Search results for: Utility Function

Authors: M. Mansouri, P. Jaklitsch, E. Teiniker

Abstract:

SQL injection on web applications is a very popular kind of attack. There are mechanisms such as intrusion detection systems in order to detect this attack. These strategies often rely on techniques implemented at high layers of the application but do not consider the low level of system calls. The problem of only considering the high level perspective is that an attacker can circumvent the detection tools using certain techniques such as URL encoding. One technique currently used for detecting low-level attacks on privileged processes is the tracing of system calls. System calls act as a single gate to the Operating System (OS) kernel; they allow catching the critical data at an appropriate level of detail. Our basic assumption is that any type of application, be it a system service, utility program or Web application, “speaks” the language of system calls when having a conversation with the OS kernel. At this level we can see the actual attack while it is happening. We conduct an experiment in order to demonstrate the suitability of system call analysis for detecting SQL injection. We are able to detect the attack. Therefore we conclude that system calls are not only powerful in detecting low-level attacks but that they also enable us to detect highlevel attacks such as SQL injection.

Keywords: Linux system calls, Web attack detection, Interception.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1982

Authors: N. M. Nawi, M. R. Ransing, R. S. Ransing

Abstract:

The conjugate gradient optimization algorithm usually used for nonlinear least squares is presented and is combined with the modified back propagation algorithm yielding a new fast training multilayer perceptron (MLP) algorithm (CGFR/AG). The approaches presented in the paper consist of three steps: (1) Modification on standard back propagation algorithm by introducing gain variation term of the activation function, (2) Calculating the gradient descent on error with respect to the weights and gains values and (3) the determination of the new search direction by exploiting the information calculated by gradient descent in step (2) as well as the previous search direction. The proposed method improved the training efficiency of back propagation algorithm by adaptively modifying the initial search direction. Performance of the proposed method is demonstrated by comparing to the conjugate gradient algorithm from neural network toolbox for the chosen benchmark. The results show that the number of iterations required by the proposed method to converge is less than 20% of what is required by the standard conjugate gradient and neural network toolbox algorithm.

Keywords: Back-propagation, activation function, conjugategradient, search direction, gain variation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2812

Authors: Mikhail Vladimirovich Deryabin, Morten Willatzen

Abstract:

In this work, we address theoretically the influence of red and white Gaussian noise for electronic energies and eigenstates of cylindrically shaped quantum dots. The stochastic effect can be imagined as resulting from crystal-growth statistical fluctuations in the quantum-dot material composition. In particular we obtain analytical expressions for the eigenvalue shifts and electronic envelope functions in the k . p formalism due to stochastic variations in the confining band-edge potential. It is shown that white noise in the band-edge potential leaves electronic properties almost unaffected while red noise may lead to changes in state energies and envelopefunction amplitudes of several percentages. In the latter case, the ensemble-averaged envelope function decays as a function of distance. It is also shown that, in a stochastic system, constant ensembleaveraged envelope functions are the only bounded solutions for the infinite quantum-wire problem and the energy spectrum is completely discrete. In other words, the infinite stochastic quantum wire behaves, ensemble-averaged, as an atom.

Keywords: cylindrical quantum dots, electronic eigen energies, red and white Gaussian noise, ensemble averaging effects.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1509

Authors: Billel Kenidra, Mohamed Benmohammed

Abstract:

Data mining technique used in the field of clustering is a subject of active research and assists in biological pattern recognition and extraction of new knowledge from raw data. Clustering means the act of partitioning an unlabeled dataset into groups of similar objects. Each group, called a cluster, consists of objects that are similar between themselves and dissimilar to objects of other groups. Several clustering methods are based on partitional clustering. This category attempts to directly decompose the dataset into a set of disjoint clusters leading to an integer number of clusters that optimizes a given criterion function. The criterion function may emphasize a local or a global structure of the data, and its optimization is an iterative relocation procedure. The K-Means algorithm is one of the most widely used partitional clustering techniques. Since K-Means is extremely sensitive to the initial choice of centers and a poor choice of centers may lead to a local optimum that is quite inferior to the global optimum, we propose a strategy to initiate K-Means centers. The improved K-Means algorithm is compared with the original K-Means, and the results prove how the efficiency has been significantly improved.

