Bharat Singh
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Bharat Singh has a total of 51 co-authors. Here are the top co-authors by number of shared publications:
- Nidhi Kushwaha
Indian Institute of Information Technology
11 shared publications Larry S. Davis
University of Maryland College Park
6 shared publications- Mahyar Najibi
University of Maryland College Park
4 shared publications O P Vyas
Software Engineering Department, Indian Institute of Information Technology, Allahabad
3 shared publicationsOm Prakash Vyas
Indian Institute of Information Technology Allahabad, India 211012
3 shared publications- Gavin Taylor
United States Naval Academy
2 shared publications
Latest Publications
- 2 January 2026
- Published by Springer Nature
- p. 406-414
A Secure Federated Learning Framework for Decentralized ECG Classification on Heterogeneous Data
- 2 January 2026
- Published by Springer Nature
- p. 406-414
A Secure Federated Learning Framework for Decentralized ECG Classification on Heterogeneous Data
- 2 July 2025
- Published by Springer Nature
- p. 479-487
Exploiting Handcrafted and Deep Learning Techniques for Autistic Face Recognition
- 2 July 2025
- Published by Springer Nature
- p. 479-487
Exploiting Handcrafted and Deep Learning Techniques for Autistic Face Recognition
- 2 July 2025
- Published by Springer Nature
- p. 489-497
Artist Prediction of Painting Through Transfer Learning
- 2 July 2025
- Published by Springer Nature
- p. 489-497
Artist Prediction of Painting Through Transfer Learning
- 25 January 2025
- Published by Springer Nature
- p. 99-104
Weather Forecasting with Time Series Dataset Using Deep Learning Algorithms
- 25 January 2025
- Published by Springer Nature
- p. 99-104
Weather Forecasting with Time Series Dataset Using Deep Learning Algorithms
- 27 December 2024
- Published by Springer Nature
- p. 55-67
Examinations of Offline Signature Forgery Detection from Classical to Deep Learning Techniques
- 27 December 2024
- Published by Springer Nature
- p. 55-67
Examinations of Offline Signature Forgery Detection from Classical to Deep Learning Techniques
- Open Access
- 9 April 2024
- Published by European Alliance for Innovation n.o. in ICST Transactions on Scalable Information Systems
- Vol. 11 (6)
Manifesto of Deep Learning Architecture for Aspect Level Sentiment Analysis to extract customer criticism
Sentiment analysis, a critical task in natural language processing, aims to automatically identify and classify the sentiment expressed in textual data. Aspect-level sentiment analysis focuses on determining sentiment at a more granular level, targeting specific aspects or features within a piece of text. In this paper, we explore various techniques for sentiment analysis, including traditional machine learning approaches and state-of-the-art deep learning models. Additionally, deep learning techniques has been utilized to identifying and extracting specific aspects from text, addressing aspect-level ambiguity, and capturing nuanced sentiments for each aspect. These datasets are valuable for conducting aspect-level sentiment analysis. In this article, we explore a language model based on pre-trained deep neural networks. This model can analyze sequences of text to classify sentiments as positive, negative, or neutral without explicit human labeling. To evaluate these models, data from Twitter's US airlines sentiment database was utilized. Experiments on this dataset reveal that the BERT, RoBERTA and DistilBERT model outperforms than the ML based model in accuracy and is more efficient in terms of training time. Notably, our findings showcase significant advancements over previous state-of-the-art methods that rely on supervised feature learning, bridging existing gaps in sentiment analysis methodologies. Our findings shed light on the advancements and challenges in sentiment analysis, offering insights for future research directions and practical applications in areas such as customer feedback analysis, social media monitoring, and opinion mining.
