Search results for: Artificial neuronal networks

Authors: R. Biondi, G. Dys, G. Ferone, T. Renard, M. Zysman

Abstract:

This paper describes an automated implementable system for impulsive signals detection and recognition. The system uses a Digital Signal Processing device for the detection and identification process. Here the system analyses the signals in real time in order to produce a particular response if needed. The system analyses the signals in real time in order to produce a specific output if needed. Detection is achieved through normalizing the inputs and comparing the read signals to a dynamic threshold and thus avoiding detections linked to loud or fluctuating environing noise. Identification is done through neuronal network algorithms. As a setup our system can receive signals to “learn” certain patterns. Through “learning” the system can recognize signals faster, inducing flexibility to new patterns similar to those known. Sound is captured through a simple jack input, and could be changed for an enhanced recording surface such as a wide-area recorder. Furthermore a communication module can be added to the apparatus to send alerts to another interface if needed.

Keywords: Sound Detection, Impulsive Signal, Background Noise, Neural Network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2335

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: 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 632

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: Ninlawat Phuangchoke, Waraporn Viyanon, Setta Sasananan

Abstract:

The most important process of the water treatment plant process is coagulation, which uses alum and poly aluminum chloride (PACL). Therefore, determining the dosage of alum and PACL is the most important factor to be prescribed. This research applies an artificial neural network (ANN), which uses the Levenberg–Marquardt algorithm to create a mathematical model (Soft Jar Test) for chemical dose prediction, as used for coagulation, such as alum and PACL, with input data consisting of turbidity, pH, alkalinity, conductivity, and, oxygen consumption (OC) of the Bangkhen Water Treatment Plant (BKWTP), under the authority of the Metropolitan Waterworks Authority of Thailand. The data were collected from 1 January 2019 to 31 December 2019 in order to cover the changing seasons of Thailand. The input data of ANN are divided into three groups: training set, test set, and validation set. The coefficient of determination and the mean absolute errors of the alum model are 0.73, 3.18 and the PACL model are 0.59, 3.21, respectively.

Keywords: Soft jar test, jar test, water treatment plant process, artificial neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 665

Authors: Manasjyoti Bhuyan, Kandarpa Kumar Sarma

Abstract:

All the available algorithms for blind estimation namely constant modulus algorithm (CMA), Decision-Directed Algorithm (DDA/DFE) suffer from the problem of convergence to local minima. Also, if the channel drifts considerably, any DDA looses track of the channel. So, their usage is limited in varying channel conditions. The primary limitation in such cases is the requirement of certain overhead bits in the transmit framework which leads to wasteful use of the bandwidth. Also such arrangements fail to use channel state information (CSI) which is an important aid in improving the quality of reception. In this work, the main objective is to reduce the overhead imposed by the pilot symbols, which in effect reduces the system throughput. Also we formulate an arrangement based on certain dynamic Artificial Neural Network (ANN) topologies which not only contributes towards the lowering of the overhead but also facilitates the use of the CSI. A 2×2 Multiple Input Multiple Output (MIMO) system is simulated and the performance variation with different channel estimation schemes are evaluated. A new semi blind approach based on dynamic ANN is proposed for channel tracking in varying channel conditions and the performance is compared with perfectly known CSI and least square (LS) based estimation.

Keywords: MIMO, Artificial Neural Network (ANN), CMA, LS, CSI.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2372

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 983

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: S. X. Sun, Q. Wang

Abstract:

With the rapid development of industrialization, countries in different stages of development in the world have gradually begun to pay attention to the impact of air pollution on health and the environment. Air control in developed countries is an effective reference for air control in developing countries. Artificial intelligence and other technologies also play a positive role in the prediction of air pollution. By comparing the annual changes of pollution in London and Beijing, this paper concludes that the pollution in developed cities is relatively low and stable, while the pollution in Beijing is relatively heavy and unstable, but is clearly improving. In addition, by analyzing the changes of major pollutants in Beijing in the past eight years, it is concluded that all pollutants except O3 show a significant downward trend. In addition, all pollutants except O3 have certain correlation. For example, PM10 and PM2.5 have the greatest influence on air quality index (AQI). Python, which is commonly used by artificial intelligence, is used as the main software to establish two models, support vector machine (SVM) and linear regression. By comparing the two models under the same conditions, it is concluded that SVM has higher accuracy in pollution prediction. The results of this study provide valuable reference for pollution control and prediction in developing countries.

Keywords: Air pollution, particulate matter, AQI, correlation coefficient, air pollution prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 584

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 1846

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: Xiao Yihong, Yu Kexin, Burra Venkata Durga Kumar

Abstract:

With the accelerating process of urbanization, the problem of urban road congestion is becoming more and more serious. Intelligent transportation system combining distributed and artificial intelligence has become a research hotspot. As the core development direction of the intelligent transportation system, Cooperative Intelligent Transportation System (C-ITS) integrates advanced information technology and communication methods and realizes the integration of human, vehicle, roadside infrastructure and other elements through the multi-agent distributed system. By analyzing the system architecture and technical characteristics of C-ITS, the paper proposes a distributed multi-agent C-ITS. The system consists of Roadside Subsystem, Vehicle Subsystem and Personal Subsystem. At the same time, we explore the scalability of the C-ITS and put forward incorporating local rewards in the centralized training decentralized execution paradigm, hoping to add a scalable value decomposition method. In addition, we also suggest introducing blockchain to improve the safety of the traffic information transmission process. The system is expected to improve vehicle capacity and traffic safety.

