iosr-JCE  Volume-28 ~ Issue-3 ~ May - Jun. 2026

Abstract: In this paper, we introduce an approach based on Deep Reinforcement Learning to optimize the RIS-NOMA scheme for the 6G wireless network. Some other parameters considered as actions in the proposed algorithm are clustering of users, power distribution, and RIS phase optimization. The two types of deep reinforcement learning algorithms, namely, SAC and MADDPG, were implemented on the proposed architecture. The performance of the proposed framework has been examined based on some parameters including sum rate, SINR, throughput, delay, energy efficiency, and Jain's fairness index. The suggested MADDPG and SAC models have shown better performance than existing models, based on the obtained results..

Key Word: Deep Reinforcement Learning (DRL), Non-Orthogonal Multiple Access (NOMA), Soft Actor Critic (SAC), Reconfigurable Intelligent Surface (RIS).

[1] Basar, E., Di Renzo, M., de Rosny, J., Debbah, M., Alouini, M. S., and Zhang, R., “Wireless Communications Through Reconfigurable Intelligent Surfaces,” IEEE Access, vol. 7, pp. 116753–116773, 2019.
[2] Chen, J., Zhang, H., and Letaief, K. B., “Multi-Agent Learning for Resource Management in 6G Heterogeneous Networks,” IEEE Journal on Selected Areas in Communications, vol. 42, no. 1, pp. 1–15, Jan. 2024.
[3] Gevez. Y, Y. I. Tek, and E. Basar, “Dynamic RIS partitioning in NOMA systems using deep reinforcement learning,” Frontiers in Antennas and Propagation, vol. 2, Art. no. 1418412, 2024, doi: 10.3389/fanpr.2024.1418412.
[4] Hou, Z., Sun, Y., Song, M., and Zhang, R., “Reconfigurable Intelligent Surface Assisted Non-Orthogonal Multiple Access,” IEEE Transactions on Wireless Communications, vol. 19, no. 11, pp. 6889–6903, Nov. 2020..

Abstract: The fast expansion of IoT systems has led to many problems in ensuring effective and safe data processing with the available computational resources in edge nodes. Conventional techniques used in IoT security systems such as AES need substantial computation power and consume too much energy. In order to overcome this challenge, the presented model applies lightweight cryptography along with the application of the Kalman Filter and adaptive genetic algorithm. The GA-based optimal Kalman filter is able to minimize any possible noise and sudden changes in the sensor data, thus ensuring higher accuracy and reliability of the collected data. According to experimental......

Key Word: Lightweight Cryptography (LWC), IoT Security, Kalman Filter (KF), Genetic Algorithm (GA), Energy Efficiency, Signal Processing

[1] Abdel-Basset, M., Mohamed, R., Elhoseny, M., and Chang, V., “A Novel Energy-Efficient Routing Protocol for IoT,” IEEE Internet of Things Journal, 2020.
[2] Alani, M. M., “Security Challenges and Attack Detection in IoT,” Frontiers in Communications and Networks, 2022.
[3] Al-Fandi, M., Al-Qaisi, L., and Almasri, M., “Energy-Efficient Security Protocols for Wireless Sensor Networks,” Scientific Reports, 2023.
[4] Biryukov, A., and Perrin, L., “State of the Art in Lightweight Symmetric Cryptography,” IACR Cryptology ePrint Archive, 2017.
[5] Daemen, J., and Rijmen, V., “AES Encryption Standard,” National Institute of Standards and Technology (NIST), 2020.

Abstract: Sentiment analysis is an important research area in Natural Language Processing (NLP) which is the automated identification and interpretation of opinions, emotions and attitudes expressed in text data. The growth of user generated content on social media, review systems, discussion forums and digital communication channels has created the demand for accurate and scalable sentiment analysis systems. There has been a lot of work on sentiment analysis in English language, but the development of effective models for multilingual and low-resource languages still remains an intimidating research problem......

Key Word: Sentiment Analysis; Multilingual Sentiment Analysis; Natural Language Processing; Machine Learning; Deep Learning; Transformer Models; BERT; IndicBERT; MuRIL; Large Language Models; Hindi Sentiment Analysis; Marathi Sentiment Analysis; Code-Mixed Text; Low-Resource Languages; Text Classification; Opinion Mining; Social Media Analytics; Explainable Artificial Intelligence; Multimodal Sentiment Analysis; Indian Languages.

[1] Conneau, A., Khandelwal, K., Goyal, N., Chaudhary, V., Wenzek, G., Guzmán, F., Grave, E., Ott, M., Zettlemoyer, L., & Stoyanov, V. (2020). Unsupervised Cross-Lingual Representation Learning at Scale. Proceedings of ACL 2020, 8440–8451.
[2] Kakwani, D., Kunchukuttan, A., Golla, S., Gokul, N., Bhattacharyya, A., Khapra, M. M., & Kumar, P. (2020). IndicNLPsuite: Monolingual Corpora, Evaluation Benchmarks and Pre-trained Multilingual Language Models for Indian Languages. Findings of EMNLP 2020, 4948–4961.
[3] Khanuja, S., Dandapat, S., Kunchukuttan, A., Singh, A., Srinivasan, B., Katti, A., Goyal, P., & Bhattacharyya, P. (2021). MuRIL: Multilingual Representations for Indian Languages. Findings of EMNLP 2021, 4879–4893.
[4] Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. NAACL-HLT, 4171–4186.
[5] Liu, Y., Ott, M., Goyal, N., Du, J., Joshi, M., Chen, D., Levy, O., Lewis, M., Zettlemoyer, L., & Stoyanov, V. (2019). RoBERTa: A Robustly Optimized BERT Pretraining Approach. arXiv:1907.11692.

