Roop Singh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Roop Singh has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
Harendra Singh
Assistant Professor, G. L. Bajaj Institute of Technology and Management, Greater Noida, India
2 shared publicationsPavan Kumar Shukla
School of Engineering and Technology, CGC University, Mohali, India
2 shared publicationsAlaknanda Ashok
Dean College of Technology, G. B. Pant University of Agriculture and Technology, Pantnagar, Uttarakhand, India
1 shared publication- Alaknanda Ashok
Dean College of Technology, GB Pant University of Agriculture and Technology, Pantnagar, India
1 shared publication Anil Singh
Associate Professor, Arni University, Kathgarh Indora Himachal Pradesh, India
1 shared publication- Idris Ismail
Universiti Teknologi PETRONAS
1 shared publication
Latest Publications
- Open Access
- 30 September 2026
- Published by FOREX Publication in International Journal of Electrical and Electronics Research
- Vol. 14 (3) , 668-675
Robust Digital Watermarking for Multimedia Content Authentication in DWT-DCT Domain
Most of the existing single domain Watermarking schemes suffer with security of multimedia content. To address this limitation, a hybrid watermarking framework integrating DWT and DCT transforms is introduced in this study. The proposed approach initially applies the Arnold transform to the color cover image to strengthen data security through image scrambling. Subsequently, the encrypted image is decomposed using a single-level discrete wavelet transform (DWT), where the selected sub-bands (𝐿𝐿1 and 𝐻𝐻1) are utilized for further watermark embedding operations. To achieve a balanced trade-off between visual quality and robustness, the chosen sub-bands are partitioned into 8×8 blocks and transformed using the discrete cosine transform (DCT). Finally, the watermark logo is embedded into the mid-frequency DCT coefficients, resulting in the generation of a secure and imperceptible watermarked image. The performance is measured on SIPI dataset in terms of PSNR, SSIM, NC. The experimental finds demonstrate that the presented method outperforms with the existing relevant schemes.
- 30 September 2026
- Published by FOREX Publication in International Journal of Electrical and Electronics Research
- Vol. 14 (3) , 668-675
Open AccessRobust Digital Watermarking for Multimedia Content Authentication in DWT-DCT Domain
Most of the existing single domain Watermarking schemes suffer with security of multimedia content. To address this limitation, a hybrid watermarking framework integrating DWT and DCT transforms is introduced in this study. The proposed approach initially applies the Arnold transform to the color cover image to strengthen data security through image scrambling. Subsequently, the encrypted image is decomposed using a single-level discrete wavelet transform (DWT), where the selected sub-bands (𝐿𝐿1 and 𝐻𝐻1) are utilized for further watermark embedding operations. To achieve a balanced trade-off between visual quality and robustness, the chosen sub-bands are partitioned into 8×8 blocks and transformed using the discrete cosine transform (DCT). Finally, the watermark logo is embedded into the mid-frequency DCT coefficients, resulting in the generation of a secure and imperceptible watermarked image. The performance is measured on SIPI dataset in terms of PSNR, SSIM, NC. The experimental finds demonstrate that the presented method outperforms with the existing relevant schemes.
- Open Access
- 28 September 2023
- Published by FOREX Publication in International Journal of Electrical and Electronics Research
- Vol. 11 (3) , 859-865
Robust medical image watermarking in frequency domain
Protecting patient information in medical image watermarking poses a significant challenge, especially when traditional methods like the Arnold transform prove inadequate in ensuring security. This paper introduces a novel approach within the Discrete Wavelet Transform (DWT) domain to address this issue effectively. By employing the Advanced Encryption Standard (AES), the security and robustness of the system are greatly enhanced through the encryption of both the medical image and patient data. The encrypted medical image undergoes a 2-level DWT process, allowing the concealment of encrypted patient information while maintaining its invisibility. This proposed scheme surpasses others in experimental evaluations, as evidenced by metrics such as PSNR and NC, solidifying its position as a more secure choice for medical image watermarking. The results validate the scheme’s robustness and imperceptibility.
- 28 September 2023
- Published by FOREX Publication in International Journal of Electrical and Electronics Research
- Vol. 11 (3) , 859-865
Open AccessRobust medical image watermarking in frequency domain
Protecting patient information in medical image watermarking poses a significant challenge, especially when traditional methods like the Arnold transform prove inadequate in ensuring security. This paper introduces a novel approach within the Discrete Wavelet Transform (DWT) domain to address this issue effectively. By employing the Advanced Encryption Standard (AES), the security and robustness of the system are greatly enhanced through the encryption of both the medical image and patient data. The encrypted medical image undergoes a 2-level DWT process, allowing the concealment of encrypted patient information while maintaining its invisibility. This proposed scheme surpasses others in experimental evaluations, as evidenced by metrics such as PSNR and NC, solidifying its position as a more secure choice for medical image watermarking. The results validate the scheme’s robustness and imperceptibility.
