Search results for: dual-cube extensive networks

Authors: A. P. Anvar, T. Dowling, T. Putland, A. M. Anvar, S.Grainger

Abstract:

This paper presents the application of Intelligent Techniques to the various duties of Intelligent Condition Monitoring Systems (ICMS) for Unmanned Aerial Vehicle (UAV) Robots. These Systems are intended to support these Intelligent Robots in the event of a Fault occurrence. Neural Networks are used for Diagnosis, whilst Fuzzy Logic is intended for Prognosis and Remedy. The ultimate goals of ICMS are to save large losses in financial cost, time and data.

Keywords: Intelligent Techniques, Condition Monitoring Systems, ICMS, Robots, Fault, Unmanned Aerial Vehicle, UAV, Neural Networks, Diagnosis, Fuzzy Logic, Prognosis, Remedy.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2354

Authors: Mohamed Othmani, Yassine Khlifi

Abstract:

This paper presents a technique for compact three dimensional (3D) object model reconstruction using wavelet networks. It consists to transform an input surface vertices into signals,and uses wavelet network parameters for signal approximations. To prove this, we use a wavelet network architecture founded on several mother wavelet families. POLYnomials WindOwed with Gaussians (POLYWOG) wavelet families are used to maximize the probability to select the best wavelets which ensure the good generalization of the network. To achieve a better reconstruction, the network is trained several iterations to optimize the wavelet network parameters until the error criterion is small enough. Experimental results will shown that our proposed technique can effectively reconstruct an irregular 3D object models when using the optimized wavelet network parameters. We will prove that an accurateness reconstruction depends on the best choice of the mother wavelets.

Keywords: 3D object, optimization, parametrization, Polywog wavelets, reconstruction, wavelet networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1501

Authors: Maria E. Manioudaki, Panayiota Poirazi

Abstract:

Yeast cells live in a constantly changing environment that requires the continuous adaptation of their genomic program in order to sustain their homeostasis, survive and proliferate. Due to the advancement of high throughput technologies, there is currently a large amount of data such as gene expression, gene deletion and protein-protein interactions for S. Cerevisiae under various environmental conditions. Mining these datasets requires efficient computational methods capable of integrating different types of data, identifying inter-relations between different components and inferring functional groups or 'modules' that shape intracellular processes. This study uses computational methods to delineate some of the mechanisms used by yeast cells to respond to environmental changes. The GRAM algorithm is first used to integrate gene expression data and ChIP-chip data in order to find modules of coexpressed and co-regulated genes as well as the transcription factors (TFs) that regulate these modules. Since transcription factors are themselves transcriptionally regulated, a three-layer regulatory cascade consisting of the TF-regulators, the TFs and the regulated modules is subsequently considered. This three-layer cascade is then modeled quantitatively using artificial neural networks (ANNs) where the input layer corresponds to the expression of the up-stream transcription factors (TF-regulators) and the output layer corresponds to the expression of genes within each module. This work shows that (a) the expression of at least 33 genes over time and for different stress conditions is well predicted by the expression of the top layer transcription factors, including cases in which the effect of up-stream regulators is shifted in time and (b) identifies at least 6 novel regulatory interactions that were not previously associated with stress-induced changes in gene expression. These findings suggest that the combination of gene expression and protein-DNA interaction data with artificial neural networks can successfully model biological pathways and capture quantitative dependencies between distant regulators and downstream genes.

Keywords: gene modules, artificial neural networks, yeast, stress

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1465

Authors: Sepehr M.H.Jamarani, M.H.Moradi, H.Behnam, G.A.Rezai Rad

Abstract:

This paper presents an approach for early breast cancer diagnostic by employing combination of artificial neural networks (ANN) and multiwaveletpacket based subband image decomposition. The microcalcifications correspond to high-frequency components of the image spectrum, detection of microcalcifications is achieved by decomposing the mammograms into different frequency subbands,, reconstructing the mammograms from the subbands containing only high frequencies. For this approach we employed different types of multiwaveletpacket. We used the result as an input of neural network for classification. The proposed methodology is tested using the Nijmegen and the Mammographic Image Analysis Society (MIAS) mammographic databases and images collected from local hospitals. Results are presented as the receiver operating characteristic (ROC) performance and are quantified by the area under the ROC curve.

