Search results for: Genetic algorithm optimization

Authors: Ali Hussian Ali AlTimemy, Fawzi M. Al Naima

Abstract:

This paper presents the prediction of kidney dysfunction using different neural network (NN) approaches. Self organization Maps (SOM), Probabilistic Neural Network (PNN) and Multi Layer Perceptron Neural Network (MLPNN) trained with Back Propagation Algorithm (BPA) are used in this study. Six hundred and sixty three sets of analytical laboratory tests have been collected from one of the private clinical laboratories in Baghdad. For each subject, Serum urea and Serum creatinin levels have been analyzed and tested by using clinical laboratory measurements. The collected urea and cretinine levels are then used as inputs to the three NN models in which the training process is done by different neural approaches. SOM which is a class of unsupervised network whereas PNN and BPNN are considered as class of supervised networks. These networks are used as a classifier to predict whether kidney is normal or it will have a dysfunction. The accuracy of prediction, sensitivity and specificity were found for each type of the proposed networks .We conclude that PNN gives faster and more accurate prediction of kidney dysfunction and it works as promising tool for predicting of routine kidney dysfunction from the clinical laboratory data.

Keywords: Kidney Dysfunction, Prediction, SOM, PNN, BPNN, Urea and Creatinine levels.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1931

Authors: Loai AbdAllah, Ilan Shimshoni

Abstract:

Missing values in data are common in real world applications. Since the performance of many data mining algorithms depend critically on it being given a good metric over the input space, we decided in this paper to define a distance function for unlabeled datasets with missing values. We use the Bhattacharyya distance, which measures the similarity of two probability distributions, to define our new distance function. According to this distance, the distance between two points without missing attributes values is simply the Mahalanobis distance. When on the other hand there is a missing value of one of the coordinates, the distance is computed according to the distribution of the missing coordinate. Our distance is general and can be used as part of any algorithm that computes the distance between data points. Because its performance depends strongly on the chosen distance measure, we opted for the k nearest neighbor classifier to evaluate its ability to accurately reflect object similarity. We experimented on standard numerical datasets from the UCI repository from different fields. On these datasets we simulated missing values and compared the performance of the kNN classifier using our distance to other three basic methods. Our  experiments show that kNN using our distance function outperforms the kNN using other methods. Moreover, the runtime performance of our method is only slightly higher than the other methods.

Keywords: Missing values, Distance metric, Bhattacharyya distance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2751

Authors: Amandeep Singh, Mandeep Kaur

Abstract:

Error correcting codes are used for detection and correction of errors in digital communication system. Error correcting coding is based on appending of redundancy to the information message according to a prescribed algorithm. Reed Solomon codes are part of channel coding and withstand the effect of noise, interference and fading. Galois field arithmetic is used for encoding and decoding reed Solomon codes. Galois field multipliers and linear feedback shift registers are used for encoding the information data block. The design of Reed Solomon encoder is complex because of use of LFSR and Galois field arithmetic. The purpose of this paper is to design and implement Reed Solomon (255, 239) encoder with optimized and lesser number of Galois Field multipliers. Symmetric generator polynomial is used to reduce the number of GF multipliers. To increase the capability toward error correction, convolution interleaving will be used with RS encoder. The Design will be implemented on Xilinx FPGA Spartan II.

Keywords: Galois Field, Generator polynomial, LFSR, Reed Solomon.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4844

Authors: S. N. Hosseini, S. M. H. Karimian

Abstract:

A new conserving approach in the context of Immersed Boundary Method (IBM) is presented to simulate one dimensional, incompressible flow in a moving boundary problem. The method employs control volume scheme to simulate the flow field. The concept of ghost node is used at the boundaries to conserve the mass and momentum equations. The Present method implements the conservation laws in all cells including boundary control volumes. Application of the method is studied in a test case with moving boundary. Comparison between the results of this new method and a sharp interface (Image Point Method) IBM algorithm shows a well distinguished improvement in both pressure and velocity fields of the present method. Fluctuations in pressure field are fully resolved in this proposed method. This approach expands the IBM capability to simulate flow field for variety of problems by implementing conservation laws in a fully Cartesian grid compared to other conserving methods.

