Search results for: training method.

Authors: Rohitash Chandra, Christian W. Omlin

Abstract:

We present a hybrid architecture of recurrent neural networks (RNNs) inspired by hidden Markov models (HMMs). We train the hybrid architecture using genetic algorithms to learn and represent dynamical systems. We train the hybrid architecture on a set of deterministic finite-state automata strings and observe the generalization performance of the hybrid architecture when presented with a new set of strings which were not present in the training data set. In this way, we show that the hybrid system of HMM and RNN can learn and represent deterministic finite-state automata. We ran experiments with different sets of population sizes in the genetic algorithm; we also ran experiments to find out which weight initializations were best for training the hybrid architecture. The results show that the hybrid architecture of recurrent neural networks inspired by hidden Markov models can train and represent dynamical systems. The best training and generalization performance is achieved when the hybrid architecture is initialized with random real weight values of range -15 to 15.

Keywords: Deterministic finite-state automata, genetic algorithm, hidden Markov models, hybrid systems and recurrent neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1850

Authors: G. Mokryani, M. R. Haghifam, J. Esmaeilpoor

Abstract:

Happening of Ferroresonance phenomenon is one of the reasons of consuming and ruining transformers, so recognition of Ferroresonance phenomenon has a special importance. A novel method for classification of Ferroresonance presented in this paper. Using this method Ferroresonance can be discriminate from other transients such as capacitor switching, load switching, transformer switching. Wavelet transform is used for decomposition of signals and Competitive Neural Network used for classification. Ferroresonance data and other transients was obtained by simulation using EMTP program. Using Daubechies wavelet transform signals has been decomposed till six levels. The energy of six detailed signals that obtained by wavelet transform are used for training and trailing Competitive Neural Network. Results show that the proposed procedure is efficient in identifying Ferroresonance from other events.

Keywords: Competitive Neural Network, Ferroresonance, EMTP program, Wavelet transform.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1383

Authors: Ejaz Ali, Muhammad Younas, Tahir Saeed

Abstract:

In this age of information technology, organizations are revisiting their approach in great deal. E-administration is the most popular area to proceed with. Organizations in order to excel over their competitors are spending a substantial chunk of its resources on E-Administration as it is the most effective, transparent and efficient way to achieve their short term as well as long term organizational goals. E-administration being a tool of ICT plays a significant role towards effective management of HR practices resulting into optimal performance of an organization. The present research was carried out to analyze the impact of moderating role of e-administration in the relationships training and performance appraisal aligned with perceived organizational performance. The study is based on RBV and AMO theories, advocating that use of latest technology in execution of human resource (HR) functions enables an organization to achieve and sustain competitive advantage which leads to optimal firm performance.

Keywords: Human resource management, HR function, e-administration, performance appraisal, training, organizational performance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1115

Authors: Mohd Faridz Ahmad, Amirul Hakim Hasbullah

Abstract:

Electrical Muscle Stimulation (EMS) has been introduced and globally gained increasing attention on its usefulness. Continuous application of EMS may lead to the increment of muscle mass and indirectly will increase the strength. This study can be used as an alternative to help people especially those living a sedentary lifestyle to improve their muscle activity without having to go through a heavy workout session. Therefore, this study intended to investigate the effectiveness of EMS training program in 5 weeks interventions towards male body composition. It was a quasiexperimental design, held at the Impulse Studio Bangsar, which examined the effects of EMS training towards skeletal muscle mass among the subjects. Fifteen subjects (n = 15) were selected to assist in this study. The demographic data showed that, the average age of the subjects was 43.07 years old ± 9.90, height (173.4 cm ± 9.09) and weight was (85.79 kg ± 18.07). Results showed that there was a significant difference on the skeletal muscle mass (p = 0.01 < 0.05), upper body (p = 0.01 < 0.05) and lower body (p = 0.00 < 0.05). Therefore, the null hypothesis has been rejected in this study. As a conclusion, the application of EMS towards body composition can increase the muscle size and strength. This method has been proven to be able to improve athlete strength and thus, may be implemented in the sports science area of knowledge.

