A5101849333- Speech and Audio Processing
- Advanced Adaptive Filtering Techniques
- Blind Source Separation Techniques
- Image and Signal Denoising Methods
- Acoustic Wave Phenomena Research
- ECG Monitoring and Analysis
- Digital Filter Design and Implementation
- Artificial Intelligence in Games
- Video Analysis and Summarization
- Reinforcement Learning in Robotics
- Sensor Technology and Measurement Systems
- Vehicular Ad Hoc Networks (VANETs)
- Advanced Vision and Imaging
- Advanced Software Engineering Methodologies
- Music and Audio Processing
- Wireless Communication Networks Research
- Model-Driven Software Engineering Techniques
- Digital Games and Media
- Software System Performance and Reliability
- Geotechnical Engineering and Soil Stabilization
- Data Stream Mining Techniques
- Online Learning and Analytics
- Advanced Wireless Communication Techniques
- Software Engineering Research
- Advanced Electrical Measurement Techniques
Institute of Management Technology
2022-2024
Birla Institute of Technology, Mesra
2014-2020
Indira Gandhi Delhi Technical University for Women
2019
A research is an intellectual system, the vehicular adhoc network (VANET), supplies cars in with critical information. Over 150,000 individuals are impacted by traffic accidents that must be kept to a minimum, and development of safety included VANET. Traffic congestion prediction mitigating car managing for benefit all road users. The system exhibit dynamic behavior, which adversely affects performance deep learning approaches prediction. In this article hybrid approach named boosted long...
In recent times noise cancellation is a vital issue, as it responsible for reducing undesired disturbances in the process of communication. Active Noise Cancellation (ANC) most effective technique to cancel noise. ANC has been an active area research and various adaptive methodologies have employed achieve better scheme. technique, aim minimize interference that corrupts original signal. broad variety applications common commercial products, industrial uses other machinery. An analysis...
The priority of current era in noise cancellation field aims at blocking the low frequency since most real life noises operate below 1 KHz. which creates obstruction everyday communication needs to be dealt an effective way. Acoustic Noise Cancellation (ANC) is hence regarded as sought after solution. ANC has created its own niche this where a wide range industrial and commercial products rely unanimously for rescue. While traditional solutions like enclosures, barriers, etc. had...
A Lock-In Amplifier (LIA) is used to remove noise from an input signal by the use of a reference signal. Generally sampling rate LIAs much higher than required frequency in typical applications. Moreover hardware configuration better requirement. The signals are processed using high-end processors which increase cost LIA. This paper aims develop inexpensive and portable alternative for digital lock-in amplifier. will enable application remote locations distributed systems require multiple...
In real life situations, the statistical characteristics of signal and noise are generally unknown & hence a digital filter having 'constant coefficients' is hardly any use. such situations adaptive desirable. Adaptive filters capable adapting their coefficients as per abnormality in input to achieve free signal. This paper discusses comparative analysis various algorithms LMS (Least mean square), BLMS (Block LMS), NLMS (Normalized BNLMS NLMS), VSLMS (Variable step size LMS) BVSLMS VSLMS)...
Voice communication has today become an important and integral part of human kind. Today the speed quality is very crucial. Speech always been degraded due to end user devices. This kind a problem can be tackled effectively when efficient devices algorithms are used cancel echo which introduced into channel. With advent sophisticated technology low cost loudspeakers power amplifiers have devised bring in non-linearity These cheap such that it can't cancelled by conventional linear acoustic...
Software effort estimation is big and active research area. useful for time efforts required to perform a particular task. But, it very rare estimate the with high level of reliability. There are various approaches software application effort. In present paper, applications efforts, neutrosophic logic approach used. Neutrosophic mathematical model ambiguity, uncertainty, incompleteness, vagueness, redundancy, contradiction inconsistency in data. It extension fuzzy logic. capable handling...
Monaural speech separation has remained a very challenging problem for longtime which can be addressed using supervised learning approach that uses features of the noisy input to predict an accurate time-frequency mask. Effective acoustic phonetic help in mask prediction at low Signal-to-Noise Ratios (SNRs). Individual capture specific attributes audio signal; therefore, it's essential employ set features. This work examines different combinations monaural as and ideal ratio straining target...
This paper presents a number of novel approaches to help facilitate Deep Reinforcement Learning (DRL) for Neural Networks based agents in the domain General Video Game Playing (GVGP). Using common processing methods, NN can retain fixed predetermined input and output shape while having flexibility play variety games. Training also be made more efficient via reward normalization. Our results show that these modifications negligibly impact learning time performance model when testedupon games...