INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,  
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)  
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue XII, December 2025  
AI-Enabled Cognitive Radio Systems: Balancing Energy Efficiency  
and Communication Performance  
1 Tapan Kumar Singh, 1 Arvind Kumar, 1 Sharad Kumar, 2 Vikas Sharma  
1 School of Engineering & Technology, Shri Venkateshwara University, Gajraula, U.P. India  
2 Department of Computer Applications, SRM Institute of Science and Technology, Delhi NCR Campus,  
Ghaziabad, U.P. India  
DOI : https://doi.org/10.51583/IJLTEMAS.2025.1412000059  
Received: 22 December 2025; Accepted: 28 December 2025; Published: 03 January 2026  
ABSTRACT  
The rapid growth of wireless communication devices has intensified the need for efficient spectrum utilization  
and sustainable energy consumption. Cognitive Radio (CR) systems offer a promising solution by dynamically  
accessing underutilized frequency bands, but energy consumption remains a critical concern. This paper  
proposes an AI-enabled framework for cognitive radio networks that intelligently balances energy efficiency  
with communication performance. Leveraging machine learning algorithms, the system optimizes spectrum  
sensing, power allocation, and transmission scheduling to minimize power usage while maximizing  
throughput. Simulation results demonstrate that the proposed approach significantly reduces energy  
consumption without compromising data rates, highlighting its potential for green wireless communications.  
The integration of AI in CR networks paves the way for more adaptive, energy-aware, and high-performance  
communication systems.  
Keywords— Cognitive Radio, Energy Efficiency, Artificial Intelligence, Machine Learning, Spectrum  
Sensing, Power Optimization, Throughput Maximization, Green Wireless Communication.  
INTRODUCTION  
The exponential growth of wireless communication services, driven by the proliferation of smartphones, IoT  
devices, and emerging 5G and beyond networks, has created unprecedented demand for radio spectrum.  
Traditional static spectrum allocation policies have led to inefficient spectrum utilization, with some bands  
being heavily congested while others remain underused. Cognitive Radio (CR) technology has emerged as a  
transformative solution to this problem, offering the ability to dynamically sense, access, and utilize vacant  
spectrum bands without causing interference to licensed users. CR networks are thus poised to enhance  
spectrum efficiency, improve connectivity, and support the ever-increasing data requirements of modern  
wireless systems. Despite their potential, one of the major challenges in deploying cognitive radio networks is  
energy consumption. Spectrum sensing, frequent channel switching, and adaptive transmission mechanisms  
inherently require significant computational and transmission power. In the context of battery-powered devices  
and large-scale wireless sensor networks, excessive energy consumption can limit network lifetime, reduce  
system reliability, and hinder sustainable communication practices. Consequently, achieving a balance  
between high communication performance, such as throughput and latency, and energy efficiency has become  
a critical research focus in CR system design. Artificial Intelligence (AI) and Machine Learning (ML)  
techniques offer a promising approach to address these challenges. By leveraging AI algorithms, CR systems  
can intelligently predict spectrum availability, optimize power allocation, and dynamically adjust transmission  
parameters, thereby reducing unnecessary energy expenditure while maintaining or improving overall network  
throughput. Techniques such as reinforcement learning, deep learning, and supervised learning enable  
cognitive radios to learn from historical network behavior, adapt to changing environmental conditions, and  
make real-time decisions that optimize performance metrics. This integration of AI transforms traditional CR  
systems into intelligent, energy-aware networks capable of self-optimization.  
www.ijltemas.in  
Page 651  
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,  
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)  
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue XII, December 2025  
AI-Enabled Cognitive Radio Framework Architecture  
Recent research has demonstrated the potential of AI-driven approaches in cognitive radio networks. For  
instance, reinforcement learning has been successfully applied to dynamically select optimal channels and  
transmission powers, minimizing interference and energy consumption. Similarly, deep neural networks have  
been employed for spectrum prediction and anomaly detection, reducing the need for continuous spectrum  
sensing and thereby conserving energy. Despite these advancements, existing methods often face trade-offs  
between complexity, computational overhead, and real-time adaptability. Moreover, integrating energy  
efficiency objectives with throughput maximization in a unified AI framework remains an open research  
challenge, particularly for heterogeneous and large-scale CR networks. This paper aims to address these  
challenges by proposing an AI-enabled cognitive radio framework that effectively balances energy efficiency  
with communication performance shown in Fig. 1. The proposed system leverages advanced machine learning  
algorithms to intelligently manage spectrum access, optimize power usage, and enhance throughput in real-  
time. By focusing on both energy conservation and high-performance communication, the framework supports  
sustainable wireless operations while meeting the growing demands of next-generation networks. Furthermore,  
the study evaluates the proposed approach through extensive simulations, demonstrating significant reductions  
in energy consumption without compromising network throughput, latency, or reliability.  
