Seema
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Seema has a total of 10 co-authors. Here are the top co-authors by number of shared publications:
Sudakar Singh Chauhan
ECE Department, Guru Ghasidas Vishwavidyalaya, Bilaspur, India
3 shared publications- Sudakar Singh Chauhan
Department of Electronics & Communication Engineering, National Institute of Technology, Kurukshetra, India
3 shared publications - Aparna N. Mahajan
Maharaja Agrasen University
2 shared publications - Dimple Saproo
Maharaja Agrasen University, Baddi, Himachal Pradesh, 173205, India
2 shared publications Dimple Saproo
ECE Department, Dronacharya College of Engineering, Gurugram, India
1 shared publication- Niranjan Yadav
Department of Electronics and Communication Engineering, Deenbandhu Chhotu Ram University of Science and Technology Murthal, Sonepat, India
1 shared publication
Latest Publications
- 18 July 2025
- Published by Springer Nature in Silicon
- Vol. 17 (12) , 2729-2770
Advancements in Tunnel Field-Effect Transistors: Material Innovations, Emerging Applications and Future Perspectives
- 18 July 2025
- Published by Springer Nature in Silicon
- Vol. 17 (12) , 2729-2770
Advancements in Tunnel Field-Effect Transistors: Material Innovations, Emerging Applications and Future Perspectives
- Open Access
- 3 April 2025
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 15 (2) , 21475-21481
Deep Feature Extraction and Classification of Diabetic Retinopathy Images using a Hybrid Approach
Hybrid approaches have improved sensitivity, accuracy, and specificity in Diabetic Retinopathy (DR) classification. Deep feature sets provide a more holistic analysis of the retinal images, resulting in better detection of premature signs of DR. Hybrid strategies for classifying DR images combine the strengths of extracted deep features using pre-trained networks and Machine Learning (ML)-based classifiers to improve classification accuracy, robustness, and efficiency. Perfect pre-trained networks VGG19, ResNet101, and Shuffle Net were considered in this work. The networks were trained using a transfer learning approach, the pre-trained networks were chosen according to their classification accuracy in conjunction with the Softmax layer. Enhanced characteristics were extracted from the pre-trained networks' last layer and were fed to the machine learning-based classifier. The feature reduction and selection methods are essential for accomplishing the desired classification accuracy. ML-based kNN classifier was used to classify DR and a PCA-based feature reduction approach was utilized to obtain optimized deep feature sets. The extensive experiments revealed that ResNet101-based deep feature extraction and the kNN classifier delivered enhanced classification accuracy. It is concluded that combining deep features and the ML-based classifier employing a hybrid method enhances accuracy, robustness, and efficiency. The hybrid approach is a powerful tool for the premature identification of DR abnormalities. The PCA-kNN classification algorithm, which employs features obtained from the ResNet101, attained a peak classification accuracy of 98.9%.
- 3 April 2025
- Published by Engineering, Technology & Applied Science Research in Engineering, Technology & Applied Science Research
- Vol. 15 (2) , 21475-21481
Open AccessDeep Feature Extraction and Classification of Diabetic Retinopathy Images using a Hybrid Approach
Hybrid approaches have improved sensitivity, accuracy, and specificity in Diabetic Retinopathy (DR) classification. Deep feature sets provide a more holistic analysis of the retinal images, resulting in better detection of premature signs of DR. Hybrid strategies for classifying DR images combine the strengths of extracted deep features using pre-trained networks and Machine Learning (ML)-based classifiers to improve classification accuracy, robustness, and efficiency. Perfect pre-trained networks VGG19, ResNet101, and Shuffle Net were considered in this work. The networks were trained using a transfer learning approach, the pre-trained networks were chosen according to their classification accuracy in conjunction with the Softmax layer. Enhanced characteristics were extracted from the pre-trained networks' last layer and were fed to the machine learning-based classifier. The feature reduction and selection methods are essential for accomplishing the desired classification accuracy. ML-based kNN classifier was used to classify DR and a PCA-based feature reduction approach was utilized to obtain optimized deep feature sets. The extensive experiments revealed that ResNet101-based deep feature extraction and the kNN classifier delivered enhanced classification accuracy. It is concluded that combining deep features and the ML-based classifier employing a hybrid method enhances accuracy, robustness, and efficiency. The hybrid approach is a powerful tool for the premature identification of DR abnormalities. The PCA-kNN classification algorithm, which employs features obtained from the ResNet101, attained a peak classification accuracy of 98.9%.