Keywords: Immersed Boundary Method, conservation of mass and momentum laws, moving boundary, boundary condition.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1990

Authors: Αlexios Kotsakis, Stefanos Katsavounis, Dimitra Alexiou

Abstract:

Networks can be utilized to represent project planning problems, using nodes for activities and arcs to indicate precedence relationship between them. For fixed activity duration, a simple algorithm calculates the amount of time required to complete a project, followed by the activities that comprise the critical path. Program Evaluation and Review Technique (PERT) generalizes the above model by incorporating uncertainty, allowing activity durations to be random variables, producing nevertheless a relatively crude solution in planning problems. In this paper, based on the findings of the relevant literature, which strongly suggests that a Beta distribution can be employed to model earthmoving activities, we utilize Monte Carlo simulation, to estimate the project completion time distribution and measure the influence of skewness, an element inherent in activities of modern technical projects. We also extract the activity criticality index, with an ultimate goal to produce more accurate planning estimations.

Keywords: Beta distribution, PERT, Monte Carlo Simulation, skewness, project completion time distribution.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 770

Authors: Tae Hyun Ahn, Gyo Woo Lee, Man Young Kim

Abstract:

Because of high thermal efficiency and low CO2 emission, diesel engines are being used widely in many industrial fields although it makes many PM and NOx which give both human health and environment a negative effect. NOx regulations for diesel engines, however, are being strengthened and it is impossible to meet the emission standard without NOx reduction devices such as SCR (Selective Catalytic Reduction), LNC (Lean NOx Catalyst), and LNT (Lean NOx Trap). Among the NOx reduction devices, urea-SCR system is known as the most stable and efficient method to solve the problem of NOx emission. But this device has some issues associated with the ammonia slip phenomenon which is occurred by shortage of evaporation and thermolysis time, and that makes it difficult to achieve uniform distribution of the injected urea in front of monolith. Therefore, this study has focused on the mixing enhancement between urea and exhaust gases to enhance the efficiency of the SCR catalyst equipped in catalytic muffler by changing inlet gas temperature and spray conditions to improve the spray uniformity of the urea water solution. Finally, it can be found that various parameters such as inlet gas temperature and injector and injection angles significantly affect the evaporation and mixing of the urea water solution with exhaust gases, and therefore, optimization of these parameters are required.

Keywords: Evaporation, Injection, Selective Catalytic Reduction (SCR), Thermolysis, UWS (Urea-Water-Solution).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2890

Authors: M.V Rajesh, Archana R, A Unnikrishnan, R Gopikakumari, Jeevamma Jacob

Abstract:

The System Identification problem looks for a suitably parameterized model, representing a given process. The parameters of the model are adjusted to optimize a performance function based on error between the given process output and identified process output. The linear system identification field is well established with many classical approaches whereas most of those methods cannot be applied for nonlinear systems. The problem becomes tougher if the system is completely unknown with only the output time series is available. It has been reported that the capability of Artificial Neural Network to approximate all linear and nonlinear input-output maps makes it predominantly suitable for the identification of nonlinear systems, where only the output time series is available. [1][2][4][5]. The work reported here is an attempt to implement few of the well known algorithms in the context of modeling of nonlinear systems, and to make a performance comparison to establish the relative merits and demerits.

Keywords: Multilayer neural networks, Radial Basis Functions, Clustering algorithm, Back Propagation training, Extended Kalmanfiltering, Mean Square Error, Nonlinear Modeling, Cramer RaoLower Bound.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1646

Authors: Umar Manzoor, Kiran Ijaz, Wajiha Shamim, Arshad Ali Shahid

Abstract:

Transaction management is one of the most crucial requirements for enterprise application development which often require concurrent access to distributed data shared amongst multiple application / nodes. Transactions guarantee the consistency of data records when multiple users or processes perform concurrent operations. Existing Fault Tolerance Infrastructure for Mobile Agents (FTIMA) provides a fault tolerant behavior in distributed transactions and uses multi-agent system for distributed transaction and processing. In the existing FTIMA architecture, data flows through the network and contains personal, private or confidential information. In banking transactions a minor change in the transaction can cause a great loss to the user. In this paper we have modified FTIMA architecture to ensure that the user request reaches the destination server securely and without any change. We have used triple DES for encryption/ decryption and MD5 algorithm for validity of message.