Keywords: Breast cancer, neural networks, diagnosis, multiwavelet packet, microcalcification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1400

Authors: S.L. Loh, S. Salleh, N.H. Sarmin

Abstract:

A spanning tree of a connected graph is a tree which consists the set of vertices and some or perhaps all of the edges from the connected graph. In this paper, a model for spanning tree transformation of connected graphs into single-row networks, namely Spanning Tree of Connected Graph Modeling (STCGM) will be introduced. Path-Growing Tree-Forming algorithm applied with Vertex-Prioritized is contained in the model to produce the spanning tree from the connected graph. Paths are produced by Path-Growing and they are combined into a spanning tree by Tree-Forming. The spanning tree that is produced from the connected graph is then transformed into single-row network using Tree Sequence Modeling (TSM). Finally, the single-row routing problem is solved using a method called Enhanced Simulated Annealing for Single-Row Routing (ESSR).

Keywords: Graph theory, simulated annealing, single-rowrouting and spanning tree.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1736

Authors: Praveen Boinee, Alessandro De Angelis, Gian Luca Foresti

Abstract:

Ensemble learning algorithms such as AdaBoost and Bagging have been in active research and shown improvements in classification results for several benchmarking data sets with mainly decision trees as their base classifiers. In this paper we experiment to apply these Meta learning techniques with classifiers such as random forests, neural networks and support vector machines. The data sets are from MAGIC, a Cherenkov telescope experiment. The task is to classify gamma signals from overwhelmingly hadron and muon signals representing a rare class classification problem. We compare the individual classifiers with their ensemble counterparts and discuss the results. WEKA a wonderful tool for machine learning has been used for making the experiments.

Keywords: Ensembles, WEKA, Neural networks [NN], SupportVector Machines [SVM], Random Forests [RF].

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1765

Authors: M. Safa, S. Samarasinghe

Abstract:

An artificial neural network (ANN) approach was used to model the energy consumption of wheat production. This study was conducted over 35,300 hectares of irrigated and dry land wheat fields in Canterbury in the 2007-2008 harvest year.1 In this study several direct and indirect factors have been used to create an artificial neural networks model to predict energy use in wheat production. The final model can predict energy consumption by using farm condition (size of wheat area and number paddocks), farmers- social properties (education), and energy inputs (N and P use, fungicide consumption, seed consumption, and irrigation frequency), it can also predict energy use in Canterbury wheat farms with error margin of ±7% (± 1600 MJ/ha).

Keywords: Artificial neural network, Canterbury, energy consumption, modelling, New Zealand, wheat.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1417

Authors: J. D. Mallapur, Supriya H., Santosh B. K., Tej H.

Abstract:

The cellular network is one of the emerging areas of communication, in which the mobile nodes act as member for one base station. The cluster based communication is now an emerging area of wireless cellular multimedia networks. The cluster renders fast communication and also a convenient way to work with connectivity. In our scheme we have proposed an optimization technique for the fuzzy cluster nodes, by categorizing the group members into three categories like long refreshable member, medium refreshable member and short refreshable member. By considering long refreshable nodes as static nodes, we compute the new membership values for the other nodes in the cluster. We compare their previous and present membership value with the threshold value to categorize them into three different members. By which, we optimize the nodes in the fuzzy clusters. The simulation results show that there is reduction in the cluster computational time and iterational time after optimization.