- Open Access
- 9 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 59297-59316
Clinical Errors From Acronym Use in Electronic Health Record: A Review of NLP-Based Disambiguation Techniques
The adoption of Electronic Health Record (EHR) and other e-health infrastructures over the years has been characterized by an increase in medical errors. This is primarily a result of the widespread usage of medical acronyms and abbreviations with multiple possible senses (i.e., ambiguous). Artificial Intelligence (AI) technology, particularly Natural Language Processing (NLP), has emerged as a promising solution for addressing the challenge of automatic sense resolution in acronyms. Machine learning (ML) techniques have been utilized efficiently in the development of such systems, gaining increasing attention in recent years. Nevertheless, there is a scarcity of comprehensive studies that investigate the global adoption of Electronic Health Records (EHR), analyze the impact of acronyms usage on medical errors in EHR, and report on the latest trends and advancements in ML-based NLP solutions to disambiguate acronyms in medical practice. In the current study, we present a detailed overview on medical error, its origins, unintended effects, and EHR-related errors as a subclass of clinical error. This study also investigates the adoption of EHR systems in developed and developing nations, and the review concludes with an examination of various artificial intelligence techniques, particularly machine learning algorithms for medical acronym and abbreviation disambiguation in EHRs.
- 9 June 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 11, 59297-59316
Open AccessClinical Errors From Acronym Use in Electronic Health Record: A Review of NLP-Based Disambiguation Techniques
The adoption of Electronic Health Record (EHR) and other e-health infrastructures over the years has been characterized by an increase in medical errors. This is primarily a result of the widespread usage of medical acronyms and abbreviations with multiple possible senses (i.e., ambiguous). Artificial Intelligence (AI) technology, particularly Natural Language Processing (NLP), has emerged as a promising solution for addressing the challenge of automatic sense resolution in acronyms. Machine learning (ML) techniques have been utilized efficiently in the development of such systems, gaining increasing attention in recent years. Nevertheless, there is a scarcity of comprehensive studies that investigate the global adoption of Electronic Health Records (EHR), analyze the impact of acronyms usage on medical errors in EHR, and report on the latest trends and advancements in ML-based NLP solutions to disambiguate acronyms in medical practice. In the current study, we present a detailed overview on medical error, its origins, unintended effects, and EHR-related errors as a subclass of clinical error. This study also investigates the adoption of EHR systems in developed and developing nations, and the review concludes with an examination of various artificial intelligence techniques, particularly machine learning algorithms for medical acronym and abbreviation disambiguation in EHRs.
- 5 July 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (3) , 3397-3432
High embedding capacity based color image watermarking scheme using SBBO in RDWT domain
- 5 July 2022
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (3) , 3397-3432
High embedding capacity based color image watermarking scheme using SBBO in RDWT domain
- Open Access
- 30 June 2022
- Published by FOREX Publication in International Journal of Electrical and Electronics Research
- Vol. 10 (2) , 405-410
Automatic Framework for Vegetable Classification using Transfer-Learning
Globally, fresh vegetables are a crucial part of our lives and they provide most of the vitamins, minerals, and proteins, in short, every nutrition that a growing body need. They vary in colors like; red, green, and yellow but as our ancestors say that green vegetables are a must for every age. To identify the fresh vegetable that makes our body healthy and notion positive the proposed automatic multi-class vegetable classifier is used. In this paper, a framework based on a deep learning approach has been proposed for multi-class vegetable classification from scratch. The accuracy of the proposed model is further increased using the transfer-learning concept (DenseNet201). The whole process is divided into four modules; data collection and pre-processing, data splitting, CNN model training, and testing, and performance improvement using a pre-trained DenseNet201 network. Data augmentation and data shuffling are used to free from lack of data availability during the training phase of the model. The proposed framework is more efficient and can predict the type of vegetables comparatively in less computational time (2 to 3 minutes) with an ‘Accuracy’ of 98.58%, ‘Sensitivity’ of 98.23%, and ‘Specificity’ of 94.25%.
