Dileep P
Research Subjects
Dileep P has a total of 17 co-authors. Here are the top co-authors by number of shared publications:
- A. Prashanthi
Nalla Narasimha Reddy Education Society’s Group of Institutions, Hyderabad, India
1 shared publication - Bandi Rambabu
CVR College of Engineering
1 shared publication - Duraisamy Suganthi
Department of Computer Science, Saveetha College of Liberal Arts and Sciences, SIMATS, Thandalam, Chennai, India
1 shared publication - Jaibir Singh
Associate Professor ,Lovely Professional University, Department: Computer Science & Engineering, Punjab, India
1 shared publication - Jayanthi Jegannathan
Department of CSE, Sona College of Technology, Salem, India
1 shared publication - M. Durairaj
Department of ECE, Saveetha School of Engineering, SIMATS, Chennai, India
1 shared publication
Latest Publications
- Open Access
- 2 March 2026
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 19 (1)
Group-Based Recommendation System Using Bi-Stage Adaptive Deep Learning Model
Recommender systems (RS) are utilized in various domains, including travel, movies, and music. The increase in social activity has led to an increase in the usage of RS in individual and group recommender systems (GRS). A GRS recommends perfect items to users according to their preferences. A bi-stage adaptive deep learning-based group recommendation system model is proposed to overcome these challenges. The aim of the proposed Bi-stage Adaptive Deep Learning-based GRS (BADLGRS) is to enhance the effectiveness of GRSs. At the GRL level, an undirected Tripartite Graph (TG) represents the interaction among groups, users, and items. Then, constructing a TG effectively represents the semantic features of both users and items within the group context. Then, a novel Deep Learning (DL) network, the Gated Recurrent Unit-based Attention Neural Network, is used to learn the semantic features of the group. Generate optimized semantic features t o produce refined and optimized semantic feature representations for both users and items, which are fed into the next stage. A two-layer graph convolutional network (TGCN) is employed for user preference learning at the GPL level, enabling the accurate learning and capture of individual user preferences. After learning the group’s preferences, we employ the Pairwise Learning Method (PLM) to effectively learn and model the aggregated preferences of the group. Additionally, the Network model optimizes the parameters of the two-layered network within the GPL stage using the PLM. Additionally, the proposed model is validated using four different datasets and outperforms existing models in terms of HR, NDCG, MAP, accuracy, recall, and f1-score for group recommendation. The proposed model acquired enhanced outcomes in terms of various assessment metrics like accuracy of 0.893, which is 28.33%, 28.89%, 29.79%, 26.54%, 25.20%, 23.96%, 22.73%, and 17.02% superior to DFM-AVG, DFM-LM, DFM-MS, COM, DPMF-CNN, AGR, AGREE, and MAGRM methods.
- 2 March 2026
- Published by Springer Nature in International Journal of Computational Intelligence Systems
- Vol. 19 (1)
Open AccessGroup-Based Recommendation System Using Bi-Stage Adaptive Deep Learning Model
Recommender systems (RS) are utilized in various domains, including travel, movies, and music. The increase in social activity has led to an increase in the usage of RS in individual and group recommender systems (GRS). A GRS recommends perfect items to users according to their preferences. A bi-stage adaptive deep learning-based group recommendation system model is proposed to overcome these challenges. The aim of the proposed Bi-stage Adaptive Deep Learning-based GRS (BADLGRS) is to enhance the effectiveness of GRSs. At the GRL level, an undirected Tripartite Graph (TG) represents the interaction among groups, users, and items. Then, constructing a TG effectively represents the semantic features of both users and items within the group context. Then, a novel Deep Learning (DL) network, the Gated Recurrent Unit-based Attention Neural Network, is used to learn the semantic features of the group. Generate optimized semantic features t o produce refined and optimized semantic feature representations for both users and items, which are fed into the next stage. A two-layer graph convolutional network (TGCN) is employed for user preference learning at the GPL level, enabling the accurate learning and capture of individual user preferences. After learning the group’s preferences, we employ the Pairwise Learning Method (PLM) to effectively learn and model the aggregated preferences of the group. Additionally, the Network model optimizes the parameters of the two-layered network within the GPL stage using the PLM. Additionally, the proposed model is validated using four different datasets and outperforms existing models in terms of HR, NDCG, MAP, accuracy, recall, and f1-score for group recommendation. The proposed model acquired enhanced outcomes in terms of various assessment metrics like accuracy of 0.893, which is 28.33%, 28.89%, 29.79%, 26.54%, 25.20%, 23.96%, 22.73%, and 17.02% superior to DFM-AVG, DFM-LM, DFM-MS, COM, DPMF-CNN, AGR, AGREE, and MAGRM methods.
