iosr-JCE  Volume-28 ~ Issue-1 ~ Jan. - Feb. 2026

Abstract: Forecasting palm oil price volatility is challenging due to nonlinear dynamics and temporal dependencies inherent in agricultural commodity markets. This study proposes a hybrid deep learning framework combining Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) networks to enhance univariate palm oil price forecasting. The key contribution lies in integrating LSTM’s long-term memory capability with GRU’s computational efficiency to capture multi-scale temporal patterns within a unified architecture..........

Key Word: Palm oil price forecasting, LSTM, GRU, hybrid deep learning, time-series prediction, commodity markets, artificial intelligence.

[1]. Ahmad, M. I., Maynard, D. R., & Mckee, M. (2021). Forecasting Palm Oil Price Volatility Using Hybrid Models. Journal Of Commodity Markets, 23, 100164. Https://Doi.Org/10.1016/J.Jcomm.2020.100164
[2]. Cho, K., Van Merriënboer, B., Gulcehre, C., Bahdanau, D., Bougares, F., Schwenk, H., & Bengio, Y. (2014). Learning Phrase Representations Using RNN Encoder–Decoder For Statistical Machine Translation. Proceedings Of EMNLP.
Https://Doi.Org/10.48550/Arxiv.1406.1078
[3]. Fischer, T., & Krauss, C. (2018). Deep Learning With Long Short-Term Memory Networks For Financial Market Predictions. European Journal Of Operational Research, 270(2), 654–669. Https://Doi.Org/10.1016/J.Ejor.2017.11.054
[4]. Gers, F. A., Schmidhuber, J., & Cummins, F. (2000). Learning To Forget: Continual Prediction With LSTM. Neural Computation, 12(10), 2451–2471. Https://Doi.Org/10.1162/089976600300015015
[5]. Gopal, K., & Jha, G. K. (2019). Time-Series Forecasting Of Agricultural Prices Using Machine Learning Techniques. Agricultural Economics Research Review, 32(2), 139–147. Https://Doi.Org/10.5958/0974-0279.2019.00029.3

Abstract: Conventional security models are becoming insufficient to address the evolution happening in cybersecurity threats following cyberattacks on critical infrastructure, which continue to escalate in scale and complexity. This paper presents an integrated exploration of AI-driven cybersecurity strategies, with a particular focus on Microsoft's Azure security ecosystem, including Sentinel, Defender, and Entra ID, as practical tools for enhancing situational awareness, reducing response time, and automating threat mitigation across sectors. Drawing on current threat..........

Key Word: AI-Driven Cybersecurity, Azure Sentinel, Zero Trust Architecture, Critical Infrastructure Protection, Microsoft Defender, Entra ID, Behavioral Analytics, SOAR, Ransomware Containment, Regulatory Compliance, Cloud-Native SIEM, National Security Framework, Cybersecurity Automation, Identity Protection, Predictive Threat Detection

[1]. Akinade, Afees & Ige, Adebimpe & Pub, Anfo. (2024). Cloud Security Challenges And Solutions: A Review Of Current Best Practices. International Journal Of Multidisciplinary Research And Growth Evaluation. 06. 26-35. 10.54660/.IJMRGE.2025.6.1.26-35.
[2]. Alamu, Rapheal. (2025). AI-Driven Anomaly Detection: Strengthening Data Security And Quality In Large Databases. AI Applications.
Https://Www.Researchgate.Net/Publication/389429725_AI-Driven_Anomaly_Detection_Strengthening_Data_Security_And_Quality_In_Large_Databases
[3]. Ali, Nadir & Jack, William. (2022). Reinforcement Learning For Adaptive Cybersecurity: A Self- Learning Approach To Threat Mitigation. 10.13140/RG.2.2.28644.28804.
[4]. Amdaris. (2021). A Total View Of Security With Microsoft Azure Sentinel. Retrieved July 2, 2025, From [Amdaris]
Https://Amdaris.Com/A-Total-View-Of-Security-With-Microsoft-Azure-Sentinel
[5]. Andrés Pereira, Nikolai Ivanov, Zhihao Wang. (2025). Real-Time AI-Based Threat Intelligence For Cloud Security Enhancement. Innovative: International Multi-Disciplinary Journal Of Applied Technology (ISSN 2995-486X) VOLUME 03 ISSUE 3
[6]. Areo, Gideon. (2024). The Future Of Cybersecurity For Critical Infrastructure: Emerging Trends And Key Challenges

Abstract: As enterprises migrate to cloud-native infrastructures and adopt hybrid work models, traditional perimeter-based security models have proven insufficient in protecting sensitive workloads and identities. This article examines the strategic implementation of Zero Trust Architecture (ZTA) within the Microsoft 365 ecosystem, emphasizing its alignment with modern security frameworks such as NIST SP 800-207 and CISA’s Zero Trust Maturity Model (ZTMM). It introduces a structured four-phase maturity model assessment, baseline definition, pilot implementation..........

