Banani Basu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Banani Basu has a total of 46 co-authors. Here are the top co-authors by number of shared publications:
- Arnab Nandi
Department of Electronics and Communication Engineering, National Institute of Technology, Silchar, Assam, India
24 shared publications - Gautam Kumar Mahanti
Department of Electronics and Communication Engineering, National Institute of Technology, Durgapur 713209, India
10 shared publications Arnab Nandi
National Institute of Technology Silchar
7 shared publications- Jayendra Kumar
School of Electronics Engineering, VIT-AP University, Amaravati, India
7 shared publications Bidisha Hazarika
Department of Electronics and Communication Engineering National Institute of Technology Silchar Silchar Assam India
4 shared publicationsFazal Ahmed Talukdar
4 shared publications
Latest Publications
- 18 September 2026
- Published by Elsevier in Measurement
- Vol. 292
Breast carcinoma subtypes classification using bi-static microwave imaging and fractional Fourier transform based signal analysis with EfficientNetV2-L classifier
- 18 September 2026
- Published by Elsevier in Measurement
- Vol. 292
Breast carcinoma subtypes classification using bi-static microwave imaging and fractional Fourier transform based signal analysis with EfficientNetV2-L classifier
- 20 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Letters
- Vol. 10  (4) , 1-4
Parkinson's Disease Identification With Antenna and Shallow Hybrid Network
Parkinson's disease (PD), a prevalent neurodegenerative disorder, is frequently misdiagnosed with similar symptoms. This study investigates the feasibility of a wrist-worn wearable antenna for identifying actual PD from false PD (essential and physiological tremors). Antenna sensitivity was measured with the biological tissues. Reflection properties were measured while patients performed four motor activities. To overcome class imbalance, a generative adversarial network was used for data augmentation. Signals were normalized and converted into 2-D representations using the Gaussian-windowed Gabor wavelet transform and the short-time Fourier synchrosqueezed transform. A deep-learning model (DLM) shallow hybrid convolutional neural network (CNN)-transformer network is utilized for obtaining local and global features, with benchmark DLMs serving as comparisons. The original and enhanced datasets were trained and evaluated using fivefold subjectwise cross-validation. The suggested model, with only 0.7 million parameters, obtained 93.22% precision, 91.12% accuracy, and 91.12% F1-score.
- 20 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Letters
- Vol. 10  (4) , 1-4
Parkinson's Disease Identification With Antenna and Shallow Hybrid Network
Parkinson's disease (PD), a prevalent neurodegenerative disorder, is frequently misdiagnosed with similar symptoms. This study investigates the feasibility of a wrist-worn wearable antenna for identifying actual PD from false PD (essential and physiological tremors). Antenna sensitivity was measured with the biological tissues. Reflection properties were measured while patients performed four motor activities. To overcome class imbalance, a generative adversarial network was used for data augmentation. Signals were normalized and converted into 2-D representations using the Gaussian-windowed Gabor wavelet transform and the short-time Fourier synchrosqueezed transform. A deep-learning model (DLM) shallow hybrid convolutional neural network (CNN)-transformer network is utilized for obtaining local and global features, with benchmark DLMs serving as comparisons. The original and enhanced datasets were trained and evaluated using fivefold subjectwise cross-validation. The suggested model, with only 0.7 million parameters, obtained 93.22% precision, 91.12% accuracy, and 91.12% F1-score.