Keywords: Body composition, EMS, skeletal muscle mass, strength.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 6217

Authors: Mehdi Ghayoumi

Abstract:

We have applied new accelerated algorithm for linear discriminate analysis (LDA) in face recognition with support vector machine. The new algorithm has the advantage of optimal selection of the step size. The gradient descent method and new algorithm has been implemented in software and evaluated on the Yale face database B. The eigenfaces of these approaches have been used to training a KNN. Recognition rate with new algorithm is compared with gradient.

Keywords: lda, adaptive, svm, face recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1377

Authors: Mohamad Saleh Sangin Ostadi, Esmail Safari, Somayeh Akbari, Kaveh Qaderi Bagajan

Abstract:

The aim of this study is to compare abused and normal male students in Tehran guidance schools with emphasis on the co-dependency of their mothers. The method of this study is based on survey method and comparison (Ex-Post Facto). The method of sampling is also multi-stage cluster. Accordingly, we did sampling from secondary schools of education and training in Tehran, including 12 schools with levels of first, second and third. Each of the schools represents the three – high, medium and low- economic and social conditions. In the following, three classes from every school and 20 students from each class were randomly selected. By (CTQ) abused and normal students were separated that 670 children were recognized as normal and 50 children as abused. Then, 50 children were randomly selected from normal group and compared with abused group. Using Spanned-Fischer Co-dependency Scale, we compared mothers of abused and normal students. The results showed that mothers of the abused children have higher co- dependency average comparing to the mothers of the normal children.

Keywords: Co-dependency, child abuse, abused children, parental psychological health.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1661

Authors: Alexander Goncharenko, Andrey Denisov, Sergey Alyamkin, Evgeny Terentev

Abstract:

The neural network quantization is highly desired procedure to perform before running neural networks on mobile devices. Quantization without fine-tuning leads to accuracy drop of the model, whereas commonly used training with quantization is done on the full set of the labeled data and therefore is both time- and resource-consuming. Real life applications require simplification and acceleration of quantization procedure that will maintain accuracy of full-precision neural network, especially for modern mobile neural network architectures like Mobilenet-v1, MobileNet-v2 and MNAS. Here we present a method to significantly optimize training with quantization procedure by introducing the trained scale factors for discretization thresholds that are separate for each filter. Using the proposed technique, we quantize the modern mobile architectures of neural networks with the set of train data of only ∼ 10% of the total ImageNet 2012 sample. Such reduction of train dataset size and small number of trainable parameters allow to fine-tune the network for several hours while maintaining the high accuracy of quantized model (accuracy drop was less than 0.5%). Ready-for-use models and code are available in the GitHub repository.

Keywords: Distillation, machine learning, neural networks, quantization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 685

Authors: Tetyana Baydyk, Ernst Kussul, Sandra Bonilla Meza

Abstract:

There are many articles that attempt to establish the role of different facial fragments in face recognition. Various approaches are used to estimate this role. Frequently, authors calculate the entropy corresponding to the fragment. This approach can only give approximate estimation. In this paper, we propose to use a more direct measure of the importance of different fragments for face recognition. We propose to select a recognition method and a face database and experimentally investigate the recognition rate using different fragments of faces. We present two such experiments in the paper. We selected the PCNC neural classifier as a method for face recognition and parts of the LFW (Labeled Faces in the Wild) face database as training and testing sets. The recognition rate of the best experiment is comparable with the recognition rate obtained using the whole face.

