Harpreet 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
Harpreet Singh has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
- Prashant Singh Rana
Department of Computer Science and Engineering, Thapar Institute of Engineering and Technology, Patiala, India
8 shared publications Prashant Singh Rana
Department of Computer Science Engineering, Thapar Institute of Engineering and Technology, Patiala, India
4 shared publications- Yosi Shacham-Diamand
Tel Aviv University
4 shared publications Divisha Garg
3 shared publicationsNeeru Jindal
Department of Electronics and Communication, Thapar Institute of Engineering and Technology, Patiala, India
3 shared publications- Divisha Garg
Thapar Institute of Engineering and Technology
2 shared publications
Latest Publications
- 19 August 2025
- Published by Springer Nature in Computing
- Vol. 107 (9) , 1-35
Designing an intelligent IoT and AI-based model for safer blood extraction and transfusion with accurate heart attack risk prediction
- 19 August 2025
- Published by Springer Nature in Computing
- Vol. 107 (9) , 1-35
Designing an intelligent IoT and AI-based model for safer blood extraction and transfusion with accurate heart attack risk prediction
- 25 May 2025
- Published by Springer Nature
- p. 117-124
Next-Gen Farming: Real-Time Monitoring of Soil Phosphate Levels Using P Sensor
- 25 May 2025
- Published by Springer Nature
- p. 117-124
Next-Gen Farming: Real-Time Monitoring of Soil Phosphate Levels Using P Sensor
- Open Access
AdapTree: Data-Driven Approach to Assessing Plant Stress Through the AI-Sensor Synergy
This study investigates plant stress assessment by integrating advanced sensor technologies and Artificial Intelligence (AI). Multi-sensor data—including electrical impedance spectroscopy, temperature, and humidity—were used to capture plant physiological responses under environmental stress conditions. The key task addressed was the prediction of stress-related parameters using machine learning. A novel boosting-based ensemble method, AdapTree, combining AdaBoost and decision trees, was proposed to improve predictive accuracy and model interpretability. Experimental evaluation across multiple regression metrics demonstrated that AdapTree outperformed baseline models, achieving an R2 score of 0.993 for impedance magnitude prediction and 0.999 for both relative humidity (RH) and temperature, along with low root mean squared error (134.565 for impedance, 0.006966 for RH, and 0.0050099 for temperature) and mean absolute error values (22.789 for impedance; 1.51 × for RH and 2.51 × for temperature). These findings validate the reliability and effectiveness of the proposed AI-driven framework in accurately interpreting sensor data for plant stress detection. The approach offers a scalable, data-driven solution to enhance precision agriculture and agricultural sustainability. Furthermore, this method can be extended to monitor additional stress markers or applied across diverse plant species and field conditions, supporting future developments in intelligent crop monitoring systems.Open AccessAdapTree: Data-Driven Approach to Assessing Plant Stress Through the AI-Sensor Synergy
This study investigates plant stress assessment by integrating advanced sensor technologies and Artificial Intelligence (AI). Multi-sensor data—including electrical impedance spectroscopy, temperature, and humidity—were used to capture plant physiological responses under environmental stress conditions. The key task addressed was the prediction of stress-related parameters using machine learning. A novel boosting-based ensemble method, AdapTree, combining AdaBoost and decision trees, was proposed to improve predictive accuracy and model interpretability. Experimental evaluation across multiple regression metrics demonstrated that AdapTree outperformed baseline models, achieving an R2 score of 0.993 for impedance magnitude prediction and 0.999 for both relative humidity (RH) and temperature, along with low root mean squared error (134.565 for impedance, 0.006966 for RH, and 0.0050099 for temperature) and mean absolute error values (22.789 for impedance; 1.51 × for RH and 2.51 × for temperature). These findings validate the reliability and effectiveness of the proposed AI-driven framework in accurately interpreting sensor data for plant stress detection. The approach offers a scalable, data-driven solution to enhance precision agriculture and agricultural sustainability. Furthermore, this method can be extended to monitor additional stress markers or applied across diverse plant species and field conditions, supporting future developments in intelligent crop monitoring systems. - RetractionOpen Access
- 10 August 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (38) , 86325
Retraction Note: Evolutionary based drug synergy prediction using adaptive Lévy based neural network structure
- 10 August 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (38) , 86325
RetractionOpen AccessRetraction Note: Evolutionary based drug synergy prediction using adaptive Lévy based neural network structure
- Open Access
Benchmarking the Effectiveness of Classification Algorithms and SVM Kernels for Dry Beans
Plant breeders and agricultural researchers can increase crop productivity by identifying desirable features, disease resistance, and nutritional content by analysing the Dry Bean dataset. This study analyses and compares different Support Vector Machine (SVM) classification algorithms, namely linear, polynomial, and radial basis function (RBF), along with other popular classification algorithms. The analysis is performed on the Dry Bean Dataset, with PCA (Principal Component Analysis) conducted as a preprocessing step for dimensionality reduction. The primary evaluation metric used is accuracy, and the RBF SVM kernel algorithm achieves the highest Accuracy of 93.34%, Precision of 92.61%, Recall of 92.35% and F1 Score as 91.40%. Along with adept visualization and empirical analysis, this study offers valuable guidance by emphasizing the importance of considering different SVM algorithms for complex and non-linear structured datasets.