- 20 September 2024
- Published by Springer Nature in Journal of Diabetes & Metabolic Disorders
- Vol. 23 (2) , 2289-2314
Deep learning based binary classification of diabetic retinopathy images using transfer learning approach
Objective Diabetic retinopathy (DR) is a common problem of diabetes, and it is the cause of blindness worldwide. Detection of diabetic radiology disease in the early detection stage is crucial for preventing vision loss. In this work, a deep learning-based binary classification of DR images has been proposed to classify DR images into healthy and unhealthy. Transfer learning-based 20 pre-trained networks have been fine-tuned using a robust dataset of diabetic radiology images. The combined dataset has been collected from three robust databases of diabetic patients annotated by experienced ophthalmologists indicating healthy or non-healthy diabetic retina images. Method This work has improved robust models by pre-processing the DR images by applying a denoising algorithm, normalization, and data augmentation. In this work, three rubout datasets of diabetic retinopathy images have been selected, named DRD- EyePACS, IDRiD, and APTOS-2019, for the extensive experiments, and a combined diabetic retinopathy image dataset has been generated for the exhaustive experiments. The datasets have been divided into training, testing, and validation sets, and the models use classification accuracy, sensitivity, specificity, precision, F1-score, and ROC-AUC to assess the model's efficiency for evaluating network performance. The present work has selected 20 different pre-trained networks based on three categories: Series, DAG, and lightweight. Results This study uses pre-processed data augmentation and normalization of data to solve overfitting problems. From the exhaustive experiments, the three best pre-trained have been selected based on the best classification accuracy from each category. It is concluded that the trained model ResNet101 based on the DAG category effectively identifies diabetic retinopathy disease accurately from radiological images from all cases. It is noted that 97.33% accuracy has been achieved using ResNet101 in the category of DAG network. Conclusion Based on the experiment results, the proposed model ResNet101 helps healthcare professionals detect retina diseases early and provides practical solutions to diabetes patients. It also gives patients and experts a second opinion for early detection of diabetic retinopathy.
- 20 September 2024
- Published by Springer Nature in Journal of Diabetes & Metabolic Disorders
- Vol. 23 (2) , 2289-2314
Deep learning based binary classification of diabetic retinopathy images using transfer learning approach
Objective Diabetic retinopathy (DR) is a common problem of diabetes, and it is the cause of blindness worldwide. Detection of diabetic radiology disease in the early detection stage is crucial for preventing vision loss. In this work, a deep learning-based binary classification of DR images has been proposed to classify DR images into healthy and unhealthy. Transfer learning-based 20 pre-trained networks have been fine-tuned using a robust dataset of diabetic radiology images. The combined dataset has been collected from three robust databases of diabetic patients annotated by experienced ophthalmologists indicating healthy or non-healthy diabetic retina images. Method This work has improved robust models by pre-processing the DR images by applying a denoising algorithm, normalization, and data augmentation. In this work, three rubout datasets of diabetic retinopathy images have been selected, named DRD- EyePACS, IDRiD, and APTOS-2019, for the extensive experiments, and a combined diabetic retinopathy image dataset has been generated for the exhaustive experiments. The datasets have been divided into training, testing, and validation sets, and the models use classification accuracy, sensitivity, specificity, precision, F1-score, and ROC-AUC to assess the model's efficiency for evaluating network performance. The present work has selected 20 different pre-trained networks based on three categories: Series, DAG, and lightweight. Results This study uses pre-processed data augmentation and normalization of data to solve overfitting problems. From the exhaustive experiments, the three best pre-trained have been selected based on the best classification accuracy from each category. It is concluded that the trained model ResNet101 based on the DAG category effectively identifies diabetic retinopathy disease accurately from radiological images from all cases. It is noted that 97.33% accuracy has been achieved using ResNet101 in the category of DAG network. Conclusion Based on the experiment results, the proposed model ResNet101 helps healthcare professionals detect retina diseases early and provides practical solutions to diabetes patients. It also gives patients and experts a second opinion for early detection of diabetic retinopathy.
- 6 July 2023
- Published by Springer Nature
- p. 19-28
Performance Analysis of Hetero-Dielectric Buried Oxide Double Gate Vertical TFET
- 6 July 2023
- Published by Springer Nature
- p. 19-28
Performance Analysis of Hetero-Dielectric Buried Oxide Double Gate Vertical TFET
- 21 May 2020
- Published by Springer Nature in Silicon
- Vol. 13 (4) , 1121-1125
Linearity Performance Analysis of Double Gate (DG) VTFET Using HDB for RF Applications
- 21 May 2020
- Published by Springer Nature in Silicon
- Vol. 13 (4) , 1121-1125
Linearity Performance Analysis of Double Gate (DG) VTFET Using HDB for RF Applications
- Open Access
- 15 October 2019
- Published by Institution of Engineering and Technology (IET) in IET Circuits, Devices & Systems
- Vol. 13 (7) , 1027-1031
Performance investigation of electrode work‐function engineered hetero‐dielectric buried oxide vertical TFET
For enhancement of and in tunnel field‐effect transistors (TFETs), it is important to choose novel materials and structures. Here, the authors design a hetero‐dielectric buried oxide vertical TFET (HDB VTFET) and its device characteristics has been investigated. This proposed device reveals the tremendous improvement in terms of sub‐threshold slope, drain‐induced barrier lowering, on‐current and suppresses the ambipolar behaviour up to V gs = −1.0 V by maintaining very low off‐current. Hence, the concept of hetero‐dielectric buried oxide (BOX) and two metal electrodes having different work‐functions are used here to obtain better results in terms of the current driving capability, steep subthreshold slope (SS) and drain‐induced barrier lowering (DIBL). This device is a promising candidate for low‐power consumption applications.