Keywords: Distributed Transaction, Security, Mobile Agents, FTIMA Architecture.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1525

Authors: H. Mehdi, Kh. S. Karimov, A. A. Kavokin

Abstract:

Methods of clustering which were developed in the data mining theory can be successfully applied to the investigation of different kinds of dependencies between the conditions of environment and human activities. It is known, that environmental parameters such as temperature, relative humidity, atmospheric pressure and illumination have significant effects on the human mental performance. To investigate these parameters effect, data mining technique of clustering using entropy and Information Gain Ratio (IGR) K(Y/X) = (H(X)–H(Y/X))/H(Y) is used, where H(Y)=-ΣPi ln(Pi). This technique allows adjusting the boundaries of clusters. It is shown that the information gain ratio (IGR) grows monotonically and simultaneously with degree of connectivity between two variables. This approach has some preferences if compared, for example, with correlation analysis due to relatively smaller sensitivity to shape of functional dependencies. Variant of an algorithm to implement the proposed method with some analysis of above problem of environmental effects is also presented. It was shown that proposed method converges with finite number of steps.

Keywords: Clustering, Correlation analysis, EnvironmentalParameters, Information Gain Ratio, Mental Performance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1824

Authors: Jean-Christophe Sibel, Sylvain Reynal, David Declercq

Abstract:

In the context of channel coding, the Generalized Belief Propagation (GBP) is an iterative algorithm used to recover the transmission bits sent through a noisy channel. To ensure a reliable transmission, we apply a map on the bits, that is called a code. This code induces artificial correlations between the bits to send, and it can be modeled by a graph whose nodes are the bits and the edges are the correlations. This graph, called Tanner graph, is used for most of the decoding algorithms like Belief Propagation or Gallager-B. The GBP is based on a non unic transformation of the Tanner graph into a so called region-graph. A clear advantage of the GBP over the other algorithms is the freedom in the construction of this graph. In this article, we explain a particular construction for specific graph topologies that involves relevant performance of the GBP. Moreover, we investigate the behavior of the GBP considered as a dynamic system in order to understand the way it evolves in terms of the time and in terms of the noise power of the channel. To this end we make use of classical measures and we introduce a new measure called the hyperspheres method that enables to know the size of the attractors.

Keywords: iterative decoder, LDPC, region-graph, chaos.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1648

Authors: Wiesław Szulczewski, Wojciech Jakubowski, Andrzej Żyromski, Małgorzata Biniak-Pieróg

Abstract:

The aim of the paper was to elaborate a novel calculator BasWilCalc, that allows to estimate the actual amount of biomass on the basket willow plantations. The proposed method is based on the results of field experiment conducted during years  2011-2013 on basket willow plantation in the south-western part of Poland. As input data the results of destructive measurements of the diameter, length and weight of willow stems and non-destructive biometric measurements of diameter in the middle of stems and their length during the growing season performed at weekly intervals were used. Performed analysis enabled to develop the algorithm which, due to the fact that energy plantations are of known and constant planting structure, allows to estimate the actual amount of willow basket biomass on the plantation with a given probability and accuracy specified by the model, based on the number of stems measured and the age of the plantation.

Keywords: Basket willow (Salix viminalis) biomass, biometric measurements, yield, biomass calculator.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1667

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 2698

Authors: Hsin-Yun Lee

Abstract:

In this study, the pedestrian simulation VISWALK integration and application platform ant algorithms written program made to construct a renovation engineering schedule planning mode. The use of simulation analysis platform construction site when the user running the simulation, after calculating the user walks in the case of construction delays, the ant algorithm to find out the minimum delay time schedule plan, and add volume and unit area deactivated loss of business computing, and finally to the owners and users of two different positions cut considerations pick out the best schedule planning. To assess and validate its effectiveness, this study constructed the model imported floor of a shopping mall floor renovation engineering cases. Verify that the case can be found from the mode of the proposed project schedule planning program can effectively reduce the delay time and the user's walking mall loss of business, the impact of the operation on the renovation engineering facilities in the building to a minimum.

Keywords: Pedestrian, renovation, schedule, simulation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2331

Authors: Tyng-Rong Roan, Fuji Foo, Wenwey Hseush

Abstract:

Recent development of AI and edge computing plays a critical role to capture meaningful events such as detection of an unattended bag. One of the core problems is re-identification across multiple CCTVs. Immediately following the detection of a meaningful event is to track and trace the objects related to the event. In an extensive environment, the challenge becomes severe when the number of CCTVs increases substantially, imposing difficulties in achieving high accuracy while maintaining real-time performance. The algorithm that re-identifies cross-boundary objects for extensive tracking is referred to Extensive Re-Identification, which emphasizes the issues related to the complexity behind a great number of CCTVs. The Spatial-Temporal Awareness approach challenges the conventional thinking and concept of operations which is labor intensive and time consuming. The ability to perform Extensive Re-Identification through a multi-sensory network provides the next-level insights – creating value beyond traditional risk management.