LITERATURE REVIEW  
Cognitive Radio (CR) technology has been extensively studied as a means to improve spectrum utilization and  
support dynamic spectrum access. Monisha et al. [1] investigated cooperative sensing strategies in  
heterogeneous spectrum environments, highlighting the importance of collaborative decision-making among  
secondary users (SUs) to enhance spectrum detection accuracy. Their work demonstrated that cooperative  
mechanisms can significantly improve spectrum availability prediction, forming a foundation for energy-  
efficient CR operations. Energy efficiency in CR networks has emerged as a critical design consideration due to  
the limited power resources of secondary devices. Elnaim et al. [2] explored the integration of cognitive radio  
networks with multi-access edge computing (MEC), focusing on minimizing energy consumption while  
maintaining computational performance. Their study highlighted that offloading computational tasks to edge  
servers can reduce on-device energy consumption, an approach relevant to AI-enabled CR systems. Premalatha  
and Singh [3] proposed a hybrid spectrum handover mechanism to optimize power usage in CR networks,  
demonstrating that intelligent handover decisions can reduce unnecessary transmission and sensing energy,  
thereby extending the network lifetime. Several studies have proposed energy-aware algorithms for access  
selection in CR and wireless sensor networks. Kalpana and Gunasundari [4] presented an energy-efficient  
access selection algorithm for cognitive wireless sensor networks, emphasizing the trade-off between energy  
savings and communication reliability. Their findings underscore the potential of algorithmic optimization to  
enhance energy efficiency in heterogeneous wireless environments. Similarly, Ge et al. [5] investigated the use  
of active reconfigurable intelligent surfaces (RIS) to enhance spectrum sensing, improving detection accuracy  
while reducing energy-intensive sensing operations. Emerging technologies, such as blockchain, have also been  
leveraged to support energy conservation in CR systems. Sharma et al. [6] proposed a blockchain-based strategy  
www.ijltemas.in  
Page 652  
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,  
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)  
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue XII, December 2025  
for cognitive wireless sensor networks, enabling secure and energy-efficient coordination among network  
nodes. Their approach demonstrated reduced energy overhead while maintaining reliability and trustworthiness  
in decentralized networks. Complementing these approaches, Sayed et al. [7] explored optimal energy  
management in home networks integrating photovoltaic systems and electric vehicles, highlighting optimization  
strategies that can be adapted for CR networks to reduce energy consumption while maximizing operational  
performance. Comprehensive reviews of CR technology and its applications indicate the growing relevance of  
AI in energy-efficient spectrum management. Al-Sudani et al. [8] provided an overview of CR trends,  
emphasizing the integration of intelligent decision-making mechanisms to improve spectrum utilization and  
energy efficiency. Recent works also explore CR applications in IoT and vehicular networks. For instance, D et  
al. [9] and Vashisht et al. [10] demonstrated the use of IoT-enabled wireless communication systems for smart  
monitoring and safety applications, highlighting the potential for AI-enhanced CR networks to optimize energy  
usage in real-world IoT deployments. Resource allocation and channel estimation strategies have been proposed  
to further improve energy efficiency in wireless networks. Lalitha and Reddy [11] developed a quality-of-  
service aided power-aware resource allocation mechanism for wireless sensor networks, demonstrating that  
adaptive allocation based on channel conditions can minimize energy consumption without sacrificing  
performance. Additionally, Moumena [12] addressed security considerations in wideband cooperative CR  
systems, combining principal component analysis (PCA) for anomaly detection with cooperative spectrum  
sensing, ensuring robust performance in the presence of malicious attacks while optimizing energy utilization.  