Key Word: Zero Trust Architecture (ZTA), Microsoft 365 Security, Entra ID, Conditional Access, Identity-Centric Access Control, NIST SP 800-207, CISA ZTMM, Privileged Identity Management (PIM), Compliance and Governance, Continuous Monitoring, Cloud Security, Zero Trust Maturity Model, Zero Trust Edge (ZTE), AI-driven Security, Cyber Resilience

[1]. Adeniyi, Emmanuel & Ogundokun, Roseline & Misra, Sanjay & Bamidele, Awotunde & Abiodun, Moses. (2022). Enhanced Security And Privacy Issues In The Multi-Tenant Environment Of Green Computing Using Blockchain Technology. 10.1007/978-3-030-89546-4_4.
[2]. Akinade, Afees & Ige, Adebimpe & Pub, Anfo. (2024). Cloud Security Challenges And Solutions: A Review Of Current Best Practices. International Journal Of Multidisciplinary Research And Growth Evaluation. 06. 26-35. 10.54660/.IJMRGE.2025.6.1.26-35.
[3]. Aslam, Muhammad. (2020). The Impact Of Multi-Factor Authentication (MFA) On Strengthening Cybersecurity In Ecommerce Applications. 10.13140/RG.2.2.15628.94083.
[4]. Bhagat, Nikhil. (2023). Cybersecurity In A Remote Work Era: Strategies For Securing Distributed Workforces. Journal Of Mathematical & Computer Applications. 1-5. 10.47363/JMCA/2023(2)E137.
[5]. Cybersecurity And Infrastructure Security Agency. (2023). Multifactor Authentication. Retrieved July 13, 2025, From CISA
Https://Www.Cisa.Gov/Topics/Cybersecurity-Best-Practices/Multifactor-Authentication

Abstract: The global rise in Alzheimer’s disease and dementia presents a critical challenge for healthcare systems, placing an immense burden on caregivers to ensure patient safety and sus- tain cognitive function. While assistive technologies exist, current solutions often remain fragmented offering either passive track- ing or static screen..........

Key Word: Alzheimer’s Disease, Object Detection, Scav- enger Hunt, TensorFlow.js, Geofencing, Reminiscence Therapy, Assistive Technology.

...

Abstract: Medicinal plant knowledge has evolved from orally transmitted ethnobotanical traditions to globally accessible digital repositories. This review traces that transition by examining prominent medicinal plant databases from around the world, alongside key Indian initiatives rooted in Ayurveda and regional biodiversity. It compares their structure, attributes, coverage, and usability, identifying strengths in taxonomy and phytochemistry but major gaps in Ayurvedic descriptors, toxicity data, and AI-readiness. While international databases emphasize molecular and.....

Key Word: Medicinal plant databases, Structured datasets, Ayurveda, Ethnobotany, Herbal informatics, Machine learning, Digital health

[1]. Ravishankar B, Shukla VJ. Indian Systems Of Medicine: A Brief Profile. African Journal Of Traditional, Complementary And Alternative Medicines. 2007;4(3):319-37.
[2]. Shaikh S, Chavan VA. An Extensive Investigation On Medicinal Plants In The Context Of Machine Learning. Journal Of Emerging Technologies And Innovative Research 12(7), C666–C675 (2025). DOI:10.56975/Jetir.V12i7.566211. Available From: Https://Doi.Org/10.56975/Jetir.V12i7.566211 (Accessed 2025/11/26).
[3]. Kalita I, Bhattacharjee S, Saharia M. Advancements In Medicinal Plant Research: Harnessing Artificial Intelligence, Machine Learning, Deep Learning, And Bioinformatics. In: Biotechnology, Multiple Omics, And Precision Breeding In Medicinal Plants. Boca Raton: CRC Press; 2025. P. 135-45.
[4]. Magare DA, Patil MB. Ethnobotany In The Digital Age: Opportunities And Challenges Of Traditional Knowledge Digitization. World Journal Of Biological, Pharmaceutical And Health Sciences. 2025;21:235-42.
[5]. Chad F. Semantic Interoperability In Heterogeneous Data Integration. 2025. Available From:
Https://Www.Researchgate.Net/Publication/390371039_Semantic_Interoperability_In_Heterogeneous_Data_Integration (Accessed 2025/11/26).