Keywords: Face recognition, Labeled Faces in the Wild (LFW) database, Random Local Descriptor (RLD), random features.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 968

Authors: J.S.C. Prentice

Abstract:

The RK1GL2X3 method is a numerical method for solving initial value problems in ordinary differential equations, and is based on the RK1GL2 method which, in turn, is a particular case of the general RKrGLm method. The RK1GL2X3 method is a fourth-order method, even though its underlying Runge-Kutta method RK1 is the first-order Euler method, and hence, RK1GL2X3 is considerably more efficient than RK1. This enhancement is achieved through an implementation involving triple-nested two-point Gauss- Legendre quadrature.

Keywords: RK1GL2X3, RK1GL2, RKrGLm, Runge-Kutta, Gauss-Legendre, initial value problem, local error, global error.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1266

Authors: Souad Demigha

Abstract:

The paper aims to specify and build a system, a learning support in radiology-senology (breast radiology) dedicated to help assist junior radiologists-senologists in their radiologysenology- related activity based on experience of expert radiologistssenologists. This system is named SAFRS (i.e. system supporting the training of radiologists-senologists). It is based on the exploitation of radiologic-senologic images (primarily mammograms but also echographic images or MRI) and their related clinical files. The aim of such a system is to help breast cancer screening in education. In order to acquire this expert radiologist-senologist knowledge, we have used the CBR (case-based reasoning) approach. The SAFRS system will promote the evolution of teaching in radiology-senology by offering the “junior radiologist" trainees an advanced pedagogical product. It will permit a strengthening of knowledge together with a very elaborate presentation of results. At last, the know-how will derive from all these factors.

Keywords: Learning support, radiology-senology, training, education, CBR, accumulated experience.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1622

Authors: Mohammed Salem Alzahrani

Abstract:

In this paper the optimality of the solution of an existing real word assignment problem known as the seat assignment problem using Seat Assignment Method (SAM) is discussed. SAM is the newly driven method from three existing methods, Hungarian Method, Northwest Corner Method and Least Cost Method in a special way that produces the easiness & fairness among all methods that solve the seat assignment problem.

Keywords: Assignment Problem, Hungarian Method, Least Cost Method, Northwest Corner Method, Seat Assignment Method (SAM), A Real Word Assignment Problem.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3388

Authors: Alquliyev R.M., Kazimov T.H., Mahmudova Sh.C., Mahmudova R.Sh.

Abstract:

The given work is devoted to the description of Information Technologies NAS of Azerbaijan created and successfully maintained in Institute. On the basis of the decision of board of the Supreme Certifying commission at the President of the Azerbaijan Republic and Presidium of National Academy of Sciences of the Azerbaijan Republic, the organization of training courses on Computer Sciences for all post-graduate students and dissertators of the republic, taking of examinations of candidate minima, it was on-line entrusted to Institute of Information Technologies of the National Academy of Sciences of Azerbaijan. Therefore, teaching the computer sciences to post-graduate students and dissertators a scientific - methodological manual on effective application of new information technologies for research works by post-graduate students and dissertators and taking of candidate minima is carried out in the Educational Center. Information and communication technologies offer new opportunities and prospects of their application for teaching and training. The new level of literacy demands creation of essentially new technology of obtaining of scientific knowledge. Methods of training and development, social and professional requirements, globalization of the communicative economic and political projects connected with construction of a new society, depends on a level of application of information and communication technologies in the educational process. Computer technologies develop ideas of programmed training, open completely new, not investigated technological ways of training connected to unique opportunities of modern computers and telecommunications. Computer technologies of training are processes of preparation and transfer of the information to the trainee by means of computer. Scientific and technical progress as well as global spread of the technologies created in the most developed countries of the world is the main proof of the leading role of education in XXI century. Information society needs individuals having modern knowledge. In practice, all technologies, using special technical information means (computer, audio, video) are called information technologies of education.

