In this paper, we propose a low latency, robust and scalable neural net based decoder for convolutional and low-density parity-check (LPDC) coding schemes. The proposed decoders are demonstrated to have bit error rate (BER) and block error rate (BLER) performances at par with the state-ofthe-art neural net based decoders while achieving more than 8 times higher decoding speed. The enhanced decoding speed is due to the use of convolutional neural network (CNN) as opposed to recurrent neural network (RNN) used in the best known neural net based decoders. This contradicts existing doctrine that only RNN based decoders can provide a performance close to the optimal ones. The key ingredient to our approach is a novel Mixed-SNR Independent Samples based Training (MIST), which allows for training of CNN with only 1% of possible datawords, even for block length as high as 1000. The proposed decoder is robust as, once trained, the same decoder can be used for a wide range of SNR values. Finally, in the presence of channel outages, the proposed decoders outperform the best known decoders, viz. unquantized Viterbi decoder for convolutional code, and belief propagation for LDPC. This gives the CNN decoder a significant advantage in 5G millimeter wave systems, where channel outages are prevalent.

No abstract

The present study is aimed to evaluate hydrogeomorphology, lineaments and landuse/landcover aspects of the study area using the IRS-IC & ID images.  The false colour composition of IRS-IC & ID images are used for this study.  It is advantageous to use satellite multispectral data as the image data in different bands can be exposed to digital improvement techniques.  So the differences in objects can be highlighted to enhance the understanding of the image. Landforms are interpreted on the basis of interpretation element keys such as- tone, texture, size, shape, color etc. and extract the specific information from the false color composited LISS-III sensor images.  Field observations showed that ground water occurs under unconfined conditions with water table at shallow to great depth. The lineament density map to be prepared to understand the impacts on groundwater percolation. The hydrogeomorphology, Lineament and Landuse/landcover maps  are  overlaid  to trace  groundwater  potential  zones.  An integrated remote sensing and geographic Information System (GIS) based approach has been used for demarcating groundwater potential zones. Remote sensing techniques have been used to describe the hydrogeomorphology, land use / land cover and the lineaments of the study area using SPOT and IRS – I D visual products.   Based on this the detailed descriptions of geomorphic features of the area are traced. Great emphasis is also given to the study of lineament pattern of the study area, the land use and land cover.

Irrigation water was supplied to supplement the water available from rainfall, So the purpose of crop production of application of water to soil is the Irrigation.  Due to lack of amount and timing of rainfall, to the moisture requirement of crops and irrigation, It is necessary to meet the needs of food and fibbers, So the raise crops is essential  in many area of the world.  Water features composed of all surface water features viz. reservoirs, tanks & ponds, beels, oxbow lakes, derelict water and brackish water, which are the function of intensity of rainfall, rainfall amounts etc. over season/a year.  The mapping, monitoring of dynamics of surface water bodies were acquire by satellite sensors through synoptic and dynamic coverage of earth surface at frequent intervals.  In FCC water bodies appear as different hues depending on their physical characteristics such as depth of water (bottom reflection), turbidity, etc. Water appears dark due to which absorbs all infrared radiations.  This helps in easy contrast distinction between water and land in near-infrared band.  Mapping, monitoring and inventory of water features over wide areas by Satellite data is a reputed proficiency for creation of dynamic databases.  Our present area of interest includes an automatic approach to capture the water body from a Resourcesat-2 AWiFS (Advanced Wide-Field Sensor) imagery using a Automated Algorithm for extraction of surface water bodies model.  The dynamics of surface water bodies in study on geospatial analysis of the evaluation of water feature sheets for the month of April, 2018 of the study area.  The water features information was generated on geospatial database from the Resourcesat-2 AWiFS image  by using bands of 1.55- 1.70 µm (SWIR), 0.77-0.86 µm (NIR), 0.62-0.68 µm (Red) and 0.52-0.59 µm (Green) for the estimation of the water spread area.  The Water Spread Area (WSA) calculated for each is 11304 ha [1] and [2].

In the recent past lot of research is taken place on surface water features. The surface water includes lakes, ponds, rivers, streams and other exposed inland water bodies. The function of rainfall amounts, intensity of rainfall etc. over season / year are the variation in spatial extent of these features.  Remote sensing providing lot of data and extracting lot of information over the changes from time to time. Nowadays the role of satellite image process is widely used in extraction of water bodies. Different researchers are using various methods to delineate water bodies from different satellite imagery varying in characteristics like spatial, spectral, and temporal. In FCC water bodies appear as different hues depending on their physical characteristics such as depth of water (bottom reflection), turbidity, etc. Water appears dark due to which absorbs all infrared radiations which helps in easy contrast distinction between water and land in near-infrared band.  Our present area of interest includes an automatic approach to capture the water body from a Resourcesat-2 AWiFS (Advanced Wide-Field Sensor) imagery using a Automated Algorithm for extraction of surface water bodies model. The dynamics of surface water bodies in Study on geospatial analysis of the extraction of water feature sheets for the month of January month 2018 of the study area.  Geospatial database on water bodies information has been created from the Resourcesat-2 AWiFS image. By using bands of 1.55- 1.70 µm (SWIR), 0.77-0.86 µm (NIR), 0.62-0.68 µm (Red) and 0.52-0.59 µm (Green) for the estimation of the water spread area.  The Water spread area (WSA) calculated for each is 37231 ha [1] and [2].