Santhosh Kumar Ramachandragowda
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
Santhosh Kumar Ramachandragowda has a total of 11 co-authors. Here are the top co-authors by number of shared publications:
- Druva Kumar Siddaraju
Dayananda Sagar College of Engineering
2 shared publications - Trupti Shripad Tagare
Dayananda Sagar College of Engineering
2 shared publications - Devaraju Ramakrishna
Department of Electronics and Telecommunication Engineering , Dayananda Sagar College of Engineering , Bengaluru , India
1 shared publication - K. Srinivas
Department of Computer Science and Engineering, Koneru Lakshmaiah Education Foundation, Hyderabad 500075, Telangana, India
1 shared publication - Kumar Puttaswamy Gowda
Dayananda Sagar College of Engineering
1 shared publication - Navya Rajashekara
Dayananda Sagar University
1 shared publication
Latest Publications
- Open Access
- 1 August 2026
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 15 (4) , 3703-3711
Deep learning intrusion detection for software-defined networking using synthetic minority oversampling
This article proposes an advanced method for network intrusion detection using a combination of recurrent neural networks (RNNs), specifically long short-term memory (LSTM), gated recurrent units (GRU), and bidirectional long short-term memory (BiLSTM) models, enhanced by synthetic minority oversampling technique (SMOTE) to address class imbalance in datasets like network security laboratory–knowledge discovery in databases (NSL-KDD). The method aims to accurately classify network traffic by learning temporal patterns of both normal and malicious activities. SMOTE is employed to balance the dataset, ensuring that underrepresented attack types receive adequate model attention, thereby improving model robustness. The proposed models (LSTM, GRU, and BiLSTM) are trained and evaluated on the NSL-KDD dataset, with hyperparameter tuning performed through RandomizedSearchCV for optimal performance. The results show a significant improvement in accuracy, precision, recall, and F1-score, with BiLSTM demonstrating the highest performance, achieving near-perfect classification results (99.5% accuracy). This method not only mitigates the issue of class imbalance but also leverages the power of RNNs for sequence modeling, offering a promising solution for effective intrusion detection in modern networks.
- 1 August 2026
- Published by Institute of Advanced Engineering and Science in IAES International Journal of Artificial Intelligence (IJ-AI)
- Vol. 15 (4) , 3703-3711
Open AccessDeep learning intrusion detection for software-defined networking using synthetic minority oversampling
This article proposes an advanced method for network intrusion detection using a combination of recurrent neural networks (RNNs), specifically long short-term memory (LSTM), gated recurrent units (GRU), and bidirectional long short-term memory (BiLSTM) models, enhanced by synthetic minority oversampling technique (SMOTE) to address class imbalance in datasets like network security laboratory–knowledge discovery in databases (NSL-KDD). The method aims to accurately classify network traffic by learning temporal patterns of both normal and malicious activities. SMOTE is employed to balance the dataset, ensuring that underrepresented attack types receive adequate model attention, thereby improving model robustness. The proposed models (LSTM, GRU, and BiLSTM) are trained and evaluated on the NSL-KDD dataset, with hyperparameter tuning performed through RandomizedSearchCV for optimal performance. The results show a significant improvement in accuracy, precision, recall, and F1-score, with BiLSTM demonstrating the highest performance, achieving near-perfect classification results (99.5% accuracy). This method not only mitigates the issue of class imbalance but also leverages the power of RNNs for sequence modeling, offering a promising solution for effective intrusion detection in modern networks.
- Open Access
- 1 December 2024
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 14 (6) , 6551-6559
Revolutionizing brain tumor diagnoses: a ResNet18 and focal loss approach to magnetic resonance imaging-based classification in neuro-oncology
Brain tumor diagnosis remains a critical challenge in neuro- oncology, where accurate and timely identification of malignancies can significantly impact patient outcomes. This research explores the integration of deep learning techniques, specifically leveraging the ResNet18 architecture coupled with focal loss, to enhance the classification accuracy of magnetic resonance imaging (MRI)-based brain tumor diagnoses. ResNet18, known for its powerful feature extraction capabilities, was employed to analyze MRI scans, while focal loss was utilized to address class imbalance issues prevalent in medical datasets. The model was trained on a comprehensive dataset, achieving an accuracy of 95.54%. These results demonstrate the potential of this approach in providing robust and precise diagnostic support in clinical settings, potentially revolutionizing the current methodologies in brain tumor detection and classification. The integration of advanced neural networks with specialized loss functions presents a significant advancement in the field, paving the way for more reliable and automated neuro-oncological diagnostics.