Keywords: Microarray data mining, biological pattern recognition, partitional clustering, k-means algorithm, centroid initialization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1256

Authors: Padmanabhan Balasubramanian, C. Ardil

Abstract:

An effective approach for realizing the binary tree structure, representing a combinational logic functionality with enhanced throughput, is discussed in this paper. The optimization in maximum operating frequency was achieved through delay minimization, which in turn was possible by means of reducing the depth of the binary network. The proposed synthesis methodology has been validated by experimentation with FPGA as the target technology. Though our proposal is technology independent, yet the heuristic enables better optimization in throughput even after technology mapping for such Boolean functionality; whose reduced CNF form is associated with a lesser literal cost than its reduced DNF form at the Boolean equation level. For cases otherwise, our method converges to similar results as that of [12]. The practical results obtained for a variety of case studies demonstrate an improvement in the maximum throughput rate for Spartan IIE (XC2S50E-7FT256) and Spartan 3 (XC3S50-4PQ144) FPGA logic families by 10.49% and 13.68% respectively. With respect to the LUTs and IOBUFs required for physical implementation of the requisite non-regenerative logic functionality, the proposed method enabled savings to the tune of 44.35% and 44.67% respectively, over the existing efficient method available in literature [12].

Keywords: Binary logic tree, FPGA based design, Boolean function, Throughput rate, CNF, DNF.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1890

Authors: Siddhartha Bhattacharyya, Paramartha Dutta, Ujjwal Maulik, Prashanta Kumar Nandi

Abstract:

The paper describes a self supervised parallel self organizing neural network (PSONN) architecture for true color image segmentation. The proposed architecture is a parallel extension of the standard single self organizing neural network architecture (SONN) and comprises an input (source) layer of image information, three single self organizing neural network architectures for segmentation of the different primary color components in a color image scene and one final output (sink) layer for fusion of the segmented color component images. Responses to the different shades of color components are induced in each of the three single network architectures (meant for component level processing) by applying a multilevel version of the characteristic activation function, which maps the input color information into different shades of color components, thereby yielding a processed component color image segmented on the basis of the different shades of component colors. The number of target classes in the segmented image corresponds to the number of levels in the multilevel activation function. Since the multilevel version of the activation function exhibits several subnormal responses to the input color image scene information, the system errors of the three component network architectures are computed from some subnormal linear index of fuzziness of the component color image scenes at the individual level. Several multilevel activation functions are employed for segmentation of the input color image scene using the proposed network architecture. Results of the application of the multilevel activation functions to the PSONN architecture are reported on three real life true color images. The results are substantiated empirically with the correlation coefficients between the segmented images and the original images.

Keywords: Colour image segmentation, fuzzy set theory, multi-level activation functions, parallel self-organizing neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2004

Authors: Yuko Hiramatsu, Fumihiro Sato, Atsushi Ito, Hiroyuki Hatano, Mie Sato, Yu Watanabe, Akira Sasaki

Abstract:

This paper presents a mobile phone application developed for sightseeing in Nikko, one of the cultural world heritages in Japan, using the BLE (Bluetooth Low Energy) beacon. Based on our pre-research, we decided to design our application for young people who walk around the area actively, but know little about the tradition and culture of Nikko. One solution is to construct many information boards to explain; however, it is difficult to construct new guide plates in cultural world heritage sites. The smartphone is a good solution to send such information to such visitors. This application was designed using a combination of the smartphone and beacons, set in the area, so that when a tourist passes near a beacon, the application displays information about the area including a map, historical or cultural information about the temples and shrines, and local shops nearby as well as a bus timetable. It is useful for foreigners, too. In addition, we developed quizzes relating to the culture and tradition of Nikko to provide information based on the Zeigarnik effect, a psychological effect. According to the results of our trials, tourists positively evaluated the basic information and young people who used the quiz function were able to learn the historical and cultural points. This application helped young visitors at Nikko to understand the cultural elements of the site. In addition, this application has a function to send notifications. This function is designed to provide information about the local community such as shops, local transportation companies and information office. The application hopes to also encourage people living in the area, and such cooperation from the local people will make this application vivid and inspire young visitors to feel that the cultural heritage site is still alive today. This is a gateway for young people to learn about a traditional place and understand the gravity of preserving such areas.

