LAL UPENDRA PRATAP SINGH

@soa.ac.in

Assistant Professor, Computer Science and Engineering
Institute of Technical Education and Research, Siksha O' Anusandhan University

LAL UPENDRA PRATAP SINGH


                     Download Compact PDF  
https://researchid.co/upendra01

RESEARCH INTERESTS

Deep Learning, Transfer Learning, Machine Learning, Computer Vision and Optimization
19

Scopus Publications

76

Scholar Citations

5

Scholar h-index

3

Scholar i10-index

Scopus Publications

  • A Novel M-Ary Improvisation-Based Parameter Aggregation Algorithm for Segmenting Brain Tumors in a Federated Learning Setup
    Shiva Kumar Bandaru, Upendra Pratap Singh
    Lecture Notes in Networks and Systems, 2026
  • Nuclear Norm-Induced Lightweight and Robust Teacher-Student Network to Classify Hyper-Spectral Scenes
    Upendra Pratap Singh, Akshay Anand, Akshat Maithani, Patel Het Manojkumar
    Lecture Notes in Networks and Systems, 2026
  • A Novel Weighted Averaged Weights Aggregation-based Federated Learning Approach for Malaria Diagnosis
    Upendra Pratap Singh, Indrajeet Sinha, Ashutosh Kumar, Akshay Siraswar
    2025 IEEE 7th International Conference on Computing Communication and Automation Iccca 2025, 2025
    Deep learning-based approaches have achieved state-of-the-art performances in numerous application domains and require training data to be centrally available. However, training data may not be centrally available in domains like medical data imaging; further, the hosting institutions/clients may be reluctant to share the data owing to security and privacy issues. Federated learning trains several local models at the institution level collaboratively and then aggregates the knowledge obtained to get a global model that generalizes to data from these participating institutions without the need for data sharing among them. This work proposes a novel federated learning-based model for malaria diagnosis using stem cells. The novelty lies in fine-tuning pre-trained models, including Xception, Resnet50 and VGG19, for the malaria diagnosis and using the most generalizable model in the federated learning setup. Additionally, we propose two novel parameter aggregation strategies, namely average weights aggregation and weighted averaged weights aggregation, to get the global model. Experiments conducted on the Malaria Cells Images Dataset confirm the usefulness of the proposed federated learning-based approach; specifically, the performance of the Xception backbone-based global model is 100% with weighted averaged weights aggregation scheme. The performance of the ResNet50-based federated model reports an accuracy of 96.0% and remains competitive with the state-of-the-art models even when the latter models are trained centrally. These results show that the proposed methodology is helpful in medical data imaging applications where institutions have limited training data and are reluctant to share their data due to inherent security and privacy issues.
  • Improving Financial Forecasting Through Hybrid Convolutional-Recurrent-Temporal Models
    Upendra Pratap Singh, Suman Kumar Singh, Snehil Singh Solanki, Virender Kumar
    2025 IEEE 7th International Conference on Computing Communication and Automation Iccca 2025, 2025
  • Lung cancer detection using convolutional neural network and transfer learning
    Rahul Sharma, Akanksha Dubey, Manoj Diwakar, Shagun Gupta, Upendra Pratap Singh, Monika Kumari Nath
    Proceedings 3rd International Conference on Advancement in Computation and Computer Technologies Incacct 2025, 2025
