are also formulated in a general way providing a large size boundary value problem. The system of differential equations is solved by the state space method for an elliptic delaminated shell having simply supported edges. The comparison of the proposed and a numerical model indicates that the primary indicator of the model is the deflection, the secondary is the widthwise distribution of the energy release rate. The model is promising and suitable to determine accurately the J-integral distribution along the delamination front. Based on the proposed model it is also possible to develop finite elements which are able to replace the computationally expensive spatial models of delaminated structures.

Keywords: J-integral, Lévy method, third-order shell theory, state space solution.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 599

Authors: Nina Suszczanska, Przemyslaw Szmal, Slawomir Kulikow

Abstract:

In the paper a method of modeling text for Polish is discussed. The method is aimed at transforming continuous input text into a text consisting of sentences in so called canonical form, whose characteristic is, among others, a complete structure as well as no anaphora or ellipses. The transformation is lossless as to the content of text being transformed. The modeling method has been worked out for the needs of the Thetos system, which translates Polish written texts into the Polish sign language. We believe that the method can be also used in various applications that deal with the natural language, e.g. in a text summary generator for Polish.

Keywords: anaphora, machine translation, NLP, sign language, text syntax.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1656

Authors: Prof. Chokri SLIM

Abstract:

A Novel fuzzy neural network combining with support vector learning mechanism called support-vector-based fuzzy neural networks (SVBFNN) is proposed. The SVBFNN combine the capability of minimizing the empirical risk (training error) and expected risk (testing error) of support vector learning in high dimensional data spaces and the efficient human-like reasoning of FNN.

Keywords: Neural network, fuzzy inference, machine learning, fuzzy modeling and rule extraction, support vector regression.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 16687

Authors: B. Wang, W. H. Or, S.C. Lee, Y.C. Leung, B. Organ

Abstract:

This study presents an investigation of diesel vehicle particulate-phase emissions with neat ultralow sulphur diesel (B0, ULSD) and 5% waste cooking oil-based biodiesel blend (B5) in Hong Kong. A Euro VI light duty diesel vehicle was tested under transient (New European Driving Cycle (NEDC)), steady-state and idling on a chassis dynamometer. Chemical analyses including organic carbon (OC), elemental carbon (EC), as well as 30 polycyclic aromatic hydrocarbons (PAHs) and 10 oxygenated PAHs (oxy-PAHs) were conducted. The OC fuel-based emission factors (EFs) for B0 ranged from 2.86 ± 0.33 to 7.19 ± 1.51 mg/kg, and those for B5 ranged from 4.31 ± 0.64 to 15.36 ± 3.77 mg/kg, respectively. The EFs of EC were low for both fuel blends (0.25 mg/kg or below). With B5, the EFs of total PAHs were decreased as compared to B0. Specifically, B5 reduced total PAH emissions by 50.2%, 30.7%, and 15.2% over NEDC, steady-state and idling, respectively. It was found that when B5 was used, PAHs and oxy-PAHs with lower molecular weight (2 to 3 rings) were reduced whereas PAHs/oxy-PAHs with medium or high molecular weight (4 to 7 rings) were increased. Our study suggests the necessity of taking atmospheric and health factors into account for biodiesel application as an alternative motor fuel.

Keywords: Biodiesel, OC/EC, PAHs, vehicular emission.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 398

Authors: Okay Gunes

Abstract:

In this article, a new method is proposed for the measuring of well-being inequality through a model composed of superimposing satisfaction waves. The displacement of households’ satisfactory state (i.e. satisfaction) is defined in a satisfaction string. The duration of the satisfactory state for a given period is measured in order to determine the relationship between utility and total satisfactory time, itself dependent on the density and tension of each satisfaction string. Thus, individual cardinal total satisfaction values are computed by way of a one-dimensional form for scalar sinusoidal (harmonic) moving wave function, using satisfaction waves with varying amplitudes and frequencies which allow us to measure wellbeing inequality. One advantage to using satisfaction waves is the ability to show that individual utility and consumption amounts would probably not commute; hence, it is impossible to measure or to know simultaneously the values of these observables from the dataset. Thus, we crystallize the problem by using a Heisenberg-type uncertainty resolution for self-adjoint economic operators. We propose to eliminate any estimation bias by correlating the standard deviations of selected economic operators; this is achieved by replacing the aforementioned observed uncertainties with households’ perceived uncertainties (i.e. corrected standard deviations) obtained through the logarithmic psychophysical law proposed by Weber and Fechner.