Abstract: The blockchain technology has become a prospective propensity to remedy prevailing levels of trust lacking in systems of health care, where challenges include an undue data dungeons, privacy breaches and extortions that are compromising patient safety and operational performance. The paper considers blockchain-based mechanisms to achieve trust in the system of a decentralized ledger that will provide integrity and protection through the presentation of the data to interested parties. Tracing an overview of the literature review and the analysis of the case study of already implemented technologies.....

Key Word: Blockchain, consensus, decentralized, healthcare, ledger.

[1] N. Nezhadsistani, N. S. Moayedian And B. Stiller, "Blockchain- Enabled Federated Learning In Healthcare: Survey And State-Of-The- Art," In Ieee Access, Vol. 13, Pp. 119922-119945, 2025, Doi: 10.1109/Access.2025.3587345. [2]
S. Bharath Babu And K. R. Jothi, "A Secure Framework For Privacy- Preserving Analytics In Healthcare Records Using Zero-Knowledge Proofs And Blockchain In Multi-Tenant Cloud Environments," In Ieee Access, Vol. 13, Pp. 8439-8455, 2025, Doi: 10.1109/Access.2024.3509457. [3]
K. Tlemçani, K. Azbeg, E. Saoudi, L. Fetjah, O. Ouchetto And S. Jai Andaloussi, "Empowering Diabetes Management Through Blockchain And Edge Computing: A Systematic Review Of Healthcare Innovations And Challenges," In Ieee Access, Vol. 13, Pp. 14426-14443, 2025, Doi: 10.1109/Access.2025.3531350. [4]
A. M. Kanthe, V. Shelake And A. Amburle, "Guardian Shield: Safeguarding Patient Data Integrity In Healthcare Systems," In Journal Of Mobile Multimedia, Vol. 21, No. 3-4, Pp. 491-504, July 2025, Doi: 10.13052/Jmm1550-4646.21349.

Abstract: The rapid diffusion of digital technologies across developing countries has fundamentally reshaped economic activity, governance, education, and social interaction. While Information and Communication Technologies (ICTs) have generated significant development gains, their expanding environmental footprint has become increasingly visible through rising energy consumption, greenhouse gas emissions, and escalating volumes of electronic waste. Green Information and Communication Technology (Green ICT) has emerged as a strategic response.....

Key Word: Green ICT, developing countries, sustainability, environmental awareness, digital literacy, ICT policy, e-waste and technology adoption

[1]. Alhassan, A., & Boateng, R. (2022). Institutional Determinants Of Green ICT Adoption In Sub-Saharan Africa. Information Technology For Development, 28(4), 621–642. Https://Doi.Org/10.1080/02681102.2022.2043210
[2]. Balde, C. P., Kuehr, R., & Forti, V. (2024). The Global E-Waste Monitor 2024: Quantities, Flows And The Circular Economy Potential (4th Ed.). United Nations University, ITU, UNITAR. Https://Ewastemonitor.Info/The-Global-E-Waste-Monitor-2024/
[3]. Hilty, L. M., & Aebischer, B. (Eds.). (2021). ICT Innovations For Sustainability (2nd Ed.). Springer. (Updated Edition Referencing Green ICT Frameworks And Sustainability Metrics.)
[4]. ITU. (2022). Measuring Digital Sustainability: ITU Guidance And Indicators. International Telecommunication Union.
Https://Www.Itu.Int
[5]. Kumar, S., & Singh, R. (2023). Financing Sustainable ICT Transitions In Developing Countries: Challenges And Mechanisms. World Development Perspectives, 30, 100407. Https://Doi.Org/10.1016/J.Wdp.2023.100407.

Abstract: This research paper presents a comprehensive comparative study of two widely used conversational AI systems—ChatGPT and Perplexity AI. These tools have rapidly emerged as essential digital assistants for academic research, professional tasks, and day-to-day learning. While ChatGPT, developed by OpenAI, is primarily a generative language model that excels in reasoning, creativity, and multi-turn conversation, Perplexity.....

Key Word: ChatGPT, Perplexity AI, Retrieval-Augmented Generation (RAG), Accuracy, Hallucination, Citations, Artificial Intelligence