Open AccessBenchmarking the Effectiveness of Classification Algorithms and SVM Kernels for Dry Beans
Plant breeders and agricultural researchers can increase crop productivity by identifying desirable features, disease resistance, and nutritional content by analysing the Dry Bean dataset. This study analyses and compares different Support Vector Machine (SVM) classification algorithms, namely linear, polynomial, and radial basis function (RBF), along with other popular classification algorithms. The analysis is performed on the Dry Bean Dataset, with PCA (Principal Component Analysis) conducted as a preprocessing step for dimensionality reduction. The primary evaluation metric used is accuracy, and the RBF SVM kernel algorithm achieves the highest Accuracy of 93.34%, Precision of 92.61%, Recall of 92.35% and F1 Score as 91.40%. Along with adept visualization and empirical analysis, this study offers valuable guidance by emphasizing the importance of considering different SVM algorithms for complex and non-linear structured datasets.
- 28 June 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (4) , 9911-9928
Enhanced spatio-temporal 3D CNN for facial expression classification in videos
- 28 June 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (4) , 9911-9928
Enhanced spatio-temporal 3D CNN for facial expression classification in videos
- Open Access
Smart Farming Revolution: Portable and Real-Time Soil Nitrogen and Phosphorus Monitoring for Sustainable Agriculture
Precision agriculture is crucial for ensuring food security in a growing global population. Nutrients, their presence, concentration, and effectiveness, are key components in data-driven agriculture. Assessing macro and micro-nutrients, as well as factors such as water and pH, helps determine soil fertility, which is vital for supporting healthy plant growth and high crop yields. Insufficient soil nutrient assessment during continuous cropping can threaten long-term agricultural viability. Soil nutrients need to be measured and replenished after each harvest for optimal yield. However, existing soil testing procedures are expensive and time-consuming. The proposed research aims to assess soil nutrient levels, specifically nitrogen and phosphorus concentrations, to provide critical information and guidance on restoring optimal soil fertility. In this research, a novel chip-level colorimeter is fabricated to detect the N and P elements of soil onto a handheld colorimeter or spectrophotometer. Chemical reaction with soil solution generates color in the presence of nutrients, which are then quantitatively measured using sensors. The test samples are collected from various farmlands, and the results are validated with laboratory analysis of samples using spectrophotometers used in laboratories. ANOVA test has been performed in which F value > 1 in our study indicates statistically significant differences between the group means. The alternate hypothesis, which proposes the presence of significant differences between the groups, is supported by the data. The device created in this paper has crucial potential in terms of environmental and biological applications.
Open AccessSmart Farming Revolution: Portable and Real-Time Soil Nitrogen and Phosphorus Monitoring for Sustainable Agriculture
Precision agriculture is crucial for ensuring food security in a growing global population. Nutrients, their presence, concentration, and effectiveness, are key components in data-driven agriculture. Assessing macro and micro-nutrients, as well as factors such as water and pH, helps determine soil fertility, which is vital for supporting healthy plant growth and high crop yields. Insufficient soil nutrient assessment during continuous cropping can threaten long-term agricultural viability. Soil nutrients need to be measured and replenished after each harvest for optimal yield. However, existing soil testing procedures are expensive and time-consuming. The proposed research aims to assess soil nutrient levels, specifically nitrogen and phosphorus concentrations, to provide critical information and guidance on restoring optimal soil fertility. In this research, a novel chip-level colorimeter is fabricated to detect the N and P elements of soil onto a handheld colorimeter or spectrophotometer. Chemical reaction with soil solution generates color in the presence of nutrients, which are then quantitatively measured using sensors. The test samples are collected from various farmlands, and the results are validated with laboratory analysis of samples using spectrophotometers used in laboratories. ANOVA test has been performed in which F value > 1 in our study indicates statistically significant differences between the group means. The alternate hypothesis, which proposes the presence of significant differences between the groups, is supported by the data. The device created in this paper has crucial potential in terms of environmental and biological applications.
- Retracted
- 4 April 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (26) , 40105-40127
RETRACTED ARTICLE: Evolutionary based drug synergy prediction using adaptive Lévy based neural network structure
- 4 April 2023
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 82 (26) , 40105-40127
RetractedRETRACTED ARTICLE: Evolutionary based drug synergy prediction using adaptive Lévy based neural network structure
- Open Access
- 11 February 2023
- Published by MDPI AG in Mathematics
- Vol. 11 (4) , 920
A Fuzzy-Based Fast Feature Selection Using Divide and Conquer Technique in Huge Dimension Dataset
Feature selection is commonly employed for identifying the top n features that significantly contribute to the desired prediction, for example, to find the top 50 or 100 genes responsible for lung or kidney cancer out of 50,000 genes. Thus, it is a huge time- and resource-consuming practice. In this work, we propose a divide-and-conquer technique with fuzzy backward feature elimination (FBFE) that helps to find the important features quickly and accurately. To show the robustness of the proposed method, it is applied to eight different datasets taken from the NCBI database. We compare the proposed method with seven state-of-the-art feature selection methods and find that the proposed method can obtain fast and better classification accuracy. The proposed method will work for qualitative, quantitative, continuous, and discrete datasets. A web service is developed for researchers and academicians to select top n features.
- 11 February 2023
- Published by MDPI AG in Mathematics
- Vol. 11 (4) , 920
Open AccessA Fuzzy-Based Fast Feature Selection Using Divide and Conquer Technique in Huge Dimension Dataset
Feature selection is commonly employed for identifying the top n features that significantly contribute to the desired prediction, for example, to find the top 50 or 100 genes responsible for lung or kidney cancer out of 50,000 genes. Thus, it is a huge time- and resource-consuming practice. In this work, we propose a divide-and-conquer technique with fuzzy backward feature elimination (FBFE) that helps to find the important features quickly and accurately. To show the robustness of the proposed method, it is applied to eight different datasets taken from the NCBI database. We compare the proposed method with seven state-of-the-art feature selection methods and find that the proposed method can obtain fast and better classification accuracy. The proposed method will work for qualitative, quantitative, continuous, and discrete datasets. A web service is developed for researchers and academicians to select top n features.