Keywords: Educational Center, post-graduate, database.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1657

Authors: Hassan Masoumi, Ahad Salimi, Nazanin Barhemmat, Babak Gholami

Abstract:

Artificial neural networks have gained a lot of interest as empirical models for their powerful representational capacity, multi input and output mapping characteristics. In fact, most feedforward networks with nonlinear nodal functions have been proved to be universal approximates. In this paper, we propose a new supervised method for color image classification based on selforganizing feature maps (SOFM). This algorithm is based on competitive learning. The method partitions the input space using self-organizing feature maps to introduce the concept of local neighborhoods. Our image classification system entered into RGB image. Experiments with simulated data showed that separability of classes increased when increasing training time. In additional, the result shows proposed algorithms are effective for color image classification.

Keywords: Classification, SOFM, neural network, RGB images.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2276

Authors: Ali Sarosh, Dong Yun-Feng, Muhammad Umer

Abstract:

Fully reusable spaceplanes do not exist as yet. This implies that design-qualification for optimized highly-integrated forebody-inlet configuration of booster-stage vehicle cannot be based on archival data of other spaceplanes. Therefore, this paper proposes a novel TIPSO-SVM expert system methodology. A non-trivial problem related to optimization and classification of hypersonic forebody-inlet configuration in conjunction with mass-model of the two-stage-to-orbit (TSTO) vehicle is solved. The hybrid-heuristic machine learning methodology is based on two-step improved particle swarm optimizer (TIPSO) algorithm and two-step support vector machine (SVM) data classification method. The efficacy of method is tested by first evolving an optimal configuration for hypersonic compression system using TIPSO algorithm; thereafter, classifying the results using two-step SVM method. In the first step extensive but non-classified mass-model training data for multiple optimized configurations is segregated and pre-classified for learning of SVM algorithm. In second step the TIPSO optimized mass-model data is classified using the SVM classification. Results showed remarkable improvement in configuration and mass-model along with sizing parameters.

Keywords: TIPSO-SVM expert system, TIPSO algorithm, two-step SVM method, aerothermodynamics, mass-modeling, TSTO vehicle.

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

Authors: Seifedine Kadry

Abstract:

In this article, our objective is the analysis of the resolution of non-linear differential systems by combining Newton and Continuation (N-C) method. The iterative numerical methods converge where the initial condition is chosen close to the exact solution. The question of choosing the initial condition is answered by N-C method.

Keywords: Continuation Method, Newton Method, Finite Difference Method, Numerical Analysis and Non-Linear partial Differential Equation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1341

Authors: Isao Taguchi, Yasuo Sugai

Abstract:

This paper proposes an efficient learning method for the layered neural networks based on the selection of training data and input characteristics of an output layer unit. Comparing to recent neural networks; pulse neural networks, quantum neuro computation, etc, the multilayer network is widely used due to its simple structure. When learning objects are complicated, the problems, such as unsuccessful learning or a significant time required in learning, remain unsolved. Focusing on the input data during the learning stage, we undertook an experiment to identify the data that makes large errors and interferes with the learning process. Our method devides the learning process into several stages. In general, input characteristics to an output layer unit show oscillation during learning process for complicated problems. The multi-stage learning method proposes by the authors for the function approximation problems of classifying learning data in a phased manner, focusing on their learnabilities prior to learning in the multi layered neural network, and demonstrates validity of the multi-stage learning method. Specifically, this paper verifies by computer experiments that both of learning accuracy and learning time are improved of the BP method as a learning rule of the multi-stage learning method. In learning, oscillatory phenomena of a learning curve serve an important role in learning performance. The authors also discuss the occurrence mechanisms of oscillatory phenomena in learning. Furthermore, the authors discuss the reasons that errors of some data remain large value even after learning, observing behaviors during learning.