PROPOSED METHODOLOGY  
The proposed methodology focuses on the systematic design, simulation, and performance evaluation of AI-  
enabled cognitive radio (CR) systems, emphasizing energy efficiency while maximizing throughput. The  
methodology is structured into distinct phases to ensure a thorough understanding of spectrum sensing, power  
management, AI-based optimization, and real-time decision-making in CR networks, addressing critical  
challenges such as dynamic spectrum access, energy-aware transmission, and interference mitigation.  
1. System Model and Assumptions: The cognitive radio system is modelled as a network of secondary users  
(SUs) accessing the spectrum opportunistically without interfering with licensed primary users (PUs). Each SU  
is assumed to have sensing, transmission, and computation capabilities, and is powered by limited energy  
resources. Spectrum availability is dynamic, with channel occupancy modelled as a stochastic process. The  
system assumes ideal synchronization for spectrum sensing, and realistic constraints are applied for  
transmission power, sensing duration, and energy consumption. AI algorithms are integrated into the CR  
system to predict spectrum occupancy, optimize power allocation, and dynamically adjust transmission  
parameters based on observed network conditions.  
2. Problem Formulation: The design problem is formulated as a multi-objective optimization task, aiming to  
minimize total energy consumption while maximizing throughput and maintaining reliable communication.  
Constraints include maximum transmission power, interference thresholds for primary users, energy budgets of  
secondary users, and quality-of-service requirements. The problem incorporates trade-offs between sensing  
accuracy, sensing frequency, and power usage. Parametric analysis is conducted to evaluate the impact of  
critical variables such as sensing duration, number of channels monitored, transmission power levels, and AI  
algorithm hyperparameters on overall network performance.  
3. AI-Based Spectrum Sensing and Power Optimization: Spectrum sensing and power allocation are  
enhanced using machine learning techniques. Supervised learning models are employed for predicting channel  
occupancy based on historical spectrum data, reducing unnecessary sensing operations and associated energy  
consumption. Reinforcement learning agents are utilized to dynamically adjust transmission power and select  
optimal channels, balancing energy efficiency with throughput maximization. The system iteratively learns  
from network feedback, continuously adapting to changing spectrum conditions, interference patterns, and  
energy availability. Simulation-based studies are conducted to assess AI model convergence, prediction  
accuracy, and decision-making latency.  
www.ijltemas.in  
Page 653  
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,  
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)  
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue XII, December 2025  
4. Comparative Perspective on AI Techniques for Spectrum Prediction and Power Optimization: A  
comparative perspective of different AI techniques highlights their suitability for spectrum prediction and  
power optimization in cognitive radio networks. Reinforcement learning (RL) is particularly effective in  
dynamic and uncertain environments, as it enables secondary users to learn optimal spectrum access and power  
control policies through interaction with the radio environment without requiring labeled data. RL-based  
approaches adapt well to time-varying spectrum availability but may suffer from slower convergence in highly  
complex scenarios. In contrast, deep learning (DL) techniques, such as deep neural networks and convolutional  
neural networks, provide high prediction accuracy for spectrum occupancy by learning complex patterns from  
historical data; however, they generally require larger datasets and higher computational resources. For real-  
time and resource-constrained cognitive radio devices, lightweight RL models offer better adaptability, while  
DL-based models are more suitable for centralized or edge-assisted architectures where computational capacity  
is sufficient. This study adopts an AI-driven approach that emphasizes adaptability and energy awareness,  
making it suitable for practical CR deployments.  
5. Throughput Maximization and Energy Minimization Strategies: To achieve throughput optimization  
without compromising energy efficiency, adaptive strategies such as dynamic channel selection, power  
control, and duty cycling are implemented. AI models prioritize channels with higher predicted availability and  
lower interference to improve spectral efficiency. Energy consumption is minimized by adjusting sensing  
intervals and transmission power based on real-time network conditions. Multi-objective optimization  
techniques are employed to explore the trade-offs between energy usage and throughput, providing optimal  
operating points for different network scenarios.  
