A5077181104- Smart Agriculture and AI
- Remote-Sensing Image Classification
- Vehicle Dynamics and Control Systems
- IoT and Edge/Fog Computing
- Real-time simulation and control systems
- Iterative Learning Control Systems
- Robotics and Automated Systems
- Advanced Surface Polishing Techniques
- Advanced MEMS and NEMS Technologies
- Robotic Path Planning Algorithms
- Artificial Intelligence in Healthcare
- Spectroscopy and Chemometric Analyses
- Piezoelectric Actuators and Control
- Advanced machining processes and optimization
- Fuzzy Logic and Control Systems
- Neural Networks and Applications
- Advanced Image Fusion Techniques
- Internet of Things and AI
- Robotic Locomotion and Control
- Remote Sensing in Agriculture
- Force Microscopy Techniques and Applications
- Leaf Properties and Growth Measurement
- Visual Attention and Saliency Detection
- VLSI and FPGA Design Techniques
- Nanofabrication and Lithography Techniques
Massachusetts Institute of Technology
2024
Karnavati University
2024
Toronto Metropolitan University
2024
eHealth Africa
2024
GLA University
2023
Birla Institute of Technology and Science, Pilani
2008-2022
Council of Scientific and Industrial Research
2009-2021
Central Electronics Engineering Research Institute
2006-2021
Stony Brook University
2016-2020
Universidad del Noreste
2020
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 naked eye for disease, but this method is imprecise can take long time. In study, we use artificial intelligence computer vision techniques to achieve goal designing developing an intelligent classification mechanism leaf diseases. This paper follows two methodologies their simulation outcomes compared performance...
According to recent survey by WHO organisation 17.5 million people dead each year. It will increase 75 in the year 2030[1].Medical professionals working field of heart disease have their own limitation, they can predict chance attack up 67% accuracy[2], with current epidemic scenario doctors need a support system for more accurate prediction disease. Machine learning algorithm and deep opens new door opportunities precise predication attack. Paper provideslot information about state art...
This paper reviews the first challenge on spectral image reconstruction from RGB images, i.e., recovery of whole-scene hyperspectral (HS) information a 3-channel image. The was divided into 2 tracks: "Clean" track sought HS noiseless images obtained known response function (representing spectrally-calibrated camera) while "Real World" challenged participants to recover cubes JPEG-compressed generated by an unknown function. To facilitate challenge, BGU Hyperspectral Image Database [4]...
Sustainability aims to meet the demands of present generation as well improve quality life, develop economy, conserve resources, and protect environment for future generations. Additive manufacturing is one techniques achieve sustainability in manufacturing. Life cycle assessment a useful tool ensure viability applicability new technology assess whether it offers tangible benefits compared conventional methods. There hardly any comparative study on life widely used filament materials. This...
Hyperspectral cameras are used to preserve fine spectral details of scenes that not captured by traditional RGB comprehensively quantizes radiance in images. Spectral provide additional information improves the performance numerous image based analytic applications, but due high hyperspectral hardware cost and associated physical constraints, images easily available for further processing. Motivated deep learning various computer vision we propose a 2D convolution neural network 3D...
Vegetation cover mapping is an imperative task of monitoring the change in vegetation as it can help us meet sustenance requirements. In this study, we explore future potential multilayer Deep learning framework (DL) that comprises hybrid CNN's, for area DL a congenial state-of-art algorithm implementing image processing. This study proposes novel exploiting hybrids CNN's with Local binary pattern and GIST features. Every CNN fed disparate combination multi-spectral Sentinel 2 satellite...
Positive-unlabeled learning is often studied under the assumption that labeled positive sample drawn randomly from true distribution of positives. In many application domains, however, certain regions in support class-conditional are over-represented while others under-represented sample. Although this introduces problems all aspects positive-unlabeled learning, we begin to address challenge by focusing on estimation class priors, quantities central posterior probabilities and recovery...