- 9 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75  (00189456) , 1-11
An RF Energy Harvesting Approach Toward Green and Sustainable Solution for Measurement Using Ultralow-Power MCU
This article introduces a differential-feed rectenna system (DFRS) designed for ultralow-power electronic (ULPE) devices suitable for energy-constrained measurement and instrumentation applications. The system harnesses RF energy in sub-6-GHz 5G bands, specifically targeting UMTS (2.1 GHz), WLAN (2.6 GHz), and WiMAX (3.6 GHz). The DFRS achieves high power conversion efficiency (PCE) and output voltage at low-input RF power by integrating a differential-feed antenna with a differential-feed rectifier. The antenna demonstrates the peak gains of 10.23, 10.65, and 13.27 dBi at 2.1, 2.6, and 3.6 GHz, respectively. A Villard voltage doubler rectifier enhances the DFRS performance, yielding a maximum RF-to-DC efficiency of 69.83% and an output voltage of 0.815 V at −5-dBm input power with a 3-k$\Omega $ load. The real-world field test shows that 30.91-$\mu $ W power is harvested at a voltage level of 1.39 V, which is sufficient to operate a low-power microcontroller unit (MCU). A proof-of-concept is established by demonstrating the ability of the proposed DFRS to energize an RF-powered MCU for overheating protection. The newly proposed energy-harvesting technique offers a practical and sustainable solution for generating a reliable energy source from ambient RF energy for low-powered sensors and the Internet of Things (IoT) devices, making it accessible anytime and anywhere.- 9 February 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 75  (00189456) , 1-11
An RF Energy Harvesting Approach Toward Green and Sustainable Solution for Measurement Using Ultralow-Power MCU
This article introduces a differential-feed rectenna system (DFRS) designed for ultralow-power electronic (ULPE) devices suitable for energy-constrained measurement and instrumentation applications. The system harnesses RF energy in sub-6-GHz 5G bands, specifically targeting UMTS (2.1 GHz), WLAN (2.6 GHz), and WiMAX (3.6 GHz). The DFRS achieves high power conversion efficiency (PCE) and output voltage at low-input RF power by integrating a differential-feed antenna with a differential-feed rectifier. The antenna demonstrates the peak gains of 10.23, 10.65, and 13.27 dBi at 2.1, 2.6, and 3.6 GHz, respectively. A Villard voltage doubler rectifier enhances the DFRS performance, yielding a maximum RF-to-DC efficiency of 69.83% and an output voltage of 0.815 V at −5-dBm input power with a 3-k$\Omega $ load. The real-world field test shows that 30.91-$\mu $ W power is harvested at a voltage level of 1.39 V, which is sufficient to operate a low-power microcontroller unit (MCU). A proof-of-concept is established by demonstrating the ability of the proposed DFRS to energize an RF-powered MCU for overheating protection. The newly proposed energy-harvesting technique offers a practical and sustainable solution for generating a reliable energy source from ambient RF energy for low-powered sensors and the Internet of Things (IoT) devices, making it accessible anytime and anywhere.- Open Access
Classification of motor faults based on transmission coefficient and reflection coefficient of omni-directional antenna using DCNN
The most commonly used electrical rotary machines in the field are induction machines. In this paper, we propose an antenna based approach for the classification of motor faults in induction motors using the reflection coefficient S11 and the transmission coefficient S21 of the antenna. The spectrograms of S11 and S21 are seen to possess unique signatures for various fault conditions that are used for the classification. To learn the required characteristics and classification boundaries, deep convolution neural network (DCNN) is applied to the spectrogram of the S-parameter. DCNN has been found to reach classification accuracy 93% using S11, 98.1% using S21 and 100% using both S11 and S21. The effect of antenna operating frequency, its location and duration of signal on the classification accuracy is also presented and discussed.
Open AccessClassification of motor faults based on transmission coefficient and reflection coefficient of omni-directional antenna using DCNN
The most commonly used electrical rotary machines in the field are induction machines. In this paper, we propose an antenna based approach for the classification of motor faults in induction motors using the reflection coefficient S11 and the transmission coefficient S21 of the antenna. The spectrograms of S11 and S21 are seen to possess unique signatures for various fault conditions that are used for the classification. To learn the required characteristics and classification boundaries, deep convolution neural network (DCNN) is applied to the spectrogram of the S-parameter. DCNN has been found to reach classification accuracy 93% using S11, 98.1% using S21 and 100% using both S11 and S21. The effect of antenna operating frequency, its location and duration of signal on the classification accuracy is also presented and discussed.
