A5100629090- Topic Modeling
- Speech and dialogue systems
- Artificial Intelligence in Education
- Network Security and Intrusion Detection
- Text and Document Classification Technologies
- Handwritten Text Recognition Techniques
- Natural Language Processing Techniques
- Neural Networks and Applications
- Remote-Sensing Image Classification
- Engineering Applied Research
- Internet Traffic Analysis and Secure E-voting
- Rough Sets and Fuzzy Logic
- Data Management and Algorithms
- Smart Systems and Machine Learning
- Spectroscopy and Chemometric Analyses
- Metal Alloys Wear and Properties
- Artificial Intelligence in Healthcare
- Video Surveillance and Tracking Methods
- Imbalanced Data Classification Techniques
- Anomaly Detection Techniques and Applications
- Impact of Light on Environment and Health
- Metallurgy and Material Forming
- IoT-based Smart Home Systems
- Vehicle License Plate Recognition
- Multimodal Machine Learning Applications
Tata Steel (India)
2024
Intel (India)
2024
Samsung (India)
2021
Tata Consultancy Services (India)
2013
Indian Institute of Information Technology Allahabad
2006
Detecting DoS attacks and other malicious activities in wireless networks is crucial for cybersecurity. The challenge arises due to the unlabeled nature of majority available network data, mainly because high volume diverse data streams from numerous sensors. complex temporal correlation patterns highly varying signatures pose a significant timeseries-based anomalies intrusion detection systems. Additionally, evolving dynamically changing attack lead zero-day (new, unknown threats). rarity...
Optical Character Recognition (OCR) is one of the challenging areas in domain image processing, where handwritten or printed characters are digitized by using an optical scanner.The then analyzed broadly two methods -(i) matrix space analysis method and (ii) feature method.Matrix takes more memory time, compared to analysis.However, it works fine for scripts which strokes prominent, e.g.English numeric scripts.On other hand, useful complex having similarity between letters its writing...
These days' multi-intent utterances have become very important for the spoken language understanding (SLU). The systems and algorithms add more complexity (Compare to single-intent-based system) SLU. As, it requires an accurate system, which can identify intents slots at fine-grain (i.e., word/token) level also able handle relation between locally utterance level. In this case, may belong multiple domains different classes. Similarly, classes, of same class be related intent Unfortunately,...
Abstract: This paper describes the major work carried out in study & analyzing critical reasons for failure of mill stand drive gearboxes that had occurred New Bar Mill (Rebar Mill) past 5 years. Suggest improvement measures and maintenance guidelines to decrease probability hence develop an action plan reliability gearboxes. In process, on basics gearbox rolling process has been done. Present production data analysis done actual load condition. Based present data, current running...
Chickens are social animals that prefer to be in the company of their flock during day and seek shelter at night. Providing them with a safe comfortable coop is essential for well-being, but managing door can tedious task, especially changing seasons when light conditions vary. Automating opening based on simplify this save time effort, ensure your chickens have access fresh air sunlight nesting place In work, chicken will solved. The device consist main microcontroller handle all...
In Spoken Language Understanding (SLU), the ability to detect out-of-domain (OOD) input dialog plays a very important role (e.g., voice assistance and chatbot systems). However, most of existing OOD detection methods rely heavily on manually labeled OOD. Manual labeling data for dynamically changing evolving area is time-consuming not immediately possible. It limits feasibility these models in practical applications. So, solve this problem, we are considering scenario having no (i.e.,...