The detection of water bodies from satellite images plays a vital role in research development. It has a wide range of applications such as the prediction of natural disasters and detecting drought and flood conditions. There were few existing applications that focused on detecting water bodies that are becoming extinct in nature. The dataset to train this deep learning model is taken from Kaggle. It has two classes, namely water bodies and masks. There is a total of 2841 sentinel-2 satellite images with corresponding 2841 masks. Additionally, the present work focuses on using UNet, Tensorflow to detect the water bodies. It uses a Nadam optimizer to reduce the losses. It also finds best-optimized parameters for the activation function, a number of nodes in each layer. This proposed model achieves integrity by embedding a security feature Elliptic Curve Digital Signature Algorithm (ECDSA). It generates a digital signature for the predicted area of water bodies which helps to secure the key and the detected water bodies while transmitting in a channel. Thus, the proposed model ensures the performance accuracy of 94% which can also work the same for edge detection, detection in blurred and low-resolution images. The model is highly robust.

/pdf/ecdsa-based-water-bodies-prediction-from-satellite-images-2eoxxlet.pdf

ECDSA-Based Water Bodies Prediction from Satellite Images with UNet

Due to non-ideal optical effects such as aberration and optical diffraction, printed poly gates on the wafer suffer from across-gate linewidth variation (AGLV) and across-chip linewidth variation (ACLV,) especially in the subwavelength regime. The poly gate distortion affects electrical characteristics of a device, including drive current (I on ), leakage current (I off ), and threshold voltage (V t ). For circuits such as compact memory cells which are sensitive to geometry variations, electrical performances can vary with the image distortion of each transistor even with resolution enhancement technologies (RETs) such as optical proximity corrections. In this paper, we demonstrate the impacts of OPC settings on the performance of a 6T-SRAM cell. The printed gate-region and active-region patterns are simulated by an in-house OPC engine we developed. A device model for each distorted transistor is then extracted based on approximating each distorted channel pattern with a set of smaller rectangles. Consequently, electrical performance such as static noise margin (SNM) can be obtained by incorporating these extracted device models into a circuit simulator. Preliminary results show that OPC settings such as segmentation length and number of corrections can affect wafer image quality and electrical performance in different ways.

Impacts of optical proximity correction settings on electrical performances

Hiring a suitable candidate for a certain job is highly demanding and requires several intense processes. Many organizations face challenges to hire a suitable candidate as they seek specific requirements mentioned in the Job Description (JD). An Artificial Intelligence (AI) based system is developed to measure and predict a suitable candidate from an available Candidate Resume (CR) database. Four clusters are prepared from JD and CR corresponding to primary skills, secondary skills, adjectives, and adverbs. The Jaccard similarity is measured between these clusters and a suitability measure is proposed based on the cluster parameters. Using the three classifiers linear regression, decision tree, Adaboost, and XGBoost the prediction of candidate suitability is performed. To carry out the classification tasks various features are formed by employing the bag of words technique. The maximum average accuracy of 95.14% is achieved for the XGBoost classifier. 

AI based suitability measurement and prediction between job description and job seeker profiles

Water management is one of the crucial topics discussed in most of the international forums. Water harvesting and recycling are the major requirements to meet the global upcoming demand of the water crisis, which is prevalent. To achieve this, we need more emphasis on water management techniques that are applied across various categories of the applications. Keeping in mind the population density index, there is a dire need to implement intelligent water management mechanisms for effective distribution, conservation and to maintain the water quality standards for various purposes. The prescribed work discusses about few major areas of applications that are required for efficient water management. Those are recent trends in wastewater recycle, water distribution, rainwater harvesting and irrigation management using various Artificial Intelligence (AI) models. The data acquired for these applications are purely unique and also differs by type. Hence, there is a dire need to use a model or algorithm that can be applied to provide solutions across all these applications. Artificial Intelligence (AI) and Deep Learning (DL) techniques along with the Internet of things (IoT) framework can facilitate in designing a smart water management system for sustainable water usage from natural resources. This work surveys various water management techniques and the use of AI/DL along with the IoT network and case studies, sample statistical analysis to develop an efficient water management framework.