- 24 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74  (00189456) , 1-11
Diagnosis of Breast Malignancy With Microwave Breast Imaging Method and Utilizing EfficientNet-B4 Deep Learning Model
In this literature, an experimental study on non-invasive microwave breast imaging technology has been proposed to diagnose breast malignancy at its primary stage. The work utilizes a novel methodology to identify small tumors present in the female breast showing benign or malignant symptoms. The proposed antenna, designed for this imaging application, features a defected ground structure and exhibits multi-resonance behavior. It functions within 2 to 12 GHz frequency range that is suitable for medical imaging applications. The performance of the model has been tested with fabricated breast phantom models mimicking the dielectric properties of biological breast tissues. Two identical antennas are located around the phantom in closer proximity to acquire reflected and transmitted signals in the form of scattering parameters. The obtained dataset has been converted to high resolution two-dimensional Scalogram images utilizing proficient signal processing with continuous wavelet transform that provides both spatial and temporal information of the signal. The images are exploited with fine-tuned EfficientNet-B4 model to classify benign and malignant tumors. The issue of overfitting caused by a small experimental dataset has been addressed through the use of image augmentation and transfer learning techniques. Using compound scaling, the proposed network creates an optimal and balanced network model that achieves 99.56% accuracy and 99.40% precision in classifying benign and malignant breast phantom images. Overall, the model outperforms other reported CNN models while being compared in terms of its performance accuracy.
- 24 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Instrumentation and Measurement
- Vol. 74  (00189456) , 1-11
Diagnosis of Breast Malignancy With Microwave Breast Imaging Method and Utilizing EfficientNet-B4 Deep Learning Model
In this literature, an experimental study on non-invasive microwave breast imaging technology has been proposed to diagnose breast malignancy at its primary stage. The work utilizes a novel methodology to identify small tumors present in the female breast showing benign or malignant symptoms. The proposed antenna, designed for this imaging application, features a defected ground structure and exhibits multi-resonance behavior. It functions within 2 to 12 GHz frequency range that is suitable for medical imaging applications. The performance of the model has been tested with fabricated breast phantom models mimicking the dielectric properties of biological breast tissues. Two identical antennas are located around the phantom in closer proximity to acquire reflected and transmitted signals in the form of scattering parameters. The obtained dataset has been converted to high resolution two-dimensional Scalogram images utilizing proficient signal processing with continuous wavelet transform that provides both spatial and temporal information of the signal. The images are exploited with fine-tuned EfficientNet-B4 model to classify benign and malignant tumors. The issue of overfitting caused by a small experimental dataset has been addressed through the use of image augmentation and transfer learning techniques. Using compound scaling, the proposed network creates an optimal and balanced network model that achieves 99.56% accuracy and 99.40% precision in classifying benign and malignant breast phantom images. Overall, the model outperforms other reported CNN models while being compared in terms of its performance accuracy.
- 30 July 2025
- Published by Elsevier in AEU - International Journal of Electronics and Communications
- Vol. 201
RF energy harvester design using a dual-band rectenna for ultra-low-power electronic systems
- 30 July 2025
- Published by Elsevier in AEU - International Journal of Electronics and Communications
- Vol. 201
RF energy harvester design using a dual-band rectenna for ultra-low-power electronic systems
- 30 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25  (12) , 21847-21856
Wearable ZOR Antenna With ANN-Assisted Optimization for On-Body Sensing Applications
Antenna miniaturization is critical for fulfilling the developing needs of modern communication and electronic systems. Miniaturization allows for easy integration into such space-constrained devices. To maintain comfort and biocompatibility in wearable applications, antennas should be modest in size. This article presents a dual-frequency wearable zeroth-order resonator (ZOR) antenna employing an interdigital capacitor-based structure. The proposed antenna is laminated on a Teflon substrate with a thickness of 1.5 mm and a dielectric constant of 2.1. The substrate size is 25×16 mm2. The proposed antenna is intended to resonate at a specified frequency, targeted at 5.29 GHz and 5.8 GHz.The radiation pattern in the E and H planes is achieved with a gain of 3.86 dBi and 3.89 dBi at the obtained frequencies. The bending analysis is performed to observe the antenna performance.The proposed antenna is capable of working in the WBAN application. The antenna is also well suited for miniaturized incorporation into wearable device applications, which provides minimal SAR. The antenna’s geometrical parameters are optimized using an Artificial Neural Network (ANN) and two other machine learning (ML) models, which resolves the manual effort and time consumption of traditional optimization methods.