Keywords: data selection, function approximation problem, multistage leaning, neural network, voluntary oscillation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1389

Authors: M. Khatami Rad, N. Jamali, M. Torabizadeh, A. Noshadi

Abstract:

In this paper, an artificial neural network simulator is employed to carry out diagnosis and prognosis on electric motor as rotating machinery based on predictive maintenance. Vibration data of the primary failed motor including unbalance, misalignment and bearing fault were collected for training the neural network. Neural network training was performed for a variety of inputs and the motor condition was used as the expert training information. The main purpose of applying the neural network as an expert system was to detect the type of failure and applying preventive maintenance. The advantage of this study is for machinery Industries by providing appropriate maintenance that has an essential activity to keep the production process going at all processes in the machinery industry. Proper maintenance is pivotal in order to prevent the possible failures in operating system and increase the availability and effectiveness of a system by analyzing vibration monitoring and developing expert system.

Keywords: Condition based monitoring, expert system, neural network, fault detection, vibration monitoring.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1943

Authors: Dewan Md. Farid, Jerome Darmont, Nouria Harbi, Nguyen Huu Hoa, Mohammad Zahidur Rahman

Abstract:

In this paper, a new learning approach for network intrusion detection using naïve Bayesian classifier and ID3 algorithm is presented, which identifies effective attributes from the training dataset, calculates the conditional probabilities for the best attribute values, and then correctly classifies all the examples of training and testing dataset. Most of the current intrusion detection datasets are dynamic, complex and contain large number of attributes. Some of the attributes may be redundant or contribute little for detection making. It has been successfully tested that significant attribute selection is important to design a real world intrusion detection systems (IDS). The purpose of this study is to identify effective attributes from the training dataset to build a classifier for network intrusion detection using data mining algorithms. The experimental results on KDD99 benchmark intrusion detection dataset demonstrate that this new approach achieves high classification rates and reduce false positives using limited computational resources.

Keywords: Attributes selection, Conditional probabilities, information gain, network intrusion detection.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2649

Authors: Yan Ma, ShunBao Li

Abstract:

A new approach is adopted in this paper based on Turk and Pentland-s eigenface method. It was found that the probability density function of the distance between the projection vector of the input face image and the average projection vector of the subject in the face database, follows Rayleigh distribution. In order to decrease the false acceptance rate and increase the recognition rate, the input face image has been recognized using two thresholds including the acceptance threshold and the rejection threshold. We also find out that the value of two thresholds will be close to each other as number of trials increases. During the training, in order to reduce the number of trials, the projection vectors for each subject has been averaged. The recognition experiments using the proposed algorithm show that the recognition rate achieves to 92.875% whilst the average number of judgment is only 2.56 times.

Keywords: Eigenface, Face Recognition, Threshold, Rayleigh Distribution, Feature Extraction

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1449

Authors: Laila Y. Fannas, Ahmed Y. Ben Sasi

Abstract:

This research presents a handwritten signature recognition based on angle feature vector using Artificial Neural Network (ANN). Each signature image will be represented by an Angle vector. The feature vector will constitute the input to the ANN. The collection of signature images will be divided into two sets. One set will be used for training the ANN in a supervised fashion. The other set which is never seen by the ANN will be used for testing. After training, the ANN will be tested for recognition of the signature. When the signature is classified correctly, it is considered correct recognition otherwise it is a failure.

Keywords: Signature Recognition, Artificial Neural Network, Angle Features.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2451

Authors: Ampon Dhamacharoen, Kanittha Chompuvised

Abstract:

In this work, we solve multipoint boundary value problems where the boundary value conditions are equations using the Newton-Broyden Shooting method (NBSM).The proposed method is tested upon several problems from the literature and the results are compared with the available exact solution. The experiments are given to illustrate the efficiency and implementation of the method.

Keywords: Boundary value problem; Multipoint equation boundary value problems, Shooting Method, Newton-Broyden method.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1739

Authors: M. F. Patricio, P. M. Rosa

Abstract:

In this paper a class of numerical methods to solve linear and nonlinear PDEs and also systems of PDEs is developed. The Differential Transform method associated with the Method of Lines (MoL) is used. The theory for linear problems is extended to the nonlinear case, and a recurrence relation is established. This method can achieve an arbitrary high-order accuracy in time. A variable stepsize algorithm and some numerical results are also presented.

