S. No. Title Page No.

Farming lands are increasingly plentiful in developing countries, making it difficult for farmers to keep track of each and every plant in their fields on a regular basis. It is also impossible for farmers to be aware of all illnesses; therefore non-native diseases are frequently overlooked. Expert consultation for this is often time consuming and pricey. As a result, an automated method to identify and classify plant diseases the utilization of image processing is required. Deep learning and convolution neural networks are employed in this study to identify sickness in agricultural produce. Because convolution neural networks are specifically intended to analyze pixel data, they deliver higher accuracy and results when classifying photos into healthy and non-healthy categories. This technique includes two phases: the first requires training the modeling for healthy and diseased photos of crops; the second phase comprises crop monitoring and identification of specific disease in the plant, which leads to early disease diagnosis.

#002 007-011

Because of its enough error detecting and repairing capabilities the low power, high efficient Low Density Parity-Check Code (LDPC) Decoder Architecture for error detection & correction applications. Low Density Parity-Check codes have been adopted in latest wireless standards such as satellite and mobile communications since they obtain superior error-detecting and correcting capabilities. However, as technology advances, building such a decoder has always been a challenge because it necessitates specific memory size and power consumptions. In this paper, we propose an LDPC decoder design by the use of Booth Algorithm that addresses these check in this study. The architecture was synthesized on Xilinx 14.7, and the synthesis report showed that the propose architecture uses less hardware and consumes less power than the conventional architecture, resulting in a more standard outcome.


A Multiplier using Carry Look Ahead Adders instead of full adders to implement the reduction of the bit product matrix into the two numbers that are added to make the product. Four-bit carry look Ahead adders are used in the reduction in place of individual full adders. Reduction of Nine partial products by a single carry look ahead adder (instead of 3 with a full adder) in same amount of time. This leads to fewer reduction stages than a traditional Wallace/Dadda Multiplier. One fewer stage is required for 4 by 4, 8 by 8, and 16 by 16 bit multipliers and 2 stages are saved for larger multipliers.


Get In Touch

  • 19, Knowledge Park-II, Institutional Area, Greater Noida (UP), India Pincode-2013066
  • editor@njet.org

© 2022 NIET Journal Of Engineering & Technology (NIETJET). All Rights Reserved