- 1 December 2024
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 14 (6) , 6551-6559
Open AccessRevolutionizing brain tumor diagnoses: a ResNet18 and focal loss approach to magnetic resonance imaging-based classification in neuro-oncology
Brain tumor diagnosis remains a critical challenge in neuro- oncology, where accurate and timely identification of malignancies can significantly impact patient outcomes. This research explores the integration of deep learning techniques, specifically leveraging the ResNet18 architecture coupled with focal loss, to enhance the classification accuracy of magnetic resonance imaging (MRI)-based brain tumor diagnoses. ResNet18, known for its powerful feature extraction capabilities, was employed to analyze MRI scans, while focal loss was utilized to address class imbalance issues prevalent in medical datasets. The model was trained on a comprehensive dataset, achieving an accuracy of 95.54%. These results demonstrate the potential of this approach in providing robust and precise diagnostic support in clinical settings, potentially revolutionizing the current methodologies in brain tumor detection and classification. The integration of advanced neural networks with specialized loss functions presents a significant advancement in the field, paving the way for more reliable and automated neuro-oncological diagnostics.
- Open Access
- 1 August 2023
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 13 (4) , 4432-4440
An efficient ultra-wideband digital transceiver for wireless applications on the field-programmable gate array platform
The ultra-wideband (UWB) technology is a promising short-range communication technology for most wireless applications. The UWB works at higher frequencies and is affected by interferences with the same frequency standards. This manuscript has designed an efficient and low-cost implementation of IEEE 802.15.4a-based UWB-digital transceiver (DTR). The design module contains UWB transmitter (TX), channel, and UWB-receiver (RX) units. Convolutional encoding and modulation units like burst position modulation and binary phase-shift keying modulation are used to construct the UWB-TX. The synchronization and Viterbi decoder units are used to recover the original data bits and are affected by noise in UWB-RX. The UWB-DTR is synthesized using Xilinx ISE® environment with Verilog hardware description language (HDL) and implemented on Artix-7 field-programmable gate array (FPGA). The UWB-DTR utilizes less than 2% (slices and look-up table/LUTs), operates at 268 MHz, and consumes 91 mW of total power on FPGA. The transceiver achieves a 6.86 Mbps data rate, which meets the IEEE 802.15.4a standard. The UWB-DTR module obtains the bit error rate (BER) of 2×10-4 by transmitting 105 data bits. The UWB-DTR module is compared with similar physical layer (PHY) transceivers with improvements in chip area (slices), power, data rate, and BER.
- 1 August 2023
- Published by Institute of Advanced Engineering and Science in International Journal of Electrical and Computer Engineering (IJECE)
- Vol. 13 (4) , 4432-4440
Open AccessAn efficient ultra-wideband digital transceiver for wireless applications on the field-programmable gate array platform
The ultra-wideband (UWB) technology is a promising short-range communication technology for most wireless applications. The UWB works at higher frequencies and is affected by interferences with the same frequency standards. This manuscript has designed an efficient and low-cost implementation of IEEE 802.15.4a-based UWB-digital transceiver (DTR). The design module contains UWB transmitter (TX), channel, and UWB-receiver (RX) units. Convolutional encoding and modulation units like burst position modulation and binary phase-shift keying modulation are used to construct the UWB-TX. The synchronization and Viterbi decoder units are used to recover the original data bits and are affected by noise in UWB-RX. The UWB-DTR is synthesized using Xilinx ISE® environment with Verilog hardware description language (HDL) and implemented on Artix-7 field-programmable gate array (FPGA). The UWB-DTR utilizes less than 2% (slices and look-up table/LUTs), operates at 268 MHz, and consumes 91 mW of total power on FPGA. The transceiver achieves a 6.86 Mbps data rate, which meets the IEEE 802.15.4a standard. The UWB-DTR module obtains the bit error rate (BER) of 2×10-4 by transmitting 105 data bits. The UWB-DTR module is compared with similar physical layer (PHY) transceivers with improvements in chip area (slices), power, data rate, and BER.