Keywords: Clusters, fuzzy and optimization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1570

Authors: J. Tospornsampan, I. Kita, M. Ishii, Y. Kitamura

Abstract:

In this paper a combination approach of two heuristic-based algorithms: genetic algorithm and tabu search is proposed. It has been developed to obtain the least cost based on the split-pipe design of looped water distribution network. The proposed combination algorithm has been applied to solve the three well-known water distribution networks taken from the literature. The development of the combination of these two heuristic-based algorithms for optimization is aimed at enhancing their strengths and compensating their weaknesses. Tabu search is rather systematic and deterministic that uses adaptive memory in search process, while genetic algorithm is probabilistic and stochastic optimization technique in which the solution space is explored by generating candidate solutions. Split-pipe design may not be realistic in practice but in optimization purpose, optimal solutions are always achieved with split-pipe design. The solutions obtained in this study have proved that the least cost solutions obtained from the split-pipe design are always better than those obtained from the single pipe design. The results obtained from the combination approach show its ability and effectiveness to solve combinatorial optimization problems. The solutions obtained are very satisfactory and high quality in which the solutions of two networks are found to be the lowest-cost solutions yet presented in the literature. The concept of combination approach proposed in this study is expected to contribute some useful benefits in diverse problems.

Keywords: GAs, Heuristics, Looped network, Least-cost design, Pipe network, Optimization, TS

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

Authors: Svitov David, Alyamkin Sergey

Abstract:

The usage of convolutional neural networks (CNNs) in conjunction with the margin-based softmax approach demonstrates the state-of-the-art performance for the face recognition problem. Recently, lightweight neural network models trained with the margin-based softmax have been introduced for the face identification task for edge devices. In this paper, we propose a distillation method for lightweight neural network architectures that outperforms other known methods for the face recognition task on LFW, AgeDB-30 and Megaface datasets. The idea of the proposed method is to use class centers from the teacher network for the student network. Then the student network is trained to get the same angles between the class centers and face embeddings predicted by the teacher network.

Keywords: ArcFace, distillation, face recognition, margin-based softmax.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 630

Authors: Wenqin Wang, Shouming Zhong

Abstract:

This paper presents the robust stability criteria for uncertain genetic regulatory networks with time-varying delays. One key point of the criterion is that the decomposition of the matrix ˜D into ˜D = ˜D1 + ˜D2. This decomposition corresponds to a decomposition of the delayed terms into two groups: the stabilizing ones and the destabilizing ones. This technique enables one to take the stabilizing effect of part of the delayed terms into account. Meanwhile, by choosing an appropriate new Lyapunov functional, a new delay-dependent stability criteria is obtained and formulated in terms of linear matrix inequalities (LMIs). Finally, numerical examples are presented to illustrate the effectiveness of the theoretical results.

Keywords: Genetic regulatory network, Time-varying delay, Uncertain system, Lyapunov-Krasovskii functional

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1523

Authors: Qitao Xie, Qingquan Zhang, Xiaofei Zhang, Di Tian, Ruixuan Wen, Ting Zhu, Ping Yi, Xin Li

Abstract:

Inspired by the recent movement of digital currency, we are building a question answering system concerning the subject of cryptocurrency using Bidirectional Encoder Representations from Transformers (BERT). The motivation behind this work is to properly assist digital currency investors by directing them to the corresponding knowledge bases that can offer them help and increase the querying speed. BERT, one of newest language models in natural language processing, was investigated to improve the quality of generated responses. We studied different combinations of hyperparameters of the BERT model to obtain the best fit responses. Further, we created an intelligent chatbot for cryptocurrency using BERT. A chatbot using BERT shows great potential for the further advancement of a cryptocurrency market tool. We show that the BERT neural networks generalize well to other tasks by applying it successfully to cryptocurrency.

Keywords: BERT, chatbot, cryptocurrency, deep learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 981

Authors: M. R. Ghasemi, A. Ehsani

Abstract:

In this paper, the optimum weight and cost of a laminated composite plate is seeked, while it undergoes the heaviest load prior to a complete failure. Various failure criteria are defined for such structures in the literature. In this work, the Tsai-Hill theory is used as the failure criterion. The theory of analysis was based on the Classical Lamination Theory (CLT). A newly type of Genetic Algorithm (GA) as an optimization technique with a direct use of real variables was employed. Yet, since the optimization via GAs is a long process, and the major time is consumed through the analysis, Radial Basis Function Neural Networks (RBFNN) was employed in predicting the output from the analysis. Thus, the process of optimization will be carried out through a hybrid neuro-GA environment, and the procedure will be carried out until a predicted optimum solution is achieved.

