Bus Encoded LUT Multiplier for Portable Biomedical Therapeutic Devices

DSP operation in a Biomedical related therapeutic hardware need to beperformed with high accuracy and with high speed. Portable DSP hardware’s likepulse/heart beat detectors must perform with reduced operational power due to lack ofconventional power sources. This work proposes a hybrid biomedical hardware chip inwhich the speed and power utilization factors are greatly improved. Multipliers are thecore operational unit of any DSP SoC. This work proposes a LUT based unsignedmultiplication which is proven to be efficient in terms of high operating speed. For n bitinput multiplication n*n memory array of 2 n bit size is required to memorize all thepossible input and output combination. Various literature works claims to be achieve highspeed multiplication with reduced LUT size by integrating a barrel shifter mechanism.This paper work address this problem, by reworking the multiplier architecture with aparallel operating pre-processing unit which used to change the multiplier and multiplicandorder with respect to the number of computational addition and subtraction stages required.Along with LUT multiplier a low power bus encoding scheme is integrated to limit the powerconstraint of the on chip DSP unit. This paper address both the speed and power optimizationtechniques and tested with various FPGA device families.

Inversion of radiative transfer model for retrieval of wheat biophysical parameters from broadband reflectance measurements

This study describes the retrieval of wheat biophysical variables of leaf chlorophyll(Cab),leaf area index(LAI),canopy chlorophyll(CCC),and leaf wetness(Cw)from broadband reflectance data corresponding to IRS LISS-3(Linear Imaging Self Scanner)sensor by inversion of PROSAIL5B canopy radiative transfer model.Reflectance data of wheat crop,grown under different treatments,were measured by hand-held spectroradiometer and later integrated to LISS-3 reflectance using its band-wise relative spectral response function.Three inversion techniques were used and their performance was compared using different statistical parameters and target diagram.The inversion techniques tried were:a look up table with best solution(LUT-I),a look up table with mean of best 10%solutions(LUT-II)and an artificial neural network(ANN).All the techniques could estimate the biophysical variables by capturing variability in their observed values,though accuracy of estimation varied among the three techniques.Target diagram clearly depicted the superiority of LUT-II over the other two approaches indicating that a mean of best 10%solutions is a better strategy while ANN was worst performer showing highest bias for all the parameters.In all the three inversion techniques,the general order of retrieval accuracy was LAI>Cab>CCC>Cw.The range of Cw was very narrow and none of the techniques could estimate variations in it.In most of the cases,the parameters were underestimated by model inversion.The best identified LUT-II technique was then applied to retrieve wheat LAI from IRS LISS-3 satellite image of 5-Feb-2012 in Sheopur district.The comparison with ground observations showed that the RMSE of LAI retrieval was about 0.56,similar to that observed in ground experimentation.The findings of this study may help in refining the protocol for generating operational crop biophysical products from IRS LISS-3 or similar sensors.

A multi-step standard-cell placement algorithm of optimizing timing and congestion behavior

The timing behavior and congestion behavior are two important goals in the performance-driven standard-cell placement. In this paper, we analyze the relationship between the timing and congestion behavior. We bring up a multi-step placement algorithm to reach the two goals. First, the timing-driven placement algorithm is used to find the global optimal solution. In the second step, the algorithm tries to decrease the maximum congestion while not deteriorating the timing behavior. We have implemented our algorithm and tested it with real circuits. The results show that the maximum delay can decrease by 30% in our timing-driven placement and in the second step the maximum congestion will decrease by 10% while the timing behavior is unchanged.