Keywords: BLE beacon, smartphone application, Zeigarnik effect, world heritage site, school trip.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1928

Authors: Ejaz Khan, Conor Heneghan

Abstract:

In this paper we propose a new criterion for solving the problem of channel shortening in multi-carrier systems. In a discrete multitone receiver, a time-domain equalizer (TEQ) reduces intersymbol interference (ISI) by shortening the effective duration of the channel impulse response. Minimum mean square error (MMSE) method for TEQ does not give satisfactory results. In [1] a new criterion for partially equalizing severe ISI channels to reduce the cyclic prefix overhead of the discrete multitone transceiver (DMT), assuming a fixed transmission bandwidth, is introduced. Due to specific constrained (unit morm constraint on the target impulse response (TIR)) in their method, the freedom to choose optimum vector (TIR) is reduced. Better results can be obtained by avoiding the unit norm constraint on the target impulse response (TIR). In this paper we change the cost function proposed in [1] to the cost function of determining the maximum of a determinant subject to linear matrix inequality (LMI) and quadratic constraint and solve the resulting optimization problem. Usefulness of the proposed method is shown with the help of simulations.

Keywords: Equalizer, target impulse response, convex optimization, matrix inequality.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1681

Authors: Sanjay Kumar Srivastava, Anu Rani Sharma, Kamna Sachdeva

Abstract:

The aim of the paper is to analyze the characteristics of winter fog in terms of its trend and spatial-temporal variability over Indo-Gangetic plains. The study reveals that during last four and half decades (1971-2015), an alarming increasing trend in fog frequency has been observed during the winter months of December and January over the study area. The frequency of fog has increased by 118.4% during the peak winter months of December and January. It has also been observed that on an average central part of IGP has 66.29% fog days followed by west IGP with 41.94% fog days. Further, Empirical Orthogonal Function (EOF) decomposition and Mann-Kendall variation analysis are used to analyze the spatial and temporal patterns of winter fog. The findings have significant implications for the further research of fog over IGP and formulate robust strategies to adapt the fog variability and mitigate its effects. The decision by Delhi Government to implement odd-even scheme to restrict the use of private vehicles in order to reduce pollution and improve quality of air may result in increasing the alarming increasing trend of fog over Delhi and its surrounding areas regions of IGP.

Keywords: Fog, climatology, spatial variability, temporal variability, empirical orthogonal function, visibility, Mann-Kendall test, variation point.

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

Authors: Ammar M. Hassan, Ayoub Al-Hamadi, Yassin M. Y. Hasan, Mohamed A. A. Wahab, Bernd Michaelis

Abstract:

Because of the great advance in multimedia technology, digital multimedia is vulnerable to malicious manipulations. In this paper, a public key self-recovery block-based video authentication technique is proposed which can not only precisely localize the alteration detection but also recover the missing data with high reliability. In the proposed block-based technique, multiple description coding MDC is used to generate two codes (two descriptions) for each block. Although one block code (one description) is enough to rebuild the altered block, the altered block is rebuilt with better quality by the two block descriptions. So using MDC increases the ratability of recovering data. A block signature is computed using a cryptographic hash function and a doubly linked chain is utilized to embed the block signature copies and the block descriptions into the LSBs of distant blocks and the block itself. The doubly linked chain scheme gives the proposed technique the capability to thwart vector quantization attacks. In our proposed technique , anyone can check the authenticity of a given video using the public key. The experimental results show that the proposed technique is reliable for detecting, localizing and recovering the alterations.

Keywords: Authentication, hash function, multiple descriptioncoding, public key encryption, watermarking.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1911

Authors: Narottam Chand

Abstract:

Wireless sensor networks (WSNs) consist of number of tiny, low cost and low power sensor nodes to monitor some physical phenomenon. The major limitation in these networks is the use of non-rechargeable battery having limited power supply. The main cause of energy consumption in such networks is communication subsystem. This paper presents an energy efficient Cluster Cooperative Caching at Sensor (C3S) based upon grid type clustering. Sensor nodes belonging to the same cluster/grid form a cooperative cache system for the node since the cost for communication with them is low both in terms of energy consumption and message exchanges. The proposed scheme uses cache admission control and utility based data replacement policy to ensure that more useful data is retained in the local cache of a node. Simulation results demonstrate that C3S scheme performs better in various performance metrics than NICoCa which is existing cooperative caching protocol for WSNs.

Keywords: Cooperative caching, cache replacement, admission control, WSN, clustering.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2247

Authors: Parvinder S. Sandhu, Urvashi Malhotra, E. Ardil

Abstract:

There is lot of work done in prediction of the fault proneness of the software systems. But, it is the severity of the faults that is more important than number of faults existing in the developed system as the major faults matters most for a developer and those major faults needs immediate attention. In this paper, we tried to predict the level of impact of the existing faults in software systems. Neuro-Fuzzy based predictor models is applied NASA-s public domain defect dataset coded in C programming language. As Correlation-based Feature Selection (CFS) evaluates the worth of a subset of attributes by considering the individual predictive ability of each feature along with the degree of redundancy between them. So, CFS is used for the selecting the best metrics that have highly correlated with level of severity of faults. The results are compared with the prediction results of Logistic Models (LMT) that was earlier quoted as the best technique in [17]. The results are recorded in terms of Accuracy, Mean Absolute Error (MAE) and Root Mean Squared Error (RMSE). The results show that Neuro-fuzzy based model provide a relatively better prediction accuracy as compared to other models and hence, can be used for the modeling of the level of impact of faults in function based systems.

