Group-Based Recommendation System Using Bi-Stage Adaptive Deep Learning Model Yojitha Chilukuri, A. Prashanthi, M. V. Kamal, P. Dileep, Rakesh Kumar Donthi, Nemala Jayasri, Ulligaddala Srinivasarao International Journal of Computational Intelligence Systems, 2026 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 to 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.
Prognosticate of Gestational Diabetes Mellitus (GDM) to Anticipate Preeclampsia Srinivasa Reddy Seelam, Bala Veeravatnam, Veena Nanda Jaya Krishna, Mantri Gayatri, M V Kamal, Animoni Nagaraju Icrteect 2025 2nd International Conference on Recent Trends in Electrical Electronics and Computing Technologies, 2025 This paper introduces a new way to predict Gestational Diabetes Mellitus (GDM) using deep learning, specifically Convolutional Neural Networks (CNNs), achieving 92% accuracy in identifying at-risk pregnancies. GDM is a condition that can cause serious complications for both mothers and infants, such as preeclampsia. Early prediction is especially important in places where regular checkups are limited. By analysing clinical data, including patient demographics and medical history, this approach enhances the understanding of risk factors and allows for timely interventions like dietary changes and blood glucose monitoring. Overall, this method represents a significant improvement in maternal care, especially for vulnerable populations, by providing high predictive accuracy and enabling proactive health measures to improve outcomes for mothers and babies.
Hybridizing Spiking Neural Networks and Federated Quantum Learning for Resource Optimization in Next-Gen 6G Architectures M.Rudra Kumar, Madadi Vijayakamal, S. Mohammed Elias Basha, V. N. V. L. S. Swathi, Lavanya Addepalli, Vidya Sagar S. D. Proceedings of 2025 1st International Conference on Radio Frequency Communication and Networks Rfcon 2025, 2025 The call for 6G networks to evolve rapidly into ultra-low latency, high energy efficiency, and intelligent resource allocations is immediate. In this paper, we propose a Holographic Edge Intelligence Framework to distribute computation and decision making among edge devices using spiking neural networks (SNNs) for energy efficient processing and quantum inspired reinforcement learning (QRL) for dynamic resource optimization. Secure and decentralized collaborations are done through a blockchain enabled federated learning mechanism. The framework is validated in a simulated 6G smart city environment and results show significant performance improvements: lower latency, less energy consumption and increased task success rate over traditional methods. This work supplies a novel and scalable basis for future network applications.
Drone/UAV design development is important in a wide range of applications: A critical review M. V. Kamal, P. Dileep, G. Sharada, V. Suneetha, M. Gayatri Drone Technology Future Trends and Practical Applications, 2023 In recent years, flying robots have played an increasingly important and growing role in the mining industry, transportation, as well as civilian and military applications. Moreover, in the last decades, researchers’ attention has focused on the development of new designs of drones for different applications. In this pandemic situation, drones play a significant role in delivering drugs and foods. Drones have the potential to be dependable medical delivery platforms for laboratory and microbiological samples, emergency medical equipment, vaccines, and pharmaceuticals, among other things. Drone use has been prioritized by government agencies. The next steps will include aggressive safety research initiatives, increased public awareness, industry expansion, and participation. A literature survey was carried out to understand the current state of the art and set a research directive for the advanced drones. There is also a great deal of interest in developing novel drones that can fly autonomously in such different locations and environments and perform a wide variety of missions. Besides classification, the discussion also includes the application of drones in various fields. Apart from the design and fabrication challenges of micro drones, the concept of emerging and controlling drones is also discussed in detail here. Furthermore, existing system limitations and controlling factors were revealed. The current applications of drones as well as their future potential in the industry are also discussed.
Unsupervised learning methods for anomaly detection and log quality improvement using process event log International Journal of Advanced Science and Technology, 2020