Keywords: Method of Lines, Differential Transform Method.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1702

Authors: Z. Veselý, M. Honner

Abstract:

High power laser – total emissivity method (HPL-TE method) for determination of coatings relative total emissivity dependent on the temperature is introduced. Method principle, experimental and evaluation parts of the method are described. Computer model of HPL-TE method is employed to perform the sensitivity analysis of the effect of method parameters on the sample surface temperature in the positions where the surface temperature and radiation heat flux are measured.

Keywords: High temperature laser testing, measurement ofthermal properties, emissivity, coatings.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1290

Authors: Ibrahim Abu-Alshaikh

Abstract:

In this study, a new root-finding method for solving nonlinear equations is proposed. This method requires two starting values that do not necessarily bracketing a root. However, when the starting values are selected to be close to a root, the proposed method converges to the root quicker than the secant method. Another advantage over all iterative methods is that; the proposed method usually converges to two distinct roots when the given function has more than one root, that is, the odd iterations of this new technique converge to a root and the even iterations converge to another root. Some numerical examples, including a sine-polynomial equation, are solved by using the proposed method and compared with results obtained by the secant method; perfect agreements are found.

Keywords: Iterative method, root-finding method, sine-polynomial equations, nonlinear equations.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1640

Authors: G. Vici, L. Cesanelli, L. Belli, R. Ceci, V. Polzonetti

Abstract:

Several factors contribute to success in sport and diet is one of them. Evidence-based sport nutrition guidelines underline the importance of macro- and micro-nutrients’ balance and timing in order to improve athlete’s physical status and performance. Nevertheless, a high content of proteins is commonly found in resistance training athletes’ diet with carbohydrate intake that is not enough or not well planned. The aim of the study was to evaluate the impact of different protein and carbohydrate diet contents on body composition and sport performance on a group of resistance training athletes. Subjects were divided as study group (n=16) and control group (n=14). For a period of 4 months, both groups were subjected to the same resistance training fitness program with study group following a specific diet and control group following an ab libitum diet. Body compositions were evaluated trough anthropometric measurement (weight, height, body circumferences and skinfolds) and Bioimpedence Analysis. Physical strength and training status of individuals were evaluated through the One Repetition Maximum test (RM1). Protein intake in studied group was found to be lower than in control group. There was a statistically significant increase of body weight, free fat mass and body mass cell of studied group respect to the control group. Fat mass remains almost constant. Statistically significant changes were observed in quadriceps and biceps circumferences, with an increase in studied group. The MR1 test showed improvement in study group’s strength but no changes in control group. Usually people consume hyper-proteic diet to achieve muscle mass development. Through this study, it was possible to show that protein intake fixed at 1,7 g/kg/d can meet the individual's needs. In parallel, the increased intake of carbohydrates, focusing on quality and timing of assumption, has enabled the obtainment of desired results with a training protocol supporting a hypertrophic strategy. Therefore, the key point seems related to the planning of a structured program both from a nutritional and training point of view.

Keywords: Body composition, diet, exercise, protein.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1005

Authors: Bing Yu , Xingshi He

Abstract:

In this paper, Differential Evolution (DE) algorithm, a new promising evolutionary algorithm, is proposed to train Radial Basis Function (RBF) network related to automatic configuration of network architecture. Classification tasks on data sets: Iris, Wine, New-thyroid, and Glass are conducted to measure the performance of neural networks. Compared with a standard RBF training algorithm in Matlab neural network toolbox, DE achieves more rational architecture for RBF networks. The resulting networks hence obtain strong generalization abilities.