- 9 April 2024
- Published by European Alliance for Innovation n.o. in ICST Transactions on Scalable Information Systems
- Vol. 11 (6)
Open AccessManifesto of Deep Learning Architecture for Aspect Level Sentiment Analysis to extract customer criticism
Sentiment analysis, a critical task in natural language processing, aims to automatically identify and classify the sentiment expressed in textual data. Aspect-level sentiment analysis focuses on determining sentiment at a more granular level, targeting specific aspects or features within a piece of text. In this paper, we explore various techniques for sentiment analysis, including traditional machine learning approaches and state-of-the-art deep learning models. Additionally, deep learning techniques has been utilized to identifying and extracting specific aspects from text, addressing aspect-level ambiguity, and capturing nuanced sentiments for each aspect. These datasets are valuable for conducting aspect-level sentiment analysis. In this article, we explore a language model based on pre-trained deep neural networks. This model can analyze sequences of text to classify sentiments as positive, negative, or neutral without explicit human labeling. To evaluate these models, data from Twitter's US airlines sentiment database was utilized. Experiments on this dataset reveal that the BERT, RoBERTA and DistilBERT model outperforms than the ML based model in accuracy and is more efficient in terms of training time. Notably, our findings showcase significant advancements over previous state-of-the-art methods that rely on supervised feature learning, bridging existing gaps in sentiment analysis methodologies. Our findings shed light on the advancements and challenges in sentiment analysis, offering insights for future research directions and practical applications in areas such as customer feedback analysis, social media monitoring, and opinion mining.
- 2 April 2024
- Published by Springer Nature
- p. 125-134
Exploiting Deep Learning Techniques for Autistic Face Recognition
- 2 April 2024
- Published by Springer Nature
- p. 125-134
Exploiting Deep Learning Techniques for Autistic Face Recognition
- 5 January 2024
- Published by Springer Nature
- p. 122-134
Aspect Level Sentiment Analysis to Extract Valuable Insight for Airline’s Customer Feedback and Reviews
- 5 January 2024
- Published by Springer Nature
- p. 122-134
Aspect Level Sentiment Analysis to Extract Valuable Insight for Airline’s Customer Feedback and Reviews
- 1 November 2023
- Published by Springer Nature
- p. 397-405
Prediction of Heart Disease with Machine Learning Methods: Comparison and Analysis
- 1 November 2023
- Published by Springer Nature
- p. 397-405
Prediction of Heart Disease with Machine Learning Methods: Comparison and Analysis
- 12 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 44 (01628828) , 1
Scale Normalized Image Pyramids with AutoFocus for Object Detection
We present an efficient foveal framework to perform object detection. A scale normalized image pyramid (SNIP) is generated that, like human vision, only attends to objects within a fixed size range at different scales. Such a restriction of objects’ size during training affords better learning of object-sensitive filters, and therefore, results in better accuracy. However, the use of an image pyramid increases the computational cost. Hence, we propose an efficient spatial sub-sampling scheme which only operates on fixed-size sub-regions likely to contain objects (as object locations are known during training). The resulting approach, referred to as Scale Normalized Image Pyramid with Efficient Resampling or SNIPER, yields up to 3× speed-up during training. Unfortunately, as object locations are unknown during inference, the entire image pyramid still needs processing. To this end, we adopt a coarse-to-fine approach, and predict the locations and extent of object-like regions which will be processed in successive scales of the image pyramid. Intuitively, it's akin to our active human-vision that first skims over the field-of-view to spot interesting regions for further processing and only recognizes objects at the right resolution. The resulting algorithm is referred to as AutoFocus and results in a 2.5-5× speed-up during inference when used with SNIP. Code: https://github.com/mahyarnajibi/SNIPER .
- 12 February 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Pattern Analysis and Machine Intelligence
- Vol. 44 (01628828) , 1
Scale Normalized Image Pyramids with AutoFocus for Object Detection
We present an efficient foveal framework to perform object detection. A scale normalized image pyramid (SNIP) is generated that, like human vision, only attends to objects within a fixed size range at different scales. Such a restriction of objects’ size during training affords better learning of object-sensitive filters, and therefore, results in better accuracy. However, the use of an image pyramid increases the computational cost. Hence, we propose an efficient spatial sub-sampling scheme which only operates on fixed-size sub-regions likely to contain objects (as object locations are known during training). The resulting approach, referred to as Scale Normalized Image Pyramid with Efficient Resampling or SNIPER, yields up to 3× speed-up during training. Unfortunately, as object locations are unknown during inference, the entire image pyramid still needs processing. To this end, we adopt a coarse-to-fine approach, and predict the locations and extent of object-like regions which will be processed in successive scales of the image pyramid. Intuitively, it's akin to our active human-vision that first skims over the field-of-view to spot interesting regions for further processing and only recognizes objects at the right resolution. The resulting algorithm is referred to as AutoFocus and results in a 2.5-5× speed-up during inference when used with SNIP. Code: https://github.com/mahyarnajibi/SNIPER .