Search results for: training algorithms

Authors: Najmeh Abedzadeh, Matthew Jacobs

Abstract:

An intrusion detection system (IDS) is a software application that monitors malicious activities and generates alerts if any are detected. However, most network activities in IDS datasets are normal, and the relatively few numbers of attacks make the available data imbalanced. Consequently, cyber-attacks can hide inside a large number of normal activities, and machine learning algorithms have difficulty learning and classifying the data correctly. In this paper, a comprehensive literature review is conducted on different types of algorithms for both implementing the IDS and methods in correcting the imbalanced IDS dataset. The most famous algorithms are machine learning (ML), deep learning (DL), synthetic minority over-sampling technique (SMOTE), and reinforcement learning (RL). Most of the research use the CSE-CIC-IDS2017, CSE-CIC-IDS2018, and NSL-KDD datasets for evaluating their algorithms.

Keywords: IDS, intrusion detection system, imbalanced datasets, sampling algorithms, big data.

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

Authors: Nazleeni Samiha Haron, Anang Hudaya Muhamad Amin, Mohd Hilmi Hasan, Izzatdin Abdul Aziz, Wirdhayu Mohd Wahid

Abstract:

In any distributed systems, process scheduling plays a vital role in determining the efficiency of the system. Process scheduling algorithms are used to ensure that the components of the system would be able to maximize its utilization and able to complete all the processes assigned in a specified period of time. This paper focuses on the development of comparative simulator for distributed process scheduling algorithms. The objectives of the works that have been carried out include the development of the comparative simulator, as well as to implement a comparative study between three distributed process scheduling algorithms; senderinitiated, receiver-initiated and hybrid sender-receiver-initiated algorithms. The comparative study was done based on the Average Waiting Time (AWT) and Average Turnaround Time (ATT) of the processes involved. The simulation results show that the performance of the algorithms depends on the number of nodes in the system.

Keywords: Distributed Systems, Load Sharing, Process Scheduling, AWT and ATT

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1575

Authors: Abdolreza Hatamlou, Yusef Farhang, Mohammad Reza Meybodi

Abstract:

Variable ordering heuristics are used in constraint satisfaction algorithms. Different characteristics of various variable ordering heuristics are complementary. Therefore we have tried to get the advantages of all heuristics to improve search algorithms performance for solving constraint satisfaction problems. This paper considers combinations based on products and quotients, and then a newer form of combination based on weighted sums of ratings from a set of base heuristics, some of which result in definite improvements in performance.

Keywords: Constraint Satisfaction Problems, Variable Ordering Heuristics, Combination, Search Algorithms

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1316

Authors: Fituri H Belgassem, Abdulbasit Nigrat, Seddeeq Ghrari

Abstract:

In this paper, the construction of fast algorithms for the computation of Periodic Walsh Piecewise-Linear PWL transform and the Periodic Haar Piecewise-Linear PHL transform will be presented. Algorithms for the computation of the inverse transforms are also proposed. The matrix equation of the PWL and PHL transforms are introduced. Comparison of the computational requirements for the periodic piecewise-linear transforms and other orthogonal transforms shows that the periodic piecewise-linear transforms require less number of operations than some orthogonal transforms such as the Fourier, Walsh and the Discrete Cosine transforms.

Keywords: Piece wise linear transforms, Fast transforms, Fast algorithms.

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

Authors: M. Hadi Mashinchi, M. Reza Mashinchi, Siti Mariyam H. J. Shamsuddin

Abstract:

In this paper a genetic algorithms approach for solving the linear and quadratic fuzzy equations Ãx̃=B̃ and Ãx̃² + B̃x̃=C̃ , where Ã, B̃, C̃ and x̃ are fuzzy numbers is proposed by genetic algorithms. Our genetic based method initially starts with a set of random fuzzy solutions. Then in each generation of genetic algorithms, the solution candidates converge more to better fuzzy solution x̃_b . In this proposed method the final reached x̃_b is not only restricted to fuzzy triangular and it can be fuzzy number.