Keywords: Distributed system, artificial intelligence, multi-agent, Cooperative Intelligent Transportation System.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 574

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: Roberto Iglesias, Theocharis Kyriacou, Ulrich Nehmzow, Steve Billings

Abstract:

Fundamental sensor-motor couplings form the backbone of most mobile robot control tasks, and often need to be implemented fast, efficiently and nevertheless reliably. Machine learning techniques are therefore often used to obtain the desired sensor-motor competences. In this paper we present an alternative to established machine learning methods such as artificial neural networks, that is very fast, easy to implement, and has the distinct advantage that it generates transparent, analysable sensor-motor couplings: system identification through nonlinear polynomial mapping. This work, which is part of the RobotMODIC project at the universities of Essex and Sheffield, aims to develop a theoretical understanding of the interaction between the robot and its environment. One of the purposes of this research is to enable the principled design of robot control programs. As a first step towards this aim we model the behaviour of the robot, as this emerges from its interaction with the environment, with the NARMAX modelling method (Nonlinear, Auto-Regressive, Moving Average models with eXogenous inputs). This method produces explicit polynomial functions that can be subsequently analysed using established mathematical methods. In this paper we demonstrate the fidelity of the obtained NARMAX models in the challenging task of robot route learning; we present a set of experiments in which a Magellan Pro mobile robot was taught to follow four different routes, always using the same mechanism to obtain the required control law.

Keywords: Mobile robotics, system identification, non-linear modelling, NARMAX.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1722

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: Tanveer A. Khan, Xue Y. Deng, Yan K. Wang, Xu Si-Wen

Abstract:

Experiments have been carried out at sub-critical Reynolds number to investigate free-to-roll motions induced by forebody and/or wings complex flow on a 30° swept back nonslender wings-slender body-model for static and dynamic (pitch-up) cases. For the dynamic (pitch-up) case it has been observed that roll amplitude decreases and lag increases with increase in pitching speed. Decrease in roll amplitude with increase in pitch rate is attributed to low disturbing rolling moment due to weaker interaction between forebody and wing flow components. Asymmetric forebody vortices dominate and control the roll motion of the model in dynamic case when non-dimensional pitch rate ≥ 1x10-2. Effectiveness of the active control scheme utilizing rotating nose with artificial tip perturbation is observed to be low in the angle of attack region where the complex flow over the wings has contributions from both forebody and wings.

Keywords: Artificial Tip Perturbation, ExperimentalInvestigations, Forebody Asymmetric Vortices, Non-slender Wings-Body Model, Wing Rock

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

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 1633

Authors: A. Kardi, R. Zagrouba, M. Alqahtani

Abstract:

The Internet of Everything (IoE) presents today a very attractive and motivating field of research. It is basically based on Wireless Sensor Networks (WSNs) in which the routing task is the major analysis topic. In fact, it directly affects the effectiveness and the lifetime of the network. This paper, developed from recent works and based on extensive researches, proposes a taxonomy of routing protocols in WSNs. Our main contribution is that we propose a classification model based on nine classes namely application type, delivery mode, initiator of communication, network architecture, path establishment (route discovery), network topology (structure), protocol operation, next hop selection and latency-awareness and energy-efficient routing protocols. In order to provide a total classification pattern to serve as reference for network designers, each class is subdivided into possible subclasses, presented, and discussed using different parameters such as purposes and characteristics.

Keywords: WSNs, sensor, routing protocols, survey.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1042

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 2476

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 2231

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: 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 1865

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: Nadia Masood Khan, Muhammad Salman Khan, Gul Muhammad Khan

Abstract:

Cardiologists perform cardiac auscultation to detect abnormalities in heart sounds. Since accurate auscultation is a crucial first step in screening patients with heart diseases, there is a need to develop computer-aided detection/diagnosis (CAD) systems to assist cardiologists in interpreting heart sounds and provide second opinions. In this paper different algorithms are implemented for automated heart sound classification using unsegmented phonocardiogram (PCG) signals. Support vector machine (SVM), artificial neural network (ANN) and cartesian genetic programming evolved artificial neural network (CGPANN) without the application of any segmentation algorithm has been explored in this study. The signals are first pre-processed to remove any unwanted frequencies. Both time and frequency domain features are then extracted for training the different models. The different algorithms are tested in multiple scenarios and their strengths and weaknesses are discussed. Results indicate that SVM outperforms the rest with an accuracy of 73.64%.

Keywords: Pattern recognition, machine learning, computer aided diagnosis, heart sound classification, and feature extraction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1283

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 1373