S. Veenadhari

Bio: S. Veenadhari is an academic researcher. The author has contributed to research in topics: Computer science & Crop yield. The author has an hindex of 1, co-authored 1 publications receiving 78 citations.

Machine learning approach for forecasting crop yield based on climatic parameters

Abstract: With the impact of climate change in India, majority of the agricultural crops are being badly affected interms of their performance over a period of last two decades. Predicting the crop yield well ahead of its harvest would help the policy makers and farmers for taking appropriate measures for marketing and storage. Such predictions will also help the associated industries for planning the logistics of their business. Several methods of predicting and modeling crop yields have been developed in the past with varying rateof success, as these don't take into account characteristicsoftheweather, a n d aremostly empirical. In the present study a software tool named ‘Crop Advisor’ has been developed as an user friendly web page for predicting the influence of climatic parameters on the crop yields.C4.5 algorithm is used to find out the most influencing climatic parameter on the crop yields of selected crops in selected districts of Madhya Pradesh. This software provides an indication of relative influence of different climatic parameters on the crop yield, other agro-input parameters responsible for crop yield are not considered in this tool, since, application of these input parameters varies with individual fields in space and time.

Secure Cluster based Routing Protocol for WSN

Abstract: In wireless sensor networks (WSNs), data communication is performed using different routing protocols. One of the mostly used routing protocol is cluster-based routing protocol. The foundation of cluster-based routing protocol is the formation of clusters and selection of Cluster Head (CH) for energy-efficient transmission. CH are solely responsible for data packets transmission among nodes. But, such protocols are susceptible to network attacks. In this paper, a novel secure cluster-based routing protocol is designed for safe data transmission. Based on the findings, the designed solution offers excellent capabilities in terms of packet delivery ratio (PDR), energy usage, throughput, and End-to-End delay.

An Efficient Classification Technique For Automatic Identification of Emotions Leading To Stress

Abstract: Facial Expression Recognition (FER) has gained interest among researchers because of its ineludible role in human computer interaction (HCI). It is found to be useful in information security, data privacy, user authentication, person identification and in many areas. FER is also useful in recognizing social signals, social behavior, deceit detection, interactive video and behavior monitoring in the field of human-computer interaction. Aim of this paper is to identify a classifier which is most accurate to identify emotions like sad, disgust, angry and fear. For this the performance of Support Vector Machine (SVM), Random Forest (RF), Radial basis function (RBF), Multilayer Perceptron Neural Network (MLPNN), Decision tree (J48), K-Nearest Neighbor (KNN), Neural Network (NN) classifiers are evaluated. Principal Component Analysis (PCA) is used as the dimensionality reduction technique. Local binary pattern (LBP), Histogram of Gradient (HOG), Gabor wavelet and Chi-Square are used as the feature extraction technique. The evaluation process was conducted on MMI, JAFFE and Extended Cohn Kanade $(\mathbf{CK}+)$ facial expression datasets. It is found that the classifier KNN gives classification accuracy of 93.46 % in identifying the emotions which may lead to stress.

Adaptive Multi-Hop Deep Learning based Drug Recommendation System with Selective Coverage Mechanism

Abstract: The goal of drug recommendation is to generate drug prescriptions based on patient’s electronic medical records and provide clinical decision support for doctors. Extracting temporal patterns and contextual information in electronic medical records is the key to successful drug recommendation. However, previous studies have ignored the relationship between patients. As a result, there are differences in the data volume of medical records among different patients, and it is impossible to adjust the focus of attention and the number of data reading iterations in the data reading process according to the individual conditions of different patients. To solve the above problems, this paper proposes a selective coverage mechanism and adaptive memory neural network, The drug recommendation model combined with reading. The model uses the neural memory network to store the temporal pattern encoding results corresponding to the patient’s health status and uses the coverage mechanism to perform data filtering and attention weight adjustment in the iterative reading process. At the same time, the model is based on the patient’s situation, Adaptively determining the number of readings of the neural memory network. Experimental results based on accurate clinical data show that this model can adaptively extract essential data from electronic medical records, construct an effective representation vector of the patient’s health status, and then complete drug recommendations.

Task Offloading Strategy using Double Q-Learning based Optimization in MEC

Abstract: Deep learning assisted mobile edge computing (MEC) has recently gained a lot of attention because of its superior ability to decrease the amount of energy and latency of MEC offloading. Energy usage during MEC offloading should be kept to a minimum, a multi-objective optimization problem is formulated, and a low-complexity allocating resources approach is implied. The paper proposes a deep double q-learning (DDQN) based optimization for MEC energy consumption reduction. The result analysis shows that energy consumption with respect to variable tasks and variable users. According to result analysis, it was observed that with increasing number of task and number of users, the energy consumption increases. With DDQN optimization energy consumption is reduced as compared to without DDQN optimization.