Keywords: Composite Laminates, GA, Multi-objectiveOptimisation, Neural Networks, RBFNN.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1631

Authors: Rakkrit Duangsoithong, Jermphiphut Jaruenpunyasak, Alba Garcia

Abstract:

The use of foot recognition can be applied in many medical fields such as the gait pattern analysis and the knee exercises of patients in rehabilitation. Generally, a camera-based foot recognition system is intended to capture a patient image in a controlled room and background to recognize the foot in the limited views. However, this system can be inconvenient to monitor the knee exercises at home. In order to overcome these problems, this paper proposes to use the deep learning method using Convolutional Neural Networks (CNNs) for foot recognition. The results are compared with the traditional classification method using LBP and HOG features with kNN and SVM classifiers. According to the results, deep learning method provides better accuracy but with higher complexity to recognize the foot images from online databases than the traditional classification method.

Keywords: Convolutional neural networks, deep learning, foot recognition, knee rehabilitation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1435

Authors: Hazem M. El-Bakry

Abstract:

In this paper, an automatic determination algorithm for nuclear magnetic resonance (NMR) spectra of the metabolites in the living body by magnetic resonance spectroscopy (MRS) without human intervention or complicated calculations is presented. In such method, the problem of NMR spectrum determination is transformed into the determination of the parameters of a mathematical model of the NMR signal. To calculate these parameters efficiently, a new model called modified Hopfield neural network is designed. The main achievement of this paper over the work in literature [30] is that the speed of the modified Hopfield neural network is accelerated. This is done by applying cross correlation in the frequency domain between the input values and the input weights. The modified Hopfield neural network can accomplish complex dignals perfectly with out any additinal computation steps. This is a valuable advantage as NMR signals are complex-valued. In addition, a technique called “modified sequential extension of section (MSES)" that takes into account the damping rate of the NMR signal is developed to be faster than that presented in [30]. Simulation results show that the calculation precision of the spectrum improves when MSES is used along with the neural network. Furthermore, MSES is found to reduce the local minimum problem in Hopfield neural networks. Moreover, the performance of the proposed method is evaluated and there is no effect on the performance of calculations when using the modified Hopfield neural networks.

Keywords: Hopfield Neural Networks, Cross Correlation, Nuclear Magnetic Resonance, Magnetic Resonance Spectroscopy, Fast Fourier Transform.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1845

Authors: K. Kalaiselvan, A. Elango, N. M. Nagarajan

Abstract:

Today automobile and aerospace industries realise Laser Beam Welding for a clean and non contact source of heating and fusion for joining of sheets. The welding performance is mainly based on by the laser welding parameters. Some concepts related to Artificial Neural Networks and how can be applied to model weld bead geometry and mechanical properties in terms of equipment parameters are reported in order to evaluate the accuracy and compare it with traditional modeling schemes. This review reveals the output features of Titanium and Aluminium weld bead geometry and mechanical properties such as ultimate tensile strength, yield strength, elongation and reduction of the area of the weld using Artificial Neural Network.

Keywords: Laser Beam Welding (LBW), Artificial Neural Networks (ANN), Optimization, Titanium and Aluminium sheets.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2357

Authors: Mohd Herwan Sulaiman, Omar Aliman, Siti Rafidah Abdul Rahim

Abstract:

This paper proposes a new methodology for the optimal allocation and sizing of Embedded Generation (EG) employing Real Coded Genetic Algorithm (RCGA) to minimize the total power losses and to improve voltage profiles in the radial distribution networks. RCGA is a method that uses continuous floating numbers as representation which is different from conventional binary numbers. The RCGA is used as solution tool, which can determine the optimal location and size of EG in radial system simultaneously. This method is developed in MATLAB. The effect of EG units- installation and their sizing to the distribution networks are demonstrated using 24 bus system.

