Prabir Saha
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Prabir Saha has a total of 40 co-authors. Here are the top co-authors by number of shared publications:
- Shubhankar Majumdar
NIT Meghalaya
8 shared publications - Gautam Srivastava
Sogang University, Seoul, Republic of Korea
4 shared publications Sheba Diamond Thabah
Department of Electronics and Communication Engineering, National Institute of Technology Meghalaya, Laitumkhrah, Shillong 793003, Meghalaya, India
4 shared publications- Jagannath Samanta
Haldia Institute of Technology
3 shared publications - M. A. Seenivasan
Department of ECE, National Institute of Technology Meghalaya, Shillong, India
3 shared publications Rekib Uddin Ahmed
Department of Electronics and Communication Engineering National Institute of Technology Meghalaya
3 shared publications
Latest Publications
- 3 September 2026
- Published by Springer Nature in Microsystem Technologies
- Vol. 32 (11) , 172
Beyond CMOS: performance-driven hybrid PMOS–memristor logic for scalable computing
- 3 September 2026
- Published by Springer Nature in Microsystem Technologies
- Vol. 32 (11) , 172
Beyond CMOS: performance-driven hybrid PMOS–memristor logic for scalable computing
- 22 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (11) , 17894-17901
Design of Synaptic Interconnection of a Sensory LIF Neuron in CMOS for High-Speed In-Sensor Neuromorphic Systems
The sensory transduction process of the sensory neurons involves detecting a stimulus from thermal (heat), chemical (taste), or mechanical stimuli (touch) by the sensory receptors and converting a stimulus into an electrical signal (spikes). The sensory (pre-synaptic) neuron passes spike signals through gap junctions called synapses (synaptic interconnection) to the post-synaptic neuron, for high-speed transmission. Such synaptic interconnections are essential for neural communication, in-sensor computing, and signal transmission. This paper presents a method for designing a current-mode analog interconnect circuit that emulates a synapse and solves resistive/ conductive interconnect issues between neurons, compared to digital interconnect (AER) methods. In addition, the implementation of the current-mode interconnect is performed through an OTA-DPI circuit that improves power and energy efficiency because it operates at lower voltage swings with good noise margins. The proposed design offers a low-loss conduction path with plasticity spike intervals that emulate STDP learning. This approach is adaptable for high-speed synaptic interconnections in neuromorphic VLSI systems. The proposed model was simulated using Cadence GPDK 45nm technology, providing a post-spike interval estimation (tpost − tpre), and emulates STDP, an excitatory synaptic current of 1.321μA, and 23.06fJ of energy per spike consumption with a 0.7V power supply.
- 22 April 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 26 (11) , 17894-17901
Design of Synaptic Interconnection of a Sensory LIF Neuron in CMOS for High-Speed In-Sensor Neuromorphic Systems
The sensory transduction process of the sensory neurons involves detecting a stimulus from thermal (heat), chemical (taste), or mechanical stimuli (touch) by the sensory receptors and converting a stimulus into an electrical signal (spikes). The sensory (pre-synaptic) neuron passes spike signals through gap junctions called synapses (synaptic interconnection) to the post-synaptic neuron, for high-speed transmission. Such synaptic interconnections are essential for neural communication, in-sensor computing, and signal transmission. This paper presents a method for designing a current-mode analog interconnect circuit that emulates a synapse and solves resistive/ conductive interconnect issues between neurons, compared to digital interconnect (AER) methods. In addition, the implementation of the current-mode interconnect is performed through an OTA-DPI circuit that improves power and energy efficiency because it operates at lower voltage swings with good noise margins. The proposed design offers a low-loss conduction path with plasticity spike intervals that emulate STDP learning. This approach is adaptable for high-speed synaptic interconnections in neuromorphic VLSI systems. The proposed model was simulated using Cadence GPDK 45nm technology, providing a post-spike interval estimation (tpost − tpre), and emulates STDP, an excitatory synaptic current of 1.321μA, and 23.06fJ of energy per spike consumption with a 0.7V power supply.