M2M (machine-to-machine) communications are bringing new challenges in the cellular networks as billions of such devices will need to be supported but at a fraction cost today's smartphones. Analysis shows that while many these generate little data load on network, their control signaling and memory/CPU resource consumption due tunnel maintenance core could still significant. To address this scalability issue, we propose modified packet architecture for LTE called LTE-Xtend customizes...
An intelligent controller is developed for stabilizing an autonomous bicycle system. The stabilized by controlling its lean alone. using fuzzy logic approach wherein the rule set designed inherent-characteristic relationship of and steer present in a bicycle. Newtonian mechanics based model along with simulated MATLAB. to actuate at constant time intervals simulation results confirm that effort successfully stabilizes unstable velocity regions.
Timely analysis and recognition of leaf diseases in plants ensures good quality productivity crops the field agriculture. Recognition rice is one biggest challenges for farmers due to incomplete awareness regarding latest sophisticated techniques disease identification. Much growth disturbed prevalence diseases. Earlier detection done manually by which very laborious time consuming. However, requisite automatic identification helps save their agricultural more efficiently. Innovations...
An autonomous bicycle system modeled with a passive rider is simulated in MATLAB-SIMULINK and the stabilizing phenomenon studied using simulation experiments. The model uses practical bicycle's data set, being used for experiment. It has been verified, variety of constraints on lean & steer that inherent stability better at high-speeds w.r.t. steering oscillations, low speeds high oscillations add to stabilize it. Also range velocities found which remains self-stable. intrinsic property...
The authors have applied robotics based approach in formulating the generalized dynamic equations of motion a bicycle system. developed model is considerably more comprehensive than any existing models. formulation considers system to be composed three rigid bodies connected by revolute joints. presented facilitates study various parameters namely- lean, steer, angular speed, lean-rate, steer- rate, lean-torque, steer-torque, speed-torque, inertial forces, coriolis and centrifugal gravity...
The authors present an adaptive neuro-fuzzy controller for stabilizing autonomous bicycle system. has been designed and verified using simulation experiments in MATLAB. found successful balancing system by running a generalized model under its control. results show that it balances the within lean values of plusmn2.5deg around equilibrium position.
This paper presents a modified dynamic bus arbiter architecture for system on chip design. A high performance SoC communication based probability distribution algorithm where all masters request are having same priority. However, the arbitration plays critical role in determining of system. When generate to access at time, manages situation using information about previously granted master, priority scheme and existing lottery scheme. method solves problem granting master more than one...
An on-line characterization system has been developed for DC motors working in Micromanufacturing applications. These sensitive applications require high precision and speed of response. The programmed on ARM microcontroller, it actuates motor automatically collects data while is being accelerated attains a steady ; the embedded routines process instantly returns current values inertia, friction coefficient, back-emf constant torque constant. A prototype control laboratory, characterized...
Modelling and analysis of actuation system is often a prerequisite for robotics design control. The premise this work involves mathematical modelling control systems decentralized systems. Two types two varying applications are considered the scope research. Hydraulic performed in modular independent approach robotic application. sample mechanism consists Winglet Cant with geometrically different parallel kinematic chains coupled together to same end-effector actuated using hydraulic...
The present study was carried out at the Research farm of Abhilashi University, Mandi (H.P) during summer season 2023. experiment laid in a randomized block design with three replications comprising seven treatments consisting different combinations organic manures and inorganic fertilizers to assess impact integrated nutrient management on growth, yield, soil economics okra crop. results revealed that treatment T7 [N: P: K (50%) + Farm Yard Manure (25%) Vermicompost (25%)] influenced all...
This work is belonging to K-means clustering algorithms classifier used with this algorithm classified data and Min Max normalization technique also enhance the results of over simply K- Means algorithm. a basically for discovering cluster within dataset. Here cancer dataset research in two categories – Cancer Non-Cancer, after execution implemented SVM Normalization technique. The initial point selection effects on algorithm, both number clusters found their centroids. In k-means methods...