Keywords: Long-short-term memory, re-identification, security critical application, spatial-temporal awareness.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 532

Authors: S.S.Mohanavalli, Sheila Anand

Abstract:

This paper proposes a novel architecture for At- Home medical care which enables senior citizens, patients with chronic ailments and patients requiring post- operative care to be remotely monitored in the comfort of their homes. This architecture is implemented using sensors and wireless networking for transmitting patient data to the hospitals, health- care centers for monitoring by medical professionals. Patients are equipped with sensors to measure their physiological parameters, like blood pressure, pulse rate etc. and a Wearable Data Acquisition Unit is used to transmit the patient sensor data. Medical professionals can be alerted to any abnormal variations in these values for diagnosis and suitable treatment. Security threats and challenges inherent to wireless communication and sensor network have been discussed and a security mechanism to ensure data confidentiality and source authentication has been proposed. Symmetric key algorithm AES has been used for encrypting the data and a patent-free, two-pass block cipher mode CCFB has been used for implementing semantic security.

Keywords: data confidentiality, integrity, remotemonitoring, source authentication

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1742

Authors: Penghui Zhang, Hua Zhang, Jun-Bo Wang, Cheng Zeng, Zijian Cao

Abstract:

With the development of software-defined networks and programmable data planes, in-band network telemetry (INT) has become an emerging technology in communications because it can get accurate and real-time network information. However, due to the expansion of the network scale, existing telemetry systems, to the best of the authors’ knowledge, have difficulty in meeting the common requirements of low overhead, low latency and full coverage for traffic measurement. This paper proposes a network-wide telemetry system with a low-latency low-overhead path planning (INT-LLPP). This paper builds a mathematical model to analyze the telemetry overhead and latency of INT systems. Then, we adopt a greedy-based path planning algorithm to reduce the overhead and latency of the network telemetry with the full network coverage. The simulation results show that network-wide telemetry is achieved and the telemetry overhead can be reduced significantly compared with existing INT systems. INT-LLPP can control the system latency to get real-time network information.

Keywords: Network telemetry, network monitoring, path planning, low latency.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 253

Authors: Chisato Murakami, Makoto Takahashi

Abstract:

Force sensor has been used as requisite for knowing information on the amount and the directions of forces on the skin surface. We have developed a four-degrees-of-freedom capacitive force sensor (approximately 20×20×5 mm³) that has a flexible structure and sixteen parallel plate capacitors. An iterative algorithm was developed for estimating four displacements from the sixteen capacitances using fourth-order polynomial approximation of characteristics between capacitance and displacement. The estimation results from measured capacitances had large error caused by deterioration of the characteristics. In this study, effective capacitors had major information were selected on the basis of the capacitance change range and the characteristic shape. Maximum errors in calibration and non-calibration points were 25%and 6.8%.However the maximum error was larger than desired value, the smallness of averaged value indicated the occurrence of a few large error points. On the other hand, error in non-calibration point was within desired value.

 

Keywords: Force sensors, capacitive sensors, estimation, iterative algorithms.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1616

Authors: Nieves M. C. Talavera-Prieto, Abel G. M. Ferreira, António T. G. Portugal, Rui J. Moreira, Jaime B. Santos

Abstract:

The knowledge of biodiesel density over large ranges of temperature and pressure is important for predicting the behavior of fuel injection and combustion systems in diesel engines, and for the optimization of such systems. In this study, cottonseed oil was transesterified into biodiesel and its density was measured at temperatures between 288 K and 358 K and pressures between 0.1 MPa and 30 MPa, with expanded uncertainty estimated as ±1.6 kg⋅m- 3. Experimental pressure-volume-temperature (pVT) cottonseed data was used along with literature data relative to other 18 biodiesels, in order to build a database used to test the correlation of density with temperarure and pressure using the Goharshadi–Morsali–Abbaspour equation of state (GMA EoS). To our knowledge, this is the first that density measurements are presented for cottonseed biodiesel under such high pressures, and the GMA EoS used to model biodiesel density. The new tested EoS allowed correlations within 0.2 kg·m-3 corresponding to average relative deviations within 0.02%. The built database was used to develop and test a new full predictive model derived from the observed linear relation between density and degree of unsaturation (DU), which depended from biodiesel FAMEs profile. The average density deviation of this method was only about 3 kg.m-3 within the temperature and pressure limits of application. These results represent appreciable improvements in the context of density prediction at high pressure when compared with other equations of state.