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75, 8008508
Machine-Learning-Assisted SDR-Based Microwave System for Wood Characterization
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75, 8008508
Machine-Learning-Assisted SDR-Based Microwave System for Wood Characterization
- Open Access
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 7, 10385-10403
FPGA-Deployed Lightweight Adaptive Hybrid DPD Implementation for PA Linearization in LEO STIN
- 1 January 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Open Journal of the Communications Society
- Vol. 7, 10385-10403
Open AccessFPGA-Deployed Lightweight Adaptive Hybrid DPD Implementation for PA Linearization in LEO STIN
- 1 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (22) , 42243-42250
Real-Time Soil Hydration Assessment and Monitoring Model for Smart Agriculture With IoT Integration
In modern agriculture, effective water management is a major concern, particularly in the areas where unpredictable climates and water scarcity. Conventional irrigation methods often depend on manual observation, which can result in excessive or insufficient irrigation, which has a detrimental effect on crop productivity, soil health, and resource utilization. Real-time, accurate, and scalable methods for tracking Soil Hydration (SH) levels in a variety of agricultural fields are lacking. This paper introduces an IoT-based Soil Hydration Estimation Model (ISHEM) for smart agriculture, utilizing Multiple Linear Regression (MLR) to estimate soil hydration (SH) content in agricultural fields. The performance of proposed model is compared with commonly used Machine Learning (ML) algorithms such as Adaptive Boost (AdaBoost), Random Forest (RF), Extreme Gradient Boost (XGBoost) and Support Vector Machine (SVM) using various performance measure metrics such as the Coefficient of Determination (R2), Mean Absolute Error (MAE), Mean Square Error (MSE), Root Mean Square Error (RMSE), Ratio between Prediction to Deviation (RPD) and Ratio of Performance to the Inter-Quartile distance (RPIQ). The ISHEM model demonstrate superior performance over existing ML algorithms by achieving lower values in key error metrics (MAE, MSE, and RMSE), as well as higher values in RPD and RPIQ. This developed model enables accurate estimation of Soil Hydration (SH) content, which can play a crucial role in enhancing the efficiency and effectiveness of smart agriculture practices.
- 1 October 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (22) , 42243-42250
Real-Time Soil Hydration Assessment and Monitoring Model for Smart Agriculture With IoT Integration
In modern agriculture, effective water management is a major concern, particularly in the areas where unpredictable climates and water scarcity. Conventional irrigation methods often depend on manual observation, which can result in excessive or insufficient irrigation, which has a detrimental effect on crop productivity, soil health, and resource utilization. Real-time, accurate, and scalable methods for tracking Soil Hydration (SH) levels in a variety of agricultural fields are lacking. This paper introduces an IoT-based Soil Hydration Estimation Model (ISHEM) for smart agriculture, utilizing Multiple Linear Regression (MLR) to estimate soil hydration (SH) content in agricultural fields. The performance of proposed model is compared with commonly used Machine Learning (ML) algorithms such as Adaptive Boost (AdaBoost), Random Forest (RF), Extreme Gradient Boost (XGBoost) and Support Vector Machine (SVM) using various performance measure metrics such as the Coefficient of Determination (R2), Mean Absolute Error (MAE), Mean Square Error (MSE), Root Mean Square Error (RMSE), Ratio between Prediction to Deviation (RPD) and Ratio of Performance to the Inter-Quartile distance (RPIQ). The ISHEM model demonstrate superior performance over existing ML algorithms by achieving lower values in key error metrics (MAE, MSE, and RMSE), as well as higher values in RPD and RPIQ. This developed model enables accurate estimation of Soil Hydration (SH) content, which can play a crucial role in enhancing the efficiency and effectiveness of smart agriculture practices.
- 23 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (23) , 43382-43389
Next-Generation Intelligent Prediction Model for Real-Time Soil Nutrients’ Monitoring in Sustainable Farming
Soil nutrient content (SNC) is a key factor in plant development, and low soil fertility leads to an uneven distribution of essential nutrients such as Nitrogen (N), Phosphorus (P), and Potassium (K). Hence, developing a nutrient predictive model has become an important area of research. Proper nutrient supplementation is essential to enhance crop yield and improve product quality. This paper proposes a model to estimate Soil Nutrient Content (SNC) using Gradient Descent Algorithm-based Multiple Linear Regression (GDA-MLR) algorithm. The model’s performance is evaluated for predicting SNC in agricultural fields. Additionally, Pearson’s correlation analysis is used to examine the relationship between SNC and factors such as moisture percentage (Mp), pH, and other soil nutrients, aiding in feature selection for the model. Model performance is evaluated using Root Mean Square Error (RMSE), Coefficient of Determination (R2), Mean Absolute Error (MAE), and Ratio of Prediction to Deviation (RPD). The proposed GDA-MLR model achieved an R2 of 99.97% with urea fertilizer (Nitrogen) application, indicating excellent predictive accuracy. Its low RMSE and high R2 demonstrate superior performance compared to existing models. This makes the model well-suited for both precision and sustainable farming, promoting efficient and eco-friendly agricultural practices.