6. Simulation and Performance Evaluation: The proposed CR system is simulated using network simulation  
tools and MATLAB-based AI frameworks. Performance metrics such as energy consumption, throughput,  
spectrum utilization, and interference with primary users are measured. Parametric studies evaluate the effect  
of AI model parameters, sensing strategies, and network topology on system performance. Comparative  
analyses are conducted with conventional CR systems lacking AI integration to quantify improvements in  
energy efficiency and communication performance.  
7. Comparative Analysis and Optimization: A detailed comparative study is performed to assess the benefits  
of AI-enabled CR systems over traditional methods. Sensitivity analysis examines the impact of design  
parameters—including sensing accuracy, AI learning rate, and transmission power—on energy and throughput  
performance. Results are analysed to identify optimal configurations, performance trade-offs, and practical  
deployment strategies. The methodology ensures a robust, energy-aware, and high-performance solution  
suitable for modern wireless communication networks, supporting sustainable and adaptive spectrum  
management.  
8. Computational Complexity and Latency Analysis: The computational complexity and latency of the  
proposed AI-enabled cognitive radio framework are critical factors for practical deployment in resource-  
limited devices. The learning-based spectrum sensing and power optimization mechanisms introduce  
additional processing overhead compared to conventional CR systems; however, this overhead is mitigated  
through reduced sensing frequency and adaptive decision-making. The computational complexity primarily  
depends on the AI model size, learning rate, and state-action space, which are kept moderate to ensure real-  
time operation. Decision latency remains within acceptable limits for CR applications, as spectrum access and  
power allocation decisions are made over discrete time slots rather than continuous processing. Overall, the  
trade-off between computational overhead and energy savings is favourable, as the reduced sensing and  
transmission energy significantly outweigh the additional processing cost introduced by AI algorithms.  
RESULT & ANALYSIS  
The proposed AI-enabled cognitive radio (CR) system was evaluated through extensive MATLAB-based  
simulations to assess energy consumption, throughput, and spectrum utilization. Performance was compared  
against a conventional CR system without AI-based optimization. The simulation environment consisted of 20  
secondary users (SUs) operating over 10 licensed channels with dynamic primary user (PU) activity modeled  
www.ijltemas.in  
Page 654  
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,  
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)  
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue XII, December 2025  
as a Markov process. The total simulation duration was 1000 time slots, with energy consumption, throughput,  
and channel utilization measured for both approaches. Although the proposed framework is evaluated through  
extensive simulations, its design closely aligns with real-world cognitive radio deployments. The system  
assumptions are consistent with practical CR architectures using spectrum sensing modules, adaptive  
transceivers, and energy-constrained devices. Moreover, the AI-based learning mechanisms can be trained and  
validated using publicly available spectrum measurement datasets, such as real-time spectrum occupancy  
traces collected from urban wireless environments. These datasets can be leveraged to further validate the  
prediction accuracy and energy optimization capability of the proposed approach, thereby enhancing its  
applicability to real-world cognitive radio systems.  
1. Energy Consumption Analysis: Energy consumption was measured in joules (J) for each SU over the  
simulation period. Table 1 summarizes the average energy consumption per SU for different spectrum sensing  
strategies. The AI-enabled CR system demonstrates a significant reduction in energy usage by minimizing  
unnecessary sensing operations and optimizing transmission power.  
Average Energy Consumption per Secondary User  
Average  
Sensing  
Duration  
(ms)  
Transmission  
Power (mW)  
Energy  
Consumption  
(J)  
Energy Reduction  
(%)  
Method  
Conventional CR  
50  
35  
100  
12.5  
7.8  
-
AI-Enabled  
(Proposed)  
CR  
80  
37.6  
The results indicate that the AI-enabled system reduces energy consumption by approximately 38% compared  
to the conventional approach, primarily due to predictive spectrum sensing and adaptive power control.  
Energy Consumption Comparison per Secondary User  
Fig. 2. comparing average energy consumption per secondary user for two cognitive radio methods. The  
Conventional CR method consumes 12.5 joules, while the AI-enabled cognitive radio (proposed) consumes 7.8  
joules, demonstrating a substantial reduction in energy usage with the proposed approach.  