Keywords: Embedded generation (EG), load flow study, optimal allocation, real coded genetic algorithm (RCGA).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1903

Authors: Ankit Sinha, Soham Banerjee, Pratik Chattopadhyay

Abstract:

Automated product recognition in retail stores is an important real-world application in the domain of Computer Vision and Pattern Recognition. In this paper, we consider the problem of automatically identifying the classes of the products placed on racks in retail stores from an image of the rack and information about the query/product images. We improve upon the existing approaches in terms of effectiveness and memory requirement by developing a two-stage object detection and recognition pipeline comprising of a Faster-RCNN-based object localizer that detects the object regions in the rack image and a ResNet-18-based image encoder that classifies  the detected regions into the appropriate classes. Each of the models is fine-tuned using appropriate data sets for better prediction and data augmentation is performed on each query image to prepare an extensive gallery set for fine-tuning the ResNet-18-based product recognition model. This encoder is trained using a triplet loss function following the strategy of online-hard-negative-mining for improved prediction. The proposed models are lightweight and can be connected in an end-to-end manner during deployment to automatically identify each product object placed in a rack image. Extensive experiments using Grozi-32k and GP-180 data sets verify the effectiveness of the proposed model.

Keywords: Retail stores, Faster-RCNN, object localization, ResNet-18, triplet loss, data augmentation, product recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 583

Authors: Namrata Mishra

Abstract:

Health of a person plays a vital role in the collective health of his community and hence the well-being of the society as a whole. But, in today’s fast paced technology driven world, health issues are increasingly being associated with human behaviors – their lifestyle. Social networks have tremendous impact on the health behavior of individuals. Many researchers have used social network analysis to understand human behavior that implicates their social and economic environments. It would be interesting to use a similar analysis to understand human behaviors that have health implications. This paper focuses on concepts of those behavioural analyses that have health implications using social networks analysis and provides possible algorithmic approaches. The results of these approaches can be used by the governing authorities for rolling out health plans, benefits and take preventive measures, while the pharmaceutical companies can target specific markets, helping health insurance companies to better model their insurance plans.

Keywords: Health behaviors, social network analysis, directed graph, breadth first search.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1908

Authors: Salvatore L., Pires B., Campos M. C. M., De Souza Jr M. B.

Abstract:

It is estimated that the total cost of abnormal conditions to US process industries is around $20 billion dollars in annual losses. The hydrotreatment (HDT) of diesel fuel in petroleum refineries is a conversion process that leads to high profitable economical returns. However, this is a difficult process to control because it is operated continuously, with high hydrogen pressures and it is also subject to disturbances in feed properties and catalyst performance. So, the automatic detection of fault and diagnosis plays an important role in this context. In this work, a hybrid approach based on neural networks together with a pos-processing classification algorithm is used to detect faults in a simulated HDT unit. Nine classes (8 faults and the normal operation) were correctly classified using the proposed approach in a maximum time of 5 minutes, based on on-line data process measurements.

Keywords: Fault detection, hydrotreatment, hybrid systems, neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1649

Authors: Hazem M. El-Bakry

Abstract:

Neural processors have shown good results for detecting a certain character in a given input matrix. In this paper, a new idead to speed up the operation of neural processors for character detection is presented. Such processors are designed based on cross correlation in the frequency domain between the input matrix and the weights of neural networks. This approach is developed to reduce the computation steps required by these faster neural networks for the searching process. The principle of divide and conquer strategy is applied through image decomposition. Each image is divided into small in size sub-images and then each one is tested separately by using a single faster neural processor. Furthermore, faster character detection is obtained by using parallel processing techniques to test the resulting sub-images at the same time using the same number of faster neural networks. In contrast to using only faster neural processors, the speed up ratio is increased with the size of the input image when using faster neural processors and image decomposition. Moreover, the problem of local subimage normalization in the frequency domain is solved. The effect of image normalization on the speed up ratio of character detection is discussed. Simulation results show that local subimage normalization through weight normalization is faster than subimage normalization in the spatial domain. The overall speed up ratio of the detection process is increased as the normalization of weights is done off line.