Keywords: Heisenberg Uncertainty Principle, superimposing satisfaction waves, Weber–Fechner law, well-being inequality.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2055

Authors: Gulshan Sharma

Abstract:

This article presents the design of optimal automatic generation control (AGC) based on full state feedback control for a multi-area interconnected power system. An extra high voltage AC transmission line in parallel with a high voltage DC link is considered as an area interconnection between the areas. The optimal AGC are designed and implemented in the wake of 1% load perturbation in one of the areas and the system dynamic response plots for various system states are obtained to investigate the system dynamic performance. The pattern of closed-loop eigenvalues are also determined to analyze the system stability. From the investigations carried out in the work, it is revealed that the dynamic performance of the system under consideration has an appreciable improvement when a high voltage DC line is paralleled with an extra high voltage AC line as an interconnection between the areas. The investigation of closed-loop eigenvalues reveals that the system stability is ensured in all case studies carried out with the designed optimal AGC.

Keywords: Automatic generation control, area control error, DC link, optimal AGC regulator, closed-loop eigenvalues.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 826

Authors: Abdelhamid Louliej, Younes Jabrane

Abstract:

Satellites are becoming indispensable assets to fifth-generation (5G) new radio architecture, complementing wireless and terrestrial communication links. The combination of satellites and 5G architecture allows consumers to access all next-generation services anytime, anywhere, including scenarios, like traveling to remote areas (without coverage). Nevertheless, this solution faces several challenges, such as a significant propagation delay, Doppler frequency shift, and high Peak-to-Average Power Ratio (PAPR), causing signal distortion due to the non-linear saturation of the High-Power Amplifier (HPA). To compensate for HPA non-linearity in 5G satellite transmission, an efficient pre-distorter scheme using Neural Networks (NN) is proposed. To assess the proposed NN pre-distorter, two types of HPA were investigated: Travelling Wave Tube Amplifier (TWTA) and Solid-State Power Amplifier (SSPA). The results show that the NN pre-distorter design presents an Error Vector Magnitude (EVM) improvement by 95.26%. Normalized Mean Square Error (NMSE) and Adjacent Channel Power Ratio (ACPR) were reduced by -43,66 dB and 24.56 dBm, respectively. Moreover, the system suffers no degradation of the Bit Error Rate (BER) for TWTA and SSPA amplifiers.

Keywords: Satellites, 5G, Neural Networks, High-Power Amplifier, Travelling Wave Tube Amplifier, Solid-State Power Amplifier, EVM, NMSE, ACPR.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 107

Authors: Behnaz Shahrokh, Garnik N. Sargsyan, Arkadi B. Harutyunyan

Abstract:

Investigations of the unimolecular decomposition of vinyl ethyl ether (VEE), vinyl propyl ether (VPE) and vinyl butyl ether (VBE) have shown that activation of the molecule of a ether results in formation of a cyclic construction - the transition state (TS), which may lead to the displacement of the thermodynamic equilibrium towards the reaction products. The TS is obtained by applying energy minimization relative to the ground state of an ether under the program MM2 when taking into account the hydrogen bond formation between a hydrogen atom of alkyl residue and the extreme atom of carbon of the vinyl group. The dissociation of TS up to the products is studied by energy minimization procedure using the mathematical program Gaussian. The obtained calculation data for VEE testify that the decomposition of this ether may be conditioned by hydrogen bond formation for two possible versions: when α- or β- hydrogen atoms of the ethyl group are bound to carbon atom of the vinyl group. Applying the same calculation methods to other ethers (VPE and VBE) it is shown that only in the case of hydrogen bonding between α-hydrogen atom of the alkyl residue and the extreme atom of carbon of the vinyl group (αH---C) results in decay of theses ethers.

Keywords: Gaussian, MM2, ethers, TS, decomposition

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1220

Authors: Felicia Magpantay, Kenzu Abdella

Abstract:

A model of a system concerning one species of demersal (inshore) fish and one of pelagic (offshore) fish undergoing fishing restricted by marine protected areas is proposed in this paper. This setup was based on the FISH-BE model applied to the Tabina fishery in Zamboanga del Sur, Philippines. The components of the model equations have been adapted from widely-accepted mechanisms in population dynamics. The model employs Gompertz-s law of growth and interaction on each type of protected and unprotected subpopulation. Exchange coefficients between protected and unprotected areas were assumed to be proportional to the relative area of the entry region. Fishing harvests were assumed to be proportional to both the number of fishers and the number of unprotected fish. An extra term was included for the pelagic population to allow for the exchange between the unprotected area and the outside environment. The systems were found to be bounded for all parameter values. The equations for the steady state were unsolvable analytically but the existence and uniqueness of non-zero steady states can be proven. Plots also show that an MPA size yielding the maximum steady state of the unprotected population can be found. All steady states were found to be globally asymptotically stable for the entire range of parameter values.