Keywords: Biodiesel, Correlation, Density, Equation of state, Prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3511

Authors: Khalid A. Al-Afandy, El-Sayyed El-Rabaie, Osama Salah, Ahmed El-Mhalaway

Abstract:

This paper presents a high secure data hiding technique using image cropping and Least Significant Bit (LSB) steganography. The predefined certain secret coordinate crops will be extracted from the cover image. The secret text message will be divided into sections. These sections quantity is equal the image crops quantity. Each section from the secret text message will embed into an image crop with a secret sequence using LSB technique. The embedding is done using the cover image color channels. Stego image is given by reassembling the image and the stego crops. The results of the technique will be compared to the other state of art techniques. Evaluation is based on visualization to detect any degradation of stego image, the difficulty of extracting the embedded data by any unauthorized viewer, Peak Signal-to-Noise Ratio of stego image (PSNR), and the embedding algorithm CPU time. Experimental results ensure that the proposed technique is more secure compared with the other traditional techniques.

Keywords: Steganography, stego, LSB, crop.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1551

Authors: Achmad Nizar Hidayanto, Elisabeth Martha Koeanan

Abstract:

Image clustering is a process of grouping images based on their similarity. The image clustering usually uses the color component, texture, edge, shape, or mixture of two components, etc. This research aims to explore image clustering using color composition. In order to complete this image clustering, three main components should be considered, which are color space, image representation (feature extraction), and clustering method itself. We aim to explore which composition of these factors will produce the best clustering results by combining various techniques from the three components. The color spaces use RGB, HSV, and L*a*b* method. The image representations use Histogram and Gaussian Mixture Model (GMM), whereas the clustering methods use KMeans and Agglomerative Hierarchical Clustering algorithm. The results of the experiment show that GMM representation is better combined with RGB and L*a*b* color space, whereas Histogram is better combined with HSV. The experiments also show that K-Means is better than Agglomerative Hierarchical for images clustering.

Keywords: Image clustering, feature extraction, RGB, HSV, L*a*b*, Gaussian Mixture Model (GMM), histogram, Agglomerative Hierarchical Clustering (AHC), K-Means, Expectation-Maximization (EM).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2206

Authors: Abderrahmane El Kachani, El Mahjoub Chakir, Anass Ait Laachir, Abdelhamid Niaaniaa, Jamal Zerouaoui, Tarik Jarou

Abstract:

This paper presents a wind turbine based on the doubly fed induction generator (DFIG) connected to the utility grid through a shunt active power filter (SAPF). The whole system is controlled by a double nonlinear predictive controller (DNPC). A Taylor series expansion is used to predict the outputs of the system. The control law is calculated by optimization of the cost function. The first nonlinear predictive controller (NPC) is designed to ensure the high performance tracking of the rotor speed and regulate the rotor current of the DFIG, while the second one is designed to control the SAPF in order to compensate the harmonic produces by the three-phase diode bridge supplied by a passive circuit (rd, Ld). As a result, we obtain sinusoidal waveforms of the stator voltage and stator current. The proposed nonlinear predictive controllers (NPCs) are validated via simulation on a 1.5 MW DFIG-based wind turbine connected to an SAPF. The results obtained appear to be satisfactory and promising.

Keywords: Wind power, doubly fed induction generator, shunt active power filter, double nonlinear predictive controller.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 918

Authors: Oscar Javier Herrera Ochoa, Ivan Dario Romero Fonseca

Abstract:

This paper presents a design of a model for planning the distribution logistics operation. The significance of this work relies on the applicability of this fact to the analysis of small and medium enterprises (SMEs) of dry freight in Bogotá. Two stages constitute this implementation: the first one is the place where optimal planning is achieved through a hybrid model developed with mixed integer programming, which considers the transhipment operation based on a combined load allocation model as a classic transshipment model; the second one is the specific routing of that operation through the heuristics of Clark and Wright. As a result, an integral model is obtained to carry out the step by step planning of the distribution of dry freight for SMEs in Bogotá. In this manner, optimum assignments are established by utilizing transshipment centers with that purpose of determining the specific routing based on the shortest distance traveled.