Keywords: Fuzzy coefficient, fuzzy equation, genetic algorithms.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2138

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 2646

Authors: Sheena Mathew, K. Poulose Jacob

Abstract:

Extensive use of the Internet coupled with the marvelous growth in e-commerce and m-commerce has created a huge demand for information security. The Secure Socket Layer (SSL) protocol is the most widely used security protocol in the Internet which meets this demand. It provides protection against eaves droppings, tampering and forgery. The cryptographic algorithms RC4 and HMAC have been in use for achieving security services like confidentiality and authentication in the SSL. But recent attacks against RC4 and HMAC have raised questions in the confidence on these algorithms. Hence two novel cryptographic algorithms MAJE4 and MACJER-320 have been proposed as substitutes for them. The focus of this work is to demonstrate the performance of these new algorithms and suggest them as dependable alternatives to satisfy the need of security services in SSL. The performance evaluation has been done by using practical implementation method.

Keywords: Confidentiality, HMAC, Integrity, MACJER-320, MAJE4, RC4, Secure Socket Layer

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1828

Authors: J. K. Alhassan, B. Attah, S. Misra

Abstract:

Human beings have the ability to make logical decisions. Although human decision - making is often optimal, it is insufficient when huge amount of data is to be classified. Medical dataset is a vital ingredient used in predicting patient’s health condition. In other to have the best prediction, there calls for most suitable machine learning algorithms. This work compared the performance of Artificial Neural Network (ANN) and Decision Tree Algorithms (DTA) as regards to some performance metrics using diabetes data. WEKA software was used for the implementation of the algorithms. Multilayer Perceptron (MLP) and Radial Basis Function (RBF) were the two algorithms used for ANN, while RegTree and LADTree algorithms were the DTA models used. From the results obtained, DTA performed better than ANN. The Root Mean Squared Error (RMSE) of MLP is 0.3913 that of RBF is 0.3625, that of RepTree is 0.3174 and that of LADTree is 0.3206 respectively.

Keywords: Artificial neural network, classification, decision tree, diabetes mellitus.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2374

Authors: Harish Chander, Balwinder Singh, Ravinder Khanna

Abstract:

In this paper, we present the comparative subjective analysis of Improved Minima Controlled Recursive Averaging (IMCRA) Algorithm, the Kalman filter and the cascading of IMCRA and Kalman filter algorithms. Performance of speech enhancement algorithms can be predicted in two different ways. One is the objective method of evaluation in which the speech quality parameters are predicted computationally. The second is a subjective listening test in which the processed speech signal is subjected to the listeners who judge the quality of speech on certain parameters. The comparative objective evaluation of these algorithms was analyzed in terms of Global SNR, Segmental SNR and Perceptual Evaluation of Speech Quality (PESQ) by the authors and it was reported that with cascaded algorithms there is a substantial increase in objective parameters. Since subjective evaluation is the real test to judge the quality of speech enhancement algorithms, the authenticity of superiority of cascaded algorithms over individual IMCRA and Kalman algorithms is tested through subjective analysis in this paper. The results of subjective listening tests have confirmed that the cascaded algorithms perform better under all types of noise conditions.

Keywords: Speech enhancement, spectral domain, time domain, PESQ, subjective analysis, objective analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1186

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 1845

Authors: H. B. Kekre, Tanuja K. Sarode

Abstract:

Mostly transforms are used for speech data compressions which are lossy algorithms. Such algorithms are tolerable for speech data compression since the loss in quality is not perceived by the human ear. However the vector quantization (VQ) has a potential to give more data compression maintaining the same quality. In this paper we propose speech data compression algorithm using vector quantization technique. We have used VQ algorithms LBG, KPE and FCG. The results table shows computational complexity of these three algorithms. Here we have introduced a new performance parameter Average Fractional Change in Speech Sample (AFCSS). Our FCG algorithm gives far better performance considering mean absolute error, AFCSS and complexity as compared to others.

Keywords: Vector Quantization, Data Compression, Encoding, , Speech coding.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2352

Authors: C. Treerattanaphan, P. Boonpramuk, P. Singla

Abstract:

Frequent, continuous speech training has proven to be a necessary part of a successful speech therapy process, but constraints of traveling time and employment dispensation become key obstacles especially for individuals living in remote areas or for dependent children who have working parents. In order to ameliorate speech difficulties with ample guidance from speech therapists, a website has been developed that supports speech therapy and training for people with articulation disorders in the standard Thai language. This web-based program has the ability to record speech training exercises for each speech trainee. The records will be stored in a database for the speech therapist to investigate, evaluate, compare and keep track of all trainees’ progress in detail. Speech trainees can request live discussions via video conference call when needed. Communication through this web-based program facilitates and reduces training time in comparison to walk-in training or appointments. This type of training also allows people with articulation disorders to practice speech lessons whenever or wherever is convenient for them, which can lead to a more regular training processes.