Analysis of agriculture data using data mining techniques: application of big data

Abstract: In agriculture sector where farmers and agribusinesses have to make innumerable decisions every day and intricate complexities involves the various factors influencing them. An essential issue for agricultural planning intention is the accurate yield estimation for the numerous crops involved in the planning. Data mining techniques are necessary approach for accomplishing practical and effective solutions for this problem. Agriculture has been an obvious target for big data. Environmental conditions, variability in soil, input levels, combinations and commodity prices have made it all the more relevant for farmers to use information and get help to make critical farming decisions. This paper focuses on the analysis of the agriculture data and finding optimal parameters to maximize the crop production using data mining techniques like PAM, CLARA, DBSCAN and Multiple Linear Regression. Mining the large amount of existing crop, soil and climatic data, and analysing new, non-experimental data optimizes the production and makes agriculture more resilient to climatic change.

Prediction of Crop Yield using Regression Analysis

Abstract: Yield prediction benefits the farmers in reducing their losses and to get best prices for their crops. The objective of this work is to analyze the environmental parameters like Area under Cultivation (AUC), Annual Rainfall (AR) and Food Price Index (FPI) that influences the yield of crop and to establish a relationship among these parameters. In this research, Regression Analysis (RA) is used to analyze the environmental factors and their infliction on crop yield. RA is a multivariate analysis technique which analyzes the factors groups them into explanatory and response variables and helps to obtain a decision. A sample of environmental factors like AR, AUC, FPI are considered for a period of 10 years from 1990-2000. Linear Regression (LR) is used to establish relationship between explanatory variables (AR, AUC, FPI) and the crop yield as response variable. R 2 value clearly shows that yield is mainly dependent on AR. AUC and FPI are the other two factors influencing the crop yield. This research can be extended by considering other factors like Minimum Support Price (MSP), Cost Price Index (CPI), Wholesale Price Index (WPI) etc. and their relationship with crop yield.

Crop Yield Prediction based on Indian Agriculture using Machine Learning

Abstract: In India, we all know that Agriculture is the backbone of the country. This paper predicts the yield of almost all kinds of crops that are planted in India. This script makes novel by the usage of simple parameters like State, district, season, area and the user can predict the yield of the crop in which year he or she wants to. The paper uses advanced regression techniques like Kernel Ridge, Lasso and ENet algorithms to predict the yield and uses the concept of Stacking Regression for enhancing the algorithms to give a better prediction.

Potato Yield Prediction Using Machine Learning Techniques and Sentinel 2 Data

Abstract: Traditional potato growth models evidence certain limitations, such as the cost of obtaining the input data required to run the models, the lack of spatial information in some instances, or the actual quality of input data. In order to address these issues, we develop a model to predict potato yield using satellite remote sensing. In an effort to offer a good predictive model that improves the state of the art on potato precision agriculture, we use images from the twin Sentinel 2 satellites (European Space Agency—Copernicus Programme) over three growing seasons, applying different machine learning models. First, we fitted nine machine learning algorithms with various pre-processing scenarios using variables from July, August and September based on the red, red-edge and infra-red bands of the spectrum. Second, we selected the best performing models and evaluated them against independent test data. Finally, we repeated the previous two steps using only variables corresponding to July and August. Our results showed that the feature selection step proved vital during data pre-processing in order to reduce multicollinearity among predictors. The Regression Quantile Lasso model (11.67% Root Mean Square Error, RMSE; R2 = 0.88 and 9.18% Mean Absolute Error, MAE) and Leap Backwards model (10.94% RMSE, R2 = 0.89 and 8.95% MAE) performed better when predictors with a correlation coefficient > 0.5 were removed from the dataset. In contrast, the Support Vector Machine Radial (svmRadial) performed better with no feature selection method (11.7% RMSE, R2 = 0.93 and 8.64% MAE). In addition, we used a random forest model to predict potato yields in Castilla y Leon (Spain) 1–2 months prior to harvest, and obtained satisfactory results (11.16% RMSE, R2 = 0.89 and 8.71% MAE). These results demonstrate the suitability of our models to predict potato yields in the region studied.

A study on various data mining techniques for crop yield prediction

Abstract: India is a country where agriculture and agriculture related industries are the major source of living for the people Agriculture is a major source of economy of the country It is also one of the country which suffer from major natural calamities like drought or flood which damages the crop This leads to huge financial loss for the farmers thus leading to the suicide Predicting the crop yield well in advance prior to its harvest can help the farmers and Government organizations to make appropriate planning like storing, selling, fixing minimum support price, importing/exporting etc Predicting a crop well in advance requires a systematic study of huge data coming from various variables like soil quality, pH, EC, N, P, K etc As Prediction of crop deals with large set of database thus making this prediction system a perfect candidate for application of data mining Through data mining we extract the knowledge from the huge size of data This paper presents the study about the various data mining techniques used for predicting the crop yield The success of any crop yield prediction system heavily relies on how accurately the features have been extracted and how appropriately classifiers have been employed This paper summarizes the results obtained by various algorithms which are being used by various authors for crop yield prediction, with their accuracy and recommendation