[1]. Á. Cabezas-Clavijo And P. Sidorenko-Bautista, “Assessing The Performance Of 8 Ai Chatbots In Bibliographic Reference Retrieval: Grok And Deepseek Outperform Chatgpt, But None Are Fully Accurate,” Arxiv Preprint, Arxiv:2505.18059, 2025.
Doi: Https://Doi.Org/10.48550/Arxiv.2505.18059
Source: Https://Arxiv.Org/Abs/2505.18059
[2]. Y. Bang Et Al., “A Multitask, Multilingual, Multimodal Evaluation Of Chatgpt On Reasoning, Hallucination, And Interactivity,” Proc. Ijcnlp–Aacl 2023, Pp. 675–718.
Doi: Https://Doi.Org/10.18653/V1/2023.Ijcnlp-Main.45
Source: Https://Aclanthology.Org/2023.Ijcnlp-Main.45
[3]. X. Wang, S. Li, And H. Zhao, “Survey On Factuality In Large Language Models,” Information Fusion, Vol. 110, 105120, 2024.
Doi: Https://Doi.Org/10.1016/J.Inffus.2024.105120
Source: Https://Www.Sciencedirect.Com/Science/Article/Pii/S1566253524000303
[4]. P. Lewis Et Al., “Retrieval-Augmented Generation For Knowledge-Intensive Nlp Tasks,” Neurips, 2020.
Doi: Https://Doi.Org/10.5555/3495724.3496517
Source: Https://Papers.Nips.Cc/Paper/2020/Hash/6b493230205f780e1bc26945df7481e5-Abstract.Html
[5]. J. Wei Et Al., “Chain-Of-Thought Prompting Elicits Reasoning In Large Language Models,” Neurips 2022.
Doi: Https://Doi.Org/10.5555/3600270.3602070
Source: Https://Arxiv.Org/Abs/2201.11903.

Abstract: This review article analyzes the significant role of deep learning in the automated classification and detection of potato leaf diseases as it prominently threatens global agricultural production. The traditional approaches to identify disease typically rely on manual inspection processes that are labor-intensive, time-consuming, prone to human-induced error, leading to variability and producing inconsistent outcomes. In contrast, the deep learning framework....

Key Word: Potato Leaf Disease Detection, Deep Learning, Convolutional Neural Network (CNNs), Image Classification, Agricultural Automation

[1]. I. Attri, L. K. Awasthi And . T. . P. Sharma, “Machine Learning In Agriculture: A Review Of Crop Management Applications,” Multimedia Tools And Applications, Vol. 83, P. 12875–12915, 2023.
[2]. M. E. Çalişkan, A. Bakhsh And K. Jabran, Potato Production Worldwide, Academic Press, 2023.
[3]. P. Andal And M. Thangaraj , “Comprehensive Review Of Methods For Leaf Disease Identification,” Discover Artificial Intelligence, Vol. 5, 2025.
[4]. M. S. Hylmi, W. And E. Suryani, “Detection Of Potato Leaf Disease Using Multi-Class Support Vector Machine Based On Texture, Color, And Shape Features,” International Conference On Electrical And Information Technology (Ieit), Pp. 20-24, 2022..

Abstract: Background: Next-generation wireless networks need ultra-low latency and high reliability, which can only be achieved by real-time bit error rate (BER) prediction in the next generation of wireless systems based on OFDM. Conventional methods reduce multi-dimensional channel states to scalars and lose information, and thus perform sub-optimally over dynamic conditions. In this paper, there is a proposal of a new online ensemble model that integrates Adaptive Random Forests (ARF) and Online Support Vector Regression (OSVR) to streamline the....

Key Word:OFDM systems, bit error rate prediction, online ensemble learning, adaptive random forests, support vector regression, concept drift, wireless communications, machine learning

[1] Abdullahi, M., Cao, A., Zafar, A., Xiao, P., & Hemadeh, I. A. (2020). A Generalized Bit Error Rate Evaluation For Index Modulation Based OFDM System. IEEE Access, 8, 70082-70094.
[2] Ay, F., Althunibat, S., Qaraqe, K. A., & Kurban, H. (2024). A Noise-Adaptive Machine Learning Framework For Optimizing User Grouping In Dynamic IM-OFDMA Systems. IEEE Transactions On Communications, 73(3), 1862-1878.
[3] Bai, Y., Zhao, Y., Liu, C., Xu, F., & Liu, G. (2024, April). Resnet Based Multi-Target Range And Velocity Estimation Method For Millimeter-Wave OFDM System. In 2024 IEEE Wireless Communications And Networking Conference (WCNC) (Pp. 1-6). IEEE.
[4] Domínguez-Bolaño, T., Rodríguez-Piñeiro, J., García-Naya, J. A., & Castedo, L. (2020). Bit Error Probability And Capacity Bound Of OFDM Systems In Deterministic Doubly-Selective Channels. IEEE Transactions On Vehicular Technology, 69(10), 11458-11469.
[5] Essai Ali, M. H., Abdellah, A. R., Atallah, H. A., Ahmed, G. S., Muthanna, A., & Koucheryavy, A. (2023). Deep Learning Peephole LSTM Neural Network-Based Channel State Estimators For OFDM 5G And Beyond Networks. Mathematics, 11(15), 3386..