Rakesh Ahuja

Rakesh Ahuja

Auto-generated profile, based on publicly available information

Rakesh Ahuja

Chitkara University

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

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

Representative Publications

View All Publications
6 January 2023 in Innovations in Systems and Software Engineering
Verified
Journal Article
Closed access
PDF file
RSRavi Kumar Sachdeva
Ravi Kumar Sachdeva
PBPriyanka Bathla
Priyanka Bathla
PRPooja Rani
Pooja Rani
VSVikas Solanki
Vikas Solanki
RARakesh Ahuja
Rakesh Ahuja

3 September 2021
Verified
Conference Paper
Closed access
PSPremananda Sahu
Premananda Sahu
SKSanjeev Kumar
Sanjeev Kumar
RARakesh Ahuja
Rakesh Ahuja
Amandeep kaurAmandeep kaur
Amandeep kaur
There is a rainy season occurs during the period from June to august in almost all geographical parts of India. Moreover, some of the states like Uttarakhand, Cherapunji, Mumbai, Tamil Nadu etc. may suffer from some natural disaster. If we early predict such misfortunes through the variety of big data collected for such distinct positions at a particular amount of time then certainly can save the life and goods from such big natural calamities. Such normalized data can be updated at a regular interval of time. In view of this, the time series data analysis provides a method to early aware and protects the life of people from such natural disasters. The proposed method exploited the use the Radial Basis Function Neural Network Model with back propagation algorithm to make compatible with time series data analysis to forecast the predication of rainfall for the state of Punjab, India. In this technique, two types of predictions are used which are based on fifteen and twenty days. The comparison results reveal those fifteen days prediction provides more effective classification accuracy than twenty days prediction.

1 May 2015
Verified
Conference Paper
Closed access
RARakesh Ahuja
Rakesh Ahuja
SBS S Bedi
S S Bedi
Video watermarking plays a key role in copyright protection domain of today's world. In the following paper, a blind watermarking algorithm is being proposed in which the watermark information is being embedded by little alteration of some of the value of DCT coefficients of luminance part of video during encoding it in MPEG-2 style. It is obvious that for any type of watermarking the three parameters, robustness, perceptibility and payload capacity must be simulated in order to provide better results. But unfortunately there is always a trade off among all these three parameters. But the proposed algorithm focused on one more issue, `elapsed time', a serious concern in video watermarking. The special care must be taken that how much time the system takes to embed the watermark. The algorithm is being tested also against several intentional and unintentional attacks to judge the robustness of this scheme. To maintain the perceptibility issue the value of threshold is manage in such a way that the quality of video must not being compromised during the embedding process. Therefore, the superiority of this algorithm is that our approach has covered three characteristics and evaluated better results as compared to the existing techniques proposed by other researchers.

3 September 2021
Verified
Conference Paper
Closed access
VLVikas Lamba
Vikas Lamba
SHSusheela Hooda
Susheela Hooda
RARakesh Ahuja
Rakesh Ahuja
Amandeep kaurAmandeep kaur
Amandeep kaur
Agriculture crop prediction is a challenging and interesting problem domain for the computer community. The computer machine helps to improve the productivity of the crop with such predication. This paper illustrates a research model which provides the predications of the wheat crop in the Rajasthan region of India. This paper uses feedforward neural network models to accomplish the task of predication for the wheat crop. These models are trained with three different feedforward neural network architectures namely multi-layer perception feedforward generalized regression and radial basis neural network. There is feature scaling method was used for normalization of large previous year's crop detail data which has been obtained by agriculture department of Rajasthan government. The simulation results indicate the better prediction with 97.75 % accuracy found by the feedforward neural network model trained with backpropagation learning rule in comparison to Generalized regression neural network and Radial basis neural network.

8 November 2015 in International Journal of Image, Graphics and Signal Processing
Verified
Journal Article
Open access
PDF file
RARakesh Ahuja
Rakesh Ahuja
SBS. S. Bedi
S. S. Bedi

6 November 2020
Verified
Conference Paper
Closed access
RARakesh Ahuja
Rakesh Ahuja
MSManish Sharma
Manish Sharma
MHMohd Junedul Haque
Mohd Junedul Haque
The paper described a new MPEG-2 compressed domain based imperceptible, blind, robust, and secure digital video watermarking method. The scheme exploited the intra coding part of MPEG compression algorithm for inserting the watermark image as copyright information. Three cryptographic keys are used to extract the watermark. This process further enhances the security of overall watermarking algorithm. Therefore, proper extraction would never possible without negotiating the unique keys. The strength of the proposed algorithm evaluated the robustness by applying wide variety of frame-based attacks to measure grading of resemblance and divergence between the extracted and original watermark respectively. The dominance of the projected technique is to obtain the admirable result for robustness and perceptibility both. The perceptibility is maintained as the scheme doesn't require to change the motion vectors resultant from DPCM process while encoding the video through MPEG-2 compression standard.