Keywords: Fast Character Detection, Neural Processors, Cross Correlation, Image Normalization, Parallel Processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1537

Authors: Jae Keun Park, Sung Je Hong, Kyong Hoon Kim, Tae Heum Kang, Wan Yeon Lee

Abstract:

In this paper, we propose a routing scheme that guarantees the residual lifetime of wireless sensor networks where each sensor node operates with a limited budget of battery energy. The scheme maximizes the communications QoS while sustaining the residual battery lifetime of the network for a specified duration. Communication paths of wireless nodes are translated into a directed acyclic graph(DAG) and the maximum-flow algorithm is applied to the graph. The found maximum flow are assigned to sender nodes, so as to maximize their communication QoS. Based on assigned flows, the scheme determines the routing path and the transmission rate of data packet so that any sensor node on the path would not exhaust its battery energy before a specified duration.

Keywords: Sensor network, battery, residual lifetime, routingscheme, QoS

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1632

Authors: Uttam Vijay, Nitin Gupta

Abstract:

Due to heavy energy constraints in WSNs clustering is an efficient way to manage the energy in sensors. There are many methods already proposed in the area of clustering and research is still going on to make clustering more energy efficient. In our paper we are proposing a minimum spanning tree based clustering using divide and conquer approach. The MST based clustering was first proposed in 1970’s for large databases. Here we are taking divide and conquer approach and implementing it for wireless sensor networks with the constraints attached to the sensor networks. This Divide and conquer approach is implemented in a way that we don’t have to construct the whole MST before clustering but we just find the edge which will be the part of the MST to a corresponding graph and divide the graph in clusters there itself if that edge from the graph can be removed judging on certain constraints and hence saving lot of computation.

Keywords: Algorithm, Clustering, Edge-Weighted Graph, Weighted-LEACH.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2475

Authors: Pawel P. Czapski, Andrzej Sluzek

Abstract:

This paper presents preliminary results regarding system-level power awareness for FPGA implementations in wireless sensor networks. Re-configurability of field programmable gate arrays (FPGA) allows for significant flexibility in its applications to embedded systems. However, high power consumption in FPGA becomes a significant factor in design considerations. We present several ideas and their experimental verifications on how to optimize power consumption at high level of designing process while maintaining the same energy per operation (low-level methods can be used additionally). This paper demonstrates that it is possible to estimate feasible power consumption savings even at the high level of designing process. It is envisaged that our results can be also applied to other embedded systems applications, not limited to FPGA-based.

Keywords: Power optimization, FPGA, system-level designing, wireless sensor networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2230

Authors: A. Mirzaaghazadeh, H. Motameni, M. Karshenas, H. Nematzadeh

Abstract:

Learning the gradient of neuron's activity function like the weight of links causes a new specification which is flexibility. In flexible neural networks because of supervising and controlling the operation of neurons, all the burden of the learning is not dedicated to the weight of links, therefore in each period of learning of each neuron, in fact the gradient of their activity function, cooperate in order to achieve the goal of learning thus the number of learning will be decreased considerably. Furthermore, learning neurons parameters immunes them against changing in their inputs and factors which cause such changing. Likewise initial selecting of weights, type of activity function, selecting the initial gradient of activity function and selecting a fixed amount which is multiplied by gradient of error to calculate the weight changes and gradient of activity function, has a direct affect in convergence of network for learning.

Keywords: Back propagation, Flexible, Gradient, Learning, Neural network, Pattern recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1495

Authors: Hamza A. Ali, Waleed A. J. Rasheed

Abstract:

The use of neural networks for recognition application is generally constrained by their inherent parameters inflexibility after the training phase. This means no adaptation is accommodated for input variations that have any influence on the network parameters. Attempts were made in this work to design a neural network that includes an additional mechanism that adjusts the threshold values according to the input pattern variations. The new approach is based on splitting the whole network into two subnets; main traditional net and a supportive net. The first deals with the required output of trained patterns with predefined settings, while the second tolerates output generation dynamically with tuning capability for any newly applied input. This tuning comes in the form of an adjustment to the threshold values. Two levels of supportive net were studied; one implements an extended additional layer with adjustable neuronal threshold setting mechanism, while the second implements an auxiliary net with traditional architecture performs dynamic adjustment to the threshold value of the main net that is constructed in dual-layer architecture. Experiment results and analysis of the proposed designs have given quite satisfactory conducts. The supportive layer approach achieved over 90% recognition rate, while the multiple network technique shows more effective and acceptable level of recognition. However, this is achieved at the price of network complexity and computation time. Recognition generalization may be also improved by accommodating capabilities involving all the innate structures in conjugation with Intelligence abilities with the needs of further advanced learning phases.

