A5026299310- Information and Cyber Security
- Emotion and Mood Recognition
- Advanced Malware Detection Techniques
- Software Engineering Research
- Human Pose and Action Recognition
- Face and Expression Recognition
- Robotic Locomotion and Control
- Cryptography and Data Security
- Face recognition and analysis
- Sentiment Analysis and Opinion Mining
- Text and Document Classification Technologies
- IoT and Edge/Fog Computing
- Gait Recognition and Analysis
- Neural Networks and Applications
- Blockchain Technology Applications and Security
- Cloud Data Security Solutions
- Anomaly Detection Techniques and Applications
- Security and Verification in Computing
- Advanced Data Processing Techniques
- Hand Gesture Recognition Systems
- Web Data Mining and Analysis
- Multimodal Machine Learning Applications
- Service-Oriented Architecture and Web Services
- Context-Aware Activity Recognition Systems
- Speech and Audio Processing
Robert Bosch (India)
2024
Jaypee Institute of Information Technology
2019-2023
Indian Institute of Information Technology Allahabad
2018-2022
SRM Institute of Science and Technology
2021
Delhi Technological University
2013-2020
Hybrid Energy (Norway)
2018
Data from point prevalence surveys (PPSs) in India are scarce. Conducting PPSs is especially challenging the absence of electronic medical records, a lack dedicated resources and high patient load resource-poor settings. This multicentre survey was conducted to provide background data for planning strengthening antimicrobial stewardship programmes across country.This inpatient PPS over 2 weeks May 2019 simultaneously five study centres India. about characteristics, indications antimicrobials...
Regularization plays an important role in fine tuning the predictor design. In this research, we have investigated how Ll and L2 regularizations affect image features. We shown here contrasting effect of 'Ll' 'L2' on extracted features images using Restricted Boltzmann Machine, energy-based stochastic graphical technique for Classification. Through results, show that regularization produces feature with global receptive fields while highly local fields. Our findings been validated extensive...
Internet of Things is a network heterogeneous devices, which communicate over wireless networks and perform the task sensing actuation. IoT aims at connecting each every machine device to provide ubiquitous connectivity. In this scenario, security privacy information play vital role. work, research done in field categorized as per issue concerned. The proposed existing methods are reviewed. Based on survey, gap issues identified.
Gesture based communication with humanoid robots, especially using hand gestures has universal appeal and could make robots share home space in a social environment if the technology can be developed matured fashion. Till date conventional vision gesture recognition had poor success rate since engineered features failed to communicate semantics unambiguously, when is dynamic nature. This research proposes deep convolutional neural network technique that able estimate command direction...
A biped locomotion is an unstable behavior to perform because it based on inverted pendulum model. Maintaining the balance and stability a challenging task. Using numerical methods solve problem doesn't brings high level of in locomotion. Even when achieved, controlling dynamic walking becomes Here, we have proposed general walk trajectory generation robot using sinusoidal cubic spline function. Since our development analytical approach, synthesizing pattern much more convenient. Through...
For effective communication between two humans, one needs to understand the emotional state of its fellow beings. Predicting human emotion involves several factors, which include, but not limited to, facial expression. Many researches in this direction are based on features extracted from expressions. In paper we proposing a model, can predict by considering as well context information. Our model only extracts expressions also is aware background image dataset. We have shown relevance...
The researchers have been focusing on embedding security from the early phases of software development lifecycle. They researched and innovated a field Security Engineering where concerns are embedded during requirement, design, testing development. Efforts were made in developing methods, methodologies, tools to handle issues. Various methods present literature for eliciting, analyzing prioritizing requirements. During design phase based prioritized requirements, environment parameters...
Providing security to complex information system development is challenging because of network and ubiquitous system. Traditional mechanisms address concerns during or design phases that may lead various loopholes over-constrained The field engineering has emerged whereby requirements are gathered along with other the initial phase software development. However, dealing code unavailability. paper first represents proposals for based on different approaches such as use case approach,...
Recognizing human emotion is a complex task and being researched upon since couple of decades. The problem has still gained popularity because its need in various domains, when it comes to computer interaction or robot interaction. As per researchers, predict other persons state mind by observing parameters, 70% them non-verbal. Human have emotions embedded their speech, pose, gesture, context, facial expressions, even the past history conversation situation. These all sub problems can be...
To enable humanoid robots to share our social space we need develop technology for easy interaction with the using multiple modes such as speech, gestures and emotions them. We have targeted this research towards addressing core issue of emotion recognition problem which would require less computation resources much lesser number network hyperparameters will be more adaptive computed on low resourced real time communication. More specifically, here proposed an Inception module based...
Memes are a way of communicating concepts across social media. However, while most memes intended to be funny, some can turn into offensive as well when text and images combined together. Recently many successful studies related sentiment analysis both image have been performed. Such technology, developed successfully, useful for effective Human-Robot-Interactions, specially with humanoid collaborative robots. In this research, we intend first develop such technology available data set using...
Providing security to complex information system development is challenging because of network and ubiquitous system. Traditional mechanisms address concerns during or design phases that may lead various loopholes over-constrained The field engineering has emerged whereby requirements are gathered along with other the initial phase software development. However, dealing code unavailability. paper first represents proposals for based on different approaches such as use case approach,...
Bipedal walking in an unknown environment is extremely challenging problem due to its inherently unstable structure. For bipedal robots, so far, this has been tried using analytical methods with predefined sets of parameters, having limited success. Such robots could walk only a structured flat floor and other restrictions. This paper proposes such models learning ability be imparted the biped based on sequences. Two sequential network have configured, Gated Recurrent Unit (GRU) Long Short...