- 15 October 2019
- Published by Institution of Engineering and Technology (IET) in IET Circuits, Devices & Systems
- Vol. 13 (7) , 1027-1031
Open AccessPerformance investigation of electrode work‐function engineered hetero‐dielectric buried oxide vertical TFET
For enhancement of and in tunnel field‐effect transistors (TFETs), it is important to choose novel materials and structures. Here, the authors design a hetero‐dielectric buried oxide vertical TFET (HDB VTFET) and its device characteristics has been investigated. This proposed device reveals the tremendous improvement in terms of sub‐threshold slope, drain‐induced barrier lowering, on‐current and suppresses the ambipolar behaviour up to V gs = −1.0 V by maintaining very low off‐current. Hence, the concept of hetero‐dielectric buried oxide (BOX) and two metal electrodes having different work‐functions are used here to obtain better results in terms of the current driving capability, steep subthreshold slope (SS) and drain‐induced barrier lowering (DIBL). This device is a promising candidate for low‐power consumption applications.
- Open Access
- 16 January 2019
- Published by Institution of Engineering and Technology (IET) in Micro & Nano Letters
- Vol. 14 (1) , 17-21
Investigation of RF and linearity performance of electrode work‐function engineered HDB vertical TFET
This work realises a hetero‐dielectric buried oxide vertical tunnel field effect transistor (HDB VTFET) and investigates its radio frequency (RF) and linearity characteristics. First time, the concept of hetero‐dielectric buried oxide (BOX) in VTFET is used to obtain the superior improvement in terms of different RF and linearity figure of merits such as , , , , Gain Bandwidth Product (GBP), , Transconductance Frequency Product (TFP), Transconductance Generation Factor (TGF), , , , , , and 1‐dB compression point. Also, the influence of HfO 2 BOX length scaling on these FOMs is analysed. The results reveal that the HDB VTFET can be a promising contender to replace bulk metal‐oxide semiconductor field‐effect transistors in analogue/mixed signal system‐on‐chip and high‐frequency microwave applications and the accuracy of this device is validated by TCAD Sentaurus simulator.
- 16 January 2019
- Published by Institution of Engineering and Technology (IET) in Micro & Nano Letters
- Vol. 14 (1) , 17-21
Open AccessInvestigation of RF and linearity performance of electrode work‐function engineered HDB vertical TFET
This work realises a hetero‐dielectric buried oxide vertical tunnel field effect transistor (HDB VTFET) and investigates its radio frequency (RF) and linearity characteristics. First time, the concept of hetero‐dielectric buried oxide (BOX) in VTFET is used to obtain the superior improvement in terms of different RF and linearity figure of merits such as , , , , Gain Bandwidth Product (GBP), , Transconductance Frequency Product (TFP), Transconductance Generation Factor (TGF), , , , , , and 1‐dB compression point. Also, the influence of HfO 2 BOX length scaling on these FOMs is analysed. The results reveal that the HDB VTFET can be a promising contender to replace bulk metal‐oxide semiconductor field‐effect transistors in analogue/mixed signal system‐on‐chip and high‐frequency microwave applications and the accuracy of this device is validated by TCAD Sentaurus simulator.
- 1 October 2018
- Published by Elsevier in Superlattices and Microstructures
- Vol. 122, 286-295
A new design approach to improve DC, analog/RF and linearity metrics of Vertical TFET for RFIC design
- 1 October 2018
- Published by Elsevier in Superlattices and Microstructures
- Vol. 122, 286-295
A new design approach to improve DC, analog/RF and linearity metrics of Vertical TFET for RFIC design
- 1 May 2018
- Published by Elsevier in Superlattices and Microstructures
- Vol. 117, 1-8
Design of double gate vertical tunnel field effect transistor using HDB and its performance estimation
- 1 May 2018
- Published by Elsevier in Superlattices and Microstructures
- Vol. 117, 1-8
Design of double gate vertical tunnel field effect transistor using HDB and its performance estimation