    Lung cancer has emerged as a significant cause for concern among individuals worldwide. Consequently, several nations provide financial resources and extend invitations to researchers and medical professionals to collaborate in addressing this issue. Lung cancer is a significant contributor to mortality subsequent to heart illness. The timely identification of lung cancer in its first stages has the potential to enhance patient survival rates. The use of Computer Vision is of utmost importance in the timely identification of lung cancer and the implementation of early therapeutic interventions, hence enhancing the likelihood of patient survival. The proposed deep learning model incorporates Convolutional Neural Network (CNN) and transfer learning techniques, along with other image processing methods like image compression and picture enhancement. These approaches are used to analyze medical images and make correct predictions. Our study demonstrates a CNN model accuracy of 91.29% and a transfer learning accuracy of 95.9%.
  • Meta-DPSTL: meta learning-based differentially private self-taught learning
    Upendra Pratap Singh, Indrajeet Kumar Sinha, Krishna Pratap Singh, Shekhar Verma
    International Journal of Machine Learning and Cybernetics, 2024
  • A Comparative Study of Adaptive Time Series Models for Weather Forecasting in Indian Scenarios
    Shalini Sharma, Upendra Pratap Singh
    2024 IEEE 21st India Council International Conference Indicon 2024, 2024
    Given the erratic changes in the weather and climate patterns across the globe and their ramifications on the livelihood, safety and security of human and animal communities, weather forecasting has evolved as a pressing task to ensure the sustainability and security of these communities. In this work, the temperature data of different places across India are considered for training different conventional and deep learning-based time series models; specifically, while ARIMA and SARIMAX models are trained in conventional settings, LSTM networks are trained in deep learning settings. The performance of these models is evaluated using AIC, BIC and HQIC metrics, followed by a systematic comparison of their modelling performances. Empirical results show that LSTM-based models capture long-term dependencies in the time series data better than conventional time series models; this improved modelling using LSTMs is quantified using AIC, BIC and HQIC scores for different places across India. The AIC, BIC, and HQIC values reported by the LSTM models are several orders of magnitude lesser than those reported by ARIMA and SARIMAX models; consequently, LSTMs are then deployed for time series prediction using temperature data of places considered in the study.
  • A nuclear norm-induced robust and lightweight relation network for few-shots classification of hyperspectral images
    Upendra Pratap Singh, Krishna Pratap Singh, Manoj Thakur
    Multimedia Tools and Applications, 2024
  • A lightweight relation network for few-shots classification of hyperspectral images
    Anshul Mishra, Upendra Pratap Singh, Krishna Pratap Singh
    Neural Computing and Applications, 2023
  • Interpretable Sequence Models for the Sales Forecasting Task: A Review
    Rishi Narang, Upendra Pratap Singh
    Proceedings of the 7th International Conference on Intelligent Computing and Control Systems Iciccs 2023, 2023