- Open Access
- 2 October 2024
- Published by Iskender AKKURT in International Journal of Computational and Experimental Science and Engineering
- Vol. 10 (4)
Autonomic Resilience in Cybersecurity: Designing the Self-Healing Network Protocol for Next-Generation Software-Defined Networking
This study rigorously compares the Self-Healing Network Protocol (SHNP) with a traditional protocol, utilizing simulations and data analysis to examine crucial network performance metrics.The research meticulously assesses latency averages—a critical measure of network responsiveness; peak data transfer rates, indicative of the network's throughput capabilities; average resource utilization, reflective of network efficiency; and resilience ratings, which gauge the network's ability to withstand and recover from operational perturbations. The SHNP emerges as a robust solution, significantly lowering latency to an average of 38.53 milliseconds, thereby facilitating expedited real-time data transmission. It also achieves notable resource utilization efficiency, evidenced by a 48.14% improvement, and shows enhanced resilience with a rating near 1.47, solidifying its superior dependability in challenging conditions. Conversely, the conventional protocol shines in its peak data transfer rate, reaching around 860.05 Mbps, which may be advantageous in situations demanding high-speed data handling. The insights derived from this analysis are pivotal for network managers and strategists, offering a nuanced perspective that supports strategic decision-making in protocol selection to meet precise network performance goals and adapt to specific operational contexts. This study underscores the dynamic evolution of network protocols and serves as a guidepost for stakeholders in selecting the most fitting protocol to meet their network's unique needs and challenges.
- 2 October 2024
- Published by Iskender AKKURT in International Journal of Computational and Experimental Science and Engineering
- Vol. 10 (4)
Open AccessAutonomic Resilience in Cybersecurity: Designing the Self-Healing Network Protocol for Next-Generation Software-Defined Networking
This study rigorously compares the Self-Healing Network Protocol (SHNP) with a traditional protocol, utilizing simulations and data analysis to examine crucial network performance metrics.The research meticulously assesses latency averages—a critical measure of network responsiveness; peak data transfer rates, indicative of the network's throughput capabilities; average resource utilization, reflective of network efficiency; and resilience ratings, which gauge the network's ability to withstand and recover from operational perturbations. The SHNP emerges as a robust solution, significantly lowering latency to an average of 38.53 milliseconds, thereby facilitating expedited real-time data transmission. It also achieves notable resource utilization efficiency, evidenced by a 48.14% improvement, and shows enhanced resilience with a rating near 1.47, solidifying its superior dependability in challenging conditions. Conversely, the conventional protocol shines in its peak data transfer rate, reaching around 860.05 Mbps, which may be advantageous in situations demanding high-speed data handling. The insights derived from this analysis are pivotal for network managers and strategists, offering a nuanced perspective that supports strategic decision-making in protocol selection to meet precise network performance goals and adapt to specific operational contexts. This study underscores the dynamic evolution of network protocols and serves as a guidepost for stakeholders in selecting the most fitting protocol to meet their network's unique needs and challenges.
- 15 September 2023
- Published by Springer Nature in Spatial Information Research
- Vol. 32 (2) , 1-8
AI-driven drowned-detection system for rapid coastal rescue operations
- 15 September 2023
- Published by Springer Nature in Spatial Information Research
- Vol. 32 (2) , 1-8
AI-driven drowned-detection system for rapid coastal rescue operations