/pdf/smart-water-resource-management-using-artificial-3rxw2qii.pdf

Smart Water Resource Management Using Artificial Intelligence—A Review

Rivers are dynamic geological agents on the earth which transport the weathered materials of the continent to the sea. Estimation of suspended sediment yield (SSY) is essential for management, planning, and designing in any river basin system. Estimation of SSY is critical due to its complex nonlinear processes, which are not captured by conventional regression methods. Rainfall, temperature, water discharge, SSY, rock type, relief, and catchment area data of 11 gauging stations were utilized to develop robust artificial intelligence (AI), similar to an artificial-neural-network (ANN)-based model for SSY prediction. The developed highly generalized global single ANN model using a large amount of data was applied at individual gauging stations for SSY prediction in the Mahanadi River basin, which is one of India’s largest peninsular rivers. It appeared that the proposed ANN model had the lowest root-mean-squared error (0.0089) and mean absolute error (0.0029) along with the highest coefficient of correlation (0.867) values among all comparative models (sediment rating curve and multiple linear regression). The ANN provided the best accuracy at Tikarapara among all stations. The ANN model was the most suitable substitute over other comparative models for SSY prediction. It was also noticed that the developed ANN model using the combined data of eleven stations performed better at Tikarapara than the other ANN which was developed using data from Tikarapara only. These approaches are suggested for SSY prediction in river basin systems due to their ease of implementation and better performance.

/pdf/an-enhanced-feed-forward-back-propagation-levenberg-3i36pj11.pdf

An Enhanced Feed-Forward Back Propagation Levenberg–Marquardt Algorithm for Suspended Sediment Yield Modeling

Suspended sediment yield (SSY) prediction plays a crucial role in the planning of water resource management and design. Accurate sediment prediction using conventional models is very difficult due to many complex processes. We developed a fully automatic highly generalized accurate and robust artificial intelligence models for SSY prediction in Godavari River Basin, India. The genetic algorithm (GA), hybridized with an artificial neural network (ANN) (GA-ANN), is a suitable artificial intelligence model for SSY prediction. The GA is used to concurrently optimize all ANN’s parameters. The GA-ANN was developed using daily water discharge, with water level as the input data to estimate the daily SSY at Polavaram, which is the farthest gauging station in the downstream of the Godavari River Basin. The performances of the GA-ANN model were evaluated by comparing with ANN, sediment rating curve (SRC) and multiple linear regression (MLR) models. It is observed that the GA-ANN contains the highest correlation coefficient (0.927) and lowest root mean square error (0.053) along with lowest biased (0.020) values among all the comparative models. The GA-ANN model is the most suitable substitute over traditional models for SSY prediction. The hybrid GA-ANN can be recommended for estimating the SSY due to comparatively superior performance and simplicity of applications.

/pdf/capability-and-robustness-of-novel-hybridized-artificial-11is150t.pdf

Capability and Robustness of Novel Hybridized Artificial Intelligence Technique for Sediment Yield Modeling in Godavari River, India

The impact of photo mask manufacturing errors in the photolithography process and subsequently on the final device and test circuit (ring oscillator) performance are investigated. A statistical Monte Carlo process generates a population of normally distributed simulated photo mask errors during the reticle manufacturing process. Further steps predict how these photo mask errors impact printed poly gate patterns under different lithography conditions. Sensitivity analysis performed with the Sequoia Device Designer software tool identified the metal oxide semiconductor field effect transistor (MOSFET) channel length (L poly ) as the most sensitive MOSFET parameter and an estimate of the distribution of device performance for realistic photo mask errors is made.

Subwavelength lithography: an impact of photomask errors on circuit performance

This is an extension of our previous work where we discussed basic assumptions of device oriented process verification. Here, we propose an integrated procedure to verify the design of active devices and interconnections. It entails extraction of device, contact, and interconnect electrical performance based on optical simulation of layout geometries, including proximity correction features, combined with critical dimension (CD) variation and misalignment. A critical analysis, proposed in this work, made it possible to focus the simulation on the selected process corner options. We integrated multi-level optical and device simulation to verify dense layouts for deep sub- wavelength design rules in a six-transistor advanced memory cell.

Advanced procedure to evaluate process performance at very low k1 based on device parameters linked to lithography and process data:II. Verification of cell layout based on integration of optical an

Devendra Joshi

Papers

Capability and Robustness of Novel Hybridized Artificial Intelligence Technique for Sediment Yield Modeling in Godavari River, India

Subwavelength lithography: an impact of photomask errors on circuit performance

Advanced procedure to evaluate process performance at very low k1 based on device parameters linked to lithography and process data:II. Verification of cell layout based on integration of optical an