Keywords: fisheries modelling, marine protected areas, sustainablefisheries, Gompertz Law

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1907

Authors: Shaukat Wasi, Zubair A. Shaikh, Sajid Qasmi, Hussain Sachwani, Rehman Lalani, Aamir Chagani

Abstract:

Automatic Extraction of Event information from social text stream (emails, social network sites, blogs etc) is a vital requirement for many applications like Event Planning and Management systems and security applications. The key information components needed from Event related text are Event title, location, participants, date and time. Emails have very unique distinctions over other social text streams from the perspective of layout and format and conversation style and are the most commonly used communication channel for broadcasting and planning events. Therefore we have chosen emails as our dataset. In our work, we have employed two statistical NLP methods, named as Finite State Machines (FSM) and Hidden Markov Model (HMM) for the extraction of event related contextual information. An application has been developed providing a comparison among the two methods over the event extraction task. It comprises of two modules, one for each method, and works for both bulk as well as direct user input. The results are evaluated using Precision, Recall and F-Score. Experiments show that both methods produce high performance and accuracy, however HMM was good enough over Title extraction and FSM proved to be better for Venue, Date, and time.

Keywords: Emails, Event Extraction, Event Detection, Finite state machines, Hidden Markov Model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2317

Authors: Qurban A Memon, Mohammad S. Laghari

Abstract:

Integration of system process information obtained through an image processing system with an evolving knowledge database to improve the accuracy and predictability of wear debris analysis is the main focus of the paper. The objective is to automate intelligently the analysis process of wear particle using classification via self-organizing maps. This is achieved using relationship measurements among corresponding attributes of various measurements for wear debris. Finally, visualization technique is proposed that helps the viewer in understanding and utilizing these relationships that enable accurate diagnostics.

Keywords: Relationship Network, Relationship Measurement, Self-organizing Clusters, Wear Debris Analysis, Kohonen Network

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1940

Authors: Jessica Lòpez Espejel, Mahaman Sanoussi Yahaya Alassan, Walid Dahhane, El Hassane Ettifouri

Abstract:

Pretrained transformer-based models have shown high performance in natural language generation task. However, a new wave of interest has surged: automatic programming language generation. This task consists of translating natural language instructions to a programming code. Despite the fact that well-known pretrained models on language generation have achieved good performance in learning programming languages, effort is still needed in automatic code generation. In this paper, we introduce JaCoText, a model based on Transformers neural network. It aims to generate java source code from natural language text. JaCoText leverages advantages of both natural language and code generation models. More specifically, we study some findings from the state of the art and use them to (1) initialize our model from powerful pretrained models, (2) explore additional pretraining on our java dataset, (3) carry out experiments combining the unimodal and bimodal data in the training, and (4) scale the input and output length during the fine-tuning of the model. Conducted experiments on CONCODE dataset show that JaCoText achieves new state-of-the-art results.

Keywords: Java code generation, Natural Language Processing, Sequence-to-sequence Models, Transformers Neural Networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 855

Authors: Wojciech Rejchel

Abstract:

The problem of ranking (rank regression) has become popular in the machine learning community. This theory relates to problems, in which one has to predict (guess) the order between objects on the basis of vectors describing their observed features. In many ranking algorithms a convex loss function is used instead of the 0-1 loss. It makes these procedures computationally efficient. Hence, convex risk minimizers and their statistical properties are investigated in this paper. Fast rates of convergence are obtained under conditions, that look similarly to the ones from the classification theory. Methods used in this paper come from the theory of U-processes as well as empirical processes.

Keywords: Convex loss function, empirical risk minimization, empirical process, U-process, boosting, euclidean family.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1414

Authors: Liton Jude Rozario, Mohammad Reduanul Haque, Md. Ziarul Islam, Mohammad Shorif Uddin

Abstract:

Face recognition is a technique to automatically identify or verify individuals. It receives great attention in identification, authentication, security and many more applications. Diverse methods had been proposed for this purpose and also a lot of comparative studies were performed. However, researchers could not reach unified conclusion. In this paper, we are reporting an extensive quantitative accuracy analysis of four most widely used face recognition algorithms: Principal Component Analysis (PCA), Independent Component Analysis (ICA), Linear Discriminant Analysis (LDA) and Support Vector Machine (SVM) using AT&T, Sheffield and Bangladeshi people face databases under diverse situations such as illumination, alignment and pose variations.