    Sequence modelling has shown tremendous potential in solving real-world sequence prediction tasks like speech recognition, time series forecasting, and context identification. However, most of these sequence models are trained on univariate datasets and cannot leverage the information available in a multivariate setting. Moreover, the prediction/decision made by these models is not interpretable; consequently, the end users are unaware of the different steps involved in reaching that prediction/decision and cannot determine if the model aligns with the business and ethical values. This work investigates the performance of different sequence learners trained in a multivariate setting for the sales forecasting task. Specifically, different sequence models, including vanilla LSTM, stacked LSTM, bidirectional LSTM, and convolution neural networkbased-LSTM, have been trained on the Walmart dataset, and a comparative analysis of their performance using mean squared error (MSE) and weighted mean absolute error (WMAE) metric is reported. For training the learners in a multivariate setting, relevant features have been identified using exploratory data analytics. Furthermore, these sequence models are made interpretable using the Local Interpretable Model Agnostic Explanation (LIME) model to explain away the key variables involved in the prediction task. Empirical results obtained on the Walmart sales dataset established that the performance of the stacked LSTM model is superior to other learners. Additionally, the stacked model being the most generalizable, is complemented by the LIME module to explain away its predictions using the relevant features.
  • Meta-DZSL: a meta-dictionary learning based approach to zero-shot recognition
    Upendra Pratap Singh, Krishna Pratap Singh, Manoj Thakur
    Applied Intelligence, 2022
  • NucNormZSL: nuclear norm-based domain adaptation in zero-shot learning
    Upendra Pratap Singh, Krishna Pratap Singh, Manoj Thakur
    Neural Computing and Applications, 2022
  • Fake News Detection Using BERT-VGG19 Multimodal Variational Autoencoder
    Ramji Jaiswal, Upendra Pratap Singh, Krishna Pratap Singh
    2021 IEEE 8th Uttar Pradesh Section International Conference on Electrical Electronics and Computer Engineering Upcon 2021, 2021
  • Few Shots Learning: Caricature to Image Recognition Using Improved Relation Network
    Rashi Agrawal, Upendra Pratap Singh, Krishna Pratap Singh
    Communications in Computer and Information Science, 2021
  • Spread Peak Prediction of Covid-19 using ANN and Regression (Workshop Paper)
    Anupam Prakash, Piyush Sharma, Indrajeet Kumar Sinha, Upendra Pratap Singh
    Proceedings 2020 IEEE 6th International Conference on Multimedia Big Data Bigmm 2020, 2020
  • Self-taught Learning: Image Classification Using Stacked Autoencoders
    Upendra Pratap Singh, Swapnil Chavan, Sahil Hindwani, Krishna Pratap Singh
    Advances in Intelligent Systems and Computing, 2020
  • Improved coupled autoencoder based zero shot recognition using active learning
    Upendra Pratap Singh, Kaustubh Rakesh, Rishabh, Vipul Kumar, Krishna Pratap Singh
    2019 IEEE Conference on Information and Communication Technology Cict 2019, 2019
  • CBAT-Color blind assisting tool
    Anupam Agrawal, Manisha Malik, Lal Upendra Pratap Singh
    Impact 2017 International Conference on Multimedia Signal Processing and Communication Technologies, 2018
  • NO-SHAM: An effective tool based on a novel hybrid approach to detect copy-move forgery in images
    Lal Upendra Pratap Singh, Anupam Agrawal
    2017 4th IEEE Uttar Pradesh Section International Conference on Electrical Computer and Electronics Upcon 2017, 2017