Abstract: Background: Alzheimer’s disease (AD) is a progressive neurodegenerative disorder in which pathological changes can occur years before clinical symptoms become apparent. Early detection is therefore important for timely intervention. Current diagnostic methods include cognitive assessments, neuroimaging, and biomarker analysis, but these approaches may not reliably identify the disease during its earliest stages and can be expensive or difficult to implement for large-scale screening. Machine learning (ML) has increasingly been applied to this problem because it can identify patterns within complex biomedical datasets.......

Key Word: Alzheimer’s disease; Machine learning; Deep learning; Multimodal data; Early diagnosis; Neurodegenerative disorders.

[1] ADI - Dementia statistics. (n.d.). ADI - Dementia Statistics. https://www.alzint.org/about/dementia-facts-figures/dementia-statistics/
[2] World Health Organization. (n.d.). Dementia. https://www.who.int/news-room/fact-sheets/detail/dementia
[3] Jack, C. R., Bennett, D. A., Blennow, K., Carrillo, M. C., Dunn, B., Haeberlein, S. B., Holtzman, D. M., Jagust, W., Jessen, F., Karlawish, J., Liu, E., Molinuevo, J. L., Montine, T., Phelps, C., Rankin, K. P., Rowe, C. C., Scheltens, P., Siemers, E., Snyder, H. M., & Sperling, R. (2018). NIA-AA research framework: Toward a biological definition of Alzheimer’s disease. Alzheimer’s & Dementia : The Journal of the Alzheimer’s Association, 14(4), 535–562. https://doi.org/10.1016/j.jalz.2018.02.018
[4] Soni, P., Hasan, S. M., Kushwaha, S. P., Singh, K., Kumar, A., Hafeez, A., Suvaiv, Samman, & Khan, S. (2025). Amyloid beta and tau aggregation: The etiology and potential pharmaceutical approaches for Alzheimer’s disease. Biomedical Research and Therapy, 12(9), 7708–7722. https://doi.org/10.15419/rjv09v43
[5] Aksman, L. M., Oxtoby, N. P., Scelsi, M. A., Wijeratne, P. A., Young, A. L., Alves, I. L., Collij, L. E., Vogel, J. W., Barkhof, F., Alexander, D. C., Altmann, A. (2023). A data-driven study of Alzheimer’s disease related amyloid and tau pathology progression. Brain, 146(12), 4935–4948. https://doi.org/10.1093/brain/awad232

Abstract: The forecasting of crop yield and of market price is needed for procurement planning and price-risk management, yet the two are predicted separately, though shared weather and crop conditions drive both. Here the two are forecast together by a single model, a Modified CNN-LSTM with multi-head attention, demonstrated on wheat in Haryana, India. Four public sources are drawn on, namely the crop-yield statistics of DES; daily AGMARKNET prices; the NDVI, EVI, and NDWI indices from Sentinel-2 and MODIS via Google Earth Engine; and ERA5-Land weather data, aligned to a district-week grid. In early fusion, the features are encoded together; in late fusion, yield is predicted first, and its supply signals are passed......

Key Word: Crop yield forecasting, agricultural price prediction, multimodal fusion, CNN-LSTM, explainable AI, wheat.

[1] V. S. Manogna, P. Raju, and K. Lavanya, "On the use of deep learning for improving agricultural commodity price forecasts," Scientific Reports, 2025.
[2] Y. Min, S. Kim, and J. Park, "Graph neural networks and recurrent architectures for international agricultural commodity price prediction," Scientific Reports, 2025.
[3] M. Nayak, B. Nayak, and P. K. Behera, "Agricultural commodity price forecasting via meta-transformer models tuned with meta-heuristic optimisation," Journal of Big Data, 2025.
[4] M. Ashfaq, H. Ali, and K. Rani, "Wheat yield prediction based on fusing climate variables with NDVI through machine learning," IEEE Access, vol. 12, 2024.

Abstract: Background: LiDAR-based 3D object detection is important for intelligent transportation, autonomous driving and roadside perception. PointPillars provides an efficient pillar-based pipeline, but its compact representation may be affected by background noise, sparse small-object points, weak pillar-context modeling and limited proposal refinement, especially when vehicle-side and infrastructure-side scenes are evaluated together. Materials and Methods: This paper proposes HAT-PointPillars, a hierarchical attention transformer framework for vehicle-side and infrastructure-side LiDAR 3D detection. The method includes Depth-Adaptive Density Preprocessing (DADP), Intra-Inter Dual Context Attention (IDCA), an Attention......

Key Word: LiDAR 3D object detection; PointPillars; vehicle-side perception; infrastructure-side perception; proposal refinement; BEV pseudo-image.

[1] Shi S, Wang X, Li H. PointRCNN: 3D object proposal generation and detection from point cloud. In: Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition; 2019 Jun 15-20; Long Beach, CA, USA. p. 770-779.
[2] Qi CR, Su H, Mo K, Guibas LJ. PointNet: deep learning on point sets for 3D classification and segmentation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2017. p. 652-660.
[3] Qi CR, Yi L, Su H, Guibas LJ. PointNet++: deep hierarchical feature learning on point sets in a metric space. In: Advances in Neural Information Processing Systems; 2017. p. 5099-5108.
[4] Zhou Y, Tuzel O. VoxelNet: end-to-end learning for point cloud based 3D object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2018 Jun 18-23; Salt Lake City, UT, USA. p. 4490-4499.
[5] Yan Y, Mao Y, Li B. SECOND: sparsely embedded convolutional detection. Sensors (Basel). 2018;18(10):3337.