Keywords: Web-Based Remote Training Program, Thai Speech Therapy, Articulation Disorders.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1817

Authors: Fateme Ashari-Ghomi, Najme Khorasani, Abbas Nowzari-Dalini

Abstract:

In this paper, we present two new ranking and unranking algorithms for k-ary trees represented by x-sequences in Gray code order. These algorithms are based on a gray code generation algorithm developed by Ahrabian et al.. In mentioned paper, a recursive backtracking generation algorithm for x-sequences corresponding to k-ary trees in Gray code was presented. This generation algorithm is based on Vajnovszki-s algorithm for generating binary trees in Gray code ordering. Up to our knowledge no ranking and unranking algorithms were given for x-sequences in this ordering. we present ranking and unranking algorithms with O(kn2) time complexity for x-sequences in this Gray code ordering

Keywords: k-ary Tree Generation, Ranking, Unranking, Gray Code.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2064

Authors: Iman Zangeneh, Mostafa Moradi, Mazyar Baranpouyan

Abstract:

System is using multiple processors for computing and information processing, is increasing rapidly speed operation of these systems compared with single processor systems, very significant impact on system performance is increased .important differences to yield a single multi-processor cpu, the scheduling policies, to reduce the implementation time of all processes. Notwithstanding the famous algorithms such as SPT, LPT, LSPT and RLPT for scheduling and there, but none led to the answer are not optimal.In this paper scheduling using genetic algorithms and innovative way to finish the whole process faster that we do and the result compared with three algorithms we mentioned.

Keywords: Multiprocessor system, genetic algorithms, time implementation process.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1520

Authors: L. Abdelmalek, M. Zerikat, M. Rahli

Abstract:

In this paper, we present a comparative study of the genetic algorithms and Hessian-s methods for optimal research of the active powers in an electric network of power. The objective function which is the performance index of production of electrical energy is minimized by satisfying the constraints of the equality type and inequality type initially by the Hessian-s methods and in the second time by the genetic Algorithms. The results found by the application of AG for the minimization of the electric production costs of power are very encouraging. The algorithms seem to be an effective technique to solve a great number of problems and which are in constant evolution. Nevertheless it should be specified that the traditional binary representation used for the genetic algorithms creates problems of optimization of management of the large-sized networks with high numerical precision.

Keywords: Genetic algorithm, Flow of optimum loadimpedances, Hessians method, Optimal distribution.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1243

Authors: Philippe Fauquet-Alekhine

Abstract:

For professions of high risk industries, simulation training has always been thought in terms of high degree of fidelity regarding the real operational situation. Due to the recent progress, this way of training is changing, modifying the human-computer and software interactions: the interactions between trainees during simulation training session tend to become virtual, transforming the social-based embodiness (the way subjects integrate social skills for interpersonal relationship with co-workers). On the basis of the analysis of eight different profession trainings, a categorization of interactions has help to produce an analytical tool, the social interactions table. This tool may be very valuable to point out the changes of social interactions when the training sessions are skipping from a high fidelity simulator to a virtual simulator. In this case, it helps the designers of professional training to analyze and to assess the consequences of the potential lack the social-based embodiness.

Keywords: Interface, interaction, simulator, virtual training.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1745

Authors: Ivan C. Mustakerov, Daniela I. Borissova

Abstract:

In recent years, new product development became more and more competitive and globalized, and the designing phase is critical for the product success. The concept of modularity can provide the necessary foundation for organizations to design products that can respond rapidly to market needs. The paper describes data structures and algorithms of intelligent Web-based system for modular design taking into account modules compatibility relationship and given design requirements. The system intelligence is realized by developed algorithms for choice of modules reflecting all system restrictions and requirements. The proposed data structure and algorithms are illustrated by case study of personal computer configuration. The applicability of the proposed approach is tested through a prototype of Web-based system.

Keywords: Data structures, algorithms, intelligent web-based system, modular design.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1768

Authors: Ioannis Pratikakis, Anna Karahaliou, Katerina Vassiou, Vassilis Virvilis, Dimitrios Kosmopoulos, Stavros Perantonis

Abstract:

In this paper, a Web-based e-Training platform that is dedicated to multimodal breast imaging is presented. The assets of this platform are summarised in (i) the efficient representation of the curriculum flow that will permit efficient training; (ii) efficient tagging of multimodal content appropriate for the completion of realistic cases and (iii) ubiquitous accessibility and platform independence via a web-based approach.

