Search results for: Time-Memory tradeoff

Authors: A. Muthuramalingam, S. Himavathi, E. Srinivasan

Abstract:

.Hardware realization of a Neural Network (NN), to a large extent depends on the efficient implementation of a single neuron. FPGA-based reconfigurable computing architectures are suitable for hardware implementation of neural networks. FPGA realization of ANNs with a large number of neurons is still a challenging task. This paper discusses the issues involved in implementation of a multi-input neuron with linear/nonlinear excitation functions using FPGA. Implementation method with resource/speed tradeoff is proposed to handle signed decimal numbers. The VHDL coding developed is tested using Xilinx XC V50hq240 Chip. To improve the speed of operation a lookup table method is used. The problems involved in using a lookup table (LUT) for a nonlinear function is discussed. The percentage saving in resource and the improvement in speed with an LUT for a neuron is reported. An attempt is also made to derive a generalized formula for a multi-input neuron that facilitates to estimate approximately the total resource requirement and speed achievable for a given multilayer neural network. This facilitates the designer to choose the FPGA capacity for a given application. Using the proposed method of implementation a neural network based application, namely, a Space vector modulator for a vector-controlled drive is presented

Keywords: FPGA implementation, multi-input neuron, neural network, nn based space vector modulator.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4424

Authors: M. S. Nourbakhsh, M. E. Khosroshahi

Abstract:

Laser soldering is based on applying some soldering material (albumin) onto the approximated edges of the cut and heating the solder (and the underlying tissues) by a laser beam. Endogenous and exogenous materials such as indocyanine green (ICG) are often added to solders to enhance light absorption. Gold nanoshells are new materials which have an optical response dictated by the plasmon resonance. The wavelength at which the resonance occurs depends on the core and shell sizes, allowing nanoshells to be tailored for particular applications. The purposes of this study was use combination of ICG and different concentration of gold nanoshells for skin tissue soldering and also to examine the effect of laser soldering parameters on the properties of repaired skin. Two mixtures of albumin solder and different combinations of ICG and gold nanoshells were prepared. A full thickness incision of 2×20 mm2 was made on the surface and after addition of mixtures it was irradiated by an 810nm diode laser at different power densities. The changes of tensile strength σt due to temperature rise, number of scan (Ns), and scan velocity (Vs) were investigated. The results showed at constant laser power density (I), σt of repaired incisions increases by increasing the concentration of gold nanoshells in solder, Ns and decreasing Vs. It is therefore important to consider the tradeoff between the scan velocity and the surface temperature for achieving an optimum operating condition. In our case this corresponds to σt =1800 gr/cm2 at I~ 47 Wcm-2, T ~ 85ºC, Ns =10 and Vs=0.3mms-1.

Keywords: Tissue soldering, gold nanoshells, indocyanine green, combination, tensile strength.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1502

Authors: I. Asanuma, T. Yamaguchi, J. Park, K. J. Mackin

Abstract:

Fishery lights on the surface could be detected by the Day and Night Band (DNB) of the Visible Infrared Imaging Radiometer Suite (VIIRS) on the Suomi National Polar-orbiting Partnership (Suomi-NPP). The DNB covers the spectral range of 500 to 900 nm and realized a higher sensitivity. The DNB has a difficulty of identification of fishing lights from lunar lights reflected by clouds, which affects observations for the half of the month. Fishery lights and lights of the surface are identified from lunar lights reflected by clouds by a method using the DNB and the infrared band, where the detection limits are defined as a function of the brightness temperature with a difference from the maximum temperature for each level of DNB radiance and with the contrast of DNB radiance against the background radiance. Fishery boats or structures on islands could be detected by the Synthetic Aperture Radar (SAR) on the polar orbit satellites using the reflected microwave by the surface reflecting targets. The SAR has a difficulty of tradeoff between spatial resolution and coverage while detecting the small targets like fishery boats. A distribution of fishery boats and island activities were detected by the scan-SAR narrow mode of Radarsat-2, which covers 300 km by 300 km with various combinations of polarizations. The fishing boats were detected as a single pixel of highly scattering targets with the scan-SAR narrow mode of which spatial resolution is 30 m. As the look angle dependent scattering signals exhibits the significant differences, the standard deviations of scattered signals for each look angles were taken into account as a threshold to identify the signal from fishing boats and structures on the island from background noise. It was difficult to validate the detected targets by DNB with SAR data because of time lag of observations for 6 hours between midnight by DNB and morning or evening by SAR. The temporal changes of island activities were detected as a change of mean intensity of DNB for circular area for a certain scale of activities. The increase of DNB mean intensity was corresponding to the beginning of dredging and the change of intensity indicated the ending of reclamation and following constructions of facilities.