Keywords: Software Metrics, Fuzzy, Neuro-Fuzzy, Software Faults, Accuracy, MAE, RMSE.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1342

Authors: Mohammad Syuhaimi Ab-Rahman, Mohd. Saiful Dzulkefly Zan, Mohd Taufiq Mohd Yusof

Abstract:

With the drastically growth in optical communication technology, a lossless, low-crosstalk and multifunction optical switch is most desirable for large-scale photonic network. To realize such a switch, we have introduced the new architecture of optical switch that embedded many functions on single device. The asymmetrical architecture of OXADM consists of 3 parts; selective port, add/drop operation, and path routing. Selective port permits only the interest wavelength pass through and acts as a filter. While add and drop function can be implemented in second part of OXADM architecture. The signals can then be re-routed to any output port or/and perform an accumulation function which multiplex all signals onto single path and then exit to any interest output port. This will be done by path routing operation. The unique features offered by OXADM has extended its application to Fiber to-the Home Technology (FTTH), here the OXADM is used as a wavelength management element in Optical Line Terminal (OLT). Each port is assigned specifically with the operating wavelengths and with the dynamic routing management to ensure no traffic combustion occurs in OLT.

Keywords: OXADM, asymmetrical architecture, optical switch, OLT, FTTH.

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

Authors: V. Agrawal, A. Sharma

Abstract:

High Strength Concrete (HSC) is defined as concrete that meets special combination of performance and uniformity requirements that cannot be achieved routinely using conventional constituents and normal mixing, placing, and curing procedures. It is a highly complex material, which makes modeling its behavior a very difficult task. This paper aimed to show possible applicability of Neural Networks (NN) to predict the slump in High Strength Concrete (HSC). Neural Network models is constructed, trained and tested using the available test data of 349 different concrete mix designs of High Strength Concrete (HSC) gathered from a particular Ready Mix Concrete (RMC) batching plant. The most versatile Neural Network model is selected to predict the slump in concrete. The data used in the Neural Network models are arranged in a format of eight input parameters that cover the Cement, Fly Ash, Sand, Coarse Aggregate (10 mm), Coarse Aggregate (20 mm), Water, Super-Plasticizer and Water/Binder ratio. Furthermore, to test the accuracy for predicting slump in concrete, the final selected model is further used to test the data of 40 different concrete mix designs of High Strength Concrete (HSC) taken from the other batching plant. The results are compared on the basis of error function (or performance function).

Keywords: Artificial Neural Networks, Concrete, prediction ofslump, slump in concrete

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3569

Authors: N.Subramanian, U.K.Misra

Abstract:

The aim of this paper is to introduce and study a new concept of strong double χ2 (M,A, Δ) of fuzzy numbers and also some properties of the resulting sequence spaces of fuzzy numbers were examined.

Keywords: Modulus function, fuzzy number, metric space.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2272

Authors: T. Ganesan, M. S. Aris, I. Elamvazuthi, Momen Kamal Tageldeen

Abstract:

Terms set in power purchase agreements (PPA) challenge power utility companies in balancing between the returns (from maximizing power production) and securing long term supply contracts at capped production. The production limitation set in the PPA has driven efforts to maximize profits through efficient and economic power production. In this paper, a combined industrial-scale gas turbine (GT) - absorption chiller (AC) system is considered to cool the GT air intake for reducing the plant’s heat rate (HR). This GT-AC system is optimized while considering power output limitations imposed by the PPA. In addition, the proposed formulation accounts for uncertainties in the ambient temperature using Type-2 fuzzy programming. Using the enhanced chaotic differential evolution (CEDE), the Pareto frontier was constructed and the optimization results are analyzed in detail.