Keywords: Breast imaging, e-Training, web-based learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1636

Authors: Liu Gang, Gu Nai-jie, Bi Kun, Tu Kun, Dong Wan-li

Abstract:

All-to-all personalized communication, also known as complete exchange, is one of the most dense communication patterns in parallel computing. In this paper, we propose new indirect algorithms for complete exchange on all-port ring and torus. The new algorithms fully utilize all communication links and transmit messages along shortest paths to completely achieve the theoretical lower bounds on message transmission, which have not be achieved among other existing indirect algorithms. For 2D r × c ( r % c ) all-port torus, the algorithm has time complexities of optimal transmission cost and O(c) message startup cost. In addition, the proposed algorithms accommodate non-power-of-two tori where the number of nodes in each dimension needs not be power-of-two or square. Finally, the algorithms are conceptually simple and symmetrical for every message and every node so that they can be easily implemented and achieve the optimum in practice.

Keywords: Complete exchange, collective communication, all-to-all personalized communication, parallel computing, wormhole routing, torus.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1461

Authors: Shiau-Feng Lin, Chiuhsiang Joe Lin, Rou-Wen Wang, Wei-Jung Shiang

Abstract:

The Virtual Reality (VR) is becoming increasingly important for business, education, and entertainment, therefore VR technology have been applied for training purposes in the areas of military, safety training and flying simulators. In particular, the superior and high reliability VR training system is very important in immersion. Manipulation training in immersive virtual environments is difficult partly because users must do without the hap contact with real objects they rely on in the real world to orient themselves and their manipulated. In this paper, we create a convincing questionnaire of immersion and an experiment to assess the influence of immersion on performance in VR training system. The Immersion Questionnaire (IQ) included spatial immersion, Psychological immersion, and Sensory immersion. We show that users with a training system complete visual attention and detection of signals. Twenty subjects were allocated to a factorial design consisting of two different VR systems (Desktop VR and Projector VR). The results indicated that different VR representation methods significantly affected the participants- Immersion dimensions.

Keywords: Virtual Reality, Training, Immersion, Visual Attention, Visual Detection

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1782

Authors: Hsin-Yi Huang, Ming-Sheng Liu, Jiun-Yan Shiau

Abstract:

Planning the order picking lists for warehouses to achieve some operational performances is a significant challenge when the costs associated with logistics are relatively high, and it is especially important in e-commerce era. Nowadays, many order planning techniques employ supervised machine learning algorithms. However, to define features for supervised machine learning algorithms is not a simple task. Against this background, we consider whether unsupervised algorithms can enhance the planning of order-picking lists. A double zone picking approach, which is based on using clustering algorithms twice, is developed. A simplified example is given to demonstrate the merit of our approach.

Keywords: order picking, warehouse, clustering, unsupervised learning

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 447

Authors: I. Sonia d’Apolito, Bianca Sisinni, Mirko Grimaldi, Barbara Gili Fivela

Abstract:

The American English contrast /ɑ-ʌ/ (cop-cup) is difficult to be produced by Italian learners since they realize L2-/ɑ-ʌ/ as L1-/ɔ-a/ respectively, due to differences in phonetic-phonological systems and also in grapheme-to-phoneme conversion rules. In this paper, we try to answer the following research questions: Can a short training improve the production of English /ɑ-ʌ/ by Italian learners? Is a perceptual training better than an articulatory (ultrasound - US) training? Thus, we compare a perceptual training with an US articulatory one to observe: 1) the effects of short trainings on L2-/ɑ-ʌ/ productions; 2) if the US articulatory training improves the pronunciation better than the perceptual training. In this pilot study, 9 Salento-Italian monolingual adults participated: 3 subjects performed a 1-hour perceptual training (ES-P); 3 subjects performed a 1-hour US training (ES-US); and 3 control subjects did not receive any training (CS). Verbal instructions about the phonetic properties of L2-/ɑ-ʌ/ and L1-/ɔ-a/ and their differences (representation on F1-F2 plane) were provided during both trainings. After these instructions, the ES-P group performed an identification training based on the High Variability Phonetic Training procedure, while the ES-US group performed the articulatory training, by means of US video of tongue gestures in L2-/ɑ-ʌ/ production and dynamic view of their own tongue movements and position using a probe under their chin. The acoustic data were analyzed and the first three formants were calculated. Independent t-tests were run to compare: 1) /ɑ-ʌ/ in pre- vs. post-test respectively; /ɑ-ʌ/ in pre- and post-test vs. L1-/a-ɔ/ respectively. Results show that in the pre-test all speakers realize L2-/ɑ-ʌ/ as L1-/ɔ-a/ respectively. Contrary to CS and ES-P groups, the ES-US group in the post-test differentiates the L2 vowels from those produced in the pre-test as well as from the L1 vowels, although only one ES-US subject produces both L2 vowels accurately. The articulatory training seems more effective than the perceptual one since it favors the production of vowels in the correct direction of L2 vowels and differently from the similar L1 vowels.