2. Throughput Performance: Throughput, measured in Mbps, represents the effective data transmission rate  
of secondary users. Table 2 compares the average throughput achieved by conventional and AI-enabled CR  
systems.  
www.ijltemas.in  
Page 655  
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,  
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)  
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue XII, December 2025  
Average Throughput Comparison  
Average Throughput  
(Mbps)  
Throughput  
Improvement (%)  
Method  
Conventional CR  
14.2  
17.5  
-
AI-Enabled CR (Proposed)  
23.2  
The AI-enabled CR system improves average throughput by 23% due to intelligent channel selection,  
predictive spectrum access, and interference-aware power allocation.  
Average Throughput Performance Comparison  
Fig. 3. comparing average throughput in Mbps for two cognitive radio methods. The Conventional CR  
achieves an average throughput of 14.2 Mbps, while the AI-enabled cognitive radio (proposed) achieves 17.5  
Mbps, indicating a throughput improvement of approximately 23.2% with the proposed approach.  
3. Spectrum Utilization Efficiency: Spectrum utilization efficiency was calculated as the ratio of time slots  
successfully used by SUs without interfering with PUs. Table 3 shows the spectrum utilization for both  
methods.  
Comparison of Spectrum Utilization Efficiency  
Spectrum  
Utilization (%)  
PU Interference  
Events  
Method  
Conventional CR  
72  
89  
15  
5
AI-Enabled CR (Proposed)  
The proposed system increases spectrum utilization to 89% while reducing PU interference events from 15 to  
5, highlighting its effectiveness in dynamic spectrum management.  
www.ijltemas.in  
Page 656  
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,  
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)  
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue XII, December 2025  
Spectrum Utilization Efficiency Comparison  
Fig. 4. comparing spectrum utilization efficiency for two cognitive radio methods. The Conventional CR  
achieves 72% spectrum utilization, whereas the AI-enabled cognitive radio (proposed) achieves 89%  
utilization. The higher utilization of the proposed method indicates more efficient spectrum usage along with  
reduced primary user interference events. The results demonstrate that AI integration in CR systems offers a  
clear advantage in both energy efficiency and communication performance. The reduction in energy  
consumption is attributed to predictive spectrum sensing, where channels are only sensed when likely to be  
vacant, and adaptive power control that minimizes unnecessary transmission power. Simultaneously,  
throughput improvement arises from optimal channel selection and interference avoidance, enabled by AI-  
based learning and prediction.  
CONCLUSION  
This paper presented an AI-enabled cognitive radio system designed to balance energy efficiency and  
communication performance. By integrating machine learning techniques for predictive spectrum sensing,  
adaptive power allocation, and dynamic channel selection, the proposed system significantly reduces energy  
consumption while enhancing throughput and spectrum utilization compared to conventional cognitive radio  
approaches. Simulation results demonstrate a reduction in energy usage by approximately 38%, a throughput  
improvement of 23%, and increased spectrum efficiency with minimal interference to primary users. These  
findings highlight the potential of AI-driven cognitive radios for sustainable and high-performance wireless  
communications. For future work, the proposed framework can be extended to incorporate deep reinforcement  
learning for large-scale heterogeneous networks, multi-agent coordination for cooperative spectrum access,  
and real-world deployment scenarios, including IoT and 5G/6G systems, to further optimize energy utilization  
and network reliability under dynamic and complex environments.  
REFERENCES  
1. M. Monisha, P. Vijayalakshmi, K. Somasundaram, N. Arunraj, P. Sathishkumar and M. Meena,  
"Cooperative Sensing with Heterogeneous Spectrum Availability in Cognitive Radio," 2022  
International Conference on Power, Energy, Control and Transmission Systems (ICPECTS), Chennai,  
India, 2022, pp. 1-6, doi: 10.1109/ICPECTS56089.2022.10047411.  
2. A. A. Elnaim et al., "Energy Consumption for Cognitive Radio Network Enabled Multi-Access Edge  
Computing," 2023 3rd International Conference on Emerging Smart Technologies and Applications  
(eSmarTA), Taiz, Yemen, 2023, pp. 1-5, doi: 10.1109/eSmarTA59349.2023.10293270.  