- 30 June 2022
- Published by FOREX Publication in International Journal of Electrical and Electronics Research
- Vol. 10 (2) , 405-410
Open AccessAutomatic Framework for Vegetable Classification using Transfer-Learning
Globally, fresh vegetables are a crucial part of our lives and they provide most of the vitamins, minerals, and proteins, in short, every nutrition that a growing body need. They vary in colors like; red, green, and yellow but as our ancestors say that green vegetables are a must for every age. To identify the fresh vegetable that makes our body healthy and notion positive the proposed automatic multi-class vegetable classifier is used. In this paper, a framework based on a deep learning approach has been proposed for multi-class vegetable classification from scratch. The accuracy of the proposed model is further increased using the transfer-learning concept (DenseNet201). The whole process is divided into four modules; data collection and pre-processing, data splitting, CNN model training, and testing, and performance improvement using a pre-trained DenseNet201 network. Data augmentation and data shuffling are used to free from lack of data availability during the training phase of the model. The proposed framework is more efficient and can predict the type of vegetables comparatively in less computational time (2 to 3 minutes) with an ‘Accuracy’ of 98.58%, ‘Sensitivity’ of 98.23%, and ‘Specificity’ of 94.25%.
- Open Access
- 13 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 52712-52723
Efficient Watermarking Method Based on Maximum Entropy Blocks Selection in Frequency Domain for Color Images
False-positive problem (FPP) is a one of the challenging tasks for the researchers. It authenticates the wrong owner to access the multimedia content. To overcome, the FPP problem, this paper introduces an efficient watermarking method based on the selection of highest entropy blocks. In this method, cover and watermark images are initially shuffled through Arnold transform. Then, the encrypted images are further processed by a 2-level discrete wavelet transform followed by singular value decomposition. The proposed method has been evaluated with geometrical, filtering, noise, and contrast adjustment attacks on the standard image datasets against five recently developed watermarking methods. The simulation results reveal that the proposed method outperforms the existing methods.
- 13 May 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 10, 52712-52723
Open AccessEfficient Watermarking Method Based on Maximum Entropy Blocks Selection in Frequency Domain for Color Images
False-positive problem (FPP) is a one of the challenging tasks for the researchers. It authenticates the wrong owner to access the multimedia content. To overcome, the FPP problem, this paper introduces an efficient watermarking method based on the selection of highest entropy blocks. In this method, cover and watermark images are initially shuffled through Arnold transform. Then, the encrypted images are further processed by a 2-level discrete wavelet transform followed by singular value decomposition. The proposed method has been evaluated with geometrical, filtering, noise, and contrast adjustment attacks on the standard image datasets against five recently developed watermarking methods. The simulation results reveal that the proposed method outperforms the existing methods.
- Open Access
- 30 June 2021
- Published by FOREX Publication in International Journal of Electrical and Electronics Research
- Vol. 9 (2) , 10-15
Classification & Feature extraction of Brain tumor from MRI Images using Modified ANN Approach
In this research paper, a new modified approach is proposed for brain tumor classification as well as feature extraction from Magnetic Resonance Imaging (MRI) after pre-processing of the images. The discrete wavelet transformation (DWT) technique is used for feature extraction from MRI images and Artificial Neural Network (ANN) is used for the classification of the type of tumor according to extracted features. Mean, Standard deviation, Variance, Entropy, Skewness, Homogeneity, Contrast, Correlation are the main features used to classify the type of tumor. The proposed model can give a better result in comparison with other available techniques in less computational time as well as a high degree of accuracy. The training and testing accuracies of the proposed model are 100% and 98.20% with a 98.70 % degree of precision respectively.
- 30 June 2021
- Published by FOREX Publication in International Journal of Electrical and Electronics Research
- Vol. 9 (2) , 10-15
Open AccessClassification & Feature extraction of Brain tumor from MRI Images using Modified ANN Approach
In this research paper, a new modified approach is proposed for brain tumor classification as well as feature extraction from Magnetic Resonance Imaging (MRI) after pre-processing of the images. The discrete wavelet transformation (DWT) technique is used for feature extraction from MRI images and Artificial Neural Network (ANN) is used for the classification of the type of tumor according to extracted features. Mean, Standard deviation, Variance, Entropy, Skewness, Homogeneity, Contrast, Correlation are the main features used to classify the type of tumor. The proposed model can give a better result in comparison with other available techniques in less computational time as well as a high degree of accuracy. The training and testing accuracies of the proposed model are 100% and 98.20% with a 98.70 % degree of precision respectively.