RECENT SCHOLAR PUBLICATIONS

  • Improving Financial Forecasting Through Hybrid Convolutional–Recurrent–Temporal Models
    UP Singh, SK Singh, SS Solanki, V Kumar
    2025 IEEE 7th International Conference on Computing, Communication and … , 2025
    2025
  • A Novel Weighted Averaged Weights Aggregation-based Federated Learning Approach for Malaria Diagnosis
    UP Singh, I Sinha, A Kumar, A Siraswar
    2025 IEEE 7th International Conference on Computing, Communication and … , 2025
    2025
  • Temporal Differencing Strategies for Optimal Band Selection in Sentinel-2 MSI for Algal Bloom Studies
    VK Mishra, UP Singh, F Nicolls, AK Mishra, H Maurya
    IGARSS 2025 - 2025 IEEE International Geoscience and Remote Sensing Symposium , 2025
    2025
  • Nuclear Norm-Induced Lightweight and Robust Teacher-Student Network to Classify Hyper-Spectral Scenes
    UP Singh, A Anand, A Maithani, PH Manojkumar
    ICT for Intelligent Systems: Proceedings of ICTIS 2025, Volume 11, 155-165 , 2025
    2025
  • A Novel M-Ary Improvisation-Based Parameter Aggregation Algorithm for Segmenting Brain Tumors in a Federated Learning Setup
    SK Bandaru, UP Singh
    Smart Trends in Computing and Communications: Proceedings of SmartCom 2025 … , 2025
    2025
  • A Comparative Study of Adaptive Time Series Models for Weather Forecasting in Indian Scenarios
    S Sharma, UP Singh
    2024 IEEE 21st India Council International Conference (INDICON), 1-6 , 2024
    2024
    Citations: 1
  • Meta-DPSTL: meta learning-based differentially private self-taught learning
    UP Singh, IK Sinha, KP Singh, S Verma
    International Journal of Machine Learning and Cybernetics 15 (9), 4021-4053 , 2024
    2024
    Citations: 1
  • Heuristics-based hyperparameter tuning for transfer learning algorithms
    UP Singh, KP Singh, M Ojha
    Advanced Machine Learning with Evolutionary and Metaheuristic Techniques … , 2024
    2024
    Citations: 2
  • A nuclear norm-induced robust and lightweight relation network for few-shots classification of hyperspectral images
    UP Singh, KP Singh, M Thakur
    Multimedia Tools and Applications 83 (3), 9279-9306 , 2024
    2024
    Citations: 1
  • Interpretable sequence models for the sales forecasting task: A review
    R Narang, UP Singh
    2023 7th International Conference on Intelligent Computing and Control … , 2023
    2023
    Citations: 5
  • A lightweight relation network for few-shots classification of hyperspectral images
    KPS Anshul Mishra, Upendra Pratap Singh
    Neural Computing and Applications , 2023
    2023
    Citations: 10
  • Meta-DZSL: a meta-dictionary learning based approach to zero-shot recognition
    UP Singh, KP Singh, M Thakur
    Applied Intelligence 52 (14), 15938-15960 , 2022
    2022
    Citations: 6
  • NucNormZSL: nuclear norm-based domain adaptation in zero-shot learning
    UP Singh, KP Singh, M Thakur
    Neural Computing and Applications 34 (3), 2353-2374 , 2022
    2022
    Citations: 5
  • Fake news detection using BERT-VGG19 multimodal variational autoencoder
    R Jaiswal, UP Singh, KP Singh
    2021 IEEE 8th Uttar Pradesh section international conference on electrical … , 2021
    2021
    Citations: 24
  • Few shots learning: Caricature to image recognition using improved relation network
    R Agrawal, UP Singh, KP Singh
    International Conference on Computer Vision and Image Processing, 162-173 , 2020
    2020
    Citations: 1
  • Spread & peak prediction of Covid-19 using ANN and regression (Workshop Paper)
    A Prakash, P Sharma, IK Sinha, UP Singh
    2020 IEEE Sixth International Conference on Multimedia Big Data (BigMM), 356-365 , 2020
    2020
    Citations: 13
  • Self-taught Learning: Image Classification Using Stacked Autoencoders
    UP Singh, S Chavan, S Hindwani, KP Singh
    Soft Computing for Problem Solving 2019: Proceedings of SocProS 2019, Volume … , 2020
    2020
  • Improved Coupled Autoencoder based Zero Shot Recognition using Active Learning
    UP Singh, K Rakesh, V Kumar, KP Singh
    2019 IEEE Conference on Information and Communication Technology, 1-6 , 2019
    2019
    Citations: 2
  • CBAT—Color blind assisting tool
    A Agrawal, M Malik, LUP Singh
    2017 International Conference on Multimedia, Signal Processing and … , 2017
    2017
    Citations: 3
  • NO-SHAM: An effective tool based on a novel hybrid approach to detect copy-move forgery in images
    LUP Singh, A Agrawal
    2017 4th IEEE Uttar Pradesh Section International Conference on Electrical … , 2017
    2017
    Citations: 2