Keywords: Absorption chillers, turbine inlet air cooling, power purchase agreement, multiobjective optimization, type-2 fuzzy programming, chaotic differential evolution.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 910

Authors: R. Govender, D. Naidoo, E. M. Buys

Abstract:

The importance of ensuring safe meat handling and processing practices has been demonstrated in global reports on food safety scares and related illness and deaths. This necessitated stricter meat safety control strategies. Today, many countries have regulated towards preventative and systematic control over safe meat processing at abattoirs utilizing the Hazard Analysis Critical Control Point (HACCP) principles. HACCP systems have been reported as effective in managing food safety risks, if correctly implemented. South Africa has regulated the Hygiene Management System (HMS) based on HACCP principles applicable to abattoirs. Regulators utilise the Hygiene Assessment System (HAS) to audit compliance at abattoirs. These systems were benchmarked from the United Kingdom (UK). Little research has been done them since inception as of 2004. This paper presents a review of the two systems, its implementation and comparison with HACCP. Recommendations are made for future research to demonstrate the utility of the HMS and HAS in assuring safe meat to consumers.

Keywords: Abattoir, co-regulation, food safety, HACCP, meat hygiene.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 6951

Authors: M. Zarei, A. Roozegar, R. Kazemzadeh, J.M. Kauffmann

Abstract:

This paper describes an efficient and practical method for economic dispatch problem in one and two area electrical power systems with considering the constraint of the tie transmission line capacity constraint. Direct search method (DSM) is used with some equality and inequality constraints of the production units with any kind of fuel cost function. By this method, it is possible to use several inequality constraints without having difficulty for complex cost functions or in the case of unavailability of the cost function derivative. To minimize the number of total iterations in searching, process multi-level convergence is incorporated in the DSM. Enhanced direct search method (EDSM) for two area power system will be investigated. The initial calculation step size that causes less iterations and then less calculation time is presented. Effect of the transmission tie line capacity, between areas, on economic dispatch problem and on total generation cost will be studied; line compensation and active power with reactive power dispatch are proposed to overcome the high generation costs for this multi-area system.

Keywords: Economic dispatch, Power System Operation, Direct Search Method, Transmission Capacity Constraint.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2457

Authors: Pedro Pablo Ramírez Sánchez, Alassane Ballé Ndiaye, Roberto Rendeiro Martín-Cejas

Abstract:

The aim of this paper is to analyse the different environmental policies adopted in Europe for car emissions, to comment on some of the possible perverse effects generated and point out these policies which are considered more efficient under the environmental perspective. This paper is focused on passenger cars as this category is the most significant in road transport. The utility of this research lies in this being the first step or basis to improve and optimise actual policies. The methodology applied in this paper refers to a comparative analysis from a practical and theoretical point of view of European environmental policies in road transport. This work describes an overview of the road transport industry in Europe pointing out some relevant aspects such as the contribution of road transport to total emissions and the vehicle fleet in Europe. Additionally, we propose a brief practice guide with the combined policies in order to optimise their aim.

Keywords: Air quality, climate change, emission, environment, perverse effect, road transport, tax policy.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 847

Authors: Shashank.B. Thakre, L.B. Bhuyar, Samir.J. Deshmukh

Abstract:

The value of overall oxygen transfer Coefficient (KLa), which is the best measure of oxygen transfer in water through aeration, is obtained by a simple approach, which sufficiently explains the utility of the method to eliminate the discrepancies due to inaccurate assumption of saturation dissolved oxygen concentration. The rate of oxygen transfer depends on number of factors like intensity of turbulence, which in turns depends on the speed of rotation, size, and number of blades, diameter and immersion depth of the rotor, and size and shape of aeration tank, as well as on physical, chemical, and biological characteristic of water. An attempt is made in this paper to correlate the overall oxygen transfer Coefficient (KLa), as an independent parameter with other influencing parameters mentioned above. It has been estimated that the simulation equation developed predicts the values of KLa and power with an average standard error of estimation of 0.0164 and 7.66 respectively and with R2 values of 0.979 and 0.989 respectively, when compared with experimentally determined values. The comparison of this model is done with the model generated using Computational fluid dynamics (CFD) and both the models were found to be in good agreement with each other.