- 23 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (23) , 43382-43389
Next-Generation Intelligent Prediction Model for Real-Time Soil Nutrients’ Monitoring in Sustainable Farming
Soil nutrient content (SNC) is a key factor in plant development, and low soil fertility leads to an uneven distribution of essential nutrients such as Nitrogen (N), Phosphorus (P), and Potassium (K). Hence, developing a nutrient predictive model has become an important area of research. Proper nutrient supplementation is essential to enhance crop yield and improve product quality. This paper proposes a model to estimate Soil Nutrient Content (SNC) using Gradient Descent Algorithm-based Multiple Linear Regression (GDA-MLR) algorithm. The model’s performance is evaluated for predicting SNC in agricultural fields. Additionally, Pearson’s correlation analysis is used to examine the relationship between SNC and factors such as moisture percentage (Mp), pH, and other soil nutrients, aiding in feature selection for the model. Model performance is evaluated using Root Mean Square Error (RMSE), Coefficient of Determination (R2), Mean Absolute Error (MAE), and Ratio of Prediction to Deviation (RPD). The proposed GDA-MLR model achieved an R2 of 99.97% with urea fertilizer (Nitrogen) application, indicating excellent predictive accuracy. Its low RMSE and high R2 demonstrate superior performance compared to existing models. This makes the model well-suited for both precision and sustainable farming, promoting efficient and eco-friendly agricultural practices.
- 9 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (5) , 8921-8928
MLSFDD: Machine-Learning-Based Smart Fire Detection Device for Precision Agriculture
The agriculture sector contributes significantly to the overall development of the Indian economy. This sector can be revamped by modern technological interventions like the Internet of Things (IoT) and Machine Learning (ML) along with traditional processes. To improve sustainable growth in the agriculture field, monitoring of parameters like temperature, light, smoke, and flame is given top priority in crop yields. In this work, a smart IoT-based device (Machine Learning-based Smart Fire Detection Device (MLSFDD)) is designed for smart agriculture. The proposed MLSFDD has gathered data from agricultural crop fields through sensors and sensed data are analyzed by employing state-of-the-art ML algorithms like Random Forest (RF), Support Vector Regression (SVR), K-Nearest Neighbours (KNN), and Decision Tree (DT) to detect the fire status by sending the notification through Android phones during strange hours. This model has been realized and examined using raw data received from different sensors. The accuracy, Root Mean Square Error (RMSE), Coefficient of Determination (R 2 ), and Ratio of Prediction to Deviation (RPD) of the proposed model have been calculated via extensive simulation of four ML algorithms. The accuracy of the prediction model of 94% for DT, 93% for RF, 90% for SVR, and 92% for KNN have been achieved. This suggested that mapping the field area’s agricultural fire content can be accomplished using the DT ML model. The study’s findings provide a valuable resource for accurate fire prediction in precision agriculture.
- 9 January 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25 (5) , 8921-8928
MLSFDD: Machine-Learning-Based Smart Fire Detection Device for Precision Agriculture
The agriculture sector contributes significantly to the overall development of the Indian economy. This sector can be revamped by modern technological interventions like the Internet of Things (IoT) and Machine Learning (ML) along with traditional processes. To improve sustainable growth in the agriculture field, monitoring of parameters like temperature, light, smoke, and flame is given top priority in crop yields. In this work, a smart IoT-based device (Machine Learning-based Smart Fire Detection Device (MLSFDD)) is designed for smart agriculture. The proposed MLSFDD has gathered data from agricultural crop fields through sensors and sensed data are analyzed by employing state-of-the-art ML algorithms like Random Forest (RF), Support Vector Regression (SVR), K-Nearest Neighbours (KNN), and Decision Tree (DT) to detect the fire status by sending the notification through Android phones during strange hours. This model has been realized and examined using raw data received from different sensors. The accuracy, Root Mean Square Error (RMSE), Coefficient of Determination (R 2 ), and Ratio of Prediction to Deviation (RPD) of the proposed model have been calculated via extensive simulation of four ML algorithms. The accuracy of the prediction model of 94% for DT, 93% for RF, 90% for SVR, and 92% for KNN have been achieved. This suggested that mapping the field area’s agricultural fire content can be accomplished using the DT ML model. The study’s findings provide a valuable resource for accurate fire prediction in precision agriculture.
- 7 January 2025
- Published by Springer Nature in Microsystem Technologies
- Vol. 31 (8) , 2131-2144
Development and performance analysis of a human respiratory system using state-space model-based system identification technique
- 7 January 2025
- Published by Springer Nature in Microsystem Technologies
- Vol. 31 (8) , 2131-2144
Development and performance analysis of a human respiratory system using state-space model-based system identification technique
- 16 November 2024
- Published by Springer Nature in Microsystem Technologies
- Vol. 31 (10) , 2771-2782
Optimized recursive approximate multipliers for edge detection and image smoothing applications
- 16 November 2024
- Published by Springer Nature in Microsystem Technologies
- Vol. 31 (10) , 2771-2782
Optimized recursive approximate multipliers for edge detection and image smoothing applications