Keywords: Day night band, fishery, SAR, South China Sea.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1093

Authors: Rajinder Singh, Ram Valluru

Abstract:

Chain Ladder (CL) method, Expected Loss Ratio (ELR) method and Bornhuetter-Ferguson (BF) method, in addition to more complex transition-rate modeling, are commonly used actuarial reserving methods in general insurance. There is limited published research about their relative performance in the context of Mortgage Insurance (MI). In our experience, these traditional techniques pose unique challenges and do not provide stable claim estimates for medium to longer term liabilities. The relative strengths and weaknesses among various alternative approaches revolve around: stability in the recent loss development pattern, sufficiency and reliability of loss development data, and agreement/disagreement between reported losses to date and ultimate loss estimate. CL method results in volatile reserve estimates, especially for accident periods with little development experience. The ELR method breaks down especially when ultimate loss ratios are not stable and predictable. While the BF method provides a good tradeoff between the loss development approach (CL) and ELR, the approach generates claim development and ultimate reserves that are disconnected from the ever-to-date (ETD) development experience for some accident years that have more development experience. Further, BF is based on subjective a priori assumption. The fundamental shortcoming of these methods is their inability to model exogenous factors, like the economy, which impact various cohorts at the same chronological time but at staggered points along their life-time development. This paper proposes an alternative approach of parametrizing the loss development curve and using logistic regression to generate the ultimate loss estimate for each homogeneous group (accident year or delinquency period). The methodology was tested on an actual MI claim development dataset where various cohorts followed a sigmoidal trend, but levels varied substantially depending upon the economic and operational conditions during the development period spanning over many years. The proposed approach provides the ability to indirectly incorporate such exogenous factors and produce more stable loss forecasts for reserving purposes as compared to the traditional CL and BF methods.

Keywords: Actuarial loss reserving techniques, logistic regression, parametric function, volatility.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 416

Authors: Hirbod Varasteh, Hamidreza Gohari Darabkhani

Abstract:

The global warming and its impact on climate change is one of main challenges for current century. Global warming is mainly due to the emission of greenhouse gases (GHG) and carbon dioxide (CO₂) is known to be the major contributor to the GHG emission profile. Whilst the energy sector is the primary source for CO₂ emission, Carbon Capture and Storage (CCS) are believed to be the solution for controlling this emission. Oxyfuel combustion (Oxy-combustion) is one of the major technologies for capturing CO₂ from power plants. For gas turbines, several Oxy-combustion power cycles (Oxyturbine cycles) have been investigated by means of thermodynamic analysis. NetPower cycle is one of the leading oxyturbine power cycles with almost full carbon capture capability from a natural gas fired power plant. In this manuscript, sensitivity analysis of the heat exchanger design in NetPower cycle is completed by means of process modelling. The heat capacity variation and supercritical CO₂ with gaseous admixtures are considered for multi-zone analysis with Aspen Plus software. It is found that the heat exchanger design has a major role to increase the efficiency of NetPower cycle. The pinch-point analysis is done to extract the composite and grand composite curve for the heat exchanger. In this paper, relationship between the cycle efficiency and the minimum approach temperature (∆Tmin) of the heat exchanger has also been evaluated.  Increase in ∆Tmin causes a decrease in the temperature of the recycle flue gases (RFG) and an overall decrease in the required power for the recycled gas compressor. The main challenge in the design of heat exchangers in power plants is a tradeoff between the capital and operational costs. To achieve lower ∆Tmin, larger size of heat exchanger is required. This means a higher capital cost but leading to a better heat recovery and lower operational cost. To achieve this, ∆Tmin is selected from the minimum point in the diagrams of capital and operational costs. This study provides an insight into the NetPower Oxy-combustion cycle’s performance analysis and operational condition based on its heat exchanger design.

Keywords: Carbon capture and storage, oxy-combustion, netpower cycle, oxyturbine power cycles, heat exchanger design, supercritical carbon dioxide, pinch point analysis.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1688