Keywords: L2 vowel production, perceptual training, articulatory training, ultrasound.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 973

Authors: Parvinder S. Sandhu, Sandeep Khimta, Kiranpreet Kaur

Abstract:

The prediction of Software quality during development life cycle of software project helps the development organization to make efficient use of available resource to produce the product of highest quality. “Whether a module is faulty or not" approach can be used to predict quality of a software module. There are numbers of software quality prediction models described in the literature based upon genetic algorithms, artificial neural network and other data mining algorithms. One of the promising aspects for quality prediction is based on clustering techniques. Most quality prediction models that are based on clustering techniques make use of K-means, Mixture-of-Guassians, Self-Organizing Map, Neural Gas and fuzzy K-means algorithm for prediction. In all these techniques a predefined structure is required that is number of neurons or clusters should be known before we start clustering process. But in case of Growing Neural Gas there is no need of predetermining the quantity of neurons and the topology of the structure to be used and it starts with a minimal neurons structure that is incremented during training until it reaches a maximum number user defined limits for clusters. Hence, in this work we have used Growing Neural Gas as underlying cluster algorithm that produces the initial set of labeled cluster from training data set and thereafter this set of clusters is used to predict the quality of test data set of software modules. The best testing results shows 80% accuracy in evaluating the quality of software modules. Hence, the proposed technique can be used by programmers in evaluating the quality of modules during software development.

Keywords: Growing Neural Gas, data clustering, fault prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1817

Authors: Ron Bishop, Jim Mitchell, Talitha Best

Abstract:

The increase in air travel worldwide has resulted in a pilot shortage. To increase student pilot capacity and lower costs, flight schools have increased the use of recreational aircraft (RA) with technological advanced cockpits in flight schools. The impact of RA based training compared to general aviation (GA) aircraft training on student mental workload is not well understood. This research investigated student pilot (N = 17) awareness of mental workload between technologically advanced cockpit equipped RA training with analogue gauge equipped GA training. The results showed a significantly higher rating of mental workload across subscales of mental and physical demand on the NASA-TLX in recreational aviation aircraft training compared to GA aircraft. Similarly, thematic content analysis of follow-up questions identified that mental workload of the student pilots flying the RA was perceived to be more than the GA aircraft.

Keywords: Glass cockpit, flight training, mental workload, student pilot.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 801

Authors: M. R. Mustafa, M. H. Isa, R. B. Rezaur

Abstract:

The use of artificial neural network (ANN) modeling for prediction and forecasting variables in water resources engineering are being increasing rapidly. Infrastructural applications of ANN in terms of selection of inputs, architecture of networks, training algorithms, and selection of training parameters in different types of neural networks used in water resources engineering have been reported. ANN modeling conducted for water resources engineering variables (river sediment and discharge) published in high impact journals since 2002 to 2011 have been examined and presented in this review. ANN is a vigorous technique to develop immense relationship between the input and output variables, and able to extract complex behavior between the water resources variables such as river sediment and discharge. It can produce robust prediction results for many of the water resources engineering problems by appropriate learning from a set of examples. It is important to have a good understanding of the input and output variables from a statistical analysis of the data before network modeling, which can facilitate to design an efficient network. An appropriate training based ANN model is able to adopt the physical understanding between the variables and may generate more effective results than conventional prediction techniques.

Keywords: ANN, discharge, modeling, prediction, sediment,

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 5590

Authors: D. Barron, M. Zeegers

Abstract:

In this paper, we argue that Design research is basic to countries- national productivity and competition agendas at the same time that vagaries of research training presents as one of the barriers faced by Design Higher Degree by Research students in engaging those agendas. We argue that, given industry requirements for research-trained recruits, students have the right to expect that research training will provide the foundations of a successful career on an academic or research pathway or a professional pathway, but that universities have yet to address problems in their provision of research training for Design doctoral students. We suggest that to facilitate this, rigorous research conducted on the provision of Doctoral programs in Design would serve to inform future activities in Design research in productive ways.