Keywords: CFD Model, Overall oxygen transfer coefficient, Power, Mathematical Model, Validation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1735

Authors: Karim Hamidi Machekposhti, Hossein Sedghi

Abstract:

This study was designed to find the best stochastic model (using of time series analysis) for annual extreme streamflow (peak and maximum streamflow) of Karkheh River at Iran. The Auto-regressive Integrated Moving Average (ARIMA) model used to simulate these series and forecast those in future. For the analysis, annual extreme streamflow data of Jelogir Majin station (above of Karkheh dam reservoir) for the years 1958–2005 were used. A visual inspection of the time plot gives a little increasing trend; therefore, series is not stationary. The stationarity observed in Auto-Correlation Function (ACF) and Partial Auto-Correlation Function (PACF) plots of annual extreme streamflow was removed using first order differencing (d=1) in order to the development of the ARIMA model. Interestingly, the ARIMA(4,1,1) model developed was found to be most suitable for simulating annual extreme streamflow for Karkheh River. The model was found to be appropriate to forecast ten years of annual extreme streamflow and assist decision makers to establish priorities for water demand. The Statistical Analysis System (SAS) and Statistical Package for the Social Sciences (SPSS) codes were used to determinate of the best model for this series.

Keywords: Stochastic models, ARIMA, extreme streamflow, Karkheh River.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 694

Authors: Apoorva Vinod, Archana Mathur, Snehanshu Saha

Abstract:

Though there exists a plethora of Activation Functions (AFs) used in single and multiple hidden layer Neural Networks (NN), their behavior always raised curiosity, whether used in combination or singly. The popular AFs – Sigmoid, ReLU, and Tanh – have performed prominently well for shallow and deep architectures. Most of the time, AFs are used singly in multi-layered NN, and, to the best of our knowledge, their performance is never studied and analyzed deeply when used in combination. In this manuscript, we experiment on multi-layered NN architecture (both on shallow and deep architectures; Convolutional NN and VGG16) and investigate how well the network responds to using two different AFs (Sigmoid-Tanh, Tanh-ReLU, ReLU-Sigmoid) used alternately against a traditional, single (Sigmoid-Sigmoid, Tanh-Tanh, ReLU-ReLU) combination. Our results show that on using two different AFs, the network achieves better accuracy, substantially lower loss, and faster convergence on 4 computer vision (CV) and 15 Non-CV (NCV) datasets. When using different AFs, not only was the accuracy greater by 6-7%, but we also accomplished convergence twice as fast. We present a case study to investigate the probability of networks suffering vanishing and exploding gradients when using two different AFs. Additionally, we theoretically showed that a composition of two or more AFs satisfies Universal Approximation Theorem (UAT).

Keywords: Activation Function, Universal Approximation function, Neural Networks, convergence.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 120

Authors: Martin J.-D. Otis, Thien-Ly Nguyen-Dang, Thierry Laliberte, Denis Ouellet, Denis Laurendeau, Clement Gosselin

Abstract:

A Cable-Driven Locomotion Interface provides a low inertia haptic interface and is used as a way of enabling the user to walk and interact with virtual surfaces. These surfaces generate Cartesian wrenches which must be optimized for each motorized reel in order to reproduce a haptic sensation in both feet. However, the use of wrench control requires a measure of the cable tensions applied to the moving platform. The latter measure may be inaccurate if it is based on sensors located near the reel. Moreover, friction hysteresis from the reel moving parts needs to be compensated for with an evaluation of low angular velocity of the motor shaft. Also, the pose of the platform is not known precisely due to cable sagging and mechanical deformation. This paper presents a non-ideal motorized reel design with its corresponding control strategy that aims at overcoming the aforementioned issues. A transfert function of the reel based on frequency responses in function of cable tension and cable length is presented with an optimal adaptative PIDF controller. Finally, an hybrid position/tension control is discussed with an analysis of the stability for achieving a complete functionnality of the haptic platform.

Keywords: haptic, reel, transparency, cable, tension, control

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1825

Authors: Radim Cajka, Pavlina Mateckova, Martina Janulikova, Marie Stara

Abstract:

Use of a sliding joint is an effective method to decrease the stress in foundation structure where there is a horizontal deformation of subsoil (areas afflicted with underground mining) or horizontal deformation of a foundation structure (pre-stressed foundations, creep, shrinkage, temperature deformation). A convenient material for a sliding joint is a bitumen asphalt belt. Experiments for different types of bitumen belts were undertaken at the Faculty of Civil Engineering - VSB Technical University of Ostrava in 2008. This year an extension of the 2008 experiments is in progress and the shear resistance of a slide joint is being tested as a function of temperature in a temperature controlled room. In this paper experimental results of temperature dependant shear resistance are presented. The result of the experiments should be the sliding joint shear resistance as a function of deformation velocity and temperature. This relationship is used for numerical analysis of stress/strain relation between foundation structure and subsoil. Using a rheological slide joint could lead to a decrease of the reinforcement amount, and contribute to higher reliability of foundation structure and thus enable design of more durable and sustainable building structures.