- 30 April 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25  (12) , 21847-21856
Wearable ZOR Antenna With ANN-Assisted Optimization for On-Body Sensing Applications
Antenna miniaturization is critical for fulfilling the developing needs of modern communication and electronic systems. Miniaturization allows for easy integration into such space-constrained devices. To maintain comfort and biocompatibility in wearable applications, antennas should be modest in size. This article presents a dual-frequency wearable zeroth-order resonator (ZOR) antenna employing an interdigital capacitor-based structure. The proposed antenna is laminated on a Teflon substrate with a thickness of 1.5 mm and a dielectric constant of 2.1. The substrate size is 25×16 mm2. The proposed antenna is intended to resonate at a specified frequency, targeted at 5.29 GHz and 5.8 GHz.The radiation pattern in the E and H planes is achieved with a gain of 3.86 dBi and 3.89 dBi at the obtained frequencies. The bending analysis is performed to observe the antenna performance.The proposed antenna is capable of working in the WBAN application. The antenna is also well suited for miniaturized incorporation into wearable device applications, which provides minimal SAR. The antenna’s geometrical parameters are optimized using an Artificial Neural Network (ANN) and two other machine learning (ML) models, which resolves the manual effort and time consumption of traditional optimization methods.
- 13 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25  (1) , 670-682
Conformal Multiband Antenna for Wearable and Gesture-Sensing Applications
Wireless body-centric communication technology has experienced substantial growth in the wearable device industry, owing to the growing demand for remote health monitoring, military and sensing applications, etc., without compromising the wearer’s comfort. This growth is aided by the popularity of wearable antennas for their beneficial features like low profile, adaptability, durability, and biocompatibility with Specific Absorption Rate (SAR), which make them viable options in Wireless Body Area Network (WBAN) deployments. This study introduces a modified T-shaped, stub-loaded planar antenna tailored for wearable applications across WiFi (2.08-2.88 GHz), WLAN (3.55-5.4 GHz), and WiMAX (5.73-5.92 GHz) bands. Leveraging strategically placed slits/stubs, additional resonances are introduced to achieve multiband functionality. This design features a via-less structure, facilitating simplified fabrication process. The effectiveness of the antenna is validated by simulation and equivalent circuit modeling. Bending analysis based on human body radii shows minimal performance deterioration, exhibiting equivalent performance when both flat and bent at 30 - 80 mm radii. The antenna offers a low SAR without introducing additional SAR reduction techniques. SAR values of 0.184 W/kg, 0.1936 W/kg, 0.4981 W/kg, 0.6531 W/kg, and 0.7339 W/kg were achieved at operating frequencies of 2.45 GHz, 3.77 GHz, 4.66 GHz, 5.23 GHz, and 5.83 GHz, respectively which ensures adherence to safety guidelines. The sensitivity of the antenna sensor is also investigated for different volumes of a tissue model through resonant frequencies shift at varying distances. Moreover, the antenna is demonstrated by experimental validation, which includes wrist placement and gesture recognition trials.
- 13 November 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 25  (1) , 670-682
Conformal Multiband Antenna for Wearable and Gesture-Sensing Applications
Wireless body-centric communication technology has experienced substantial growth in the wearable device industry, owing to the growing demand for remote health monitoring, military and sensing applications, etc., without compromising the wearer’s comfort. This growth is aided by the popularity of wearable antennas for their beneficial features like low profile, adaptability, durability, and biocompatibility with Specific Absorption Rate (SAR), which make them viable options in Wireless Body Area Network (WBAN) deployments. This study introduces a modified T-shaped, stub-loaded planar antenna tailored for wearable applications across WiFi (2.08-2.88 GHz), WLAN (3.55-5.4 GHz), and WiMAX (5.73-5.92 GHz) bands. Leveraging strategically placed slits/stubs, additional resonances are introduced to achieve multiband functionality. This design features a via-less structure, facilitating simplified fabrication process. The effectiveness of the antenna is validated by simulation and equivalent circuit modeling. Bending analysis based on human body radii shows minimal performance deterioration, exhibiting equivalent performance when both flat and bent at 30 - 80 mm radii. The antenna offers a low SAR without introducing additional SAR reduction techniques. SAR values of 0.184 W/kg, 0.1936 W/kg, 0.4981 W/kg, 0.6531 W/kg, and 0.7339 W/kg were achieved at operating frequencies of 2.45 GHz, 3.77 GHz, 4.66 GHz, 5.23 GHz, and 5.83 GHz, respectively which ensures adherence to safety guidelines. The sensitivity of the antenna sensor is also investigated for different volumes of a tissue model through resonant frequencies shift at varying distances. Moreover, the antenna is demonstrated by experimental validation, which includes wrist placement and gesture recognition trials.