Keywords: Classification, Recognition, Neural Networks, Pattern Recognition, Generalization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1627

Authors: Jin Myoung Kim, Tae Ho Cho

Abstract:

Wireless Sensor networks have a wide spectrum of civil and military applications that call for secure communication such as the terrorist tracking, target surveillance in hostile environments. For the secure communication in these application areas, we propose a method for generating a hierarchical key structure for the efficient group key management. In this paper, we apply A* algorithm in generating a hierarchical key structure by considering the history data of the ratio of addition and eviction of sensor nodes in a location where sensor nodes are deployed. Thus generated key tree structure provides an efficient way of managing the group key in terms of energy consumption when addition and eviction event occurs. A* algorithm tries to minimize the number of messages needed for group key management by the history data. The experimentation with the tree shows efficiency of the proposed method.

Keywords: Heuristic search, key management, security, sensor network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1684

Authors: Amir Rastegarnia, Mohammad Ali Tinati, Azam Khalili

Abstract:

In this paper we consider the issue of distributed adaptive estimation over sensor networks. To deal with more realistic scenario, different variance for observation noise is assumed for sensors in the network. To solve the problem of different variance of observation noise, the proposed method is divided into two phases: I) Estimating each sensor-s observation noise variance and II) using the estimated variances to obtain the desired parameter. Our proposed algorithm is based on a diffusion least mean square (LMS) implementation with linear combiner model. In the proposed algorithm, the step-size parameter the coefficients of linear combiner are adjusted according to estimated observation noise variances. As the simulation results show, the proposed algorithm considerably improves the diffusion LMS algorithm given in literature.

Keywords: Adaptive filter, distributed estimation, sensor network, diffusion.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1864

Authors: Surender Kumar Soni, Dhirendra Pratap Singh

Abstract:

Wireless Sensor Networks can be used to monitor the physical phenomenon in such areas where human approach is nearly impossible. Hence the limited power supply is the major constraint of the WSNs due to the use of non-rechargeable batteries in sensor nodes. A lot of researches are going on to reduce the energy consumption of sensor nodes. Energy map can be used with clustering, data dissemination and routing techniques to reduce the power consumption of WSNs. Energy map can also be used to know which part of the network is going to fail in near future. In this paper, Energy map is constructed using the prediction based approach. Adaptive alpha GM(1,1) model is used as the prediction model. GM(1,1) is being used worldwide in many applications for predicting future values of time series using some past values due to its high computational efficiency and accuracy.

Keywords: Adaptive Alpha GM(1, 1) Model, Energy Map, Prediction Based Data Reduction, Wireless Sensor Networks

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1801

Authors: Koray U. Erbas

Abstract:

Neural networks are appealing for many applications since they are able to learn complex non-linear relationships between input and output data. As the number of neurons and layers in a neural network increase, it is possible to represent more complex relationships with automatically extracted features. Nowadays Deep Neural Networks (DNNs) are widely used in Computer Vision problems such as; classification, object detection, segmentation image editing etc. In this work, Facial Emotion Recognition task is performed by proposed Convolutional Neural Network (CNN)-based DNN architecture using FER2013 Dataset. Moreover, the effects of different hyperparameters (activation function, kernel size, initializer, batch size and network size) are investigated and ablation study results for Pooling Layer, Dropout and Batch Normalization are presented.

Keywords: Convolutional Neural Network, Deep Learning, Deep Learning Based FER, Facial Emotion Recognition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1371