Keywords: Design, Doctoral Design Education, Research Training

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1396

Authors: Hassan Ghasemzadeh, Sepideh Mazrouee, Hassan Goldani Moghaddam, Hamid Shojaei, Mohammad Reza Kakoee

Abstract:

Block replacement algorithms to increase hit ratio have been extensively used in cache memory management. Among basic replacement schemes, LRU and FIFO have been shown to be effective replacement algorithms in terms of hit rates. In this paper, we introduce a flexible stack-based circuit which can be employed in hardware implementation of both LRU and FIFO policies. We propose a simple and efficient architecture such that stack-based replacement algorithms can be implemented without the drawbacks of the traditional architectures. The stack is modular and hence, a set of stack rows can be cascaded depending on the number of blocks in each cache set. Our circuit can be implemented in conjunction with the cache controller and static/dynamic memories to form a cache system. Experimental results exhibit that our proposed circuit provides an average value of 26% improvement in storage bits and its maximum operating frequency is increased by a factor of two

Keywords: Cache Memory, Replacement Algorithms, LeastRecently Used Algorithm, First In First Out Algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3389

Authors: Sandeep Sharma, Sarabjit Singh, Meenakshi Sharma

Abstract:

Load balancing is the process of improving the performance of a parallel and distributed system through a redistribution of load among the processors [1] [5]. In this paper we present the performance analysis of various load balancing algorithms based on different parameters, considering two typical load balancing approaches static and dynamic. The analysis indicates that static and dynamic both types of algorithm can have advancements as well as weaknesses over each other. Deciding type of algorithm to be implemented will be based on type of parallel applications to solve. The main purpose of this paper is to help in design of new algorithms in future by studying the behavior of various existing algorithms.

Keywords: Load balancing (LB), workload, distributed systems, Static Load balancing, Dynamic Load Balancing

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 5866

Authors: Sema Müge Özdemiray

Abstract:

In line with the new public management approach to provide effective and efficient services necessary to achieve the social goals of public institutions, employees must have the knowledge and skills required by the age. In conjunction with the transition from personnel management to human resources management, it is seen that there is a change in the understanding of in-service training, the understanding of "required in-service training" has switched to the understanding of "continuous in-service training". However, in terms of in-service training in Turkey, it seems to be trouble at the point of adopting to change. The main purpose of this study is to primarily create a conceptual framework of in-service training and subsequently determine, analyze and discuss the developments and problems faced by in-service training in Turkey in the transition from personnel management to human resources management. In accordance with this purpose, the necessary data of this study were collected using qualitative approaches. Observation and document analysis was used and content analysis was performed on the data gathered in the study. The results of this study, according to data such as the number of institutions requesting in-service training, allocated budget of in-service training, the number of people participating in such training, transition of personnel management to human resources management should not lead to a paradigm shift in Turkey’s understanding of in-service training, although this is compulsory for public institutions in accordance with the law in Turkey. In-service training in Turkish public administration is still not implemented effectively and is seen as a social activity for employees and a formality for institutions.

Keywords: Human resources management, in-service training, personnel management, public institutions.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 982

Authors: Hema C. R., Paulraj M. P., S. Yaacob, A. H. Adom, R. Nagarajan

Abstract:

Motor imagery classification provides an important basis for designing Brain Machine Interfaces [BMI]. A BMI captures and decodes brain EEG signals and transforms human thought into actions. The ability of an individual to control his EEG through imaginary mental tasks enables him to control devices through the BMI. This paper presents a method to design a four state BMI using EEG signals recorded from the C3 and C4 locations. Principle features extracted through principle component analysis of the segmented EEG are analyzed using two novel classification algorithms using Elman recurrent neural network and functional link neural network. Performance of both classifiers is evaluated using a particle swarm optimization training algorithm; results are also compared with the conventional back propagation training algorithm. EEG motor imagery recorded from two subjects is used in the offline analysis. From overall classification performance it is observed that the BP algorithm has higher average classification of 93.5%, while the PSO algorithm has better training time and maximum classification. The proposed methods promises to provide a useful alternative general procedure for motor imagery classification

Keywords: Motor Imagery, Brain Machine Interfaces, Neural Networks, Particle Swarm Optimization, EEG signal processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2397