Keywords: differential evolution, neural network, Rbf function

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2003

Authors: Jeff A. Tysinger, Dawn P. Tysinger

Abstract:

There has been considerable growth in online learning. Researchers continue to explore the impact various methods of delivery. Podcasting is a popular method for sharing information. The purpose of this study was to examine the impact of student motivation and the perception of the acquisition of knowledge in an online environment of a skill-based class. 25 students in a school psychology graduate class completed a pretest and posttest examining podcast use and familiarity. In addition, at the completion of the course they were administered a modified version of the Instructional Materials Motivation Survey. The four subscales were examined (attention, relevance, confidence, and satisfaction). Results indicated that students are motivated, they perceive podcasts as positive instructional tools, and students are successful in acquiring the needed information. Additional benefits of using podcasts and recommendations in school psychology training are discussed.

Keywords: Motivation, online learning, pedagogy, podcast.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 702

Authors: F.Alilat, S.Loumi, H.Merrad, B.Sansal

Abstract:

In this article a modification of the algorithm of the fuzzy ART network, aiming at returning it supervised is carried out. It consists of the search for the comparison, training and vigilance parameters giving the minimum quadratic distances between the output of the training base and those obtained by the network. The same process is applied for the determination of the parameters of the fuzzy ARTMAP giving the most powerful network. The modification consist in making learn the fuzzy ARTMAP a base of examples not only once as it is of use, but as many time as its architecture is in evolution or than the objective error is not reached . In this way, we don-t worry about the values to impose on the eight (08) parameters of the network. To evaluate each one of these three networks modified, a comparison of their performances is carried out. As application we carried out a classification of the image of Algiers-s bay taken by SPOT XS. We use as criterion of evaluation the training duration, the mean square error (MSE) in step control and the rate of good classification per class. The results of this study presented as curves, tables and images show that modified fuzzy ARTMAP presents the best compromise quality/computing time.

Keywords: Neural Networks, fuzzy ART, fuzzy ARTMAP, Remote sensing, multispectral Classification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1324

Authors: Abdul Rashid Ahmadi, Samiullah Paracha, Hamidullah Sokout, Mohammad Hanif Gharanai

Abstract:

Conventional educational practices, do not offer all the required skills for teachers to successfully survive in today’s workplace. Due to poor professional training, a big gap exists across the curriculum plan and the teacher practices in the classroom. As such, raising the quality of teaching through ICT-enabled training and professional development of teachers should be an urgent priority. ‘Mobile Learning’, in that vein, is an increasingly growing field of educational research and practice across schools and work places. In this paper, we propose a novel Mobile learning system that allows the users to learn through an intelligent mobile learning in cooperatively every-time and every-where. The system will reduce the training cost and increase consistency, efficiency, and data reliability. To establish that our system will display neither functional nor performance failure, the evaluation strategy is based on formal observation of users interacting with system followed by questionnaires and structured interviews.

Keywords: Computer Assisted Learning, Intelligent Tutoring system, Learner Centered Design, Mobile Mediated Learning and Teacher education (MMLTE).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2193

Authors: Hadi Veisi, Mansour Jamzad

Abstract:

In this paper we present an adaptive method for image compression that is based on complexity level of the image. The basic compressor/de-compressor structure of this method is a multilayer perceptron artificial neural network. In adaptive approach different Back-Propagation artificial neural networks are used as compressor and de-compressor and this is done by dividing the image into blocks, computing the complexity of each block and then selecting one network for each block according to its complexity value. Three complexity measure methods, called Entropy, Activity and Pattern-based are used to determine the level of complexity in image blocks and their ability in complexity estimation are evaluated and compared. In training and evaluation, each image block is assigned to a network based on its complexity value. Best-SNR is another alternative in selecting compressor network for image blocks in evolution phase which chooses one of the trained networks such that results best SNR in compressing the input image block. In our evaluations, best results are obtained when overlapping the blocks is allowed and choosing the networks in compressor is based on the Best-SNR. In this case, the results demonstrate superiority of this method comparing with previous similar works and JPEG standard coding.

Keywords: Adaptive image compression, Image complexity, Multi-layer perceptron neural network, JPEG Standard, PSNR.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2174