Keywords: PCA, ICA, LDA, SVM, face recognition, noise.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2431

Authors: Barbara Covarrubias Venegas, Sabine Groblschegg, Bernhard Klaus, Julia Domnanovich

Abstract:

Research Objectives: The roles and activities of Human Resource Management (HRM) have changed a lot in the past years. Driven by a changing environment and therefore new business requirements, the scope of human resource (HR) activities has widened. The extent to which these activities should focus on strategic issues to support the long term success of a company has been discussed in science for many years. As many economies of Central and Eastern Europe (CEE) experienced a phase of transition after the socialist era and are now recovering from the 2008 global crisis it is needed to examine the current state of HR positioning. Furthermore a trend in HR work developing from rather administrative units to being strategic partners of management can be noticed. This leads to the question of better understanding the underlying competencies which are necessary to support organisations. This topic was addressed by the international study “HR Competencies in international comparison”. The quantitative survey was conducted by the Institute for Human Resources & Organisation of FHWien University of Applied Science of WKW (A) in cooperation with partner universities in the countries Bosnia- Herzegovina, Croatia, Serbia and Slovenia. Methodology: Using the questionnaire developed by Dave Ulrich we tested whether the HR Competency model can be used for Austria, Bosnia and Herzegovina, Croatia, Serbia and Slovenia. After performing confirmatory and exploratory factor analysis for the whole data set containing all five countries we could clearly distinguish between four competencies. In a further step our analysis focused on median and average comparisons between the HR competency dimensions. Conclusion: Our literature review, in alignment with other studies, shows a relatively rapid pace of development of HR Roles and HR Competencies in BCSS in the past decades. Comparing data from BCSS and Austria we still can notice that regards strategic orientation there is a lack in BCSS countries, thus competencies are not as developed as in Austria. This leads us to the tentative conclusion that HR has undergone a rapid change but is still in a State of Transition from being a rather administrative unit to performing the role of a strategic partner.

Keywords: Comparative study, HR competencies, HRM, HR Roles.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2162

Authors: J. Ramos, V. Gil, A. F. Torres

Abstract:

In this research (using induction furnace process) nodular iron with three different percentages of copper (residual, 0.5% and 1,2%) was obtained. Chemical analysis was performed by mass spectrometry and microstructures were characterized by Optical Microscopy (ASTM E3) and Scanning Electron Microscopy (SEM). The study of mechanical behavior was carried out in a mechanical test machine (ASTM E8) and a Pin on disk tribometer (ASTM G99) was used to assess wear resistance. It is observed that the dissolution of copper in crystal lattice increases the pearlite structure improving the wear and hardness behavior, but producing a contrary effect on the energy absorption.

Keywords: Ferritic and perlite structure, mechanical properties, nodular iron, wear.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2267

Authors: Mohammad Reza Tabatabaei, Mohammad Bagher Haddadi, Mojtaba Saeedimoghadam, Ali Vaseghi Ardekani

Abstract:

Economic Dispatch (ED) is one of the most challenging problems of power system since it is difficult to determine the optimum generation scheduling to meet the particular load demand with the minimum fuel costs while all constraints are satisfied. The objective of the Economic Dispatch Problems (EDPs) of electric power generation is to schedule the committed generating units outputs so as to meet the required load demand at minimum operating cost while satisfying all units and system equality and inequality constraints. In this paper, an efficient and practical steady-state genetic algorithm (SSGAs) has been proposed for solving the economic dispatch problem. The objective is to minimize the total generation fuel cost and keep the power flows within the security limits. To achieve that, the present work is developed to determine the optimal location and size of capacitors in transmission power system where, the Participation Factor Algorithm and the Steady State Genetic Algorithm are proposed to select the best locations for the capacitors and determine the optimal size for them.

Keywords: Economic Dispatch, Lagrange, Capacitors Placement, Losses Reduction, Genetic Algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1672

Authors: R. Usubamatov, M. Z. Abdulmuin

Abstract:

Automated production lines with so called 'hard structures' are widely used in manufacturing. Designers segmented these lines into sections by placing a buffer between the series of machine tools to increase productivity. In real production condition the capacity of a buffer system is limited and real production line can compensate only some part of the productivity losses of an automated line. The productivity of such production lines cannot be readily determined. This paper presents mathematical approach to solving the structure of section-based automated production lines by criterion of maximum productivity.

Keywords: optimization production line, productivity, sections

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1325

Authors: S. Moein, S. A. Monadjemi, P. Moallem

Abstract:

In this paper, application of artificial neural networks in typical disease diagnosis has been investigated. The real procedure of medical diagnosis which usually is employed by physicians was analyzed and converted to a machine implementable format. Then after selecting some symptoms of eight different diseases, a data set contains the information of a few hundreds cases was configured and applied to a MLP neural network. The results of the experiments and also the advantages of using a fuzzy approach were discussed as well. Outcomes suggest the role of effective symptoms selection and the advantages of data fuzzificaton on a neural networks-based automatic medical diagnosis system.

Keywords: Artificial Neural Networks, Fuzzy Logic, MedicalDiagnosis, Symptoms, Fuzzification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2260