Keywords: Transshipment model, mixed integer programming, saving algorithm, dry freight transportation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 913

Authors: Shuen-Tai Wang, Fang-An Kuo, Chau-Yi Chou, Yu-Bin Fang

Abstract:

2016 has become the year of the Artificial Intelligence explosion. AI technologies are getting more and more matured that most world well-known tech giants are making large investment to increase the capabilities in AI. Machine learning is the science of getting computers to act without being explicitly programmed, and deep learning is a subset of machine learning that uses deep neural network to train a machine to learn  features directly from data. Deep learning realizes many machine learning applications which expand the field of AI. At the present time, deep learning frameworks have been widely deployed on servers for deep learning applications in both academia and industry. In training deep neural networks, there are many standard processes or algorithms, but the performance of different frameworks might be different. In this paper we evaluate the running performance of two state-of-the-art distributed deep learning frameworks that are running training calculation in parallel over multi GPU and multi nodes in our cloud environment. We evaluate the training performance of the frameworks with ResNet-50 convolutional neural network, and we analyze what factors that result in the performance among both distributed frameworks as well. Through the experimental analysis, we identify the overheads which could be further optimized. The main contribution is that the evaluation results provide further optimization directions in both performance tuning and algorithmic design.

Keywords: Artificial Intelligence, machine learning, deep learning, convolutional neural networks.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1257

Authors: Mohsen Maadani, Seyed Ahmad Motamedi

Abstract:

The use of wireless technology in industrial networks has gained vast attraction in recent years. In this paper, we have thoroughly analyzed the effect of contention window (CW) size on the performance of IEEE 802.11-based industrial wireless networks (IWN), from delay and reliability perspective. Results show that the default values of CWmin, CWmax, and retry limit (RL) are far from the optimum performance due to the industrial application characteristics, including short packet and noisy environment. In this paper, an adaptive CW algorithm (payload-dependent) has been proposed to minimize the average delay. Finally a simple, but effective CW and RL setting has been proposed for industrial applications which outperforms the minimum-average-delay solution from maximum delay and jitter perspective, at the cost of a little higher average delay. Simulation results show an improvement of up to 20%, 25%, and 30% in average delay, maximum delay and jitter respectively.

Keywords: Average Delay, Contention Window, Distributed Coordination Function (DCF), Jitter, Industrial Wireless Network (IWN), Maximum Delay, Reliability, Retry Limit.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2035

Authors: Hao Liu, Lihui Zheng, Chinedu J. Okere, Chao Wang, Xiangchun Wang, Peng Zhang

Abstract:

The coalbed methane (CBM) extraction industry (an unconventional energy source) has not established guidelines for experimental evaluation of sensitivity damage for coal samples. The existing experimental process of previous researches mainly followed the industry standard for conventional oil and gas reservoirs (CIS). However, the existing evaluation method ignores certain critical differences between CBM reservoirs and conventional reservoirs, which could inevitably result in an inaccurate evaluation of sensitivity damage and, eventually, poor decisions regarding the formulation of formation damage prevention measures. In this study, we propose improved experimental guidelines for evaluating seepage sensitivity damage of CBM reservoirs by leveraging on the shortcomings of the existing methods. The proposed method was established via a theoretical analysis of the main drawbacks of the existing methods and validated through comparative experiments. The results show that the proposed evaluation technique provided reliable experimental results that can better reflect actual reservoir conditions and correctly guide the future development of CBM reservoirs. This study is pioneering the research on the optimization of experimental parameters for efficient exploration and development of CBM reservoirs.

Keywords: Coalbed methane, formation damage, permeability, unconventional energy source.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 385

Authors: Syed Munvar Ali, V. Vijaya Kumar Reddy, M. Surya Kalavathi

Abstract:

In this paper, a dual inverter configuration has been implemented for induction motor drive. This isolated dual inverter is capable to produce high quality of output voltage and minimize common mode voltage (CMV). To this isolated dual inverter a decoupled space vector based pulse width modulation (PWM) technique is proposed. Conventional space vector based PWM (SVPWM) techniques require reference voltage vector calculation and sector identification. The proposed decoupled SVPWM technique generates gating pulses from instantaneous phase voltages and gives a CMV of ±v_dc/6. To evaluate proposed algorithm MATLAB based simulation studies are carried on indirect vector controlled open end winding induction motor drive.