Keywords: Pre-stressed foundations, sliding joint, soil-structure interaction, subsoil horizontal deformation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1992

Authors: A. Leelasantitham, B. Srisuchinwong

Abstract:

A high-frequency low-power sinusoidal quadrature oscillator is presented through the use of two 2nd-order low-pass current-mirror (CM)-based filters, a 1st-order CM low-pass filter and a CM bilinear transfer function. The technique is relatively simple based on (i) inherent time constants of current mirrors, i.e. the internal capacitances and the transconductance of a diode-connected NMOS, (ii) a simple negative resistance RN formed by a resistor load RL of a current mirror. Neither external capacitances nor inductances are required. As a particular example, a 1.9-GHz, 0.45-mW, 2-V CMOS low-pass-filter-based all-current-mirror sinusoidal quadrature oscillator is demonstrated. The oscillation frequency (f0) is 1.9 GHz and is current-tunable over a range of 370 MHz or 21.6 %. The power consumption is at approximately 0.45 mW. The amplitude matching and the quadrature phase matching are better than 0.05 dB and 0.15°, respectively. Total harmonic distortions (THD) are less than 0.3 %. At 2 MHz offset from the 1.9 GHz, the carrier to noise ratio (CNR) is 90.01 dBc/Hz whilst the figure of merit called a normalized carrier-to-noise ratio (CNRnorm) is 153.03 dBc/Hz. The ratio of the oscillation frequency (f0) to the unity-gain frequency (fT) of a transistor is 0.25. Comparisons to other approaches are also included.

Keywords: Sinusoidal quadrature oscillator, low-pass-filterbased, current-mirror bilinear transfer function, all-current-mirror, negative resistance, low power, high frequency, low distortion.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2051

Authors: Masamitsu Chikaraishi, Mutsuto Kawahara

Abstract:

This paper focuses on a technique for identifying the geological boundary of the ground strata in front of a tunnel excavation site using the first order adjoint method based on the optimal control theory. The geological boundary is defined as the boundary which is different layers of elastic modulus. At tunnel excavations, it is important to presume the ground situation ahead of the cutting face beforehand. Excavating into weak strata or fault fracture zones may cause extension of the construction work and human suffering. A theory for determining the geological boundary of the ground in a numerical manner is investigated, employing excavating blasts and its vibration waves as the observation references. According to the optimal control theory, the performance function described by the square sum of the residuals between computed and observed velocities is minimized. The boundary layer is determined by minimizing the performance function. The elastic analysis governed by the Navier equation is carried out, assuming the ground as an elastic body with linear viscous damping. To identify the boundary, the gradient of the performance function with respect to the geological boundary can be calculated using the adjoint equation. The weighed gradient method is effectively applied to the minimization algorithm. To solve the governing and adjoint equations, the Galerkin finite element method and the average acceleration method are employed for the spatial and temporal discretizations, respectively. Based on the method presented in this paper, the different boundary of three strata can be identified. For the numerical studies, the Suemune tunnel excavation site is employed. At first, the blasting force is identified in order to perform the accuracy improvement of analysis. We identify the geological boundary after the estimation of blasting force. With this identification procedure, the numerical analysis results which almost correspond with the observation data were provided.

Keywords: Parameter identification, finite element method, average acceleration method, first order adjoint equation method, weighted gradient method, geological boundary, navier equation, optimal control theory.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1565

Authors: Lily Ingsrisawang, Tasanee Nacharoen

Abstract:

The problems arising from unbalanced data sets generally appear in real world applications. Due to unequal class distribution, many researchers have found that the performance of existing classifiers tends to be biased towards the majority class. The k-nearest neighbors’ nonparametric discriminant analysis is a method that was proposed for classifying unbalanced classes with good performance. In this study, the methods of discriminant analysis are of interest in investigating misclassification error rates for classimbalanced data of three diabetes risk groups. The purpose of this study was to compare the classification performance between parametric discriminant analysis and nonparametric discriminant analysis in a three-class classification of class-imbalanced data of diabetes risk groups. Data from a project maintaining healthy conditions for 599 employees of a government hospital in Bangkok were obtained for the classification problem. The employees were divided into three diabetes risk groups: non-risk (90%), risk (5%), and diabetic (5%). The original data including the variables of diabetes risk group, age, gender, blood glucose, and BMI were analyzed and bootstrapped for 50 and 100 samples, 599 observations per sample, for additional estimation of the misclassification error rate. Each data set was explored for the departure of multivariate normality and the equality of covariance matrices of the three risk groups. Both the original data and the bootstrap samples showed nonnormality and unequal covariance matrices. The parametric linear discriminant function, quadratic discriminant function, and the nonparametric k-nearest neighbors’ discriminant function were performed over 50 and 100 bootstrap samples and applied to the original data. Searching the optimal classification rule, the choices of prior probabilities were set up for both equal proportions (0.33: 0.33: 0.33) and unequal proportions of (0.90:0.05:0.05), (0.80: 0.10: 0.10) and (0.70, 0.15, 0.15). The results from 50 and 100 bootstrap samples indicated that the k-nearest neighbors approach when k=3 or k=4 and the defined prior probabilities of non-risk: risk: diabetic as 0.90: 0.05:0.05 or 0.80:0.10:0.10 gave the smallest error rate of misclassification. The k-nearest neighbors approach would be suggested for classifying a three-class-imbalanced data of diabetes risk groups.