3. M. Premalatha and N. Singh, "Increased Efficient Usage of Power in Cognitive Radio Networks  
Utilizing Hybridized Handover of Spectrum," 2024 5th International Conference for Emerging  
Technology (INCET), Belgaum, India, 2024, pp. 1-5, doi: 10.1109/INCET61516.2024.10593262.  
www.ijltemas.in  
Page 657  
INTERNATIONAL JOURNAL OF LATEST TECHNOLOGY IN ENGINEERING,  
MANAGEMENT & APPLIED SCIENCE (IJLTEMAS)  
ISSN 2278-2540 | DOI: 10.51583/IJLTEMAS | Volume XIV, Issue XII, December 2025  
4. S. Kalpana and R. Gunasundari, "Energy Efficient Access Selection Algorithm using Cognitive  
Wireless Sensor Networks," 2022 International Conference on Smart Technologies and Systems for  
Next  
Generation  
Computing  
(ICSTSN),  
Villupuram,  
India,  
2022,  
pp.  
1-4,  
doi:  
10.1109/ICSTSN53084.2022.9761337.  
5. J. Ge, Y. -C. Liang and S. Sun, "Active RIS Enhanced Spectrum Sensing for Opportunistic Cognitive  
Radio Networks," GLOBECOM 2023 - 2023 IEEE Global Communications Conference, Kuala  
Lumpur, Malaysia, 2023, pp. 3252-3257, doi: 10.1109/GLOBECOM54140.2023.10436997.  
6. K. Sharma, R. Goyal, S. K. Bhagat, S. Agarwal, G. S. Bisht and M. Hussien, "A Novel Blockchain-  
Based Strategy for Energy Conservation in Cognitive Wireless Sensor Networks," 2024 4th  
International Conference on Blockchain Technology and Information Security (ICBCTIS), Wuhan,  
China, 2024, pp. 314-319, doi: 10.1109/ICBCTIS64495.2024.00056.  
7. S. E. Sayed, R. Ahmed and A. El-Zonkoly, "Optimal Home Energy Management Algorithm  
Incorporating PVs/Electric Vehicles," 2024 6th International Youth Conference on Radio Electronics,  
Electrical and Power Engineering (REEPE), Moscow, Russian Federation, 2024, pp. 1-6, doi:  
10.1109/REEPE60449.2024.10479736.  
8. H. Al-Sudani, A. A. Thabit and Y. Dalveren, "Cognitive Radio and Its Applications in the New Trend  
of Communication System: A Review," 2022 5th International Conference on Engineering Technology  
and  
its  
Applications  
(IICETA),  
Al-Najaf,  
Iraq,  
2022,  
pp.  
419-423,  
doi:  
10.1109/IICETA54559.2022.9888674.  
9. S. K. D, L. S. A. Busala, R. Bade, A. Dandasi and L. Jakkani, "IoT Based Smart Trash Bin for Level  
and Harmful Gases Indication System," 2025 6th International Conference on Data Intelligence and  
Cognitive  
Informatics  
(ICDICI),  
Tirunelveli,  
India,  
2025,  
pp.  
1833-1839,  
doi:  
10.1109/ICDICI66477.2025.11135363.  
10. S. Vashisht, N. Kumar and S. Awasthi, "Dual-Node LoRa-Enabled Obstacle Detection and Rider  
Notification System for Enhancing Safety in Two-Wheeler Vehicles with Wireless Communication,"  
2025 International Conference on Cognitive Computing in Engineering, Communications, Sciences  
and Biomedical Health Informatics (IC3ECSBHI), Greater Noida, India, 2025, pp. 1528-1532, doi:  
10.1109/IC3ECSBHI63591.2025.10991224.  
11. A. Lalitha and G. H. Reddy, "Quality of Service Aided Power Aware Resource Allocation  
Optimization with Channel Estimation in Wireless Sensor Network," 2023 Second International  
Conference on Augmented Intelligence and Sustainable Systems (ICAISS), Trichy, India, 2023, pp.  
1278-1285, doi: 10.1109/ICAISS58487.2023.10250507.  
12. A. Moumena, "Centralized Wideband Cooperative CRs Combined with PCA Anomaly Detector in the  
Presence of malicious Attacks," 2022 7th International Conference on Image and Signal Processing and  
their Applications (ISPA), Mostaganem, Algeria, 2022, pp. 1-8, doi:  
10.1109/ISPA54004.2022.9786282.  
www.ijltemas.in  
Page 658