MOST CITED SCHOLAR PUBLICATIONS

  • Fake news detection using BERT-VGG19 multimodal variational autoencoder
    R Jaiswal, UP Singh, KP Singh
    2021 IEEE 8th Uttar Pradesh section international conference on electrical … , 2021
    2021
    Citations: 24
  • Spread & peak prediction of Covid-19 using ANN and regression (Workshop Paper)
    A Prakash, P Sharma, IK Sinha, UP Singh
    2020 IEEE Sixth International Conference on Multimedia Big Data (BigMM), 356-365 , 2020
    2020
    Citations: 13
  • A lightweight relation network for few-shots classification of hyperspectral images
    KPS Anshul Mishra, Upendra Pratap Singh
    Neural Computing and Applications , 2023
    2023
    Citations: 10
  • Meta-DZSL: a meta-dictionary learning based approach to zero-shot recognition
    UP Singh, KP Singh, M Thakur
    Applied Intelligence 52 (14), 15938-15960 , 2022
    2022
    Citations: 6
  • Interpretable sequence models for the sales forecasting task: A review
    R Narang, UP Singh
    2023 7th International Conference on Intelligent Computing and Control … , 2023
    2023
    Citations: 5
  • NucNormZSL: nuclear norm-based domain adaptation in zero-shot learning
    UP Singh, KP Singh, M Thakur
    Neural Computing and Applications 34 (3), 2353-2374 , 2022
    2022
    Citations: 5
  • CBAT—Color blind assisting tool
    A Agrawal, M Malik, LUP Singh
    2017 International Conference on Multimedia, Signal Processing and … , 2017
    2017
    Citations: 3
  • Heuristics-based hyperparameter tuning for transfer learning algorithms
    UP Singh, KP Singh, M Ojha
    Advanced Machine Learning with Evolutionary and Metaheuristic Techniques … , 2024
    2024
    Citations: 2
  • Improved Coupled Autoencoder based Zero Shot Recognition using Active Learning
    UP Singh, K Rakesh, V Kumar, KP Singh
    2019 IEEE Conference on Information and Communication Technology, 1-6 , 2019
    2019
    Citations: 2
  • NO-SHAM: An effective tool based on a novel hybrid approach to detect copy-move forgery in images
    LUP Singh, A Agrawal
    2017 4th IEEE Uttar Pradesh Section International Conference on Electrical … , 2017
    2017
    Citations: 2
  • A Comparative Study of Adaptive Time Series Models for Weather Forecasting in Indian Scenarios
    S Sharma, UP Singh
    2024 IEEE 21st India Council International Conference (INDICON), 1-6 , 2024
    2024
    Citations: 1
  • Meta-DPSTL: meta learning-based differentially private self-taught learning
    UP Singh, IK Sinha, KP Singh, S Verma
    International Journal of Machine Learning and Cybernetics 15 (9), 4021-4053 , 2024
    2024
    Citations: 1
  • A nuclear norm-induced robust and lightweight relation network for few-shots classification of hyperspectral images
    UP Singh, KP Singh, M Thakur
    Multimedia Tools and Applications 83 (3), 9279-9306 , 2024
    2024
    Citations: 1
  • Few shots learning: Caricature to image recognition using improved relation network
    R Agrawal, UP Singh, KP Singh
    International Conference on Computer Vision and Image Processing, 162-173 , 2020
    2020
    Citations: 1
  • Improving Financial Forecasting Through Hybrid Convolutional–Recurrent–Temporal Models
    UP Singh, SK Singh, SS Solanki, V Kumar
    2025 IEEE 7th International Conference on Computing, Communication and … , 2025
    2025
  • A Novel Weighted Averaged Weights Aggregation-based Federated Learning Approach for Malaria Diagnosis
    UP Singh, I Sinha, A Kumar, A Siraswar
    2025 IEEE 7th International Conference on Computing, Communication and … , 2025
    2025
  • Temporal Differencing Strategies for Optimal Band Selection in Sentinel-2 MSI for Algal Bloom Studies
    VK Mishra, UP Singh, F Nicolls, AK Mishra, H Maurya
    IGARSS 2025 - 2025 IEEE International Geoscience and Remote Sensing Symposium , 2025
    2025
  • Nuclear Norm-Induced Lightweight and Robust Teacher-Student Network to Classify Hyper-Spectral Scenes
    UP Singh, A Anand, A Maithani, PH Manojkumar
    ICT for Intelligent Systems: Proceedings of ICTIS 2025, Volume 11, 155-165 , 2025
    2025
  • A Novel M-Ary Improvisation-Based Parameter Aggregation Algorithm for Segmenting Brain Tumors in a Federated Learning Setup
    SK Bandaru, UP Singh
    Smart Trends in Computing and Communications: Proceedings of SmartCom 2025 … , 2025
    2025
  • Self-taught Learning: Image Classification Using Stacked Autoencoders
    UP Singh, S Chavan, S Hindwani, KP Singh
    Soft Computing for Problem Solving 2019: Proceedings of SocProS 2019, Volume … , 2020
    2020