Keywords: Bootstrap, diabetes risk groups, error rate, k-nearest neighbors.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1986

Authors: Amin Aghatabar Roodbary, Mohammad Hassan Bastani

Abstract:

One of the defects of stepped frequency radar systems is their sensitivity to target motion. In such systems, target motion causes range cell shift, false peaks, Signal to Noise Ratio (SNR) reduction and range profile spreading because of power spectrum interference of each range cell in adjacent range cells which induces distortion in High Resolution Range Profile (HRRP) and disrupt target recognition process. Thus Target Motion Parameters (TMPs) effects compensation should be employed. In this paper, such a method for estimating TMPs (velocity and acceleration) and consequently eliminating or suppressing the unwanted effects on HRRP based on entropy minimization has been proposed. This method is carried out in two major steps: in the first step, a discrete search method has been utilized over the whole acceleration-velocity lattice network, in a specific interval seeking to find a less-accurate minimum point of the entropy function. Then in the second step, a 1-D search over velocity is done in locus of the minimum for several constant acceleration lines, in order to enhance the accuracy of the minimum point found in the first step. The provided simulation results demonstrate the effectiveness of the proposed method.

Keywords: ATR, HRRP, motion compensation, SFW, TMP.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 622

Authors: C. Ardil

Abstract:

Aircraft selection decisions can be challenging due to their multidimensional and interdisciplinary nature. They involve multiple stakeholders with conflicting objectives and numerous alternative options with uncertain outcomes. This study focuses on the analysis of aerial firefighting aircraft that can be chosen for the Air Fire Service to extinguish forest fires. To make such a selection, the characteristics of the fire zones must be considered, and the capability to manage the logistics involved in such operations, as well as the purchase and maintenance of the aircraft, must be determined. The selection of firefighting aircraft is particularly complex because they have longer fleet lives and require more demanding operation and maintenance than scheduled passenger air service. This paper aims to use the fuzzy proximity measure method to select the most appropriate aerial firefighting aircraft based on decision criteria using multiple attribute decision making analysis. Following fuzzy decision analysis, the most suitable aerial firefighting aircraft is ranked and determined for the Air Fire Service.

Keywords: Aerial firefighting aircraft selection, multiple criteria decision making, fuzzy sets, standard fuzzy sets, determinate fuzzy sets, indeterminate fuzzy sets, proximity measure method, Minkowski distance family function, Hausdorff distance function, MCDM, PMM, PMM-F

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 345

Authors: John Kabuba, Antoine Mulaba-Bafubiandi, Kim Battle

Abstract:

This paper presents a critical study about the application of Neural Networks to ion-exchange process. Ionexchange is a complex non-linear process involving many factors influencing the ions uptake mechanisms from the pregnant solution. The following step includes the elution. Published data presents empirical isotherm equations with definite shortcomings resulting in unreliable predictions. Although Neural Network simulation technique encounters a number of disadvantages including its “black box", and a limited ability to explicitly identify possible causal relationships, it has the advantage to implicitly handle complex nonlinear relationships between dependent and independent variables. In the present paper, the Neural Network model based on the back-propagation algorithm Levenberg-Marquardt was developed using a three layer approach with a tangent sigmoid transfer function (tansig) at hidden layer with 11 neurons and linear transfer function (purelin) at out layer. The above mentioned approach has been used to test the effectiveness in simulating ion exchange processes. The modeling results showed that there is an excellent agreement between the experimental data and the predicted values of copper ions removed from aqueous solutions.

Keywords: Copper, ion-exchange process, neural networks, simulation

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1608