Himanshu Dutt Sharma

Himanshu Dutt Sharma

Auto-generated profile, based on publicly available information

Himanshu Dutt Sharma

Department of Electronics and Communication Engineering

Research Focus & Metrics

Academic Career Length

21Years (2006-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
10 February 2022 in Journal of Food Quality
Verified
Journal Article
Open access
PDF file
ASAshutosh Kumar Singh
Ashutosh Kumar Singh
SSSvn Sreenivasu
Svn Sreenivasu
UMU.S.B. K. Mahalaxmi
U.S.B. K. Mahalaxmi
HSHimanshu Sharma
Himanshu Sharma
DPDinesh D. Patil
Dinesh D. Patil
Evans AsensoEvans Asenso
Evans Asenso
Plant diseases are unfavourable factors that cause a significant decrease in the quality and quantity of crops. Experienced biologists or farmers often observe plants with the naked eye for disease, but this method is often imprecise and can take a long time. In this study, we use artificial intelligence and computer vision techniques to achieve the goal of designing and developing an intelligent classification mechanism for leaf diseases. This paper follows two methodologies and their simulation outcomes are compared for performance evaluation. In the first part, data augmentation is performed on the PlantVillage data set images (for apple, corn, potato, tomato, and rice plants), and their deep features are extracted using convolutional neural network (CNN). These features are classified by a Bayesian optimized support vector machine classifier and the results attained in terms of precision, sensitivity, f-score, and accuracy. The above-said methodologies will enable farmers all over the world to take early action to prevent their crops from becoming irreversibly damaged, thereby saving the world and themselves from a potential economic crisis. The second part of the methodology starts with the preprocessing of data set images, and their texture and color features are extracted by histogram of oriented gradient (HoG), GLCM, and color moments. Here, the three types of features, that is, color, texture, and deep features, are combined to form hybrid features. The binary particle swarm optimization is applied for the selection of these hybrid features followed by the classification with random forest classifier to get the simulation results. Binary particle swarm optimization plays a crucial role in hybrid feature selection; the purpose of this Algorithm is to obtain the suitable output with the least features. The comparative analysis of both techniques is presented with the use of the above-mentioned evaluation parameters.

22 September 2006
Verified
Conference Paper
Closed access
HSHimanshu Dutt Sharma
Himanshu Dutt Sharma
NUN. UmaShankar
N. UmaShankar
An intelligent controller is developed for stabilizing an autonomous bicycle system. The autonomous bicycle is stabilized by controlling its lean alone. The controller is developed using fuzzy logic approach wherein the rule set is designed using the inherent-characteristic relationship of lean and steer present in a bicycle. The Newtonian mechanics based bicycle model along with the controller is simulated in Matlab. The controller is simulated to actuate at constant time intervals and the simulation results confirm that the controller effort successfully stabilizes the bicycle in unstable velocity regions

1 January 2014
Verified
Conference Paper
Closed access
GNGaurav Singh Naruka
Gaurav Singh Naruka
NJNiharika Jha
Niharika Jha
HSHimanshu Dutt Sharma
Himanshu Dutt Sharma
A linear standing wave ultrasonic motor driven Nano Positioning System with resolution 100nm requires model identification and robust controller design from its time domain data for application in high speed micromanufacturing system. From the time domain data acquired during experiments and iterative model estimations three best are chosen for controller design. Instrumental Variable method is used for model identification giving fitting accuracy in the range of 94%. Using this estimation internal model control (IMC) and Robust response time controllers have been designed. Using different methods and model transfer functions 12 sets of controllers have been designed and tested on the set up. The most optimum controller show rise time (ms), settling time (ms) and overshoot (%) in range of [1.2, 1.6, 0] respectively. which is significantly above the factory setting controller performance i.e improvement by 80% in rise time and 25% in settling time. Detail analysis of various system models and controller combination have been conducted. MATLAB® simulation testing is used for estimation and primary validation of models and controllers whereas final validation is achieved by implementing the designed controllers on the Nano Positioning System using PIMikroMove® software.