Keywords: Inverter configuration, decoupled SVPWM, common mode voltage, vector control.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 733

Authors: Sanaa Chafik, ImaneDaoudi, Mounim A. El Yacoubi, Hamid El Ouardi

Abstract:

Locality Sensitive Hashing (LSH) is one of the most promising techniques for solving nearest neighbour search problem in high dimensional space. Euclidean LSH is the most popular variation of LSH that has been successfully applied in many multimedia applications. However, the Euclidean LSH presents limitations that affect structure and query performances. The main limitation of the Euclidean LSH is the large memory consumption. In order to achieve a good accuracy, a large number of hash tables is required. In this paper, we propose a new hashing algorithm to overcome the storage space problem and improve query time, while keeping a good accuracy as similar to that achieved by the original Euclidean LSH. The Experimental results on a real large-scale dataset show that the proposed approach achieves good performances and consumes less memory than the Euclidean LSH.

Keywords: Approximate Nearest Neighbor Search, Content based image retrieval (CBIR), Curse of dimensionality, Locality sensitive hashing, Multidimensional indexing, Scalability.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2577

Authors: Desmond B. Keenan, Paul Grossman

Abstract:

In order to provide accurate heart rate variability indices of sympathetic and parasympathetic activity, the low frequency and high frequency components of an RR heart rate signal must be adequately separated. This is not always possible by just applying spectral analysis, as power from the high and low frequency components often leak into their adjacent bands. Furthermore, without the respiratory spectra it is not obvious that the low frequency component is not another respiratory component, which can appear in the lower band. This paper describes an adaptive filter, which aids the separation of the low frequency sympathetic and high frequency parasympathetic components from an ECG R-R interval signal, enabling the attainment of more accurate heart rate variability measures. The algorithm is applied to simulated signals and heart rate and respiratory signals acquired from an ambulatory monitor incorporating single lead ECG and inductive plethysmography sensors embedded in a garment. The results show an improvement over standard heart rate variability spectral measurements.

Keywords: Heart rate variability, vagal tone, sympathetic, parasympathetic, spectral analysis, adaptive filter.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1754

Authors: Ratul Das

Abstract:

The present experimental study insights the decontamination of instantaneous velocity fluctuations captured by Acoustic Doppler Velocimeter (ADV) in gravel-bed streams to ascertain near-bed turbulence for low Reynolds number. The interference between incidental and reflected pulses produce spikes in the ADV data especially in the near-bed flow zone and therefore filtering the data are very essential. Nortek’s Vectrino four-receiver ADV probe was used to capture the instantaneous three-dimensional velocity fluctuations over a non-cohesive bed. A spike removal algorithm based on the acceleration threshold method was applied to note the bed roughness and its influence on velocity fluctuations and velocity power spectra in the carrier fluid. The velocity power spectra of despiked signals with a best combination of velocity threshold (VT) and acceleration threshold (AT) are proposed which ascertained velocity power spectra a satisfactory fit with the Kolmogorov “–5/3 scaling-law” in the inertial sub-range. Also, velocity distributions below the roughness crest level fairly follows a third-degree polynomial series.

Keywords: Acoustic Doppler Velocimeter, gravel-bed, spike removal, Reynolds shear stress, near-bed turbulence, velocity power spectra.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1179

Authors: Jieun Kim, Yongtae Park, Hakyeon Lee

Abstract:

The emergence of mobile application services and App Store has led to the explosive growth of user innovation, which users voluntarily contribute to. User innovation communities where end users freely reveal innovative ideas and needs with other community members are becoming increasingly influential in this area. However, user-s ideas in user innovation community are not enough to be new service opportunity, because some of them can already developed as existing services in App Store. Moreover, the existing services similar to new service opportunity can be significant references to apply analogy to develop service concept. In response, this research proposes Case-Based Reasoning approach to matching the user needs and existing services, identifying unmet opportunistic user needs, and retrieving similar services with opportunity. Due to its intuitive and transparent algorithm, users related to App Store innovation communities can easily employ Case-Based Reasoning based approach to their innovation.

Keywords: App Store, Case-Based Reasoning, Mobile Application Service, User innovation community.

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